diff --git a/.github/workflows/publish.yml b/.github/workflows/publish.yml index 396e2b8..23b23bd 100644 --- a/.github/workflows/publish.yml +++ b/.github/workflows/publish.yml @@ -12,9 +12,9 @@ jobs: python-version: ["3.10", "3.11", "3.12", "3.13", "3.14"] os: [ubuntu-latest, windows-latest, macos-latest] steps: - - uses: actions/checkout@v4 + - uses: actions/checkout@v7 - name: Set up Python ${{ matrix.python-version }} - uses: actions/setup-python@v5 + uses: actions/setup-python@v6 with: python-version: ${{ matrix.python-version }} cache: pip @@ -29,9 +29,9 @@ jobs: runs-on: ubuntu-latest needs: [test] steps: - - uses: actions/checkout@v4 + - uses: actions/checkout@v7 - name: Set up Python - uses: actions/setup-python@v5 + uses: actions/setup-python@v6 with: python-version: '3.14' cache: pip diff --git a/.github/workflows/test-coverage.yml b/.github/workflows/test-coverage.yml index 1f55f4e..7668f1b 100644 --- a/.github/workflows/test-coverage.yml +++ b/.github/workflows/test-coverage.yml @@ -12,9 +12,9 @@ jobs: runs-on: ubuntu-latest steps: - name: Check out repo - uses: actions/checkout@v4 + uses: actions/checkout@v7 - name: Set up Python - uses: actions/setup-python@v5 + uses: actions/setup-python@v6 with: python-version: "3.11" cache: pip diff --git a/.github/workflows/test.yml b/.github/workflows/test.yml index d85cbf8..5924fd8 100644 --- a/.github/workflows/test.yml +++ b/.github/workflows/test.yml @@ -14,9 +14,9 @@ jobs: numpy: [0, 1] os: [ubuntu-latest, macos-latest, windows-latest, macos-14] steps: - - uses: actions/checkout@v4 + - uses: actions/checkout@v7 - name: Set up Python ${{ matrix.python-version }} - uses: actions/setup-python@v5 + uses: actions/setup-python@v6 with: python-version: ${{ matrix.python-version }} allow-prereleases: true @@ -43,6 +43,9 @@ jobs: run: pytest --sqlite-autocommit - name: run mypy run: mypy sqlite_utils tests + - name: run pyright regression checks + if: matrix.os == 'ubuntu-latest' && matrix.python-version == '3.14' + run: pyright sqlite_utils tests - name: run flake8 run: flake8 - name: run ty @@ -50,6 +53,11 @@ jobs: run: | pip install uv uv run ty check sqlite_utils + - name: Check no accidental dev= dependencies needed + if: matrix.os == 'ubuntu-latest' + run: | + pip install uv + uv run --no-default-groups sqlite-utils --help - name: Check formatting run: black . --check - name: Check if cog needs to be run diff --git a/.gitignore b/.gitignore index 6743708..5b5d2c6 100644 --- a/.gitignore +++ b/.gitignore @@ -15,6 +15,7 @@ venv .schema .vscode .hypothesis +.claude/ Pipfile Pipfile.lock uv.lock diff --git a/Justfile b/Justfile index 5caa120..7347534 100644 --- a/Justfile +++ b/Justfile @@ -2,20 +2,25 @@ @default: test lint # Run pytest with supplied options -@test *options: +@test *options: test-no-dev-dependencies uv run pytest {{options}} +@test-no-dev-dependencies: + uv run --isolated --no-default-groups sqlite-utils --help > /dev/null + @run *options: uv run -- {{options}} -# Run linters: black, flake8, mypy, ty, cog +# Run linters: black, flake8, mypy, pyright, ty, cog @lint: just run black . --check uv run flake8 uv run mypy sqlite_utils tests + uv run pyright sqlite_utils tests uv run ty check sqlite_utils uv run cog --check README.md docs/*.rst uv run --group docs codespell docs/*.rst --ignore-words docs/codespell-ignore-words.txt + uv run --group docs codespell sqlite_utils --ignore-words docs/codespell-ignore-words.txt # Rebuild docs with cog @cog: diff --git a/docs/changelog.rst b/docs/changelog.rst index 0943dca..5d024e1 100644 --- a/docs/changelog.rst +++ b/docs/changelog.rst @@ -4,6 +4,99 @@ Changelog =========== +.. _v4_2_1: + +4.2.1 (2026-08-13) +------------------ + +- Fix for ``No module named 'typing_extensions'`` crashing bug accidentally shipped in version 4.2. (:issue:`842`) + +.. _v4_2: + +4.2 (2026-08-13) +---------------- + +- New ``table.checks``, ``table.column_checks`` and ``table.table_checks`` introspection properties expose column-level and table-level ``CHECK`` constraints. (:issue:`834`) +- New ``sqlite_utils.ANY`` marker type for creating and introspecting SQLite ``ANY`` columns. The Python API and CLI can create, add and transform these columns, and ``table.transform()`` and ``table.extract()`` now preserve ``ANY`` columns and their values in ``STRICT`` tables. (:issue:`790`) +- ``table.default_values`` now unescapes doubled single quotes in string defaults, so a default such as ``'O''Brien'`` is returned as ``"O'Brien"``. Thanks, `ikatyal2110 `__. (`#811 `__) +- ``table.default_values`` now decodes unquoted ``TRUE``, ``FALSE`` and ``NULL`` default literals as ``True``, ``False`` and ``None`` respectively. (:issue:`836`) +- ``table.enable_fts(..., tokenize=...)`` and ``sqlite-utils enable-fts --tokenize`` now safely quote the tokenizer argument, preventing a crafted value from injecting additional SQL. Thanks, `Bunlong Heng `__. (`#828 `__) +- ``rows_where()``, ``pks_and_rows_where()``, ``search()`` and ``search_sql()`` now support ``offset=`` without requiring ``limit=``. The ``sqlite-utils rows --offset`` option now works without ``--limit`` too. Thanks, `ethanhawkes-gif `__. (:issue:`816`, `#821 `__) +- Empty or whitespace-only input passed to ``rows_from_file()`` is now handled as an empty CSV file instead of raising ``csv.Error``. Thanks, `Rami Abdelrazzaq `__. (:issue:`808`, `#837 `__) +- ``sqlite-utils convert --dry-run`` now works for table and column names containing closing square brackets. (:issue:`829`) +- ``table.indexes`` and ``table.xindexes`` now work for table, index and column names containing double quotes. This also fixes ``table.transform()`` for tables with those identifiers. Thanks, `nyxst4ck `__. (:issue:`824`, `#825 `__) +- Improved type annotations throughout the package and added Pyright regression checks to CI. (:issue:`833`) +- Changing a ``TEXT`` column to ``INTEGER``, ``FLOAT`` or ``REAL`` using ``table.transform()`` or ``sqlite-utils transform`` now converts exact empty strings to ``NULL``. Previously they remained empty strings in the numeric column. Thanks, `ikatyal2110 `__. (:issue:`488`, `#805 `__) + +``table.transform()`` can handle many more edge-cases: + +- ``table.transform()`` now preserves column-level and composite ``UNIQUE`` constraints, including constraint names, collations, sort order and ``ON CONFLICT`` behavior. Renaming columns updates those constraints, while dropping any constituent column removes the entire constraint. (:issue:`762`) +- ``table.transform()`` now preserves ``AUTOINCREMENT`` primary keys and their sequence high-water marks. Previously a transform removed ``AUTOINCREMENT`` and could reuse deleted row IDs. (:issue:`602`) +- ``table.transform()`` now preserves ``CHECK`` constraints, including comments within their expressions. Renaming a column rewrites identifier references in checks without changing string literals or function names. Dropping a column drops a check owned by that column, and raises ``TransformError`` if a remaining check depends on it. (:issue:`762`) +- ``table.transform()`` now preserves comments immediately before or after column definitions. These comments move with the column if it is renamed or reordered, and are removed if the column is dropped. (:issue:`762`) +- ``table.transform(rename=...)`` now preserves explicit indexes on renamed columns by dropping and recreating those indexes against the new column names. Previously this raised a ``TransformError``. (:issue:`822`) +- ``table.transform()`` now works for tables that are referenced by views. Previously the ``ALTER TABLE ... RENAME TO`` step raised ``no such table`` if a view referenced the table being transformed. View definitions are left unchanged - see :ref:`python_api_transform_views`. This also fixes a bug where ``transform(keep_table=...)`` silently rewrote dependent views to point at the frozen backup table instead of the live one. (:issue:`831`) + + +.. _v3_39_1: + +3.39.1 (2026-07-25) +------------------- + +- Fixed a bug where ``table.delete_where()`` left the connection in an open transaction, causing deleted rows to be silently restored when the connection was closed. (:issue:`815`) + +.. _v4_1_1: + +4.1.1 (2026-07-12) +------------------ + +- ``table.transform()`` now raises a ``TransactionError`` if called while a transaction is open with ``PRAGMA foreign_keys`` enabled and the table is referenced by foreign keys with destructive ``ON DELETE`` actions - ``CASCADE``, ``SET NULL`` or ``SET DEFAULT``. The pragma cannot be changed inside a transaction, so previously dropping the old table as part of the transform could fire those actions and silently delete or modify referencing rows. See :ref:`python_api_transform_foreign_keys_transactions` for details and workarounds. (:issue:`794`) +- The :ref:`CLI ` and :ref:`Python API ` documentation now cross-reference each other: CLI sections link to the equivalent Python API functionality and Python API sections link back to the corresponding CLI command. (:issue:`791`) + +.. _v4_1: + +4.1 (2026-07-11) +---------------- + +- ``sqlite-utils insert`` and ``sqlite-utils upsert`` now accept a ``--code`` option for :ref:`providing a block of Python code ` (or a path to a ``.py`` file) that defines a ``rows()`` function or ``rows`` iterable of rows to insert, as an alternative to importing from a file. (:issue:`684`) +- ``sqlite-utils insert`` and ``sqlite-utils upsert`` now accept ``--type column-name type`` to :ref:`override the type automatically chosen when the table is created `. This is useful for CSV or TSV columns such as ZIP codes that look like integers but should be stored as ``TEXT`` to preserve leading zeros. (:issue:`131`) +- New ``table.drop_index(name)`` method and ``sqlite-utils drop-index`` command for dropping an index by name. Both accept ``ignore=True``/``--ignore`` to ignore a missing index. (:issue:`626`) +- ``sqlite-utils query`` can now read the SQL query from standard input by passing ``-`` in place of the query, for example ``echo "select * from dogs" | sqlite-utils query dogs.db -``. (:issue:`765`) +- ``sqlite-utils upsert`` can now infer the primary key of an existing table, so ``--pk`` can be omitted when upserting into a table that already has a primary key. +- ``table.transform()`` and ``table.transform_sql()`` now accept ``strict=True`` or ``strict=False`` to change a table's `SQLite strict mode `__. Omitting the option preserves the existing mode. (:issue:`787`) +- The ``sqlite-utils transform`` command now accepts ``--strict`` and ``--no-strict`` to change a table's strict mode. (:issue:`787`) + +.. _v4_0: + +4.0 (2026-07-07) +---------------- + +The 4.0 release includes some minor backwards-incompatible fixes (hence the major version number bump) and introduces three major new features: + +- :ref:`Database migrations `, providing a structured mechanism for evolving a project's schema over time. (:issue:`752`) +- :ref:`Nested transaction support ` via ``db.atomic()``, plus numerous improvements to how transactions work across the library. (:issue:`755`) +- Support for :ref:`compound foreign keys `, including creation, transformation and introspection through :ref:`table.foreign_keys `. (:issue:`594`) + +Other notable changes include: + +- Upserts now use SQLite's ``INSERT ... ON CONFLICT ... DO UPDATE SET`` syntax, detect existing table primary keys automatically and reject records that are missing required primary key values. (:issue:`652`) +- ``db.query()`` now executes immediately and rejects statements that do not return rows; use ``db.execute()`` for writes and DDL. +- CSV and TSV imports now detect column types by default, while inserts into existing tables preserve those tables' column types. (:issue:`679`) +- Foreign key handling now preserves ``ON DELETE``/``ON UPDATE`` actions during transforms and resolves referenced primary keys more accurately. (:issue:`530`) +- Column names passed to Python API methods are now matched case-insensitively, mirroring SQLite's own identifier behavior. (:issue:`760`) +- The command-line tool now emits UTF-8 JSON output by default, with ``--ascii`` available to restore escaped output. (:issue:`625`) +- ``table.extract()`` and ``extracts=`` no longer create lookup table records for all-``null`` values. (:issue:`186`) + +See :ref:`upgrading_3_to_4` for details on backwards-incompatible changes. + +The detailed release notes for the features and fixes shipped during the 4.0 pre-release cycle are available in :ref:`4.0a0 `, :ref:`4.0a1 `, :ref:`4.0rc1 `, :ref:`4.0rc2 `, :ref:`4.0rc3 ` and :ref:`4.0rc4 `. + +Bug fixes since 4.0rc4 +~~~~~~~~~~~~~~~~~~~~~~ + +- Fixed 4.0 regressions in ``insert``/``upsert`` against tables that use SQLite's implicit ``rowid`` primary key. Passing ``pk="rowid"``, ``pk="_rowid_"`` or ``pk="oid"`` now works again for rowid tables, and ``last_pk`` is set correctly. (:issue:`781`) +- Fixed ``insert(..., ignore=True)`` and ``insert_all(..., ignore=True)`` so an ignored insert that conflicts with an existing primary key row now reports that existing row in ``last_rowid`` and ``last_pk`` where possible. This also works for compound primary keys and list-mode inserts. (:issue:`783`) + .. _v4_0rc4: 4.0rc4 (2026-07-06) diff --git a/docs/cli-reference.rst b/docs/cli-reference.rst index 49eba52..c53d642 100644 --- a/docs/cli-reference.rst +++ b/docs/cli-reference.rst @@ -19,7 +19,7 @@ This page lists the ``--help`` for every ``sqlite-utils`` CLI sub-command. go_first = [ "query", "memory", "insert", "upsert", "bulk", "search", "transform", "extract", "schema", "insert-files", "analyze-tables", "convert", "tables", "views", "rows", - "triggers", "indexes", "create-database", "create-table", "create-index", + "triggers", "indexes", "create-database", "create-table", "create-index", "drop-index", "migrate", "enable-fts", "populate-fts", "rebuild-fts", "disable-fts" ] refs = { @@ -46,6 +46,7 @@ This page lists the ``--help`` for every ``sqlite-utils`` CLI sub-command. "add-foreign-keys": "cli_add_foreign_keys", "index-foreign-keys": "cli_index_foreign_keys", "create-index": "cli_create_index", + "drop-index": "cli_drop_index", "enable-wal": "cli_wal", "enable-counts": "cli_enable_counts", "bulk": "cli_bulk", @@ -109,6 +110,10 @@ See :ref:`cli_query`. "select * from chickens where age > :age" \ -p age 1 + Pass "-" as the SQL to read the query from standard input: + + echo "select * from chickens" | sqlite-utils data.db - + Options: --attach ... Additional databases to attach - specify alias and filepath @@ -134,8 +139,8 @@ See :ref:`cli_query`. -r, --raw Raw output, first column of first row --raw-lines Raw output, first column of each row -p, --param ... Named :parameters for SQL query - --functions TEXT Python code or file path defining custom SQL - functions + --functions TEXT Python code or a file path defining custom SQL + functions; can be used multiple times --load-extension TEXT Path to SQLite extension, with optional :entrypoint -h, --help Show this message and exit. @@ -177,8 +182,8 @@ See :ref:`cli_memory`. sqlite-utils memory animals.csv --schema Options: - --functions TEXT Python code or file path defining custom SQL - functions + --functions TEXT Python code or a file path defining custom SQL + functions; can be used multiple times --attach ... Additional databases to attach - specify alias and filepath --flatten Flatten nested JSON objects, so {"foo": {"bar": @@ -226,7 +231,7 @@ See :ref:`cli_inserting_data`, :ref:`cli_insert_csv_tsv`, :ref:`cli_insert_unstr :: - Usage: sqlite-utils insert [OPTIONS] PATH TABLE FILE + Usage: sqlite-utils insert [OPTIONS] PATH TABLE [FILE] Insert records from FILE into a table, creating the table if it does not already exist. @@ -242,6 +247,9 @@ See :ref:`cli_inserting_data`, :ref:`cli_insert_csv_tsv`, :ref:`cli_insert_unstr - Use --lines to write each incoming line to a column called "line" - Use --text to write the entire input to a column called "text" + Use --type column-name type to override the type automatically chosen when the + table is created. + You can also use --convert to pass a fragment of Python code that will be used to convert each input. @@ -268,8 +276,20 @@ See :ref:`cli_inserting_data`, :ref:`cli_insert_csv_tsv`, :ref:`cli_insert_unstr echo 'A bunch of words' | sqlite-utils insert words.db words - \ --text --convert '({"word": w} for w in text.split())' + Instead of a FILE you can use --code to provide a block of Python code that + defines the rows to insert, as either a rows() function that yields + dictionaries or a "rows" iterable. --code can also be a path to a .py file: + + sqlite-utils insert data.db creatures --code ' + def rows(): + yield {"id": 1, "name": "Cleo"} + yield {"id": 2, "name": "Suna"} + ' --pk id + Options: --pk TEXT Columns to use as the primary key, e.g. id + --code TEXT Python code defining a rows() function or iterable + of rows to insert --flatten Flatten nested JSON objects, so {"a": {"b": 1}} becomes {"a_b": 1} --nl Expect newline-delimited JSON @@ -290,6 +310,7 @@ See :ref:`cli_inserting_data`, :ref:`cli_insert_csv_tsv`, :ref:`cli_insert_unstr --alter Alter existing table to add any missing columns --not-null TEXT Columns that should be created as NOT NULL --default ... Default value that should be set for a column + --type ... Column types to use when creating the table --no-detect-types Treat all CSV/TSV columns as TEXT --analyze Run ANALYZE at the end of this operation --load-extension TEXT Path to SQLite extension, with optional :entrypoint @@ -311,12 +332,17 @@ See :ref:`cli_upsert`. :: - Usage: sqlite-utils upsert [OPTIONS] PATH TABLE FILE + Usage: sqlite-utils upsert [OPTIONS] PATH TABLE [FILE] Upsert records based on their primary key. Works like 'insert' but if an incoming record has a primary key that matches an existing record the existing record will be updated. + If the table already exists and has a primary key, --pk can be omitted. + + Use --type column-name type to override the type automatically chosen when the + table is created. + Example: echo '[ @@ -326,7 +352,8 @@ See :ref:`cli_upsert`. Options: --pk TEXT Columns to use as the primary key, e.g. id - [required] + --code TEXT Python code defining a rows() function or iterable + of rows to insert --flatten Flatten nested JSON objects, so {"a": {"b": 1}} becomes {"a_b": 1} --nl Expect newline-delimited JSON @@ -347,6 +374,7 @@ See :ref:`cli_upsert`. --alter Alter existing table to add any missing columns --not-null TEXT Columns that should be created as NOT NULL --default ... Default value that should be set for a column + --type ... Column types to use when creating the table --no-detect-types Treat all CSV/TSV columns as TEXT --analyze Run ANALYZE at the end of this operation --load-extension TEXT Path to SQLite extension, with optional :entrypoint @@ -379,7 +407,8 @@ See :ref:`cli_bulk`. Options: --batch-size INTEGER Commit every X records - --functions TEXT Python code or file path defining custom SQL functions + --functions TEXT Python code or a file path defining custom SQL + functions; can be used multiple times --flatten Flatten nested JSON objects, so {"a": {"b": 1}} becomes {"a_b": 1} --nl Expect newline-delimited JSON @@ -465,7 +494,7 @@ See :ref:`cli_transform_table`. Options: --type ... Change column type to INTEGER, TEXT, FLOAT, - REAL or BLOB + REAL, BLOB or ANY --drop TEXT Drop this column --rename ... Rename this column to X -o, --column-order TEXT Reorder columns @@ -479,6 +508,8 @@ See :ref:`cli_transform_table`. Add a foreign key constraint from a column to another table with another column --drop-foreign-key TEXT Drop foreign key constraint for this column + --strict / --no-strict Enable or disable STRICT mode (default: + preserve current mode) --sql Output SQL without executing it --load-extension TEXT Path to SQLite extension, with optional :entrypoint @@ -616,6 +647,11 @@ See :ref:`cli_convert`. "value" is a variable with the column value to be converted. + CODE can also be a reference to a callable that takes the value, for example: + + sqlite-utils convert my.db mytable date r.parsedate + sqlite-utils convert my.db mytable data json.loads --import json + Use "-" for CODE to read Python code from standard input. The following common operations are available as recipe functions: @@ -626,20 +662,18 @@ See :ref:`cli_convert`. Convert a string like a,b,c into a JSON array ["a", "b", "c"] r.parsedate(value: 'str', dayfirst: 'bool' = False, yearfirst: 'bool' = False, - errors: 'Optional[object]' = None) -> 'Optional[str]' + errors: 'object | None' = None) -> 'str | None' Parse a date and convert it to ISO date format: yyyy-mm-dd - - dayfirst=True: treat xx as the day in xx/yy/zz - yearfirst=True: treat xx as the year in xx/yy/zz - errors=r.IGNORE to ignore values that cannot be parsed - errors=r.SET_NULL to set values that cannot be parsed to null r.parsedatetime(value: 'str', dayfirst: 'bool' = False, yearfirst: 'bool' = - False, errors: 'Optional[object]' = None) -> 'Optional[str]' + False, errors: 'object | None' = None) -> 'str | None' Parse a datetime and convert it to ISO datetime format: yyyy-mm-ddTHH:MM:SS - - dayfirst=True: treat xx as the day in xx/yy/zz - yearfirst=True: treat xx as the year in xx/yy/zz - errors=r.IGNORE to ignore values that cannot be parsed @@ -926,10 +960,10 @@ See :ref:`cli_create_table`. sqlite-utils create-table my.db people \ id integer \ name text \ - height float \ + height real \ photo blob --pk id - Valid column types are text, integer, float and blob. + Valid column types are text, integer, real, float, blob and any. Options: --pk TEXT Column to use as primary key @@ -975,6 +1009,29 @@ See :ref:`cli_create_index`. -h, --help Show this message and exit. +.. _cli_ref_drop_index: + +drop-index +========== + +See :ref:`cli_drop_index`. + +:: + + Usage: sqlite-utils drop-index [OPTIONS] PATH TABLE INDEX + + Drop an index by index name from the specified table + + Example: + + sqlite-utils drop-index chickens.db chickens idx_chickens_name + + Options: + --ignore Ignore if index does not exist + --load-extension TEXT Path to SQLite extension, with optional :entrypoint + -h, --help Show this message and exit. + + .. _cli_ref_migrate: migrate @@ -1024,7 +1081,7 @@ See :ref:`cli_fts`. Usage: sqlite-utils enable-fts [OPTIONS] PATH TABLE COLUMN... - Enable full-text search for specific table and columns" + Enable full-text search for specific table and columns Example: @@ -1200,7 +1257,7 @@ See :ref:`cli_add_column`. :: Usage: sqlite-utils add-column [OPTIONS] PATH TABLE COL_NAME - [integer|int|float|real|text|str|blob|bytes] + [integer|int|float|real|text|str|blob|bytes|any] Add a column to the specified table diff --git a/docs/cli.rst b/docs/cli.rst index 063e80f..78c33b8 100644 --- a/docs/cli.rst +++ b/docs/cli.rst @@ -29,6 +29,16 @@ The ``sqlite-utils query`` command lets you run queries directly against a SQLit .. note:: In Python: :ref:`db.query() ` CLI reference: :ref:`sqlite-utils query ` +Pass ``-`` as the SQL query to read the query from standard input. This is useful for longer queries that would otherwise require careful shell escaping, or for piping in SQL generated by another tool: + +.. code-block:: bash + + echo "select * from dogs" | sqlite-utils query dogs.db - + +.. code-block:: bash + + sqlite-utils query dogs.db - < query.sql + .. _cli_query_json: Returning JSON @@ -351,7 +361,7 @@ To return the first column of each result as raw data, separated by newlines, us Using named parameters ---------------------- -You can pass named parameters to the query using ``-p``: +You can pass named parameters to the query using ``-p name value``: .. code-block:: bash @@ -414,6 +424,9 @@ The ``--functions`` option can be used multiple times to load functions from mul from urllib.parse import urlparse return urlparse(url).path' +.. note:: + In Python: :ref:`db.register_function() ` + .. _cli_query_extensions: SQLite extensions @@ -1014,6 +1027,9 @@ To show more than 10 common values, use ``--common-limit 20``. To skip the most sqlite-utils analyze-tables github.db tags --common-limit 20 --no-least +.. note:: + In Python: :ref:`table.analyze_column() ` CLI reference: :ref:`sqlite-utils analyze-tables ` + .. _cli_analyze_tables_save: Saving the analyzed table details @@ -1181,6 +1197,9 @@ You can delete all the existing rows in the table before inserting the new recor You can add the ``--analyze`` option to run ``ANALYZE`` against the table after the rows have been inserted. +.. note:: + In Python: :ref:`table.insert_all() ` CLI reference: :ref:`sqlite-utils insert ` + .. _cli_inserting_data_binary: Inserting binary data @@ -1356,6 +1375,32 @@ Will produce this schema with automatically detected types: "weight" REAL ); +.. _cli_insert_csv_tsv_column_types: + +Overriding column types +----------------------- + +Use ``--type column-name type`` to override the type automatically chosen when the table is created. This option can be used more than once, and works with both ``insert`` and ``upsert``: + +.. code-block:: bash + + sqlite-utils insert places.db places places.csv --csv \ + --type zipcode text \ + --type score real + +This is useful for values such as ZIP codes, which may look like integers but should be stored as ``TEXT`` to preserve leading zeros. + +The column type should be one of ``TEXT``, ``INTEGER``, ``FLOAT``, ``REAL``, ``BLOB`` or ``ANY``. Column types are matched case-insensitively. + +``ANY`` is especially useful with ``--strict``. An ``ANY`` column in a strict table preserves values without coercion, so text such as ``000123`` remains text instead of being converted to an integer: + +.. code-block:: bash + + sqlite-utils insert events.db events events.csv --csv --strict \ + --type payload any + +As with detected column types, ``--type`` only affects tables created by the command. If the table already exists, its existing column types are left unchanged. + To disable type detection and treat all columns as TEXT, use ``--no-detect-types``: .. code-block:: bash @@ -1551,6 +1596,27 @@ The result looks like this: COMMIT; +.. _cli_insert_code: + +Inserting rows generated by Python code +======================================= + +Instead of providing a ``FILE`` to import, you can use the ``--code`` option to pass a block of Python code that generates the rows to insert. This is the command-line equivalent of calling ``db["creatures"].insert_all(rows())`` from the :ref:`Python API `. + +Your code should define either a ``rows()`` function that returns or yields dictionaries, or a ``rows`` iterable such as a list of dictionaries: + +.. code-block:: bash + + sqlite-utils insert data.db creatures --code ' + def rows(): + yield {"id": 1, "name": "Cleo"} + yield {"id": 2, "name": "Suna"} + ' --pk id + +``--code`` can also be given a path to a Python ``.py`` file. + +The ``--code`` option works with both ``sqlite-utils insert`` and ``sqlite-utils upsert``, and composes with table options such as ``--pk``, ``--replace``, ``--alter``, ``--not-null`` and ``--default``. It cannot be combined with a ``FILE`` argument or with input format options such as ``--csv`` or ``--convert``. + .. _cli_insert_replace: Insert-replacing data @@ -1565,6 +1631,9 @@ To replace a dog with in ID of 2 with a new record, run the following: echo '{"id": 2, "name": "Pancakes", "age": 3}' | \ sqlite-utils insert dogs.db dogs - --pk=id --replace +.. note:: + In Python: :ref:`table.insert(..., replace=True) ` CLI reference: :ref:`sqlite-utils insert ` + .. _cli_upsert: Upserting data @@ -1583,12 +1652,17 @@ For example: This will update the dog with an ID of 2 to have an age of 4, creating a new record (with a null name) if one does not exist. If a row DOES exist the name will be left as-is. +If the table already exists and has a primary key, you can omit the ``--pk`` option and ``sqlite-utils`` will use that existing primary key. + The command will fail if you reference columns that do not exist on the table. To automatically create missing columns, use the ``--alter`` option. .. note:: ``upsert`` in sqlite-utils 1.x worked like ``insert ... --replace`` does in 2.x. See `issue #66 `__ for details of this change. +.. note:: + In Python: :ref:`table.upsert() ` CLI reference: :ref:`sqlite-utils upsert ` + .. _cli_bulk: Executing SQL in bulk @@ -1790,6 +1864,9 @@ You can include named parameters in your where clause and populate them using on The ``--dry-run`` option will output a preview of the conversion against the first ten rows, without modifying the database. +.. note:: + In Python: :ref:`table.convert() ` CLI reference: :ref:`sqlite-utils convert ` + .. _cli_convert_import: Importing additional modules @@ -2071,6 +2148,12 @@ You can create a table in `SQLite STRICT mode ` CLI reference: :ref:`sqlite-utils create-table ` + .. _cli_renaming_tables: Renaming a table @@ -2101,6 +2187,9 @@ Yo ucan rename a table using the ``rename-table`` command: Pass ``--ignore`` to ignore any errors caused by the table not existing, or the new name already being in use. +.. note:: + In Python: :ref:`db.rename_table() ` CLI reference: :ref:`sqlite-utils rename-table ` + .. _cli_duplicate_table: Duplicating tables @@ -2112,6 +2201,9 @@ The ``duplicate`` command duplicates a table - creating a new table with the sam sqlite-utils duplicate books.db authors authors_copy +.. note:: + In Python: :ref:`table.duplicate() ` CLI reference: :ref:`sqlite-utils duplicate ` + .. _cli_drop_table: Dropping tables @@ -2125,12 +2217,15 @@ You can drop a table using the ``drop-table`` command: Use ``--ignore`` to ignore the error if the table does not exist. +.. note:: + In Python: :ref:`table.drop() ` CLI reference: :ref:`sqlite-utils drop-table ` + .. _cli_transform_table: Transforming tables =================== -The ``transform`` command allows you to apply complex transformations to a table that cannot be implemented using a regular SQLite ``ALTER TABLE`` command. See :ref:`python_api_transform` for details of how this works. The ``transform`` command preserves a table's ``STRICT`` mode. +The ``transform`` command allows you to apply complex transformations to a table that cannot be implemented using a regular SQLite ``ALTER TABLE`` command. See :ref:`python_api_transform` for details of how this works. By default, the ``transform`` command preserves a table's ``STRICT`` mode. .. code-block:: bash @@ -2141,7 +2236,7 @@ The ``transform`` command allows you to apply complex transformations to a table Every option for this table (with the exception of ``--pk-none``) can be specified multiple times. The options are as follows: ``--type column-name new-type`` - Change the type of the specified column. Valid types are ``integer``, ``text``, ``float``, ``blob``. + Change the type of the specified column. Valid types are ``integer``, ``text``, ``float``, ``real``, ``blob`` and ``any``. Changing a ``TEXT`` column to ``INTEGER``, ``FLOAT`` or ``REAL`` converts exact empty-string values to ``NULL``. ``--drop column-name`` Drop the specified column. @@ -2176,6 +2271,12 @@ Every option for this table (with the exception of ``--pk-none``) can be specifi ``--add-foreign-key column other_table other_column`` Add a foreign key constraint to ``column`` pointing to ``other_table.other_column``. +``--strict`` + Convert the table to a `SQLite STRICT table `__. The command fails if the available SQLite version does not support strict tables. If existing rows contain values that are incompatible with their declared column types the transformation fails and the original table is left unchanged. + +``--no-strict`` + Convert a strict table back to a regular non-strict table. + If you want to see the SQL that will be executed to make the change without actually executing it, add the ``--sql`` flag. For example: .. code-block:: bash @@ -2200,7 +2301,14 @@ If you want to see the SQL that will be executed to make the change without actu INSERT INTO "roadside_attractions_new_4033a60276b9" ("longitude", "latitude", "id", "name") SELECT "longitude", "latitude", "pk", "name" FROM "roadside_attractions"; DROP TABLE "roadside_attractions"; + PRAGMA legacy_alter_table=ON; ALTER TABLE "roadside_attractions_new_4033a60276b9" RENAME TO "roadside_attractions"; + PRAGMA legacy_alter_table=OFF; + +Tables that are referenced by views can be transformed - the view definitions are left unchanged, see :ref:`python_api_transform_views` for details. + +.. note:: + In Python: :ref:`table.transform() ` CLI reference: :ref:`sqlite-utils transform ` .. _cli_transform_table_add_primary_key_to_rowid: @@ -2379,6 +2487,9 @@ After running the above, the command ``sqlite-utils schema global.db`` reveals t CREATE UNIQUE INDEX "idx_countries_country_name" ON "countries" ("country", "name"); +.. note:: + In Python: :ref:`table.extract() ` CLI reference: :ref:`sqlite-utils extract ` + .. _cli_create_view: Creating views @@ -2400,6 +2511,9 @@ You can create a view using the ``create-view`` command: Use ``--replace`` to replace an existing view of the same name, and ``--ignore`` to do nothing if a view already exists. +.. note:: + In Python: :ref:`db.create_view() ` CLI reference: :ref:`sqlite-utils create-view ` + .. _cli_drop_view: Dropping views @@ -2413,6 +2527,9 @@ You can drop a view using the ``drop-view`` command: Use ``--ignore`` to ignore the error if the view does not exist. +.. note:: + In Python: :ref:`view.drop() ` CLI reference: :ref:`sqlite-utils drop-view ` + .. _cli_add_column: Adding columns @@ -2453,6 +2570,9 @@ You can set a ``NOT NULL DEFAULT 'x'`` constraint on the new column using ``--no sqlite-utils add-column mydb.db dogs friends_count integer --not-null-default 0 +.. note:: + In Python: :ref:`table.add_column() ` CLI reference: :ref:`sqlite-utils add-column ` + .. _cli_add_column_alter: Adding columns automatically on insert/update @@ -2464,6 +2584,9 @@ You can use the ``--alter`` option to automatically add new columns if the data sqlite-utils insert dogs.db dogs new-dogs.json --pk=id --alter +.. note:: + In Python: :ref:`table.insert(..., alter=True) ` + .. _cli_add_foreign_key: Adding foreign key constraints @@ -2491,6 +2614,9 @@ Add ``--ignore`` to ignore an existing foreign key (as opposed to returning an e See :ref:`python_api_add_foreign_key` in the Python API documentation for further details, including how the automatic table guessing mechanism works. +.. note:: + In Python: :ref:`table.add_foreign_key() ` CLI reference: :ref:`sqlite-utils add-foreign-key ` + .. _cli_add_foreign_keys: Adding multiple foreign keys at once @@ -2506,6 +2632,9 @@ Adding a foreign key requires a ``VACUUM``. On large databases this can be an ex When you are using this command each foreign key needs to be defined in full, as four arguments - the table, column, other table and other column. +.. note:: + In Python: :ref:`db.add_foreign_keys() ` CLI reference: :ref:`sqlite-utils add-foreign-keys ` + .. _cli_index_foreign_keys: Adding indexes for all foreign keys @@ -2517,6 +2646,9 @@ If you want to ensure that every foreign key column in your database has a corre sqlite-utils index-foreign-keys books.db +.. note:: + In Python: :ref:`db.index_foreign_keys() ` CLI reference: :ref:`sqlite-utils index-foreign-keys ` + .. _cli_defaults_not_null: Setting defaults and not null constraints @@ -2532,6 +2664,9 @@ You can use the ``--not-null`` and ``--default`` options (to both ``insert`` and --default age 2 \ --default score 5 +.. note:: + In Python: :ref:`not_null= and defaults= arguments ` + .. _cli_create_index: Creating indexes @@ -2563,6 +2698,25 @@ If your column names are already prefixed with a hyphen you'll need to manually Add the ``--analyze`` option to run ``ANALYZE`` against the index after it has been created. +.. note:: + In Python: :ref:`table.create_index() ` CLI reference: :ref:`sqlite-utils create-index ` + +.. _cli_drop_index: + +Dropping indexes +================ + +You can drop an index from an existing table using the ``drop-index`` command: + +.. code-block:: bash + + sqlite-utils drop-index mydb.db mytable idx_mytable_col1 + +Use ``--ignore`` to ignore the error if the index does not exist on that table. + +.. note:: + In Python: :ref:`table.drop_index() ` CLI reference: :ref:`sqlite-utils drop-index ` + .. _cli_fts: Configuring full-text search @@ -2616,6 +2770,9 @@ You can rebuild every FTS table by running ``rebuild-fts`` without passing any t sqlite-utils rebuild-fts mydb.db +.. note:: + In Python: :ref:`table.enable_fts() ` CLI reference: :ref:`sqlite-utils enable-fts ` + .. _cli_search: Executing searches @@ -2672,6 +2829,9 @@ Use the ``--sql`` option to output the SQL that would be executed, rather than r order by "documents_fts".rank +.. note:: + In Python: :ref:`table.search() ` CLI reference: :ref:`sqlite-utils search ` + .. _cli_enable_counts: Enabling cached counts @@ -2695,6 +2855,9 @@ If the ``_counts`` table ever becomes out-of-sync with the actual table counts y sqlite-utils reset-counts mydb.db +.. note:: + In Python: :ref:`table.enable_counts() ` CLI reference: :ref:`sqlite-utils enable-counts ` + .. _cli_analyze: Optimizing index usage with ANALYZE @@ -2718,6 +2881,9 @@ You can run it against specific tables, or against specific named indexes, by pa You can also run ``ANALYZE`` as part of another command using the ``--analyze`` option. This is supported by the ``create-index``, ``insert`` and ``upsert`` commands. +.. note:: + In Python: :ref:`db.analyze() ` CLI reference: :ref:`sqlite-utils analyze ` + .. _cli_vacuum: Vacuum @@ -2729,6 +2895,9 @@ You can run VACUUM to optimize your database like so: sqlite-utils vacuum mydb.db +.. note:: + In Python: :ref:`db.vacuum() ` CLI reference: :ref:`sqlite-utils vacuum ` + .. _cli_optimize: Optimize @@ -2752,6 +2921,9 @@ To optimize specific tables rather than every FTS table, pass those tables as ex sqlite-utils optimize mydb.db table_1 table_2 +.. note:: + In Python: :ref:`table.optimize() ` CLI reference: :ref:`sqlite-utils optimize ` + .. _cli_wal: WAL mode @@ -2771,6 +2943,9 @@ You can disable WAL mode using ``disable-wal``: Both of these commands accept one or more database files as arguments. +.. note:: + In Python: :ref:`db.enable_wal() and db.disable_wal() ` CLI reference: :ref:`sqlite-utils enable-wal ` + .. _cli_dump: Dumping the database to SQL @@ -2786,6 +2961,9 @@ The ``dump`` command outputs a SQL dump of the schema and full contents of the s ... COMMIT; +.. note:: + In Python: :ref:`db.iterdump() ` CLI reference: :ref:`sqlite-utils dump ` + .. _cli_load_extension: Loading SQLite extensions @@ -2833,6 +3011,9 @@ Eight (case-insensitive) types are allowed: * GEOMETRYCOLLECTION * GEOMETRY +.. note:: + In Python: :ref:`table.add_geometry_column() ` CLI reference: :ref:`sqlite-utils add-geometry-column ` + .. _cli_spatialite_indexes: Adding spatial indexes @@ -2846,6 +3027,9 @@ Once you have a geometry column, you can speed up bounding box queries by adding See this `SpatiaLite Cookbook recipe `__ for examples of how to use a spatial index. +.. note:: + In Python: :ref:`table.create_spatial_index() ` CLI reference: :ref:`sqlite-utils create-spatial-index ` + .. _cli_install: Installing packages diff --git a/docs/conf.py b/docs/conf.py index 4f29b39..62d4642 100644 --- a/docs/conf.py +++ b/docs/conf.py @@ -1,10 +1,7 @@ -#!/usr/bin/env python3 -# -*- coding: utf-8 -*- - import inspect -from pathlib import Path -from subprocess import Popen, PIPE, check_output import sys +from pathlib import Path +from subprocess import PIPE, CalledProcessError, Popen, check_output # This file is execfile()d with the current directory set to its # containing dir. @@ -50,7 +47,7 @@ extlinks = { def _linkcode_git_ref(): try: return check_output(["git", "rev-parse", "HEAD"]).decode("utf8").strip() - except Exception: + except (CalledProcessError, OSError): return "main" @@ -79,7 +76,7 @@ def linkcode_resolve(domain, info): obj = inspect.unwrap(obj) source_file = inspect.getsourcefile(obj) _, line_number = inspect.getsourcelines(obj) - except Exception: + except (OSError, TypeError, ValueError): return None if source_file is None: diff --git a/docs/migrations.rst b/docs/migrations.rst index cfdbf13..23aa9d8 100644 --- a/docs/migrations.rst +++ b/docs/migrations.rst @@ -27,7 +27,7 @@ Here is a simple example of a ``migrations.py`` file which creates a table, then .. code-block:: python - from sqlite_utils import Database, Migrations + from sqlite_utils import Migrations migrations = Migrations("creatures") @@ -51,6 +51,8 @@ Once you have a ``Migrations(name)`` collection with one or more migrations regi .. code-block:: python + from sqlite_utils import Database + db = Database("creatures.db") migrations.apply(db) diff --git a/docs/python-api.rst b/docs/python-api.rst index 11af1f4..d515642 100644 --- a/docs/python-api.rst +++ b/docs/python-api.rst @@ -109,6 +109,14 @@ You can also create a named in-memory database. Unlike regular memory databases db = Database(memory_name="my_shared_database") +After creating a ``Database`` you can use ``db.memory`` and ``db.memory_name`` to tell whether it is backed by an in-memory database and to read the shared cache name. ``db.memory`` is ``True`` for any in-memory database and ``db.memory_name`` holds the name passed to ``memory_name=``, or ``None`` otherwise. + +.. code-block:: python + + db = Database(memory_name="shared") + db.memory # True + db.memory_name # "shared" + Connections use ``PRAGMA recursive_triggers=on`` by default. If you don't want to use `recursive triggers `__ you can turn them off using: .. code-block:: python @@ -176,6 +184,9 @@ You can attach an additional database using the ``.attach()`` method, providing You can reference tables in the attached database using the alias value you passed to ``db.attach(alias, filepath)`` as a prefix, for example the ``second.table_in_second`` reference in the SQL query above. +.. note:: + In the CLI: :ref:`sqlite-utils --attach ` + .. _python_api_tracing: Tracing queries @@ -246,6 +257,9 @@ If a query returns more than one column with the same name - a join between two A suffix that would collide with another column in the query is skipped - ``select 1 as id, 2 as id, 3 as id_2`` returns ``{'id': 1, 'id_3': 2, 'id_2': 3}``. The same renaming is applied by ``table.rows_where()`` and ``table.search()``. +.. note:: + In the CLI: :ref:`sqlite-utils query ` + .. _python_api_execute: db.execute(sql, params) @@ -312,11 +326,15 @@ Every method in this library that writes to the database - ``insert()``, ``upser The same applies to raw SQL executed with :ref:`db.execute() ` - a write statement is committed as soon as it has run. +Another way to think about this is that each sqlite-utils method call is its own unit of work. If several method calls must either all succeed or all fail, use ``db.atomic()`` to turn them into a single unit of work. + You never need to call ``commit()``, and you do not need to close the database to persist your changes. There are exactly two situations where you need to think about transactions: 1. You want to group several write operations together, so they either all succeed or all fail - use :ref:`db.atomic() `. 2. You are :ref:`managing a transaction yourself ` with ``db.begin()``, in which case nothing is committed until you commit - the library will never commit a transaction you opened. +``with Database(...) as db:`` is not a transaction block. It manages the lifetime of the database connection and closes it on exit. Use ``with db.atomic():`` for a transaction. + .. _python_api_atomic: Grouping changes with db.atomic() @@ -332,6 +350,27 @@ Use ``db.atomic()`` to group multiple operations in a single transaction: The transaction commits when the block exits. If an exception is raised, changes made inside the block will be rolled back. +This matters when several operations represent a single logical change. Without ``db.atomic()``, an earlier method call remains committed if a later one fails: + +.. code-block:: python + + # These are two separate transactions + db.table("accounts").update(1, {"balance": 90}) + db.table("accounts").update(2, {"balance": 110}) + + # These updates either both succeed or both fail + with db.atomic(): + db.table("accounts").update(1, {"balance": 90}) + db.table("accounts").update(2, {"balance": 110}) + +Transactions can also improve performance. Calling ``insert()`` repeatedly outside ``db.atomic()`` creates and commits a separate transaction for every call. For bulk inserts, prefer :ref:`insert_all() `. If you need to call several different methods in a loop, wrap the loop in ``db.atomic()``: + +.. code-block:: python + + with db.atomic(): + for row in rows: + db.table("events").insert(row) + ``db.atomic()`` can be nested. Nested blocks use SQLite savepoints, so an exception in an inner block can roll back to that savepoint without rolling back the entire outer transaction: .. code-block:: python @@ -360,6 +399,8 @@ Write statements executed with :ref:`db.execute() ` follow t db.execute("insert into news (headline) values (?)", ["Dog wins award"]) # Already committed +``db.execute()`` participates in sqlite-utils transaction handling. Calling ``db.conn.execute()`` directly bypasses that policy and leaves transaction handling to Python's underlying ``sqlite3.Connection``. Prefer ``db.execute()`` unless you deliberately need the lower-level API. + If a transaction is open - because the call happens inside a ``db.atomic()`` block, or after ``db.begin()`` - the statement becomes part of that transaction instead, and commits when the transaction commits: .. code-block:: python @@ -391,9 +432,12 @@ You can take full manual control using the ``db.begin()``, ``db.commit()`` and ` The library will never commit a transaction you opened. If you call write methods such as ``insert()`` - or use ``db.atomic()`` - while your transaction is open, they participate in it using SQLite savepoints instead of committing: exiting an ``atomic()`` block releases its savepoint, but nothing is saved to disk until you commit the outer transaction yourself. If you roll back, their changes are rolled back too. -Two related safeguards to be aware of: +Prefer ``db.atomic()`` or ``db.begin()``, ``db.commit()`` and ``db.rollback()`` over mixing sqlite-utils transaction methods with calls to ``db.conn.commit()``, ``db.conn.rollback()`` or raw transaction-control SQL. Mixing the two layers makes it much harder to tell which layer owns the current transaction. + +Some related safeguards to be aware of: - ``db.enable_wal()`` and ``db.disable_wal()`` raise a ``sqlite_utils.db.TransactionError`` if called while a transaction is open, because changing the journal mode would commit it as a side effect. +- ``table.transform()`` raises a ``sqlite_utils.db.TransactionError`` if called while a transaction is open with ``PRAGMA foreign_keys`` enabled and the table is referenced by foreign keys with destructive ``ON DELETE`` actions, because the pragma cannot be turned off mid-transaction to protect those referencing rows - see :ref:`python_api_transform_foreign_keys_transactions`. - Closing the database - explicitly with ``db.close()``, or by exiting a ``with Database(...) as db:`` block - rolls back any transaction that is still open, see :ref:`python_api_close`. .. _python_api_transactions_modes: @@ -401,9 +445,11 @@ Two related safeguards to be aware of: Supported connection modes -------------------------- -``db.atomic()`` and the automatic per-method transactions require a connection in Python's default transaction handling mode. Passing a connection created with the Python 3.12+ ``sqlite3.connect(..., autocommit=True)`` or ``autocommit=False`` options to ``Database()`` raises a ``sqlite_utils.db.TransactionError``. +``db.atomic()`` and the automatic per-method transactions currently require a connection using Python's legacy transaction control mode (``sqlite3.LEGACY_TRANSACTION_CONTROL`` on Python 3.12 and later). Passing a connection created with the Python 3.12+ ``sqlite3.connect(..., autocommit=True)`` or ``autocommit=False`` options to ``Database()`` raises a ``sqlite_utils.db.TransactionError``. -This is because ``commit()`` and ``rollback()`` behave differently on those connections - under ``autocommit=True`` they are documented no-ops - which would cause every write made by this library to be silently discarded when the connection closed, rather than failing loudly. +Connections using ``autocommit=False`` are not supported because Python keeps a transaction open continuously. sqlite-utils uses ``Connection.in_transaction`` to distinguish its own transactions from transactions opened by its caller, and that distinction is not available in this mode. + +Connections using ``autocommit=True`` are also currently rejected because sqlite-utils has not formally exposed that as a supported configuration. .. _python_api_table: @@ -458,6 +504,9 @@ You can also iterate through the table objects themselves using the ``.tables`` >>> db.tables [] +.. note:: + In the CLI: :ref:`sqlite-utils tables ` + .. _python_api_views: Listing views @@ -483,6 +532,9 @@ View objects are similar to Table objects, except that any attempts to insert or * ``rows_where(where, where_args, order_by, select)`` * ``drop()`` +.. note:: + In the CLI: :ref:`sqlite-utils views ` + .. _python_api_rows: Listing rows @@ -538,6 +590,9 @@ This method also accepts ``offset=`` and ``limit=`` arguments, for specifying an ... print(row) {'id': 1, 'age': 4, 'name': 'Cleo'} +.. note:: + In the CLI: :ref:`sqlite-utils rows ` + .. _python_api_rows_count_where: Counting rows @@ -622,6 +677,9 @@ The ``db.schema`` property returns the full SQL schema for the database as a str "name" TEXT ); +.. note:: + In the CLI: :ref:`sqlite-utils schema ` + .. _python_api_creating_tables: Creating tables @@ -770,6 +828,22 @@ You can pass ``strict=True`` to create a table in ``STRICT`` mode: "name": str, }, strict=True) +SQLite ``STRICT`` tables can use the ``ANY`` column type for values that should retain their exact SQLite storage class without coercion. Use the ``sqlite_utils.ANY`` marker type: + +.. code-block:: python + + import sqlite_utils + + db.table("events").create({ + "id": int, + "payload": sqlite_utils.ANY, + }, pk="id", strict=True) + +An ``ANY`` column can store integers, floating point values, text, binary data or ``None``. In a ``STRICT`` table a text value such as ``"000123"`` remains text with its leading zeroes intact. SQLite also accepts ``ANY`` columns in ordinary non-``STRICT`` tables, but those columns apply numeric affinity and would store that same value as the integer ``123``. + +.. note:: + In the CLI: :ref:`sqlite-utils create-table ` + .. _python_api_compound_primary_keys: Compound primary keys @@ -950,6 +1024,9 @@ Here's an example that uses these features: # ) +.. note:: + In the CLI: :ref:`sqlite-utils insert --not-null and --default ` + .. _python_api_rename_table: Renaming a table @@ -967,6 +1044,9 @@ This executes the following SQL: ALTER TABLE [my_table] RENAME TO [new_name_for_my_table] +.. note:: + In the CLI: :ref:`sqlite-utils rename-table ` + .. _python_api_duplicate: Duplicating tables @@ -982,6 +1062,9 @@ The new ``authors_copy`` table will now contain a duplicate copy of the data fro This method raises ``sqlite_utils.db.NoTable`` if the table does not exist. +.. note:: + In the CLI: :ref:`sqlite-utils duplicate ` + .. _python_api_bulk_inserts: Bulk inserts @@ -1024,6 +1107,9 @@ You can delete all the existing rows in the table before inserting the new recor Pass ``analyze=True`` to run ``ANALYZE`` against the table after inserting the new records. +.. note:: + In the CLI: :ref:`sqlite-utils insert ` + .. _python_api_insert_lists: Inserting data from a list or tuple iterator @@ -1101,6 +1187,9 @@ To replace any existing records that have a matching primary key, use the ``repl .. note:: Prior to sqlite-utils 2.0 the ``.upsert()`` and ``.upsert_all()`` methods worked the same way as ``.insert(replace=True)`` does today. See :ref:`python_api_upsert` for the new behaviour of those methods introduced in 2.0. +.. note:: + In the CLI: :ref:`sqlite-utils insert --replace ` + .. _python_api_update: Updating a specific record @@ -1186,6 +1275,9 @@ Every record passed to ``upsert()`` or ``upsert_all()`` must include a value for .. note:: ``.upsert()`` and ``.upsert_all()`` in sqlite-utils 1.x worked like ``.insert(..., replace=True)`` and ``.insert_all(..., replace=True)`` do in 2.x. See `issue #66 `__ for details of this change. +.. note:: + In the CLI: :ref:`sqlite-utils upsert ` + .. _python_api_old_upsert: Alternative upserts using INSERT OR IGNORE @@ -1490,7 +1582,7 @@ You can specify the ``col_type`` argument either using a SQLite type as a string The ``col_type`` is optional - if you omit it the type of ``TEXT`` will be used. -SQLite types you can specify are ``"TEXT"``, ``"INTEGER"``, ``"FLOAT"``, ``"REAL"`` or ``"BLOB"``. +SQLite types you can specify are ``"TEXT"``, ``"INTEGER"``, ``"FLOAT"``, ``"REAL"``, ``"BLOB"`` or ``"ANY"``. You can use the ``sqlite_utils.ANY`` marker instead of the ``"ANY"`` string. If you pass a Python type, it will be mapped to SQLite types as shown here:: @@ -1503,6 +1595,7 @@ If you pass a Python type, it will be mapped to SQLite types as shown here:: datetime.date: "TEXT" datetime.time: "TEXT" datetime.timedelta: "TEXT" + sqlite_utils.ANY: "ANY" # If numpy is installed np.int8: "INTEGER" @@ -1537,6 +1630,9 @@ You can set a ``NOT NULL DEFAULT 'x'`` constraint on the new column using ``not_ db.table("dogs").add_column("friends_count", int, not_null_default=0) +.. note:: + In the CLI: :ref:`sqlite-utils add-column ` + .. _python_api_add_column_alter: Adding columns automatically on insert/update @@ -1560,6 +1656,9 @@ You can insert or update data that includes new columns and have the table autom new_table = db.table("new_table", alter=True) new_table.insert({"name": "Gareth", "age": 32, "shoe_size": 11}) +.. note:: + In the CLI: :ref:`sqlite-utils insert --alter ` + .. _python_api_add_foreign_key: Adding foreign key constraints @@ -1618,6 +1717,9 @@ Use ``on_delete=`` and ``on_update=`` to specify ``ON DELETE`` and ``ON UPDATE`` This creates a foreign key with an ``ON DELETE CASCADE`` clause, so deleting an author will also delete their books (provided foreign key enforcement is enabled with ``PRAGMA foreign_keys = ON``). Valid actions are ``"SET NULL"``, ``"SET DEFAULT"``, ``"CASCADE"``, ``"RESTRICT"`` and the default ``"NO ACTION"``. +.. note:: + In the CLI: :ref:`sqlite-utils add-foreign-key ` + .. _python_api_add_foreign_keys: Adding multiple foreign key constraints at once @@ -1638,6 +1740,9 @@ This method runs the same checks as ``.add_foreign_keys()`` and will raise ``sql Foreign keys that already exist are silently skipped, so repeated calls are idempotent - but only if they match exactly. Requesting a foreign key that exists with different ``ON DELETE``/``ON UPDATE`` actions raises ``AlterError``: use ``table.transform()`` to change the actions of an existing foreign key. +.. note:: + In the CLI: :ref:`sqlite-utils add-foreign-keys ` + .. _python_api_index_foreign_keys: Adding indexes for all foreign keys @@ -1651,6 +1756,9 @@ If you want to ensure that every foreign key column in your database has a corre Compound foreign keys get a single composite index across their columns. +.. note:: + In the CLI: :ref:`sqlite-utils index-foreign-keys ` + .. _python_api_drop: Dropping a table or view @@ -1672,6 +1780,9 @@ Pass ``ignore=True`` if you want to ignore the error caused by the table or view db.table("my_table").drop(ignore=True) +.. note:: + In the CLI: :ref:`sqlite-utils drop-table ` and :ref:`sqlite-utils drop-view ` + .. _python_api_transform: Transforming a table @@ -1700,6 +1811,9 @@ To keep the original table around instead of dropping it, pass the ``keep_table= This method raises a ``sqlite_utils.db.TransformError`` exception if the table cannot be transformed, usually because there are existing constraints or indexes that are incompatible with modifications to the columns. +.. note:: + In the CLI: :ref:`sqlite-utils transform ` + .. _python_api_transform_alter_column_types: Altering column types @@ -1712,8 +1826,35 @@ To alter the type of a column, use the ``types=`` argument: # Convert the 'age' column to an integer, and 'weight' to a float table.transform(types={"age": int, "weight": float}) +When a ``TEXT`` column is changed to ``INTEGER``, ``FLOAT`` or ``REAL``, exact empty-string values are stored as ``NULL``. Other values, including whitespace-only strings, are copied normally. + See :ref:`python_api_add_column` for a list of available types. +.. _python_api_transform_strict: + +Changing strict mode +-------------------- + +The optional ``strict=`` parameter can change whether a table uses `SQLite STRICT mode `__. Pass ``strict=True`` to convert a regular table to a strict table: + +.. code-block:: python + + table.transform(strict=True) + +Pass ``strict=False`` to convert a strict table back to a regular non-strict table: + +.. code-block:: python + + table.transform(strict=False) + +If the table has ``ANY`` columns, converting it to non-strict mode can coerce text values that look numeric. For example, SQLite converts ``"000123"`` to the integer ``123`` when copying it into an ordinary ``ANY`` column. This is SQLite's documented distinction between `STRICT and ordinary ANY columns `__. + +The default is ``strict=None``, which preserves the table's existing strict mode. + +Passing ``strict=True`` raises ``sqlite_utils.db.TransformError`` if the available SQLite version does not support strict tables. + +Converting to a strict table validates all existing rows as they are copied into the replacement table. If a value is incompatible with its declared column type, SQLite raises ``sqlite3.IntegrityError`` and the transformation is rolled back, leaving the original table and its data unchanged. + .. _python_api_transform_rename_columns: Renaming columns @@ -1863,6 +2004,28 @@ A bare column name drops any foreign key that column participates in, including Renaming a column with ``rename=`` updates any foreign keys that use it, and dropping a column with ``drop=`` also drops any foreign keys it participates in - for a compound foreign key this removes the whole constraint. +.. _python_api_transform_check_constraints: + +CHECK constraints +----------------- + +``.transform()`` preserves both column-level and table-level ``CHECK`` constraints. If a column is renamed, references to that column in the check expression are renamed too. + +A column-level check is removed if its owning column is dropped. Dropping a column referenced by any remaining check raises ``TransformError`` instead of creating an invalid or unexpectedly weakened schema. + +Comments immediately before or after a column definition are preserved too. They move with that column if it is renamed or reordered, and are removed if the column is dropped. A comment between two column definitions is treated as belonging to the following column. + +.. _python_api_transform_views: + +Tables referenced by views +-------------------------- + +Tables that are referenced by views can be safely transformed - the view definitions are left byte-for-byte unchanged, and views continue to read from the live table even when ``keep_table=`` is used to keep a copy of the original around. + +A view that references a column which the transform renamed or dropped will remain defined but will raise a ``no such column`` error when it is next queried. This is inherent to SQLite views, whose SQL is stored as text - if you rename or drop columns that a view depends on you should update that view definition yourself. + +To achieve this, the SQL produced by ``transform_sql()`` turns on ``PRAGMA legacy_alter_table`` for its ``ALTER TABLE ... RENAME TO`` statements, then restores the pragma to the value it had when the SQL was generated - without this, SQLite would attempt to rewrite references to the renamed table in every view definition, which fails when a view references the table that was just dropped. + .. _python_api_transform_sql: Custom transformations with .transform_sql() @@ -1874,6 +2037,36 @@ If you want to do something more advanced, you can call the ``table.transform_sq This method will return a list of SQL statements that should be executed to implement the change. You can then make modifications to that SQL - or add additional SQL statements - before executing it yourself. +.. _python_api_transform_foreign_keys_transactions: + +Foreign keys and transactions +----------------------------- + +Because ``.transform()`` drops the old table, running it with ``PRAGMA foreign_keys`` enabled could fire ``ON DELETE`` actions on any tables that reference it - an inbound ``ON DELETE CASCADE`` foreign key would silently delete those referencing rows. To prevent this, ``.transform()`` turns ``PRAGMA foreign_keys`` off for the duration of the operation and restores it afterwards, running ``PRAGMA foreign_key_check`` before committing. + +``PRAGMA foreign_keys`` cannot be changed inside a transaction, so this protection is impossible if you call ``.transform()`` while a transaction is already open - for example inside a ``with db.atomic():`` block or after ``db.begin()``. If ``PRAGMA foreign_keys`` is on and another table references the table being transformed with a destructive ``ON DELETE`` action - ``CASCADE``, ``SET NULL`` or ``SET DEFAULT`` - the method will refuse to run and raise a ``sqlite_utils.db.TransactionError``: + +.. code-block:: python + + from sqlite_utils.db import TransactionError + + try: + with db.atomic(): + db["authors"].transform(types={"id": str}) + except TransactionError as ex: + print("Could not transform in transaction:", ex) + +To transform such a table either call ``.transform()`` outside of the transaction, or execute ``PRAGMA foreign_keys = off`` before opening it: + +.. code-block:: python + + db.execute("PRAGMA foreign_keys = off") + with db.atomic(): + db["authors"].transform(types={"id": str}) + db.execute("PRAGMA foreign_keys = on") + +Tables referenced by foreign keys without a destructive action (the default ``NO ACTION``, or ``RESTRICT``) can still be transformed inside a transaction - sqlite-utils uses ``PRAGMA defer_foreign_keys`` to postpone the foreign key checks until the transaction commits. + .. _python_api_extract: Extracting columns into a separate table @@ -2032,6 +2225,9 @@ This produces a lookup table like so: Rows where every extracted column is ``null`` are not extracted: no record is created for them in the lookup table and their foreign key column is left as ``null``. When extracting multiple columns, rows where at least one of the extracted columns has a value will be extracted as usual. +.. note:: + In the CLI: :ref:`sqlite-utils extract ` + .. _python_api_hash: Setting an ID based on the hash of the row contents @@ -2093,6 +2289,9 @@ You can pass ``ignore=True`` to silently ignore an existing view and do nothing, select * from dogs where is_good_dog = 1 """, replace=True) +.. note:: + In the CLI: :ref:`sqlite-utils create-view ` + Storing JSON ============ @@ -2211,6 +2410,9 @@ If you are using ``pysqlite3`` the underlying method may be missing. If you inst pip install sqlite-dump +.. note:: + In the CLI: :ref:`sqlite-utils dump ` + .. _python_api_introspection: Introspecting tables and views @@ -2274,6 +2476,11 @@ The ``.columns_dict`` property returns a dictionary version of the columns with >>> db.table("PlantType").columns_dict {'id': , 'value': } +SQLite ``ANY`` columns are represented by the ``sqlite_utils.ANY`` marker type:: + + >>> db.table("events").columns_dict + {'id': , 'payload': } + .. _python_api_introspection_default_values: .default_values @@ -2307,6 +2514,43 @@ Almost all SQLite tables have a ``rowid`` column, but a table with no explicitly False +.. _python_api_introspection_checks: + +.checks +------- + +The ``.checks`` property returns the column-level and table-level ``CHECK`` constraints defined on a table, as a list of ``Check`` objects. Each object has ``check`` (the expression inside ``CHECK (...)``), ``name``, ``column`` and ``options`` attributes. ``column`` is an empty string for a table-level check. ``options`` contains a list of values only when a column check consists entirely of ``column IN (literal, ...)``. The original constraint fragment is available as ``sql``; ``start`` and ``end`` are its offsets within ``table.schema``. + +.. code-block:: python + + >>> db["scores"].checks + [Check(check='score > 0', name='positive', column='score', options=None), + Check(check='score <= maximum', name='within_maximum', column='', options=None)] + +.. _python_api_introspection_column_checks: + +.column_checks +-------------- + +The ``.column_checks`` property returns the column-level checks grouped by column name: + +.. code-block:: python + + >>> db["scores"].column_checks + {'score': [Check(check='score > 0', name='positive', column='score', options=None)]} + +.. _python_api_introspection_table_checks: + +.table_checks +------------- + +The ``.table_checks`` property returns only the table-level checks: + +.. code-block:: python + + >>> db["scores"].table_checks + [Check(check='score <= maximum', name='within_maximum', column='', options=None)] + .. _python_api_introspection_foreign_keys: .foreign_keys @@ -2410,6 +2654,9 @@ The ``.indexes`` property returns all indexes created for a table, as a list of Index(seq=4, name='"Street_Tree_List_qCaretaker"', unique=0, origin='c', partial=0, columns=['qCaretaker']), Index(seq=5, name='"Street_Tree_List_PlantType"', unique=0, origin='c', partial=0, columns=['PlantType'])] +.. note:: + In the CLI: :ref:`sqlite-utils indexes ` + .. _python_api_introspection_xindexes: .xindexes @@ -2453,6 +2700,9 @@ The ``.triggers`` property lists database triggers. It can be used on both datab >>> db.triggers ... similar output to db.table("authors").triggers +.. note:: + In the CLI: :ref:`sqlite-utils triggers ` + .. _python_api_introspection_triggers_dict: .triggers_dict @@ -2601,6 +2851,9 @@ To remove the FTS tables and triggers you created, use the ``disable_fts()`` tab db.table("dogs").disable_fts() +.. note:: + In the CLI: :ref:`sqlite-utils enable-fts ` + .. _python_api_quote_fts: Quoting characters for use in search @@ -2665,6 +2918,9 @@ To return just the title and published columns for three matches for ``"dog"`` w ): print(article) +.. note:: + In the CLI: :ref:`sqlite-utils search ` + .. _python_api_fts_search_sql: Building SQL queries with table.search_sql() @@ -2749,6 +3005,9 @@ This runs the following SQL:: INSERT INTO dogs_fts (dogs_fts) VALUES ("rebuild"); +.. note:: + In the CLI: :ref:`sqlite-utils rebuild-fts ` + .. _python_api_fts_optimize: Optimizing a full-text search table @@ -2764,6 +3023,9 @@ This runs the following SQL:: INSERT INTO dogs_fts (dogs_fts) VALUES ("optimize"); +.. note:: + In the CLI: :ref:`sqlite-utils optimize ` + .. _python_api_cached_table_counts: Cached table counts using triggers @@ -2826,6 +3088,9 @@ If the ``_counts`` table ever becomes out-of-sync with the actual table counts y db.reset_counts() +.. note:: + In the CLI: :ref:`sqlite-utils enable-counts ` + .. _python_api_create_index: Creating indexes @@ -2869,6 +3134,17 @@ Use ``if_not_exists=True`` to do nothing if an index with that name already exis Pass ``analyze=True`` to run ``ANALYZE`` against the new index after creating it. +You can drop an index from a table using ``.drop_index(index_name)``: + +.. code-block:: python + + db.table("dogs").drop_index("idx_dogs_name") + +Use ``ignore=True`` to ignore the error if the index does not exist. + +.. note:: + In the CLI: :ref:`sqlite-utils create-index ` and :ref:`sqlite-utils drop-index ` + .. _python_api_analyze: Optimizing index usage with ANALYZE @@ -2896,6 +3172,9 @@ To run against all indexes attached to a specific table, you can either pass the db.table("dogs").analyze() +.. note:: + In the CLI: :ref:`sqlite-utils analyze ` + .. _python_api_vacuum: Vacuum @@ -2907,6 +3186,9 @@ You can optimize your database by running VACUUM against it like so: Database("my_database.db").vacuum() +.. note:: + In the CLI: :ref:`sqlite-utils vacuum ` + .. _python_api_wal: WAL mode @@ -2934,6 +3216,9 @@ You can check the current journal mode for a database using the ``journal_mode`` This will usually be ``wal`` or ``delete`` (meaning WAL is disabled), but can have other values - see the `PRAGMA journal_mode `__ documentation. +.. note:: + In the CLI: :ref:`sqlite-utils enable-wal and disable-wal ` + .. _python_api_suggest_column_types: Suggesting column types @@ -3074,6 +3359,9 @@ You can cause ``sqlite3`` to return more useful errors, including the traceback sqlite3.enable_callback_tracebacks(True) +.. note:: + In the CLI: :ref:`sqlite-utils query --functions ` + .. _python_api_quote: Quoting strings for use in SQL @@ -3206,6 +3494,9 @@ Initialize SpatiaLite .. automethod:: sqlite_utils.db.Database.init_spatialite :noindex: +.. note:: + In the CLI: :ref:`sqlite-utils create-database --init-spatialite ` + .. _python_api_gis_find_spatialite: Finding SpatiaLite @@ -3221,6 +3512,9 @@ Adding geometry columns .. automethod:: sqlite_utils.db.Table.add_geometry_column :noindex: +.. note:: + In the CLI: :ref:`sqlite-utils add-geometry-column ` + .. _python_api_gis_create_spatial_index: Creating a spatial index @@ -3228,3 +3522,6 @@ Creating a spatial index .. automethod:: sqlite_utils.db.Table.create_spatial_index :noindex: + +.. note:: + In the CLI: :ref:`sqlite-utils create-spatial-index ` diff --git a/pyproject.toml b/pyproject.toml index c1024c2..92650e2 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -1,6 +1,6 @@ [project] name = "sqlite-utils" -version = "4.0rc4" +version = "4.2.1" description = "CLI tool and Python library for manipulating SQLite databases" readme = { file = "README.md", content-type = "text/markdown" } authors = [ @@ -48,6 +48,7 @@ dev = [ # flake8 "flake8", "flake8-pyproject", + "pyright>=1.1.411", "ty>=0.0.37", # For stable cog: "tabulate>=0.10.0", @@ -79,7 +80,14 @@ build-backend = "setuptools.build_meta" max-line-length = 160 # Black compatibility, E203 whitespace before ':': extend-ignore = ["E203"] -extend-exclude = [".venv", "build", "dist", "docs", "sqlite_utils.egg-info"] +extend-exclude = [ + ".venv", + ".claude", + "build", + "dist", + "docs", + "sqlite_utils.egg-info", +] [tool.setuptools.package-data] sqlite_utils = ["py.typed"] diff --git a/sqlite_utils/__init__.py b/sqlite_utils/__init__.py index 58ee7ab..3f350e1 100644 --- a/sqlite_utils/__init__.py +++ b/sqlite_utils/__init__.py @@ -1,7 +1,13 @@ -from .utils import suggest_column_types -from .hookspecs import hookimpl -from .hookspecs import hookspec from .db import Database +from .hookspecs import hookimpl, hookspec from .migrations import Migrations +from .utils import ANY, suggest_column_types -__all__ = ["Database", "Migrations", "suggest_column_types", "hookimpl", "hookspec"] +__all__ = [ + "ANY", + "Database", + "Migrations", + "hookimpl", + "hookspec", + "suggest_column_types", +] diff --git a/sqlite_utils/cli.py b/sqlite_utils/cli.py index fe7dbe4..c230902 100644 --- a/sqlite_utils/cli.py +++ b/sqlite_utils/cli.py @@ -1,53 +1,59 @@ import base64 +import csv as csv_std import difflib -from typing import Any -import click -from click_default_group import DefaultGroup -from datetime import datetime, timezone import hashlib -import pathlib -from runpy import run_module -import sqlite_utils -from sqlite_utils.db import ( - AlterError, - BadMultiValues, - DEFAULT, - DescIndex, - InvalidColumns, - NoTable, - NoView, - quote_identifier, -) -from sqlite_utils.plugins import ensure_plugins_loaded, pm, get_plugins -from sqlite_utils.utils import maximize_csv_field_size_limit -from sqlite_utils import recipes -import textwrap import inspect import io import itertools import json import os -import pdb +import pathlib +import pdb # noqa: T100 import sys -import csv as csv_std +import textwrap +from datetime import datetime, timezone +from runpy import run_module +from typing import Any + +import click import tabulate +from click_default_group import DefaultGroup + +import sqlite_utils +from sqlite_utils import recipes +from sqlite_utils.db import ( + DEFAULT, + AlterError, + BadMultiValues, + DescIndex, + InvalidColumns, + NoTable, + NoView, + PrimaryKeyRequired, + quote_identifier, +) +from sqlite_utils.plugins import ensure_plugins_loaded, get_plugins, pm +from sqlite_utils.utils import maximize_csv_field_size_limit + from .utils import ( + Format, OperationalError, + TypeTracker, _compile_code, chunks, + decode_base64_values, dedupe_keys, file_progress, find_spatialite, - flatten as _flatten, - sqlite3, - decode_base64_values, progressbar, rows_from_file, - Format, - TypeTracker, + sqlite3, +) +from .utils import ( + flatten as _flatten, ) -CONTEXT_SETTINGS = dict(help_option_names=["-h", "--help"]) +CONTEXT_SETTINGS = {"help_option_names": ["-h", "--help"]} def _register_db_for_cleanup(db): @@ -66,11 +72,11 @@ def _close_databases(ctx): for db in ctx.meta.get("_databases_to_close", []): try: db.close() - except Exception: + except sqlite3.Error: pass -VALID_COLUMN_TYPES = ("INTEGER", "TEXT", "FLOAT", "REAL", "BLOB") +VALID_COLUMN_TYPES = ("INTEGER", "TEXT", "FLOAT", "REAL", "BLOB", "ANY") UNICODE_ERROR = """ {} @@ -153,6 +159,17 @@ def load_extension_option(fn): )(fn) +def functions_option(fn): + return click.option( + "--functions", + help=( + "Python code or a file path defining custom SQL functions; " + "can be used multiple times" + ), + multiple=True, + )(fn) + + @click.group( cls=DefaultGroup, default="query", @@ -162,7 +179,6 @@ def load_extension_option(fn): @click.version_option() def cli(): "Commands for interacting with a SQLite database" - pass @cli.command() @@ -473,7 +489,17 @@ def dump(path, load_extension): @click.argument( "col_type", type=click.Choice( - ["integer", "int", "float", "real", "text", "str", "blob", "bytes"], + [ + "integer", + "int", + "float", + "real", + "text", + "str", + "blob", + "bytes", + "any", + ], case_sensitive=False, ), required=False, @@ -680,6 +706,34 @@ def create_index( ) +@cli.command(name="drop-index") +@click.argument( + "path", + type=click.Path(exists=True, file_okay=True, dir_okay=False, allow_dash=False), + required=True, +) +@click.argument("table") +@click.argument("index") +@click.option("--ignore", help="Ignore if index does not exist", is_flag=True) +@load_extension_option +def drop_index(path, table, index, ignore, load_extension): + """ + Drop an index by index name from the specified table + + Example: + + \b + sqlite-utils drop-index chickens.db chickens idx_chickens_name + """ + db = sqlite_utils.Database(path) + _register_db_for_cleanup(db) + _load_extensions(db, load_extension) + try: + db.table(table).drop_index(index, ignore=ignore) + except OperationalError as ex: + raise click.ClickException(str(ex)) + + @cli.command(name="enable-fts") @click.argument( "path", @@ -706,7 +760,7 @@ def create_index( def enable_fts( path, table, column, fts4, fts5, tokenize, create_triggers, replace, load_extension ): - """Enable full-text search for specific table and columns" + """Enable full-text search for specific table and columns Example: @@ -851,7 +905,7 @@ def enable_counts(path, tables, load_extension): # Check all tables exist bad_tables = [table for table in tables if not db[table].exists()] if bad_tables: - raise click.ClickException("Invalid tables: {}".format(bad_tables)) + raise click.ClickException(f"Invalid tables: {bad_tables}") for table in tables: db.table(table).enable_counts() @@ -932,13 +986,19 @@ def insert_upsert_options(*, require_pk=False): required=True, ), click.argument("table"), - click.argument("file", type=click.File("rb", lazy=True), required=True), + click.argument( + "file", type=click.File("rb", lazy=True), required=False + ), click.option( "--pk", help="Columns to use as the primary key, e.g. id", multiple=True, required=require_pk, ), + click.option( + "--code", + help="Python code defining a rows() function or iterable of rows to insert", + ), ) + _import_options + ( @@ -962,6 +1022,16 @@ def insert_upsert_options(*, require_pk=False): type=(str, str), help="Default value that should be set for a column", ), + click.option( + "--type", + "types", + type=( + str, + click.Choice(list(VALID_COLUMN_TYPES), case_sensitive=False), + ), + multiple=True, + help="Column types to use when creating the table", + ), click.option( "--no-detect-types", is_flag=True, @@ -1016,6 +1086,7 @@ def insert_upsert_implementation( truncate=False, not_null=None, default=None, + types=None, no_detect_types=False, analyze=False, load_extension=None, @@ -1023,11 +1094,121 @@ def insert_upsert_implementation( bulk_sql=None, functions=None, strict=False, + code=None, ): db = sqlite_utils.Database(path) _register_db_for_cleanup(db) _load_extensions(db, load_extension) _maybe_register_functions(db, functions) + column_type_overrides = {column: ctype.upper() for column, ctype in (types or [])} + + def _insert_docs(docs, tracker=None): + extra_kwargs: dict[str, Any] = { + "ignore": ignore, + "replace": replace, + "truncate": truncate, + "analyze": analyze, + "strict": strict, + } + if not_null: + extra_kwargs["not_null"] = set(not_null) + if default: + extra_kwargs["defaults"] = dict(default) + if column_type_overrides: + extra_kwargs["columns"] = column_type_overrides + if upsert: + extra_kwargs["upsert"] = upsert + + # docs should all be dictionaries + docs = (verify_is_dict(doc) for doc in docs) + + # Apply {"$base64": true, ...} decoding, if needed + docs = (decode_base64_values(doc) for doc in docs) + + # For bulk_sql= we use cursor.executemany() instead + if bulk_sql: + if batch_size: + doc_chunks = chunks(docs, batch_size) + else: + doc_chunks = [docs] + for doc_chunk in doc_chunks: + with db.atomic(): + db.conn.cursor().executemany(bulk_sql, doc_chunk) + return + + # table_names() rather than db.table(), which raises NoTable for + # views before the error handling below can deal with them + table_existed_before_insert = table in db.table_names() + try: + db.table(table).insert_all( + docs, pk=pk, batch_size=batch_size, alter=alter, **extra_kwargs + ) + except (NoTable, InvalidColumns, PrimaryKeyRequired) as e: + raise click.ClickException(str(e)) + except Exception as e: + if ( + isinstance(e, OperationalError) + and e.args + and ( + "has no column named" in e.args[0] or "no such column" in e.args[0] + ) + ): + raise click.ClickException( + f"{e.args[0]}\n\nTry using --alter to add additional columns" + ) + # If we can find sql= and parameters= arguments, show those + variables = _find_variables(e.__traceback__, ["sql", "parameters"]) + if "sql" in variables and "parameters" in variables: + raise click.ClickException( + "{}\n\nsql = {}\nparameters = {}".format( + str(e), variables["sql"], variables["parameters"] + ) + ) + else: + raise + # Apply detected types only to a table this command created - + # transforming a pre-existing table would rewrite its column types + # and corrupt values such as TEXT zip codes with leading zeros + if ( + tracker is not None + and not table_existed_before_insert + and db.table(table).exists() + ): + detected_types = tracker.types + detected_types.update(column_type_overrides) + db.table(table).transform(types=detected_types) + + if code is not None: + if file is not None: + raise click.ClickException("--code cannot be used with a FILE argument") + if any( + [ + flatten, + nl, + csv, + tsv, + empty_null, + lines, + text, + convert, + sniff, + no_headers, + delimiter, + quotechar, + encoding, + ] + ): + raise click.ClickException( + "--code cannot be used with input format options" + ) + _insert_docs(_rows_from_code(code)) + return + + if file is None: + raise click.ClickException( + "Provide either a FILE argument or --code to specify rows to insert" + ) + if (delimiter or quotechar or sniff or no_headers) and not tsv: csv = True if (nl + csv + tsv) >= 2: @@ -1071,7 +1252,7 @@ def insert_upsert_implementation( reader = csv_std.reader(decoded, **csv_reader_args) # type: ignore first_row = next(reader) if no_headers: - headers = ["untitled_{}".format(i + 1) for i in range(len(first_row))] + headers = [f"untitled_{i + 1}" for i in range(len(first_row))] reader = itertools.chain([first_row], reader) else: headers = first_row @@ -1100,9 +1281,7 @@ def insert_upsert_implementation( docs = [docs] except json.decoder.JSONDecodeError as ex: raise click.ClickException( - "Invalid JSON - use --csv for CSV or --tsv for TSV files\n\nJSON error: {}".format( - ex - ) + f"Invalid JSON - use --csv for CSV or --tsv for TSV files\n\nJSON error: {ex}" ) if flatten: docs = (_flatten(doc) for doc in docs) @@ -1121,7 +1300,7 @@ def insert_upsert_implementation( docs = (fn(doc["line"]) for doc in docs) elif text: # Special case: this is allowed to be an iterable - text_value = list(docs)[0]["text"] + text_value = next(iter(docs))["text"] fn_return = fn(text_value) if isinstance(fn_return, dict): docs = [fn_return] @@ -1135,78 +1314,7 @@ def insert_upsert_implementation( else: docs = (fn(doc) or doc for doc in docs) - extra_kwargs = { - "ignore": ignore, - "replace": replace, - "truncate": truncate, - "analyze": analyze, - "strict": strict, - } - if not_null: - extra_kwargs["not_null"] = set(not_null) - if default: - extra_kwargs["defaults"] = dict(default) - if upsert: - extra_kwargs["upsert"] = upsert - - # docs should all be dictionaries - docs = (verify_is_dict(doc) for doc in docs) - - # Apply {"$base64": true, ...} decoding, if needed - docs = (decode_base64_values(doc) for doc in docs) - - # For bulk_sql= we use cursor.executemany() instead - if bulk_sql: - if batch_size: - doc_chunks = chunks(docs, batch_size) - else: - doc_chunks = [docs] - for doc_chunk in doc_chunks: - with db.atomic(): - db.conn.cursor().executemany(bulk_sql, doc_chunk) - return - - # table_names() rather than db.table(), which raises NoTable for - # views before the error handling below can deal with them - table_existed_before_insert = table in db.table_names() - try: - db.table(table).insert_all( - docs, pk=pk, batch_size=batch_size, alter=alter, **extra_kwargs - ) - except (NoTable, InvalidColumns) as e: - raise click.ClickException(str(e)) - except Exception as e: - if ( - isinstance(e, OperationalError) - and e.args - and ( - "has no column named" in e.args[0] or "no such column" in e.args[0] - ) - ): - raise click.ClickException( - "{}\n\nTry using --alter to add additional columns".format( - e.args[0] - ) - ) - # If we can find sql= and parameters= arguments, show those - variables = _find_variables(e.__traceback__, ["sql", "parameters"]) - if "sql" in variables and "parameters" in variables: - raise click.ClickException( - "{}\n\nsql = {}\nparameters = {}".format( - str(e), variables["sql"], variables["parameters"] - ) - ) - else: - raise - # Apply detected types only to a table this command created - - # transforming a pre-existing table would rewrite its column types - # and corrupt values such as TEXT zip codes with leading zeros - if ( - tracker is not None - and not table_existed_before_insert - and db.table(table).exists() - ): - db.table(table).transform(types=tracker.types) + _insert_docs(docs, tracker=tracker) # Clean up open file-like objects if sniff_buffer: @@ -1249,6 +1357,7 @@ def insert( table, file, pk, + code, flatten, nl, csv, @@ -1275,6 +1384,7 @@ def insert( truncate, not_null, default, + types, strict, ): """ @@ -1293,6 +1403,9 @@ def insert( - Use --lines to write each incoming line to a column called "line" - Use --text to write the entire input to a column called "text" + Use --type column-name type to override the type automatically chosen + when the table is created. + You can also use --convert to pass a fragment of Python code that will be used to convert each input. @@ -1320,6 +1433,17 @@ def insert( \b echo 'A bunch of words' | sqlite-utils insert words.db words - \\ --text --convert '({"word": w} for w in text.split())' + + Instead of a FILE you can use --code to provide a block of Python code + that defines the rows to insert, as either a rows() function that yields + dictionaries or a "rows" iterable. --code can also be a path to a .py file: + + \b + sqlite-utils insert data.db creatures --code ' + def rows(): + yield {"id": 1, "name": "Cleo"} + yield {"id": 2, "name": "Suna"} + ' --pk id """ try: insert_upsert_implementation( @@ -1354,19 +1478,22 @@ def insert( silent=silent, not_null=not_null, default=default, + types=types, strict=strict, + code=code, ) except UnicodeDecodeError as ex: raise click.ClickException(UNICODE_ERROR.format(ex)) @cli.command() -@insert_upsert_options(require_pk=True) +@insert_upsert_options() def upsert( path, table, file, pk, + code, flatten, nl, csv, @@ -1386,6 +1513,7 @@ def upsert( alter, not_null, default, + types, no_detect_types, analyze, load_extension, @@ -1397,6 +1525,11 @@ def upsert( an incoming record has a primary key that matches an existing record the existing record will be updated. + If the table already exists and has a primary key, --pk can be omitted. + + Use --type column-name type to override the type automatically chosen + when the table is created. + Example: \b @@ -1431,11 +1564,13 @@ def upsert( upsert=True, not_null=not_null, default=default, + types=types, no_detect_types=no_detect_types, analyze=analyze, load_extension=load_extension, silent=silent, strict=strict, + code=code, ) except UnicodeDecodeError as ex: raise click.ClickException(UNICODE_ERROR.format(ex)) @@ -1450,11 +1585,7 @@ def upsert( @click.argument("sql") @click.argument("file", type=click.File("rb"), required=True) @click.option("--batch-size", type=int, default=100, help="Commit every X records") -@click.option( - "--functions", - help="Python code or file path defining custom SQL functions", - multiple=True, -) +@functions_option @import_options @load_extension_option def bulk( @@ -1634,10 +1765,10 @@ def create_table( sqlite-utils create-table my.db people \\ id integer \\ name text \\ - height float \\ + height real \\ photo blob --pk id - Valid column types are text, integer, float and blob. + Valid column types are text, integer, real, float, blob and any. """ db = sqlite_utils.Database(path) _register_db_for_cleanup(db) @@ -1653,17 +1784,14 @@ def create_table( ctype = columns.pop(0) if ctype.upper() not in VALID_COLUMN_TYPES: raise click.ClickException( - "column types must be one of {}".format(VALID_COLUMN_TYPES) + f"column types must be one of {VALID_COLUMN_TYPES}" ) coltypes[name] = ctype.upper() # Does table already exist? - if table in db.table_names(): - if not ignore and not replace and not transform: - raise click.ClickException( - 'Table "{}" already exists. Use --replace to delete and replace it.'.format( - table - ) - ) + if table in db.table_names() and not ignore and not replace and not transform: + raise click.ClickException( + f'Table "{table}" already exists. Use --replace to delete and replace it.' + ) db.table(table).create( coltypes, pk=pks[0] if len(pks) == 1 else pks, @@ -1698,7 +1826,7 @@ def duplicate(path, table, new_table, ignore, load_extension): db.table(table).duplicate(new_table) except NoTable: if not ignore: - raise click.ClickException('Table "{}" does not exist'.format(table)) + raise click.ClickException(f'Table "{table}" does not exist') @cli.command(name="rename-table") @@ -1722,9 +1850,7 @@ def rename_table(path, table, new_name, ignore, load_extension): db.rename_table(table, new_name) except sqlite3.OperationalError as ex: if not ignore: - raise click.ClickException( - 'Table "{}" could not be renamed. {}'.format(table, str(ex)) - ) + raise click.ClickException(f'Table "{table}" could not be renamed. {ex!s}') @cli.command(name="drop-table") @@ -1753,10 +1879,10 @@ def drop_table(path, table, ignore, load_extension): # A view exists with this name if not ignore: raise click.ClickException( - '"{}" is a view, not a table - use drop-view to drop it'.format(table) + f'"{table}" is a view, not a table - use drop-view to drop it' ) except OperationalError: - raise click.ClickException('Table "{}" does not exist'.format(table)) + raise click.ClickException(f'Table "{table}" does not exist') @cli.command(name="create-view") @@ -1798,9 +1924,7 @@ def create_view(path, view, select, ignore, replace, load_extension): db.view(view).drop() else: raise click.ClickException( - 'View "{}" already exists. Use --replace to delete and replace it.'.format( - view - ) + f'View "{view}" already exists. Use --replace to delete and replace it.' ) db.create_view(view, select) @@ -1832,9 +1956,9 @@ def drop_view(path, view, ignore, load_extension): return if view in db.table_names(): raise click.ClickException( - '"{}" is a table, not a view - use drop-table to drop it'.format(view) + f'"{view}" is a table, not a view - use drop-table to drop it' ) - raise click.ClickException('View "{}" does not exist'.format(view)) + raise click.ClickException(f'View "{view}" does not exist') @cli.command() @@ -1860,11 +1984,7 @@ def drop_view(path, view, ignore, load_extension): type=(str, str), help="Named :parameters for SQL query", ) -@click.option( - "--functions", - help="Python code or file path defining custom SQL functions", - multiple=True, -) +@functions_option @load_extension_option def query( path, @@ -1893,7 +2013,15 @@ def query( sqlite-utils data.db \\ "select * from chickens where age > :age" \\ -p age 1 + + Pass "-" as the SQL to read the query from standard input: + + \b + echo "select * from chickens" | sqlite-utils data.db - """ + if sql == "-": + # Read SQL from standard input + sql = sys.stdin.read() db = sqlite_utils.Database(path) _register_db_for_cleanup(db) for alias, attach_path in attach: @@ -1929,11 +2057,7 @@ def query( nargs=-1, ) @click.argument("sql") -@click.option( - "--functions", - help="Python code or file path defining custom SQL functions", - multiple=True, -) +@functions_option @click.option( "--attach", type=(str, click.Path(file_okay=True, dir_okay=False, allow_dash=False)), @@ -2056,7 +2180,7 @@ def memory( file_path = pathlib.Path(path) stem = file_path.stem if stem_counts.get(stem): - file_table = "{}_{}".format(stem, stem_counts[stem]) + file_table = f"{stem}_{stem_counts[stem]}" else: file_table = stem stem_counts[stem] = stem_counts.get(stem, 1) + 1 @@ -2075,14 +2199,14 @@ def memory( if tracker is not None and db.table(file_table).exists(): db.table(file_table).transform(types=tracker.types) # Add convenient t / t1 / t2 views - view_names = ["t{}".format(i + 1)] + view_names = [f"t{i + 1}"] if i == 0: view_names.append("t") for view_name in view_names: if not db[view_name].exists(): db.create_view( view_name, - "select * from {}".format(quote_identifier(file_table)), + f"select * from {quote_identifier(file_table)}", ) finally: if should_close_fp and fp: @@ -2252,19 +2376,17 @@ def search( # Check table exists table_obj = db.table(dbtable) if not table_obj.exists(): - raise click.ClickException("Table '{}' does not exist".format(dbtable)) + raise click.ClickException(f"Table '{dbtable}' does not exist") if not table_obj.detect_fts(): raise click.ClickException( - "Table '{}' is not configured for full-text search".format(dbtable) + f"Table '{dbtable}' is not configured for full-text search" ) if column: # Check they all exist table_columns = table_obj.columns_dict for c in column: if c not in table_columns: - raise click.ClickException( - "Table '{}' has no column '{}".format(dbtable, c) - ) + raise click.ClickException(f"Table '{dbtable}' has no column '{c}") sql = table_obj.search_sql(columns=column, order_by=order, limit=limit) if show_sql: click.echo(sql) @@ -2291,7 +2413,7 @@ def search( except click.ClickException as e: if "malformed MATCH expression" in str(e) or "unterminated string" in str(e): raise click.ClickException( - "{}\n\nTry running this again with the --quote option".format(str(e)) + f"{e!s}\n\nTry running this again with the --quote option" ) else: raise @@ -2358,15 +2480,17 @@ def rows( columns = "*" if column: columns = ", ".join(quote_identifier(c) for c in column) - sql = "select {} from {}".format(columns, quote_identifier(dbtable)) + sql = f"select {columns} from {quote_identifier(dbtable)}" if where: sql += " where " + where if order: sql += " order by " + order if limit: - sql += " limit {}".format(limit) + sql += f" limit {limit}" if offset: - sql += " offset {}".format(offset) + if not limit: + sql += " limit -1" + sql += f" offset {offset}" ctx.invoke( query, path=path, @@ -2554,12 +2678,10 @@ def schema( "--type", type=( str, - click.Choice( - ["INTEGER", "TEXT", "FLOAT", "REAL", "BLOB"], case_sensitive=False - ), + click.Choice(list(VALID_COLUMN_TYPES), case_sensitive=False), ), multiple=True, - help="Change column type to INTEGER, TEXT, FLOAT, REAL or BLOB", + help="Change column type to INTEGER, TEXT, FLOAT, REAL, BLOB or ANY", ) @click.option("--drop", type=str, multiple=True, help="Drop this column") @click.option( @@ -2597,6 +2719,11 @@ def schema( multiple=True, help="Drop foreign key constraint for this column", ) +@click.option( + "--strict/--no-strict", + default=None, + help="Enable or disable STRICT mode (default: preserve current mode)", +) @click.option("--sql", is_flag=True, help="Output SQL without executing it") @load_extension_option def transform( @@ -2614,6 +2741,7 @@ def transform( default_none, add_foreign_keys, drop_foreign_keys, + strict, sql, load_extension, ): @@ -2633,7 +2761,7 @@ def transform( for column, ctype in type: if ctype.upper() not in VALID_COLUMN_TYPES: raise click.ClickException( - "column types must be one of {}".format(VALID_COLUMN_TYPES) + f"column types must be one of {VALID_COLUMN_TYPES}" ) types[column] = ctype.upper() @@ -2675,6 +2803,7 @@ def transform( defaults=default_dict, drop_foreign_keys=drop_foreign_keys_value, add_foreign_keys=add_foreign_keys_value, + strict=strict, ): click.echo(line) else: @@ -2688,6 +2817,7 @@ def transform( defaults=default_dict, drop_foreign_keys=drop_foreign_keys_value, add_foreign_keys=add_foreign_keys_value, + strict=strict, ) @@ -2729,12 +2859,12 @@ def extract( db = sqlite_utils.Database(path) _register_db_for_cleanup(db) _load_extensions(db, load_extension) - kwargs: dict[str, Any] = dict( - columns=columns, - table=other_table, - fk_column=fk_column, - rename=dict(rename), - ) + kwargs: dict[str, Any] = { + "columns": columns, + "table": other_table, + "fk_column": fk_column, + "rename": dict(rename), + } try: db.table(table).extract(**kwargs) except (NoTable, InvalidColumns) as e: @@ -2829,7 +2959,7 @@ def insert_files( with progressbar(paths_and_relative_paths, silent=silent) as bar: def to_insert(): - for path, relative_path in bar: + for file_path, relative_path in bar: row = {} # content_text is special case as it considers 'encoding' @@ -2841,19 +2971,21 @@ def insert_files( raise UnicodeDecodeErrorForPath(e, resolved) lookups = dict(FILE_COLUMNS, content_text=_content_text) - if path == "-": + if file_path == "-": stdin_data = sys.stdin.buffer.read() # We only support a subset of columns for this case lookups = { "name": lambda p: name or "-", "path": lambda p: name or "-", - "content": lambda p: stdin_data, - "content_text": lambda p: stdin_data.decode( + "content": lambda p, data=stdin_data: data, + "content_text": lambda p, data=stdin_data: data.decode( encoding or "utf-8" ), - "sha256": lambda p: hashlib.sha256(stdin_data).hexdigest(), - "md5": lambda p: hashlib.md5(stdin_data).hexdigest(), - "size": lambda p: len(stdin_data), + "sha256": lambda p, data=stdin_data: hashlib.sha256( + data + ).hexdigest(), + "md5": lambda p, data=stdin_data: hashlib.md5(data).hexdigest(), + "size": lambda p, data=stdin_data: len(data), } for coldef in column: if ":" in coldef: @@ -2861,7 +2993,7 @@ def insert_files( else: colname, coltype = coldef, coldef try: - value = lookups[coltype](path) + value = lookups[coltype](file_path) row[colname] = value except KeyError: raise click.ClickException( @@ -2889,7 +3021,7 @@ def insert_files( except UnicodeDecodeErrorForPath as e: raise click.ClickException( UNICODE_ERROR.format( - "Could not read file '{}' as text\n\n{}".format(e.path, e.exception) + f"Could not read file '{e.path}' as text\n\n{e.exception}" ) ) @@ -3047,6 +3179,12 @@ def _generate_convert_help(): "value" is a variable with the column value to be converted. + CODE can also be a reference to a callable that takes the value, for example: + + \b + sqlite-utils convert my.db mytable date r.parsedate + sqlite-utils convert my.db mytable data json.loads --import json + Use "-" for CODE to read Python code from standard input. The following common operations are available as recipe functions: @@ -3060,9 +3198,8 @@ def _generate_convert_help(): ] for name in recipe_names: fn = getattr(recipes, name) - help += "\n\nr.{}{}\n\n\b{}".format( - name, str(inspect.signature(fn)), textwrap.dedent(fn.__doc__.rstrip()) - ) + doc = textwrap.dedent(fn.__doc__.rstrip()).replace("\b\n", "") + help += f"\n\nr.{name}{inspect.signature(fn)!s}\n\n\b{doc}" help += "\n\n" help += textwrap.dedent(""" You can use these recipes like so: @@ -3146,26 +3283,21 @@ def convert( raise click.ClickException(str(e)) if dry_run: # Pull first 20 values for first column and preview them - if multi: - - def preview(v): + def preview(v): + if multi: return json.dumps(fn(v), default=repr, ensure_ascii=False) if v else v - - else: - - def preview(v): - return fn(v) if v else v + return fn(v) if v else v db.conn.create_function("preview_transform", 1, preview) sql = """ select - [{column}] as value, - preview_transform([{column}]) as preview - from [{table}]{where} limit 10 + {column} as value, + preview_transform({column}) as preview + from {table}{where} limit 10 """.format( - column=columns[0], - table=table, - where=" where {}".format(where) if where is not None else "", + column=quote_identifier(columns[0]), + table=quote_identifier(table), + where=f" where {where}" if where is not None else "", ) for row in db.conn.execute(sql, where_args).fetchall(): click.echo(str(row[0])) @@ -3185,7 +3317,7 @@ def convert( def wrapped_fn(value): try: return fn_(value) - except Exception as ex: + except Exception as ex: # noqa: BLE001 print("\nException raised, dropping into pdb...:", ex) pdb.post_mortem(ex.__traceback__) sys.exit(1) @@ -3205,9 +3337,7 @@ def convert( ) except BadMultiValues as e: raise click.ClickException( - "When using --multi code must return a Python dictionary - returned: {}".format( - repr(e.values) - ) + f"When using --multi code must return a Python dictionary - returned: {e.values!r}" ) @@ -3325,7 +3455,7 @@ def create_spatial_index(db_path, table, column_name, load_extension): def _find_migration_files(migrations): if not migrations: - migrations = [pathlib.Path(".").resolve()] + migrations = [pathlib.Path.cwd()] files = set() for path_str in migrations: path = pathlib.Path(path_str) @@ -3350,7 +3480,7 @@ def _load_migration_sets(files): "__file__": str(filepath), "__name__": "__sqlite_utils_migration__", } - exec(code, namespace) + exec(code, namespace) # noqa: S102 migration_sets.extend( obj for obj in namespace.values() if _compatible_migration_set(obj) ) @@ -3359,17 +3489,17 @@ def _load_migration_sets(files): def _display_migration_list(db, migration_sets): for migration_set in migration_sets: - click.echo("Migrations for: {}".format(migration_set.name)) + click.echo(f"Migrations for: {migration_set.name}") click.echo() click.echo(" Applied:") for migration in migration_set.applied(db): - click.echo(" {} - {}".format(migration.name, migration.applied_at)) + click.echo(f" {migration.name} - {migration.applied_at}") click.echo() click.echo(" Pending:") output = False for migration in migration_set.pending(db): output = True - click.echo(" {}".format(migration.name)) + click.echo(f" {migration.name}") if not output: click.echo(" (none)") click.echo() @@ -3449,7 +3579,7 @@ def migrate(db_path, migrations, stop_before, list_, verbose): prev_schema = db.schema if verbose: - click.echo("Migrating {}".format(db_path)) + click.echo(f"Migrating {db_path}") click.echo("\nSchema before:\n") click.echo(textwrap.indent(prev_schema, " ") or " (empty)") click.echo() @@ -3460,9 +3590,7 @@ def migrate(db_path, migrations, stop_before, list_, verbose): names = {m.name for m in migration_set.pending(db)} names.update(m.name for m in migration_set.applied(db)) known_names.update(names) - known_names.update( - "{}:{}".format(migration_set.name, name) for name in names - ) + known_names.update(f"{migration_set.name}:{name}" for name in names) unknown = [value for value in stop_before if value not in known_names] if unknown: raise click.ClickException( @@ -3518,7 +3646,7 @@ def _render_common(title, values): return "" lines = [title] for value, count in values: - lines.append(" {}: {}".format(count, value)) + lines.append(f" {count}: {value}") return "\n".join(lines) @@ -3588,7 +3716,7 @@ def maybe_json(value): if not isinstance(value, str): return value stripped = value.strip() - if not (stripped.startswith("{") or stripped.startswith("[")): + if not (stripped.startswith(("{", "["))): return value try: return json.loads(stripped) @@ -3606,7 +3734,7 @@ def json_binary(value): def verify_is_dict(doc): if not isinstance(doc, dict): raise click.ClickException( - "Rows must all be dictionaries, got: {}".format(repr(doc)[:1000]) + f"Rows must all be dictionaries, got: {repr(doc)[:1000]}" ) return doc @@ -3634,14 +3762,14 @@ def _register_functions(db, functions): try: functions = pathlib.Path(functions).read_text() except FileNotFoundError: - raise click.ClickException("File not found: {}".format(functions)) + raise click.ClickException(f"File not found: {functions}") sqlite3.enable_callback_tracebacks(True) globals = {} try: - exec(functions, globals) + exec(functions, globals) # noqa: S102 except SyntaxError as ex: - raise click.ClickException("Error in functions definition: {}".format(ex)) + raise click.ClickException(f"Error in functions definition: {ex}") # Register all callables in the locals dict: for name, value in globals.items(): if callable(value) and not name.startswith("_"): @@ -3654,3 +3782,32 @@ def _maybe_register_functions(db, functions_list): for functions in functions_list: if isinstance(functions, str) and functions.strip(): _register_functions(db, functions) + + +def _rows_from_code(code): + # code may be a path to a .py file + if "\n" not in code and code.endswith(".py"): + try: + code = pathlib.Path(code).read_text() + except FileNotFoundError: + raise click.ClickException(f"File not found: {code}") + namespace: dict[str, Any] = {} + try: + exec(code, namespace) # noqa: S102 + except SyntaxError as ex: + raise click.ClickException(f"Error in --code: {ex}") + rows: Any = namespace.get("rows") + if callable(rows): + rows = rows() + if isinstance(rows, dict): + rows = [rows] + error = click.ClickException( + "--code must define a 'rows' function or iterable of rows to insert" + ) + if rows is None or isinstance(rows, (str, bytes)): + raise error + try: + iter(rows) + except TypeError: + raise error + return rows diff --git a/sqlite_utils/create_table_parser.py b/sqlite_utils/create_table_parser.py new file mode 100644 index 0000000..7377f4f --- /dev/null +++ b/sqlite_utils/create_table_parser.py @@ -0,0 +1,897 @@ +"""Helpers for parsing constraints from SQLite CREATE TABLE SQL. + +SQLite does not expose CHECK constraints through a pragma, so preserving them +across a table rebuild requires reading ``sqlite_schema.sql``. This module is +deliberately small, but it uses a real lexer: strings, quoted identifiers and +comments are opaque, every token retains its source span and malformed input is +reported instead of being silently under-parsed. +""" + +import re +from dataclasses import dataclass, field +from typing import Any + + +@dataclass +class Check: + check: str + name: str = "" + column: str = "" + options: list[Any] | None = None + # Source details are excluded from equality and repr so callers can compare + # semantic constraints while still having the original SQL available for + # diagnostics or future lossless edits. + sql: str = field(default="", compare=False, repr=False) + start: int = field(default=-1, compare=False, repr=False) + end: int = field(default=-1, compare=False, repr=False) + + +@dataclass(frozen=True) +class ColumnComments: + before: str = "" + after: str = "" + + +@dataclass(frozen=True) +class UniqueColumn: + name: str + collation: str = "" + order: str = "" + + +@dataclass +class Unique: + columns: tuple[UniqueColumn, ...] + name: str = "" + column: str = "" + conflict: str = "" + sql: str = field(default="", compare=False, repr=False) + start: int = field(default=-1, compare=False, repr=False) + end: int = field(default=-1, compare=False, repr=False) + + +class ParseError(ValueError): + pass + + +@dataclass(frozen=True) +class _Token: + kind: str + text: str + start: int + end: int + + def is_keyword(self, keyword: str) -> bool: + return self.kind == "word" and self.text.upper() == keyword + + +_PUNCTUATION = frozenset("(),.;+-*/%<>=!~|&?:") +_TRIVIA = frozenset(("whitespace", "comment")) +_TABLE_CONSTRAINT_KEYWORDS = frozenset(("PRIMARY", "UNIQUE", "CHECK", "FOREIGN")) +_OTHER_COLUMN_CONSTRAINT_KEYWORDS = frozenset( + ("PRIMARY", "UNIQUE", "REFERENCES", "DEFAULT", "NOT", "COLLATE", "GENERATED") +) +_SQLITE_KEYWORDS = frozenset( + ( + "ABORT", + "ACTION", + "ADD", + "AFTER", + "ALL", + "ALTER", + "ANALYZE", + "AND", + "AS", + "ASC", + "ATTACH", + "AUTOINCREMENT", + "BEFORE", + "BEGIN", + "BETWEEN", + "BY", + "CASCADE", + "CASE", + "CAST", + "CHECK", + "COLLATE", + "COLUMN", + "COMMIT", + "CONFLICT", + "CONSTRAINT", + "CREATE", + "CROSS", + "CURRENT_DATE", + "CURRENT_TIME", + "CURRENT_TIMESTAMP", + "DATABASE", + "DEFAULT", + "DEFERRABLE", + "DEFERRED", + "DELETE", + "DESC", + "DETACH", + "DISTINCT", + "DO", + "DROP", + "EACH", + "ELSE", + "END", + "ESCAPE", + "EXCEPT", + "EXCLUDE", + "EXCLUSIVE", + "EXISTS", + "EXPLAIN", + "FAIL", + "FALSE", + "FILTER", + "FIRST", + "FOLLOWING", + "FOR", + "FOREIGN", + "FROM", + "FULL", + "GENERATED", + "GLOB", + "GROUP", + "GROUPS", + "HAVING", + "IF", + "IGNORE", + "IMMEDIATE", + "IN", + "INDEX", + "INDEXED", + "INITIALLY", + "INNER", + "INSERT", + "INSTEAD", + "INTERSECT", + "INTO", + "IS", + "ISNULL", + "JOIN", + "KEY", + "LAST", + "LEFT", + "LIKE", + "LIMIT", + "MATCH", + "MATERIALIZED", + "NATURAL", + "NO", + "NOT", + "NOTHING", + "NOTNULL", + "NULL", + "NULLS", + "OF", + "OFFSET", + "ON", + "OR", + "ORDER", + "OTHERS", + "OUTER", + "OVER", + "PARTITION", + "PLAN", + "PRAGMA", + "PRECEDING", + "PRIMARY", + "QUERY", + "RAISE", + "RANGE", + "RECURSIVE", + "REFERENCES", + "REGEXP", + "REINDEX", + "RELEASE", + "RENAME", + "REPLACE", + "RESTRICT", + "RETURNING", + "RIGHT", + "ROLLBACK", + "ROW", + "ROWS", + "SAVEPOINT", + "SELECT", + "SET", + "STRICT", + "TABLE", + "TEMP", + "TEMPORARY", + "THEN", + "TIES", + "TO", + "TRANSACTION", + "TRIGGER", + "TRUE", + "UNBOUNDED", + "UNION", + "UNIQUE", + "UPDATE", + "USING", + "VACUUM", + "VALUES", + "VIEW", + "VIRTUAL", + "WHEN", + "WHERE", + "WINDOW", + "WITH", + "WITHOUT", + ) +) +_INTEGER_RE = re.compile(r"[+-]?(?:0[xX][0-9a-fA-F]+|[0-9]+)\Z") +_FLOAT_RE = re.compile( + r"[+-]?(?:(?:[0-9]+\.[0-9]*|\.[0-9]+)(?:[eE][+-]?[0-9]+)?|" + r"[0-9]+[eE][+-]?[0-9]+)\Z" +) + + +def _lex(sql: str) -> list[_Token]: + tokens: list[_Token] = [] + i = 0 + while i < len(sql): + start = i + char = sql[i] + if char.isspace(): + i += 1 + while i < len(sql) and sql[i].isspace(): + i += 1 + tokens.append(_Token("whitespace", sql[start:i], start, i)) + continue + if sql.startswith("--", i): + newline = sql.find("\n", i + 2) + i = len(sql) if newline == -1 else newline + 1 + tokens.append(_Token("comment", sql[start:i], start, i)) + continue + if sql.startswith("/*", i): + end = sql.find("*/", i + 2) + if end == -1: + raise ParseError("Unterminated SQL comment") + i = end + 2 + tokens.append(_Token("comment", sql[start:i], start, i)) + continue + if char in ("'", '"', "`"): + quote = char + i += 1 + while i < len(sql): + if sql[i] == quote: + if i + 1 < len(sql) and sql[i + 1] == quote: + i += 2 + continue + i += 1 + break + i += 1 + else: + raise ParseError(f"Unterminated {quote} quoted token") + kind = "string" if quote == "'" else "identifier" + tokens.append(_Token(kind, sql[start:i], start, i)) + continue + if char == "[": + end = sql.find("]", i + 1) + if end == -1: + raise ParseError("Unterminated [ quoted identifier") + i = end + 1 + tokens.append(_Token("identifier", sql[start:i], start, i)) + continue + if char in _PUNCTUATION: + i += 1 + tokens.append(_Token("punct", char, start, i)) + continue + # SQLite accepts any character >= U+0080 in a bare identifier. More + # generally, consume until a lexical delimiter rather than relying on + # Python's narrower definition of an alphanumeric character. + i += 1 + while i < len(sql): + if sql[i].isspace() or sql[i] in _PUNCTUATION or sql[i] in "'\"`[": + break + i += 1 + tokens.append(_Token("word", sql[start:i], start, i)) + return tokens + + +def _meaningful(tokens: list[_Token]) -> list[_Token]: + return [token for token in tokens if token.kind not in _TRIVIA] + + +def _unquote(token: str) -> str: + if len(token) >= 2 and token[0] in ("'", '"', "`") and token[-1] == token[0]: + return token[1:-1].replace(token[0] * 2, token[0]) + if len(token) >= 2 and token[0] == "[" and token[-1] == "]": + return token[1:-1] + return token + + +def _matching_paren(tokens: list[_Token], open_index: int) -> int: + if tokens[open_index].text != "(": + raise ParseError("Expected an opening parenthesis") + depth = 0 + for index in range(open_index, len(tokens)): + if tokens[index].text == "(": + depth += 1 + elif tokens[index].text == ")": + depth -= 1 + if depth == 0: + return index + raise ParseError("Unbalanced parentheses") + + +def _split_spans(sql: str, tokens: list[_Token]) -> list[tuple[str, int, int]]: + if not tokens: + return [] + items: list[tuple[str, int, int]] = [] + depth = 0 + start = tokens[0].start + for token in tokens: + if token.text == "(": + depth += 1 + elif token.text == ")": + depth -= 1 + if depth < 0: + raise ParseError("Unbalanced parentheses") + elif token.text == "," and depth == 0: + raw = sql[start : token.start] + item = raw.strip() + if item: + item_start = start + len(raw) - len(raw.lstrip()) + items.append((item, item_start, item_start + len(item))) + start = token.end + if depth: + raise ParseError("Unbalanced parentheses") + raw = sql[start : tokens[-1].end] + item = raw.strip() + if item: + item_start = start + len(raw) - len(raw.lstrip()) + items.append((item, item_start, item_start + len(item))) + return items + + +def _split_ranges(sql: str, tokens: list[_Token]) -> list[str]: + return [item for item, _, _ in _split_spans(sql, tokens)] + + +def _strip_outer_parens(tokens: list[_Token]) -> list[_Token]: + while tokens and tokens[0].text == "(": + close = _matching_paren(tokens, 0) + if close != len(tokens) - 1: + break + tokens = tokens[1:-1] + return tokens + + +_NO_LITERAL = object() + + +def _literal_value(text: str) -> Any: + tokens = _meaningful(_lex(text)) + if len(tokens) == 1 and tokens[0].kind == "string": + return _unquote(tokens[0].text) + raw = "".join(token.text for token in tokens) + if raw.upper() == "NULL": + return None + if raw.upper() == "TRUE": + return True + if raw.upper() == "FALSE": + return False + if _INTEGER_RE.fullmatch(raw): + try: + return ( + int(raw, 16) if raw.lower().lstrip("+-").startswith("0x") else int(raw) + ) + except ValueError: + return _NO_LITERAL + if _FLOAT_RE.fullmatch(raw): + try: + return float(raw) + except ValueError: + return _NO_LITERAL + return _NO_LITERAL + + +def _ascii_fold(identifier: str) -> str: + return identifier.translate( + str.maketrans("ABCDEFGHIJKLMNOPQRSTUVWXYZ", "abcdefghijklmnopqrstuvwxyz") + ) + + +def _parse_options(expression: str, column: str) -> list[Any] | None: + tokens = _strip_outer_parens(_meaningful(_lex(expression))) + if len(tokens) < 4: + return None + lhs = tokens[0] + if lhs.kind not in ("word", "identifier"): + return None + if column and _ascii_fold(_unquote(lhs.text)) != _ascii_fold(column): + return None + if not tokens[1].is_keyword("IN") or tokens[2].text != "(": + return None + close = _matching_paren(tokens, 2) + if close != len(tokens) - 1: + return None + inner = expression[tokens[2].end : tokens[close].start] + inner_tokens = _lex(inner) + if not _meaningful(inner_tokens): + return [] + values = [] + for item in _split_ranges(inner, inner_tokens): + value = _literal_value(item) + if value is _NO_LITERAL: + return None + values.append(value) + return values + + +def _check_after( + item: str, + tokens: list[_Token], + check_index: int, + name: str, + column: str, + constraint_start: int, + base_offset: int, +) -> tuple[Check, int]: + if check_index + 1 >= len(tokens) or tokens[check_index + 1].text != "(": + raise ParseError("CHECK must be followed by a parenthesized expression") + close = _matching_paren(tokens, check_index + 1) + expression = item[tokens[check_index + 1].end : tokens[close].start].strip() + source_start = tokens[constraint_start].start + source_end = tokens[close].end + return ( + Check( + expression, + name=name, + column=column, + options=_parse_options(expression, column), + sql=item[source_start:source_end], + start=base_offset + source_start, + end=base_offset + source_end, + ), + close + 1, + ) + + +def _column_checks( + item: str, tokens: list[_Token], column: str, base_offset: int +) -> list[Check]: + checks: list[Check] = [] + pending_name = "" + pending_start: int | None = None + index = 1 + while index < len(tokens): + token = tokens[index] + if token.text == "(": + index = _matching_paren(tokens, index) + 1 + continue + if token.is_keyword("CONSTRAINT"): + if index + 1 >= len(tokens): + raise ParseError("CONSTRAINT is missing its name") + pending_name = _unquote(tokens[index + 1].text) + pending_start = index + index += 2 + continue + if token.is_keyword("CHECK"): + check, index = _check_after( + item, + tokens, + index, + pending_name, + column, + pending_start if pending_start is not None else index, + base_offset, + ) + checks.append(check) + pending_name = "" + pending_start = None + continue + if ( + token.kind == "word" + and token.text.upper() in _OTHER_COLUMN_CONSTRAINT_KEYWORDS + ): + pending_name = "" + pending_start = None + index += 1 + return checks + + +def _table_body(create_sql: str) -> tuple[str, int] | None: + all_tokens = _lex(create_sql) + tokens = _meaningful(all_tokens) + if not tokens or not tokens[0].is_keyword("CREATE"): + raise ParseError("Expected CREATE TABLE") + index = 1 + if index < len(tokens) and ( + tokens[index].is_keyword("TEMP") or tokens[index].is_keyword("TEMPORARY") + ): + index += 1 + if index < len(tokens) and tokens[index].is_keyword("VIRTUAL"): + return None + if index >= len(tokens) or not tokens[index].is_keyword("TABLE"): + raise ParseError("Expected CREATE TABLE") + index += 1 + if ( + index + 2 < len(tokens) + and tokens[index].is_keyword("IF") + and tokens[index + 1].is_keyword("NOT") + and tokens[index + 2].is_keyword("EXISTS") + ): + index += 3 + if index >= len(tokens): + raise ParseError("CREATE TABLE is missing its table name") + index += 1 + if index + 1 < len(tokens) and tokens[index].text == ".": + index += 2 + if index < len(tokens) and tokens[index].is_keyword("AS"): + return None + if index >= len(tokens) or tokens[index].text != "(": + raise ParseError("CREATE TABLE is missing its column list") + close = _matching_paren(tokens, index) + trailing = tokens[close + 1 :] + allowed_trailing = {"STRICT", "WITHOUT", "ROWID", ",", ";"} + if any(token.text.upper() not in allowed_trailing for token in trailing): + raise ParseError("Unexpected SQL after CREATE TABLE column list") + + body_start = tokens[index].end + body_end = tokens[close].start + return create_sql[body_start:body_end], body_start + + +def parse_checks(create_sql: str) -> list[Check]: + """Return CHECK constraints from a valid SQLite CREATE TABLE statement.""" + body_info = _table_body(create_sql) + if body_info is None: + return [] + body, body_start = body_info + body_tokens = _lex(body) + checks: list[Check] = [] + for item, item_start, _ in _split_spans(body, body_tokens): + item_tokens = _meaningful(_lex(item)) + if not item_tokens: + continue + item_index = 0 + constraint_name = "" + if item_tokens[item_index].is_keyword("CONSTRAINT"): + if len(item_tokens) < 2: + raise ParseError("CONSTRAINT is missing its name") + constraint_name = _unquote(item_tokens[1].text) + item_index = 2 + head = item_tokens[item_index] if item_index < len(item_tokens) else None + if ( + head + and head.kind == "word" + and head.text.upper() in _TABLE_CONSTRAINT_KEYWORDS + ): + if head.is_keyword("CHECK"): + check, _ = _check_after( + item, + item_tokens, + item_index, + constraint_name, + "", + 0, + body_start + item_start, + ) + checks.append(check) + continue + column = _unquote(item_tokens[0].text) + checks.extend( + _column_checks(item, item_tokens, column, body_start + item_start) + ) + return checks + + +def parse_autoincrement(create_sql: str) -> str | None: + """Return the AUTOINCREMENT column from a valid CREATE TABLE statement.""" + body_info = _table_body(create_sql) + if body_info is None: + return None + body, _ = body_info + for item, _, _ in _split_spans(body, _lex(body)): + item_tokens = _meaningful(_lex(item)) + if not item_tokens: + continue + head = item_tokens[0] + if ( + head.kind == "word" and head.text.upper() in _TABLE_CONSTRAINT_KEYWORDS + ) or head.is_keyword("CONSTRAINT"): + continue + column = _unquote(head.text) + index = 1 + while index < len(item_tokens): + token = item_tokens[index] + if token.text == "(": + index = _matching_paren(item_tokens, index) + 1 + continue + if token.is_keyword("AUTOINCREMENT"): + return column + index += 1 + return None + + +_CONFLICT_ACTIONS = frozenset(("ROLLBACK", "ABORT", "FAIL", "IGNORE", "REPLACE")) + + +def _conflict_after(tokens: list[_Token], index: int) -> tuple[str, int]: + if index >= len(tokens) or not tokens[index].is_keyword("ON"): + return "", index + if index + 2 >= len(tokens) or not tokens[index + 1].is_keyword("CONFLICT"): + raise ParseError("ON after UNIQUE must be followed by CONFLICT and an action") + action = tokens[index + 2].text.upper() + if tokens[index + 2].kind != "word" or action not in _CONFLICT_ACTIONS: + raise ParseError("Invalid UNIQUE ON CONFLICT action") + return action, index + 3 + + +def _unique_columns( + item: str, tokens: list[_Token], open_index: int +) -> tuple[tuple[UniqueColumn, ...], int]: + close = _matching_paren(tokens, open_index) + inner = item[tokens[open_index].end : tokens[close].start] + columns: list[UniqueColumn] = [] + for raw_column in _split_ranges(inner, _lex(inner)): + column_tokens = _meaningful(_lex(raw_column)) + if not column_tokens or column_tokens[0].kind not in ( + "word", + "identifier", + "string", + ): + raise ParseError("UNIQUE constraint has an invalid column") + name = _unquote(column_tokens[0].text) + collation = "" + order = "" + index = 1 + if index < len(column_tokens) and column_tokens[index].is_keyword("COLLATE"): + if index + 1 >= len(column_tokens): + raise ParseError("COLLATE in UNIQUE constraint is missing its name") + collation = _unquote(column_tokens[index + 1].text) + index += 2 + if index < len(column_tokens) and ( + column_tokens[index].is_keyword("ASC") + or column_tokens[index].is_keyword("DESC") + ): + order = column_tokens[index].text.upper() + index += 1 + if index != len(column_tokens): + raise ParseError("UNIQUE constraint has an invalid indexed column") + columns.append(UniqueColumn(name, collation=collation, order=order)) + if not columns: + raise ParseError("UNIQUE constraint must include at least one column") + return tuple(columns), close + 1 + + +def _column_uniques( + item: str, tokens: list[_Token], column: str, base_offset: int +) -> list[Unique]: + uniques: list[Unique] = [] + collation = "" + collation_index = 1 + while collation_index < len(tokens): + token = tokens[collation_index] + if token.text == "(": + collation_index = _matching_paren(tokens, collation_index) + 1 + continue + if token.is_keyword("COLLATE"): + if collation_index + 1 >= len(tokens): + raise ParseError("COLLATE is missing its name") + collation = _unquote(tokens[collation_index + 1].text) + collation_index += 2 + continue + collation_index += 1 + pending_name = "" + pending_start: int | None = None + index = 1 + while index < len(tokens): + token = tokens[index] + if token.text == "(": + index = _matching_paren(tokens, index) + 1 + continue + if token.is_keyword("CONSTRAINT"): + if index + 1 >= len(tokens): + raise ParseError("CONSTRAINT is missing its name") + pending_name = _unquote(tokens[index + 1].text) + pending_start = index + index += 2 + continue + if token.is_keyword("UNIQUE"): + source_start = tokens[ + pending_start if pending_start is not None else index + ].start + conflict, next_index = _conflict_after(tokens, index + 1) + source_end = tokens[next_index - 1].end + uniques.append( + Unique( + (UniqueColumn(column, collation=collation),), + name=pending_name, + column=column, + conflict=conflict, + sql=item[source_start:source_end], + start=base_offset + source_start, + end=base_offset + source_end, + ) + ) + pending_name = "" + pending_start = None + index = next_index + continue + if ( + token.kind == "word" + and token.text.upper() in _OTHER_COLUMN_CONSTRAINT_KEYWORDS + ): + pending_name = "" + pending_start = None + index += 1 + return uniques + + +def parse_uniques(create_sql: str) -> list[Unique]: + """Return column-level and table-level UNIQUE constraints.""" + body_info = _table_body(create_sql) + if body_info is None: + return [] + body, body_start = body_info + uniques: list[Unique] = [] + for item, item_start, _ in _split_spans(body, _lex(body)): + item_tokens = _meaningful(_lex(item)) + if not item_tokens: + continue + item_index = 0 + constraint_name = "" + if item_tokens[item_index].is_keyword("CONSTRAINT"): + if len(item_tokens) < 2: + raise ParseError("CONSTRAINT is missing its name") + constraint_name = _unquote(item_tokens[1].text) + item_index = 2 + head = item_tokens[item_index] if item_index < len(item_tokens) else None + if head and head.is_keyword("UNIQUE"): + if ( + item_index + 1 >= len(item_tokens) + or item_tokens[item_index + 1].text != "(" + ): + raise ParseError("Table UNIQUE must be followed by a column list") + columns, next_index = _unique_columns(item, item_tokens, item_index + 1) + conflict, next_index = _conflict_after(item_tokens, next_index) + if next_index != len(item_tokens): + raise ParseError("Unexpected SQL after UNIQUE constraint") + source_start = item_tokens[0].start + source_end = item_tokens[next_index - 1].end + uniques.append( + Unique( + columns, + name=constraint_name, + conflict=conflict, + sql=item[source_start:source_end], + start=body_start + item_start + source_start, + end=body_start + item_start + source_end, + ) + ) + continue + if ( + head + and head.kind == "word" + and head.text.upper() in _TABLE_CONSTRAINT_KEYWORDS + ): + continue + column = _unquote(item_tokens[0].text) + uniques.extend( + _column_uniques( + item, + item_tokens, + column, + body_start + item_start, + ) + ) + return uniques + + +def parse_column_comments(create_sql: str) -> dict[str, ColumnComments]: + """Return comments immediately before and after each column definition.""" + body_info = _table_body(create_sql) + if body_info is None: + return {} + body, _ = body_info + comments: dict[str, ColumnComments] = {} + for item, _, _ in _split_spans(body, _lex(body)): + item_tokens = _meaningful(_lex(item)) + if not item_tokens: + continue + item_index = 0 + if item_tokens[item_index].is_keyword("CONSTRAINT"): + item_index = 2 + head = item_tokens[item_index] if item_index < len(item_tokens) else None + if ( + head + and head.kind == "word" + and head.text.upper() in _TABLE_CONSTRAINT_KEYWORDS + ): + continue + column = _unquote(item_tokens[0].text) + before = item[: item_tokens[0].start].strip() + after = item[item_tokens[-1].end :].strip() + if before or after: + comments[column] = ColumnComments(before=before, after=after) + return comments + + +def _is_identifier_token(tokens: list[_Token], index: int) -> bool: + token = tokens[index] + if index + 1 < len(tokens) and tokens[index + 1].text in ("(", "."): + return False + if index and ( + tokens[index - 1].is_keyword("COLLATE") or tokens[index - 1].is_keyword("AS") + ): + return False + if token.kind == "identifier": + return True + if token.kind != "word" or token.text.upper() in _SQLITE_KEYWORDS: + return False + return True + + +def check_references_identifier(expression: str, identifier: str) -> bool: + tokens = _meaningful(_lex(expression)) + folded = _ascii_fold(identifier) + return any( + _is_identifier_token(tokens, index) + and _ascii_fold(_unquote(token.text)) == folded + for index, token in enumerate(tokens) + ) + + +def sql_ends_in_line_comment(sql: str) -> bool: + """Return True if appended SQL would be swallowed by a ``--`` comment.""" + tokens = _lex(sql) + if not tokens: + return False + final = tokens[-1] + return ( + final.kind == "comment" + and final.text.startswith("--") + and not final.text.endswith(("\n", "\r")) + ) + + +def _valid_bare_identifier(identifier: str) -> bool: + if not identifier or identifier.upper() in _SQLITE_KEYWORDS: + return False + first = identifier[0] + if not (first == "_" or first.isalpha() or ord(first) >= 0x80): + return False + return all( + char == "_" or char == "$" or char.isalnum() or ord(char) >= 0x80 + for char in identifier[1:] + ) + + +def _quote_replacement(original: str, replacement: str) -> str: + if original.startswith('"'): + return '"{}"'.format(replacement.replace('"', '""')) + if original.startswith("`"): + return "`{}`".format(replacement.replace("`", "``")) + if original.startswith("[") and "]" not in replacement: + return f"[{replacement}]" + if _valid_bare_identifier(replacement): + return replacement + return '"{}"'.format(replacement.replace('"', '""')) + + +def rewrite_check_expression(expression: str, rename: dict[str, str]) -> str: + """Rewrite column identifiers in a CHECK expression, preserving trivia.""" + if not rename: + return expression + tokens = _lex(expression) + meaningful = _meaningful(tokens) + replacements = {_ascii_fold(key): value for key, value in rename.items()} + edits: list[tuple[int, int, str]] = [] + for index, token in enumerate(meaningful): + if not _is_identifier_token(meaningful, index): + continue + replacement = replacements.get(_ascii_fold(_unquote(token.text))) + if replacement is not None: + edits.append( + (token.start, token.end, _quote_replacement(token.text, replacement)) + ) + for start, end, replacement in reversed(edits): + expression = expression[:start] + replacement + expression[end:] + return expression diff --git a/sqlite_utils/db.py b/sqlite_utils/db.py index bec68fc..c011d9b 100644 --- a/sqlite_utils/db.py +++ b/sqlite_utils/db.py @@ -1,19 +1,4 @@ -from .utils import ( - chunks, - dedupe_keys, - hash_record, - sqlite3, - OperationalError, - suggest_column_types, - types_for_column_types, - column_affinity, - progressbar, - find_spatialite, -) import binascii -from collections import namedtuple -from dataclasses import dataclass, field -from collections.abc import Mapping import contextlib import datetime import decimal @@ -25,26 +10,50 @@ import os import pathlib import re import secrets -from sqlite_fts4 import rank_bm25 import textwrap -from typing import ( - cast, - Any, - Callable, - Dict, - Generator, - Iterable, - Sequence, - Set, - Type, - Union, - Optional, - List, - Tuple, -) import uuid +from collections import namedtuple +from collections.abc import Callable, Generator, Iterable, Mapping, Sequence +from dataclasses import dataclass, field +from types import TracebackType +from typing import ( + Any, + TypeVar, + Union, + cast, +) + +from sqlite_fts4 import rank_bm25 from sqlite_utils.plugins import ensure_plugins_loaded, pm +from .create_table_parser import ( + Check, + ColumnComments, + ParseError, + Unique, + UniqueColumn, + check_references_identifier, + parse_autoincrement, + parse_checks, + parse_column_comments, + parse_uniques, + rewrite_check_expression, + sql_ends_in_line_comment, +) +from .utils import ( + ANY, + OperationalError, + chunks, + column_affinity, + dedupe_keys, + find_spatialite, + hash_record, + progressbar, + sqlite3, + suggest_column_types, + types_for_column_types, +) + try: iterdump = importlib.import_module("sqlite_dump").iterdump except ImportError: @@ -53,6 +62,11 @@ except ImportError: SQLITE_MAX_VARS = 999 +# Names that refer to a rowid table's implicit integer primary key. These are +# valid primary key targets even though they are not listed among a table's +# columns. See https://www.sqlite.org/lang_createtable.html#rowid +ROWID_ALIASES = frozenset({"rowid", "_rowid_", "oid"}) + _quote_fts_re = re.compile(r'\s+|(".*?")') _virtual_table_using_re = re.compile( @@ -85,6 +99,46 @@ def quote_identifier(identifier: str) -> str: return '"{}"'.format(identifier.replace('"', '""')) +def _check_constraint_sql(check: Check) -> str: + prefix = f"CONSTRAINT {quote_identifier(check.name)} " if check.name else "" + newline = "\n" if sql_ends_in_line_comment(check.check) else "" + return f"{prefix}CHECK ({check.check}{newline})" + + +def _unique_constraint_sql(unique: Unique) -> str: + prefix = f"CONSTRAINT {quote_identifier(unique.name)} " if unique.name else "" + if unique.column: + constraint = "UNIQUE" + else: + columns = [] + for column in unique.columns: + column_sql = quote_identifier(column.name) + if column.collation: + column_sql += f" COLLATE {quote_identifier(column.collation)}" + if column.order: + column_sql += f" {column.order}" + columns.append(column_sql) + constraint = "UNIQUE ({})".format(", ".join(columns)) + conflict = f" ON CONFLICT {unique.conflict}" if unique.conflict else "" + return f"{prefix}{constraint}{conflict}" + + +def _column_definition_with_comments( + definition: str, comments: ColumnComments | None +) -> str: + if comments is None: + return definition + before = textwrap.dedent(comments.before).strip() + after = textwrap.dedent(comments.after).strip() + if before: + definition = f"{textwrap.indent(before, ' ')}\n{definition}" + if after: + definition = f"{definition} {after}" + if sql_ends_in_line_comment(after): + definition += "\n" + return definition + + _IDENTIFIER_CASEFOLD = str.maketrans( "ABCDEFGHIJKLMNOPQRSTUVWXYZ", "abcdefghijklmnopqrstuvwxyz" ) @@ -221,11 +275,11 @@ class ForeignKey: table: str # column/other_column are None for compound keys, which would break # ordering against str values - comparison uses columns/other_columns - column: Optional[str] = field(compare=False) + column: str | None = field(compare=False) other_table: str - other_column: Optional[str] = field(compare=False) - columns: Tuple[str, ...] = () - other_columns: Tuple[str, ...] = () + other_column: str | None = field(compare=False) + columns: tuple[str, ...] | list[str] = () + other_columns: tuple[str, ...] | list[str] = () is_compound: bool = False on_delete: str = "NO ACTION" on_update: str = "NO ACTION" @@ -254,9 +308,9 @@ def _fk_actions_sql(fk: ForeignKey) -> str: "ON UPDATE/ON DELETE clauses for a foreign key, or an empty string." actions = "" if fk.on_update and fk.on_update != "NO ACTION": - actions += " ON UPDATE {}".format(fk.on_update) + actions += f" ON UPDATE {fk.on_update}" if fk.on_delete and fk.on_delete != "NO ACTION": - actions += " ON DELETE {}".format(fk.on_delete) + actions += f" ON DELETE {fk.on_delete}" return actions @@ -273,20 +327,22 @@ class TransformError(Exception): # A single column name, or a tuple of columns for a compound foreign key -ForeignKeyColumns = Union[str, Tuple[str, ...], List[str]] +ForeignKeyColumns = str | tuple[str, ...] | list[str] # (table, column(s), other_table, other_column(s)) -ForeignKeyTuple = Tuple[str, ForeignKeyColumns, str, ForeignKeyColumns] +ForeignKeyTuple = tuple[str, ForeignKeyColumns, str, ForeignKeyColumns] -ForeignKeyIndicator = Union[ - str, - ForeignKey, - Tuple[ForeignKeyColumns, str], - Tuple[ForeignKeyColumns, str, ForeignKeyColumns], - ForeignKeyTuple, -] +ForeignKeyIndicator = ( + str + | ForeignKey + | tuple[ForeignKeyColumns, str] + | tuple[ForeignKeyColumns, str, ForeignKeyColumns] + | ForeignKeyTuple +) -ForeignKeysType = Union[Iterable[ForeignKeyIndicator], List[ForeignKeyIndicator]] +ForeignKeysType = Iterable[ForeignKeyIndicator] | list[ForeignKeyIndicator] + +PrimaryKey = str | tuple[str, ...] | list[str] class Default: @@ -295,7 +351,9 @@ class Default: DEFAULT = Default() -Tracer = Callable[[str, Optional[Union[Sequence[Any], Dict[str, Any]]]], None] +T = TypeVar("T") + +Tracer = Callable[[str, Sequence[Any] | dict[str, Any] | None], None] def _iter_complete_sql_statements(sql: str) -> Generator[str, None, None]: @@ -311,7 +369,7 @@ def _iter_complete_sql_statements(sql: str) -> Generator[str, None, None]: yield statement_sql -COLUMN_TYPE_MAPPING: Dict[Any, str] = { +COLUMN_TYPE_MAPPING: dict[Any, str] = { float: "REAL", int: "INTEGER", bool: "INTEGER", @@ -329,6 +387,7 @@ COLUMN_TYPE_MAPPING: Dict[Any, str] = { decimal.Decimal: "REAL", None.__class__: "TEXT", uuid.UUID: "TEXT", + ANY: "ANY", # SQLite explicit types "TEXT": "TEXT", "INTEGER": "INTEGER", @@ -343,6 +402,8 @@ COLUMN_TYPE_MAPPING: Dict[Any, str] = { "real": "REAL", "blob": "BLOB", "bytes": "BLOB", + "ANY": "ANY", + "any": "ANY", } # If numpy is available, add more types if np: @@ -507,12 +568,12 @@ class Database: def __init__( self, - filename_or_conn: Optional[Union[str, pathlib.Path, sqlite3.Connection]] = None, + filename_or_conn: str | pathlib.Path | sqlite3.Connection | None = None, memory: bool = False, - memory_name: Optional[str] = None, + memory_name: str | None = None, recreate: bool = False, recursive_triggers: bool = True, - tracer: Optional[Tracer] = None, + tracer: Tracer | None = None, use_counts_table: bool = False, execute_plugins: bool = True, use_old_upsert: bool = False, @@ -527,7 +588,7 @@ class Database: ): raise ValueError("Either specify a filename_or_conn or pass memory=True") if memory_name: - uri = "file:{}?mode=memory&cache=shared".format(memory_name) + uri = f"file:{memory_name}?mode=memory&cache=shared" self.conn = sqlite3.connect( uri, uri=True, @@ -564,7 +625,7 @@ class Database: "transaction handling - connections created with " "autocommit=True or autocommit=False are not supported" ) - self._tracer: Optional[Tracer] = tracer + self._tracer: Tracer | None = tracer if recursive_triggers: self.execute("PRAGMA recursive_triggers=on;") self._registered_functions: set = set() @@ -574,14 +635,14 @@ class Database: pm.hook.prepare_connection(conn=self.conn) self.strict = strict - def __enter__(self) -> "Database": + def __enter__(self): return self def __exit__( self, - exc_type: Optional[Type[BaseException]], - exc_val: Optional[BaseException], - exc_tb: Optional[object], + exc_type: type[BaseException] | None, + exc_val: BaseException | None, + exc_tb: TracebackType | None, ) -> None: self.close() @@ -597,8 +658,8 @@ class Database: Nested blocks use SQLite savepoints. """ if self.conn.in_transaction: - savepoint = "sqlite_utils_{}".format(secrets.token_hex(16)) - self.conn.execute("SAVEPOINT {};".format(savepoint)) + savepoint = f"sqlite_utils_{secrets.token_hex(16)}" + self.conn.execute(f"SAVEPOINT {savepoint};") try: yield self except BaseException: @@ -607,11 +668,11 @@ class Database: # anyway would mask the original exception with # "no such savepoint" if self.conn.in_transaction: - self.conn.execute("ROLLBACK TO SAVEPOINT {};".format(savepoint)) - self.conn.execute("RELEASE SAVEPOINT {};".format(savepoint)) + self.conn.execute(f"ROLLBACK TO SAVEPOINT {savepoint};") + self.conn.execute(f"RELEASE SAVEPOINT {savepoint};") raise else: - self.conn.execute("RELEASE SAVEPOINT {};".format(savepoint)) + self.conn.execute(f"RELEASE SAVEPOINT {savepoint};") else: self.conn.execute("BEGIN") try: @@ -690,9 +751,7 @@ class Database: self.conn.isolation_level = old_isolation_level @contextlib.contextmanager - def tracer( - self, tracer: Optional[Tracer] = None - ) -> Generator["Database", None, None]: + def tracer(self, tracer: Tracer | None = None) -> Generator["Database", None, None]: """ Context manager to temporarily set a tracer function - all executed SQL queries will be passed to this. @@ -729,15 +788,15 @@ class Database: return self.table(table_name) def __repr__(self) -> str: - return "".format(self.conn) + return f"" def register_function( self, - fn: Optional[Callable] = None, + fn: Callable | None = None, deterministic: bool = False, replace: bool = False, - name: Optional[str] = None, - ) -> Optional[Callable[[Callable], Callable]]: + name: str | None = None, + ) -> Callable[[Callable], Callable] | None: """ ``fn`` will be made available as a function within SQL, with the same name and number of arguments. Can be used as a decorator:: @@ -765,7 +824,7 @@ class Database: arity = len(inspect.signature(fn).parameters) if not replace and (fn_name, arity) in self._registered_functions: return fn - kwargs: Dict[str, bool] = {} + kwargs: dict[str, bool] = {} registered = False if deterministic: # Try this, but fall back if sqlite3.NotSupportedError @@ -791,7 +850,7 @@ class Database: "Register the ``rank_bm25(match_info)`` function used for calculating relevance with SQLite FTS4." self.register_function(rank_bm25, deterministic=True, replace=True) - def attach(self, alias: str, filepath: Union[str, pathlib.Path]) -> None: + def attach(self, alias: str, filepath: str | pathlib.Path) -> None: """ Attach another SQLite database file to this connection with the specified alias, equivalent to:: @@ -800,15 +859,13 @@ class Database: :param alias: Alias name to use :param filepath: Path to SQLite database file on disk """ - attach_sql = """ - ATTACH DATABASE '{}' AS {}; - """.format( - str(pathlib.Path(filepath).resolve()), quote_identifier(alias) - ).strip() + attach_sql = f""" + ATTACH DATABASE '{pathlib.Path(filepath).resolve()!s}' AS {quote_identifier(alias)}; + """.strip() self.execute(attach_sql) def query( - self, sql: str, params: Optional[Union[Sequence, Dict[str, Any]]] = None + self, sql: str, params: Sequence | dict[str, Any] | None = None ) -> Generator[dict, None, None]: """ Execute ``sql`` and return an iterable of dictionaries representing each row. @@ -886,7 +943,7 @@ class Database: self.conn.execute('RELEASE "sqlite_utils_query"') def execute( - self, sql: str, parameters: Optional[Union[Sequence, Dict[str, Any]]] = None + self, sql: str, parameters: Sequence | dict[str, Any] | None = None ) -> sqlite3.Cursor: """ Execute SQL query and return a ``sqlite3.Cursor``. @@ -955,7 +1012,7 @@ class Database: :param table_name: Name of the table """ if table_name in self.view_names(): - raise NoTable("Table {} is actually a view".format(table_name)) + raise NoTable(f"Table {table_name} is actually a view") kwargs.setdefault("strict", self.strict) return Table(self, table_name, **kwargs) @@ -968,11 +1025,9 @@ class Database: if view_name not in self.view_names(): if view_name in self.table_names(): raise NoView( - "View {name} does not exist - {name} is a table".format( - name=view_name - ) + f"View {view_name} does not exist - {view_name} is a table" ) - raise NoView("View {} does not exist".format(view_name)) + raise NoView(f"View {view_name} does not exist") return View(self, view_name) def quote(self, value: str) -> str: @@ -1008,9 +1063,7 @@ class Database: query += '"' bits = _quote_fts_re.split(query) bits = [b for b in bits if b and b != '""'] - return " ".join( - '"{}"'.format(bit) if not bit.startswith('"') else bit for bit in bits - ) + return " ".join(f'"{bit}"' if not bit.startswith('"') else bit for bit in bits) def quote_default_value(self, value: str) -> str: if any( @@ -1031,11 +1084,11 @@ class Database: if str(value).endswith(")"): # Expr - return "({})".format(value) + return f"({value})" return self.quote(value) - def table_names(self, fts4: bool = False, fts5: bool = False) -> List[str]: + def table_names(self, fts4: bool = False, fts5: bool = False) -> list[str]: """ List of string table names in this database. @@ -1050,7 +1103,7 @@ class Database: sql = "select name from sqlite_master where {}".format(" AND ".join(where)) return [r[0] for r in self.execute(sql).fetchall()] - def view_names(self) -> List[str]: + def view_names(self) -> list[str]: "List of string view names in this database." return [ r[0] @@ -1060,17 +1113,17 @@ class Database: ] @property - def tables(self) -> List["Table"]: + def tables(self) -> list["Table"]: "List of Table objects in this database." return [self.table(name) for name in self.table_names()] @property - def views(self) -> List["View"]: + def views(self) -> list["View"]: "List of View objects in this database." return [self.view(name) for name in self.view_names()] @property - def triggers(self) -> List[Trigger]: + def triggers(self) -> list[Trigger]: "List of ``(name, table_name, sql)`` tuples representing triggers in this database." return [ Trigger(*r) @@ -1080,7 +1133,7 @@ class Database: ] @property - def triggers_dict(self) -> Dict[str, str]: + def triggers_dict(self) -> dict[str, str]: "A ``{trigger_name: sql}`` dictionary of triggers in this database." return {trigger.name: trigger.sql for trigger in self.triggers} @@ -1102,14 +1155,12 @@ class Database: "Does this database support STRICT mode?" if not hasattr(self, "_supports_strict"): try: - table_name = "t{}".format(secrets.token_hex(16)) + table_name = f"t{secrets.token_hex(16)}" with self.atomic(): - self.conn.execute( - "create table {} (name text) strict".format(table_name) - ) - self.conn.execute("drop table {}".format(table_name)) + self.conn.execute(f"create table {table_name} (name text) strict") + self.conn.execute(f"drop table {table_name}") self._supports_strict = True - except Exception: + except sqlite3.OperationalError: self._supports_strict = False return self._supports_strict @@ -1117,32 +1168,28 @@ class Database: def supports_on_conflict(self) -> bool: # SQLite's upsert is implemented as INSERT INTO ... ON CONFLICT DO ... if not hasattr(self, "_supports_on_conflict"): - table_name = "t{}".format(secrets.token_hex(16)) + table_name = f"t{secrets.token_hex(16)}" try: with self.atomic(): self.conn.execute( - "create table {} (id integer primary key, name text)".format( - table_name - ) + f"create table {table_name} (id integer primary key, name text)" ) self.conn.execute( - "insert into {} (id, name) values (1, 'one')".format(table_name) + f"insert into {table_name} (id, name) values (1, 'one')" ) self.conn.execute( - ( - "insert into {} (id, name) values (1, 'two') " - "on conflict do update set name = 'two'" - ).format(table_name) + f"insert into {table_name} (id, name) values (1, 'two') " + "on conflict do update set name = 'two'" ) self._supports_on_conflict = True - except Exception: + except sqlite3.OperationalError: self._supports_on_conflict = False finally: - self.conn.execute("drop table if exists {}".format(table_name)) + self.conn.execute(f"drop table if exists {table_name}") return self._supports_on_conflict @property - def sqlite_version(self) -> Tuple[int, ...]: + def sqlite_version(self) -> tuple[int, ...]: "Version of SQLite, as a tuple of integers for example ``(3, 36, 0)``." row = self.execute("select sqlite_version()").fetchall()[0] return tuple(map(int, row[0].split("."))) @@ -1186,7 +1233,7 @@ class Database: # guarantee of atomic() and of user-managed transactions if self.conn.in_transaction: raise TransactionError( - "{} cannot be used while a transaction is open".format(operation) + f"{operation} cannot be used while a transaction is open" ) def _ensure_counts_table(self) -> None: @@ -1207,14 +1254,14 @@ class Database: table.enable_counts() self.use_counts_table = True - def cached_counts(self, tables: Optional[Iterable[str]] = None) -> Dict[str, int]: + def cached_counts(self, tables: Iterable[str] | None = None) -> dict[str, int]: """ Return ``{table_name: count}`` dictionary of cached counts for specified tables, or all tables if ``tables`` not provided. :param tables: Subset list of tables to return counts for. """ - sql = 'select "table", count from {}'.format(self._counts_table_name) + sql = f'select "table", count from {self._counts_table_name}' tables_list = list(tables) if tables else None if tables_list: sql += ' where "table" in ({})'.format(", ".join("?" for _ in tables_list)) @@ -1236,13 +1283,13 @@ class Database: ) def execute_returning_dicts( - self, sql: str, params: Optional[Union[Sequence, Dict[str, Any]]] = None - ) -> List[dict]: + self, sql: str, params: Sequence | dict[str, Any] | None = None + ) -> list[dict]: return list(self.query(sql, params)) def resolve_foreign_keys( self, name: str, foreign_keys: ForeignKeysType - ) -> List[ForeignKey]: + ) -> list[ForeignKey]: """ Given a list of differing foreign_keys definitions, return a list of fully resolved ForeignKey() named tuples. @@ -1269,7 +1316,7 @@ class Database: fks.append(ForeignKey(name, fk, other_table, other_column)) continue if not isinstance(fk, (tuple, list)): - raise ValueError( + raise ValueError( # noqa: TRY004 "foreign_keys= should be a list of tuples, " "ForeignKey objects or column name strings" ) @@ -1277,9 +1324,7 @@ class Database: if len(tuple_or_list) == 4: if tuple_or_list[0] != name: raise ValueError( - "First item in {} should have been {}".format( - tuple_or_list, name - ) + f"First item in {tuple_or_list} should have been {name}" ) tuple_or_list = tuple_or_list[1:] if len(tuple_or_list) not in (2, 3): @@ -1294,8 +1339,8 @@ class Database: if len(tuple_or_list) == 3: if not isinstance(tuple_or_list[2], (list, tuple)): raise ValueError( - "Compound foreign key {} should reference a tuple " - "of other columns".format(tuple(tuple_or_list)) + f"Compound foreign key {tuple(tuple_or_list)} should reference a tuple " + "of other columns" ) other_columns = tuple(tuple_or_list[2]) else: @@ -1303,8 +1348,8 @@ class Database: other_columns = tuple(self.table(other_table).pks) if len(columns) != len(other_columns): raise ValueError( - "Compound foreign key {} should have the same number " - "of columns on both sides".format(tuple(tuple_or_list)) + f"Compound foreign key {tuple(tuple_or_list)} should have the same number " + "of columns on both sides" ) if len(columns) == 1: # Single-column key passed as a one-item list @@ -1384,17 +1429,21 @@ class Database: def create_table_sql( self, name: str, - columns: Dict[str, Any], - pk: Optional[Any] = None, - foreign_keys: Optional[ForeignKeysType] = None, - column_order: Optional[List[str]] = None, - not_null: Optional[Iterable[str]] = None, - defaults: Optional[Dict[str, Any]] = None, - hash_id: Optional[str] = None, - hash_id_columns: Optional[Iterable[str]] = None, - extracts: Optional[Union[Dict[str, str], List[str]]] = None, + columns: dict[str, Any], + pk: Any | None = None, + foreign_keys: ForeignKeysType | None = None, + column_order: list[str] | None = None, + not_null: Iterable[str] | None = None, + defaults: dict[str, Any] | None = None, + hash_id: str | None = None, + hash_id_columns: Iterable[str] | None = None, + extracts: dict[str, str] | list[str] | None = None, if_not_exists: bool = False, strict: bool = False, + _checks: Iterable[Check] | None = None, + _column_comments: Mapping[str, ColumnComments] | None = None, + _autoincrement: str | None = None, + _uniques: Iterable[Unique] | None = None, ) -> str: """ Returns the SQL ``CREATE TABLE`` statement for creating the specified table. @@ -1414,7 +1463,7 @@ class Database: """ if hash_id_columns and (hash_id is None): hash_id = "id" - resolved_fks: List[ForeignKey] = [ + resolved_fks: list[ForeignKey] = [ self._resolve_foreign_key_casing(fk, columns) for fk in self.resolve_foreign_keys(name, foreign_keys or []) ] @@ -1440,19 +1489,86 @@ class Database: defaults = {resolve_casing(n, columns): v for n, v in (defaults or {}).items()} if column_order is not None: column_order = [resolve_casing(c, columns) for c in column_order] + column_comments = { + resolve_casing(name, columns): comments + for name, comments in (_column_comments or {}).items() + } + checks = list(_checks or ()) + checks_by_column: dict[str, list[Check]] = {} + table_checks: list[Check] = [] + for check in checks: + if check.column: + column = resolve_casing(check.column, columns) + if column not in columns: + raise AlterError( + f"No such column for CHECK constraint: {check.column}" + ) + checks_by_column.setdefault(column, []).append(check) + else: + table_checks.append(check) + uniques_by_column: dict[str, list[Unique]] = {} + table_uniques: list[Unique] = [] + for unique in _uniques or (): + resolved_unique = Unique( + tuple( + UniqueColumn( + resolve_casing(column.name, columns), + collation=column.collation, + order=column.order, + ) + for column in unique.columns + ), + name=unique.name, + column=( + resolve_casing(unique.column, columns) if unique.column else "" + ), + conflict=unique.conflict, + ) + missing = [ + column.name + for column in resolved_unique.columns + if column.name not in columns + ] + if missing: + raise AlterError( + "No such column for UNIQUE constraint: {}".format( + ", ".join(missing) + ) + ) + if resolved_unique.column: + if ( + len(resolved_unique.columns) != 1 + or resolved_unique.columns[0].name != resolved_unique.column + ): + raise AlterError("Invalid column-level UNIQUE constraint") + if any( + column.collation or column.order + for column in resolved_unique.columns + ): + # Render this as a table constraint so the collation or sort + # order that governs uniqueness can be represented explicitly. + table_uniques.append( + Unique( + resolved_unique.columns, + name=resolved_unique.name, + conflict=resolved_unique.conflict, + ) + ) + else: + uniques_by_column.setdefault(resolved_unique.column, []).append( + resolved_unique + ) + else: + table_uniques.append(resolved_unique) if not columns: raise ValueError("Tables must have at least one column") if not all(n in columns for n in not_null): raise ValueError( - "not_null set {} includes items not in columns {}".format( - repr(not_null), repr(set(columns.keys())) - ) + f"not_null set {not_null!r} includes items not in columns {set(columns.keys())!r}" ) if not all(n in columns for n in defaults): raise ValueError( - "defaults set {} includes items not in columns {}".format( - repr(set(defaults)), repr(set(columns.keys())) - ) + f"defaults set {set(defaults)!r} includes items not in columns {set(columns.keys())!r}" ) column_items = list(columns.items()) if column_order is not None: @@ -1472,9 +1588,7 @@ class Database: if other_column != "rowid" and not any( c for c in self[fk.other_table].columns if c.name == other_column ): - raise AlterError( - "No such column: {}.{}".format(fk.other_table, other_column) - ) + raise AlterError(f"No such column: {fk.other_table}.{other_column}") column_defs = [] # ensure pk is a tuple @@ -1487,37 +1601,56 @@ class Database: column_items.insert(0, (pk, int)) elif pk: pk = [resolve_casing(p, [c[0] for c in column_items]) for p in pk] + if _autoincrement is not None: + _autoincrement = resolve_casing( + _autoincrement, [c[0] for c in column_items] + ) + if _autoincrement != single_pk: + raise ValueError("AUTOINCREMENT requires a single-column primary key") for column_name, column_type in column_items: column_extras = [] if column_name == single_pk: column_extras.append("PRIMARY KEY") + if column_name == _autoincrement: + if COLUMN_TYPE_MAPPING[column_type] != "INTEGER": + raise ValueError( + "AUTOINCREMENT requires an INTEGER PRIMARY KEY column" + ) + column_extras.append("AUTOINCREMENT") if column_name in not_null: column_extras.append("NOT NULL") if column_name in defaults and defaults[column_name] is not None: column_extras.append( - "DEFAULT {}".format(self.quote_default_value(defaults[column_name])) + f"DEFAULT {self.quote_default_value(defaults[column_name])}" ) if column_name in foreign_keys_by_column: fk = foreign_keys_by_column[column_name] column_extras.append( - "REFERENCES {}({}){}".format( - quote_identifier(fk.other_table), - quote_identifier(cast(str, fk.other_column)), - _fk_actions_sql(fk), - ) + f"REFERENCES {quote_identifier(fk.other_table)}({quote_identifier(cast(str, fk.other_column))}){_fk_actions_sql(fk)}" ) + column_extras.extend( + _unique_constraint_sql(unique) + for unique in uniques_by_column.get(column_name, ()) + ) + column_extras.extend( + _check_constraint_sql(check) + for check in checks_by_column.get(column_name, ()) + ) column_type_str = COLUMN_TYPE_MAPPING[column_type] # Special case for strict tables to map FLOAT to REAL # Refs https://github.com/simonw/sqlite-utils/issues/644 if strict and column_type_str == "FLOAT": column_type_str = "REAL" + column_definition = " {} {column_type}{column_extras}".format( + quote_identifier(column_name), + column_type=column_type_str, + column_extras=( + (" " + " ".join(column_extras)) if column_extras else "" + ), + ) column_defs.append( - " {} {column_type}{column_extras}".format( - quote_identifier(column_name), - column_type=column_type_str, - column_extras=( - (" " + " ".join(column_extras)) if column_extras else "" - ), + _column_definition_with_comments( + column_definition, column_comments.get(column_name) ) ) extra_pk = "" @@ -1545,6 +1678,12 @@ class Database: actions=_fk_actions_sql(fk), ) ) + column_defs.extend( + f" {_unique_constraint_sql(unique)}" for unique in table_uniques + ) + column_defs.extend( + f" {_check_constraint_sql(check)}" for check in table_checks + ) columns_sql = ",\n".join(column_defs) sql = """CREATE TABLE {if_not_exists}{table} ( {columns_sql}{extra_pk} @@ -1561,15 +1700,15 @@ class Database: def create_table( self, name: str, - columns: Dict[str, Any], - pk: Optional[Any] = None, - foreign_keys: Optional[ForeignKeysType] = None, - column_order: Optional[List[str]] = None, - not_null: Optional[Iterable[str]] = None, - defaults: Optional[Dict[str, Any]] = None, - hash_id: Optional[str] = None, - hash_id_columns: Optional[Iterable[str]] = None, - extracts: Optional[Union[Dict[str, str], List[str]]] = None, + columns: dict[str, Any], + pk: Any | None = None, + foreign_keys: ForeignKeysType | None = None, + column_order: list[str] | None = None, + not_null: Iterable[str] | None = None, + defaults: dict[str, Any] | None = None, + hash_id: str | None = None, + hash_id_columns: Iterable[str] | None = None, + extracts: dict[str, str] | list[str] | None = None, if_not_exists: bool = False, replace: bool = False, ignore: bool = False, @@ -1613,11 +1752,11 @@ class Database: resolve_casing(col_name, existing_columns): col_type for col_name, col_type in columns.items() } - missing_columns = dict( - (col_name, col_type) + missing_columns = { + col_name: col_type for col_name, col_type in columns.items() if col_name not in existing_columns - ) + } columns_to_drop = [ column for column in existing_columns if column not in columns ] @@ -1704,9 +1843,7 @@ class Database: :param new_name: Name to rename it to """ self.execute( - "ALTER TABLE {} RENAME TO {}".format( - quote_identifier(name), quote_identifier(new_name) - ) + f"ALTER TABLE {quote_identifier(name)} RENAME TO {quote_identifier(new_name)}" ) def create_view( @@ -1722,23 +1859,20 @@ class Database: """ if ignore and replace: raise ValueError("Use one or the other of ignore/replace, not both") - create_sql = "CREATE VIEW {name} AS {sql}".format( - name=quote_identifier(name), sql=sql - ) - if ignore or replace: - # Does view exist already? - if name in self.view_names(): - if ignore: + create_sql = f"CREATE VIEW {quote_identifier(name)} AS {sql}" + if (ignore or replace) and name in self.view_names(): + # View exists already + if ignore: + return self + elif replace: + # If SQL is the same, do nothing + if create_sql == self[name].schema: return self - elif replace: - # If SQL is the same, do nothing - if create_sql == self[name].schema: - return self - self[name].drop() + self[name].drop() self.execute(create_sql) return self - def m2m_table_candidates(self, table: str, other_table: str) -> List[str]: + def m2m_table_candidates(self, table: str, other_table: str) -> list[str]: """ Given two table names returns the name of tables that could define a many-to-many relationship between those two tables, based on having @@ -1757,7 +1891,7 @@ class Database: return candidates def add_foreign_keys( - self, foreign_keys: Iterable[Union[ForeignKey, ForeignKeyTuple]] + self, foreign_keys: Iterable[ForeignKey | ForeignKeyTuple] ) -> None: """ See :ref:`python_api_add_foreign_keys`. @@ -1777,7 +1911,7 @@ class Database: "(table, column, other_table, other_column)" ) - foreign_keys_to_create: List[ForeignKey] = [] + foreign_keys_to_create: list[ForeignKey] = [] # Verify that all tables and columns exist for fk in foreign_keys: @@ -1818,27 +1952,25 @@ class Database: table = fk_object.table other_table = fk_object.other_table if not self.table(table).exists(): - raise AlterError("No such table: {}".format(table)) + raise AlterError(f"No such table: {table}") table_obj = self.table(table) fk_object = self._resolve_foreign_key_casing( fk_object, table_obj.columns_dict ) - columns = fk_object.columns - other_columns = fk_object.other_columns + columns = tuple(fk_object.columns) + other_columns = tuple(fk_object.other_columns) for column in columns: if column not in table_obj.columns_dict: - raise AlterError("No such column: {} in {}".format(column, table)) + raise AlterError(f"No such column: {column} in {table}") if not self[other_table].exists(): - raise AlterError("No such other_table: {}".format(other_table)) + raise AlterError(f"No such other_table: {other_table}") for other_column in other_columns: if ( other_column != "rowid" and other_column not in self[other_table].columns_dict ): raise AlterError( - "No such other_column: {} in {}".format( - other_column, other_table - ) + f"No such other_column: {other_column} in {other_table}" ) # Silently skip foreign keys that exist already - but only if # they match exactly, including ON DELETE/ON UPDATE actions @@ -1869,7 +2001,7 @@ class Database: ) # Group them by table - by_table: Dict[str, List[ForeignKey]] = {} + by_table: dict[str, list[ForeignKey]] = {} for fk_object in foreign_keys_to_create: by_table.setdefault(fk_object.table, []).append(fk_object) @@ -1886,15 +2018,16 @@ class Database: existing_indexes = {tuple(i.columns) for i in table.indexes} for fk in table.foreign_keys: # A compound foreign key gets a single composite index - if fk.columns not in existing_indexes: + fk_columns = tuple(fk.columns) + if fk_columns not in existing_indexes: table.create_index(fk.columns, find_unique_name=True) - existing_indexes.add(fk.columns) + existing_indexes.add(fk_columns) def vacuum(self) -> None: "Run a SQLite ``VACUUM`` against the database." self.execute("VACUUM;") - def analyze(self, name: Optional[str] = None) -> None: + def analyze(self, name: str | None = None) -> None: """ Run ``ANALYZE`` against the entire database or a named table or index. @@ -1902,7 +2035,7 @@ class Database: """ sql = "ANALYZE" if name is not None: - sql += " {}".format(quote_identifier(name)) + sql += f" {quote_identifier(name)}" self.execute(sql) def iterdump(self) -> Generator[str, None, None]: @@ -1917,7 +2050,7 @@ class Database: "conn.iterdump() not found - try pip install sqlite-dump" ) - def init_spatialite(self, path: Optional[str] = None) -> bool: + def init_spatialite(self, path: str | None = None) -> bool: """ The ``init_spatialite`` method will load and initialize the SpatiaLite extension. The ``path`` argument should be an absolute path to the compiled extension, which @@ -1975,8 +2108,8 @@ class Queryable: def count_where( self, - where: Optional[str] = None, - where_args: Optional[Union[Sequence, Dict[str, Any]]] = None, + where: str | None = None, + where_args: Sequence | dict[str, Any] | None = None, ) -> int: """ Executes ``SELECT count(*) FROM table WHERE ...`` and returns a count. @@ -1985,7 +2118,7 @@ class Queryable: :param where_args: Parameters to use with that fragment - an iterable for ``id > ?`` parameters, or a dictionary for ``id > :id`` """ - sql = "select count(*) from {}".format(quote_identifier(self.name)) + sql = f"select count(*) from {quote_identifier(self.name)}" if where is not None: sql += " where " + where return self.db.execute(sql, where_args or []).fetchone()[0] @@ -2000,19 +2133,19 @@ class Queryable: return self.count_where() @property - def rows(self) -> Generator[Dict[str, Any], None, None]: + def rows(self) -> Generator[dict[str, Any], None, None]: "Iterate over every dictionaries for each row in this table or view." return self.rows_where() def rows_where( self, - where: Optional[str] = None, - where_args: Optional[Union[Sequence, Dict[str, Any]]] = None, - order_by: Optional[str] = None, + where: str | None = None, + where_args: Sequence | dict[str, Any] | None = None, + order_by: str | None = None, select: str = "*", - limit: Optional[int] = None, - offset: Optional[int] = None, - ) -> Generator[Dict[str, Any], None, None]: + limit: int | None = None, + offset: int | None = None, + ) -> Generator[dict[str, Any], None, None]: """ Iterate over every row in this table or view that matches the specified where clause. @@ -2028,15 +2161,19 @@ class Queryable: """ if not self.exists(): return - sql = "select {} from {}".format(select, quote_identifier(self.name)) + sql = f"select {select} from {quote_identifier(self.name)}" if where is not None: sql += " where " + where if order_by is not None: sql += " order by " + order_by if limit is not None: - sql += " limit {}".format(limit) + sql += f" limit {limit}" if offset is not None: - sql += " offset {}".format(offset) + # SQLite requires a limit clause before offset - a negative limit + # means "no upper bound", so offset works without an explicit limit + if limit is None: + sql += " limit -1" + sql += f" offset {offset}" cursor = self.db.execute(sql, where_args or []) columns = dedupe_keys(c[0] for c in cursor.description) for row in cursor: @@ -2044,12 +2181,12 @@ class Queryable: def pks_and_rows_where( self, - where: Optional[str] = None, - where_args: Optional[Union[Sequence, Dict[str, Any]]] = None, - order_by: Optional[str] = None, - limit: Optional[int] = None, - offset: Optional[int] = None, - ) -> Generator[Tuple[Any, Dict[str, Any]], None, None]: + where: str | None = None, + where_args: Sequence | dict[str, Any] | None = None, + order_by: str | None = None, + limit: int | None = None, + offset: int | None = None, + ) -> Generator[tuple[Any, dict[str, Any]], None, None]: """ Like ``.rows_where()`` but returns ``(pk, row)`` pairs - ``pk`` can be a single value or tuple. @@ -2091,17 +2228,17 @@ class Queryable: yield row_pk, row @property - def columns(self) -> List["Column"]: + def columns(self) -> list["Column"]: "List of :ref:`Columns ` representing the columns in this table or view." if not self.exists(): return [] rows = self.db.execute( - "PRAGMA table_info({})".format(quote_identifier(self.name)) + f"PRAGMA table_info({quote_identifier(self.name)})" ).fetchall() return [Column(*row) for row in rows] @property - def columns_dict(self) -> Dict[str, Any]: + def columns_dict(self) -> dict[str, Any]: "``{column_name: python-type}`` dictionary representing columns in this table or view." return {column.name: column_affinity(column.type) for column in self.columns} @@ -2141,48 +2278,48 @@ class Table(Queryable): """ #: The ``rowid`` of the last inserted, updated or selected row. - last_rowid: Optional[int] = None + last_rowid: int | None = None #: The primary key of the last inserted, updated or selected row. - last_pk: Optional[Any] = None + last_pk: Any | None = None def __init__( self, db: Database, name: str, - pk: Optional[Any] = None, - foreign_keys: Optional[ForeignKeysType] = None, - column_order: Optional[List[str]] = None, - not_null: Optional[Iterable[str]] = None, - defaults: Optional[Dict[str, Any]] = None, + pk: Any | None = None, + foreign_keys: ForeignKeysType | None = None, + column_order: list[str] | None = None, + not_null: Iterable[str] | None = None, + defaults: dict[str, Any] | None = None, batch_size: int = 100, - hash_id: Optional[str] = None, - hash_id_columns: Optional[Iterable[str]] = None, + hash_id: str | None = None, + hash_id_columns: Iterable[str] | None = None, alter: bool = False, ignore: bool = False, replace: bool = False, - extracts: Optional[Union[Dict[str, str], List[str]]] = None, - conversions: Optional[dict] = None, - columns: Optional[Dict[str, Any]] = None, + extracts: dict[str, str] | list[str] | None = None, + conversions: dict | None = None, + columns: dict[str, Any] | None = None, strict: bool = False, ): super().__init__(db, name) - self._defaults = dict( - pk=pk, - foreign_keys=foreign_keys, - column_order=column_order, - not_null=not_null, - defaults=defaults, - batch_size=batch_size, - hash_id=hash_id, - hash_id_columns=hash_id_columns, - alter=alter, - ignore=ignore, - replace=replace, - extracts=extracts, - conversions=conversions or {}, - columns=columns, - strict=strict, - ) + self._defaults = { + "pk": pk, + "foreign_keys": foreign_keys, + "column_order": column_order, + "not_null": not_null, + "defaults": defaults, + "batch_size": batch_size, + "hash_id": hash_id, + "hash_id_columns": hash_id_columns, + "alter": alter, + "ignore": ignore, + "replace": replace, + "extracts": extracts, + "conversions": conversions or {}, + "columns": columns, + "strict": strict, + } def __repr__(self) -> str: return "
".format( @@ -2207,7 +2344,7 @@ class Table(Queryable): return self.name in self.db.table_names() @property - def pks(self) -> List[str]: + def pks(self) -> list[str]: """ Primary key columns for this table, in PRIMARY KEY declaration order - ``PRAGMA table_info`` sets ``is_pk`` to the 1-based position of each @@ -2229,7 +2366,28 @@ class Table(Queryable): "Does this table use ``rowid`` for its primary key (no other primary keys are specified)?" return not any(column for column in self.columns if column.is_pk) - def get(self, pk_values: Union[list, tuple, str, int]) -> dict: + @property + def checks(self) -> list[Check]: + "List of column-level and table-level CHECK constraints on this table." + if not self.exists() or self.virtual_table_using is not None: + return [] + return parse_checks(self.schema) + + @property + def column_checks(self) -> dict[str, list[Check]]: + "CHECK constraints grouped by the column on which they are defined." + checks: dict[str, list[Check]] = {} + for check in self.checks: + if check.column: + checks.setdefault(check.column, []).append(check) + return checks + + @property + def table_checks(self) -> list[Check]: + "Table-level CHECK constraints on this table." + return [check for check in self.checks if not check.column] + + def get(self, pk_values: list | tuple | str | int) -> dict: """ Return row (as dictionary) for the specified primary key. @@ -2248,17 +2406,17 @@ class Table(Queryable): ) ) - wheres = ["{} = ?".format(quote_identifier(pk_name)) for pk_name in pks] + wheres = [f"{quote_identifier(pk_name)} = ?" for pk_name in pks] rows = self.rows_where(" and ".join(wheres), pk_values) try: - row = list(rows)[0] + row = next(iter(rows)) self.last_pk = last_pk return row - except IndexError: + except StopIteration: raise NotFoundError @property - def foreign_keys(self) -> List["ForeignKey"]: + def foreign_keys(self) -> list["ForeignKey"]: """ List of foreign keys defined on this table. @@ -2268,12 +2426,12 @@ class Table(Queryable): """ # PRAGMA foreign_key_list returns one row per column, grouped by "id" # with "seq" giving the column order within a compound foreign key. - by_id: Dict[int, list] = {} + by_id: dict[int, list] = {} for row in self.db.execute( - "PRAGMA foreign_key_list({})".format(quote_identifier(self.name)) + f"PRAGMA foreign_key_list({quote_identifier(self.name)})" ).fetchall(): if row is not None: - id, seq, table_name, from_, to_, on_update, on_delete, match = row + id, seq, table_name, from_, to_, on_update, on_delete, _match = row by_id.setdefault(id, []).append( (seq, table_name, from_, to_, on_update, on_delete) ) @@ -2306,7 +2464,7 @@ class Table(Queryable): return fks @property - def virtual_table_using(self) -> Optional[str]: + def virtual_table_using(self) -> str | None: "Type of virtual table, or ``None`` if this is not a virtual table." match = _virtual_table_using_re.match(self.schema) if match is None: @@ -2314,18 +2472,13 @@ class Table(Queryable): return match.groupdict()["using"].upper() @property - def indexes(self) -> List[Index]: + def indexes(self) -> list[Index]: "List of indexes defined on this table." - sql = 'PRAGMA index_list("{}")'.format(self.name) + sql = f"PRAGMA index_list({quote_identifier(self.name)})" indexes = [] for row in self.db.execute_returning_dicts(sql): index_name = row["name"] - index_name_quoted = ( - '"{}"'.format(index_name) - if not index_name.startswith('"') - else index_name - ) - column_sql = "PRAGMA index_info({})".format(index_name_quoted) + column_sql = f"PRAGMA index_info({quote_identifier(index_name)})" columns = [] for seqno, cid, name in self.db.execute(column_sql).fetchall(): columns.append(name) @@ -2338,18 +2491,13 @@ class Table(Queryable): return indexes @property - def xindexes(self) -> List[XIndex]: + def xindexes(self) -> list[XIndex]: "List of indexes defined on this table using the more detailed ``XIndex`` format." - sql = 'PRAGMA index_list("{}")'.format(self.name) + sql = f"PRAGMA index_list({quote_identifier(self.name)})" indexes = [] for row in self.db.execute_returning_dicts(sql): index_name = row["name"] - index_name_quoted = ( - '"{}"'.format(index_name) - if not index_name.startswith('"') - else index_name - ) - column_sql = "PRAGMA index_xinfo({})".format(index_name_quoted) + column_sql = f"PRAGMA index_xinfo({quote_identifier(index_name)})" index_columns = [] for info in self.db.execute(column_sql).fetchall(): index_columns.append(XIndexColumn(*info)) @@ -2357,7 +2505,7 @@ class Table(Queryable): return indexes @property - def triggers(self) -> List[Trigger]: + def triggers(self) -> list[Trigger]: "List of triggers defined on this table." return [ Trigger(*r) @@ -2369,12 +2517,12 @@ class Table(Queryable): ] @property - def triggers_dict(self) -> Dict[str, str]: + def triggers_dict(self) -> dict[str, str]: "``{trigger_name: sql}`` dictionary of triggers defined on this table." return {trigger.name: trigger.sql for trigger in self.triggers} @property - def default_values(self) -> Dict[str, Any]: + def default_values(self) -> dict[str, Any]: "``{column_name: default_value}`` dictionary of default values for columns in this table." return { column.name: _decode_default_value(column.default_value) @@ -2391,20 +2539,20 @@ class Table(Queryable): def create( self, - columns: Dict[str, Any], - pk: Optional[Any] = DEFAULT, - foreign_keys: Union[Optional[ForeignKeysType], Default] = DEFAULT, - column_order: Union[Optional[List[str]], Default] = DEFAULT, - not_null: Union[Optional[Iterable[str]], Default] = DEFAULT, - defaults: Union[Optional[Dict[str, Any]], Default] = DEFAULT, - hash_id: Union[Optional[str], Default] = DEFAULT, - hash_id_columns: Union[Optional[Iterable[str]], Default] = DEFAULT, - extracts: Union[Optional[Union[Dict[str, str], List[str]]], Default] = DEFAULT, + columns: dict[str, Any], + pk: Any | None = DEFAULT, + foreign_keys: ForeignKeysType | None | Default = DEFAULT, + column_order: list[str] | None | Default = DEFAULT, + not_null: Iterable[str] | None | Default = DEFAULT, + defaults: dict[str, Any] | None | Default = DEFAULT, + hash_id: str | None | Default = DEFAULT, + hash_id_columns: Iterable[str] | None | Default = DEFAULT, + extracts: dict[str, str] | list[str] | None | Default = DEFAULT, if_not_exists: bool = False, replace: bool = False, ignore: bool = False, transform: bool = False, - strict: Union[bool, Default] = DEFAULT, + strict: bool | Default | None = DEFAULT, ) -> "Table": """ Create a table with the specified columns. @@ -2475,7 +2623,7 @@ class Table(Queryable): replace=replace, ignore=ignore, transform=transform, - strict=strict, # type: ignore[arg-type] + strict=cast(bool, strict), ) return self @@ -2488,27 +2636,25 @@ class Table(Queryable): if not self.exists(): raise NoTable(f"Table {self.name} does not exist") with self.db.atomic(): - sql = "CREATE TABLE {} AS SELECT * FROM {};".format( - quote_identifier(new_name), - quote_identifier(self.name), - ) + sql = f"CREATE TABLE {quote_identifier(new_name)} AS SELECT * FROM {quote_identifier(self.name)};" self.db.execute(sql) return self.db.table(new_name) def transform( self, *, - types: Optional[dict] = None, - rename: Optional[dict] = None, - drop: Optional[Iterable] = None, - pk: Optional[Any] = DEFAULT, - not_null: Optional[Iterable[str]] = None, - defaults: Optional[Dict[str, Any]] = None, - drop_foreign_keys: Optional[Iterable[str]] = None, - add_foreign_keys: Optional[ForeignKeysType] = None, - foreign_keys: Optional[ForeignKeysType] = None, - column_order: Optional[List[str]] = None, - keep_table: Optional[str] = None, + types: dict | None = None, + rename: dict | None = None, + drop: Iterable | None = None, + pk: Any | None = DEFAULT, + not_null: Iterable[str] | None = None, + defaults: dict[str, Any] | None = None, + drop_foreign_keys: Iterable[str] | None = None, + add_foreign_keys: ForeignKeysType | None = None, + foreign_keys: ForeignKeysType | None = None, + column_order: list[str] | None = None, + keep_table: str | None = None, + strict: bool | None = None, ) -> "Table": """ Apply an advanced alter table, including operations that are not supported by @@ -2516,6 +2662,11 @@ class Table(Queryable): See :ref:`python_api_transform` for full details. + Raises :py:class:`sqlite_utils.db.TransactionError` if called while a + transaction is open with ``PRAGMA foreign_keys`` enabled and the table + is referenced by foreign keys with destructive ``ON DELETE`` actions - + see :ref:`python_api_transform_foreign_keys_transactions`. + :param types: Columns that should have their type changed, for example ``{"weight": float}`` :param rename: Columns to rename, for example ``{"headline": "title"}`` :param drop: Columns to drop @@ -2531,6 +2682,8 @@ class Table(Queryable): to use when creating the table :param keep_table: If specified, the existing table will be renamed to this and will not be dropped + :param strict: Set to ``True`` to make the table strict or ``False`` to make it + non-strict. Defaults to ``None``, which preserves the existing strict mode. """ if not self.exists(): raise ValueError("Cannot transform a table that doesn't exist yet") @@ -2546,6 +2699,7 @@ class Table(Queryable): foreign_keys=foreign_keys, column_order=column_order, keep_table=keep_table, + strict=strict, ) pragma_foreign_keys_was_on = bool( self.db.execute("PRAGMA foreign_keys").fetchone()[0] @@ -2557,6 +2711,36 @@ class Table(Queryable): should_defer_foreign_keys = ( pragma_foreign_keys_was_on and already_in_transaction ) + if should_defer_foreign_keys: + # PRAGMA foreign_keys is a no-op inside a transaction, and + # defer_foreign_keys only defers violation checks, not ON DELETE + # actions - so dropping the old table would still fire destructive + # actions on any tables that reference it. Refuse rather than + # silently modify or delete those rows. + destructive_fks = [ + (table.name, fk) + for table in self.db.tables + for fk in table.foreign_keys + if fk.other_table == self.name + and fk.on_delete in ("CASCADE", "SET NULL", "SET DEFAULT") + ] + if destructive_fks: + raise TransactionError( + "Cannot transform table {table} while a transaction is open: " + "PRAGMA foreign_keys cannot be changed inside a transaction, " + "and the table is referenced by foreign keys with ON DELETE " + "actions that would fire when the old table is dropped: " + "{fks}. Call transform() outside of the transaction, or " + 'execute "PRAGMA foreign_keys = off" before opening it.'.format( + table=self.name, + fks=", ".join( + "{}.{} (ON DELETE {})".format( + table_name, ", ".join(fk.columns), fk.on_delete + ) + for table_name, fk in destructive_fks + ), + ) + ) defer_foreign_keys_was_on = False try: if should_disable_foreign_keys: @@ -2582,24 +2766,27 @@ class Table(Queryable): self.db.execute("PRAGMA defer_foreign_keys=OFF;") if should_disable_foreign_keys: self.db.execute("PRAGMA foreign_keys=1;") + if strict is not None: + self._defaults["strict"] = strict return self def transform_sql( self, *, - types: Optional[dict] = None, - rename: Optional[dict] = None, - drop: Optional[Iterable] = None, - pk: Optional[Any] = DEFAULT, - not_null: Optional[Iterable[str]] = None, - defaults: Optional[Dict[str, Any]] = None, - drop_foreign_keys: Optional[Iterable] = None, - add_foreign_keys: Optional[ForeignKeysType] = None, - foreign_keys: Optional[ForeignKeysType] = None, - column_order: Optional[List[str]] = None, - tmp_suffix: Optional[str] = None, - keep_table: Optional[str] = None, - ) -> List[str]: + types: dict | None = None, + rename: dict | None = None, + drop: Iterable | None = None, + pk: Any | None = DEFAULT, + not_null: Iterable[str] | None = None, + defaults: dict[str, Any] | None = None, + drop_foreign_keys: Iterable | None = None, + add_foreign_keys: ForeignKeysType | None = None, + foreign_keys: ForeignKeysType | None = None, + column_order: list[str] | None = None, + tmp_suffix: str | None = None, + keep_table: str | None = None, + strict: bool | None = None, + ) -> list[str]: """ Return a list of SQL statements that should be executed in order to apply this transformation. @@ -2619,7 +2806,11 @@ class Table(Queryable): :param tmp_suffix: Suffix to use for the temporary table name :param keep_table: If specified, the existing table will be renamed to this and will not be dropped + :param strict: Set to ``True`` to make the table strict or ``False`` to make it + non-strict. Defaults to ``None``, which preserves the existing strict mode. """ + if strict is True and not self.db.supports_strict: + raise TransformError("SQLite does not support STRICT tables") types = types or {} rename = rename or {} drop = drop or set() @@ -2638,7 +2829,7 @@ class Table(Queryable): if isinstance(not_null, dict): not_null = { resolve_casing(c, existing_columns): v - for c, v in cast(Dict[str, Any], not_null).items() + for c, v in cast(dict[str, Any], not_null).items() } elif isinstance(not_null, set): not_null = {resolve_casing(c, existing_columns) for c in not_null} @@ -2649,7 +2840,75 @@ class Table(Queryable): if column_order is not None: column_order = [resolve_casing(c, existing_columns) for c in column_order] - create_table_foreign_keys: List[ForeignKeyIndicator] = [] + try: + existing_checks = self.checks + existing_column_comments = parse_column_comments(self.schema) + existing_autoincrement = parse_autoincrement(self.schema) + existing_uniques = parse_uniques(self.schema) + except ParseError as ex: + raise TransformError( + f"Could not parse table schema for table {self.name!r}: {ex}" + ) from ex + create_table_checks: list[Check] = [] + for check in existing_checks: + owner = ( + resolve_casing(check.column, existing_columns) if check.column else "" + ) + # A column-level constraint disappears with the column that owns it. + if owner and owner in drop: + continue + for dropped_column in drop: + if check_references_identifier(check.check, dropped_column): + raise TransformError( + f"Cannot drop column {dropped_column!r}: it is used by " + f"CHECK constraint {check.name or check.check!r}" + ) + create_table_checks.append( + Check( + rewrite_check_expression(check.check, rename), + name=check.name, + column=rename.get(owner) or owner, + ) + ) + + create_table_uniques: list[Unique] = [] + for unique in existing_uniques: + columns = tuple( + UniqueColumn( + resolve_casing(column.name, existing_columns), + collation=column.collation, + order=column.order, + ) + for column in unique.columns + ) + if any(column.name in drop for column in columns): + continue + owner = ( + resolve_casing(unique.column, existing_columns) if unique.column else "" + ) + create_table_uniques.append( + Unique( + tuple( + UniqueColumn( + rename.get(column.name) or column.name, + collation=column.collation, + order=column.order, + ) + for column in columns + ), + name=unique.name, + column=rename.get(owner) or owner, + conflict=unique.conflict, + ) + ) + + create_table_column_comments: dict[str, ColumnComments] = {} + for column, comments in existing_column_comments.items(): + owner = resolve_casing(column, existing_columns) + if owner not in drop: + create_table_column_comments[rename.get(owner) or owner] = comments + + create_table_foreign_keys: list[ForeignKeyIndicator] = [] if foreign_keys is not None: if add_foreign_keys is not None: @@ -2726,21 +2985,24 @@ class Table(Queryable): for fk in self.db.resolve_foreign_keys(self.name, add_foreign_keys): create_table_foreign_keys.append(fk_with_renamed_columns(fk)) - new_table_name = "{}_new_{}".format( - self.name, tmp_suffix or os.urandom(6).hex() - ) + new_table_name = f"{self.name}_new_{tmp_suffix or os.urandom(6).hex()}" current_column_pairs = list(self.columns_dict.items()) new_column_pairs = [] copy_from_to = {column: column for column, _ in current_column_pairs} for name, type_ in current_column_pairs: type_ = types.get(name) or type_ if name in drop: - del [copy_from_to[name]] + del copy_from_to[name] continue new_name = rename.get(name) or name new_column_pairs.append((new_name, type_)) copy_from_to[name] = new_name + if existing_autoincrement: + existing_autoincrement = resolve_casing( + existing_autoincrement, existing_columns + ) + if pk is DEFAULT: pks_renamed = tuple( rename.get(pk_name) or pk_name @@ -2751,6 +3013,28 @@ class Table(Queryable): else: pk = pks_renamed + create_table_autoincrement = None + if existing_autoincrement and existing_autoincrement not in drop: + renamed_autoincrement = ( + rename.get(existing_autoincrement) or existing_autoincrement + ) + single_pk = pk[0] if isinstance(pk, (list, tuple)) and len(pk) == 1 else pk + new_column_types = dict(new_column_pairs) + if ( + single_pk == renamed_autoincrement + and COLUMN_TYPE_MAPPING.get(new_column_types.get(renamed_autoincrement)) + == "INTEGER" + ): + create_table_autoincrement = renamed_autoincrement + + autoincrement_sequence = None + if create_table_autoincrement: + sequence_row = self.db.execute( + "SELECT seq FROM sqlite_sequence WHERE name = ?", [self.name] + ).fetchone() + if sequence_row is not None: + autoincrement_sequence = sequence_row[0] + # not_null may be a set or dict, need to convert to a set create_table_not_null = { rename.get(c.name) or c.name @@ -2773,9 +3057,7 @@ class Table(Queryable): pass else: raise ValueError( - "not_null must be a dict or a set or None, it was {}".format( - repr(not_null) - ) + f"not_null must be a dict or a set or None, it was {not_null!r}" ) # defaults= create_table_defaults = { @@ -2801,10 +3083,27 @@ class Table(Queryable): defaults=create_table_defaults, foreign_keys=create_table_foreign_keys, column_order=column_order, - strict=self.strict, + strict=self.strict if strict is None else strict, + _checks=create_table_checks, + _column_comments=create_table_column_comments, + _autoincrement=create_table_autoincrement, + _uniques=create_table_uniques, ).strip() ) + # Columns being changed from TEXT to a numeric type: coerce empty strings to NULL + _numeric_sql_types = {"INTEGER", "REAL", "FLOAT", "NUMERIC"} + text_to_numeric_cols = { + col_name + for col_name, new_type in types.items() + if existing_columns.get(col_name) == str + and COLUMN_TYPE_MAPPING.get( + new_type, + new_type.upper() if isinstance(new_type, str) else "", + ) + in _numeric_sql_types + } + # Copy across data, respecting any renamed columns new_cols = [] old_cols = [] @@ -2815,60 +3114,151 @@ class Table(Queryable): if "rowid" not in new_cols: new_cols.insert(0, "rowid") old_cols.insert(0, "rowid") + + def _copy_expr(col): + if col in text_to_numeric_cols: + return "NULLIF({}, '')".format(quote_identifier(col)) + return quote_identifier(col) + copy_sql = "INSERT INTO {} ({new_cols})\n SELECT {old_cols} FROM {};".format( quote_identifier(new_table_name), quote_identifier(self.name), - old_cols=", ".join(quote_identifier(col) for col in old_cols), + old_cols=", ".join(_copy_expr(col) for col in old_cols), new_cols=", ".join(quote_identifier(col) for col in new_cols), ) sqls.append(copy_sql) - # Drop (or keep) the old table - if keep_table: - sqls.append( - "ALTER TABLE {} RENAME TO {};".format( - quote_identifier(self.name), quote_identifier(keep_table) + # Capture indexes before the old table is changed. Simple indexes that + # reference renamed columns are recreated from structured PRAGMA + # metadata instead of editing their stored CREATE INDEX SQL. + index_drop_sqls = [] + index_create_sqls = [] + xindexes_by_name = {index.name: index for index in self.xindexes} + for index in self.indexes: + if index.origin == "pk": + continue + index_sql = self.db.execute( + """SELECT sql FROM sqlite_master WHERE type = 'index' AND name = :index_name;""", + {"index_name": index.name}, + ).fetchall()[0][0] + if index_sql is None: + if index.origin == "u": + # UNIQUE constraints are reproduced in CREATE TABLE above. + continue + raise TransformError( + f"Index '{index.name}' on table '{self.name}' does not have a " + "CREATE INDEX statement. You must manually drop this index prior to running this " + "transformation and manually recreate the new index after running this transformation." ) + dropped_index_column = next( + (column for column in index.columns if column in drop), None + ) + renamed_index_column = next( + (column for column in index.columns if column in rename), None + ) + if dropped_index_column is not None: + raise TransformError( + f"Index '{index.name}' column '{dropped_index_column}' is not in updated table '{self.name}'. " + f"You must manually drop this index prior to running this transformation " + f"and manually recreate the new index after running this transformation. " + f"The original index sql statement is: `{index_sql}`. No changes have been applied to this table." + ) + xindex = xindexes_by_name[index.name] + indexed_columns = sorted( + (column for column in xindex.columns if column.key), + key=lambda column: column.seqno, + ) + if (rename or drop) and ( + index.partial or any(column.name is None for column in indexed_columns) + ): + raise TransformError( + f"Index '{index.name}' is a partial or expression index, so it " + f"cannot be safely recreated while columns are renamed or dropped. " + f"You must manually drop this index prior to running this transformation " + f"and manually recreate the new index after running this transformation. " + f"The original index sql statement is: `{index_sql}`. No changes have been applied to this table." + ) + if renamed_index_column is not None: + columns_sql = [] + for column in indexed_columns: + assert column.name is not None + column_sql = quote_identifier( + rename.get(column.name) or column.name + ) + if column.coll and column.coll.upper() != "BINARY": + column_sql += f" COLLATE {quote_identifier(column.coll)}" + if column.desc: + column_sql += " DESC" + columns_sql.append(column_sql) + index_sql = "CREATE {unique}INDEX {index_name} ON {table_name} ({columns})".format( + unique="UNIQUE " if index.unique else "", + index_name=quote_identifier(index.name), + table_name=quote_identifier(self.name), + columns=", ".join(columns_sql), + ) + index_drop_sqls.append( + f"DROP INDEX IF EXISTS {quote_identifier(index.name)};" + ) + elif keep_table: + index_drop_sqls.append( + f"DROP INDEX IF EXISTS {quote_identifier(index.name)};" + ) + index_create_sqls.append(index_sql) + sqls.extend(index_drop_sqls) + # Drop (or keep) the old table, then rename the new one into place. + # Since SQLite 3.25 ALTER TABLE ... RENAME TO rewrites references to + # the renamed table in every view definition, which fails if a view + # references the table that was just dropped - and with keep_table= + # would silently repoint views at the backup table. These renames are + # an implementation detail of transform(), so use legacy_alter_table + # to leave view definitions untouched, restoring the connection's + # current value afterwards. + legacy_alter_table_row = self.db.execute("PRAGMA legacy_alter_table").fetchone() + legacy_alter_table_was_on = bool( + legacy_alter_table_row and legacy_alter_table_row[0] + ) + if keep_table: + sqls.append("PRAGMA legacy_alter_table=ON;") + sqls.append( + f"ALTER TABLE {quote_identifier(self.name)} RENAME TO {quote_identifier(keep_table)};" ) else: - sqls.append("DROP TABLE {};".format(quote_identifier(self.name))) - # Rename the new one + sqls.append(f"DROP TABLE {quote_identifier(self.name)};") + sqls.append("PRAGMA legacy_alter_table=ON;") sqls.append( - "ALTER TABLE {} RENAME TO {};".format( - quote_identifier(new_table_name), quote_identifier(self.name) + f"ALTER TABLE {quote_identifier(new_table_name)} RENAME TO {quote_identifier(self.name)};" + ) + sqls.append( + "PRAGMA legacy_alter_table={};".format( + "ON" if legacy_alter_table_was_on else "OFF" ) ) + if autoincrement_sequence is not None: + table_name_literal = self.db.quote(self.name) + sqls.extend( + ( + "UPDATE sqlite_sequence SET seq = MAX(seq, {sequence}) " + "WHERE name = {table_name};".format( + sequence=autoincrement_sequence, + table_name=table_name_literal, + ), + "INSERT INTO sqlite_sequence (name, seq) " + "SELECT {table_name}, {sequence} WHERE NOT EXISTS " + "(SELECT 1 FROM sqlite_sequence WHERE name = {table_name});".format( + sequence=autoincrement_sequence, + table_name=table_name_literal, + ), + ) + ) # Re-add existing indexes - for index in self.indexes: - if index.origin != "pk": - index_sql = self.db.execute( - """SELECT sql FROM sqlite_master WHERE type = 'index' AND name = :index_name;""", - {"index_name": index.name}, - ).fetchall()[0][0] - if index_sql is None: - raise TransformError( - f"Index '{index.name}' on table '{self.name}' does not have a " - "CREATE INDEX statement. You must manually drop this index prior to running this " - "transformation and manually recreate the new index after running this transformation." - ) - if keep_table: - sqls.append(f"DROP INDEX IF EXISTS {quote_identifier(index.name)};") - for col in index.columns: - if col in rename.keys() or col in drop: - raise TransformError( - f"Index '{index.name}' column '{col}' is not in updated table '{self.name}'. " - f"You must manually drop this index prior to running this transformation " - f"and manually recreate the new index after running this transformation. " - f"The original index sql statement is: `{index_sql}`. No changes have been applied to this table." - ) - sqls.append(index_sql) + sqls.extend(index_create_sqls) return sqls def extract( self, - columns: Union[str, Iterable[str]], - table: Optional[str] = None, - fk_column: Optional[str] = None, - rename: Optional[Dict[str, str]] = None, + columns: str | Iterable[str], + table: str | None = None, + fk_column: str | None = None, + rename: dict[str, str] | None = None, ) -> "Table": """ Extract specified columns into a separate table. @@ -2887,15 +3277,13 @@ class Table(Queryable): rename = {resolve_casing(k, self.columns_dict): v for k, v in rename.items()} if not set(columns).issubset(self.columns_dict.keys()): raise InvalidColumns( - "Invalid columns {} for table with columns {}".format( - columns, list(self.columns_dict.keys()) - ) + f"Invalid columns {columns} for table with columns {list(self.columns_dict.keys())}" ) with self.db.atomic(): table = table or "_".join(columns) lookup_table = self.db.table(table) - fk_column = fk_column or "{}_id".format(table) - magic_lookup_column = "{}_{}".format(fk_column, os.urandom(6).hex()) + fk_column = fk_column or f"{table}_id" + magic_lookup_column = f"{fk_column}_{os.urandom(6).hex()}" # Populate the lookup table with all of the extracted unique values lookup_columns_definition = { @@ -2904,42 +3292,43 @@ class Table(Queryable): if col in columns } if lookup_table.exists(): + if ( + self.strict + and ANY in lookup_columns_definition.values() + and not lookup_table.strict + ): + raise InvalidColumns( + f"Lookup table {table} already exists but is not STRICT, " + "so it cannot preserve ANY column values" + ) if not set(lookup_columns_definition.items()).issubset( lookup_table.columns_dict.items() ): raise InvalidColumns( - "Lookup table {} already exists but does not have columns {}".format( - table, lookup_columns_definition - ) + f"Lookup table {table} already exists but does not have columns {lookup_columns_definition}" ) else: lookup_table.create( { - **{ - "id": int, - }, + "id": int, **lookup_columns_definition, }, pk="id", + strict=self.strict, ) lookup_columns = [(rename.get(col) or col) for col in columns] lookup_table.create_index(lookup_columns, unique=True, if_not_exists=True) # Rows where every extracted column is null are left alone - they # get a null foreign key and no lookup table record, see #186 all_columns_are_null = " AND ".join( - "{} IS NULL".format(quote_identifier(c)) for c in columns + f"{quote_identifier(c)} IS NULL" for c in columns ) # INSERT OR IGNORE dedupes against the unique index, but unique # indexes treat NULLs as distinct - the NOT EXISTS guard uses IS # comparison so NULL-containing rows match existing lookup rows # instead of being inserted again already_in_lookup = " AND ".join( - "{lookup}.{lookup_col} IS {source}.{source_col}".format( - lookup=quote_identifier(table), - lookup_col=quote_identifier(rename.get(column) or column), - source=quote_identifier(self.name), - source_col=quote_identifier(column), - ) + f"{quote_identifier(table)}.{quote_identifier(rename.get(column) or column)} IS {quote_identifier(self.name)}.{quote_identifier(column)}" for column in columns ) self.db.execute( @@ -2967,12 +3356,10 @@ class Table(Queryable): quote_identifier(magic_lookup_column), quote_identifier(table), where=" AND ".join( - "{}.{} IS {}.{}".format( - quote_identifier(self.name), - quote_identifier(column), - quote_identifier(table), - quote_identifier(rename.get(column) or column), - ) + f"{quote_identifier(self.name)}." + f"{quote_identifier(column)} IS " + f"{quote_identifier(table)}." + f"{quote_identifier(rename.get(column) or column)}" for column in columns ), all_null=all_columns_are_null, @@ -3001,8 +3388,8 @@ class Table(Queryable): def create_index( self, - columns: Iterable[Union[str, DescIndex]], - index_name: Optional[str] = None, + columns: Iterable[str | DescIndex], + index_name: str | None = None, unique: bool = False, if_not_exists: bool = False, find_unique_name: bool = False, @@ -3029,16 +3416,14 @@ class Table(Queryable): columns_sql = [] for column in columns: if isinstance(column, DescIndex): - columns_sql.append("{} desc".format(quote_identifier(column))) + columns_sql.append(f"{quote_identifier(column)} desc") else: columns_sql.append(quote_identifier(column)) suffix = None created_index_name = None while True: - created_index_name = ( - "{}_{}".format(index_name, suffix) if suffix else index_name - ) + created_index_name = f"{index_name}_{suffix}" if suffix else index_name sql = ( textwrap.dedent(""" CREATE {unique}INDEX {if_not_exists}{index_name} @@ -3070,18 +3455,32 @@ class Table(Queryable): suffix += 1 continue else: - raise e + raise if analyze: self.db.analyze(created_index_name) return self + def drop_index(self, index_name: str, ignore: bool = False): + """ + Drop an index on this table. + + :param index_name: Name of the index to drop + :param ignore: Set to ``True`` to ignore the error if the index does not exist + """ + if index_name not in {index.name for index in self.indexes}: + if ignore: + return self + raise OperationalError(f"No index named {index_name} on table {self.name}") + self.db.execute(f"DROP INDEX {quote_identifier(index_name)}") + return self + def add_column( self, col_name: str, - col_type: Optional[Any] = None, - fk: Optional[str] = None, - fk_col: Optional[str] = None, - not_null_default: Optional[Any] = None, + col_type: Any | None = None, + fk: str | None = None, + fk_col: str | None = None, + not_null_default: Any | None = None, ): """ Add a column to this table. See :ref:`python_api_add_column`. @@ -3096,12 +3495,12 @@ class Table(Queryable): if fk is not None: # fk must be a valid table if fk not in self.db.table_names(): - raise AlterError("table '{}' does not exist".format(fk)) + raise AlterError(f"table '{fk}' does not exist") # if fk_col specified, must be a valid column if fk_col is not None: fk_col = resolve_casing(fk_col, self.db[fk].columns_dict) if fk_col not in self.db[fk].columns_dict: - raise AlterError("table '{}' has no column {}".format(fk, fk_col)) + raise AlterError(f"table '{fk}' has no column {fk_col}") else: # automatically set fk_col to first primary_key of fk table pks = sorted( @@ -3118,8 +3517,8 @@ class Table(Queryable): col_type = str not_null_sql = None if not_null_default is not None: - not_null_sql = "NOT NULL DEFAULT {}".format( - self.db.quote_default_value(not_null_default) + not_null_sql = ( + f"NOT NULL DEFAULT {self.db.quote_default_value(not_null_default)}" ) sql = "ALTER TABLE {} ADD COLUMN {} {col_type}{not_null_default};".format( quote_identifier(self.name), @@ -3139,7 +3538,7 @@ class Table(Queryable): :param ignore: Set to ``True`` to ignore the error if the table does not exist """ try: - self.db.execute("DROP TABLE {}".format(quote_identifier(self.name))) + self.db.execute(f"DROP TABLE {quote_identifier(self.name)}") except sqlite3.OperationalError: if not ignore: raise @@ -3171,16 +3570,14 @@ class Table(Queryable): return existing_tables[table] # If we get here there's no obvious candidate - raise an error raise NoObviousTable( - "No obvious foreign key table for column '{}' - tried {}".format( - column, repr(possibilities) - ) + f"No obvious foreign key table for column '{column}' - tried {possibilities!r}" ) def guess_foreign_column(self, other_table: str) -> str: pks = [c for c in self.db[other_table].columns if c.is_pk] if len(pks) != 1: raise BadPrimaryKey( - "Could not detect single primary key for table '{}'".format(other_table) + f"Could not detect single primary key for table '{other_table}'" ) else: return pks[0].name @@ -3188,8 +3585,8 @@ class Table(Queryable): def add_foreign_key( self, column: ForeignKeyColumns, - other_table: Optional[str] = None, - other_column: Optional[ForeignKeyColumns] = None, + other_table: str | None = None, + other_column: ForeignKeyColumns | None = None, ignore: bool = False, on_delete: str = "NO ACTION", on_update: str = "NO ACTION", @@ -3208,18 +3605,21 @@ class Table(Queryable): :param on_update: ``ON UPDATE`` action for the foreign key. """ columns = (column,) if isinstance(column, str) else tuple(column) + if not columns: + raise ValueError("column must contain at least one column name") columns = tuple(resolve_casing(c, self.columns_dict) for c in columns) + assert columns # Ensure columns exist for col in columns: if col not in self.columns_dict: - raise AlterError("No such column: {}".format(col)) + raise AlterError(f"No such column: {col}") # If other_table is not specified, attempt to guess it from the column if other_table is None: if len(columns) > 1: raise ValueError( "other_table must be specified for a compound foreign key" ) - other_table = self.guess_foreign_table(columns[0]) + other_table = self.guess_foreign_table(next(iter(columns))) # If other_column is not specified, detect the primary key on other_table if other_column is None: if len(columns) > 1: @@ -3245,7 +3645,7 @@ class Table(Queryable): not [c for c in self.db[other_table].columns if c.name == other_col] and other_col != "rowid" ): - raise AlterError("No such column: {}.{}".format(other_table, other_col)) + raise AlterError(f"No such column: {other_table}.{other_col}") # Check we do not already have an existing foreign key if any( fk @@ -3346,9 +3746,7 @@ class Table(Queryable): def has_counts_triggers(self) -> bool: "Does this table have triggers setup to update cached counts?" trigger_names = { - "{table}{counts_table}_{suffix}".format( - counts_table=self.db._counts_table_name, table=self.name, suffix=suffix - ) + f"{self.name}{self.db._counts_table_name}_{suffix}" for suffix in ["insert", "delete"] } return trigger_names.issubset(self.triggers_dict.keys()) @@ -3358,7 +3756,7 @@ class Table(Queryable): columns: Iterable[str], fts_version: str = "FTS5", create_triggers: bool = False, - tokenize: Optional[str] = None, + tokenize: str | None = None, replace: bool = False, ): """ @@ -3385,13 +3783,15 @@ class Table(Queryable): table_fts=quote_identifier(self.name + "_fts"), columns=", ".join(quote_identifier(c) for c in columns), fts_version=fts_version, - tokenize="\n tokenize='{}',".format(tokenize) if tokenize else "", + tokenize=( + f"\n tokenize={self.db.quote(tokenize)}," if tokenize else "" + ), ) ) should_recreate = False - if replace and self.db["{}_fts".format(self.name)].exists(): + if replace and self.db[f"{self.name}_fts"].exists(): # Does the table need to be recreated? - fts_schema = self.db["{}_fts".format(self.name)].schema + fts_schema = self.db[f"{self.name}_fts"].schema if fts_schema != create_fts_sql: should_recreate = True expected_triggers = {self.name + suffix for suffix in ("_ai", "_ad", "_au")} @@ -3410,8 +3810,8 @@ class Table(Queryable): self.populate_fts(columns) if create_triggers: - old_cols = ", ".join("old.{}".format(quote_identifier(c)) for c in columns) - new_cols = ", ".join("new.{}".format(quote_identifier(c)) for c in columns) + old_cols = ", ".join(f"old.{quote_identifier(c)}" for c in columns) + new_cols = ", ".join(f"new.{quote_identifier(c)}" for c in columns) columns_quoted = ", ".join(quote_identifier(c) for c in columns) table = quote_identifier(self.name) table_fts = quote_identifier(self.name + "_fts") @@ -3483,7 +3883,7 @@ class Table(Queryable): with self.db.atomic(): for trigger_name in trigger_names: self.db.execute( - "DROP TRIGGER IF EXISTS {}".format(quote_identifier(trigger_name)) + f"DROP TRIGGER IF EXISTS {quote_identifier(trigger_name)}" ) return self @@ -3501,7 +3901,7 @@ class Table(Queryable): ) return self - def detect_fts(self) -> Optional[str]: + def detect_fts(self) -> str | None: "Detect if table has a corresponding FTS virtual table and return it" sql = textwrap.dedent(""" SELECT name FROM sqlite_master @@ -3516,8 +3916,8 @@ class Table(Queryable): ) """).strip() args = { - "like": "%VIRTUAL TABLE%USING FTS%content=[{}]%".format(self.name), - "like2": '%VIRTUAL TABLE%USING FTS%content="{}"%'.format(self.name), + "like": f"%VIRTUAL TABLE%USING FTS%content=[{self.name}]%", + "like2": f'%VIRTUAL TABLE%USING FTS%content="{self.name}"%', "table": self.name, } rows = self.db.execute(sql, args).fetchall() @@ -3538,11 +3938,11 @@ class Table(Queryable): def search_sql( self, - columns: Optional[Iterable[str]] = None, - order_by: Optional[str] = None, - limit: Optional[int] = None, - offset: Optional[int] = None, - where: Optional[str] = None, + columns: Iterable[str] | None = None, + order_by: str | None = None, + limit: int | None = None, + offset: int | None = None, + where: str | None = None, include_rank: bool = False, ) -> str: """ " @@ -3559,16 +3959,16 @@ class Table(Queryable): original = "original_" if self.name == "original" else "original" original_quoted = quote_identifier(original) columns_sql = "*" - columns_with_prefix_sql = "{}.*".format(original_quoted) + columns_with_prefix_sql = f"{original_quoted}.*" if columns: columns_sql = ",\n ".join(quote_identifier(c) for c in columns) columns_with_prefix_sql = ",\n ".join( - "{}.{}".format(original_quoted, quote_identifier(c)) for c in columns + f"{original_quoted}.{quote_identifier(c)}" for c in columns ) fts_table = self.detect_fts() if not fts_table: raise ValueError( - "Full-text search is not configured for table '{}'".format(self.name) + f"Full-text search is not configured for table '{self.name}'" ) fts_table_quoted = quote_identifier(fts_table) virtual_table_using = self.db.table(fts_table).virtual_table_using @@ -3591,22 +3991,22 @@ class Table(Queryable): {limit_offset} """).strip() if virtual_table_using == "FTS5": - rank_implementation = "{}.rank".format(fts_table_quoted) + rank_implementation = f"{fts_table_quoted}.rank" else: self.db.register_fts4_bm25() - rank_implementation = "rank_bm25(matchinfo({}, 'pcnalx'))".format( - fts_table_quoted - ) + rank_implementation = f"rank_bm25(matchinfo({fts_table_quoted}, 'pcnalx'))" if include_rank: columns_with_prefix_sql += ",\n " + rank_implementation + " rank" limit_offset = "" if limit is not None: - limit_offset += " limit {}".format(limit) + limit_offset += f" limit {limit}" if offset is not None: - limit_offset += " offset {}".format(offset) + if limit is None: + limit_offset += " limit -1" + limit_offset += f" offset {offset}" return sql.format( dbtable=quote_identifier(self.name), - where_clause="\n where {}".format(where) if where else "", + where_clause=f"\n where {where}" if where else "", original=original_quoted, columns=columns_sql, columns_with_prefix=columns_with_prefix_sql, @@ -3618,12 +4018,12 @@ class Table(Queryable): def search( self, q: str, - order_by: Optional[str] = None, - columns: Optional[Iterable[str]] = None, - limit: Optional[int] = None, - offset: Optional[int] = None, - where: Optional[str] = None, - where_args: Optional[Union[Iterable, dict]] = None, + order_by: str | None = None, + columns: Iterable[str] | None = None, + limit: int | None = None, + offset: int | None = None, + where: str | None = None, + where_args: Iterable | dict | None = None, include_rank: bool = False, quote: bool = False, ) -> Generator[dict, None, None]: @@ -3666,10 +4066,12 @@ class Table(Queryable): for row in cursor: yield dict(zip(columns, row)) - def value_or_default(self, key: str, value: Any) -> Any: - return self._defaults[key] if value is DEFAULT else value + def value_or_default(self, key: str, value: T | Default) -> T: + if value is DEFAULT: + return cast(T, self._defaults[key]) + return cast(T, value) - def delete(self, pk_values: Union[list, tuple, str, int, float]) -> "Table": + def delete(self, pk_values: list | tuple | str | float) -> "Table": """ Delete row matching the specified primary key. @@ -3678,7 +4080,7 @@ class Table(Queryable): if not isinstance(pk_values, (list, tuple)): pk_values = [pk_values] self.get(pk_values) - wheres = ["{} = ?".format(quote_identifier(pk_name)) for pk_name in self.pks] + wheres = [f"{quote_identifier(pk_name)} = ?" for pk_name in self.pks] sql = "delete from {} where {wheres}".format( quote_identifier(self.name), wheres=" and ".join(wheres) ) @@ -3688,8 +4090,8 @@ class Table(Queryable): def delete_where( self, - where: Optional[str] = None, - where_args: Optional[Union[Sequence, Dict[str, Any]]] = None, + where: str | None = None, + where_args: Sequence | dict[str, Any] | None = None, analyze: bool = False, ) -> "Table": """ @@ -3704,7 +4106,7 @@ class Table(Queryable): """ if not self.exists(): return self - sql = "delete from {}".format(quote_identifier(self.name)) + sql = f"delete from {quote_identifier(self.name)}" if where is not None: sql += " where " + where with self.db.atomic(): @@ -3715,10 +4117,10 @@ class Table(Queryable): def update( self, - pk_values: Union[list, tuple, str, int, float], - updates: Optional[dict] = None, + pk_values: list | tuple | str | float, + updates: dict | None = None, alter: bool = False, - conversions: Optional[dict] = None, + conversions: dict | None = None, ) -> "Table": """ Execute a SQL ``UPDATE`` against the specified row. @@ -3749,7 +4151,7 @@ class Table(Queryable): "{} = {}".format(quote_identifier(key), conversions.get(key, "?")) ) args.append(jsonify_if_needed(value)) - wheres = ["{} = ?".format(quote_identifier(pk_name)) for pk_name in pks] + wheres = [f"{quote_identifier(pk_name)} = ?" for pk_name in pks] args.extend(pk_values) sql = "update {} set {sets} where {wheres}".format( quote_identifier(self.name), @@ -3774,14 +4176,14 @@ class Table(Queryable): def convert( self, - columns: Union[str, List[str]], + columns: str | list[str], fn: Callable, - output: Optional[str] = None, - output_type: Optional[Any] = None, + output: str | None = None, + output_type: Any | None = None, drop: bool = False, multi: bool = False, - where: Optional[str] = None, - where_args: Optional[Union[Sequence, Dict[str, Any]]] = None, + where: str | None = None, + where_args: Sequence | dict[str, Any] | None = None, show_progress: bool = False, ) -> "Table": """ @@ -3838,15 +4240,11 @@ class Table(Queryable): quote_identifier(self.name), sets=", ".join( [ - "{} = {}({})".format( - quote_identifier(output or column), - fn_name, - quote_identifier(column), - ) + f"{quote_identifier(output or column)} = {fn_name}({quote_identifier(column)})" for column in columns ] ), - where=" where {}".format(where) if where is not None else "", + where=f" where {where}" if where is not None else "", ) with self.db.atomic(): self.db.execute(sql, where_args or []) @@ -3856,10 +4254,10 @@ class Table(Queryable): def _convert_multi( self, column, fn, drop, show_progress, where=None, where_args=None - ): + ) -> "Table": # First we execute the function pk_to_values = {} - new_column_types: Dict[str, Set[type]] = {} + new_column_types: dict[str, set[type]] = {} pks = self.pks with progressbar( @@ -3891,15 +4289,18 @@ class Table(Queryable): self.add_column(column_name, column_type) # Run the updates - with progressbar( - length=self.count, silent=not show_progress, label="2: Updating" - ) as bar: - with self.db.atomic(): - for pk, updates in pk_to_values.items(): - self.update(pk, updates) - bar.update(1) - if drop: - self.transform(drop=(column,)) + with ( + progressbar( + length=self.count, silent=not show_progress, label="2: Updating" + ) as bar, + self.db.atomic(), + ): + for pk, updates in pk_to_values.items(): + self.update(pk, updates) + bar.update(1) + if drop: + self.transform(drop=(column,)) + return self def build_insert_queries_and_params( self, @@ -4099,9 +4500,7 @@ class Table(Queryable): ) for col in set_cols ), - wheres=" AND ".join( - "{} = ?".format(quote_identifier(pk)) for pk in pks - ), + wheres=" AND ".join(f"{quote_identifier(pk)} = ?" for pk in pks), ) queries_and_params.append( ( @@ -4134,7 +4533,7 @@ class Table(Queryable): replace, ignore, list_mode=False, - ) -> Optional[sqlite3.Cursor]: + ) -> sqlite3.Cursor | None: queries_and_params = self.build_insert_queries_and_params( extracts, chunk, @@ -4204,21 +4603,21 @@ class Table(Queryable): def insert( self, - record: Dict[str, Any], - pk=DEFAULT, - foreign_keys=DEFAULT, - column_order: Optional[Union[List[str], Default]] = DEFAULT, - not_null: Optional[Union[Iterable[str], Default]] = DEFAULT, - defaults: Optional[Union[Dict[str, Any], Default]] = DEFAULT, - hash_id: Optional[Union[str, Default]] = DEFAULT, - hash_id_columns: Optional[Union[Iterable[str], Default]] = DEFAULT, - alter: Optional[Union[bool, Default]] = DEFAULT, - ignore: Optional[Union[bool, Default]] = DEFAULT, - replace: Optional[Union[bool, Default]] = DEFAULT, - extracts: Optional[Union[Dict[str, str], List[str], Default]] = DEFAULT, - conversions: Optional[Union[Dict[str, str], Default]] = DEFAULT, - columns: Optional[Union[Dict[str, Any], Default]] = DEFAULT, - strict: Optional[Union[bool, Default]] = DEFAULT, + record: dict[str, Any], + pk: PrimaryKey | Default | None = DEFAULT, + foreign_keys: ForeignKeysType | Default | None = DEFAULT, + column_order: list[str] | Default | None = DEFAULT, + not_null: Iterable[str] | Default | None = DEFAULT, + defaults: dict[str, Any] | Default | None = DEFAULT, + hash_id: str | Default | None = DEFAULT, + hash_id_columns: Iterable[str] | Default | None = DEFAULT, + alter: bool | Default | None = DEFAULT, + ignore: bool | Default | None = DEFAULT, + replace: bool | Default | None = DEFAULT, + extracts: dict[str, str] | list[str] | Default | None = DEFAULT, + conversions: dict[str, str] | Default | None = DEFAULT, + columns: dict[str, Any] | Default | None = DEFAULT, + strict: bool | Default | None = DEFAULT, ) -> "Table": """ Insert a single record into the table. The table will be created with a schema that matches @@ -4273,28 +4672,25 @@ class Table(Queryable): def insert_all( self, - records: Union[ - Iterable[Dict[str, Any]], - Iterable[Sequence[Any]], - ], - pk=DEFAULT, - foreign_keys=DEFAULT, - column_order=DEFAULT, - not_null=DEFAULT, - defaults=DEFAULT, - batch_size=DEFAULT, - hash_id=DEFAULT, - hash_id_columns=DEFAULT, - alter=DEFAULT, - ignore=DEFAULT, - replace=DEFAULT, - truncate=False, - extracts=DEFAULT, - conversions=DEFAULT, - columns=DEFAULT, - upsert=False, - analyze=False, - strict=DEFAULT, + records: Iterable[dict[str, Any]] | Iterable[Sequence[Any]], + pk: PrimaryKey | Default | None = DEFAULT, + foreign_keys: ForeignKeysType | Default | None = DEFAULT, + column_order: list[str] | Default | None = DEFAULT, + not_null: Iterable[str] | Default | None = DEFAULT, + defaults: dict[str, Any] | Default | None = DEFAULT, + batch_size: int | Default = DEFAULT, + hash_id: str | Default | None = DEFAULT, + hash_id_columns: Iterable[str] | Default | None = DEFAULT, + alter: bool | Default | None = DEFAULT, + ignore: bool | Default | None = DEFAULT, + replace: bool | Default | None = DEFAULT, + truncate: bool = False, + extracts: dict[str, str] | list[str] | Default | None = DEFAULT, + conversions: dict[str, str] | Default | None = DEFAULT, + columns: dict[str, Any] | Default | None = DEFAULT, + upsert: bool = False, + analyze: bool = False, + strict: bool | Default | None = DEFAULT, ) -> "Table": """ Like ``.insert()`` but takes a list of records and ensures that the table @@ -4343,10 +4739,14 @@ class Table(Queryable): if pk and not hash_id and self.exists(): pk_cols = [pk] if isinstance(pk, str) else list(pk) existing_columns = self.columns_dict + # rowid and its aliases are valid primary keys for a rowid table + # even though they are not listed among the table's columns + rowid_aliases = ROWID_ALIASES if self.use_rowid else frozenset() missing_pk_cols = [ col for col in pk_cols - if resolve_casing(col, existing_columns) not in existing_columns + if col.lower() not in rowid_aliases + and resolve_casing(col, existing_columns) not in existing_columns ] if missing_pk_cols: invalid_pk_error = InvalidColumns( @@ -4369,7 +4769,7 @@ class Table(Queryable): # Detect if we're using list-based iteration or dict-based iteration list_mode = False - column_names: List[str] = [] + column_names: list[str] = [] # Fix up any records with square braces in the column names (only for dict mode) # We'll handle this differently for list mode @@ -4389,7 +4789,7 @@ class Table(Queryable): raise ValueError( "When using list-based iteration, the first yielded value must be a list of column name strings" ) - column_names = cast(List[str], list(first_record)) + column_names = cast(list[str], list(first_record)) all_columns = column_names num_columns = len(column_names) # Get the actual first data record @@ -4398,7 +4798,7 @@ class Table(Queryable): except StopIteration: return self # Only headers, no data if not isinstance(first_record, (list, tuple)): - raise ValueError( + raise ValueError( # noqa: TRY004 "After column names list, all subsequent records must also be lists" ) else: @@ -4408,13 +4808,11 @@ class Table(Queryable): first_record = next(records_iter) except StopIteration: return self - first_record = cast(Dict[str, Any], first_record) + first_record = cast(dict[str, Any], first_record) num_columns = len(first_record.keys()) if num_columns > SQLITE_MAX_VARS: - raise ValueError( - "Rows can have a maximum of {} columns".format(SQLITE_MAX_VARS) - ) + raise ValueError(f"Rows can have a maximum of {SQLITE_MAX_VARS} columns") batch_size = ( 1 if num_columns == 0 @@ -4424,7 +4822,7 @@ class Table(Queryable): self.last_pk = None if truncate and self.exists(): with self.db.atomic(): - self.db.execute("DELETE FROM {};".format(quote_identifier(self.name))) + self.db.execute(f"DELETE FROM {quote_identifier(self.name)};") result = None for chunk in chunks(itertools.chain([first_record], records_iter), batch_size): chunk = list(chunk) @@ -4437,7 +4835,7 @@ class Table(Queryable): chunk_as_dicts = [dict(zip(column_names, row)) for row in chunk] column_types = suggest_column_types(chunk_as_dicts) else: - dict_chunk = cast(List[Dict[str, Any]], chunk) + dict_chunk = cast(list[dict[str, Any]], chunk) column_types = suggest_column_types(dict_chunk) if extracts: for col in extracts: @@ -4464,10 +4862,10 @@ class Table(Queryable): if hash_id: all_columns.insert(0, hash_id) else: - all_columns_set: Set[str] = set() - for record in cast(List[Dict[str, Any]], chunk): + all_columns_set: set[str] = set() + for record in cast(list[dict[str, Any]], chunk): all_columns_set.update(record.keys()) - all_columns = list(sorted(all_columns_set)) + all_columns = sorted(all_columns_set) if hash_id: all_columns.insert(0, hash_id) if deferred_invalid_pk_check is not None: @@ -4482,7 +4880,7 @@ class Table(Queryable): raise invalid_pk_error else: if not list_mode: - for record in cast(List[Dict[str, Any]], chunk): + for record in cast(list[dict[str, Any]], chunk): all_columns += [ column for column in record if column not in all_columns ] @@ -4512,47 +4910,80 @@ class Table(Queryable): if not upsert and result is not None: ignored_insert = ignore and result.rowcount == 0 if ignored_insert: + # The row was not inserted because it conflicts with an + # existing row. Point last_pk / last_rowid at that existing + # row when we can identify it from the record's primary key + # values, rather than leaving them stale or unset. if list_mode: - first_record_list = cast(Sequence[Any], first_record) - if hash_id: - pass - elif isinstance(pk, str): - pk_index = column_names.index( - resolve_casing(pk, column_names) - ) - self.last_pk = first_record_list[pk_index] - elif pk: - self.last_pk = tuple( - first_record_list[ - column_names.index(resolve_casing(p, column_names)) - ] - for p in pk - ) + first_record_dict = dict( + zip(column_names, cast(Sequence[Any], first_record)) + ) else: - first_record_dict = cast(Dict[str, Any], first_record) - if hash_id: - self.last_pk = hash_record( - first_record_dict, hash_id_columns - ) - elif isinstance(pk, str): - self.last_pk = first_record_dict[ - resolve_casing(pk, first_record_dict) + first_record_dict = cast(dict[str, Any], first_record) + if hash_id: + self.last_pk = hash_record(first_record_dict, hash_id_columns) + elif isinstance(pk, str): + self.last_pk = first_record_dict[ + resolve_casing(pk, first_record_dict) + ] + elif pk: + self.last_pk = tuple( + first_record_dict[resolve_casing(p, first_record_dict)] + for p in pk + ) + # Locate the existing conflicting row using its primary key + # columns so we can report its rowid (and pk if not already + # known). Falls back to leaving them unset if the conflict + # cannot be resolved to a pk lookup (e.g. a UNIQUE column). + key_cols: list[str] | None = None + if isinstance(pk, str): + key_cols = [pk] + elif pk: + key_cols = list(pk) + elif not hash_id and not self.use_rowid: + key_cols = self.pks + if key_cols: + try: + key_values = [ + first_record_dict[resolve_casing(c, first_record_dict)] + for c in key_cols ] - elif pk: - self.last_pk = tuple( - first_record_dict[resolve_casing(p, first_record_dict)] - for p in pk + except KeyError: + key_values = None + if key_values is not None: + where = " and ".join( + f"{quote_identifier(c)} = ?" for c in key_cols ) + existing = self.db.execute( + f"select rowid from {quote_identifier(self.name)} where {where} limit 1", + key_values, + ).fetchone() + if existing is not None: + self.last_rowid = existing[0] + # On a primary key conflict the record's pk + # values identify the existing row + if self.last_pk is None: + self.last_pk = ( + key_values[0] + if len(key_cols) == 1 + else tuple(key_values) + ) else: self.last_rowid = result.lastrowid - if (hash_id or pk) and self.last_rowid: + # A rowid-alias pk resolves directly to the rowid, so there + # is no separate pk column to look up + rowid_pk = isinstance(pk, str) and pk.lower() in ROWID_ALIASES + if (hash_id or (pk and not rowid_pk)) and self.last_rowid: # Set self.last_pk to the pk(s) for that rowid - row = list(self.rows_where("rowid = ?", [self.last_rowid]))[0] + row = next( + iter(self.rows_where("rowid = ?", [self.last_rowid])) + ) if hash_id: self.last_pk = row[hash_id] elif isinstance(pk, str): self.last_pk = row[resolve_casing(pk, row)] else: + assert pk is not None self.last_pk = tuple( row[resolve_casing(p, row)] for p in pk ) @@ -4570,6 +5001,7 @@ class Table(Queryable): pk_index = column_names.index(resolve_casing(pk, column_names)) self.last_pk = first_record_list[pk_index] else: + assert pk is not None self.last_pk = tuple( first_record_list[ column_names.index(resolve_casing(p, column_names)) @@ -4577,10 +5009,11 @@ class Table(Queryable): for p in pk ) else: - first_record_dict = cast(Dict[str, Any], first_record) + first_record_dict = cast(dict[str, Any], first_record) if hash_id: self.last_pk = hash_record(first_record_dict, hash_id_columns) else: + assert pk is not None self.last_pk = ( first_record_dict[resolve_casing(pk, first_record_dict)] if isinstance(pk, str) @@ -4597,19 +5030,19 @@ class Table(Queryable): def upsert( self, - record, - pk=DEFAULT, - foreign_keys=DEFAULT, - column_order=DEFAULT, - not_null=DEFAULT, - defaults=DEFAULT, - hash_id=DEFAULT, - hash_id_columns=DEFAULT, - alter=DEFAULT, - extracts=DEFAULT, - conversions=DEFAULT, - columns=DEFAULT, - strict=DEFAULT, + record: dict[str, Any], + pk: PrimaryKey | Default | None = DEFAULT, + foreign_keys: ForeignKeysType | Default | None = DEFAULT, + column_order: list[str] | Default | None = DEFAULT, + not_null: Iterable[str] | Default | None = DEFAULT, + defaults: dict[str, Any] | Default | None = DEFAULT, + hash_id: str | Default | None = DEFAULT, + hash_id_columns: Iterable[str] | Default | None = DEFAULT, + alter: bool | Default | None = DEFAULT, + extracts: dict[str, str] | list[str] | Default | None = DEFAULT, + conversions: dict[str, str] | Default | None = DEFAULT, + columns: dict[str, Any] | Default | None = DEFAULT, + strict: bool | Default | None = DEFAULT, ) -> "Table": """ Like ``.insert()`` but performs an ``UPSERT``, where records are inserted if they do @@ -4635,24 +5068,21 @@ class Table(Queryable): def upsert_all( self, - records: Union[ - Iterable[Dict[str, Any]], - Iterable[Sequence[Any]], - ], - pk=DEFAULT, - foreign_keys=DEFAULT, - column_order=DEFAULT, - not_null=DEFAULT, - defaults=DEFAULT, - batch_size=DEFAULT, - hash_id=DEFAULT, - hash_id_columns=DEFAULT, - alter=DEFAULT, - extracts=DEFAULT, - conversions=DEFAULT, - columns=DEFAULT, - analyze=False, - strict=DEFAULT, + records: Iterable[dict[str, Any]] | Iterable[Sequence[Any]], + pk: PrimaryKey | Default | None = DEFAULT, + foreign_keys: ForeignKeysType | Default | None = DEFAULT, + column_order: list[str] | Default | None = DEFAULT, + not_null: Iterable[str] | Default | None = DEFAULT, + defaults: dict[str, Any] | Default | None = DEFAULT, + batch_size: int | Default = DEFAULT, + hash_id: str | Default | None = DEFAULT, + hash_id_columns: Iterable[str] | Default | None = DEFAULT, + alter: bool | Default | None = DEFAULT, + extracts: dict[str, str] | list[str] | Default | None = DEFAULT, + conversions: dict[str, str] | Default | None = DEFAULT, + columns: dict[str, Any] | Default | None = DEFAULT, + analyze: bool = False, + strict: bool | Default | None = DEFAULT, ) -> "Table": """ Like ``.upsert()`` but can be applied to a list of records. @@ -4676,7 +5106,7 @@ class Table(Queryable): strict=strict, ) - def add_missing_columns(self, records: Iterable[Dict[str, Any]]) -> "Table": + def add_missing_columns(self, records: Iterable[dict[str, Any]]) -> "Table": needed_columns = suggest_column_types(records) current_columns = {c.lower() for c in self.columns_dict} for col_name, col_type in needed_columns.items(): @@ -4686,17 +5116,17 @@ class Table(Queryable): def lookup( self, - lookup_values: Dict[str, Any], - extra_values: Optional[Dict[str, Any]] = None, - pk: Optional[str] = "id", - foreign_keys: Optional[ForeignKeysType] = None, - column_order: Optional[List[str]] = None, - not_null: Optional[Iterable[str]] = None, - defaults: Optional[Dict[str, Any]] = None, - extracts: Optional[Union[Dict[str, str], List[str]]] = None, - conversions: Optional[Dict[str, str]] = None, - columns: Optional[Dict[str, Any]] = None, - strict: Optional[bool] = False, + lookup_values: dict[str, Any], + extra_values: dict[str, Any] | None = None, + pk: str | None = "id", + foreign_keys: ForeignKeysType | None = None, + column_order: list[str] | None = None, + not_null: Iterable[str] | None = None, + defaults: dict[str, Any] | None = None, + extracts: dict[str, str] | list[str] | None = None, + conversions: dict[str, str] | None = None, + columns: dict[str, Any] | None = None, + strict: bool | None = False, ): """ Create or populate a lookup table with the specified values. @@ -4722,7 +5152,7 @@ class Table(Queryable): :param strict: Boolean, apply STRICT mode if creating the table. """ if not isinstance(lookup_values, dict): - raise ValueError("lookup_values must be a dictionary") + raise ValueError("lookup_values must be a dictionary") # noqa: TRY004 if pk is None: raise ValueError("pk cannot be None") if extra_values is not None and not isinstance(extra_values, dict): @@ -4740,9 +5170,7 @@ class Table(Queryable): } not in unique_column_sets: self.create_index(lookup_values.keys(), unique=True) # IS rather than = so that null values are matched correctly - wheres = [ - "{} IS ?".format(quote_identifier(column)) for column in lookup_values - ] + wheres = [f"{quote_identifier(column)} IS ?" for column in lookup_values] rows = list( self.rows_where( " and ".join(wheres), [value for _, value in lookup_values.items()] @@ -4782,12 +5210,10 @@ class Table(Queryable): def m2m( self, other_table: Union[str, "Table"], - record_or_iterable: Optional[ - Union[Iterable[Dict[str, Any]], Dict[str, Any]] - ] = None, - pk: Optional[Union[Any, Default]] = DEFAULT, - lookup: Optional[Dict[str, Any]] = None, - m2m_table: Optional[str] = None, + record_or_iterable: Iterable[dict[str, Any]] | dict[str, Any] | None = None, + pk: Any | Default | None = DEFAULT, + lookup: dict[str, Any] | None = None, + m2m_table: str | None = None, alter: bool = False, ): """ @@ -4820,8 +5246,8 @@ class Table(Queryable): raise ValueError("Provide lookup= or record, not both") elif record_or_iterable is None: raise ValueError("Provide lookup= or record, not both") - tables = list(sorted([self.name, other_table.name])) - columns = ["{}_id".format(t) for t in tables] + tables = sorted([self.name, other_table.name]) + columns = [f"{t}_id" for t in tables] if m2m_table is not None: m2m_table_name = m2m_table else: @@ -4831,9 +5257,7 @@ class Table(Queryable): m2m_table_name = candidates[0] elif len(candidates) > 1: raise NoObviousTable( - "No single obvious m2m table for {}, {} - use m2m_table= parameter".format( - self.name, other_table.name - ) + f"No single obvious m2m table for {self.name}, {other_table.name} - use m2m_table= parameter" ) else: # If not, create a new table @@ -4844,7 +5268,7 @@ class Table(Queryable): if isinstance(record_or_iterable, Mapping): records = [record_or_iterable] else: - records = cast(List, record_or_iterable) + records = cast(list, record_or_iterable) # Ensure each record exists in other table for record in records: id = other_table.insert( @@ -4852,8 +5276,8 @@ class Table(Queryable): ).last_pk m2m_table_obj.insert( { - "{}_id".format(other_table.name): id, - "{}_id".format(self.name): our_id, + f"{other_table.name}_id": id, + f"{self.name}_id": our_id, }, replace=True, ) @@ -4861,8 +5285,8 @@ class Table(Queryable): id = other_table.lookup(lookup) m2m_table_obj.insert( { - "{}_id".format(other_table.name): id, - "{}_id".format(self.name): our_id, + f"{other_table.name}_id": id, + f"{self.name}_id": our_id, }, replace=True, ) @@ -4909,21 +5333,19 @@ class Table(Queryable): table_quoted = quote_identifier(table) column_quoted = quote_identifier(column) num_null = db.execute( - "select count(*) from {} where {} is null".format( - table_quoted, column_quoted - ) + f"select count(*) from {table_quoted} where {column_quoted} is null" ).fetchone()[0] num_blank = db.execute( - "select count(*) from {} where {} = ''".format(table_quoted, column_quoted) + f"select count(*) from {table_quoted} where {column_quoted} = ''" ).fetchone()[0] num_distinct = db.execute( - "select count(distinct {}) from {}".format(column_quoted, table_quoted) + f"select count(distinct {column_quoted}) from {table_quoted}" ).fetchone()[0] most_common_results = None least_common_results = None if num_distinct == 1: value = db.execute( - "select {} from {} limit 1".format(column_quoted, table_quoted) + f"select {column_quoted} from {table_quoted} limit 1" ).fetchone()[0] most_common_results = [(truncate(value), total_rows)] elif num_distinct != total_rows: @@ -4935,13 +5357,10 @@ class Table(Queryable): most_common_results = [ (truncate(r[0]), r[1]) for r in db.execute( - "select {}, count(*) from {} group by {} order by count(*) desc, {} limit {}".format( - column_quoted, - table_quoted, - column_quoted, - column_quoted, - common_limit, - ) + f"select {column_quoted}, count(*) " + f"from {table_quoted} group by {column_quoted} " + f"order by count(*) desc, {column_quoted} " + f"limit {common_limit}" ).fetchall() ] most_common_results.sort(key=lambda p: (p[1], p[0]), reverse=True) @@ -4953,13 +5372,10 @@ class Table(Queryable): least_common_results = [ (truncate(r[0]), r[1]) for r in db.execute( - "select {}, count(*) from {} group by {} order by count(*), {} desc limit {}".format( - column_quoted, - table_quoted, - column_quoted, - column_quoted, - common_limit, - ) + f"select {column_quoted}, count(*) " + f"from {table_quoted} group by {column_quoted} " + f"order by count(*), {column_quoted} desc " + f"limit {common_limit}" ).fetchall() ] least_common_results.sort(key=lambda p: (p[1], p[0])) @@ -5076,7 +5492,7 @@ class View(Queryable): """ try: - self.db.execute("DROP VIEW {}".format(quote_identifier(self.name))) + self.db.execute(f"DROP VIEW {quote_identifier(self.name)}") except sqlite3.OperationalError: if not ignore: raise @@ -5089,16 +5505,14 @@ def jsonify_if_needed(value: object) -> object: return json.dumps(value, default=repr, ensure_ascii=False) elif isinstance(value, (datetime.time, datetime.date, datetime.datetime)): return value.isoformat() - elif isinstance(value, datetime.timedelta): - return str(value) - elif isinstance(value, uuid.UUID): + elif isinstance(value, (datetime.timedelta, uuid.UUID)): return str(value) else: return value def resolve_extracts( - extracts: Optional[Union[Dict[str, str], List[str], Tuple[str]]], + extracts: dict[str, str] | list[str] | tuple[str] | None, ) -> dict: if extracts is None: extracts = {} @@ -5109,8 +5523,8 @@ def resolve_extracts( def _decode_default_value(value: str) -> object: if value.startswith("'") and value.endswith("'"): - # It's a string - return value[1:-1] + # It's a string; unescape doubled single quotes + return value[1:-1].replace("''", "'") if value.isdigit(): # It's an integer return int(value) @@ -5118,6 +5532,13 @@ def _decode_default_value(value: str) -> object: # It's a binary string, stored as hex to_decode = value[2:-1] return binascii.unhexlify(to_decode) + upper = value.upper() + if upper == "TRUE": + return True + if upper == "FALSE": + return False + if upper == "NULL": + return None # If it is a string containing a floating point number: try: return float(value) diff --git a/sqlite_utils/hookspecs.py b/sqlite_utils/hookspecs.py index a746619..73d1acc 100644 --- a/sqlite_utils/hookspecs.py +++ b/sqlite_utils/hookspecs.py @@ -1,8 +1,7 @@ import sqlite3 import click -from pluggy import HookimplMarker -from pluggy import HookspecMarker +from pluggy import HookimplMarker, HookspecMarker hookspec = HookspecMarker("sqlite_utils") hookimpl = HookimplMarker("sqlite_utils") diff --git a/sqlite_utils/migrations.py b/sqlite_utils/migrations.py index 00d0fa5..69397ba 100644 --- a/sqlite_utils/migrations.py +++ b/sqlite_utils/migrations.py @@ -1,19 +1,28 @@ -from collections.abc import Iterable -from dataclasses import dataclass import datetime -from typing import Callable, cast, TYPE_CHECKING +from collections.abc import Callable, Iterable +from dataclasses import dataclass +from typing import TYPE_CHECKING, Protocol, TypeVar, cast if TYPE_CHECKING: from sqlite_utils.db import Database, Table +class _MigrationFunction(Protocol): + __name__: str + + def __call__(self, db: "Database", /) -> None: ... + + +_MigrationFunctionT = TypeVar("_MigrationFunctionT", bound=_MigrationFunction) + + class Migrations: migrations_table = "_sqlite_migrations" @dataclass class _Migration: name: str - fn: Callable + fn: _MigrationFunction transactional: bool = True @dataclass @@ -32,7 +41,7 @@ class Migrations: def __call__( self, *, name: str | None = None, transactional: bool = True - ) -> Callable: + ) -> Callable[[_MigrationFunctionT], _MigrationFunctionT]: """ :param name: The name to use for this migration - if not provided, the name of the function will be used. @@ -43,13 +52,11 @@ class Migrations: example those that execute ``VACUUM``. """ - def inner(func: Callable) -> Callable: - migration_name = name or getattr(func, "__name__") + def inner(func: _MigrationFunctionT) -> _MigrationFunctionT: + migration_name = name or func.__name__ if any(m.name == migration_name for m in self._migrations): raise ValueError( - "Migration '{}' is already registered in set '{}'".format( - migration_name, self.name - ) + f"Migration '{migration_name}' is already registered in set '{self.name}'" ) self._migrations.append( self._Migration(migration_name, func, transactional) diff --git a/sqlite_utils/plugins.py b/sqlite_utils/plugins.py index 0aff7ff..10815b4 100644 --- a/sqlite_utils/plugins.py +++ b/sqlite_utils/plugins.py @@ -1,7 +1,7 @@ -from typing import Dict, List, Union +import sys import pluggy -import sys + from . import hookspecs pm: pluggy.PluginManager = pluggy.PluginManager("sqlite_utils") @@ -17,13 +17,13 @@ def ensure_plugins_loaded() -> None: _plugins_loaded = True -def get_plugins() -> List[Dict[str, Union[str, List[str]]]]: +def get_plugins() -> list[dict[str, str | list[str]]]: ensure_plugins_loaded() - plugins: List[Dict[str, Union[str, List[str]]]] = [] + plugins: list[dict[str, str | list[str]]] = [] plugin_to_distinfo = dict(pm.list_plugin_distinfo()) for plugin in pm.get_plugins(): hookcallers = pm.get_hookcallers(plugin) or [] - plugin_info: Dict[str, Union[str, List[str]]] = { + plugin_info: dict[str, str | list[str]] = { "name": plugin.__name__, "hooks": [h.name for h in hookcallers], } diff --git a/sqlite_utils/recipes.py b/sqlite_utils/recipes.py index 55b55a4..d28a099 100644 --- a/sqlite_utils/recipes.py +++ b/sqlite_utils/recipes.py @@ -1,9 +1,9 @@ from __future__ import annotations -from typing import Callable, Optional +import json +from collections.abc import Callable from dateutil import parser -import json IGNORE: object = object() SET_NULL: object = object() @@ -13,8 +13,8 @@ def parsedate( value: str, dayfirst: bool = False, yearfirst: bool = False, - errors: Optional[object] = None, -) -> Optional[str]: + errors: object | None = None, +) -> str | None: """ Parse a date and convert it to ISO date format: yyyy-mm-dd \b @@ -44,8 +44,8 @@ def parsedatetime( value: str, dayfirst: bool = False, yearfirst: bool = False, - errors: Optional[object] = None, -) -> Optional[str]: + errors: object | None = None, +) -> str | None: """ Parse a datetime and convert it to ISO datetime format: yyyy-mm-ddTHH:MM:SS \b diff --git a/sqlite_utils/utils.py b/sqlite_utils/utils.py index b39b117..ee6695b 100644 --- a/sqlite_utils/utils.py +++ b/sqlite_utils/utils.py @@ -9,20 +9,12 @@ import itertools import json import os import sys +from collections.abc import Callable, Generator, Iterable, Iterator from typing import ( + TYPE_CHECKING, Any, BinaryIO, - Callable, - Dict, - Generator, - Iterable, - Iterator, - List, - Optional, - Set, - Tuple, - Type, - TYPE_CHECKING, + Generic, TypeVar, Union, cast, @@ -33,8 +25,8 @@ import click from . import recipes if TYPE_CHECKING: - import sqlite3 # noqa: F401 - from sqlite3 import dbapi2 # noqa: F401 + import sqlite3 + from sqlite3 import dbapi2 OperationalError = dbapi2.OperationalError else: @@ -44,7 +36,7 @@ else: OperationalError = dbapi2.OperationalError except ImportError: import sqlite3 # noqa: F401 - from sqlite3 import dbapi2 # noqa: F401 + from sqlite3 import dbapi2 OperationalError = dbapi2.OperationalError @@ -61,12 +53,16 @@ SPATIALITE_PATHS = ( ORIGINAL_CSV_FIELD_SIZE_LIMIT = csv.field_size_limit() # Type alias for row dictionaries - values can be various SQLite-compatible types -RowValue = Union[None, int, float, str, bytes, bool, List[str]] -Row = Dict[str, RowValue] +RowValue = None | int | float | str | bytes | bool | list[str] +Row = dict[str, RowValue] T = TypeVar("T") +class ANY: + """Marker type for an SQLite ``ANY`` column.""" + + class _CloseableIterator(Iterator[Row]): """Iterator wrapper that closes a file when iteration is complete.""" @@ -103,7 +99,7 @@ def maximize_csv_field_size_limit() -> None: field_size_limit = int(field_size_limit / 10) -def find_spatialite() -> Optional[str]: +def find_spatialite() -> str | None: """ The ``find_spatialite()`` function searches for the `SpatiaLite `__ SQLite extension in some common places. It returns a string path to the location, or ``None`` if SpatiaLite was not found. @@ -132,9 +128,9 @@ def find_spatialite() -> Optional[str]: def suggest_column_types( - records: Iterable[Dict[str, Any]], -) -> Dict[str, type]: - all_column_types: Dict[str, Set[type]] = {} + records: Iterable[dict[str, Any]], +) -> dict[str, type]: + all_column_types: dict[str, set[type]] = {} for record in records: for key, value in record.items(): all_column_types.setdefault(key, set()).add(type(value)) @@ -142,9 +138,9 @@ def suggest_column_types( def types_for_column_types( - all_column_types: Dict[str, Set[type]], -) -> Dict[str, type]: - column_types: Dict[str, type] = {} + all_column_types: dict[str, set[type]], +) -> dict[str, type]: + column_types: dict[str, type] = {} for key, types in all_column_types.items(): # Ignore null values if at least one other type present: if len(types) > 1: @@ -153,7 +149,7 @@ def types_for_column_types( if {None.__class__} == types: t = str elif len(types) == 1: - t = list(types)[0] + t = next(iter(types)) # But if it's a subclass of list / tuple / dict, use str # instead as we will be storing it as JSON in the table for superclass in (list, tuple, dict): @@ -186,11 +182,13 @@ def column_affinity(column_type: str) -> type: return bytes if "REAL" in column_type or "FLOA" in column_type or "DOUB" in column_type: return float + if column_type == "ANY": + return ANY # Default is 'NUMERIC', which we currently also treat as float return float -def decode_base64_values(doc: Dict[str, Any]) -> Dict[str, Any]: +def decode_base64_values(doc: dict[str, Any]) -> dict[str, Any]: # Looks for '{"$base64": true..., "encoded": ...}' values and decodes them to_fix = [ k @@ -263,9 +261,9 @@ class RowError(Exception): def _extra_key_strategy( - reader: Iterable[Dict[Optional[str], object]], - ignore_extras: Optional[bool] = False, - extras_key: Optional[str] = None, + reader: Iterable[dict[str | None, object]], + ignore_extras: bool | None = False, + extras_key: str | None = None, ) -> Iterable[Row]: # Logic for handling CSV rows with more values than there are headings for row in reader: @@ -279,9 +277,7 @@ def _extra_key_strategy( yield cast(Row, row) elif not extras_key: extras = row.pop(None) - raise RowError( - "Row {} contained these extra values: {}".format(row, extras) - ) + raise RowError(f"Row {row} contained these extra values: {extras}") else: extras_value = row.pop(None) row_out = cast(Row, row) @@ -291,12 +287,12 @@ def _extra_key_strategy( def rows_from_file( fp: BinaryIO, - format: Optional[Format] = None, - dialect: Optional[Type[csv.Dialect]] = None, - encoding: Optional[str] = None, - ignore_extras: Optional[bool] = False, - extras_key: Optional[str] = None, -) -> Tuple[Iterable[Row], Format]: + format: Format | None = None, + dialect: type[csv.Dialect] | None = None, + encoding: str | None = None, + ignore_extras: bool | None = False, + extras_key: str | None = None, +) -> tuple[Iterable[Row], Format]: """ Load a sequence of dictionaries from a file-like object containing one of four different formats. @@ -355,7 +351,11 @@ def rows_from_file( reader = csv.DictReader(decoded_fp, dialect=dialect) else: reader = csv.DictReader(decoded_fp) - rows = _extra_key_strategy(reader, ignore_extras, extras_key) + rows = _extra_key_strategy( + cast(Iterable[dict[str | None, object]], reader), + ignore_extras, + extras_key, + ) return _CloseableIterator(iter(rows), decoded_fp), Format.CSV elif format == Format.TSV: rows, _ = rows_from_file( @@ -363,7 +363,7 @@ def rows_from_file( ) return ( _extra_key_strategy( - cast(Iterable[Dict[Optional[str], object]], rows), + cast(Iterable[dict[str | None, object]], rows), ignore_extras, extras_key, ), @@ -379,7 +379,9 @@ def rows_from_file( raise TypeError( "rows_from_file() requires a file-like object that supports peek(), such as io.BytesIO" ) - if first_bytes.startswith(b"[") or first_bytes.startswith(b"{"): + if not first_bytes: + return (), Format.CSV + if first_bytes.startswith((b"[", b"{")): # TODO: Detect newline-JSON return rows_from_file(buffered, format=Format.JSON) else: @@ -393,7 +395,7 @@ def rows_from_file( detected_format = Format.TSV if dialect.delimiter == "\t" else Format.CSV return ( _extra_key_strategy( - cast(Iterable[Dict[Optional[str], object]], rows), + cast(Iterable[dict[str | None, object]], rows), ignore_extras, extras_key, ), @@ -425,9 +427,9 @@ class TypeTracker: """ def __init__(self) -> None: - self.trackers: Dict[str, "ValueTracker"] = {} + self.trackers: dict[str, ValueTracker] = {} - def wrap(self, iterator: Iterable[Dict[str, Any]]) -> Iterable[Dict[str, Any]]: + def wrap(self, iterator: Iterable[dict[str, Any]]) -> Iterable[dict[str, Any]]: """ Use this to loop through an existing iterator, tracking the column types as part of the iteration. @@ -441,7 +443,7 @@ class TypeTracker: yield row @property - def types(self) -> Dict[str, str]: + def types(self) -> dict[str, str]: """ A dictionary mapping column names to their detected types. This can be passed to the ``db[table_name].transform(types=tracker.types)`` method. @@ -450,17 +452,15 @@ class TypeTracker: class ValueTracker: - couldbe: Dict[str, Callable[[object], bool]] + couldbe: dict[str, Callable[[object], bool]] def __init__(self) -> None: self.couldbe = {key: getattr(self, "test_" + key) for key in self.get_tests()} @classmethod - def get_tests(cls) -> List[str]: + def get_tests(cls) -> list[str]: return [ - key.split("test_")[-1] - for key in cls.__dict__.keys() - if key.startswith("test_") + key.split("test_")[-1] for key in cls.__dict__ if key.startswith("test_") ] def test_integer(self, value: object) -> bool: @@ -492,7 +492,7 @@ class ValueTracker: def evaluate(self, value: object) -> None: if not value or not self.couldbe: return - not_these: List[str] = [] + not_these: list[str] = [] for name, test in self.couldbe.items(): if not test(value): not_these.append(name) @@ -500,12 +500,12 @@ class ValueTracker: del self.couldbe[key] -class NullProgressBar: +class NullProgressBar(Generic[T]): def __init__(self, *args: Iterable[T]) -> None: self.args = args def __iter__(self) -> Iterator[T]: - yield from self.args[0] # type: ignore + yield from self.args[0] def update(self, value: int) -> None: pass @@ -524,14 +524,14 @@ def progressbar(*args: Iterable[T], **kwargs: Any) -> Generator[Any, None, None] def _compile_code( code: str, imports: Iterable[str], variable: str = "value" ) -> Callable[..., Any]: - globals_dict: Dict[str, Any] = {"r": recipes, "recipes": recipes} + globals_dict: dict[str, Any] = {"r": recipes, "recipes": recipes} # Handle imports first so they're available for all approaches for import_ in imports: globals_dict[import_.split(".")[0]] = __import__(import_) # If user defined a convert() function, return that try: - exec(code, globals_dict) + exec(code, globals_dict) # noqa: S102 return cast(Callable[..., object], globals_dict["convert"]) except (AttributeError, SyntaxError, NameError, KeyError, TypeError): pass @@ -542,20 +542,20 @@ def _compile_code( fn = eval(code, globals_dict) if callable(fn): return cast(Callable[..., object], fn) - except Exception: + except Exception: # noqa: BLE001, S110 pass # Try compiling their code as a function instead body_variants = [code] # If single line and no 'return', try adding the return if "\n" not in code and not code.strip().startswith("return "): - body_variants.insert(0, "return {}".format(code)) + body_variants.insert(0, f"return {code}") code_o = None for variant in body_variants: - new_code = ["def fn({}):".format(variable)] + new_code = [f"def fn({variable}):"] for line in variant.split("\n"): - new_code.append(" {}".format(line)) + new_code.append(f" {line}") try: code_o = compile("\n".join(new_code), "", "exec") break @@ -566,7 +566,7 @@ def _compile_code( if code_o is None: raise SyntaxError("Could not compile code") - exec(code_o, globals_dict) + exec(code_o, globals_dict) # noqa: S102 return cast(Callable[..., object], globals_dict["fn"]) @@ -582,7 +582,7 @@ def chunks(sequence: Iterable[T], size: int) -> Iterable[Iterable[T]]: yield itertools.chain([item], itertools.islice(iterator, size - 1)) -def hash_record(record: Dict[str, Any], keys: Optional[Iterable[str]] = None) -> str: +def hash_record(record: dict[str, Any], keys: Iterable[str] | None = None) -> str: """ ``record`` should be a Python dictionary. Returns a sha1 hash of the keys and values in that record. @@ -603,7 +603,7 @@ def hash_record(record: Dict[str, Any], keys: Optional[Iterable[str]] = None) -> :param record: Record to generate a hash for :param keys: Subset of keys to use for that hash """ - to_hash: Dict[str, Any] = record + to_hash: dict[str, Any] = record if keys is not None: to_hash = {key: record[key] for key in keys} return hashlib.sha1( @@ -613,7 +613,7 @@ def hash_record(record: Dict[str, Any], keys: Optional[Iterable[str]] = None) -> ).hexdigest() -def dedupe_keys(keys: Iterable[str]) -> List[str]: +def dedupe_keys(keys: Iterable[str]) -> list[str]: """ Rename duplicates in a list of column names so every name is unique, by appending ``_2``, ``_3``... to later occurrences - skipping any @@ -636,7 +636,7 @@ def dedupe_keys(keys: Iterable[str]) -> List[str]: new_key = key suffix = 2 while new_key in seen or new_key in taken: - new_key = "{}_{}".format(key, suffix) + new_key = f"{key}_{suffix}" suffix += 1 key = new_key seen.add(key) @@ -644,7 +644,7 @@ def dedupe_keys(keys: Iterable[str]) -> List[str]: return result -def _flatten(d: Dict[str, Any]) -> Generator[Tuple[str, Any], None, None]: +def _flatten(d: dict[str, Any]) -> Generator[tuple[str, Any], None, None]: for key, value in d.items(): if isinstance(value, dict): for key2, value2 in _flatten(value): @@ -653,7 +653,7 @@ def _flatten(d: Dict[str, Any]) -> Generator[Tuple[str, Any], None, None]: yield key, value -def flatten(row: Dict[str, Any]) -> Dict[str, Any]: +def flatten(row: dict[str, Any]) -> dict[str, Any]: """ Turn a nested dict e.g. ``{"a": {"b": 1}}`` into a flat dict: ``{"a_b": 1}`` diff --git a/tests/conftest.py b/tests/conftest.py index 728db7b..a4eb860 100644 --- a/tests/conftest.py +++ b/tests/conftest.py @@ -1,6 +1,7 @@ +import pytest + from sqlite_utils import Database from sqlite_utils.utils import sqlite3 -import pytest CREATE_TABLES = """ create table Gosh (c1 text, c2 text, c3 text); @@ -55,7 +56,7 @@ def close_all_databases(): for db in databases: try: db.close() - except Exception: + except sqlite3.Error: pass diff --git a/tests/test_analyze.py b/tests/test_analyze.py index a4cd8a2..edd5174 100644 --- a/tests/test_analyze.py +++ b/tests/test_analyze.py @@ -3,11 +3,13 @@ import pytest @pytest.fixture def db(fresh_db): - fresh_db["one_index"].insert({"id": 1, "name": "Cleo"}, pk="id") - fresh_db["one_index"].create_index(["name"]) - fresh_db["two_indexes"].insert({"id": 1, "name": "Cleo", "species": "dog"}, pk="id") - fresh_db["two_indexes"].create_index(["name"]) - fresh_db["two_indexes"].create_index(["species"]) + fresh_db.table("one_index").insert({"id": 1, "name": "Cleo"}, pk="id") + fresh_db.table("one_index").create_index(["name"]) + fresh_db.table("two_indexes").insert( + {"id": 1, "name": "Cleo", "species": "dog"}, pk="id" + ) + fresh_db.table("two_indexes").create_index(["name"]) + fresh_db.table("two_indexes").create_index(["species"]) return fresh_db @@ -17,7 +19,7 @@ def test_analyze_whole_database(db): assert set(db.table_names()).issuperset( {"one_index", "two_indexes", "sqlite_stat1"} ) - assert list(db["sqlite_stat1"].rows) == [ + assert list(db.table("sqlite_stat1").rows) == [ {"tbl": "two_indexes", "idx": "idx_two_indexes_species", "stat": "1 1"}, {"tbl": "two_indexes", "idx": "idx_two_indexes_name", "stat": "1 1"}, {"tbl": "one_index", "idx": "idx_one_index_name", "stat": "1 1"}, @@ -30,12 +32,12 @@ def test_analyze_one_table(db, method): if method == "db_method_with_name": db.analyze("one_index") elif method == "table_method": - db["one_index"].analyze() + db.table("one_index").analyze() assert set(db.table_names()).issuperset( {"one_index", "two_indexes", "sqlite_stat1"} ) - assert list(db["sqlite_stat1"].rows) == [ + assert list(db.table("sqlite_stat1").rows) == [ {"tbl": "one_index", "idx": "idx_one_index_name", "stat": "1 1"} ] @@ -46,6 +48,6 @@ def test_analyze_index_by_name(db): assert set(db.table_names()).issuperset( {"one_index", "two_indexes", "sqlite_stat1"} ) - assert list(db["sqlite_stat1"].rows) == [ + assert list(db.table("sqlite_stat1").rows) == [ {"tbl": "two_indexes", "idx": "idx_two_indexes_species", "stat": "1 1"}, ] diff --git a/tests/test_analyze_tables.py b/tests/test_analyze_tables.py index a2ce585..9e4799c 100644 --- a/tests/test_analyze_tables.py +++ b/tests/test_analyze_tables.py @@ -1,13 +1,15 @@ -from sqlite_utils.db import Database, ColumnDetails -from sqlite_utils import cli -from click.testing import CliRunner -import pytest import sqlite3 +import pytest +from click.testing import CliRunner + +from sqlite_utils import cli +from sqlite_utils.db import ColumnDetails, Database + @pytest.fixture def db_to_analyze(fresh_db): - stuff = fresh_db["stuff"] + stuff = fresh_db.table("stuff") stuff.insert_all( [ {"id": 1, "owner": "Terryterryterry", "size": 5}, @@ -43,7 +45,7 @@ def big_db_to_analyze_path(tmpdir): "all_null": None, } ) - db["stuff"].insert_all(to_insert) + db.table("stuff").insert_all(to_insert) return path @@ -124,7 +126,7 @@ def big_db_to_analyze_path(tmpdir): ) def test_analyze_column(db_to_analyze, column, extra_kwargs, expected): assert ( - db_to_analyze["stuff"].analyze_column( + db_to_analyze.table("stuff").analyze_column( column, common_limit=2, value_truncate=5, **extra_kwargs ) == expected @@ -184,7 +186,7 @@ def test_analyze_table_save(db_to_analyze_path): cli.cli, ["analyze-tables", db_to_analyze_path, "--save"] ) assert result.exit_code == 0 - rows = list(Database(db_to_analyze_path)["_analyze_tables_"].rows) + rows = list(Database(db_to_analyze_path).table("_analyze_tables_").rows) assert rows == [ { "table": "stuff", @@ -246,7 +248,7 @@ def test_analyze_table_save_no_most_no_least_options( args.append("--no-least") result = CliRunner().invoke(cli.cli, args) assert result.exit_code == 0 - rows = list(Database(big_db_to_analyze_path)["_analyze_tables_"].rows) + rows = list(Database(big_db_to_analyze_path).table("_analyze_tables_").rows) expected = { "table": "stuff", "column": "category", @@ -295,13 +297,13 @@ def test_analyze_table_column_all_nulls(big_db_to_analyze_path): def test_analyze_table_validate_columns(tmpdir, args, expected_error): path = str(tmpdir / "test_validate_columns.db") db = Database(path) - db["one"].insert( + db.table("one").insert( { "id": 1, "name": "one", } ) - db["two"].insert( + db.table("two").insert( { "id": 1, "age": 5, diff --git a/tests/test_atomic.py b/tests/test_atomic.py index c3fd02f..89a318a 100644 --- a/tests/test_atomic.py +++ b/tests/test_atomic.py @@ -28,11 +28,13 @@ from sqlite_utils.utils import sqlite3 END; """, [ - "CREATE TRIGGER t_ai AFTER INSERT ON t\n" - " BEGIN\n" - " UPDATE t SET value = 'a;b' WHERE id = new.id;\n" - " INSERT INTO log VALUES ('x;y');\n" - " END;" + ( + "CREATE TRIGGER t_ai AFTER INSERT ON t\n" + " BEGIN\n" + " UPDATE t SET value = 'a;b' WHERE id = new.id;\n" + " INSERT INTO log VALUES ('x;y');\n" + " END;" + ) ], ), ), @@ -43,52 +45,48 @@ def test_iter_complete_sql_statements(sql, expected): def test_atomic_commits(fresh_db): with fresh_db.atomic(): - fresh_db["dogs"].insert({"id": 1, "name": "Cleo"}, pk="id") + fresh_db.table("dogs").insert({"id": 1, "name": "Cleo"}, pk="id") - assert list(fresh_db["dogs"].rows) == [{"id": 1, "name": "Cleo"}] + assert list(fresh_db.table("dogs").rows) == [{"id": 1, "name": "Cleo"}] def test_atomic_rolls_back(fresh_db): - with pytest.raises(RuntimeError): - with fresh_db.atomic(): - fresh_db["dogs"].insert({"id": 1, "name": "Cleo"}, pk="id") - raise RuntimeError("boom") + with pytest.raises(RuntimeError), fresh_db.atomic(): + fresh_db.table("dogs").insert({"id": 1, "name": "Cleo"}, pk="id") + raise RuntimeError("boom") - assert not fresh_db["dogs"].exists() + assert not fresh_db.table("dogs").exists() def test_nested_atomic_rolls_back_to_savepoint(fresh_db): - fresh_db["dogs"].create({"id": int, "name": str}, pk="id") + fresh_db.table("dogs").create({"id": int, "name": str}, pk="id") with fresh_db.atomic(): - fresh_db["dogs"].insert({"id": 1, "name": "Cleo"}) - with pytest.raises(RuntimeError): - with fresh_db.atomic(): - fresh_db["dogs"].insert({"id": 2, "name": "Pancakes"}) - raise RuntimeError("boom") - fresh_db["dogs"].insert({"id": 3, "name": "Marnie"}) + fresh_db.table("dogs").insert({"id": 1, "name": "Cleo"}) + with pytest.raises(RuntimeError), fresh_db.atomic(): + fresh_db.table("dogs").insert({"id": 2, "name": "Pancakes"}) + raise RuntimeError("boom") + fresh_db.table("dogs").insert({"id": 3, "name": "Marnie"}) - assert list(fresh_db["dogs"].rows) == [ + assert list(fresh_db.table("dogs").rows) == [ {"id": 1, "name": "Cleo"}, {"id": 3, "name": "Marnie"}, ] def test_outer_atomic_rolls_back_released_savepoint(fresh_db): - with pytest.raises(RuntimeError): + with pytest.raises(RuntimeError), fresh_db.atomic(): + fresh_db.table("dogs").insert({"id": 1, "name": "Cleo"}, pk="id") with fresh_db.atomic(): - fresh_db["dogs"].insert({"id": 1, "name": "Cleo"}, pk="id") - with fresh_db.atomic(): - fresh_db["dogs"].insert({"id": 2, "name": "Pancakes"}) - raise RuntimeError("boom") + fresh_db.table("dogs").insert({"id": 2, "name": "Pancakes"}) + raise RuntimeError("boom") - assert not fresh_db["dogs"].exists() + assert not fresh_db.table("dogs").exists() def test_executescript_does_not_commit_open_atomic_block(fresh_db): - with pytest.raises(RuntimeError): - with fresh_db.atomic(): - fresh_db.executescript(""" + with pytest.raises(RuntimeError), fresh_db.atomic(): + fresh_db.executescript(""" CREATE TABLE dogs(id INTEGER PRIMARY KEY, name TEXT); CREATE TRIGGER dogs_ai AFTER INSERT ON dogs BEGIN @@ -97,44 +95,43 @@ def test_executescript_does_not_commit_open_atomic_block(fresh_db): -- This comment has a semicolon; INSERT INTO dogs VALUES (1, 'Cleo; the first'); """) - raise RuntimeError("boom") + raise RuntimeError("boom") - assert not fresh_db["dogs"].exists() + assert not fresh_db.table("dogs").exists() def test_transform_does_not_commit_open_atomic_block(fresh_db): - fresh_db["dogs"].insert({"id": 1, "name": "Cleo", "age": "5"}, pk="id") + fresh_db.table("dogs").insert({"id": 1, "name": "Cleo", "age": "5"}, pk="id") - with pytest.raises(RuntimeError): - with fresh_db.atomic(): - fresh_db["dogs"].insert({"id": 2, "name": "Pancakes", "age": "6"}) - fresh_db["dogs"].transform(rename={"age": "dog_age"}) - raise RuntimeError("boom") + with pytest.raises(RuntimeError), fresh_db.atomic(): + fresh_db.table("dogs").insert({"id": 2, "name": "Pancakes", "age": "6"}) + fresh_db.table("dogs").transform(rename={"age": "dog_age"}) + raise RuntimeError("boom") assert ( - fresh_db["dogs"].schema + fresh_db.table("dogs").schema == 'CREATE TABLE "dogs" (\n "id" INTEGER PRIMARY KEY,\n "name" TEXT,\n "age" TEXT\n)' ) - assert list(fresh_db["dogs"].rows) == [ + assert list(fresh_db.table("dogs").rows) == [ {"id": 1, "name": "Cleo", "age": "5"}, ] def test_transform_parent_table_with_foreign_keys_in_atomic(fresh_db): fresh_db.conn.execute("PRAGMA foreign_keys=ON") - fresh_db["authors"].insert({"id": 1, "name": "Tina"}, pk="id") - fresh_db["books"].insert( + fresh_db.table("authors").insert({"id": 1, "name": "Tina"}, pk="id") + fresh_db.table("books").insert( {"id": 1, "title": "Book", "author_id": 1}, pk="id", foreign_keys={"author_id"}, ) with fresh_db.atomic(): - fresh_db["authors"].transform(rename={"name": "full_name"}) + fresh_db.table("authors").transform(rename={"name": "full_name"}) assert fresh_db.conn.execute("PRAGMA foreign_keys").fetchone()[0] assert ( - fresh_db["authors"].schema + fresh_db.table("authors").schema == 'CREATE TABLE "authors" (\n "id" INTEGER PRIMARY KEY,\n "full_name" TEXT\n)' ) assert fresh_db.execute("PRAGMA foreign_key_check").fetchall() == [] @@ -142,20 +139,19 @@ def test_transform_parent_table_with_foreign_keys_in_atomic(fresh_db): def test_transform_parent_table_with_foreign_keys_rolls_back(fresh_db): fresh_db.conn.execute("PRAGMA foreign_keys=ON") - fresh_db["authors"].insert({"id": 1, "name": "Tina"}, pk="id") - fresh_db["books"].insert( + fresh_db.table("authors").insert({"id": 1, "name": "Tina"}, pk="id") + fresh_db.table("books").insert( {"id": 1, "title": "Book", "author_id": 1}, pk="id", foreign_keys={"author_id"}, ) - with pytest.raises(RuntimeError): - with fresh_db.atomic(): - fresh_db["authors"].transform(rename={"name": "full_name"}) - raise RuntimeError("boom") + with pytest.raises(RuntimeError), fresh_db.atomic(): + fresh_db.table("authors").transform(rename={"name": "full_name"}) + raise RuntimeError("boom") assert ( - fresh_db["authors"].schema + fresh_db.table("authors").schema == 'CREATE TABLE "authors" (\n "id" INTEGER PRIMARY KEY,\n "name" TEXT\n)' ) assert fresh_db.conn.execute("PRAGMA foreign_keys").fetchone()[0] @@ -164,49 +160,51 @@ def test_transform_parent_table_with_foreign_keys_rolls_back(fresh_db): def test_transform_detects_foreign_key_check_violations(fresh_db): fresh_db.conn.execute("PRAGMA foreign_keys=ON") - fresh_db["authors"].insert({"id": 1, "name": "Tina"}, pk="id") - fresh_db["books"].insert({"id": 1, "author_id": 2}, pk="id") + fresh_db.table("authors").insert({"id": 1, "name": "Tina"}, pk="id") + fresh_db.table("books").insert({"id": 1, "author_id": 2}, pk="id") with pytest.raises(sqlite3.IntegrityError): - fresh_db["books"].transform(add_foreign_keys=(("author_id", "authors", "id"),)) + fresh_db.table("books").transform( + add_foreign_keys=(("author_id", "authors", "id"),) + ) - assert fresh_db["books"].foreign_keys == [] + assert fresh_db.table("books").foreign_keys == [] assert fresh_db.conn.execute("PRAGMA foreign_keys").fetchone()[0] def test_atomic_inside_manual_transaction_uses_savepoint(fresh_db): - fresh_db["t"].insert({"id": 1}, pk="id") + fresh_db.table("t").insert({"id": 1}, pk="id") fresh_db.execute("begin") with fresh_db.atomic(): - fresh_db["t"].insert({"id": 2}, pk="id") + fresh_db.table("t").insert({"id": 2}, pk="id") # Nothing is committed until the user's own transaction commits assert fresh_db.conn.in_transaction fresh_db.rollback() - assert [r["id"] for r in fresh_db["t"].rows] == [1] + assert [r["id"] for r in fresh_db.table("t").rows] == [1] # And with a commit instead, the atomic block's writes persist fresh_db.execute("begin") with fresh_db.atomic(): - fresh_db["t"].insert({"id": 3}, pk="id") + fresh_db.table("t").insert({"id": 3}, pk="id") fresh_db.commit() - assert [r["id"] for r in fresh_db["t"].rows] == [1, 3] + assert [r["id"] for r in fresh_db.table("t").rows] == [1, 3] def test_begin_commit_rollback(tmpdir): path = str(tmpdir / "test.db") db = Database(path) - db["t"].insert({"id": 1}, pk="id") + db.table("t").insert({"id": 1}, pk="id") db.begin() - db["t"].insert({"id": 2}, pk="id") + db.table("t").insert({"id": 2}, pk="id") assert db.conn.in_transaction db.rollback() assert not db.conn.in_transaction - assert [r["id"] for r in db["t"].rows] == [1] + assert [r["id"] for r in db.table("t").rows] == [1] db.begin() - db["t"].insert({"id": 3}, pk="id") + db.table("t").insert({"id": 3}, pk="id") db.commit() db.close() db2 = Database(path) - assert [r["id"] for r in db2["t"].rows] == [1, 3] + assert [r["id"] for r in db2.table("t").rows] == [1, 3] db2.close() @@ -226,7 +224,7 @@ def test_commit_and_rollback_without_transaction_are_noops(fresh_db): def test_execute_write_commits_immediately(tmpdir): path = str(tmpdir / "test.db") db = Database(path) - db["t"].insert({"id": 1}, pk="id") + db.table("t").insert({"id": 1}, pk="id") db.execute("insert into t (id) values (2)") # No implicit transaction is left open assert not db.conn.in_transaction @@ -238,24 +236,24 @@ def test_execute_write_commits_immediately(tmpdir): def test_execute_write_respects_explicit_transaction(fresh_db): - fresh_db["t"].insert({"id": 1}, pk="id") + fresh_db.table("t").insert({"id": 1}, pk="id") fresh_db.begin() fresh_db.execute("insert into t (id) values (2)") # Still inside the explicit transaction - not committed assert fresh_db.conn.in_transaction fresh_db.rollback() - assert [r["id"] for r in fresh_db["t"].rows] == [1] + assert [r["id"] for r in fresh_db.table("t").rows] == [1] def test_execute_comment_prefixed_begin_leaves_transaction_open(fresh_db): # A BEGIN hidden behind a leading comment must not be auto-committed # out from under the caller - fresh_db["t"].insert({"id": 1}, pk="id") + fresh_db.table("t").insert({"id": 1}, pk="id") fresh_db.execute("-- start a transaction\nbegin") assert fresh_db.conn.in_transaction fresh_db.execute("insert into t (id) values (2)") fresh_db.rollback() - assert [r["id"] for r in fresh_db["t"].rows] == [1] + assert [r["id"] for r in fresh_db.table("t").rows] == [1] def _sqlite_accepts_bom(): @@ -273,12 +271,12 @@ def test_execute_prefixed_begin_leaves_transaction_open(fresh_db, begin_sql): # out from under the caller if begin_sql.startswith("\ufeff") and not _sqlite_accepts_bom(): pytest.skip("This SQLite version rejects a leading byte order mark") - fresh_db["t"].insert({"id": 1}, pk="id") + fresh_db.table("t").insert({"id": 1}, pk="id") fresh_db.execute(begin_sql) assert fresh_db.conn.in_transaction fresh_db.execute("insert into t (id) values (2)") fresh_db.rollback() - assert [r["id"] for r in fresh_db["t"].rows] == [1] + assert [r["id"] for r in fresh_db.table("t").rows] == [1] def test_execute_failed_write_rolls_back_implicit_transaction(tmpdir): @@ -286,40 +284,40 @@ def test_execute_failed_write_rolls_back_implicit_transaction(tmpdir): # that would silently disable auto-commit for every subsequent write path = str(tmpdir / "test.db") db = Database(path) - db["t"].insert({"id": 1}, pk="id") + db.table("t").insert({"id": 1}, pk="id") with pytest.raises(sqlite3.IntegrityError): db.execute("insert into t (id) values (1)") assert not db.conn.in_transaction # Subsequent writes commit as normal and survive closing the connection - db["other"].insert({"id": 2}) + db.table("other").insert({"id": 2}) db.close() db2 = Database(path) - assert db2["other"].exists() + assert db2.table("other").exists() db2.close() def test_execute_failed_write_preserves_explicit_transaction(fresh_db): # A failed write inside an explicit transaction must not roll back # the caller's earlier work - only the caller decides that - fresh_db["t"].insert({"id": 1}, pk="id") + fresh_db.table("t").insert({"id": 1}, pk="id") fresh_db.begin() fresh_db.execute("insert into t (id) values (2)") with pytest.raises(sqlite3.IntegrityError): fresh_db.execute("insert into t (id) values (1)") assert fresh_db.conn.in_transaction fresh_db.commit() - assert [r["id"] for r in fresh_db["t"].rows] == [1, 2] + assert [r["id"] for r in fresh_db.table("t").rows] == [1, 2] def test_execute_failed_write_inside_atomic_preserves_block(fresh_db): # A caught failure inside an atomic() block must leave the block's # transaction open so its other work still commits - fresh_db["t"].insert({"id": 1}, pk="id") + fresh_db.table("t").insert({"id": 1}, pk="id") with fresh_db.atomic(): fresh_db.execute("insert into t (id) values (2)") with pytest.raises(sqlite3.IntegrityError): fresh_db.execute("insert into t (id) values (1)") - assert [r["id"] for r in fresh_db["t"].rows] == [1, 2] + assert [r["id"] for r in fresh_db.table("t").rows] == [1, 2] def test_query_returning_commits_after_iteration(tmpdir): @@ -329,7 +327,7 @@ def test_query_returning_commits_after_iteration(tmpdir): _pytest.skip("RETURNING requires SQLite 3.35.0 or higher") path = str(tmpdir / "test.db") db = Database(path) - db["t"].insert({"id": 1}, pk="id") + db.table("t").insert({"id": 1}, pk="id") rows = list(db.query("insert into t (id) values (2) returning id")) assert rows == [{"id": 2}] assert not db.conn.in_transaction @@ -354,9 +352,11 @@ def test_atomic_preserves_error_from_transaction_destroying_trigger(fresh_db): # with "cannot rollback - no transaction is active" fresh_db.execute("create table t (id integer primary key, v text)") fresh_db.execute(TRIGGER_SQL) - with pytest.raises(sqlite3.IntegrityError, match="trigger says no"): - with fresh_db.atomic(): - fresh_db.execute("insert into t (v) values ('bad')") + with ( + pytest.raises(sqlite3.IntegrityError, match="trigger says no"), + fresh_db.atomic(), + ): + fresh_db.execute("insert into t (v) values ('bad')") assert not fresh_db.conn.in_transaction @@ -367,16 +367,17 @@ def test_nested_atomic_preserves_error_from_transaction_destroying_trigger( # "no such savepoint" from ROLLBACK TO SAVEPOINT fresh_db.execute("create table t (id integer primary key, v text)") fresh_db.execute(TRIGGER_SQL) - with pytest.raises(sqlite3.IntegrityError, match="trigger says no"): - with fresh_db.atomic(): - with fresh_db.atomic(): - fresh_db.execute("insert into t (v) values ('bad')") + with ( + pytest.raises(sqlite3.IntegrityError, match="trigger says no"), + fresh_db.atomic(), + fresh_db.atomic(), + ): + fresh_db.execute("insert into t (v) values ('bad')") assert not fresh_db.conn.in_transaction def test_atomic_preserves_error_from_insert_or_rollback(fresh_db): - fresh_db["t"].insert({"id": 1}, pk="id") - with pytest.raises(sqlite3.IntegrityError): - with fresh_db.atomic(): - fresh_db.execute("insert or rollback into t (id) values (1)") + fresh_db.table("t").insert({"id": 1}, pk="id") + with pytest.raises(sqlite3.IntegrityError), fresh_db.atomic(): + fresh_db.execute("insert or rollback into t (id) values (1)") assert not fresh_db.conn.in_transaction diff --git a/tests/test_attach.py b/tests/test_attach.py index b594b3b..2b11e36 100644 --- a/tests/test_attach.py +++ b/tests/test_attach.py @@ -6,10 +6,10 @@ def test_attach(tmpdir): bar_path = str(tmpdir / "bar.db") db = Database(foo_path) with db.conn: - db["foo"].insert({"id": 1, "text": "foo"}) + db.table("foo").insert({"id": 1, "text": "foo"}) db2 = Database(bar_path) with db2.conn: - db2["bar"].insert({"id": 1, "text": "bar"}) + db2.table("bar").insert({"id": 1, "text": "bar"}) db.attach("bar", bar_path) assert db.execute( "select * from foo union all select * from bar.bar" diff --git a/tests/test_cli.py b/tests/test_cli.py index 06e14ea..064026a 100644 --- a/tests/test_cli.py +++ b/tests/test_cli.py @@ -1,13 +1,16 @@ -from sqlite_utils import cli, Database -from sqlite_utils.db import Index, ForeignKey -from click.testing import CliRunner -from pathlib import Path -import subprocess -import sys import json import os -import pytest +import sqlite3 +import subprocess +import sys import textwrap +from pathlib import Path + +import pytest +from click.testing import CliRunner + +from sqlite_utils import ANY, Database, cli +from sqlite_utils.db import ForeignKey, Index def write_json(file_path, data): @@ -20,7 +23,7 @@ def _supports_pragma_function_list(): try: db.execute("select * from pragma_function_list()") return True - except Exception: + except sqlite3.DatabaseError: return False finally: db.close() @@ -69,13 +72,13 @@ def test_views(db_path): def test_tables_fts4(db_path): - Database(db_path)["Gosh"].enable_fts(["c2"], fts_version="FTS4") + Database(db_path).table("Gosh").enable_fts(["c2"], fts_version="FTS4") result = CliRunner().invoke(cli.cli, ["tables", "--fts4", db_path]) assert '[{"table": "Gosh_fts"}]' == result.output.strip() def test_tables_fts5(db_path): - Database(db_path)["Gosh"].enable_fts(["c2"], fts_version="FTS5") + Database(db_path).table("Gosh").enable_fts(["c2"], fts_version="FTS5") result = CliRunner().invoke(cli.cli, ["tables", "--fts5", db_path]) assert '[{"table": "Gosh_fts"}]' == result.output.strip() @@ -83,7 +86,7 @@ def test_tables_fts5(db_path): def test_tables_counts_and_columns(db_path): db = Database(db_path) with db.conn: - db["lots"].insert_all([{"id": i, "age": i + 1} for i in range(30)]) + db.table("lots").insert_all([{"id": i, "age": i + 1} for i in range(30)]) result = CliRunner().invoke(cli.cli, ["tables", "--counts", "--columns", db_path]) assert ( '[{"table": "Gosh", "count": 0, "columns": ["c1", "c2", "c3"]},\n' @@ -118,7 +121,7 @@ def test_tables_counts_and_columns(db_path): def test_tables_counts_and_columns_csv(db_path, format, expected): db = Database(db_path) with db.conn: - db["lots"].insert_all([{"id": i, "age": i + 1} for i in range(30)]) + db.table("lots").insert_all([{"id": i, "age": i + 1} for i in range(30)]) result = CliRunner().invoke( cli.cli, ["tables", "--counts", "--columns", format, db_path] ) @@ -128,7 +131,7 @@ def test_tables_counts_and_columns_csv(db_path, format, expected): def test_tables_schema(db_path): db = Database(db_path) with db.conn: - db["lots"].insert_all([{"id": i, "age": i + 1} for i in range(30)]) + db.table("lots").insert_all([{"id": i, "age": i + 1} for i in range(30)]) result = CliRunner().invoke(cli.cli, ["tables", "--schema", db_path]) assert ( '[{"table": "Gosh", "schema": "CREATE TABLE Gosh (c1 text, c2 text, c3 text)"},\n' @@ -180,12 +183,12 @@ def test_tables_schema(db_path): def test_output_table(db_path, options, expected): db = Database(db_path) with db.conn: - db["rows"].insert_all( + db.table("rows").insert_all( [ { - "c1": "verb{}".format(i), - "c2": "noun{}".format(i), - "c3": "adjective{}".format(i), + "c1": f"verb{i}", + "c2": f"noun{i}", + "c3": f"adjective{i}", } for i in range(4) ] @@ -204,7 +207,7 @@ def test_output_table_no_headers(db_path, fmt_option): # tabulate formats and the column names were always printed. db = Database(db_path) with db.conn: - db["dogs"].insert_all( + db.table("dogs").insert_all( [ {"id": 1, "name": "Cleo", "age": 4}, {"id": 2, "name": "Pancakes", "age": 2}, @@ -241,14 +244,14 @@ def test_output_table_no_headers(db_path, fmt_option): def test_create_index(db_path): db = Database(db_path) - assert [] == db["Gosh"].indexes + assert [] == db.table("Gosh").indexes result = CliRunner().invoke(cli.cli, ["create-index", db_path, "Gosh", "c1"]) assert result.exit_code == 0 assert [ Index( seq=0, name="idx_Gosh_c1", unique=0, origin="c", partial=0, columns=["c1"] ) - ] == db["Gosh"].indexes + ] == db.table("Gosh").indexes # Try with a custom name result = CliRunner().invoke( cli.cli, ["create-index", db_path, "Gosh", "c2", "--name", "blah"] @@ -259,7 +262,7 @@ def test_create_index(db_path): Index( seq=1, name="idx_Gosh_c1", unique=0, origin="c", partial=0, columns=["c1"] ), - ] == db["Gosh"].indexes + ] == db.table("Gosh").indexes # Try a two-column unique index create_index_unique_args = [ "create-index", @@ -280,7 +283,7 @@ def test_create_index(db_path): partial=0, columns=["c1", "c2"], ) - ] == db["Gosh2"].indexes + ] == db.table("Gosh2").indexes # Trying to create the same index should fail assert CliRunner().invoke(cli.cli, create_index_unique_args).exit_code != 0 # ... unless we use --if-not-exists or --ignore @@ -291,10 +294,28 @@ def test_create_index(db_path): ) +def test_drop_index(db_path): + db = Database(db_path) + db.table("Gosh").create_index(["c1"]) + assert [index.name for index in db.table("Gosh").indexes] == ["idx_Gosh_c1"] + result = CliRunner().invoke(cli.cli, ["drop-index", db_path, "Gosh", "idx_Gosh_c1"]) + assert result.exit_code == 0 + assert db.table("Gosh").indexes == [] + + result = CliRunner().invoke(cli.cli, ["drop-index", db_path, "Gosh", "idx_Gosh_c1"]) + assert result.exit_code == 1 + assert "No index named idx_Gosh_c1" in result.output + + result = CliRunner().invoke( + cli.cli, ["drop-index", db_path, "Gosh", "idx_Gosh_c1", "--ignore"] + ) + assert result.exit_code == 0 + + def test_create_index_analyze(db_path): db = Database(db_path) assert "sqlite_stat1" not in db.table_names() - assert [] == db["Gosh"].indexes + assert [] == db.table("Gosh").indexes result = CliRunner().invoke( cli.cli, ["create-index", db_path, "Gosh", "c1", "--analyze"] ) @@ -304,7 +325,7 @@ def test_create_index_analyze(db_path): def test_create_index_desc(db_path): db = Database(db_path) - assert [] == db["Gosh"].indexes + assert [] == db.table("Gosh").indexes result = CliRunner().invoke(cli.cli, ["create-index", db_path, "Gosh", "--", "-c1"]) assert result.exit_code == 0 assert ( @@ -334,18 +355,19 @@ def test_create_index_desc(db_path): ("blob", "BLOB", 'CREATE TABLE "dogs" (\n "name" TEXT\n, "blob" BLOB)'), ("blob", "bytes", 'CREATE TABLE "dogs" (\n "name" TEXT\n, "blob" BLOB)'), ("blob", "BYTES", 'CREATE TABLE "dogs" (\n "name" TEXT\n, "blob" BLOB)'), + ("anything", "any", 'CREATE TABLE "dogs" (\n "name" TEXT\n, "anything" ANY)'), ("default", None, 'CREATE TABLE "dogs" (\n "name" TEXT\n, "default" TEXT)'), ), ) def test_add_column(db_path, col_name, col_type, expected_schema): db = Database(db_path) db.create_table("dogs", {"name": str}) - assert db["dogs"].schema == 'CREATE TABLE "dogs" (\n "name" TEXT\n)' + assert db.table("dogs").schema == 'CREATE TABLE "dogs" (\n "name" TEXT\n)' args = ["add-column", db_path, "dogs", col_name] if col_type is not None: args.append(col_type) assert CliRunner().invoke(cli.cli, args).exit_code == 0 - assert db["dogs"].schema == expected_schema + assert db.table("dogs").schema == expected_schema @pytest.mark.parametrize("ignore", (True, False)) @@ -364,7 +386,7 @@ def test_add_column_ignore(db_path, ignore): def test_add_column_not_null_default(db_path): db = Database(db_path) db.create_table("dogs", {"name": str}) - assert db["dogs"].schema == 'CREATE TABLE "dogs" (\n "name" TEXT\n)' + assert db.table("dogs").schema == 'CREATE TABLE "dogs" (\n "name" TEXT\n)' args = [ "add-column", db_path, @@ -374,7 +396,7 @@ def test_add_column_not_null_default(db_path): "dogs'dawg", ] assert CliRunner().invoke(cli.cli, args).exit_code == 0 - assert db["dogs"].schema == ( + assert db.table("dogs").schema == ( 'CREATE TABLE "dogs" (\n' ' "name" TEXT\n' ", \"nickname\" TEXT NOT NULL DEFAULT 'dogs''dawg')" @@ -394,10 +416,10 @@ def test_add_column_not_null_default(db_path): ) def test_add_foreign_key(db_path, args, assert_message): db = Database(db_path) - db["authors"].insert_all( + db.table("authors").insert_all( [{"id": 1, "name": "Sally"}, {"id": 2, "name": "Asheesh"}], pk="id" ) - db["books"].insert_all( + db.table("books").insert_all( [ {"title": "Hedgehogs of the world", "author_id": 1}, {"title": "How to train your wolf", "author_id": 2}, @@ -410,7 +432,7 @@ def test_add_foreign_key(db_path, args, assert_message): ForeignKey( table="books", column="author_id", other_table="authors", other_column="id" ) - ] == db["books"].foreign_keys + ] == db.table("books").foreign_keys # Error if we try to add it twice: result = CliRunner().invoke( @@ -439,14 +461,14 @@ def test_add_foreign_key(db_path, args, assert_message): def test_add_column_foreign_key(db_path): db = Database(db_path) - db["authors"].insert({"id": 1, "name": "Sally"}, pk="id") - db["books"].insert({"title": "Hedgehogs of the world"}) + db.table("authors").insert({"id": 1, "name": "Sally"}, pk="id") + db.table("books").insert({"title": "Hedgehogs of the world"}) # Add an author_id foreign key column to the books table result = CliRunner().invoke( cli.cli, ["add-column", db_path, "books", "author_id", "--fk", "authors"] ) assert result.exit_code == 0, result.output - assert db["books"].schema == ( + assert db.table("books").schema == ( 'CREATE TABLE "books" (\n' ' "title" TEXT,\n' ' "author_id" INTEGER REFERENCES "authors"("id")\n' @@ -467,7 +489,7 @@ def test_add_column_foreign_key(db_path): ], ) assert result.exit_code == 0, result.output - assert db["books"].schema == ( + assert db.table("books").schema == ( 'CREATE TABLE "books" (\n' ' "title" TEXT,\n' ' "author_id" INTEGER REFERENCES "authors"("id"),\n' @@ -484,7 +506,7 @@ def test_add_column_foreign_key(db_path): def test_suggest_alter_if_column_missing(db_path): db = Database(db_path) - db["authors"].insert({"id": 1, "name": "Sally"}, pk="id") + db.table("authors").insert({"id": 1, "name": "Sally"}, pk="id") result = CliRunner().invoke( cli.cli, ["insert", db_path, "authors", "-"], @@ -500,27 +522,27 @@ def test_suggest_alter_if_column_missing(db_path): def test_index_foreign_keys(db_path): test_add_column_foreign_key(db_path) db = Database(db_path) - assert [] == db["books"].indexes + assert [] == db.table("books").indexes result = CliRunner().invoke(cli.cli, ["index-foreign-keys", db_path]) assert result.exit_code == 0 assert [["author_id"], ["author_name_ref"]] == [ - i.columns for i in db["books"].indexes + i.columns for i in db.table("books").indexes ] def test_enable_fts(db_path): db = Database(db_path) - assert db["Gosh"].detect_fts() is None + assert db.table("Gosh").detect_fts() is None result = CliRunner().invoke( cli.cli, ["enable-fts", db_path, "Gosh", "c1", "--fts4"] ) assert result.exit_code == 0 - assert "Gosh_fts" == db["Gosh"].detect_fts() + assert "Gosh_fts" == db.table("Gosh").detect_fts() # Table names with restricted chars are handled correctly. # colons and dots are restricted characters for table names. - db["http://example.com"].create({"c1": str, "c2": str, "c3": str}) - assert db["http://example.com"].detect_fts() is None + db.table("http://example.com").create({"c1": str, "c2": str, "c3": str}) + assert db.table("http://example.com").detect_fts() is None result = CliRunner().invoke( cli.cli, [ @@ -534,7 +556,7 @@ def test_enable_fts(db_path): ], ) assert result.exit_code == 0 - assert "http://example.com_fts" == db["http://example.com"].detect_fts() + assert "http://example.com_fts" == db.table("http://example.com").detect_fts() # Check tokenize was set to porter assert ( 'CREATE VIRTUAL TABLE "http://example.com_fts" USING FTS4 (\n' @@ -542,19 +564,19 @@ def test_enable_fts(db_path): " tokenize='porter',\n" ' content="http://example.com"' "\n)" - ) == db["http://example.com_fts"].schema - db["http://example.com"].drop() + ) == db.table("http://example.com_fts").schema + db.table("http://example.com").drop() def test_enable_fts_replace(db_path): db = Database(db_path) - assert db["Gosh"].detect_fts() is None + assert db.table("Gosh").detect_fts() is None result = CliRunner().invoke( cli.cli, ["enable-fts", db_path, "Gosh", "c1", "--fts4"] ) assert result.exit_code == 0 - assert "Gosh_fts" == db["Gosh"].detect_fts() - assert db["Gosh_fts"].columns_dict == {"c1": str} + assert "Gosh_fts" == db.table("Gosh").detect_fts() + assert db.table("Gosh_fts").columns_dict == {"c1": str} # This should throw an error result2 = CliRunner().invoke( @@ -568,11 +590,11 @@ def test_enable_fts_replace(db_path): cli.cli, ["enable-fts", db_path, "Gosh", "c2", "--fts4", "--replace"] ) assert result3.exit_code == 0 - assert db["Gosh_fts"].columns_dict == {"c2": str} + assert db.table("Gosh_fts").columns_dict == {"c2": str} def test_enable_fts_with_triggers(db_path): - Database(db_path)["Gosh"].insert_all([{"c1": "baz"}]) + Database(db_path).table("Gosh").insert_all([{"c1": "baz"}]) exit_code = ( CliRunner() .invoke( @@ -591,12 +613,12 @@ def test_enable_fts_with_triggers(db_path): ) assert [("baz",)] == search("baz") - Database(db_path)["Gosh"].insert_all([{"c1": "martha"}]) + Database(db_path).table("Gosh").insert_all([{"c1": "martha"}]) assert [("martha",)] == search("martha") def test_populate_fts(db_path): - Database(db_path)["Gosh"].insert_all([{"c1": "baz"}]) + Database(db_path).table("Gosh").insert_all([{"c1": "baz"}]) exit_code = ( CliRunner() .invoke(cli.cli, ["enable-fts", db_path, "Gosh", "c1", "--fts4"]) @@ -612,7 +634,7 @@ def test_populate_fts(db_path): ) assert [("baz",)] == search("baz") - Database(db_path)["Gosh"].insert_all([{"c1": "martha"}]) + Database(db_path).table("Gosh").insert_all([{"c1": "martha"}]) assert [] == search("martha") exit_code = ( CliRunner().invoke(cli.cli, ["populate-fts", db_path, "Gosh", "c1"]).exit_code @@ -624,7 +646,7 @@ def test_populate_fts(db_path): def test_disable_fts(db_path): db = Database(db_path) assert {"Gosh", "Gosh2"} == set(db.table_names()) - db["Gosh"].enable_fts(["c1"], create_triggers=True) + db.table("Gosh").enable_fts(["c1"], create_triggers=True) assert { "Gosh_fts", "Gosh_fts_idx", @@ -656,18 +678,18 @@ def test_optimize(db_path, tables): db = Database(db_path) with db.conn: for table in ("Gosh", "Gosh2"): - db[table].insert_all( + db.table(table).insert_all( [ { - "c1": "verb{}".format(i), - "c2": "noun{}".format(i), - "c3": "adjective{}".format(i), + "c1": f"verb{i}", + "c2": f"noun{i}", + "c3": f"adjective{i}", } for i in range(10000) ] ) - db["Gosh"].enable_fts(["c1", "c2", "c3"], fts_version="FTS4") - db["Gosh2"].enable_fts(["c1", "c2", "c3"], fts_version="FTS5") + db.table("Gosh").enable_fts(["c1", "c2", "c3"], fts_version="FTS4") + db.table("Gosh2").enable_fts(["c1", "c2", "c3"], fts_version="FTS5") size_before_optimize = os.stat(db_path).st_size result = CliRunner().invoke(cli.cli, ["optimize", db_path] + tables) assert result.exit_code == 0 @@ -685,29 +707,29 @@ def test_rebuild_fts_fixes_docsize_error(db_path): db = Database(db_path, recursive_triggers=False) records = [ { - "c1": "verb{}".format(i), - "c2": "noun{}".format(i), - "c3": "adjective{}".format(i), + "c1": f"verb{i}", + "c2": f"noun{i}", + "c3": f"adjective{i}", } for i in range(10000) ] with db.conn: - db["fts5_table"].insert_all(records, pk="c1") - db["fts5_table"].enable_fts( + db.table("fts5_table").insert_all(records, pk="c1") + db.table("fts5_table").enable_fts( ["c1", "c2", "c3"], fts_version="FTS5", create_triggers=True ) # Search should work - assert list(db["fts5_table"].search("verb1")) + assert list(db.table("fts5_table").search("verb1")) # Replicate docsize error from this issue for FTS5 # https://github.com/simonw/sqlite-utils/issues/149 - assert db["fts5_table_fts_docsize"].count == 10000 - db["fts5_table"].insert_all(records, replace=True) - assert db["fts5_table"].count == 10000 - assert db["fts5_table_fts_docsize"].count == 20000 + assert db.table("fts5_table_fts_docsize").count == 10000 + db.table("fts5_table").insert_all(records, replace=True) + assert db.table("fts5_table").count == 10000 + assert db.table("fts5_table_fts_docsize").count == 20000 # Running rebuild-fts should fix this result = CliRunner().invoke(cli.cli, ["rebuild-fts", db_path, "fts5_table"]) assert result.exit_code == 0 - assert db["fts5_table_fts_docsize"].count == 10000 + assert db.table("fts5_table_fts_docsize").count == 10000 @pytest.mark.parametrize( @@ -720,7 +742,7 @@ def test_rebuild_fts_fixes_docsize_error(db_path): def test_query_csv(db_path, format, expected): db = Database(db_path) with db.conn: - db["dogs"].insert_all( + db.table("dogs").insert_all( [ {"id": 1, "age": 4, "name": "Cleo"}, {"id": 2, "age": 2, "name": "Pancakes"}, @@ -772,7 +794,7 @@ _one_query = "select id, name, age from dogs where id = 1" def test_query_json(db_path, sql, args, expected): db = Database(db_path) with db.conn: - db["dogs"].insert_all( + db.table("dogs").insert_all( [ {"id": 1, "age": 4, "name": "Cleo"}, {"id": 2, "age": 2, "name": "Pancakes"}, @@ -782,6 +804,25 @@ def test_query_json(db_path, sql, args, expected): assert expected == result.output.strip() +def test_query_sql_from_stdin(db_path): + # https://github.com/simonw/sqlite-utils/issues/765 + db = Database(db_path) + with db.conn: + db.table("dogs").insert_all( + [ + {"id": 1, "age": 4, "name": "Cleo"}, + {"id": 2, "age": 2, "name": "Pancakes"}, + ] + ) + result = CliRunner().invoke( + cli.cli, + ["query", db_path, "-"], + input="select name from dogs order by name", + ) + assert result.exit_code == 0, result.output + assert json.loads(result.output) == [{"name": "Cleo"}, {"name": "Pancakes"}] + + def test_query_json_empty(db_path): result = CliRunner().invoke( cli.cli, @@ -964,7 +1005,7 @@ LOREM_IPSUM_COMPRESSED = ( def test_query_json_binary(db_path): db = Database(db_path) with db.conn: - db["files"].insert( + db.table("files").insert( { "name": "lorem.txt", "sz": 16984, @@ -981,16 +1022,14 @@ def test_query_json_binary(db_path): "data": { "$base64": True, "encoded": ( - ( - "eJzt0c1xAyEMBeC7q1ABHleR3HxNAQrIjmb4M0gelx+RTY7p4N2WBYT0vmufUknH" - "8kq5lz5pqRFXsTOl3pYkE/NJnHXoStruJEVjc0mOCyTqq/ZMJnXEZW1Js2ZvRm5U+" - "DPKk9hRWqjyvTFx0YfzhT6MpGmN2lR1fzxjyfVMD9dFrS+bnkleMpMam/ZGXgrX1I" - "/K+5Au3S/9lNQRh0k4Gq/RUz8GiKfsQm+7JLsJ6fTo5JhVG00ZU76kZZkxePx49uI" - "jnpNoJyYlWUsoaSl/CcVATje/Kxu13RANnrHweaH3V5Jh4jvGyKCnxJLiXPKhmW3f" - "iCnG7Jql7RR3UvFo8jJ4z039dtOkTFmWzL1be9lt8A5II471m6vXy+l0BR/4wAc+8" - "IEPfOADH/jABz7wgQ984AMf+MAHPvCBD3zgAx/4wAc+8IEPfOADH/jABz7wgQ984A" - "Mf+MAHPvCBD3zgAx/4wAc+8IEPfOADH/jABz7wgQ984PuP7xubBoN9" - ) + "eJzt0c1xAyEMBeC7q1ABHleR3HxNAQrIjmb4M0gelx+RTY7p4N2WBYT0vmufUknH" + "8kq5lz5pqRFXsTOl3pYkE/NJnHXoStruJEVjc0mOCyTqq/ZMJnXEZW1Js2ZvRm5U+" + "DPKk9hRWqjyvTFx0YfzhT6MpGmN2lR1fzxjyfVMD9dFrS+bnkleMpMam/ZGXgrX1I" + "/K+5Au3S/9lNQRh0k4Gq/RUz8GiKfsQm+7JLsJ6fTo5JhVG00ZU76kZZkxePx49uI" + "jnpNoJyYlWUsoaSl/CcVATje/Kxu13RANnrHweaH3V5Jh4jvGyKCnxJLiXPKhmW3f" + "iCnG7Jql7RR3UvFo8jJ4z039dtOkTFmWzL1be9lt8A5II471m6vXy+l0BR/4wAc+8" + "IEPfOADH/jABz7wgQ984AMf+MAHPvCBD3zgAx/4wAc+8IEPfOADH/jABz7wgQ984A" + "Mf+MAHPvCBD3zgAx/4wAc+8IEPfOADH/jABz7wgQ984PuP7xubBoN9" ), }, } @@ -1021,7 +1060,7 @@ def test_query_params(db_path, sql, params, expected): def test_query_json_with_json_cols(db_path): db = Database(db_path) with db.conn: - db["dogs"].insert( + db.table("dogs").insert( { "id": 1, "name": "Cleo", @@ -1050,7 +1089,7 @@ def test_query_json_with_json_cols(db_path): def test_query_json_unicode_not_escaped_by_default(db_path): db = Database(db_path) with db.conn: - db["text"].insert({"id": 1, "text": "Japanese 日本語"}, pk="id") + db.table("text").insert({"id": 1, "text": "Japanese 日本語"}, pk="id") result = CliRunner().invoke(cli.cli, [db_path, "select id, text from text"]) assert result.exit_code == 0 assert result.output.strip() == '[{"id": 1, "text": "Japanese 日本語"}]' @@ -1064,7 +1103,7 @@ def test_query_json_unicode_not_escaped_by_default(db_path): def test_query_json_ascii_option(db_path, command): db = Database(db_path) with db.conn: - db["text"].insert({"id": 1, "text": "Japanese 日本語"}, pk="id") + db.table("text").insert({"id": 1, "text": "Japanese 日本語"}, pk="id") if command == "query": args = [db_path, "select id, text from text", "--ascii"] else: @@ -1080,7 +1119,7 @@ def test_query_json_ascii_option(db_path, command): [(b"\x00\x0fbinary", True), ("this is text", False), (1, False), (1.5, False)], ) def test_query_raw(db_path, content, is_binary): - Database(db_path)["files"].insert({"content": content}) + Database(db_path).table("files").insert({"content": content}) result = CliRunner().invoke( cli.cli, [db_path, "select content from files", "--raw"] ) @@ -1095,7 +1134,7 @@ def test_query_raw(db_path, content, is_binary): [(b"\x00\x0fbinary", True), ("this is text", False), (1, False), (1.5, False)], ) def test_query_raw_lines(db_path, content, is_binary): - Database(db_path)["files"].insert_all({"content": content} for _ in range(3)) + Database(db_path).table("files").insert_all({"content": content} for _ in range(3)) result = CliRunner().invoke( cli.cli, [db_path, "select content from files", "--raw-lines"] ) @@ -1145,6 +1184,11 @@ def test_query_memory_does_not_create_file(tmpdir): ["-c", "name", "--limit", "1", "--offset", "1"], '[{"name": "Pancakes"}]', ), + # --offset without --limit + ( + ["-c", "name", "--offset", "1"], + '[{"name": "Pancakes"}]', + ), # --where ( ["-c", "name", "--where", "id = 1"], @@ -1172,12 +1216,12 @@ def test_query_memory_does_not_create_file(tmpdir): def test_rows(db_path, args, expected): db = Database(db_path) with db.conn: - db["dogs"].insert_all( + db.table("dogs").insert_all( [ {"id": 1, "age": 4, "name": "Cleo"}, {"id": 2, "age": 2, "name": "Pancakes"}, ], - column_order=("id", "name", "age"), + column_order=["id", "name", "age"], ) result = CliRunner().invoke(cli.cli, ["rows", db_path, "dogs"] + args) assert expected == result.output.strip() @@ -1197,7 +1241,7 @@ def test_upsert(db_path, tmpdir): catch_exceptions=False, ) assert result.exit_code == 0, result.output - assert 2 == db["dogs"].count + assert 2 == db.table("dogs").count # Now run the upsert to update just their ages upsert_dogs = [ {"id": 1, "age": 5}, @@ -1216,26 +1260,44 @@ def test_upsert(db_path, tmpdir): ] -def test_upsert_pk_required(db_path, tmpdir): +def test_upsert_pk_inferred_from_existing_table(db_path, tmpdir): json_path = str(tmpdir / "dogs.json") + db = Database(db_path) insert_dogs = [ {"id": 1, "name": "Cleo", "age": 4}, {"id": 2, "name": "Nixie", "age": 4}, ] write_json(json_path, insert_dogs) + result = CliRunner().invoke( + cli.cli, + ["insert", db_path, "dogs", json_path, "--pk", "id"], + catch_exceptions=False, + ) + assert result.exit_code == 0, result.output + + write_json( + json_path, + [ + {"id": 1, "age": 5}, + {"id": 2, "age": 5}, + ], + ) result = CliRunner().invoke( cli.cli, ["upsert", db_path, "dogs", json_path], catch_exceptions=False, ) - assert result.exit_code == 2 - assert "Error: Missing option '--pk'" in result.output + assert result.exit_code == 0, result.output + assert list(db.query("select * from dogs order by id")) == [ + {"id": 1, "name": "Cleo", "age": 5}, + {"id": 2, "name": "Nixie", "age": 5}, + ] def test_upsert_analyze(db_path, tmpdir): db = Database(db_path) - db["rows"].insert({"id": 1, "foo": "x", "n": 3}, pk="id") - db["rows"].create_index(["n"]) + db.table("rows").insert({"id": 1, "foo": "x", "n": 3}, pk="id") + db.table("rows").create_index(["n"]) assert "sqlite_stat1" not in db.table_names() result = CliRunner().invoke( cli.cli, @@ -1249,7 +1311,7 @@ def test_upsert_analyze(db_path, tmpdir): def test_upsert_flatten(tmpdir): db_path = str(tmpdir / "flat.db") db = Database(db_path) - db["upsert_me"].insert({"id": 1, "name": "Example"}, pk="id") + db.table("upsert_me").insert({"id": 1, "name": "Example"}, pk="id") result = CliRunner().invoke( cli.cli, ["upsert", db_path, "upsert_me", "-", "--flatten", "--pk", "id", "--alter"], @@ -1363,7 +1425,7 @@ def test_create_table(args, schema): ) assert result.exit_code == 0 db = Database("test.db") - assert schema == db["t"].schema + assert schema == db.table("t").schema def test_create_table_foreign_key(): @@ -1398,21 +1460,21 @@ def test_create_table_foreign_key(): ' "id" INTEGER PRIMARY KEY,\n' ' "name" TEXT\n' ")" - ) == db["authors"].schema + ) == db.table("authors").schema assert ( 'CREATE TABLE "books" (\n' ' "id" INTEGER PRIMARY KEY,\n' ' "title" TEXT,\n' ' "author_id" INTEGER REFERENCES "authors"("id")\n' ")" - ) == db["books"].schema + ) == db.table("books").schema def test_create_table_error_if_table_exists(): runner = CliRunner() with runner.isolated_filesystem(): db = Database("test.db") - db["dogs"].insert({"name": "Cleo"}) + db.table("dogs").insert({"name": "Cleo"}) result = runner.invoke( cli.cli, ["create-table", "test.db", "dogs", "id", "integer"] ) @@ -1427,24 +1489,24 @@ def test_create_table_ignore(): runner = CliRunner() with runner.isolated_filesystem(): db = Database("test.db") - db["dogs"].insert({"name": "Cleo"}) + db.table("dogs").insert({"name": "Cleo"}) result = runner.invoke( cli.cli, ["create-table", "test.db", "dogs", "id", "integer", "--ignore"] ) assert result.exit_code == 0 - assert 'CREATE TABLE "dogs" (\n "name" TEXT\n)' == db["dogs"].schema + assert 'CREATE TABLE "dogs" (\n "name" TEXT\n)' == db.table("dogs").schema def test_create_table_replace(): runner = CliRunner() with runner.isolated_filesystem(): db = Database("test.db") - db["dogs"].insert({"name": "Cleo"}) + db.table("dogs").insert({"name": "Cleo"}) result = runner.invoke( cli.cli, ["create-table", "test.db", "dogs", "id", "integer", "--replace"] ) assert result.exit_code == 0 - assert 'CREATE TABLE "dogs" (\n "id" INTEGER\n)' == db["dogs"].schema + assert 'CREATE TABLE "dogs" (\n "id" INTEGER\n)' == db.table("dogs").schema def test_create_view(): @@ -1456,7 +1518,8 @@ def test_create_view(): ) assert result.exit_code == 0 assert ( - 'CREATE VIEW "version" AS select sqlite_version()' == db["version"].schema + 'CREATE VIEW "version" AS select sqlite_version()' + == db.view("version").schema ) @@ -1493,7 +1556,7 @@ def test_create_view_ignore(): assert result.exit_code == 0 assert ( 'CREATE VIEW "version" AS select sqlite_version() + 1' - == db["version"].schema + == db.view("version").schema ) @@ -1514,7 +1577,8 @@ def test_create_view_replace(): ) assert result.exit_code == 0 assert ( - 'CREATE VIEW "version" AS select sqlite_version()' == db["version"].schema + 'CREATE VIEW "version" AS select sqlite_version()' + == db.view("version").schema ) @@ -1522,7 +1586,7 @@ def test_drop_table(): runner = CliRunner() with runner.isolated_filesystem(): db = Database("test.db") - db["t"].create({"pk": int}, pk="pk") + db.table("t").create({"pk": int}, pk="pk") assert "t" in db.table_names() result = runner.invoke( cli.cli, @@ -1540,7 +1604,7 @@ def test_drop_table_error(): runner = CliRunner() with runner.isolated_filesystem(): db = Database("test.db") - db["t"].create({"pk": int}, pk="pk") + db.table("t").create({"pk": int}, pk="pk") result = runner.invoke( cli.cli, [ @@ -1563,7 +1627,7 @@ def test_drop_table_on_view_errors(): runner = CliRunner() with runner.isolated_filesystem(): db = Database("test.db") - db["t"].insert({"id": 1}) + db.table("t").insert({"id": 1}) db.create_view("v", "select * from t") result = runner.invoke(cli.cli, ["drop-table", "test.db", "v"]) assert result.exit_code == 1 @@ -1599,7 +1663,7 @@ def test_drop_view_on_table_errors(): runner = CliRunner() with runner.isolated_filesystem(): db = Database("test.db") - db["t"].insert({"id": 1}) + db.table("t").insert({"id": 1}) result = runner.invoke(cli.cli, ["drop-view", "test.db", "t"]) assert result.exit_code == 1 assert 'Error: "t" is a table, not a view - use drop-table to drop it' == ( @@ -1616,7 +1680,7 @@ def test_drop_view_error(): runner = CliRunner() with runner.isolated_filesystem(): db = Database("test.db") - db["t"].create({"pk": int}, pk="pk") + db.table("t").create({"pk": int}, pk="pk") result = runner.invoke( cli.cli, [ @@ -1641,7 +1705,7 @@ def test_enable_wal(): with runner.isolated_filesystem(): for dbname in dbs: db = Database(dbname) - db["t"].create({"pk": int}, pk="pk") + db.table("t").create({"pk": int}, pk="pk") assert db.journal_mode == "delete" result = runner.invoke(cli.cli, ["enable-wal"] + dbs, catch_exceptions=False) assert result.exit_code == 0 @@ -1656,7 +1720,7 @@ def test_disable_wal(): with runner.isolated_filesystem(): for dbname in dbs: db = Database(dbname) - db["t"].create({"pk": int}, pk="pk") + db.table("t").create({"pk": int}, pk="pk") db.enable_wal() assert db.journal_mode == "wal" result = runner.invoke(cli.cli, ["disable-wal"] + dbs) @@ -1679,7 +1743,7 @@ def test_disable_wal(): def test_query_update(db_path, args, expected): db = Database(db_path) with db.conn: - db["dogs"].insert_all( + db.table("dogs").insert_all( [ {"id": 1, "age": 4, "name": "Cleo"}, ] @@ -1695,11 +1759,13 @@ def test_query_update(db_path, args, expected): def test_add_foreign_keys(db_path): db = Database(db_path) - db["countries"].insert({"id": 7, "name": "Panama"}, pk="id") - db["authors"].insert({"id": 3, "name": "Matilda", "country_id": 7}, pk="id") - db["books"].insert({"id": 2, "title": "Wolf anatomy", "author_id": 3}, pk="id") - assert db["authors"].foreign_keys == [] - assert db["books"].foreign_keys == [] + db.table("countries").insert({"id": 7, "name": "Panama"}, pk="id") + db.table("authors").insert({"id": 3, "name": "Matilda", "country_id": 7}, pk="id") + db.table("books").insert( + {"id": 2, "title": "Wolf anatomy", "author_id": 3}, pk="id" + ) + assert db.table("authors").foreign_keys == [] + assert db.table("books").foreign_keys == [] result = CliRunner().invoke( cli.cli, [ @@ -1716,7 +1782,7 @@ def test_add_foreign_keys(db_path): ], ) assert result.exit_code == 0 - assert db["authors"].foreign_keys == [ + assert db.table("authors").foreign_keys == [ ForeignKey( table="authors", column="country_id", @@ -1724,7 +1790,7 @@ def test_add_foreign_keys(db_path): other_column="id", ) ] - assert db["books"].foreign_keys == [ + assert db.table("books").foreign_keys == [ ForeignKey( table="books", column="author_id", other_table="authors", other_column="id" ) @@ -1848,7 +1914,7 @@ def test_add_foreign_keys(db_path): def test_transform(db_path, args, expected_schema): db = Database(db_path) with db.conn: - db["dogs"].insert( + db.table("dogs").insert( {"id": 1, "age": 4, "name": "Cleo"}, not_null={"age"}, defaults={"age": 1}, @@ -1857,20 +1923,20 @@ def test_transform(db_path, args, expected_schema): result = CliRunner().invoke(cli.cli, ["transform", db_path, "dogs"] + args) print(result.output) assert result.exit_code == 0 - schema = db["dogs"].schema + schema = db.table("dogs").schema assert schema == expected_schema def test_transform_sql(db_path): db = Database(db_path) with db.conn: - db["dogs"].insert( + db.table("dogs").insert( {"id": 1, "age": 4, "name": "Cleo"}, not_null={"age"}, defaults={"age": 1}, pk="id", ) - original_schema = db["dogs"].schema + original_schema = db.table("dogs").schema result = CliRunner().invoke( cli.cli, ["transform", db_path, "dogs", "--drop", "name", "--sql"] @@ -1881,7 +1947,84 @@ def test_transform_sql(db_path): assert '"age" INTEGER NOT NULL DEFAULT' in result.output assert 'DROP TABLE "dogs";' in result.output assert 'ALTER TABLE "dogs_new_' in result.output - assert db["dogs"].schema == original_schema + assert db.table("dogs").schema == original_schema + + +@pytest.mark.parametrize( + "initial_strict,args,expected_strict", + ( + (False, [], False), + (True, [], True), + (False, ["--strict"], True), + (True, ["--no-strict"], False), + ), +) +def test_transform_strict_option(db_path, initial_strict, args, expected_strict): + db = Database(db_path) + if not db.supports_strict: + pytest.skip("SQLite version does not support strict tables") + db.table("dogs").create({"id": int}, strict=initial_strict) + + result = CliRunner().invoke(cli.cli, ["transform", db_path, "dogs"] + args) + + assert result.exit_code == 0, result.output + assert db.table("dogs").strict is expected_strict + + +@pytest.mark.parametrize( + "initial_strict,flag,sql_is_strict", + ( + (False, "--strict", True), + (True, "--no-strict", False), + ), +) +def test_transform_strict_option_sql(db_path, initial_strict, flag, sql_is_strict): + db = Database(db_path) + if not db.supports_strict: + pytest.skip("SQLite version does not support strict tables") + db.table("dogs").create({"id": int}, strict=initial_strict) + + result = CliRunner().invoke(cli.cli, ["transform", db_path, "dogs", flag, "--sql"]) + + assert result.exit_code == 0, result.output + assert (") STRICT;" in result.output) is sql_is_strict + assert db.table("dogs").strict is initial_strict + + +def test_transform_strict_option_with_invalid_data(db_path): + db = Database(db_path) + if not db.supports_strict: + pytest.skip("SQLite version does not support strict tables") + dogs = db.table("dogs") + dogs.create({"id": int}) + dogs.insert({"id": "not-an-integer"}) + + result = CliRunner().invoke(cli.cli, ["transform", db_path, "dogs", "--strict"]) + + assert result.exit_code == 1 + assert isinstance(result.exception, sqlite3.IntegrityError) + assert dogs.strict is False + assert list(dogs.rows) == [{"id": "not-an-integer"}] + assert not any(name.startswith("dogs_new_") for name in db.table_names()) + + +def test_transform_column_to_any(db_path): + db = Database(db_path) + if not db.supports_strict: + pytest.skip("SQLite version does not support strict tables") + db.table("items").create({"data": str}, strict=True) + db.table("items").insert({"data": "000123"}) + + result = CliRunner().invoke( + cli.cli, ["transform", db_path, "items", "--type", "data", "any"] + ) + + assert result.exit_code == 0, result.output + assert db.table("items").columns_dict == {"data": ANY} + assert db.execute("select typeof(data), data from items").fetchone() == ( + "text", + "000123", + ) @pytest.mark.parametrize( @@ -1929,10 +2072,10 @@ def test_transform_add_or_drop_foreign_key(db_path, extra_args, expected_schema) db = Database(db_path) with db.conn: # Create table with three foreign keys so we can drop two of them - db["continent"].insert({"id": 1, "name": "Europe"}, pk="id") - db["country"].insert({"id": 1, "name": "France"}, pk="id") - db["city"].insert({"id": 24, "name": "Paris"}, pk="id") - db["places"].insert( + db.table("continent").insert({"id": 1, "name": "Europe"}, pk="id") + db.table("country").insert({"id": 1, "name": "France"}, pk="id") + db.table("city").insert({"id": 24, "name": "Paris"}, pk="id") + db.table("places").insert( { "id": 32, "name": "Caveau de la Huchette", @@ -1953,7 +2096,7 @@ def test_transform_add_or_drop_foreign_key(db_path, extra_args, expected_schema) + extra_args, ) assert result.exit_code == 0 - schema = db["places"].schema + schema = db.table("places").schema assert schema == expected_schema @@ -2000,11 +2143,13 @@ _common_other_schema = ( ), ( ["--rename", "name", "name2"], - 'CREATE TABLE "trees" (\n' - ' "id" INTEGER PRIMARY KEY,\n' - ' "address" TEXT,\n' - ' "species_id" INTEGER REFERENCES "species"("id")\n' - ")", + ( + 'CREATE TABLE "trees" (\n' + ' "id" INTEGER PRIMARY KEY,\n' + ' "address" TEXT,\n' + ' "species_id" INTEGER REFERENCES "species"("id")\n' + ")" + ), 'CREATE TABLE "species" (\n "id" INTEGER PRIMARY KEY,\n "species" TEXT\n)', ), ], @@ -2012,7 +2157,7 @@ _common_other_schema = ( def test_extract(db_path, args, expected_table_schema, expected_other_schema): db = Database(db_path) with db.conn: - db["trees"].insert( + db.table("trees").insert( {"id": 1, "address": "4 Park Ave", "species": "Palm"}, pk="id", ) @@ -2021,11 +2166,11 @@ def test_extract(db_path, args, expected_table_schema, expected_other_schema): ) print(result.output) assert result.exit_code == 0 - schema = db["trees"].schema + schema = db.table("trees").schema assert schema == expected_table_schema - other_schema = [t for t in db.tables if t.name not in ("trees", "Gosh", "Gosh2")][ - 0 - ].schema + other_schema = next( + t for t in db.tables if t.name not in ("trees", "Gosh", "Gosh2") + ).schema assert other_schema == expected_other_schema @@ -2069,7 +2214,7 @@ def test_insert_encoding(tmpdir): ) assert good_result.exit_code == 0 db = Database(db_path) - assert list(db["places"].rows) == [ + assert list(db.table("places").rows) == [ { "date": "2020-01-01", "name": "Barra da Lagoa", @@ -2105,7 +2250,7 @@ def test_insert_encoding(tmpdir): def test_search(tmpdir, fts, extra_arg, expected): db_path = str(tmpdir / "test.db") db = Database(db_path) - db["articles"].insert_all( + db.table("articles").insert_all( [ {"id": 1, "title": "Title the first"}, {"id": 2, "title": "Title the second"}, @@ -2113,7 +2258,7 @@ def test_search(tmpdir, fts, extra_arg, expected): ], pk="id", ) - db["articles"].enable_fts(["title"], fts_version=fts) + db.table("articles").enable_fts(["title"], fts_version=fts) result = CliRunner().invoke( cli.cli, ["search", db_path, "articles", "second"] + ([extra_arg] if extra_arg else []), @@ -2126,7 +2271,7 @@ def test_search(tmpdir, fts, extra_arg, expected): def test_search_quote(tmpdir): db_path = str(tmpdir / "test.db") db = Database(db_path) - db["creatures"].insert({"name": "dog."}).enable_fts(["name"]) + db.table("creatures").insert({"name": "dog."}).enable_fts(["name"]) # Without --quote should return an error error_result = CliRunner().invoke(cli.cli, ["search", db_path, "creatures", 'dog"']) assert error_result.exit_code == 1 @@ -2234,11 +2379,11 @@ _TRIGGERS_EXPECTED = ( def test_triggers(tmpdir, extra_args, expected): db_path = str(tmpdir / "test.db") db = Database(db_path) - db["articles"].insert( + db.table("articles").insert( {"id": 1, "title": "Title the first"}, pk="id", ) - db["counter"].insert({"count": 1}) + db.table("counter").insert({"count": 1}) db.conn.execute(textwrap.dedent(""" CREATE TRIGGER blah AFTER INSERT ON articles BEGIN @@ -2299,9 +2444,9 @@ def test_triggers(tmpdir, extra_args, expected): def test_schema(tmpdir, options, expected): db_path = str(tmpdir / "test.db") db = Database(db_path) - db["dogs"].create({"id": int, "name": str}) - db["chickens"].create({"id": int, "name": str, "breed": str}) - db["chickens"].create_index(["breed"]) + db.table("dogs").create({"id": int, "name": str}) + db.table("chickens").create({"id": int, "name": str, "breed": str}) + db.table("chickens").create_index(["breed"]) result = CliRunner().invoke( cli.cli, ["schema", db_path] + options, @@ -2317,7 +2462,7 @@ def test_long_csv_column_value(tmpdir): with open(csv_path, "w") as csv_file: long_string = "a" * 131073 csv_file.write("id,text\n") - csv_file.write("1,{}\n".format(long_string)) + csv_file.write(f"1,{long_string}\n") result = CliRunner().invoke( cli.cli, ["insert", db_path, "bigtable", csv_path, "--csv"], @@ -2325,7 +2470,7 @@ def test_long_csv_column_value(tmpdir): ) assert result.exit_code == 0 db = Database(db_path) - rows = list(db["bigtable"].rows) + rows = list(db.table("bigtable").rows) assert len(rows) == 1 assert rows[0]["text"] == long_string @@ -2343,8 +2488,8 @@ def test_import_no_headers(tmpdir, args, tsv): csv_path = str(tmpdir / "test.csv") with open(csv_path, "w") as csv_file: sep = "\t" if tsv else "," - csv_file.write("Cleo{sep}Dog{sep}5\n".format(sep=sep)) - csv_file.write("Tracy{sep}Spider{sep}7\n".format(sep=sep)) + csv_file.write(f"Cleo{sep}Dog{sep}5\n") + csv_file.write(f"Tracy{sep}Spider{sep}7\n") result = CliRunner().invoke( cli.cli, ["insert", db_path, "creatures", csv_path] + args + ["--no-detect-types"], @@ -2352,7 +2497,7 @@ def test_import_no_headers(tmpdir, args, tsv): ) assert result.exit_code == 0, result.output db = Database(db_path) - schema = db["creatures"].schema + schema = db.table("creatures").schema assert schema == ( 'CREATE TABLE "creatures" (\n' ' "untitled_1" TEXT,\n' @@ -2360,7 +2505,7 @@ def test_import_no_headers(tmpdir, args, tsv): ' "untitled_3" TEXT\n' ")" ) - rows = list(db["creatures"].rows) + rows = list(db.table("creatures").rows) assert rows == [ {"untitled_1": "Cleo", "untitled_2": "Dog", "untitled_3": "5"}, {"untitled_1": "Tracy", "untitled_2": "Spider", "untitled_3": "7"}, @@ -2372,10 +2517,10 @@ def test_attach(tmpdir): bar_path = str(tmpdir / "bar.db") db = Database(foo_path) with db.conn: - db["foo"].insert({"id": 1, "text": "foo"}) + db.table("foo").insert({"id": 1, "text": "foo"}) db2 = Database(bar_path) with db2.conn: - db2["bar"].insert({"id": 1, "text": "bar"}) + db2.table("bar").insert({"id": 1, "text": "bar"}) db.attach("bar", bar_path) sql = "select * from foo union all select * from bar.bar" result = CliRunner().invoke( @@ -2436,7 +2581,7 @@ def test_insert_detect_types(tmpdir): ) assert result.exit_code == 0 db = Database(db_path) - assert list(db["creatures"].rows) == [ + assert list(db.table("creatures").rows) == [ {"name": "Cleo", "age": 6, "weight": 45.5}, {"name": "Dori", "age": 1, "weight": 3.5}, ] @@ -2468,7 +2613,7 @@ def test_upsert_detect_types(tmpdir): ) assert result.exit_code == 0 db = Database(db_path) - assert list(db["creatures"].rows) == [ + assert list(db.table("creatures").rows) == [ {"id": 1, "name": "Cleo", "age": 6, "weight": 45.5}, {"id": 2, "name": "Dori", "age": 1, "weight": 3.5}, ] @@ -2487,7 +2632,7 @@ def test_csv_detect_types_creates_real_columns(tmpdir): assert result.exit_code == 0 db = Database(db_path) # Check that the schema uses REAL for the weight column - assert db["creatures"].schema == ( + assert db.table("creatures").schema == ( 'CREATE TABLE "creatures" (\n' ' "name" TEXT,\n' ' "age" INTEGER,\n' @@ -2509,11 +2654,11 @@ def test_insert_no_detect_types(tmpdir): assert result.exit_code == 0 db = Database(db_path) # All columns should be TEXT when --no-detect-types is used - assert list(db["creatures"].rows) == [ + assert list(db.table("creatures").rows) == [ {"name": "Cleo", "age": "6", "weight": "45.5"}, {"name": "Dori", "age": "1", "weight": "3.5"}, ] - assert db["creatures"].schema == ( + assert db.table("creatures").schema == ( 'CREATE TABLE "creatures" (\n' ' "name" TEXT,\n' ' "age" TEXT,\n' @@ -2544,11 +2689,11 @@ def test_upsert_no_detect_types(tmpdir): assert result.exit_code == 0 db = Database(db_path) # All columns should be TEXT when --no-detect-types is used - assert list(db["creatures"].rows) == [ + assert list(db.table("creatures").rows) == [ {"id": "1", "name": "Cleo", "age": "6", "weight": "45.5"}, {"id": "2", "name": "Dori", "age": "1", "weight": "3.5"}, ] - assert db["creatures"].schema == ( + assert db.table("creatures").schema == ( 'CREATE TABLE "creatures" (\n' ' "id" TEXT PRIMARY KEY,\n' ' "name" TEXT,\n' @@ -2576,7 +2721,9 @@ def test_integer_overflow_error(tmpdir): def test_python_dash_m(): "Tool can be run using python -m sqlite_utils" result = subprocess.run( - [sys.executable, "-m", "sqlite_utils", "--help"], stdout=subprocess.PIPE + [sys.executable, "-m", "sqlite_utils", "--help"], + stdout=subprocess.PIPE, + check=False, ) assert result.returncode == 0 assert b"Commands for interacting with a SQLite database" in result.stdout @@ -2628,20 +2775,20 @@ def test_create_database(tmpdir, enable_wal): def test_analyze(tmpdir, options, expected): db_path = str(tmpdir / "test.db") db = Database(db_path) - db["one_index"].insert({"id": 1, "name": "Cleo"}, pk="id") - db["one_index"].create_index(["name"]) - db["two_indexes"].insert({"id": 1, "name": "Cleo", "species": "dog"}, pk="id") - db["two_indexes"].create_index(["name"]) - db["two_indexes"].create_index(["species"]) + db.table("one_index").insert({"id": 1, "name": "Cleo"}, pk="id") + db.table("one_index").create_index(["name"]) + db.table("two_indexes").insert({"id": 1, "name": "Cleo", "species": "dog"}, pk="id") + db.table("two_indexes").create_index(["name"]) + db.table("two_indexes").create_index(["species"]) result = CliRunner().invoke(cli.cli, ["analyze", db_path] + options) assert result.exit_code == 0 - assert list(db["sqlite_stat1"].rows) == expected + assert list(db.table("sqlite_stat1").rows) == expected def test_rename_table(tmpdir): db_path = str(tmpdir / "test.db") db = Database(db_path) - db["one"].insert({"id": 1, "name": "Cleo"}, pk="id") + db.table("one").insert({"id": 1, "name": "Cleo"}, pk="id") # First try a non-existent table result_error = CliRunner().invoke( cli.cli, @@ -2659,7 +2806,7 @@ def test_rename_table(tmpdir): catch_exceptions=False, ) assert result_error2.exit_code == 0 - previous_columns = db["one"].columns_dict + previous_columns = db.table("one").columns_dict # Now try for a table that exists result = CliRunner().invoke( cli.cli, @@ -2667,13 +2814,13 @@ def test_rename_table(tmpdir): catch_exceptions=False, ) assert result.exit_code == 0 - assert db["two"].columns_dict == previous_columns + assert db.table("two").columns_dict == previous_columns def test_duplicate_table(tmpdir): db_path = str(tmpdir / "test.db") db = Database(db_path) - db["one"].insert({"id": 1, "name": "Cleo"}, pk="id") + db.table("one").insert({"id": 1, "name": "Cleo"}, pk="id") # First try a non-existent table result_error = CliRunner().invoke( cli.cli, @@ -2696,8 +2843,8 @@ def test_duplicate_table(tmpdir): catch_exceptions=False, ) assert result.exit_code == 0 - assert db["one"].columns_dict == db["two"].columns_dict - assert list(db["one"].rows) == list(db["two"].rows) + assert db.table("one").columns_dict == db.table("two").columns_dict + assert list(db.table("one").rows) == list(db.table("two").rows) @pytest.mark.skipif(not _has_compiled_ext(), reason="Requires compiled ext.c") @@ -2716,14 +2863,14 @@ def test_load_extension(entrypoint, should_pass, should_fail): for func in should_pass: result = CliRunner().invoke( cli.cli, - ["memory", "select {}()".format(func), "--load-extension", ext], + ["memory", f"select {func}()", "--load-extension", ext], catch_exceptions=False, ) assert result.exit_code == 0 for func in should_fail: result = CliRunner().invoke( cli.cli, - ["memory", "select {}()".format(func), "--load-extension", ext], + ["memory", f"select {func}()", "--load-extension", ext], catch_exceptions=False, ) assert result.exit_code == 1 @@ -2740,9 +2887,33 @@ def test_create_table_strict(strict): + (["--strict"] if strict else []), ) assert result.exit_code == 0 - assert db["items"].strict == strict or not db.supports_strict + assert db.table("items").strict == strict or not db.supports_strict # Should have a floating point column - assert db["items"].columns_dict == {"id": int, "w": float} + assert db.table("items").columns_dict == {"id": int, "w": float} + + +def test_create_table_strict_any(): + runner = CliRunner() + with runner.isolated_filesystem(): + db = Database("test.db") + if not db.supports_strict: + pytest.skip("SQLite version does not support strict tables") + result = runner.invoke( + cli.cli, + [ + "create-table", + "test.db", + "items", + "id", + "integer", + "data", + "any", + "--strict", + ], + ) + assert result.exit_code == 0, result.output + assert db.table("items").strict is True + assert db.table("items").columns_dict == {"id": int, "data": ANY} @pytest.mark.parametrize("method", ("insert", "upsert")) @@ -2757,12 +2928,45 @@ def test_insert_upsert_strict(tmpdir, method, strict): ) assert result.exit_code == 0 db = Database(db_path) - assert db["items"].strict == strict or not db.supports_strict + assert db.table("items").strict == strict or not db.supports_strict + + +@pytest.mark.parametrize("method", ("insert", "upsert")) +def test_insert_upsert_strict_any(tmpdir, method): + db_path = str(tmpdir / "test.db") + db = Database(db_path) + if not db.supports_strict: + pytest.skip("SQLite version does not support strict tables") + db.close() + result = CliRunner().invoke( + cli.cli, + [ + method, + db_path, + "items", + "-", + "--csv", + "--pk", + "id", + "--type", + "data", + "any", + "--strict", + ], + input="id,data\n1,000123", + ) + assert result.exit_code == 0, result.output + db = Database(db_path) + assert db.table("items").columns_dict == {"id": int, "data": ANY} + assert db.execute("select typeof(data), data from items").fetchone() == ( + "text", + "000123", + ) def test_extract_bad_column_clean_error(db_path): db = Database(db_path) - db["trees"].insert({"id": 1, "species": "Palm"}, pk="id") + db.table("trees").insert({"id": 1, "species": "Palm"}, pk="id") result = CliRunner().invoke(cli.cli, ["extract", db_path, "trees", "nope"]) assert result.exit_code == 1 assert result.exception is None or isinstance(result.exception, SystemExit) @@ -2771,7 +2975,7 @@ def test_extract_bad_column_clean_error(db_path): def test_extract_view_clean_error(db_path): db = Database(db_path) - db["trees"].insert({"id": 1, "species": "Palm"}, pk="id") + db.table("trees").insert({"id": 1, "species": "Palm"}, pk="id") db.create_view("v", "select * from trees") result = CliRunner().invoke(cli.cli, ["extract", db_path, "v", "species"]) assert result.exit_code == 1 diff --git a/tests/test_cli_bulk.py b/tests/test_cli_bulk.py index 514f4ac..c5c9dcd 100644 --- a/tests/test_cli_bulk.py +++ b/tests/test_cli_bulk.py @@ -1,17 +1,19 @@ -from click.testing import CliRunner -from sqlite_utils import cli, Database import pathlib -import pytest import subprocess import sys import time +import pytest +from click.testing import CliRunner + +from sqlite_utils import Database, cli + @pytest.fixture def test_db_and_path(tmpdir): db_path = str(pathlib.Path(tmpdir) / "data.db") db = Database(db_path) - db["example"].insert_all( + db.table("example").insert_all( [ {"id": 1, "name": "One"}, {"id": 2, "name": "Two"}, @@ -42,7 +44,7 @@ def test_cli_bulk(test_db_and_path): {"id": 2, "name": "Two"}, {"id": 3, "name": "THREE"}, {"id": 4, "name": "FOUR"}, - ] == list(db["example"].rows) + ] == list(db.table("example").rows) def test_cli_bulk_multiple_functions(test_db_and_path): @@ -68,7 +70,7 @@ def test_cli_bulk_multiple_functions(test_db_and_path): {"id": 2, "name": "Two"}, {"id": 3, "name": "THREE"}, {"id": 4, "name": "FOUR"}, - ] == list(db["example"].rows) + ] == list(db.table("example").rows) def test_cli_bulk_batch_size(test_db_and_path): @@ -89,17 +91,18 @@ def test_cli_bulk_batch_size(test_db_and_path): stdin=subprocess.PIPE, stdout=sys.stdout, ) + assert proc.stdin is not None # Writing one record should not commit proc.stdin.write(b'{"id": 3, "name": "Three"}\n\n') proc.stdin.flush() time.sleep(1) - assert db["example"].count == 2 + assert db.table("example").count == 2 # Writing another should trigger a commit: proc.stdin.write(b'{"id": 4, "name": "Four"}\n\n') proc.stdin.flush() time.sleep(1) - assert db["example"].count == 4 + assert db.table("example").count == 4 proc.stdin.close() proc.wait() diff --git a/tests/test_cli_convert.py b/tests/test_cli_convert.py index 6c3f5c5..9f59d59 100644 --- a/tests/test_cli_convert.py +++ b/tests/test_cli_convert.py @@ -1,16 +1,18 @@ -from click.testing import CliRunner -from sqlite_utils import cli -import sqlite_utils import json -import textwrap import pathlib +import textwrap + import pytest +from click.testing import CliRunner + +import sqlite_utils +from sqlite_utils import cli @pytest.fixture def test_db_and_path(fresh_db_and_path): db, db_path = fresh_db_and_path - db["example"].insert_all( + db.table("example").insert_all( [ {"id": 1, "dt": "5th October 2019 12:04"}, {"id": 2, "dt": "6th October 2019 00:05:06"}, @@ -45,12 +47,12 @@ def fresh_db_and_path(tmpdir): ) def test_convert_code(fresh_db_and_path, code): db, db_path = fresh_db_and_path - db["t"].insert({"text": "October"}) + db.table("t").insert({"text": "October"}) result = CliRunner().invoke( cli.cli, ["convert", db_path, "t", "text", code], catch_exceptions=False ) assert result.exit_code == 0, result.output - value = list(db["t"].rows)[0]["text"] + value = next(iter(db.table("t").rows))["text"] assert value == "Spooktober" @@ -63,7 +65,7 @@ def test_convert_code(fresh_db_and_path, code): ) def test_convert_code_errors(fresh_db_and_path, bad_code): db, db_path = fresh_db_and_path - db["t"].insert({"text": "October"}) + db.table("t").insert({"text": "October"}) result = CliRunner().invoke( cli.cli, ["convert", db_path, "t", "text", bad_code], catch_exceptions=False ) @@ -91,12 +93,12 @@ def test_convert_import(test_db_and_path): {"id": 2, "dt": "6th OXXober 2019 00:05:06"}, {"id": 3, "dt": ""}, {"id": 4, "dt": None}, - ] == list(db["example"].rows) + ] == list(db.table("example").rows) def test_convert_import_nested(fresh_db_and_path): db, db_path = fresh_db_and_path - db["example"].insert({"xml": ''}) + db.table("example").insert({"xml": ''}) result = CliRunner().invoke( cli.cli, [ @@ -112,7 +114,7 @@ def test_convert_import_nested(fresh_db_and_path): assert result.exit_code == 0, result.output assert [ {"xml": "Cleo"}, - ] == list(db["example"].rows) + ] == list(db.table("example").rows) def test_convert_dryrun(test_db_and_path): @@ -150,7 +152,7 @@ def test_convert_dryrun(test_db_and_path): "Would affect 4 rows" ) # But it should not have actually modified the table data - assert list(db["example"].rows) == [ + assert list(db.table("example").rows) == [ {"id": 1, "dt": "5th October 2019 12:04"}, {"id": 2, "dt": "6th October 2019 00:05:06"}, {"id": 3, "dt": ""}, @@ -179,6 +181,34 @@ def test_convert_dryrun(test_db_and_path): assert result.output.strip().split("\n")[-1] == "Would affect 1 row" +def test_convert_dryrun_table_and_column_names_containing_closing_bracket( + fresh_db_and_path, +): + db, db_path = fresh_db_and_path + table_name = "table]name" + column_name = "column]name" + db[table_name].insert({column_name: "hello"}) + + result = CliRunner().invoke( + cli.cli, + [ + "convert", + db_path, + table_name, + column_name, + "value.upper()", + "--dry-run", + ], + catch_exceptions=False, + ) + + assert result.exit_code == 0 + assert result.output.strip() == ( + "hello\n --- becomes:\nHELLO\n\nWould affect 1 row" + ) + assert list(db[table_name].rows) == [{column_name: "hello"}] + + def test_convert_multi_dryrun(test_db_and_path): db_path = test_db_and_path[1] result = CliRunner().invoke( @@ -267,7 +297,7 @@ def test_convert_output_column(test_db_and_path, drop): if drop: for row in expected: del row["dt"] - assert list(db["example"].rows) == expected + assert list(db.table("example").rows) == expected @pytest.mark.parametrize( @@ -350,7 +380,7 @@ def test_convert_output_error(test_db_and_path, options, expected_error): @pytest.mark.parametrize("drop", (True, False)) def test_convert_multi(fresh_db_and_path, drop): db, db_path = fresh_db_and_path - db["creatures"].insert_all( + db.table("creatures").insert_all( [ {"id": 1, "name": "Simon"}, {"id": 2, "name": "Cleo"}, @@ -376,12 +406,12 @@ def test_convert_multi(fresh_db_and_path, drop): if drop: for row in expected: del row["name"] - assert list(db["creatures"].rows) == expected + assert list(db.table("creatures").rows) == expected def test_convert_multi_complex_column_types(fresh_db_and_path): db, db_path = fresh_db_and_path - db["rows"].insert_all( + db.table("rows").insert_all( [ {"id": 1}, {"id": 2}, @@ -410,7 +440,7 @@ def test_convert_multi_complex_column_types(fresh_db_and_path): ], ) assert result.exit_code == 0, result.output - assert list(db["rows"].rows) == [ + assert list(db.table("rows").rows) == [ {"id": 1, "is_str": "", "is_float": 1.2, "is_int": None, "is_bytes": None}, {"id": 2, "is_str": None, "is_float": 1.0, "is_int": 12, "is_bytes": None}, { @@ -422,7 +452,7 @@ def test_convert_multi_complex_column_types(fresh_db_and_path): }, {"id": 4, "is_str": None, "is_float": None, "is_int": None, "is_bytes": None}, ] - assert db["rows"].schema == ( + assert db.table("rows").schema == ( 'CREATE TABLE "rows" (\n' ' "id" INTEGER PRIMARY KEY\n' ', "is_str" TEXT, "is_float" REAL, "is_int" INTEGER, "is_bytes" BLOB)' @@ -433,7 +463,7 @@ def test_convert_multi_complex_column_types(fresh_db_and_path): def test_recipe_jsonsplit(tmpdir, delimiter): db_path = str(pathlib.Path(tmpdir) / "data.db") db = sqlite_utils.Database(db_path) - db["example"].insert_all( + db.table("example").insert_all( [ {"id": 1, "tags": (delimiter or ",").join(["foo", "bar"])}, {"id": 2, "tags": (delimiter or ",").join(["bar", "baz"])}, @@ -442,11 +472,11 @@ def test_recipe_jsonsplit(tmpdir, delimiter): ) code = "r.jsonsplit(value)" if delimiter: - code = 'recipes.jsonsplit(value, delimiter="{}")'.format(delimiter) + code = f'recipes.jsonsplit(value, delimiter="{delimiter}")' args = ["convert", db_path, "example", "tags", code] result = CliRunner().invoke(cli.cli, args) assert result.exit_code == 0, result.output - assert list(db["example"].rows) == [ + assert list(db.table("example").rows) == [ {"id": 1, "tags": '["foo", "bar"]'}, {"id": 2, "tags": '["bar", "baz"]'}, ] @@ -462,7 +492,7 @@ def test_recipe_jsonsplit(tmpdir, delimiter): ) def test_recipe_jsonsplit_type(fresh_db_and_path, type, expected_array): db, db_path = fresh_db_and_path - db["example"].insert_all( + db.table("example").insert_all( [ {"id": 1, "records": "1,2,3"}, ], @@ -470,17 +500,17 @@ def test_recipe_jsonsplit_type(fresh_db_and_path, type, expected_array): ) code = "r.jsonsplit(value)" if type: - code = "recipes.jsonsplit(value, type={})".format(type) + code = f"recipes.jsonsplit(value, type={type})" args = ["convert", db_path, "example", "records", code] result = CliRunner().invoke(cli.cli, args) assert result.exit_code == 0, result.output - assert json.loads(db["example"].get(1)["records"]) == expected_array + assert json.loads(db.table("example").get(1)["records"]) == expected_array @pytest.mark.parametrize("drop", (True, False)) def test_recipe_jsonsplit_output(fresh_db_and_path, drop): db, db_path = fresh_db_and_path - db["example"].insert_all( + db.table("example").insert_all( [ {"id": 1, "records": "1,2,3"}, ], @@ -499,7 +529,7 @@ def test_recipe_jsonsplit_output(fresh_db_and_path, drop): } if drop: del expected["records"] - assert db["example"].get(1) == expected + assert db.table("example").get(1) == expected def test_cannot_use_drop_without_multi_or_output(fresh_db_and_path): @@ -556,7 +586,7 @@ def test_convert_where(test_db_and_path): ], ) assert result.exit_code == 0, result.output - assert list(db["example"].rows) == [ + assert list(db.table("example").rows) == [ {"id": 1, "dt": "5th October 2019 12:04"}, {"id": 2, "dt": "6TH OCTOBER 2019 00:05:06"}, {"id": 3, "dt": ""}, @@ -566,7 +596,7 @@ def test_convert_where(test_db_and_path): def test_convert_where_multi(fresh_db_and_path): db, db_path = fresh_db_and_path - db["names"].insert_all( + db.table("names").insert_all( [{"id": 1, "name": "Cleo"}, {"id": 2, "name": "Bants"}], pk="id" ) result = CliRunner().invoke( @@ -586,7 +616,7 @@ def test_convert_where_multi(fresh_db_and_path): ], ) assert result.exit_code == 0, result.output - assert list(db["names"].rows) == [ + assert list(db.table("names").rows) == [ {"id": 1, "name": "Cleo", "upper": None}, {"id": 2, "name": "Bants", "upper": "BANTS"}, ] @@ -594,7 +624,7 @@ def test_convert_where_multi(fresh_db_and_path): def test_convert_code_standard_input(fresh_db_and_path): db, db_path = fresh_db_and_path - db["names"].insert_all([{"id": 1, "name": "Cleo"}], pk="id") + db.table("names").insert_all([{"id": 1, "name": "Cleo"}], pk="id") result = CliRunner().invoke( cli.cli, [ @@ -607,27 +637,27 @@ def test_convert_code_standard_input(fresh_db_and_path): input="value.upper()", ) assert result.exit_code == 0, result.output - assert list(db["names"].rows) == [ + assert list(db.table("names").rows) == [ {"id": 1, "name": "CLEO"}, ] def test_convert_hyphen_workaround(fresh_db_and_path): db, db_path = fresh_db_and_path - db["names"].insert_all([{"id": 1, "name": "Cleo"}], pk="id") + db.table("names").insert_all([{"id": 1, "name": "Cleo"}], pk="id") result = CliRunner().invoke( cli.cli, ["convert", db_path, "names", "name", '"-"'], ) assert result.exit_code == 0, result.output - assert list(db["names"].rows) == [ + assert list(db.table("names").rows) == [ {"id": 1, "name": "-"}, ] def test_convert_initialization_pattern(fresh_db_and_path): db, db_path = fresh_db_and_path - db["names"].insert_all([{"id": 1, "name": "Cleo"}], pk="id") + db.table("names").insert_all([{"id": 1, "name": "Cleo"}], pk="id") result = CliRunner().invoke( cli.cli, [ @@ -640,7 +670,7 @@ def test_convert_initialization_pattern(fresh_db_and_path): input="import random\nrandom.seed(1)\ndef convert(value): return random.randint(0, 100)", ) assert result.exit_code == 0, result.output - assert list(db["names"].rows) == [ + assert list(db.table("names").rows) == [ {"id": 1, "name": "17"}, ] @@ -655,13 +685,13 @@ def test_convert_handles_falsey_values(fresh_db_and_path): "x", "-", ] - db["t"].insert_all([{"x": 0}, {"x": 1}]) - assert db["t"].get(1)["x"] == 0 - assert db["t"].get(2)["x"] == 1 + db.table("t").insert_all([{"x": 0}, {"x": 1}]) + assert db.table("t").get(1)["x"] == 0 + assert db.table("t").get(2)["x"] == 1 result = CliRunner().invoke(cli.cli, args, input="value + 1") assert result.exit_code == 0, result.output - assert db["t"].get(1)["x"] == 1 - assert db["t"].get(2)["x"] == 2 + assert db.table("t").get(1)["x"] == 1 + assert db.table("t").get(2)["x"] == 2 @pytest.mark.parametrize( @@ -682,7 +712,7 @@ def test_convert_callable_reference(test_db_and_path, code): cli.cli, ["convert", db_path, "example", "dt", code], catch_exceptions=False ) assert result.exit_code == 0, result.output - rows = list(db["example"].rows) + rows = list(db.table("example").rows) assert rows[0]["dt"] == "2019-10-05" assert rows[1]["dt"] == "2019-10-06" assert rows[2]["dt"] == "" @@ -692,7 +722,7 @@ def test_convert_callable_reference(test_db_and_path, code): def test_convert_callable_reference_with_import(fresh_db_and_path): """Test callable reference from an imported module""" db, db_path = fresh_db_and_path - db["example"].insert({"id": 1, "data": '{"name": "test"}'}) + db.table("example").insert({"id": 1, "data": '{"name": "test"}'}) result = CliRunner().invoke( cli.cli, [ @@ -708,5 +738,5 @@ def test_convert_callable_reference_with_import(fresh_db_and_path): ) assert result.exit_code == 0, result.output # json.loads returns a dict, which sqlite stores as JSON string - row = db["example"].get(1) + row = db.table("example").get(1) assert row["data"] == '{"name": "test"}' diff --git a/tests/test_cli_insert.py b/tests/test_cli_insert.py index 5af8a2f..0117862 100644 --- a/tests/test_cli_insert.py +++ b/tests/test_cli_insert.py @@ -1,11 +1,13 @@ -from sqlite_utils import cli, Database -from click.testing import CliRunner import json -import pytest import subprocess import sys import time +import pytest +from click.testing import CliRunner + +from sqlite_utils import Database, cli + def test_insert_simple(tmpdir): json_path = str(tmpdir / "dog.json") @@ -19,7 +21,7 @@ def test_insert_simple(tmpdir): ) db = Database(db_path) assert ["dogs"] == db.table_names() - assert [] == db["dogs"].indexes + assert [] == db.table("dogs").indexes def test_insert_from_stdin(tmpdir): @@ -94,12 +96,12 @@ def test_insert_with_primary_keys(db_path, tmpdir, args, expected_pks): Database(db_path).query("select * from dogs") ) db = Database(db_path) - assert db["dogs"].pks == expected_pks + assert db.table("dogs").pks == expected_pks def test_insert_multiple_with_primary_key(db_path, tmpdir): json_path = str(tmpdir / "dogs.json") - dogs = [{"id": i, "name": "Cleo {}".format(i), "age": i + 3} for i in range(1, 21)] + dogs = [{"id": i, "name": f"Cleo {i}", "age": i + 3} for i in range(1, 21)] with open(json_path, "w") as fp: fp.write(json.dumps(dogs)) result = CliRunner().invoke( @@ -108,13 +110,13 @@ def test_insert_multiple_with_primary_key(db_path, tmpdir): assert result.exit_code == 0 db = Database(db_path) assert dogs == list(db.query("select * from dogs order by id")) - assert ["id"] == db["dogs"].pks + assert ["id"] == db.table("dogs").pks def test_insert_multiple_with_compound_primary_key(db_path, tmpdir): json_path = str(tmpdir / "dogs.json") dogs = [ - {"breed": "mixed", "id": i, "name": "Cleo {}".format(i), "age": i + 3} + {"breed": "mixed", "id": i, "name": f"Cleo {i}", "age": i + 3} for i in range(1, 21) ] with open(json_path, "w") as fp: @@ -125,7 +127,7 @@ def test_insert_multiple_with_compound_primary_key(db_path, tmpdir): assert result.exit_code == 0 db = Database(db_path) assert dogs == list(db.query("select * from dogs order by breed, id")) - assert {"breed", "id"} == set(db["dogs"].pks) + assert {"breed", "id"} == set(db.table("dogs").pks) assert ( 'CREATE TABLE "dogs" (\n' ' "breed" TEXT,\n' @@ -134,14 +136,13 @@ def test_insert_multiple_with_compound_primary_key(db_path, tmpdir): ' "age" INTEGER,\n' ' PRIMARY KEY ("id", "breed")\n' ")" - ) == db["dogs"].schema + ) == db.table("dogs").schema def test_insert_not_null_default(db_path, tmpdir): json_path = str(tmpdir / "dogs.json") dogs = [ - {"id": i, "name": "Cleo {}".format(i), "age": i + 3, "score": 10} - for i in range(1, 21) + {"id": i, "name": f"Cleo {i}", "age": i + 3, "score": 10} for i in range(1, 21) ] with open(json_path, "w") as fp: fp.write(json.dumps(dogs)) @@ -159,7 +160,7 @@ def test_insert_not_null_default(db_path, tmpdir): ' "name" TEXT NOT NULL,\n' " \"age\" INTEGER NOT NULL DEFAULT '1',\n" " \"score\" INTEGER DEFAULT '5'\n)" - ) == db["dogs"].schema + ) == db.table("dogs").schema def test_insert_binary_base64(db_path): @@ -190,7 +191,7 @@ def test_insert_newline_delimited(db_path): def test_insert_ignore(db_path, tmpdir): db = Database(db_path) - db["dogs"].insert({"id": 1, "name": "Cleo"}, pk="id") + db.table("dogs").insert({"id": 1, "name": "Cleo"}, pk="id") json_path = str(tmpdir / "dogs.json") with open(json_path, "w") as fp: fp.write(json.dumps([{"id": 1, "name": "Bailey"}])) @@ -231,7 +232,7 @@ def test_insert_csv_tsv(content, options, db_path, tmpdir): catch_exceptions=False, ) assert result.exit_code == 0 - assert [{"foo": "1", "bar": "2", "baz": "cat,dog"}] == list(db["data"].rows) + assert [{"foo": "1", "bar": "2", "baz": "cat,dog"}] == list(db.table("data").rows) @pytest.mark.parametrize("empty_null", (True, False)) @@ -247,7 +248,7 @@ def test_insert_csv_empty_null(db_path, empty_null): ) assert result.exit_code == 0 db = Database(db_path) - assert [r for r in db["data"].rows] == [ + assert [r for r in db.table("data").rows] == [ {"foo": "1", "bar": None if empty_null else "", "baz": "cat"} ] @@ -301,7 +302,7 @@ def test_insert_replace(db_path, tmpdir): test_insert_multiple_with_primary_key(db_path, tmpdir) json_path = str(tmpdir / "insert-replace.json") db = Database(db_path) - assert db["dogs"].count == 20 + assert db.table("dogs").count == 20 insert_replace_dogs = [ {"id": 1, "name": "Insert replaced 1", "age": 4}, {"id": 2, "name": "Insert replaced 2", "age": 4}, @@ -313,7 +314,7 @@ def test_insert_replace(db_path, tmpdir): cli.cli, ["insert", db_path, "dogs", json_path, "--pk", "id", "--replace"] ) assert result.exit_code == 0, result.output - assert db["dogs"].count == 21 + assert db.table("dogs").count == 21 assert ( list(db.query("select * from dogs where id in (1, 2, 21) order by id")) == insert_replace_dogs @@ -376,7 +377,7 @@ def test_insert_alter(db_path, tmpdir): assert result.exit_code == 0, result.output # Soundness check the database itself db = Database(db_path) - assert {"foo": str, "n": int, "baz": int} == db["from_json_nl"].columns_dict + assert {"foo": str, "n": int, "baz": int} == db.table("from_json_nl").columns_dict assert [ {"foo": "bar", "n": 1, "baz": None}, {"foo": "baz", "n": 2, "baz": None}, @@ -386,8 +387,8 @@ def test_insert_alter(db_path, tmpdir): def test_insert_analyze(db_path): db = Database(db_path) - db["rows"].insert({"foo": "x", "n": 3}) - db["rows"].create_index(["n"]) + db.table("rows").insert({"foo": "x", "n": 3}) + db.table("rows").create_index(["n"]) assert "sqlite_stat1" not in db.table_names() result = CliRunner().invoke( cli.cli, @@ -576,18 +577,19 @@ def test_insert_streaming_batch_size_1(db_path): stdin=subprocess.PIPE, stdout=sys.stdout, ) + assert proc.stdin is not None proc.stdin.write(b'{"name": "Azi"}\n') proc.stdin.flush() def try_until(expected): tries = 0 while True: - rows = list(Database(db_path)["rows"].rows) + rows = list(Database(db_path).table("rows").rows) if rows == expected: return tries += 1 if tries > 10: - assert False, "Expected {}, got {}".format(expected, rows) + assert False, f"Expected {expected}, got {rows}" time.sleep(tries * 0.1) try_until([{"name": "Azi"}]) @@ -614,13 +616,13 @@ def test_insert_csv_headers_only(tmpdir): assert result.exit_code == 0 # Table should not exist since there were no data rows db = Database(db_path) - assert not db["data"].exists() + assert not db.table("data").exists() def test_insert_into_view_errors(tmpdir): db_path = str(tmpdir / "test.db") db = Database(db_path) - db["t"].insert({"id": 1}) + db.table("t").insert({"id": 1}) db.create_view("v", "select * from t") db.close() result = CliRunner().invoke( @@ -636,7 +638,7 @@ def test_insert_csv_detect_types_leaves_existing_table_alone(db_path): # table would rewrite its column types and corrupt data such as # TEXT zip codes with leading zeros db = Database(db_path) - db["places"].insert({"name": "Boston", "zip": "01234"}) + db.table("places").insert({"name": "Boston", "zip": "01234"}) result = CliRunner().invoke( cli.cli, ["insert", db_path, "places", "-", "--csv"], @@ -644,8 +646,8 @@ def test_insert_csv_detect_types_leaves_existing_table_alone(db_path): input="name,zip\nSF,94107", ) assert result.exit_code == 0, result.output - assert db["places"].columns_dict["zip"] is str - assert list(db["places"].rows) == [ + assert db.table("places").columns_dict["zip"] is str + assert list(db.table("places").rows) == [ {"name": "Boston", "zip": "01234"}, {"name": "SF", "zip": "94107"}, ] @@ -661,12 +663,59 @@ def test_insert_csv_detect_types_new_table(db_path): ) assert result.exit_code == 0, result.output db = Database(db_path) - assert db["data"].columns_dict == {"name": str, "age": int, "weight": float} + assert db.table("data").columns_dict == {"name": str, "age": int, "weight": float} + + +@pytest.mark.parametrize( + "command,extra_args,input_text,expected_row", + ( + ( + "insert", + [], + "zipcode,score\n01234,9.5\n", + {"zipcode": "01234", "score": 9.5}, + ), + ( + "upsert", + ["--pk", "id"], + "id,zipcode,score\n1,01234,9.5\n", + {"id": 1, "zipcode": "01234", "score": 9.5}, + ), + ), +) +def test_insert_upsert_csv_type_overrides_detected_types( + db_path, command, extra_args, input_text, expected_row +): + result = CliRunner().invoke( + cli.cli, + [ + command, + db_path, + "places", + "-", + "--csv", + ] + + extra_args + + [ + "--type", + "zipcode", + "text", + ], + catch_exceptions=False, + input=input_text, + ) + assert result.exit_code == 0, result.output + db = Database(db_path) + expected_columns = {"zipcode": str, "score": float} + if command == "upsert": + expected_columns = {"id": int, **expected_columns} + assert db.table("places").columns_dict == expected_columns + assert list(db.table("places").rows) == [expected_row] def test_upsert_csv_detect_types_leaves_existing_table_alone(db_path): db = Database(db_path) - db["places"].insert({"id": 1, "name": "Boston", "zip": "01234"}, pk="id") + db.table("places").insert({"id": 1, "name": "Boston", "zip": "01234"}, pk="id") result = CliRunner().invoke( cli.cli, ["upsert", db_path, "places", "-", "--csv", "--pk", "id"], @@ -674,15 +723,15 @@ def test_upsert_csv_detect_types_leaves_existing_table_alone(db_path): input="id,name,zip\n2,SF,94107", ) assert result.exit_code == 0, result.output - assert db["places"].columns_dict["zip"] is str - assert db["places"].get(1)["zip"] == "01234" + assert db.table("places").columns_dict["zip"] is str + assert db.table("places").get(1)["zip"] == "01234" def test_insert_invalid_pk_clean_error(db_path): # An invalid --pk against an existing table should be a clean CLI # error, not a raw InvalidColumns traceback db = Database(db_path) - db["t"].insert({"a": 1}) + db.table("t").insert({"a": 1}) result = CliRunner().invoke( cli.cli, ["insert", db_path, "t", "-", "--pk", "badcol"], @@ -691,3 +740,155 @@ def test_insert_invalid_pk_clean_error(db_path): assert result.exit_code == 1 assert result.exception is None or isinstance(result.exception, SystemExit) assert result.output.startswith("Error: Invalid primary key column") + + +# --code tests, see https://github.com/simonw/sqlite-utils/issues/684 +CODE_ROWS_FUNCTION = """ +def rows(): + yield {"id": 1, "name": "Cleo"} + yield {"id": 2, "name": "Suna"} +""" + +CODE_ROWS_ITERABLE = """ +rows = [ + {"id": 1, "name": "Cleo"}, + {"id": 2, "name": "Suna"}, +] +""" + + +@pytest.mark.parametrize("code", (CODE_ROWS_FUNCTION, CODE_ROWS_ITERABLE)) +def test_insert_code(tmpdir, code): + db_path = str(tmpdir / "dogs.db") + result = CliRunner().invoke( + cli.cli, + ["insert", db_path, "creatures", "--code", code, "--pk", "id"], + ) + assert result.exit_code == 0, result.output + db = Database(db_path) + assert db.table("creatures").pks == ["id"] + assert list(db.table("creatures").rows) == [ + {"id": 1, "name": "Cleo"}, + {"id": 2, "name": "Suna"}, + ] + + +def test_insert_code_from_file(tmpdir): + db_path = str(tmpdir / "dogs.db") + code_path = str(tmpdir / "gen.py") + with open(code_path, "w") as fp: + fp.write(CODE_ROWS_FUNCTION) + result = CliRunner().invoke( + cli.cli, + ["insert", db_path, "creatures", "--code", code_path], + ) + assert result.exit_code == 0, result.output + assert list(Database(db_path).table("creatures").rows) == [ + {"id": 1, "name": "Cleo"}, + {"id": 2, "name": "Suna"}, + ] + + +def test_upsert_code(tmpdir): + db_path = str(tmpdir / "dogs.db") + db = Database(db_path) + db.table("creatures").insert_all( + [{"id": 1, "name": "old"}, {"id": 2, "name": "Suna"}], pk="id" + ) + result = CliRunner().invoke( + cli.cli, + ["upsert", db_path, "creatures", "--code", CODE_ROWS_FUNCTION, "--pk", "id"], + ) + assert result.exit_code == 0, result.output + assert list(db.table("creatures").rows) == [ + {"id": 1, "name": "Cleo"}, + {"id": 2, "name": "Suna"}, + ] + + +def test_insert_code_requires_file_or_code(tmpdir): + db_path = str(tmpdir / "dogs.db") + result = CliRunner().invoke(cli.cli, ["insert", db_path, "creatures"]) + assert result.exit_code == 1 + assert "Provide either a FILE argument or --code" in result.output + + +def test_insert_code_mutually_exclusive_with_file(tmpdir): + db_path = str(tmpdir / "dogs.db") + result = CliRunner().invoke( + cli.cli, + ["insert", db_path, "creatures", "-", "--code", CODE_ROWS_FUNCTION], + input="{}", + ) + assert result.exit_code == 1 + assert "--code cannot be used with a FILE argument" in result.output + + +def test_insert_code_rejects_input_format_options(tmpdir): + db_path = str(tmpdir / "dogs.db") + result = CliRunner().invoke( + cli.cli, + ["insert", db_path, "creatures", "--code", CODE_ROWS_FUNCTION, "--csv"], + ) + assert result.exit_code == 1 + assert "--code cannot be used with input format options" in result.output + + +def test_insert_code_missing_rows(tmpdir): + db_path = str(tmpdir / "dogs.db") + result = CliRunner().invoke( + cli.cli, + ["insert", db_path, "creatures", "--code", "x = 1"], + ) + assert result.exit_code == 1 + assert "must define a 'rows' function or iterable" in result.output + + +def test_insert_code_single_dict(tmpdir): + db_path = str(tmpdir / "dogs.db") + result = CliRunner().invoke( + cli.cli, + [ + "insert", + db_path, + "creatures", + "--code", + 'rows = {"id": 1, "name": "Cleo"}', + "--pk", + "id", + ], + ) + assert result.exit_code == 0, result.output + assert list(Database(db_path).table("creatures").rows) == [ + {"id": 1, "name": "Cleo"} + ] + + +def test_insert_code_not_iterable(tmpdir): + db_path = str(tmpdir / "dogs.db") + result = CliRunner().invoke( + cli.cli, + ["insert", db_path, "creatures", "--code", "rows = 5"], + ) + assert result.exit_code == 1 + assert "must define a 'rows' function or iterable" in result.output + + +def test_insert_code_syntax_error(tmpdir): + db_path = str(tmpdir / "dogs.db") + result = CliRunner().invoke( + cli.cli, + ["insert", db_path, "creatures", "--code", "def rows(:"], + ) + assert result.exit_code == 1 + assert "Error in --code" in result.output + + +def test_insert_code_file_not_found(tmpdir): + db_path = str(tmpdir / "dogs.db") + result = CliRunner().invoke( + cli.cli, + ["insert", db_path, "creatures", "--code", "missing.py"], + ) + assert result.exit_code == 1 + assert "File not found: missing.py" in result.output diff --git a/tests/test_cli_memory.py b/tests/test_cli_memory.py index 2ed4aaa..445f50b 100644 --- a/tests/test_cli_memory.py +++ b/tests/test_cli_memory.py @@ -1,5 +1,6 @@ -import click import json + +import click import pytest from click.testing import CliRunner @@ -28,7 +29,7 @@ def test_memory_csv(tmpdir, sql_from, use_stdin): fp.write(content) result = CliRunner().invoke( cli.cli, - ["memory", csv_path, "select * from {}".format(sql_from), "--nl"], + ["memory", csv_path, f"select * from {sql_from}", "--nl"], input=input, ) assert result.exit_code == 0 @@ -53,7 +54,7 @@ def test_memory_tsv(tmpdir, use_stdin): sql_from = "chickens" result = CliRunner().invoke( cli.cli, - ["memory", path, "select * from {}".format(sql_from)], + ["memory", path, f"select * from {sql_from}"], input=input, ) assert result.exit_code == 0, result.output @@ -79,7 +80,7 @@ def test_memory_json(tmpdir, use_stdin): sql_from = "chickens" result = CliRunner().invoke( cli.cli, - ["memory", path, "select * from {}".format(sql_from)], + ["memory", path, f"select * from {sql_from}"], input=input, ) assert result.exit_code == 0, result.output @@ -105,7 +106,7 @@ def test_memory_json_nl(tmpdir, use_stdin): sql_from = "chickens" result = CliRunner().invoke( cli.cli, - ["memory", path, "select * from {}".format(sql_from)], + ["memory", path, f"select * from {sql_from}"], input=input, ) assert result.exit_code == 0, result.output @@ -135,7 +136,7 @@ def test_memory_csv_encoding(tmpdir, use_stdin): CliRunner() .invoke( cli.cli, - ["memory", csv_path, "select * from {}".format(sql_from), "--nl"], + ["memory", csv_path, f"select * from {sql_from}", "--nl"], input=input, ) .exit_code @@ -227,7 +228,7 @@ def test_memory_save(tmpdir, extra_args): ) assert result.exit_code == 0 db = Database(save_to) - assert list(db["stdin"].rows) == [ + assert list(db.table("stdin").rows) == [ {"id": 1, "name": "Cleo"}, {"id": 2, "name": "Bants"}, ] diff --git a/tests/test_cli_migrate.py b/tests/test_cli_migrate.py index 0f29e36..7439887 100644 --- a/tests/test_cli_migrate.py +++ b/tests/test_cli_migrate.py @@ -1,7 +1,8 @@ import pathlib -from click.testing import CliRunner import pytest +from click.testing import CliRunner + import sqlite_utils import sqlite_utils.cli @@ -12,11 +13,11 @@ m = Migrations("hello") @m() def foo(db): - db["foo"].insert({"hello": "world"}) + db.table("foo").insert({"hello": "world"}) @m() def bar(db): - db["bar"].insert({"hello": "world"}) + db.table("bar").insert({"hello": "world"}) """ @@ -41,21 +42,21 @@ creatures = Migrations("creatures") @creatures() def create_table(db): - db["creatures"].insert({"name": "Cleo"}) + db.table("creatures").insert({"name": "Cleo"}) @creatures() def add_weight(db): - db["creature_weights"].insert({"weight": 4.2}) + db.table("creature_weights").insert({"weight": 4.2}) sales = Migrations("sales") @sales() def create_table(db): - db["sales"].insert({"id": 1}) + db.table("sales").insert({"id": 1}) @sales() def add_weight(db): - db["sales_weights"].insert({"weight": 10}) + db.table("sales_weights").insert({"weight": 10}) """, "utf-8", ) @@ -98,10 +99,10 @@ def test_basic(two_migrations, arg): assert " Pending:\n (none)" in list_output db = sqlite_utils.Database(db_path) - assert db["foo"].exists() - assert db["bar"].exists() - assert db["_sqlite_migrations"].exists() - rows = list(db["_sqlite_migrations"].rows) + assert db.table("foo").exists() + assert db.table("bar").exists() + assert db.table("_sqlite_migrations").exists() + rows = list(db.table("_sqlite_migrations").rows) assert len(rows) == 2 assert rows[0]["name"] == "foo" assert rows[1]["name"] == "bar" @@ -112,13 +113,13 @@ def test_list_same_migration_names_in_different_sets(capsys): @applied(name="foo") def applied_foo(db): - db["applied"].insert({"hello": "world"}) + db.table("applied").insert({"hello": "world"}) pending = sqlite_utils.Migrations("pending") @pending(name="foo") def pending_foo(db): - db["pending"].insert({"hello": "world"}) + db.table("pending").insert({"hello": "world"}) db = sqlite_utils.Database(memory=True) applied.apply(db) @@ -143,7 +144,7 @@ m = Migrations("hello") @m() def foo(db): - db["dogs"].insert({"id": 1, "name": "Cleo"}) + db.table("dogs").insert({"id": 1, "name": "Cleo"}) """, "utf-8", ) @@ -183,9 +184,9 @@ Schema after: new_migration = """ @m() def bar(db): - db["dogs"].add_column("age", int) - db["dogs"].add_column("weight", float) - db["dogs"].transform() + db.table("dogs").add_column("age", int) + db.table("dogs").add_column("weight", float) + db.table("dogs").transform() """ migrations_py.write_text(migrations_py.read_text("utf-8") + new_migration) @@ -223,8 +224,8 @@ def test_stop_before(two_migrations): ) assert result.exit_code == 0 db = sqlite_utils.Database(db_path) - assert db["foo"].exists() - assert not db["bar"].exists() + assert db.table("foo").exists() + assert not db.table("bar").exists() def test_stop_before_multiple_sets_unqualified(two_migrations): @@ -238,7 +239,7 @@ m = Migrations("hello2") @m() def foo(db): - db["foo"].insert({"hello": "world"}) + db.table("foo").insert({"hello": "world"}) """, "utf-8", ) @@ -256,7 +257,7 @@ def foo(db): assert result.exit_code == 0, result.output db = sqlite_utils.Database(db_path) assert db.table_names() == ["_sqlite_migrations"] - assert list(db["_sqlite_migrations"].rows) == [] + assert list(db.table("_sqlite_migrations").rows) == [] def test_stop_before_qualified_only_affects_named_set(two_sets_same_migration_name): @@ -274,10 +275,10 @@ def test_stop_before_qualified_only_affects_named_set(two_sets_same_migration_na ) assert result.exit_code == 0, result.output db = sqlite_utils.Database(db_path) - assert db["creatures"].exists() - assert not db["creature_weights"].exists() - assert db["sales"].exists() - assert db["sales_weights"].exists() + assert db.table("creatures").exists() + assert not db.table("creature_weights").exists() + assert db.table("sales").exists() + assert db.table("sales_weights").exists() def test_stop_before_multiple_qualified(two_sets_same_migration_name): @@ -297,10 +298,10 @@ def test_stop_before_multiple_qualified(two_sets_same_migration_name): ) assert result.exit_code == 0, result.output db = sqlite_utils.Database(db_path) - assert db["creatures"].exists() - assert not db["creature_weights"].exists() - assert db["sales"].exists() - assert not db["sales_weights"].exists() + assert db.table("creatures").exists() + assert not db.table("creature_weights").exists() + assert db.table("sales").exists() + assert not db.table("sales_weights").exists() LEGACY_MIGRATIONS = """ @@ -330,7 +331,7 @@ class LegacyMigrations: return fn def ensure_migrations_table(self, db): - db[self.migrations_table].create( + db.table(self.migrations_table).create( {"migration_set": str, "name": str, "applied_at": str}, pk=("migration_set", "name"), if_not_exists=True, @@ -340,7 +341,7 @@ class LegacyMigrations: self.ensure_migrations_table(db) return [ _Applied(row["name"], row["applied_at"]) - for row in db[self.migrations_table].rows_where( + for row in db.table(self.migrations_table).rows_where( "migration_set = ?", [self.name] ) ] @@ -354,7 +355,7 @@ class LegacyMigrations: if migration.name == stop_before: return migration.fn(db) - db[self.migrations_table].insert( + db.table(self.migrations_table).insert( { "migration_set": self.name, "name": migration.name, @@ -368,11 +369,11 @@ legacy = LegacyMigrations("legacy_set") @legacy def first(db): - db["first"].insert({"hello": "world"}) + db.table("first").insert({"hello": "world"}) @legacy def second(db): - db["second"].insert({"hello": "world"}) + db.table("second").insert({"hello": "world"}) """ @@ -445,11 +446,11 @@ def test_list_does_not_upgrade_legacy_migrations_table(two_migrations): path, _ = two_migrations db_path = str(path / "test.db") db = sqlite_utils.Database(db_path) - db["_sqlite_migrations"].create( + db.table("_sqlite_migrations").create( {"migration_set": str, "name": str, "applied_at": str}, pk=("migration_set", "name"), ) - db["_sqlite_migrations"].insert( + db.table("_sqlite_migrations").insert( {"migration_set": "hello", "name": "foo", "applied_at": "x"} ) db.close() @@ -461,7 +462,7 @@ def test_list_does_not_upgrade_legacy_migrations_table(two_migrations): assert "foo - x" in result.output # --list must not perform the one-way legacy schema upgrade db2 = sqlite_utils.Database(db_path) - assert db2["_sqlite_migrations"].pks == ["migration_set", "name"] + assert db2.table("_sqlite_migrations").pks == ["migration_set", "name"] db2.close() @@ -484,7 +485,7 @@ def test_stop_before_applied_migration_errors(two_migrations): assert result.exit_code != 0 assert "already been applied" in result.output db = sqlite_utils.Database(db_path) - assert not db["bar"].exists() + assert not db.table("bar").exists() def test_list_with_legacy_class_is_read_only(tmpdir): @@ -495,7 +496,7 @@ def test_list_with_legacy_class_is_read_only(tmpdir): (path / "migrations.py").write_text(LEGACY_MIGRATIONS, "utf-8") db_path = str(path / "test.db") db = sqlite_utils.Database(db_path) - db["existing"].insert({"id": 1}) + db.table("existing").insert({"id": 1}) db.close() result = CliRunner().invoke( sqlite_utils.cli.cli, ["migrate", db_path, str(path), "--list"] diff --git a/tests/test_column_affinity.py b/tests/test_column_affinity.py index fb8f340..2d7846e 100644 --- a/tests/test_column_affinity.py +++ b/tests/test_column_affinity.py @@ -1,4 +1,6 @@ import pytest + +from sqlite_utils import ANY from sqlite_utils.utils import column_affinity EXAMPLES = [ @@ -25,6 +27,8 @@ EXAMPLES = [ ("DOUBLE", float), ("DOUBLE PRECISION", float), ("FLOAT", float), + ("ANY", ANY), + ("any", ANY), # Numeric, treated as float: ("NUMERIC", float), ("DECIMAL(10,5)", float), @@ -41,5 +45,5 @@ def test_column_affinity(column_def, expected_type): @pytest.mark.parametrize("column_def,expected_type", EXAMPLES) def test_columns_dict(fresh_db, column_def, expected_type): - fresh_db.execute("create table foo (col {})".format(column_def)) - assert {"col": expected_type} == fresh_db["foo"].columns_dict + fresh_db.execute(f"create table foo (col {column_def})") + assert {"col": expected_type} == fresh_db.table("foo").columns_dict diff --git a/tests/test_column_casing.py b/tests/test_column_casing.py index ce11345..b3f03c9 100644 --- a/tests/test_column_casing.py +++ b/tests/test_column_casing.py @@ -13,14 +13,14 @@ from sqlite_utils.db import ForeignKey def test_insert_populates_last_pk_case_insensitively(fresh_db): - books = fresh_db["books"] + books = fresh_db.table("books") books.create({"Id": int, "Title": str}, pk="Id") books.insert({"Id": 1, "Title": "One"}, pk="id") assert books.last_pk == 1 def test_insert_populates_last_pk_compound_pk_case_insensitively(fresh_db): - books = fresh_db["books"] + books = fresh_db.table("books") books.create({"Author": str, "Position": int, "Title": str}) books.insert( {"Author": "Sue", "Position": 1, "Title": "One"}, pk=("author", "position") @@ -31,7 +31,7 @@ def test_insert_populates_last_pk_compound_pk_case_insensitively(fresh_db): @pytest.mark.parametrize("use_old_upsert", (False, True)) def test_upsert_pk_case_differs_from_schema(use_old_upsert): db = Database(memory=True, use_old_upsert=use_old_upsert) - books = db["books"] + books = db.table("books") books.create({"Id": int, "Title": str}, pk="Id") books.insert({"Id": 1, "Title": "One"}) books.upsert({"id": 1, "title": "Won"}, pk="id") @@ -43,7 +43,7 @@ def test_upsert_pk_case_differs_from_schema(use_old_upsert): def test_upsert_record_key_case_differs_from_pk(use_old_upsert): # all_columns comes from the record keys, pk= from the caller db = Database(memory=True, use_old_upsert=use_old_upsert) - books = db["books"] + books = db.table("books") books.create({"Id": int, "Title": str}, pk="Id") books.upsert({"ID": 1, "Title": "One"}, pk="id") assert list(books.rows) == [{"Id": 1, "Title": "One"}] @@ -52,7 +52,7 @@ def test_upsert_record_key_case_differs_from_pk(use_old_upsert): def test_upsert_inferred_pk_case_differs_from_record_keys(fresh_db): # pk is inferred from the existing schema as "Id", records use "id" - books = fresh_db["books"] + books = fresh_db.table("books") books.create({"Id": int, "Title": str}, pk="Id") books.upsert({"id": 1, "title": "One"}) assert list(books.rows) == [{"Id": 1, "Title": "One"}] @@ -60,7 +60,7 @@ def test_upsert_inferred_pk_case_differs_from_record_keys(fresh_db): def test_upsert_list_mode_pk_case_insensitive(fresh_db): - books = fresh_db["books"] + books = fresh_db.table("books") books.create({"Id": int, "Title": str}, pk="Id") books.upsert_all([["id", "title"], [1, "One"]], pk="Id") assert list(books.rows) == [{"Id": 1, "Title": "One"}] @@ -68,84 +68,84 @@ def test_upsert_list_mode_pk_case_insensitive(fresh_db): def test_lookup_pk_case_insensitive(fresh_db): - fresh_db["species"].create({"ID": int, "Name": str}, pk="ID") - fresh_db["species"].insert({"ID": 5, "Name": "Palm"}) - fresh_db["species"].create_index(["Name"], unique=True) - assert fresh_db["species"].lookup({"Name": "Palm"}, pk="id") == 5 + fresh_db.table("species").create({"ID": int, "Name": str}, pk="ID") + fresh_db.table("species").insert({"ID": 5, "Name": "Palm"}) + fresh_db.table("species").create_index(["Name"], unique=True) + assert fresh_db.table("species").lookup({"Name": "Palm"}, pk="id") == 5 def test_lookup_does_not_create_redundant_index(fresh_db): - fresh_db["species"].create({"id": int, "Name": str}, pk="id") - fresh_db["species"].create_index(["Name"], unique=True) - fresh_db["species"].lookup({"name": "Palm"}) - assert len(fresh_db["species"].indexes) == 1 + fresh_db.table("species").create({"id": int, "Name": str}, pk="id") + fresh_db.table("species").create_index(["Name"], unique=True) + fresh_db.table("species").lookup({"name": "Palm"}) + assert len(fresh_db.table("species").indexes) == 1 def test_create_table_transform_same_columns_different_case(fresh_db): - fresh_db["t"].create({"Name": str, "Age": int}) - fresh_db["t"].insert({"Name": "Cleo", "Age": 5}) + fresh_db.table("t").create({"Name": str, "Age": int}) + fresh_db.table("t").insert({"Name": "Cleo", "Age": 5}) fresh_db.create_table("t", {"name": str, "age": int}, transform=True) # Schema casing is preserved - SQLite considers these the same columns - assert fresh_db["t"].columns_dict == {"Name": str, "Age": int} - assert list(fresh_db["t"].rows) == [{"Name": "Cleo", "Age": 5}] + assert fresh_db.table("t").columns_dict == {"Name": str, "Age": int} + assert list(fresh_db.table("t").rows) == [{"Name": "Cleo", "Age": 5}] def test_create_table_transform_case_insensitive_with_changes(fresh_db): - fresh_db["t"].create({"Name": str, "Age": int}) + fresh_db.table("t").create({"Name": str, "Age": int}) fresh_db.create_table("t", {"name": str, "age": str, "size": int}, transform=True) # age changed type, size added, Name untouched - assert fresh_db["t"].columns_dict == {"Name": str, "Age": str, "size": int} + assert fresh_db.table("t").columns_dict == {"Name": str, "Age": str, "size": int} def test_transform_types_case_insensitive(fresh_db): - fresh_db["t"].create({"Name": str, "Age": str}) - fresh_db["t"].transform(types={"age": int}) - assert fresh_db["t"].columns_dict == {"Name": str, "Age": int} + fresh_db.table("t").create({"Name": str, "Age": str}) + fresh_db.table("t").transform(types={"age": int}) + assert fresh_db.table("t").columns_dict == {"Name": str, "Age": int} def test_transform_rename_case_insensitive(fresh_db): - fresh_db["t"].create({"Name": str}) - fresh_db["t"].transform(rename={"name": "title"}) - assert fresh_db["t"].columns_dict == {"title": str} + fresh_db.table("t").create({"Name": str}) + fresh_db.table("t").transform(rename={"name": "title"}) + assert fresh_db.table("t").columns_dict == {"title": str} def test_transform_drop_case_insensitive(fresh_db): - fresh_db["t"].create({"Name": str, "Age": int}) - fresh_db["t"].transform(drop=["name"]) - assert fresh_db["t"].columns_dict == {"Age": int} + fresh_db.table("t").create({"Name": str, "Age": int}) + fresh_db.table("t").transform(drop=["name"]) + assert fresh_db.table("t").columns_dict == {"Age": int} def test_transform_not_null_and_defaults_case_insensitive(fresh_db): - fresh_db["t"].create({"Name": str, "Age": int}) - fresh_db["t"].transform(not_null={"name"}, defaults={"age": 3}) - columns = {c.name: c for c in fresh_db["t"].columns} + fresh_db.table("t").create({"Name": str, "Age": int}) + fresh_db.table("t").transform(not_null={"name"}, defaults={"age": 3}) + columns = {c.name: c for c in fresh_db.table("t").columns} assert columns["Name"].notnull - assert fresh_db["t"].default_values == {"Age": 3} + assert fresh_db.table("t").default_values == {"Age": 3} def test_transform_pk_case_insensitive(fresh_db): - fresh_db["t"].create({"Id": int, "Name": str}) - fresh_db["t"].transform(pk="id") - assert fresh_db["t"].pks == ["Id"] - assert fresh_db["t"].columns_dict == {"Id": int, "Name": str} + fresh_db.table("t").create({"Id": int, "Name": str}) + fresh_db.table("t").transform(pk="id") + assert fresh_db.table("t").pks == ["Id"] + assert fresh_db.table("t").columns_dict == {"Id": int, "Name": str} def test_transform_drop_foreign_keys_case_insensitive(fresh_db): - fresh_db["parent"].create({"Id": int}, pk="Id") - fresh_db["child"].create( + fresh_db.table("parent").create({"Id": int}, pk="Id") + fresh_db.table("child").create( {"id": int, "Parent_ID": int}, pk="id", foreign_keys=[("Parent_ID", "parent", "Id")], ) - fresh_db["child"].transform(drop_foreign_keys=["parent_id"]) - assert fresh_db["child"].foreign_keys == [] + fresh_db.table("child").transform(drop_foreign_keys=["parent_id"]) + assert fresh_db.table("child").foreign_keys == [] def test_add_foreign_key_case_insensitive(fresh_db): - fresh_db["parent"].create({"Id": int}, pk="Id") - fresh_db["child"].create({"id": int, "Parent_ID": int}, pk="id") - fresh_db["child"].add_foreign_key("parent_id", "parent", "id") - fks = fresh_db["child"].foreign_keys + fresh_db.table("parent").create({"Id": int}, pk="Id") + fresh_db.table("child").create({"id": int, "Parent_ID": int}, pk="id") + fresh_db.table("child").add_foreign_key("parent_id", "parent", "id") + fks = fresh_db.table("child").foreign_keys assert len(fks) == 1 # The foreign key should use the schema casing of the columns assert fks[0].column == "Parent_ID" @@ -153,79 +153,83 @@ def test_add_foreign_key_case_insensitive(fresh_db): def test_add_foreign_keys_case_insensitive(fresh_db): - fresh_db["parent"].create({"Id": int}, pk="Id") - fresh_db["child"].create({"id": int, "Parent_ID": int}, pk="id") + fresh_db.table("parent").create({"Id": int}, pk="Id") + fresh_db.table("child").create({"id": int, "Parent_ID": int}, pk="id") fresh_db.add_foreign_keys([("child", "parent_id", "parent", "id")]) - fks = fresh_db["child"].foreign_keys + fks = fresh_db.table("child").foreign_keys assert len(fks) == 1 assert fks[0].column == "Parent_ID" assert fks[0].other_column == "Id" def test_add_foreign_key_detects_existing_case_insensitively(fresh_db): - fresh_db["parent"].create({"Id": int}, pk="Id") - fresh_db["child"].create( + fresh_db.table("parent").create({"Id": int}, pk="Id") + fresh_db.table("child").create( {"id": int, "Parent_ID": int}, pk="id", foreign_keys=[("Parent_ID", "parent", "Id")], ) # ignore=True should treat this as already existing, not add a duplicate - fresh_db["child"].add_foreign_key("parent_id", "parent", "id", ignore=True) - assert len(fresh_db["child"].foreign_keys) == 1 + fresh_db.table("child").add_foreign_key("parent_id", "parent", "id", ignore=True) + assert len(fresh_db.table("child").foreign_keys) == 1 def test_add_column_fk_col_case_insensitive(fresh_db): - fresh_db["parent"].create({"Id": int}, pk="Id") - fresh_db["child"].create({"id": int}, pk="id") - fresh_db["child"].add_column("parent_id", int, fk="parent", fk_col="id") - fks = fresh_db["child"].foreign_keys + fresh_db.table("parent").create({"Id": int}, pk="Id") + fresh_db.table("child").create({"id": int}, pk="id") + fresh_db.table("child").add_column("parent_id", int, fk="parent", fk_col="id") + fks = fresh_db.table("child").foreign_keys assert len(fks) == 1 assert fks[0].other_column == "Id" def test_extract_case_insensitive(fresh_db): - fresh_db["trees"].insert({"id": 1, "Species": "Palm"}, pk="id") - fresh_db["trees"].extract("species") - assert fresh_db["trees"].columns_dict == {"id": int, "Species_id": int} - assert list(fresh_db["Species"].rows) == [{"id": 1, "Species": "Palm"}] + fresh_db.table("trees").insert({"id": 1, "Species": "Palm"}, pk="id") + fresh_db.table("trees").extract("species") + assert fresh_db.table("trees").columns_dict == {"id": int, "Species_id": int} + assert list(fresh_db.table("Species").rows) == [{"id": 1, "Species": "Palm"}] def test_convert_multi_case_insensitive(fresh_db): - fresh_db["t"].insert({"id": 1, "Name": "Cleo"}, pk="id") - fresh_db["t"].convert("name", lambda v: {"upper": v.upper()}, multi=True) - assert list(fresh_db["t"].rows) == [{"id": 1, "Name": "Cleo", "upper": "CLEO"}] + fresh_db.table("t").insert({"id": 1, "Name": "Cleo"}, pk="id") + fresh_db.table("t").convert("name", lambda v: {"upper": v.upper()}, multi=True) + assert list(fresh_db.table("t").rows) == [ + {"id": 1, "Name": "Cleo", "upper": "CLEO"} + ] def test_convert_output_case_insensitive(fresh_db): - fresh_db["t"].insert({"id": 1, "Name": "Cleo", "Upper": None}, pk="id") - fresh_db["t"].convert("name", lambda v: v.upper(), output="upper") - assert list(fresh_db["t"].rows) == [{"id": 1, "Name": "Cleo", "Upper": "CLEO"}] + fresh_db.table("t").insert({"id": 1, "Name": "Cleo", "Upper": None}, pk="id") + fresh_db.table("t").convert("name", lambda v: v.upper(), output="upper") + assert list(fresh_db.table("t").rows) == [ + {"id": 1, "Name": "Cleo", "Upper": "CLEO"} + ] def test_create_table_sql_pk_case_insensitive(fresh_db): - fresh_db["t"].create({"Id": int, "Name": str}, pk="id") + fresh_db.table("t").create({"Id": int, "Name": str}, pk="id") # Should not have created an extra lowercase "id" column - assert fresh_db["t"].columns_dict == {"Id": int, "Name": str} - assert fresh_db["t"].pks == ["Id"] + assert fresh_db.table("t").columns_dict == {"Id": int, "Name": str} + assert fresh_db.table("t").pks == ["Id"] def test_create_table_not_null_and_defaults_case_insensitive(fresh_db): - fresh_db["t"].create( + fresh_db.table("t").create( {"Name": str, "Age": int}, not_null={"name"}, defaults={"age": 1} ) - columns = {c.name: c for c in fresh_db["t"].columns} + columns = {c.name: c for c in fresh_db.table("t").columns} assert columns["Name"].notnull - assert fresh_db["t"].default_values == {"Age": 1} + assert fresh_db.table("t").default_values == {"Age": 1} def test_create_table_foreign_keys_case_insensitive(fresh_db): - fresh_db["parent"].create({"Id": int}, pk="Id") - fresh_db["child"].create( + fresh_db.table("parent").create({"Id": int}, pk="Id") + fresh_db.table("child").create( {"id": int, "Parent_ID": int}, pk="id", foreign_keys=[("parent_id", "parent", "id")], ) - fks = fresh_db["child"].foreign_keys + fks = fresh_db.table("child").foreign_keys assert fks == [ ForeignKey( table="child", column="Parent_ID", other_table="parent", other_column="Id" diff --git a/tests/test_constructor.py b/tests/test_constructor.py index 7714f26..412b66c 100644 --- a/tests/test_constructor.py +++ b/tests/test_constructor.py @@ -1,8 +1,10 @@ +import sys + +import pytest + from sqlite_utils import Database from sqlite_utils.db import TransactionError from sqlite_utils.utils import sqlite3 -import pytest -import sys def test_recursive_triggers(): @@ -18,8 +20,8 @@ def test_recursive_triggers_off(): def test_memory_name(): db1 = Database(memory_name="shared") db2 = Database(memory_name="shared") - db1["dogs"].insert({"name": "Cleo"}) - assert list(db2["dogs"].rows) == [{"name": "Cleo"}] + db1.table("dogs").insert({"name": "Cleo"}) + assert list(db2.table("dogs").rows) == [{"name": "Cleo"}] def test_sqlite_version(): @@ -34,7 +36,7 @@ def test_sqlite_version(): def test_database_context_manager(tmpdir): path = str(tmpdir / "test.db") with Database(path) as db: - db["t"].insert({"id": 1}) + db.table("t").insert({"id": 1}) # Raw writes commit automatically too db.execute("insert into t (id) values (2)") # An explicitly opened transaction left uncommitted on purpose: @@ -45,7 +47,7 @@ def test_database_context_manager(tmpdir): db.execute("select 1") # ... and the open explicit transaction was rolled back, not committed db2 = Database(path) - assert [r["id"] for r in db2["t"].rows] == [1, 2] + assert [r["id"] for r in db2.table("t").rows] == [1, 2] db2.close() @@ -81,9 +83,34 @@ def test_autocommit_connections_are_rejected(tmpdir, autocommit): ) def test_legacy_transaction_control_connection_is_accepted(tmpdir): conn = sqlite3.connect( - str(tmpdir / "test.db"), autocommit=sqlite3.LEGACY_TRANSACTION_CONTROL + str(tmpdir / "test.db"), + autocommit=sqlite3.LEGACY_TRANSACTION_CONTROL, # type: ignore[arg-type] ) db = Database(conn) - db["t"].insert({"id": 1}, pk="id") - assert [r["id"] for r in db["t"].rows] == [1] + db.table("t").insert({"id": 1}, pk="id") + assert [r["id"] for r in db.table("t").rows] == [1] db.close() + + +def test_memory_attribute_for_memory_true(): + db = Database(memory=True) + assert db.memory is True + assert db.memory_name is None + + +def test_memory_attribute_for_memory_name(): + db = Database(memory_name="shared_attr") + assert db.memory is True + assert db.memory_name == "shared_attr" + + +def test_memory_attribute_for_memory_string_path(): + db = Database(":memory:") + assert db.memory is True + assert db.memory_name is None + + +def test_memory_attribute_for_file_path(tmpdir): + db = Database(str(tmpdir / "file.db")) + assert db.memory is False + assert db.memory_name is None diff --git a/tests/test_conversions.py b/tests/test_conversions.py index d70f5c8..bb58df4 100644 --- a/tests/test_conversions.py +++ b/tests/test_conversions.py @@ -1,17 +1,17 @@ def test_insert_conversion(fresh_db): - table = fresh_db["table"] + table = fresh_db.table("table") table.insert({"foo": "bar"}, conversions={"foo": "upper(?)"}) assert [{"foo": "BAR"}] == list(table.rows) def test_insert_all_conversion(fresh_db): - table = fresh_db["table"] + table = fresh_db.table("table") table.insert_all([{"foo": "bar"}], conversions={"foo": "upper(?)"}) assert [{"foo": "BAR"}] == list(table.rows) def test_upsert_conversion(fresh_db): - table = fresh_db["table"] + table = fresh_db.table("table") table.upsert({"id": 1, "foo": "bar"}, pk="id", conversions={"foo": "upper(?)"}) assert [{"id": 1, "foo": "BAR"}] == list(table.rows) table.upsert( @@ -21,7 +21,7 @@ def test_upsert_conversion(fresh_db): def test_upsert_all_conversion(fresh_db): - table = fresh_db["table"] + table = fresh_db.table("table") table.upsert_all( [{"id": 1, "foo": "bar"}], pk="id", conversions={"foo": "upper(?)"} ) @@ -29,7 +29,7 @@ def test_upsert_all_conversion(fresh_db): def test_update_conversion(fresh_db): - table = fresh_db["table"] + table = fresh_db.table("table") table.insert({"id": 5, "foo": "bar"}, pk="id") table.update(5, {"foo": "baz"}, conversions={"foo": "upper(?)"}) assert [{"id": 5, "foo": "BAZ"}] == list(table.rows) diff --git a/tests/test_convert.py b/tests/test_convert.py index ea3fd96..1f9e9ed 100644 --- a/tests/test_convert.py +++ b/tests/test_convert.py @@ -1,6 +1,7 @@ -from sqlite_utils.db import BadMultiValues import pytest +from sqlite_utils.db import BadMultiValues + @pytest.mark.parametrize( "columns,fn,expected", @@ -26,7 +27,7 @@ import pytest ), ) def test_convert(fresh_db, columns, fn, expected): - table = fresh_db["table"] + table = fresh_db.table("table") table.insert({"title": "Mixed Case", "abstract": "Abstract"}) table.convert(columns, fn) assert list(table.rows) == [expected] @@ -36,7 +37,7 @@ def test_convert(fresh_db, columns, fn, expected): "where,where_args", (("id > 1", None), ("id > :id", {"id": 1}), ("id > ?", [1])) ) def test_convert_where(fresh_db, where, where_args): - table = fresh_db["table"] + table = fresh_db.table("table") table.insert_all( [ {"id": 1, "title": "One"}, @@ -52,7 +53,7 @@ def test_convert_where(fresh_db, where, where_args): def test_convert_handles_falsey_values(fresh_db): # Falsey values like 0 should be converted (issue #527) - table = fresh_db["table"] + table = fresh_db.table("table") table.insert_all([{"x": 0}, {"x": 1}]) assert table.get(1)["x"] == 0 assert table.get(2)["x"] == 1 @@ -69,14 +70,14 @@ def test_convert_handles_falsey_values(fresh_db): ), ) def test_convert_output(fresh_db, drop, expected): - table = fresh_db["table"] + table = fresh_db.table("table") table.insert({"title": "Mixed Case"}) table.convert("title", lambda v: v.upper(), output="other", drop=drop) assert list(table.rows) == [expected] def test_convert_output_multiple_column_error(fresh_db): - table = fresh_db["table"] + table = fresh_db.table("table") with pytest.raises(ValueError) as excinfo: table.convert(["title", "other"], lambda v: v, output="out") assert "output= can only be used with a single column" in str(excinfo.value) @@ -90,14 +91,14 @@ def test_convert_output_multiple_column_error(fresh_db): ), ) def test_convert_output_type(fresh_db, type, expected): - table = fresh_db["table"] + table = fresh_db.table("table") table.insert({"number": "123"}) table.convert("number", lambda v: v, output="other", output_type=type, drop=True) assert list(table.rows) == [expected] def test_convert_multi(fresh_db): - table = fresh_db["table"] + table = fresh_db.table("table") table.insert({"title": "Mixed Case"}) table.convert( "title", @@ -122,7 +123,7 @@ def test_convert_multi(fresh_db): def test_convert_multi_where(fresh_db): - table = fresh_db["table"] + table = fresh_db.table("table") table.insert_all( [ {"id": 1, "title": "One"}, @@ -144,14 +145,14 @@ def test_convert_multi_where(fresh_db): def test_convert_multi_exception(fresh_db): - table = fresh_db["table"] + table = fresh_db.table("table") table.insert({"title": "Mixed Case"}) with pytest.raises(BadMultiValues): table.convert("title", lambda v: v.upper(), multi=True) def test_convert_repeated(fresh_db): - table = fresh_db["table"] + table = fresh_db.table("table") col = "num" table.insert({col: 1}) table.convert(col, lambda x: x * 2) diff --git a/tests/test_create.py b/tests/test_create.py index 42fa1c4..b738df9 100644 --- a/tests/test_create.py +++ b/tests/test_create.py @@ -1,26 +1,29 @@ -from sqlite_utils.db import ( - Index, - Database, - DescIndex, - AlterError, - InvalidColumns, - NoObviousTable, - OperationalError, - ForeignKey, - Table, - View, - NoTable, - NoView, -) -from sqlite_utils.utils import hash_record, sqlite3 import collections import datetime import decimal import json import pathlib -import pytest import uuid +import pytest + +from sqlite_utils import ANY +from sqlite_utils.db import ( + AlterError, + Database, + DescIndex, + ForeignKey, + Index, + InvalidColumns, + NoObviousTable, + NoTable, + NoView, + OperationalError, + Table, + View, +) +from sqlite_utils.utils import hash_record, sqlite3 + try: import pandas as pd # type: ignore except ImportError: @@ -78,9 +81,10 @@ def test_create_table_compound_primary_key(fresh_db): @pytest.mark.parametrize("pk", ("id", ["id"])) def test_create_table_with_single_primary_key(fresh_db, pk): - fresh_db["foo"].insert({"id": 1}, pk=pk) + fresh_db.table("foo").insert({"id": 1}, pk=pk) assert ( - fresh_db["foo"].schema == 'CREATE TABLE "foo" (\n "id" INTEGER PRIMARY KEY\n)' + fresh_db.table("foo").schema + == 'CREATE TABLE "foo" (\n "id" INTEGER PRIMARY KEY\n)' ) @@ -157,7 +161,7 @@ def test_create_table_with_not_null(fresh_db): ), ) def test_create_table_from_example(fresh_db, example, expected_columns): - people_table = fresh_db["people"] + people_table = fresh_db.table("people") assert people_table.last_rowid is None assert people_table.last_pk is None people_table.insert(example) @@ -165,13 +169,13 @@ def test_create_table_from_example(fresh_db, example, expected_columns): assert people_table.last_pk == 1 assert ["people"] == fresh_db.table_names() assert expected_columns == [ - {"name": col.name, "type": col.type} for col in fresh_db["people"].columns + {"name": col.name, "type": col.type} for col in fresh_db.table("people").columns ] def test_create_table_from_example_with_compound_primary_keys(fresh_db): record = {"name": "Zhang", "group": "staff", "employee_id": 2} - table = fresh_db["people"].insert(record, pk=("group", "employee_id")) + table = fresh_db.table("people").insert(record, pk=("group", "employee_id")) assert ["group", "employee_id"] == table.pks assert record == table.get(("staff", 2)) @@ -182,7 +186,7 @@ def test_create_table_from_example_with_compound_primary_keys(fresh_db): @pytest.mark.parametrize("use_old_upsert", (False, True)) def test_create_table_with_custom_columns(method_name, use_old_upsert): db = Database(memory=True, use_old_upsert=use_old_upsert) - table = db["dogs"] + table = db.table("dogs") method = getattr(table, method_name) record = {"id": 1, "name": "Cleo", "age": "5"} if method_name.endswith("_all"): @@ -216,14 +220,16 @@ def test_create_table_column_order(fresh_db, use_table_factory): if use_table_factory: fresh_db.table("table", column_order=column_order).insert(row) else: - fresh_db["table"].insert(row, column_order=column_order) + fresh_db.table("table").insert(row, column_order=column_order) assert [ {"name": "abc", "type": "TEXT"}, {"name": "ccc", "type": "TEXT"}, {"name": "zzz", "type": "TEXT"}, {"name": "bbb", "type": "TEXT"}, {"name": "aaa", "type": "TEXT"}, - ] == [{"name": col.name, "type": col.type} for col in fresh_db["table"].columns] + ] == [ + {"name": col.name, "type": col.type} for col in fresh_db.table("table").columns + ] @pytest.mark.parametrize( @@ -259,8 +265,8 @@ def test_create_table_works_for_m2m_with_only_foreign_keys( fresh_db.table("one", pk="id").insert({"id": 1}) fresh_db.table("two", pk="id").insert({"id": 1}) else: - fresh_db["one"].insert({"id": 1}, pk="id") - fresh_db["two"].insert({"id": 1}, pk="id") + fresh_db.table("one").insert({"id": 1}, pk="id") + fresh_db.table("two").insert({"id": 1}, pk="id") row = {"one_id": 1, "two_id": 1} @@ -268,7 +274,7 @@ def test_create_table_works_for_m2m_with_only_foreign_keys( if use_table_factory: fresh_db.table("m2m", foreign_keys=foreign_key_specification).insert(row) else: - fresh_db["m2m"].insert(row, foreign_keys=foreign_key_specification) + fresh_db.table("m2m").insert(row, foreign_keys=foreign_key_specification) if expected_exception: with pytest.raises(expected_exception): @@ -279,7 +285,7 @@ def test_create_table_works_for_m2m_with_only_foreign_keys( assert [ {"name": "one_id", "type": "INTEGER"}, {"name": "two_id", "type": "INTEGER"}, - ] == [{"name": col.name, "type": col.type} for col in fresh_db["m2m"].columns] + ] == [{"name": col.name, "type": col.type} for col in fresh_db.table("m2m").columns] assert sorted( [ {"column": "one_id", "other_table": "one", "other_column": "id"}, @@ -293,7 +299,7 @@ def test_create_table_works_for_m2m_with_only_foreign_keys( "other_table": fk.other_table, "other_column": fk.other_column, } - for fk in fresh_db["m2m"].foreign_keys + for fk in fresh_db.table("m2m").foreign_keys ], key=lambda s: repr(s), ) @@ -320,7 +326,7 @@ def test_self_referential_foreign_key(fresh_db): def test_create_error_if_invalid_foreign_keys(fresh_db): with pytest.raises(AlterError): - fresh_db["one"].insert( + fresh_db.table("one").insert( {"id": 1, "ref_id": 3}, pk="id", foreign_keys=(("ref_id", "bad_table", "bad_column"),), @@ -329,7 +335,7 @@ def test_create_error_if_invalid_foreign_keys(fresh_db): def test_create_error_if_invalid_self_referential_foreign_keys(fresh_db): with pytest.raises(AlterError) as ex: - fresh_db["one"].insert( + fresh_db.table("one").insert( {"id": 1, "ref_id": 3}, pk="id", foreign_keys=(("ref_id", "one", "bad_column"),), @@ -395,41 +401,43 @@ def test_create_error_if_invalid_self_referential_foreign_keys(fresh_db): ) def test_add_column(fresh_db, col_name, col_type, not_null_default, expected_schema): fresh_db.create_table("dogs", {"name": str}) - assert fresh_db["dogs"].schema == 'CREATE TABLE "dogs" (\n "name" TEXT\n)' - fresh_db["dogs"].add_column(col_name, col_type, not_null_default=not_null_default) - assert fresh_db["dogs"].schema == expected_schema + assert fresh_db.table("dogs").schema == 'CREATE TABLE "dogs" (\n "name" TEXT\n)' + fresh_db.table("dogs").add_column( + col_name, col_type, not_null_default=not_null_default + ) + assert fresh_db.table("dogs").schema == expected_schema def test_add_foreign_key(fresh_db): - fresh_db["authors"].insert_all( + fresh_db.table("authors").insert_all( [{"id": 1, "name": "Sally"}, {"id": 2, "name": "Asheesh"}], pk="id" ) - fresh_db["books"].insert_all( + fresh_db.table("books").insert_all( [ {"title": "Hedgehogs of the world", "author_id": 1}, {"title": "How to train your wolf", "author_id": 2}, ] ) - assert [] == fresh_db["books"].foreign_keys - t = fresh_db["books"].add_foreign_key("author_id", "authors", "id") + assert [] == fresh_db.table("books").foreign_keys + t = fresh_db.table("books").add_foreign_key("author_id", "authors", "id") # Ensure it returned self: assert isinstance(t, Table) and t.name == "books" assert [ ForeignKey( table="books", column="author_id", other_table="authors", other_column="id" ) - ] == fresh_db["books"].foreign_keys + ] == fresh_db.table("books").foreign_keys def test_add_foreign_key_if_column_contains_space(fresh_db): - fresh_db["authors"].insert_all([{"id": 1, "name": "Sally"}], pk="id") - fresh_db["books"].insert_all( + fresh_db.table("authors").insert_all([{"id": 1, "name": "Sally"}], pk="id") + fresh_db.table("books").insert_all( [ {"title": "Hedgehogs of the world", "author id": 1}, ] ) - fresh_db["books"].add_foreign_key("author id", "authors", "id") - assert fresh_db["books"].foreign_keys == [ + fresh_db.table("books").add_foreign_key("author id", "authors", "id") + assert fresh_db.table("books").foreign_keys == [ ForeignKey( table="books", column="author id", other_table="authors", other_column="id" ) @@ -437,44 +445,44 @@ def test_add_foreign_key_if_column_contains_space(fresh_db): def test_add_foreign_key_error_if_column_does_not_exist(fresh_db): - fresh_db["books"].insert( + fresh_db.table("books").insert( {"id": 1, "title": "Hedgehogs of the world", "author_id": 1} ) with pytest.raises(AlterError): - fresh_db["books"].add_foreign_key("author2_id", "books", "id") + fresh_db.table("books").add_foreign_key("author2_id", "books", "id") def test_add_foreign_key_error_if_other_table_does_not_exist(fresh_db): - fresh_db["books"].insert({"title": "Hedgehogs of the world", "author_id": 1}) + fresh_db.table("books").insert({"title": "Hedgehogs of the world", "author_id": 1}) with pytest.raises(AlterError): - fresh_db["books"].add_foreign_key("author_id", "authors", "id") + fresh_db.table("books").add_foreign_key("author_id", "authors", "id") def test_add_foreign_key_error_if_already_exists(fresh_db): - fresh_db["books"].insert({"title": "Hedgehogs of the world", "author_id": 1}) - fresh_db["authors"].insert({"id": 1, "name": "Sally"}, pk="id") - fresh_db["books"].add_foreign_key("author_id", "authors", "id") + fresh_db.table("books").insert({"title": "Hedgehogs of the world", "author_id": 1}) + fresh_db.table("authors").insert({"id": 1, "name": "Sally"}, pk="id") + fresh_db.table("books").add_foreign_key("author_id", "authors", "id") with pytest.raises(AlterError) as ex: - fresh_db["books"].add_foreign_key("author_id", "authors", "id") + fresh_db.table("books").add_foreign_key("author_id", "authors", "id") assert "Foreign key already exists for author_id => authors.id" == ex.value.args[0] def test_add_foreign_key_no_error_if_exists_and_ignore_true(fresh_db): - fresh_db["books"].insert({"title": "Hedgehogs of the world", "author_id": 1}) - fresh_db["authors"].insert({"id": 1, "name": "Sally"}, pk="id") - fresh_db["books"].add_foreign_key("author_id", "authors", "id") - fresh_db["books"].add_foreign_key("author_id", "authors", "id", ignore=True) + fresh_db.table("books").insert({"title": "Hedgehogs of the world", "author_id": 1}) + fresh_db.table("authors").insert({"id": 1, "name": "Sally"}, pk="id") + fresh_db.table("books").add_foreign_key("author_id", "authors", "id") + fresh_db.table("books").add_foreign_key("author_id", "authors", "id", ignore=True) def test_add_foreign_keys(fresh_db): - fresh_db["authors"].insert_all( + fresh_db.table("authors").insert_all( [{"id": 1, "name": "Sally"}, {"id": 2, "name": "Asheesh"}], pk="id" ) - fresh_db["categories"].insert_all([{"id": 1, "name": "Wildlife"}], pk="id") - fresh_db["books"].insert_all( + fresh_db.table("categories").insert_all([{"id": 1, "name": "Wildlife"}], pk="id") + fresh_db.table("books").insert_all( [{"title": "Hedgehogs of the world", "author_id": 1, "category_id": 1}] ) - assert [] == fresh_db["books"].foreign_keys + assert [] == fresh_db.table("books").foreign_keys fresh_db.add_foreign_keys( [ ("books", "author_id", "authors", "id"), @@ -491,14 +499,14 @@ def test_add_foreign_keys(fresh_db): other_table="categories", other_column="id", ), - ] == sorted(fresh_db["books"].foreign_keys) + ] == sorted(fresh_db.table("books").foreign_keys) def test_add_column_foreign_key(fresh_db): fresh_db.create_table("dogs", {"name": str}) fresh_db.create_table("breeds", {"name": str}) - fresh_db["dogs"].add_column("breed_id", fk="breeds") - assert fresh_db["dogs"].schema == ( + fresh_db.table("dogs").add_column("breed_id", fk="breeds") + assert fresh_db.table("dogs").schema == ( 'CREATE TABLE "dogs" (\n' ' "name" TEXT,\n' ' "breed_id" INTEGER REFERENCES "breeds"("rowid")\n' @@ -506,8 +514,8 @@ def test_add_column_foreign_key(fresh_db): ) # And again with an explicit primary key column fresh_db.create_table("subbreeds", {"name": str, "primkey": str}, pk="primkey") - fresh_db["dogs"].add_column("subbreed_id", fk="subbreeds") - assert fresh_db["dogs"].schema == ( + fresh_db.table("dogs").add_column("subbreed_id", fk="subbreeds") + assert fresh_db.table("dogs").schema == ( 'CREATE TABLE "dogs" (\n' ' "name" TEXT,\n' ' "breed_id" INTEGER REFERENCES "breeds"("rowid"),\n' @@ -519,9 +527,9 @@ def test_add_column_foreign_key(fresh_db): def test_add_foreign_key_guess_table(fresh_db): fresh_db.create_table("dogs", {"name": str}) fresh_db.create_table("breeds", {"name": str, "id": int}, pk="id") - fresh_db["dogs"].add_column("breed_id", int) - fresh_db["dogs"].add_foreign_key("breed_id") - assert fresh_db["dogs"].schema == ( + fresh_db.table("dogs").add_column("breed_id", int) + fresh_db.table("dogs").add_foreign_key("breed_id") + assert fresh_db.table("dogs").schema == ( 'CREATE TABLE "dogs" (\n' ' "name" TEXT,\n' ' "breed_id" INTEGER REFERENCES "breeds"("id")\n' @@ -531,21 +539,23 @@ def test_add_foreign_key_guess_table(fresh_db): def test_index_foreign_keys(fresh_db): test_add_foreign_key_guess_table(fresh_db) - assert [] == fresh_db["dogs"].indexes + assert [] == fresh_db.table("dogs").indexes fresh_db.index_foreign_keys() - assert [["breed_id"]] == [i.columns for i in fresh_db["dogs"].indexes] + assert [["breed_id"]] == [i.columns for i in fresh_db.table("dogs").indexes] # Calling it a second time should do nothing fresh_db.index_foreign_keys() - assert [["breed_id"]] == [i.columns for i in fresh_db["dogs"].indexes] + assert [["breed_id"]] == [i.columns for i in fresh_db.table("dogs").indexes] def test_index_foreign_keys_if_index_name_is_already_used(fresh_db): # https://github.com/simonw/sqlite-utils/issues/335 test_add_foreign_key_guess_table(fresh_db) # Add index with a name that will conflict with index_foreign_keys() - fresh_db["dogs"].create_index(["name"], index_name="idx_dogs_breed_id") + fresh_db.table("dogs").create_index(["name"], index_name="idx_dogs_breed_id") fresh_db.index_foreign_keys() - assert {(idx.name, tuple(idx.columns)) for idx in fresh_db["dogs"].indexes} == { + assert { + (idx.name, tuple(idx.columns)) for idx in fresh_db.table("dogs").indexes + } == { ("idx_dogs_breed_id_2", ("breed_id",)), ("idx_dogs_breed_id", ("name",)), } @@ -569,7 +579,7 @@ def test_index_foreign_keys_if_index_name_is_already_used(fresh_db): def test_insert_row_alter_table( fresh_db, extra_data, expected_new_columns, use_table_factory ): - table = fresh_db["books"] + table = fresh_db.table("books") table.insert({"title": "Hedgehogs of the world", "author_id": 1}) assert [ {"name": "title", "type": "TEXT"}, @@ -580,7 +590,7 @@ def test_insert_row_alter_table( if use_table_factory: fresh_db.table("books", alter=True).insert(record) else: - fresh_db["books"].insert(record, alter=True) + fresh_db.table("books").insert(record, alter=True) assert [ {"name": "title", "type": "TEXT"}, {"name": "author_id", "type": "INTEGER"}, @@ -590,7 +600,7 @@ def test_insert_row_alter_table( def test_add_missing_columns_case_insensitive(fresh_db): - table = fresh_db["foo"] + table = fresh_db.table("foo") table.insert({"id": 1, "name": "Cleo"}, pk="id") table.add_missing_columns([{"Name": ".", "age": 4}]) assert ( @@ -616,7 +626,7 @@ def test_insert_replace_rows_alter_table(fresh_db, use_table_factory): table.insert(first_row) table.insert_all(next_rows, replace=True) else: - table = fresh_db["books"] + table = fresh_db.table("books") table.insert(first_row, pk="id") table.insert_all(next_rows, alter=True, replace=True) assert { @@ -662,8 +672,8 @@ def test_insert_all_with_extra_columns_in_later_chunks(fresh_db): {"record": "Record 3"}, {"record": "Record 4", "extra": 1}, ] - fresh_db["t"].insert_all(chunk, batch_size=2, alter=True) - assert list(fresh_db["t"].rows) == [ + fresh_db.table("t").insert_all(chunk, batch_size=2, alter=True) + assert list(fresh_db.table("t").rows) == [ {"record": "Record 1", "extra": None}, {"record": "Record 2", "extra": None}, {"record": "Record 3", "extra": None}, @@ -673,7 +683,7 @@ def test_insert_all_with_extra_columns_in_later_chunks(fresh_db): def test_bulk_insert_more_than_999_values(fresh_db): "Inserting 100 items with 11 columns should work" - fresh_db["big"].insert_all( + fresh_db.table("big").insert_all( ( { "id": i + 1, @@ -692,19 +702,19 @@ def test_bulk_insert_more_than_999_values(fresh_db): ), pk="id", ) - assert fresh_db["big"].count == 100 + assert fresh_db.table("big").count == 100 @pytest.mark.parametrize( "num_columns,should_error", ((900, False), (999, False), (1000, True)) ) def test_error_if_more_than_999_columns(fresh_db, num_columns, should_error): - record = dict([("c{}".format(i), i) for i in range(num_columns)]) + record = {f"c{i}": i for i in range(num_columns)} if should_error: with pytest.raises(ValueError): - fresh_db["big"].insert(record) + fresh_db.table("big").insert(record) else: - fresh_db["big"].insert(record) + fresh_db.table("big").insert(record) def test_columns_not_in_first_record_should_not_cause_batch_to_be_too_large(fresh_db): @@ -718,17 +728,11 @@ def test_columns_not_in_first_record_should_not_cause_batch_to_be_too_large(fres records = [ {"c0": "first record"}, # one column in first record -> batch size = 999 # fill out the batch with 99 records with enough columns to exceed THRESHOLD - *[ - dict([("c{}".format(i), j) for i in range(extra_columns)]) - for j in range(batch_size - 1) - ], + *[{f"c{i}": j for i in range(extra_columns)} for j in range(batch_size - 1)], ] - try: - fresh_db["too_many_columns"].insert_all( - records, alter=True, batch_size=batch_size - ) - except sqlite3.OperationalError: - raise + fresh_db.table("too_many_columns").insert_all( + records, alter=True, batch_size=batch_size + ) @pytest.mark.parametrize( @@ -773,7 +777,7 @@ def test_columns_not_in_first_record_should_not_cause_batch_to_be_too_large(fres ), ) def test_create_index(fresh_db, columns, index_name, expected_index): - dogs = fresh_db["dogs"] + dogs = fresh_db.table("dogs") dogs.insert({"name": "Cleo", "twitter": "cleopaws", "age": 3, "is good dog": True}) assert [] == dogs.indexes dogs.create_index(columns, index_name) @@ -781,7 +785,7 @@ def test_create_index(fresh_db, columns, index_name, expected_index): def test_create_index_unique(fresh_db): - dogs = fresh_db["dogs"] + dogs = fresh_db.table("dogs") dogs.insert({"name": "Cleo", "twitter": "cleopaws", "age": 3, "is_good_dog": True}) assert [] == dogs.indexes dogs.create_index(["name"], unique=True) @@ -799,7 +803,7 @@ def test_create_index_unique(fresh_db): def test_create_index_if_not_exists(fresh_db): - dogs = fresh_db["dogs"] + dogs = fresh_db.table("dogs") dogs.insert({"name": "Cleo", "twitter": "cleopaws", "age": 3, "is_good_dog": True}) assert [] == dogs.indexes dogs.create_index(["name"]) @@ -809,8 +813,36 @@ def test_create_index_if_not_exists(fresh_db): dogs.create_index(["name"], if_not_exists=True) +def test_drop_index(fresh_db): + dogs = fresh_db.table("dogs") + dogs.insert({"name": "Cleo", "twitter": "cleopaws", "age": 3, "is_good_dog": True}) + dogs.create_index(["name"]) + assert [index.name for index in dogs.indexes] == ["idx_dogs_name"] + dogs.drop_index("idx_dogs_name") + assert dogs.indexes == [] + + +def test_drop_index_ignore(fresh_db): + dogs = fresh_db.table("dogs") + dogs.insert({"name": "Cleo"}) + with pytest.raises(OperationalError, match="No index named idx_dogs_name"): + dogs.drop_index("idx_dogs_name") + dogs.drop_index("idx_dogs_name", ignore=True) + + +def test_drop_index_wrong_table(fresh_db): + dogs = fresh_db.table("dogs") + cats = fresh_db.table("cats") + dogs.insert({"name": "Cleo"}) + cats.insert({"name": "Misty"}) + dogs.create_index(["name"]) + with pytest.raises(OperationalError, match="No index named idx_dogs_name"): + cats.drop_index("idx_dogs_name") + assert [index.name for index in dogs.indexes] == ["idx_dogs_name"] + + def test_create_index_desc(fresh_db): - dogs = fresh_db["dogs"] + dogs = fresh_db.table("dogs") dogs.insert({"name": "Cleo", "twitter": "cleopaws", "age": 3, "is good dog": True}) assert [] == dogs.indexes dogs.create_index([DescIndex("age"), "name"]) @@ -823,7 +855,7 @@ def test_create_index_desc(fresh_db): def test_create_index_find_unique_name(fresh_db): - table = fresh_db["t"] + table = fresh_db.table("t") table.insert({"id": 1}) table.create_index(["id"]) # Without find_unique_name should error @@ -838,12 +870,12 @@ def test_create_index_find_unique_name(fresh_db): def test_create_index_analyze(fresh_db): - dogs = fresh_db["dogs"] + dogs = fresh_db.table("dogs") assert "sqlite_stat1" not in fresh_db.table_names() dogs.insert({"name": "Cleo", "twitter": "cleopaws"}) dogs.create_index(["name"], analyze=True) assert "sqlite_stat1" in fresh_db.table_names() - assert list(fresh_db["sqlite_stat1"].rows) == [ + assert list(fresh_db.table("sqlite_stat1").rows) == [ {"tbl": "dogs", "idx": "idx_dogs_name", "stat": "1 1"} ] @@ -865,14 +897,14 @@ def test_create_index_analyze(fresh_db): ), ) def test_insert_dictionaries_and_lists_as_json(fresh_db, data_structure): - fresh_db["test"].insert({"id": 1, "data": data_structure}, pk="id") + fresh_db.table("test").insert({"id": 1, "data": data_structure}, pk="id") row = fresh_db.execute("select id, data from test").fetchone() assert row[0] == 1 assert data_structure == json.loads(row[1]) def test_insert_list_nested_unicode(fresh_db): - fresh_db["test"].insert( + fresh_db.table("test").insert( {"id": 1, "data": {"key1": {"nested": ["cømplex"]}}}, pk="id" ) row = fresh_db.execute("select id, data from test").fetchone() @@ -881,44 +913,44 @@ def test_insert_list_nested_unicode(fresh_db): def test_insert_uuid(fresh_db): uuid4 = uuid.uuid4() - fresh_db["test"].insert({"uuid": uuid4}) - row = list(fresh_db["test"].rows)[0] + fresh_db.table("test").insert({"uuid": uuid4}) + row = next(iter(fresh_db.table("test").rows)) assert {"uuid"} == row.keys() assert isinstance(row["uuid"], str) assert row["uuid"] == str(uuid4) def test_insert_memoryview(fresh_db): - fresh_db["test"].insert({"data": memoryview(b"hello")}) - row = list(fresh_db["test"].rows)[0] + fresh_db.table("test").insert({"data": memoryview(b"hello")}) + row = next(iter(fresh_db.table("test").rows)) assert {"data"} == row.keys() assert isinstance(row["data"], bytes) assert row["data"] == b"hello" def test_insert_thousands_using_generator(fresh_db): - fresh_db["test"].insert_all( - {"i": i, "word": "word_{}".format(i)} for i in range(10000) + fresh_db.table("test").insert_all( + {"i": i, "word": f"word_{i}"} for i in range(10000) ) assert [{"name": "i", "type": "INTEGER"}, {"name": "word", "type": "TEXT"}] == [ - {"name": col.name, "type": col.type} for col in fresh_db["test"].columns + {"name": col.name, "type": col.type} for col in fresh_db.table("test").columns ] - assert fresh_db["test"].count == 10000 + assert fresh_db.table("test").count == 10000 def test_insert_thousands_raises_exception_with_extra_columns_after_first_100(fresh_db): # https://github.com/simonw/sqlite-utils/issues/139 with pytest.raises(Exception, match="table test has no column named extra"): - fresh_db["test"].insert_all( - [{"i": i, "word": "word_{}".format(i)} for i in range(100)] + fresh_db.table("test").insert_all( + [{"i": i, "word": f"word_{i}"} for i in range(100)] + [{"i": 101, "extra": "This extra column should cause an exception"}], ) def test_insert_thousands_adds_extra_columns_after_first_100_with_alter(fresh_db): # https://github.com/simonw/sqlite-utils/issues/139 - fresh_db["test"].insert_all( - [{"i": i, "word": "word_{}".format(i)} for i in range(100)] + fresh_db.table("test").insert_all( + [{"i": i, "word": f"word_{i}"} for i in range(100)] + [{"i": 101, "extra": "Should trigger ALTER"}], alter=True, ) @@ -930,15 +962,15 @@ def test_insert_thousands_adds_extra_columns_after_first_100_with_alter(fresh_db def test_insert_all_pk_not_in_records_raises(fresh_db, num_rows): # https://github.com/simonw/sqlite-utils/issues/732 fresh_db.conn.execute("CREATE TABLE t (a TEXT, b INT, PRIMARY KEY (a, b))") - rows = [{"a": "x{}".format(i), "b": i} for i in range(num_rows)] + rows = [{"a": f"x{i}", "b": i} for i in range(num_rows)] with pytest.raises(InvalidColumns) as ex: - fresh_db["t"].insert_all(rows, pk="not_a_column") + fresh_db.table("t").insert_all(rows, pk="not_a_column") assert ex.value.args == ( "Invalid primary key column ['not_a_column'] for table t with columns ['a', 'b']", ) - assert fresh_db["t"].count == 0 + assert fresh_db.table("t").count == 0 @pytest.mark.parametrize("num_rows", (1, 2, 3, 10)) @@ -947,23 +979,23 @@ def test_insert_all_pk_not_in_records_alter_raises(fresh_db, num_rows): # known - a pk column that is in neither the table nor the records # still raises fresh_db.conn.execute("CREATE TABLE t (a TEXT, b INT, PRIMARY KEY (a, b))") - rows = [{"a": "x{}".format(i), "b": i} for i in range(num_rows)] + rows = [{"a": f"x{i}", "b": i} for i in range(num_rows)] with pytest.raises(InvalidColumns) as ex: - fresh_db["t"].insert_all(rows, pk="not_a_column", alter=True) + fresh_db.table("t").insert_all(rows, pk="not_a_column", alter=True) assert ex.value.args == ( "Invalid primary key column ['not_a_column'] for table t with columns ['a', 'b']", ) - assert fresh_db["t"].count == 0 + assert fresh_db.table("t").count == 0 def test_insert_pk_in_records_with_alter_adds_column(fresh_db): # 3.x allowed insert(pk=..., alter=True) to add the pk column from the # records - the InvalidColumns check must not fire in that case - fresh_db["t"].insert({"a": 1}) - fresh_db["t"].insert({"id": 5, "a": 2}, pk="id", alter=True) - assert fresh_db["t"].columns_dict.keys() == {"a", "id"} + fresh_db.table("t").insert({"a": 1}) + fresh_db.table("t").insert({"id": 5, "a": 2}, pk="id", alter=True) + assert fresh_db.table("t").columns_dict.keys() == {"a", "id"} assert list(fresh_db.query("select * from t order by a")) == [ {"a": 1, "id": None}, {"a": 2, "id": 5}, @@ -974,42 +1006,132 @@ def test_insert_all_invalid_pk_alter_empty_records_is_noop(fresh_db): # With alter=True the pk check needs record keys, so an empty iterator # returns without error - matching the 3.x no-op for empty inserts fresh_db.conn.execute("CREATE TABLE t (a TEXT)") - fresh_db["t"].insert_all([], pk="not_a_column", alter=True) - assert fresh_db["t"].count == 0 + fresh_db.table("t").insert_all([], pk="not_a_column", alter=True) + assert fresh_db.table("t").count == 0 def test_insert_ignore(fresh_db): - fresh_db["test"].insert({"id": 1, "bar": 2}, pk="id") + fresh_db.table("test").insert({"id": 1, "bar": 2}, pk="id") # Should raise an error if we try this again with pytest.raises(Exception, match="UNIQUE constraint failed"): - fresh_db["test"].insert({"id": 1, "bar": 2}, pk="id") + fresh_db.table("test").insert({"id": 1, "bar": 2}, pk="id") # Using ignore=True should cause our insert to be silently ignored - fresh_db["test"].insert({"id": 1, "bar": 3}, pk="id", ignore=True) + fresh_db.table("test").insert({"id": 1, "bar": 3}, pk="id", ignore=True) # Only one row, and it should be bar=2, not bar=3 rows = list(fresh_db.query("select * from test")) assert rows == [{"id": 1, "bar": 2}] +def test_insert_ignore_reports_existing_row(fresh_db): + # An ignored insert (row already exists) should point last_rowid and + # last_pk at the existing conflicting row - see the Datasette insert API + fresh_db.table("docs").insert({"id": 1, "title": "Exists"}, pk="id") + # Insert a conflicting row with ignore=True and no explicit pk= + table = fresh_db.table("docs").insert({"id": 1, "title": "One"}, ignore=True) + assert table.last_rowid == 1 + assert table.last_pk == 1 + assert list(fresh_db.table("docs").rows_where("rowid = ?", [table.last_rowid])) == [ + {"id": 1, "title": "Exists"} + ] + + +@pytest.mark.parametrize("rowid_alias", ("rowid", "_rowid_", "oid")) +@pytest.mark.parametrize("method", ("upsert", "insert_replace", "insert_ignore")) +def test_pk_rowid_alias_on_rowid_table(fresh_db, rowid_alias, method): + # rowid and its aliases are valid primary keys for a rowid table even + # though they are not listed among the table's columns - see the Datasette + # upsert API against tables without an explicit primary key + fresh_db.table("t").insert({"title": "Hello"}) + assert fresh_db.table("t").pks == ["rowid"] + record = {rowid_alias: 1, "title": "Updated"} + if method == "upsert": + table = fresh_db.table("t").upsert(record, pk=rowid_alias) + elif method == "insert_replace": + table = fresh_db.table("t").insert(record, pk=rowid_alias, replace=True) + else: + table = fresh_db.table("t").insert(record, pk=rowid_alias, ignore=True) + assert table.last_pk == 1 + expected_title = "Hello" if method == "insert_ignore" else "Updated" + assert list(fresh_db.table("t").rows) == [{"title": expected_title}] + + +def test_insert_ignore_reports_existing_row_compound_pk(fresh_db): + # Compound primary key variant of the ignored-insert lookup + fresh_db.table("t").insert_all([{"a": 1, "b": 2, "note": "first"}], pk=("a", "b")) + table = fresh_db.table("t").insert( + {"a": 1, "b": 2, "note": "second"}, pk=("a", "b"), ignore=True + ) + assert table.last_pk == (1, 2) + assert list(fresh_db.table("t").rows_where("rowid = ?", [table.last_rowid])) == [ + {"a": 1, "b": 2, "note": "first"} + ] + + +def test_insert_ignore_reports_existing_row_list_mode(fresh_db): + # List-based iteration variant of the ignored-insert lookup + fresh_db.table("t").insert_all([["id", "title"], [1, "first"]], pk="id") + table = fresh_db.table("t").insert_all( + [["id", "title"], [1, "second"]], pk="id", ignore=True + ) + assert table.last_pk == 1 + assert table.last_rowid == 1 + assert list(fresh_db.table("t").rows) == [{"id": 1, "title": "first"}] + + +def test_insert_ignore_hash_id_reports_pk(fresh_db): + # With hash_id the pk is the computed hash; the original record has no id + # column to look up so last_rowid is left unset + first = fresh_db.table("dogs").insert({"name": "Cleo"}, hash_id="id") + table = fresh_db.table("dogs").insert({"name": "Cleo"}, hash_id="id", ignore=True) + assert table.last_pk == first.last_pk + assert table.last_rowid is None + assert fresh_db.table("dogs").count == 1 + + +def test_insert_ignore_unresolvable_conflict_leaves_pk_unset(fresh_db): + # When the conflict cannot be resolved to a primary key lookup, last_pk and + # last_rowid are left unset rather than reporting a misleading value + + # rowid table with a UNIQUE column and no primary key: no pk to look up + fresh_db.table("u").db.execute("create table u (title text unique)") + fresh_db.table("u").insert({"title": "x"}) + table = fresh_db.table("u").insert({"title": "x"}, ignore=True) + assert table.last_pk is None + assert table.last_rowid is None + assert fresh_db.table("u").count == 1 + + # Conflict on a UNIQUE column other than the primary key: the pk value from + # the record does not match the existing row, so the lookup finds nothing + fresh_db.table("docs").db.execute( + "create table docs (id integer primary key, email text unique)" + ) + fresh_db.table("docs").insert({"id": 1, "email": "a"}, pk="id") + table = fresh_db.table("docs").insert({"id": 2, "email": "a"}, ignore=True) + assert table.last_pk is None + assert table.last_rowid is None + assert fresh_db.table("docs").count == 1 + + def test_insert_ignore_with_pk_after_other_table_insert(fresh_db): # https://github.com/simonw/sqlite-utils/issues/554 user = {"id": "abc", "name": "david"} - fresh_db["users"].insert(user, pk="id") - fresh_db["comments"].insert_all( + fresh_db.table("users").insert(user, pk="id") + fresh_db.table("comments").insert_all( [ {"id": "def", "text": "ok"}, {"id": "ghi", "text": "great"}, ], ) - table = fresh_db["users"].insert(user, pk="id", ignore=True) + table = fresh_db.table("users").insert(user, pk="id", ignore=True) assert table.last_pk == "abc" - assert list(fresh_db["users"].rows) == [user] + assert list(fresh_db.table("users").rows) == [user] def test_insert_hash_id(fresh_db): - dogs = fresh_db["dogs"] + dogs = fresh_db.table("dogs") id = dogs.insert({"name": "Cleo", "twitter": "cleopaws"}, hash_id="id").last_pk assert "f501265970505d9825d8d9f590bfab3519fb20b1" == id assert dogs.count == 1 @@ -1027,8 +1149,8 @@ def test_insert_hash_id_columns(fresh_db, use_table_factory): dogs = fresh_db.table("dogs", hash_id_columns=("name", "twitter")) insert_kwargs = {} else: - dogs = fresh_db["dogs"] - insert_kwargs = dict(hash_id_columns=("name", "twitter")) + dogs = fresh_db.table("dogs") + insert_kwargs = {"hash_id_columns": ("name", "twitter")} id = dogs.insert( {"name": "Cleo", "twitter": "cleopaws", "age": 5}, @@ -1048,26 +1170,27 @@ def test_insert_hash_id_columns(fresh_db, use_table_factory): def test_vacuum(fresh_db): - fresh_db["data"].insert({"foo": "foo", "bar": "bar"}) + fresh_db.table("data").insert({"foo": "foo", "bar": "bar"}) fresh_db.vacuum() def test_works_with_pathlib_path(tmpdir): path = pathlib.Path(tmpdir / "test.db") db = Database(path) - db["demo"].insert_all([{"foo": 1}]) - assert db["demo"].count == 1 + db.table("demo").insert_all([{"foo": 1}]) + assert db.table("demo").count == 1 @pytest.mark.skipif(pd is None, reason="pandas and numpy are not installed") def test_create_table_numpy(fresh_db): + assert pd is not None df = pd.DataFrame({"col 1": range(3), "col 2": range(3)}) - fresh_db["pandas"].insert_all(df.to_dict(orient="records")) + fresh_db.table("pandas").insert_all(df.to_dict(orient="records")) assert [ {"col 1": 0, "col 2": 0}, {"col 1": 1, "col 2": 1}, {"col 1": 2, "col 2": 2}, - ] == list(fresh_db["pandas"].rows) + ] == list(fresh_db.table("pandas").rows) # Now try all the different types df = pd.DataFrame( { @@ -1112,7 +1235,7 @@ def test_create_table_numpy(fresh_db): "float32", "float64", ] == [str(t) for t in df.dtypes] - fresh_db["types"].insert_all(df.to_dict(orient="records")) + fresh_db.table("types").insert_all(df.to_dict(orient="records")) assert [ { "np.float16": 16.5, @@ -1127,7 +1250,7 @@ def test_create_table_numpy(fresh_db): "np.uint64": 64, "np.uint8": 8, } - ] == list(fresh_db["types"].rows) + ] == list(fresh_db.table("types").rows) def test_cannot_provide_both_filename_and_memory(): @@ -1139,31 +1262,31 @@ def test_cannot_provide_both_filename_and_memory(): def test_creates_id_column(fresh_db): last_pk = fresh_db.table("cats", pk="id").insert({"name": "barry"}).last_pk - assert [{"name": "barry", "id": last_pk}] == list(fresh_db["cats"].rows) + assert [{"name": "barry", "id": last_pk}] == list(fresh_db.table("cats").rows) def test_drop(fresh_db): - fresh_db["t"].insert({"foo": 1}) + fresh_db.table("t").insert({"foo": 1}) assert ["t"] == fresh_db.table_names() - assert None is fresh_db["t"].drop() + assert None is fresh_db.table("t").drop() assert [] == fresh_db.table_names() def test_drop_view(fresh_db): fresh_db.create_view("foo_view", "select 1") assert ["foo_view"] == fresh_db.view_names() - assert None is fresh_db["foo_view"].drop() + assert None is fresh_db.view("foo_view").drop() assert [] == fresh_db.view_names() def test_drop_ignore(fresh_db): with pytest.raises(sqlite3.OperationalError): - fresh_db["does_not_exist"].drop() - fresh_db["does_not_exist"].drop(ignore=True) + fresh_db.table("does_not_exist").drop() + fresh_db.table("does_not_exist").drop(ignore=True) # Testing view is harder, we need to create it in order # to get a View object, then drop it twice fresh_db.create_view("foo_view", "select 1") - view = fresh_db["foo_view"] + view = fresh_db.view("foo_view") assert isinstance(view, View) view.drop() with pytest.raises(sqlite3.OperationalError): @@ -1172,16 +1295,16 @@ def test_drop_ignore(fresh_db): def test_insert_all_empty_list(fresh_db): - fresh_db["t"].insert({"foo": 1}) - assert fresh_db["t"].count == 1 - fresh_db["t"].insert_all([]) - assert fresh_db["t"].count == 1 - fresh_db["t"].insert_all([], replace=True) - assert fresh_db["t"].count == 1 + fresh_db.table("t").insert({"foo": 1}) + assert fresh_db.table("t").count == 1 + fresh_db.table("t").insert_all([]) + assert fresh_db.table("t").count == 1 + fresh_db.table("t").insert_all([], replace=True) + assert fresh_db.table("t").count == 1 def test_insert_all_single_column(fresh_db): - table = fresh_db["table"] + table = fresh_db.table("table") table.insert_all([{"name": "Cleo"}], pk="name") assert [{"name": "Cleo"}] == list(table.rows) assert table.pks == ["name"] @@ -1189,31 +1312,33 @@ def test_insert_all_single_column(fresh_db): @pytest.mark.parametrize("method_name", ("insert_all", "upsert_all")) def test_insert_all_analyze(fresh_db, method_name): - table = fresh_db["table"] + table = fresh_db.table("table") table.insert_all([{"id": 1, "name": "Cleo"}], pk="id") assert "sqlite_stat1" not in fresh_db.table_names() table.create_index(["name"], analyze=True) - assert list(fresh_db["sqlite_stat1"].rows) == [ + assert list(fresh_db.table("sqlite_stat1").rows) == [ {"tbl": "table", "idx": "idx_table_name", "stat": "1 1"} ] method = getattr(table, method_name) method([{"id": 2, "name": "Suna"}], pk="id", analyze=True) assert "sqlite_stat1" in fresh_db.table_names() - assert list(fresh_db["sqlite_stat1"].rows) == [ + assert list(fresh_db.table("sqlite_stat1").rows) == [ {"tbl": "table", "idx": "idx_table_name", "stat": "2 1"} ] def test_create_with_a_null_column(fresh_db): record = {"name": "Name", "description": None} - fresh_db["t"].insert(record) - assert [record] == list(fresh_db["t"].rows) + fresh_db.table("t").insert(record) + assert [record] == list(fresh_db.table("t").rows) def test_create_with_nested_bytes(fresh_db): record = {"id": 1, "data": {"foo": b"bytes"}} - fresh_db["t"].insert(record) - assert [{"id": 1, "data": '{"foo": "b\'bytes\'"}'}] == list(fresh_db["t"].rows) + fresh_db.table("t").insert(record) + assert [{"id": 1, "data": '{"foo": "b\'bytes\'"}'}] == list( + fresh_db.table("t").rows + ) @pytest.mark.parametrize( @@ -1242,6 +1367,18 @@ def test_quote(fresh_db, input, expected): {"col": list}, '"col" TEXT', ), + ( + {"col": ANY}, + '"col" ANY', + ), + ( + {"col": "ANY"}, + '"col" ANY', + ), + ( + {"col": "any"}, + '"col" ANY', + ), ), ) def test_create_table_sql(fresh_db, columns, expected_sql_middle): @@ -1251,7 +1388,7 @@ def test_create_table_sql(fresh_db, columns, expected_sql_middle): def test_create(fresh_db): - fresh_db["t"].create( + fresh_db.table("t").create( { "id": int, "text": str, @@ -1264,7 +1401,7 @@ def test_create(fresh_db): not_null=("float", "integer"), defaults={"integer": 0}, ) - assert fresh_db["t"].schema == ( + assert fresh_db.table("t").schema == ( 'CREATE TABLE "t" (\n' ' "id" INTEGER PRIMARY KEY,\n' ' "float" REAL NOT NULL,\n' @@ -1276,37 +1413,37 @@ def test_create(fresh_db): def test_create_if_not_exists(fresh_db): - fresh_db["t"].create({"id": int}) + fresh_db.table("t").create({"id": int}) # This should error with pytest.raises(sqlite3.OperationalError): - fresh_db["t"].create({"id": int}) + fresh_db.table("t").create({"id": int}) # This should not - fresh_db["t"].create({"id": int}, if_not_exists=True) + fresh_db.table("t").create({"id": int}, if_not_exists=True) def test_create_if_no_columns(fresh_db): with pytest.raises(ValueError) as error: - fresh_db["t"].create({}) + fresh_db.table("t").create({}) assert error.value.args[0] == "Tables must have at least one column" def test_create_ignore(fresh_db): - fresh_db["t"].create({"id": int}) + fresh_db.table("t").create({"id": int}) # This should error with pytest.raises(sqlite3.OperationalError): - fresh_db["t"].create({"id": int}) + fresh_db.table("t").create({"id": int}) # This should not - fresh_db["t"].create({"id": int}, ignore=True) + fresh_db.table("t").create({"id": int}, ignore=True) def test_create_replace(fresh_db): - fresh_db["t"].create({"id": int}) + fresh_db.table("t").create({"id": int}) # This should error with pytest.raises(sqlite3.OperationalError): - fresh_db["t"].create({"id": int}) + fresh_db.table("t").create({"id": int}) # This should not - fresh_db["t"].create({"name": str}, replace=True) - assert fresh_db["t"].schema == ('CREATE TABLE "t" (\n' ' "name" TEXT\n' ")") + fresh_db.table("t").create({"name": str}, replace=True) + assert fresh_db.table("t").schema == ('CREATE TABLE "t" (\n' ' "name" TEXT\n' ")") @pytest.mark.parametrize( @@ -1374,23 +1511,43 @@ def test_create_replace(fresh_db): ) def test_create_transform(fresh_db, cols, kwargs, expected_schema, should_transform): fresh_db.create_table("demo", {"id": int, "name": str}, pk="id") - fresh_db["demo"].insert({"id": 1, "name": "Cleo"}) + fresh_db.table("demo").insert({"id": 1, "name": "Cleo"}) traces = [] with fresh_db.tracer(lambda sql, parameters: traces.append((sql, parameters))): - fresh_db["demo"].create(cols, **kwargs, transform=True) + fresh_db.table("demo").create(cols, **kwargs, transform=True) at_least_one_create_table = any(sql.startswith("CREATE TABLE") for sql, _ in traces) assert should_transform == at_least_one_create_table - new_schema = fresh_db["demo"].schema + new_schema = fresh_db.table("demo").schema assert new_schema == expected_schema, repr(new_schema) - assert fresh_db["demo"].count == 1 + assert fresh_db.table("demo").count == 1 + + +def test_create_transform_keyword_literal_defaults_unchanged(fresh_db): + fresh_db.execute( + "create table demo (" + "id integer primary key, " + "enabled integer default TRUE, " + "disabled integer default FALSE, " + "nullable text default NULL" + ")" + ) + traces = [] + with fresh_db.tracer(lambda sql, parameters: traces.append((sql, parameters))): + fresh_db.table("demo").create( + {"id": int, "enabled": int, "disabled": int, "nullable": str}, + pk="id", + defaults={"enabled": True, "disabled": False, "nullable": None}, + transform=True, + ) + assert not any(sql.startswith("CREATE TABLE") for sql, _ in traces) def test_rename_table(fresh_db): - fresh_db["t"].insert({"foo": "bar"}) + fresh_db.table("t").insert({"foo": "bar"}) assert ["t"] == fresh_db.table_names() fresh_db.rename_table("t", "renamed") assert ["renamed"] == fresh_db.table_names() - assert [{"foo": "bar"}] == list(fresh_db["renamed"].rows) + assert [{"foo": "bar"}] == list(fresh_db.table("renamed").rows) # Should error if table does not exist: with pytest.raises(sqlite3.OperationalError): fresh_db.rename_table("does_not_exist", "renamed") @@ -1417,7 +1574,7 @@ def test_database_strict_override(strict): ) @pytest.mark.parametrize("strict", (False, True)) def test_insert_upsert_strict(fresh_db, method_name, strict): - table = fresh_db["t"] + table = fresh_db.table("t") method = getattr(table, method_name) record = {"id": 1} if method_name.endswith("_all"): @@ -1440,11 +1597,38 @@ def test_create_table_strict(fresh_db, strict): @pytest.mark.parametrize("strict", (False, True)) def test_create_strict(fresh_db, strict): - table = fresh_db["t"] + table = fresh_db.table("t") table.create({"id": int}, strict=strict) assert table.strict == strict or not fresh_db.supports_strict +def test_create_strict_with_any(fresh_db): + if not fresh_db.supports_strict: + pytest.skip("SQLite version does not support strict tables") + table = fresh_db.table("items").create( + {"id": int, "data": ANY}, pk="id", strict=True + ) + table.insert_all( + [ + {"id": 1, "data": 42}, + {"id": 2, "data": "000123"}, + {"id": 3, "data": 3.14}, + {"id": 4, "data": b"bytes"}, + {"id": 5, "data": None}, + ] + ) + assert table.columns_dict == {"id": int, "data": ANY} + assert fresh_db.execute( + "select typeof(data), data from items order by id" + ).fetchall() == [ + ("integer", 42), + ("text", "000123"), + ("real", 3.14), + ("blob", b"bytes"), + ("null", None), + ] + + def test_bad_table_and_view_exceptions(fresh_db): fresh_db.table("t").insert({"id": 1}, pk="id") fresh_db.create_view("v", "select * from t") @@ -1465,7 +1649,7 @@ def test_bad_table_and_view_exceptions(fresh_db): def test_pk_persists_after_insert_655(fresh_db): """When pk is passed to insert(), subsequent inserts should use it.""" - table = fresh_db["users"] + table = fresh_db.table("users") table.insert({"id": 1, "name": "Alice"}, pk="id") # Second insert should use pk="id" from _defaults table.insert({"id": 2, "name": "Bob"}) @@ -1476,7 +1660,7 @@ def test_pk_persists_after_insert_655(fresh_db): def test_pk_persists_after_insert_all_655(fresh_db): """When pk is passed to insert_all(), subsequent inserts should use it.""" - table = fresh_db["users"] + table = fresh_db.table("users") table.insert_all([{"id": 1, "name": "Alice"}], pk="id") # Second insert_all should use pk="id" from _defaults table.insert_all([{"id": 2, "name": "Bob"}]) @@ -1486,7 +1670,7 @@ def test_pk_persists_after_insert_all_655(fresh_db): def test_pk_persists_after_create_655(fresh_db): """When pk is passed to create(), it should be stored in _defaults.""" - table = fresh_db["users"] + table = fresh_db.table("users") table.create({"id": int, "name": str}, pk="id") assert table._defaults["pk"] == "id" # Subsequent insert should use the pk @@ -1497,8 +1681,8 @@ def test_pk_persists_after_create_655(fresh_db): def test_foreign_keys_persist_after_create_655(fresh_db): """When foreign_keys is passed to create(), it should be stored in _defaults.""" - fresh_db["authors"].insert({"id": 1, "name": "Alice"}, pk="id") - table = fresh_db["books"] + fresh_db.table("authors").insert({"id": 1, "name": "Alice"}, pk="id") + table = fresh_db.table("books") table.create( {"id": int, "title": str, "author_id": int}, pk="id", @@ -1510,38 +1694,38 @@ def test_foreign_keys_persist_after_create_655(fresh_db): def test_not_null_persists_after_create_655(fresh_db): """When not_null is passed to create(), it should be stored in _defaults.""" - table = fresh_db["users"] + table = fresh_db.table("users") table.create({"id": int, "name": str}, pk="id", not_null=["name"]) assert table._defaults["not_null"] == ["name"] def test_defaults_persist_after_create_655(fresh_db): """When defaults is passed to create(), it should be stored in _defaults.""" - table = fresh_db["users"] + table = fresh_db.table("users") table.create({"id": int, "score": int}, pk="id", defaults={"score": 0}) assert table._defaults["defaults"] == {"score": 0} def test_strict_persists_after_create_655(fresh_db): """When strict is passed to create(), it should be stored in _defaults.""" - table = fresh_db["users"] + table = fresh_db.table("users") table.create({"id": int, "name": str}, pk="id", strict=True) assert table._defaults["strict"] is True def test_upsert_uses_pk_from_prior_insert_655(fresh_db): """After insert with pk, upsert should use the same pk.""" - table = fresh_db["users"] + table = fresh_db.table("users") table.insert({"id": 1, "name": "Alice"}, pk="id") # Upsert should work without specifying pk again table.upsert({"id": 1, "name": "Alice Updated"}) assert table.count == 1 - assert list(table.rows)[0]["name"] == "Alice Updated" + assert next(iter(table.rows))["name"] == "Alice Updated" def test_upsert_all_uses_pk_from_prior_insert_655(fresh_db): """After insert with pk, upsert_all should use the same pk.""" - table = fresh_db["users"] + table = fresh_db.table("users") table.insert({"id": 1, "name": "Alice"}, pk="id") # Upsert_all should work without specifying pk again table.upsert_all([{"id": 1, "name": "Alice Updated"}, {"id": 2, "name": "Bob"}]) diff --git a/tests/test_create_table_parser.py b/tests/test_create_table_parser.py new file mode 100644 index 0000000..74a089c --- /dev/null +++ b/tests/test_create_table_parser.py @@ -0,0 +1,243 @@ +import sqlite3 + +import hypothesis.strategies as st +import pytest +from hypothesis import given + +from sqlite_utils.create_table_parser import ( + Check, + ColumnComments, + ParseError, + Unique, + UniqueColumn, + parse_autoincrement, + parse_checks, + parse_column_comments, + parse_uniques, +) + + +def test_parse_column_and_table_checks(): + sql = """ + CREATE TABLE people ( + age INTEGER CONSTRAINT positive CHECK (age > 0), + status TEXT CHECK(status IN ('active', 'inactive')), + CONSTRAINT adult CHECK(age >= 18) + ) + """ + assert parse_checks(sql) == [ + Check("age > 0", name="positive", column="age"), + Check( + "status IN ('active', 'inactive')", + column="status", + options=["active", "inactive"], + ), + Check("age >= 18", name="adult"), + ] + checks = parse_checks(sql) + assert checks[0].sql == "CONSTRAINT positive CHECK (age > 0)" + assert sql[checks[0].start : checks[0].end] == checks[0].sql + assert checks[1].sql == "CHECK(status IN ('active', 'inactive'))" + assert sql[checks[2].start : checks[2].end] == checks[2].sql + + +def test_comments_are_trivia_not_constraints(): + sql = """ + CREATE /* fake CHECK (nope), ( */ TABLE t ( + a INTEGER /* CHECK (a < 0), phantom */, + b INTEGER CHECK /* between keyword and expression */ (b > 0), + /* CHECK (also_fake) */ CONSTRAINT upper CHECK(b < 10) + ) + """ + sqlite3.connect(":memory:").execute(sql) + assert parse_checks(sql) == [ + Check("b > 0", column="b"), + Check("b < 10", name="upper"), + ] + + +def test_parse_comments_owned_by_columns(): + sql = """ + CREATE TABLE t ( + -- Before id + id /* Between name and type */ INTEGER /* After id */, + /* Between column definitions */ + value TEXT CHECK(value != '') /* After value */, + /* Before a table constraint, not a column */ + CHECK(value != 'forbidden') + ) + """ + assert parse_column_comments(sql) == { + "id": ColumnComments(before="-- Before id", after="/* After id */"), + "value": ColumnComments( + before="/* Between column definitions */", + after="/* After value */", + ), + } + + +@pytest.mark.parametrize( + "expression,expected", + [ + ("value IN ('one', 'two')", ["one", "two"]), + ("((value IN ('one', 'two')))", ["one", "two"]), + ("value NOT IN ('one', 'two')", None), + ("value IN ('one', 'two') OR enabled", None), + ("other IN ('one', 'two')", None), + ("value IN (lower('one'), 'two')", None), + ('value IN ("other")', None), + ], +) +def test_options_only_for_exact_literal_in_check(expression, expected): + sql = f"CREATE TABLE t(value TEXT CHECK({expression}), enabled INTEGER, other TEXT)" + sqlite3.connect(":memory:").execute(sql) + assert parse_checks(sql)[0].options == expected + + +@pytest.mark.parametrize("column", ["💩x", "e\u0301"]) +def test_unquoted_unicode_identifiers(column): + sql = f"CREATE TABLE t({column} INTEGER CHECK({column} > 0))" + sqlite3.connect(":memory:").execute(sql) + assert parse_checks(sql) == [Check(f"{column} > 0", column=column)] + + +@pytest.mark.parametrize( + "sql", + [ + "SELECT CHECK(x > 0)", + "CREATE TABLE t(x INTEGER CHECK(x > 0)", + "CREATE TABLE t(x TEXT CHECK(x != 'unterminated))", + "CREATE TABLE t(x INTEGER /* unterminated)", + ], +) +def test_invalid_sql_raises_parse_error(sql): + with pytest.raises(ParseError): + parse_checks(sql) + + +def test_virtual_table_has_no_checks(): + assert ( + parse_checks("CREATE /* comment */ VIRTUAL TABLE search USING fts5(text)") == [] + ) + + +@pytest.mark.parametrize( + "sql,expected", + [ + ( + "CREATE TABLE t(id INTEGER PRIMARY KEY AUTOINCREMENT, value TEXT)", + "id", + ), + ( + 'CREATE TABLE t("quoted id" INTEGER PRIMARY KEY AUTOINCREMENT)', + "quoted id", + ), + ( + 'CREATE TABLE t("autoincrement" INTEGER PRIMARY KEY, value TEXT)', + None, + ), + ( + "CREATE TABLE t(id INTEGER PRIMARY KEY /* AUTOINCREMENT */, value TEXT)", + None, + ), + ( + "CREATE TABLE t(id INTEGER PRIMARY KEY, value TEXT CHECK(value != 'AUTOINCREMENT'))", + None, + ), + ], +) +def test_parse_autoincrement(sql, expected): + sqlite3.connect(":memory:").execute(sql) + assert parse_autoincrement(sql) == expected + + +def test_parse_column_and_table_uniques(): + sql = """ + CREATE TABLE memberships ( + email TEXT COLLATE RTRIM CONSTRAINT unique_email UNIQUE ON CONFLICT IGNORE, + account_id INTEGER, + CONSTRAINT unique_membership UNIQUE ( + account_id DESC, + email COLLATE NOCASE ASC + ) ON CONFLICT REPLACE + ) + """ + sqlite3.connect(":memory:").execute(sql) + assert parse_uniques(sql) == [ + Unique( + (UniqueColumn("email", collation="RTRIM"),), + name="unique_email", + column="email", + conflict="IGNORE", + ), + Unique( + ( + UniqueColumn("account_id", order="DESC"), + UniqueColumn("email", collation="NOCASE", order="ASC"), + ), + name="unique_membership", + conflict="REPLACE", + ), + ] + uniques = parse_uniques(sql) + assert uniques[0].sql == "CONSTRAINT unique_email UNIQUE ON CONFLICT IGNORE" + assert sql[uniques[1].start : uniques[1].end] == uniques[1].sql + + +def test_unique_like_text_in_comments_and_checks_is_ignored(): + sql = """ + CREATE TABLE t ( + value TEXT /* UNIQUE ON CONFLICT REPLACE */ + CHECK(value != 'UNIQUE(other)'), + other TEXT + ) + """ + sqlite3.connect(":memory:").execute(sql) + assert parse_uniques(sql) == [] + + +comment_or_space = st.sampled_from( + [ + " ", + "\n ", + "/* comment with , ( ) and CHECK(fake) */", + "-- comment with , ( ) and CHECK(fake)\n", + ] +) + + +@given(gaps=st.lists(comment_or_space, min_size=5, max_size=5)) +def test_comments_and_whitespace_can_separate_check_tokens(gaps): + sql = ( + f"CREATE{gaps[0]}TABLE{gaps[1]}t{gaps[2]}(" + f"value INTEGER CHECK{gaps[3]}(value{gaps[4]}> 0))" + ) + connection = sqlite3.connect(":memory:") + connection.execute(sql) + stored_sql = connection.execute( + "select sql from sqlite_master where name = 't'" + ).fetchone()[0] + assert parse_checks(stored_sql) == [Check(f"value{gaps[4]}> 0", column="value")] + + +safe_string_text = st.text( + alphabet=st.characters( + blacklist_categories=("Cc", "Cs"), + blacklist_characters=("'",), + ), + max_size=40, +) + + +@given(value=safe_string_text) +def test_check_like_text_inside_strings_is_opaque(value): + sql = f"CREATE TABLE t(value TEXT CHECK(value != '{value}'))" + connection = sqlite3.connect(":memory:") + connection.execute(sql) + stored_sql = connection.execute( + "select sql from sqlite_master where name = 't'" + ).fetchone()[0] + checks = parse_checks(stored_sql) + assert len(checks) == 1 + assert checks[0].column == "value" + assert checks[0].check == f"value != '{value}'" diff --git a/tests/test_create_view.py b/tests/test_create_view.py index 056e246..2b70099 100644 --- a/tests/test_create_view.py +++ b/tests/test_create_view.py @@ -1,4 +1,5 @@ import pytest + from sqlite_utils.utils import OperationalError diff --git a/tests/test_default_value.py b/tests/test_default_value.py index 3724d99..02b28c3 100644 --- a/tests/test_default_value.py +++ b/tests/test_default_value.py @@ -31,10 +31,10 @@ EXAMPLES = [ @pytest.mark.parametrize("column_def,initial_value,expected_value", EXAMPLES) def test_quote_default_value(fresh_db, column_def, initial_value, expected_value): - fresh_db.execute("create table foo (col {})".format(column_def)) - assert initial_value == fresh_db["foo"].columns[0].default_value + fresh_db.execute(f"create table foo (col {column_def})") + assert initial_value == fresh_db.table("foo").columns[0].default_value assert expected_value == fresh_db.quote_default_value( - fresh_db["foo"].columns[0].default_value + fresh_db.table("foo").columns[0].default_value ) @@ -48,7 +48,7 @@ def test_insert_empty_record_uses_default_values(fresh_db): ) """) - table = fresh_db["has_defaults"] + table = fresh_db.table("has_defaults") table.insert({}) rows = list(table.rows) diff --git a/tests/test_delete.py b/tests/test_delete.py index a2d93aa..a9341b8 100644 --- a/tests/test_delete.py +++ b/tests/test_delete.py @@ -2,15 +2,15 @@ import sqlite_utils def test_delete_rowid_table(fresh_db): - table = fresh_db["table"] - table.insert({"foo": 1}).last_pk + table = fresh_db.table("table") + table.insert({"foo": 1}) rowid = table.insert({"foo": 2}).last_pk table.delete(rowid) assert [{"foo": 1}] == list(table.rows) def test_delete_pk_table(fresh_db): - table = fresh_db["table"] + table = fresh_db.table("table") table.insert({"id": 1}, pk="id") table.insert({"id": 2}, pk="id") table.delete(1) @@ -18,7 +18,7 @@ def test_delete_pk_table(fresh_db): def test_delete_where(fresh_db): - table = fresh_db["table"] + table = fresh_db.table("table") for i in range(1, 11): table.insert({"id": i}, pk="id") assert table.count == 10 @@ -27,7 +27,7 @@ def test_delete_where(fresh_db): def test_delete_where_all(fresh_db): - table = fresh_db["table"] + table = fresh_db.table("table") for i in range(1, 11): table.insert({"id": i}, pk="id") assert table.count == 10 @@ -38,27 +38,27 @@ def test_delete_where_all(fresh_db): def test_delete_where_commits(tmpdir): path = str(tmpdir / "test.db") db = sqlite_utils.Database(path) - db["table"].insert_all([{"id": i} for i in range(5)], pk="id") - db["table"].delete_where("id > ?", [2]) + db.table("table").insert_all([{"id": i} for i in range(5)], pk="id") + db.table("table").delete_where("id > ?", [2]) # The connection must not be left inside an open transaction, # otherwise subsequent atomic() blocks never commit either assert not db.conn.in_transaction - db["table"].insert({"id": 100}) + db.table("table").insert({"id": 100}) db.close() db2 = sqlite_utils.Database(path) - assert [r["id"] for r in db2["table"].rows] == [0, 1, 2, 100] + assert [r["id"] for r in db2.table("table").rows] == [0, 1, 2, 100] db2.close() def test_delete_where_analyze(fresh_db): - table = fresh_db["table"] + table = fresh_db.table("table") table.insert_all(({"id": i, "i": i} for i in range(10)), pk="id") table.create_index(["i"], analyze=True) assert "sqlite_stat1" in fresh_db.table_names() - assert list(fresh_db["sqlite_stat1"].rows) == [ + assert list(fresh_db.table("sqlite_stat1").rows) == [ {"tbl": "table", "idx": "idx_table_i", "stat": "10 1"} ] table.delete_where("id > ?", [5], analyze=True) - assert list(fresh_db["sqlite_stat1"].rows) == [ + assert list(fresh_db.table("sqlite_stat1").rows) == [ {"tbl": "table", "idx": "idx_table_i", "stat": "6 1"} ] diff --git a/tests/test_docs.py b/tests/test_docs.py index f657416..6bc06c8 100644 --- a/tests/test_docs.py +++ b/tests/test_docs.py @@ -1,8 +1,10 @@ -from click.testing import CliRunner -from sqlite_utils import cli, recipes -from pathlib import Path -import pytest import re +from pathlib import Path + +import pytest +from click.testing import CliRunner + +from sqlite_utils import cli, recipes docs_path = Path(__file__).parent.parent / "docs" commands_re = re.compile(r"(?:\$ | )sqlite-utils (\S+)") @@ -34,7 +36,7 @@ def test_commands_are_documented(documented_commands, command): @pytest.mark.parametrize("command", cli.cli.commands.values()) def test_commands_have_help(command): - assert command.help, "{} is missing its help".format(command) + assert command.help, f"{command} is missing its help" def test_convert_help(): diff --git a/tests/test_duplicate.py b/tests/test_duplicate.py index 28961d2..c7a5612 100644 --- a/tests/test_duplicate.py +++ b/tests/test_duplicate.py @@ -1,7 +1,9 @@ -from sqlite_utils.db import NoTable import datetime + import pytest +from sqlite_utils.db import NoTable + def test_duplicate(fresh_db): # Create table using native Sqlite statement: @@ -12,7 +14,7 @@ def test_duplicate(fresh_db): "bool_col" INTEGER, "datetime_col" TEXT)""") # Insert one row of mock data: - dt = datetime.datetime.now() + dt = datetime.datetime.now(datetime.timezone.utc) data = { "text_col": "Cleo", "real_col": 3.14, @@ -20,7 +22,7 @@ def test_duplicate(fresh_db): "bool_col": True, "datetime_col": str(dt), } - table1 = fresh_db["table1"] + table1 = fresh_db.table("table1") row_id = table1.insert(data).last_rowid # Duplicate table: table2 = table1.duplicate("table2") @@ -38,4 +40,4 @@ def test_duplicate(fresh_db): def test_duplicate_fails_if_table_does_not_exist(fresh_db): with pytest.raises(NoTable): - fresh_db["not_a_table"].duplicate("duplicated") + fresh_db.table("not_a_table").duplicate("duplicated") diff --git a/tests/test_enable_counts.py b/tests/test_enable_counts.py index 2f6b0db..1230b6c 100644 --- a/tests/test_enable_counts.py +++ b/tests/test_enable_counts.py @@ -1,14 +1,14 @@ -from sqlite_utils import Database -from sqlite_utils import cli -from click.testing import CliRunner import pytest +from click.testing import CliRunner + +from sqlite_utils import Database, cli def test_enable_counts_specific_table(fresh_db): - foo = fresh_db["foo"] + foo = fresh_db.table("foo") assert fresh_db.table_names() == [] for i in range(10): - foo.insert({"name": "item {}".format(i)}) + foo.insert({"name": f"item {i}"}) assert fresh_db.table_names() == ["foo"] assert foo.count == 10 # Now enable counts @@ -41,24 +41,24 @@ def test_enable_counts_specific_table(fresh_db): ), } assert fresh_db.table_names() == ["foo", "_counts"] - assert list(fresh_db["_counts"].rows) == [{"count": 10, "table": "foo"}] + assert list(fresh_db.table("_counts").rows) == [{"count": 10, "table": "foo"}] # Add some items to test the triggers for i in range(5): - foo.insert({"name": "item {}".format(10 + i)}) + foo.insert({"name": f"item {10 + i}"}) assert foo.count == 15 - assert list(fresh_db["_counts"].rows) == [{"count": 15, "table": "foo"}] + assert list(fresh_db.table("_counts").rows) == [{"count": 15, "table": "foo"}] # Delete some items foo.delete_where("rowid < 7") assert foo.count == 9 - assert list(fresh_db["_counts"].rows) == [{"count": 9, "table": "foo"}] + assert list(fresh_db.table("_counts").rows) == [{"count": 9, "table": "foo"}] foo.delete_where() assert foo.count == 0 - assert list(fresh_db["_counts"].rows) == [{"count": 0, "table": "foo"}] + assert list(fresh_db.table("_counts").rows) == [{"count": 0, "table": "foo"}] def test_enable_counts_all_tables(fresh_db): - foo = fresh_db["foo"] - bar = fresh_db["bar"] + foo = fresh_db.table("foo") + bar = fresh_db.table("bar") foo.insert({"name": "Cleo"}) bar.insert({"name": "Cleo"}) foo.enable_fts(["name"]) @@ -73,7 +73,7 @@ def test_enable_counts_all_tables(fresh_db): "foo_fts_config", "_counts", } - assert list(fresh_db["_counts"].rows) == [ + assert list(fresh_db.table("_counts").rows) == [ {"count": 1, "table": "foo"}, {"count": 1, "table": "bar"}, {"count": 3, "table": "foo_fts_data"}, @@ -87,10 +87,10 @@ def test_enable_counts_all_tables(fresh_db): def counts_db_path(tmpdir): path = str(tmpdir / "test.db") db = Database(path) - db["foo"].insert({"name": "bar"}) - db["bar"].insert({"name": "bar"}) - db["bar"].insert({"name": "bar"}) - db["baz"].insert({"name": "bar"}) + db.table("foo").insert({"name": "bar"}) + db.table("bar").insert({"name": "bar"}) + db.table("bar").insert({"name": "bar"}) + db.table("baz").insert({"name": "bar"}) return path @@ -163,25 +163,25 @@ def test_uses_counts_after_enable_counts(counts_db_path): def test_reset_counts(counts_db_path): db = Database(counts_db_path) - db["foo"].enable_counts() - db["bar"].enable_counts() + db.table("foo").enable_counts() + db.table("bar").enable_counts() assert db.cached_counts() == {"foo": 1, "bar": 2} # Corrupt the value - db["_counts"].update("foo", {"count": 3}) + db.table("_counts").update("foo", {"count": 3}) assert db.cached_counts() == {"foo": 3, "bar": 2} - assert db["foo"].count == 3 + assert db.table("foo").count == 3 # Reset them db.reset_counts() assert db.cached_counts() == {"foo": 1, "bar": 2} - assert db["foo"].count == 1 + assert db.table("foo").count == 1 def test_reset_counts_cli(counts_db_path): db = Database(counts_db_path) - db["foo"].enable_counts() - db["bar"].enable_counts() + db.table("foo").enable_counts() + db.table("bar").enable_counts() assert db.cached_counts() == {"foo": 1, "bar": 2} - db["_counts"].update("foo", {"count": 3}) + db.table("_counts").update("foo", {"count": 3}) result = CliRunner().invoke(cli.cli, ["reset-counts", counts_db_path]) assert result.exit_code == 0 assert db.cached_counts() == {"foo": 1, "bar": 2} diff --git a/tests/test_extract.py b/tests/test_extract.py index c73ee7a..f855041 100644 --- a/tests/test_extract.py +++ b/tests/test_extract.py @@ -1,19 +1,22 @@ -from sqlite_utils.db import InvalidColumns import itertools + import pytest +from sqlite_utils import ANY +from sqlite_utils.db import InvalidColumns + @pytest.mark.parametrize("table", [None, "Species"]) @pytest.mark.parametrize("fk_column", [None, "species"]) def test_extract_single_column(fresh_db, table, fk_column): expected_table = table or "species" - expected_fk = fk_column or "{}_id".format(expected_table) + expected_fk = fk_column or f"{expected_table}_id" iter_species = itertools.cycle(["Palm", "Spruce", "Mangrove", "Oak"]) - fresh_db["tree"].insert_all( + fresh_db.table("tree").insert_all( ( { "id": i, - "name": "Tree {}".format(i), + "name": f"Tree {i}", "species": next(iter_species), "end": 1, } @@ -21,28 +24,27 @@ def test_extract_single_column(fresh_db, table, fk_column): ), pk="id", ) - fresh_db["tree"].extract("species", table=table, fk_column=fk_column) - assert fresh_db["tree"].schema == ( + fresh_db.table("tree").extract("species", table=table, fk_column=fk_column) + assert fresh_db.table("tree").schema == ( 'CREATE TABLE "tree" (\n' ' "id" INTEGER PRIMARY KEY,\n' ' "name" TEXT,\n' - ' "{}" INTEGER REFERENCES "{}"("id"),\n'.format(expected_fk, expected_table) + f' "{expected_fk}" INTEGER REFERENCES "{expected_table}"("id"),\n' + ' "end" INTEGER\n' + ")" ) - assert fresh_db[expected_table].schema == ( - 'CREATE TABLE "{}" (\n'.format(expected_table) - + ' "id" INTEGER PRIMARY KEY,\n' + assert fresh_db.table(expected_table).schema == ( + f'CREATE TABLE "{expected_table}" (\n' + ' "id" INTEGER PRIMARY KEY,\n' ' "species" TEXT\n' ")" ) - assert list(fresh_db[expected_table].rows) == [ + assert list(fresh_db.table(expected_table).rows) == [ {"id": 1, "species": "Palm"}, {"id": 2, "species": "Spruce"}, {"id": 3, "species": "Mangrove"}, {"id": 4, "species": "Oak"}, ] - assert list(itertools.islice(fresh_db["tree"].rows, 0, 4)) == [ + assert list(itertools.islice(fresh_db.table("tree").rows, 0, 4)) == [ {"id": 1, "name": "Tree 1", expected_fk: 1, "end": 1}, {"id": 2, "name": "Tree 2", expected_fk: 2, "end": 1}, {"id": 3, "name": "Tree 3", expected_fk: 3, "end": 1}, @@ -53,11 +55,11 @@ def test_extract_single_column(fresh_db, table, fk_column): def test_extract_multiple_columns_with_rename(fresh_db): iter_common = itertools.cycle(["Palm", "Spruce", "Mangrove", "Oak"]) iter_latin = itertools.cycle(["Arecaceae", "Picea", "Rhizophora", "Quercus"]) - fresh_db["tree"].insert_all( + fresh_db.table("tree").insert_all( ( { "id": i, - "name": "Tree {}".format(i), + "name": f"Tree {i}", "common_name": next(iter_common), "latin_name": next(iter_latin), } @@ -66,30 +68,30 @@ def test_extract_multiple_columns_with_rename(fresh_db): pk="id", ) - fresh_db["tree"].extract( + fresh_db.table("tree").extract( ["common_name", "latin_name"], rename={"common_name": "name"} ) - assert fresh_db["tree"].schema == ( + assert fresh_db.table("tree").schema == ( 'CREATE TABLE "tree" (\n' ' "id" INTEGER PRIMARY KEY,\n' ' "name" TEXT,\n' ' "common_name_latin_name_id" INTEGER REFERENCES "common_name_latin_name"("id")\n' ")" ) - assert fresh_db["common_name_latin_name"].schema == ( + assert fresh_db.table("common_name_latin_name").schema == ( 'CREATE TABLE "common_name_latin_name" (\n' ' "id" INTEGER PRIMARY KEY,\n' ' "name" TEXT,\n' ' "latin_name" TEXT\n' ")" ) - assert list(fresh_db["common_name_latin_name"].rows) == [ + assert list(fresh_db.table("common_name_latin_name").rows) == [ {"name": "Palm", "id": 1, "latin_name": "Arecaceae"}, {"name": "Spruce", "id": 2, "latin_name": "Picea"}, {"name": "Mangrove", "id": 3, "latin_name": "Rhizophora"}, {"name": "Oak", "id": 4, "latin_name": "Quercus"}, ] - assert list(itertools.islice(fresh_db["tree"].rows, 0, 4)) == [ + assert list(itertools.islice(fresh_db.table("tree").rows, 0, 4)) == [ {"id": 1, "name": "Tree 1", "common_name_latin_name_id": 1}, {"id": 2, "name": "Tree 2", "common_name_latin_name_id": 2}, {"id": 3, "name": "Tree 3", "common_name_latin_name_id": 3}, @@ -98,7 +100,7 @@ def test_extract_multiple_columns_with_rename(fresh_db): def test_extract_invalid_columns(fresh_db): - fresh_db["tree"].insert( + fresh_db.table("tree").insert( { "id": 1, "name": "Tree 1", @@ -108,19 +110,19 @@ def test_extract_invalid_columns(fresh_db): pk="id", ) with pytest.raises(InvalidColumns): - fresh_db["tree"].extract(["bad_column"]) + fresh_db.table("tree").extract(["bad_column"]) def test_extract_rowid_table(fresh_db): - fresh_db["tree"].insert( + fresh_db.table("tree").insert( { "name": "Tree 1", "common_name": "Palm", "latin_name": "Arecaceae", } ) - fresh_db["tree"].extract(["common_name", "latin_name"]) - assert fresh_db["tree"].schema == ( + fresh_db.table("tree").extract(["common_name", "latin_name"]) + assert fresh_db.table("tree").schema == ( 'CREATE TABLE "tree" (\n' ' "name" TEXT,\n' ' "common_name_latin_name_id" INTEGER REFERENCES "common_name_latin_name"("id")\n' @@ -138,68 +140,68 @@ def test_extract_rowid_table(fresh_db): def test_reuse_lookup_table(fresh_db): - fresh_db["species"].insert({"id": 1, "name": "Wolf"}, pk="id") - fresh_db["sightings"].insert({"id": 10, "species": "Wolf"}, pk="id") - fresh_db["individuals"].insert( + fresh_db.table("species").insert({"id": 1, "name": "Wolf"}, pk="id") + fresh_db.table("sightings").insert({"id": 10, "species": "Wolf"}, pk="id") + fresh_db.table("individuals").insert( {"id": 10, "name": "Terriana", "species": "Fox"}, pk="id" ) - fresh_db["sightings"].extract("species", rename={"species": "name"}) - fresh_db["individuals"].extract("species", rename={"species": "name"}) - assert fresh_db["sightings"].schema == ( + fresh_db.table("sightings").extract("species", rename={"species": "name"}) + fresh_db.table("individuals").extract("species", rename={"species": "name"}) + assert fresh_db.table("sightings").schema == ( 'CREATE TABLE "sightings" (\n' ' "id" INTEGER PRIMARY KEY,\n' ' "species_id" INTEGER REFERENCES "species"("id")\n' ")" ) - assert fresh_db["individuals"].schema == ( + assert fresh_db.table("individuals").schema == ( 'CREATE TABLE "individuals" (\n' ' "id" INTEGER PRIMARY KEY,\n' ' "name" TEXT,\n' ' "species_id" INTEGER REFERENCES "species"("id")\n' ")" ) - assert list(fresh_db["species"].rows) == [ + assert list(fresh_db.table("species").rows) == [ {"id": 1, "name": "Wolf"}, {"id": 2, "name": "Fox"}, ] def test_extract_error_on_incompatible_existing_lookup_table(fresh_db): - fresh_db["species"].insert({"id": 1}) - fresh_db["tree"].insert({"name": "Tree 1", "common_name": "Palm"}) + fresh_db.table("species").insert({"id": 1}) + fresh_db.table("tree").insert({"name": "Tree 1", "common_name": "Palm"}) with pytest.raises(InvalidColumns): - fresh_db["tree"].extract("common_name", table="species") + fresh_db.table("tree").extract("common_name", table="species") # Try again with incompatible existing column type - fresh_db["species2"].insert({"id": 1, "common_name": 3.5}) + fresh_db.table("species2").insert({"id": 1, "common_name": 3.5}) with pytest.raises(InvalidColumns): - fresh_db["tree"].extract("common_name", table="species2") + fresh_db.table("tree").extract("common_name", table="species2") def test_extract_works_with_null_values(fresh_db): - fresh_db["listens"].insert_all( + fresh_db.table("listens").insert_all( [ {"id": 1, "track_title": "foo", "album_title": "bar"}, {"id": 2, "track_title": "baz", "album_title": None}, ], pk="id", ) - fresh_db["listens"].extract( + fresh_db.table("listens").extract( columns=["album_title"], table="albums", fk_column="album_id" ) - assert list(fresh_db["listens"].rows) == [ + assert list(fresh_db.table("listens").rows) == [ {"id": 1, "track_title": "foo", "album_id": 1}, {"id": 2, "track_title": "baz", "album_id": None}, ] - assert list(fresh_db["albums"].rows) == [ + assert list(fresh_db.table("albums").rows) == [ {"id": 1, "album_title": "bar"}, ] def test_extract_null_values_single_column(fresh_db): # https://github.com/simonw/sqlite-utils/issues/186 - fresh_db["species"].insert({"id": 1, "species": "Wolf"}, pk="id") - fresh_db["individuals"].insert_all( + fresh_db.table("species").insert({"id": 1, "species": "Wolf"}, pk="id") + fresh_db.table("individuals").insert_all( [ {"id": 10, "name": "Terriana", "species": "Fox"}, {"id": 11, "name": "Spenidorm", "species": None}, @@ -209,13 +211,13 @@ def test_extract_null_values_single_column(fresh_db): ], pk="id", ) - fresh_db["individuals"].extract("species") + fresh_db.table("individuals").extract("species") # No null row should have been added to species - assert list(fresh_db["species"].rows) == [ + assert list(fresh_db.table("species").rows) == [ {"id": 1, "species": "Wolf"}, {"id": 2, "species": "Fox"}, ] - assert list(fresh_db["individuals"].rows) == [ + assert list(fresh_db.table("individuals").rows) == [ {"id": 10, "name": "Terriana", "species_id": 2}, {"id": 11, "name": "Spenidorm", "species_id": None}, {"id": 12, "name": "Grantheim", "species_id": 1}, @@ -227,7 +229,7 @@ def test_extract_null_values_single_column(fresh_db): def test_extract_null_values_multiple_columns(fresh_db): # A row should be extracted if at least one column is not null - # only rows where ALL extracted columns are null are left alone - fresh_db["circulation"].insert_all( + fresh_db.table("circulation").insert_all( [ {"id": 1, "title": "title one", "creator": "creator one", "year": 2018}, {"id": 2, "title": "title two", "creator": None, "year": 2019}, @@ -236,14 +238,14 @@ def test_extract_null_values_multiple_columns(fresh_db): ], pk="id", ) - fresh_db["circulation"].extract( + fresh_db.table("circulation").extract( ["title", "creator"], table="books", fk_column="book_id" ) - assert list(fresh_db["books"].rows) == [ + assert list(fresh_db.table("books").rows) == [ {"id": 1, "title": "title one", "creator": "creator one"}, {"id": 2, "title": "title two", "creator": None}, ] - assert list(fresh_db["circulation"].rows) == [ + assert list(fresh_db.table("circulation").rows) == [ {"id": 1, "book_id": 1, "year": 2018}, {"id": 2, "book_id": 2, "year": 2019}, {"id": 3, "book_id": None, "year": 2020}, @@ -254,20 +256,20 @@ def test_extract_null_values_multiple_columns(fresh_db): def test_extract_null_values_existing_lookup_table_with_null_row(fresh_db): # Even if the lookup table already contains an all-null row, rows where # every extracted column is null should keep a null foreign key - fresh_db["species"].insert({"id": 1, "species": None}, pk="id") - fresh_db["individuals"].insert_all( + fresh_db.table("species").insert({"id": 1, "species": None}, pk="id") + fresh_db.table("individuals").insert_all( [ {"id": 10, "name": "Terriana", "species": "Fox"}, {"id": 11, "name": "Spenidorm", "species": None}, ], pk="id", ) - fresh_db["individuals"].extract("species") - assert list(fresh_db["species"].rows) == [ + fresh_db.table("individuals").extract("species") + assert list(fresh_db.table("species").rows) == [ {"id": 1, "species": None}, {"id": 2, "species": "Fox"}, ] - assert list(fresh_db["individuals"].rows) == [ + assert list(fresh_db.table("individuals").rows) == [ {"id": 10, "name": "Terriana", "species_id": 2}, {"id": 11, "name": "Spenidorm", "species_id": None}, ] @@ -278,17 +280,19 @@ def test_extract_repeated_into_shared_lookup_with_nulls(fresh_db): # cannot dedupe NULL-containing rows against the existing lookup # table - extracting a second table into the same lookup previously # inserted duplicate rows that nothing pointed to - fresh_db["t1"].insert_all( + fresh_db.table("t1").insert_all( [ {"id": 1, "species": None, "common": "X"}, {"id": 2, "species": "Oak", "common": "Oak"}, ], pk="id", ) - fresh_db["t2"].insert_all([{"id": 1, "species": None, "common": "X"}], pk="id") - fresh_db["t1"].extract(["species", "common"], table="lk") - fresh_db["t2"].extract(["species", "common"], table="lk") - assert fresh_db["lk"].count == 2 + fresh_db.table("t2").insert_all( + [{"id": 1, "species": None, "common": "X"}], pk="id" + ) + fresh_db.table("t1").extract(["species", "common"], table="lk") + fresh_db.table("t2").extract(["species", "common"], table="lk") + assert fresh_db.table("lk").count == 2 # Both tables point at the same lookup row t1_fk = fresh_db.execute("select lk_id from t1 where id = 1").fetchone()[0] t2_fk = fresh_db.execute("select lk_id from t2 where id = 1").fetchone()[0] @@ -297,8 +301,43 @@ def test_extract_repeated_into_shared_lookup_with_nulls(fresh_db): def test_extract_repeated_into_shared_lookup_no_nulls(fresh_db): # Non-NULL rows were already deduped by the unique index - keep it so - fresh_db["t1"].insert_all([{"id": 1, "species": "Oak"}], pk="id") - fresh_db["t2"].insert_all([{"id": 1, "species": "Oak"}], pk="id") - fresh_db["t1"].extract(["species"], table="lk") - fresh_db["t2"].extract(["species"], table="lk") - assert fresh_db["lk"].count == 1 + fresh_db.table("t1").insert_all([{"id": 1, "species": "Oak"}], pk="id") + fresh_db.table("t2").insert_all([{"id": 1, "species": "Oak"}], pk="id") + fresh_db.table("t1").extract(["species"], table="lk") + fresh_db.table("t2").extract(["species"], table="lk") + assert fresh_db.table("lk").count == 1 + + +def test_extract_preserves_strict_any(fresh_db): + if not fresh_db.supports_strict: + pytest.skip("SQLite version does not support strict tables") + fresh_db.execute("create table items (id integer primary key, data any) strict") + fresh_db.execute("insert into items values (1, ?)", ("000123",)) + + fresh_db["items"].extract("data", table="data_values") + + lookup = fresh_db["data_values"] + assert lookup.strict is True + assert lookup.columns_dict == {"id": int, "data": ANY} + assert fresh_db.execute( + "select typeof(data), data from data_values" + ).fetchone() == ("text", "000123") + + +def test_extract_strict_any_rejects_non_strict_lookup(fresh_db): + if not fresh_db.supports_strict: + pytest.skip("SQLite version does not support strict tables") + fresh_db.execute("create table items (data any) strict") + fresh_db.execute("insert into items values (?)", ("000123",)) + fresh_db.execute("create table data_values (id integer primary key, data any)") + + with pytest.raises( + InvalidColumns, + match="is not STRICT, so it cannot preserve ANY column values", + ): + fresh_db["items"].extract("data", table="data_values") + + assert fresh_db.execute("select typeof(data), data from items").fetchone() == ( + "text", + "000123", + ) diff --git a/tests/test_extracts.py b/tests/test_extracts.py index 7add79a..4e7cf39 100644 --- a/tests/test_extracts.py +++ b/tests/test_extracts.py @@ -1,13 +1,14 @@ -from sqlite_utils.db import Index import pytest +from sqlite_utils.db import Index + @pytest.mark.parametrize( "kwargs,expected_table", [ - (dict(extracts={"species_id": "Species"}), "Species"), - (dict(extracts=["species_id"]), "species_id"), - (dict(extracts=("species_id",)), "species_id"), + ({"extracts": {"species_id": "Species"}}, "Species"), + ({"extracts": ["species_id"]}, "species_id"), + ({"extracts": ("species_id",)}, "species_id"), ], ) @pytest.mark.parametrize("use_table_factory", [True, False]) @@ -30,20 +31,16 @@ def test_extracts(fresh_db, kwargs, expected_table, use_table_factory): # Should now have two tables: Trees and Species assert {expected_table, "Trees"} == set(fresh_db.table_names()) assert ( - 'CREATE TABLE "{}" (\n "id" INTEGER PRIMARY KEY,\n "value" TEXT\n)'.format( - expected_table - ) - == fresh_db[expected_table].schema + f'CREATE TABLE "{expected_table}" (\n "id" INTEGER PRIMARY KEY,\n "value" TEXT\n)' + == fresh_db.table(expected_table).schema ) assert ( - 'CREATE TABLE "Trees" (\n "id" INTEGER,\n "species_id" INTEGER REFERENCES "{}"("id")\n)'.format( - expected_table - ) - == fresh_db["Trees"].schema + f'CREATE TABLE "Trees" (\n "id" INTEGER,\n "species_id" INTEGER REFERENCES "{expected_table}"("id")\n)' + == fresh_db.table("Trees").schema ) # Should have a foreign key reference - assert len(fresh_db["Trees"].foreign_keys) == 1 - fk = fresh_db["Trees"].foreign_keys[0] + assert len(fresh_db.table("Trees").foreign_keys) == 1 + fk = fresh_db.table("Trees").foreign_keys[0] assert fk.table == "Trees" assert fk.column == "species_id" @@ -51,28 +48,28 @@ def test_extracts(fresh_db, kwargs, expected_table, use_table_factory): assert [ Index( seq=0, - name="idx_{}_value".format(expected_table), + name=f"idx_{expected_table}_value", unique=1, origin="c", partial=0, columns=["value"], ) - ] == fresh_db[expected_table].indexes + ] == fresh_db.table(expected_table).indexes # Finally, check the rows assert [{"id": 1, "value": "Oak"}, {"id": 2, "value": "Palm"}] == list( - fresh_db[expected_table].rows + fresh_db.table(expected_table).rows ) assert [ {"id": 1, "species_id": 1}, {"id": 2, "species_id": 1}, {"id": 3, "species_id": 2}, - ] == list(fresh_db["Trees"].rows) + ] == list(fresh_db.table("Trees").rows) def test_extracts_null_values(fresh_db): # https://github.com/simonw/sqlite-utils/issues/186 # Null values should stay null, not be extracted into the lookup table - fresh_db["Trees"].insert_all( + fresh_db.table("Trees").insert_all( [ {"id": 1, "species_id": "Oak"}, {"id": 2, "species_id": None}, @@ -81,11 +78,11 @@ def test_extracts_null_values(fresh_db): ], extracts={"species_id": "Species"}, ) - assert list(fresh_db["Species"].rows) == [ + assert list(fresh_db.table("Species").rows) == [ {"id": 1, "value": "Oak"}, {"id": 2, "value": "Palm"}, ] - assert list(fresh_db["Trees"].rows) == [ + assert list(fresh_db.table("Trees").rows) == [ {"id": 1, "species_id": 1}, {"id": 2, "species_id": None}, {"id": 3, "species_id": 2}, @@ -95,7 +92,7 @@ def test_extracts_null_values(fresh_db): def test_extracts_null_values_list_mode(fresh_db): # Same as test_extracts_null_values but for list-based records - fresh_db["Trees"].insert_all( + fresh_db.table("Trees").insert_all( [ ["id", "species_id"], [1, "Oak"], @@ -105,11 +102,11 @@ def test_extracts_null_values_list_mode(fresh_db): ], extracts={"species_id": "Species"}, ) - assert list(fresh_db["Species"].rows) == [ + assert list(fresh_db.table("Species").rows) == [ {"id": 1, "value": "Oak"}, {"id": 2, "value": "Palm"}, ] - assert list(fresh_db["Trees"].rows) == [ + assert list(fresh_db.table("Trees").rows) == [ {"id": 1, "species_id": 1}, {"id": 2, "species_id": None}, {"id": 3, "species_id": 2}, diff --git a/tests/test_foreign_keys.py b/tests/test_foreign_keys.py index b37d374..f916c65 100644 --- a/tests/test_foreign_keys.py +++ b/tests/test_foreign_keys.py @@ -1,6 +1,7 @@ """Tests for compound (multi-column) foreign keys - issue #594.""" import pytest + from sqlite_utils import Database from sqlite_utils.db import AlterError, ForeignKey from sqlite_utils.utils import sqlite3 @@ -31,7 +32,7 @@ def compound_db(): def test_compound_foreign_key(compound_db): - fks = compound_db["courses"].foreign_keys + fks = compound_db.table("courses").foreign_keys assert len(fks) == 1 fk = fks[0] assert fk.is_compound is True @@ -45,10 +46,10 @@ def test_compound_foreign_key(compound_db): def test_single_foreign_key_gets_columns_fields(fresh_db): - fresh_db["authors"].insert({"id": 1, "name": "Sally"}, pk="id") - fresh_db["books"].insert({"title": "Hedgehogs", "author_id": 1}) - fresh_db["books"].add_foreign_key("author_id", "authors", "id") - fk = fresh_db["books"].foreign_keys[0] + fresh_db.table("authors").insert({"id": 1, "name": "Sally"}, pk="id") + fresh_db.table("books").insert({"title": "Hedgehogs", "author_id": 1}) + fresh_db.table("books").add_foreign_key("author_id", "authors", "id") + fk = fresh_db.table("books").foreign_keys[0] assert fk.is_compound is False assert fk.column == "author_id" assert fk.other_column == "id" @@ -59,27 +60,29 @@ def test_single_foreign_key_gets_columns_fields(fresh_db): def test_foreign_key_no_longer_unpacks_as_tuple(fresh_db): # Clean break in 4.0: ForeignKey is a dataclass, not a namedtuple, so the # old tuple unpacking and indexing patterns now fail hard. - fresh_db["authors"].insert({"id": 1, "name": "Sally"}, pk="id") - fresh_db["books"].insert({"title": "Hedgehogs", "author_id": 1}) - fresh_db["books"].add_foreign_key("author_id", "authors", "id") - fk = fresh_db["books"].foreign_keys[0] + fresh_db.table("authors").insert({"id": 1, "name": "Sally"}, pk="id") + fresh_db.table("books").insert({"title": "Hedgehogs", "author_id": 1}) + fresh_db.table("books").add_foreign_key("author_id", "authors", "id") + fk = fresh_db.table("books").foreign_keys[0] with pytest.raises(TypeError): - table, column, other_table, other_column = fk + _table, _column, _other_table, _other_column = fk with pytest.raises(TypeError): fk[0] def test_foreign_keys_are_sortable(fresh_db): - fresh_db["authors"].insert({"id": 1, "name": "Sally"}, pk="id") - fresh_db["categories"].insert({"id": 1, "name": "Wildlife"}, pk="id") - fresh_db["books"].insert({"title": "Hedgehogs", "author_id": 1, "category_id": 1}) + fresh_db.table("authors").insert({"id": 1, "name": "Sally"}, pk="id") + fresh_db.table("categories").insert({"id": 1, "name": "Wildlife"}, pk="id") + fresh_db.table("books").insert( + {"title": "Hedgehogs", "author_id": 1, "category_id": 1} + ) fresh_db.add_foreign_keys( [ ("books", "author_id", "authors", "id"), ("books", "category_id", "categories", "id"), ] ) - fks = sorted(fresh_db["books"].foreign_keys) + fks = sorted(fresh_db.table("books").foreign_keys) assert fks[0].column == "author_id" assert fks[1].column == "category_id" @@ -104,7 +107,7 @@ def test_mixed_compound_and_single_foreign_keys_are_sortable(): REFERENCES departments(campus_name, dept_code) ); """) - fks = db["courses"].foreign_keys + fks = db.table("courses").foreign_keys assert len(fks) == 2 assert {fk.is_compound for fk in fks} == {True, False} fks_sorted = sorted(fks) @@ -162,8 +165,8 @@ def test_create_table_with_compound_foreign_key(departments_db, foreign_keys): pk="course_code", foreign_keys=foreign_keys, ) - assert departments_db["courses"].schema == EXPECTED_COURSES_SCHEMA - fks = departments_db["courses"].foreign_keys + assert departments_db.table("courses").schema == EXPECTED_COURSES_SCHEMA + fks = departments_db.table("courses").foreign_keys assert len(fks) == 1 fk = fks[0] assert fk.is_compound is True @@ -180,10 +183,10 @@ def test_create_table_compound_foreign_key_enforced(departments_db): pk="course_code", foreign_keys=[(("campus_name", "dept_code"), "departments")], ) - departments_db["departments"].insert( + departments_db.table("departments").insert( {"campus_name": "Berkeley", "dept_code": "CS", "dept_name": "Computer Science"} ) - departments_db["courses"].insert( + departments_db.table("courses").insert( {"course_code": "CS101", "campus_name": "Berkeley", "dept_code": "CS"} ) with pytest.raises(sqlite3.IntegrityError): @@ -206,8 +209,8 @@ def test_create_table_compound_foreign_key_missing_other_column(departments_db): def test_transform_preserves_compound_foreign_key(compound_db): - compound_db["courses"].transform(rename={"course_name": "title"}) - fks = compound_db["courses"].foreign_keys + compound_db.table("courses").transform(rename={"course_name": "title"}) + fks = compound_db.table("courses").foreign_keys assert len(fks) == 1 fk = fks[0] assert fk.is_compound is True @@ -217,8 +220,8 @@ def test_transform_preserves_compound_foreign_key(compound_db): def test_transform_rename_member_column_updates_compound_foreign_key(compound_db): - compound_db["courses"].transform(rename={"campus_name": "campus"}) - fks = compound_db["courses"].foreign_keys + compound_db.table("courses").transform(rename={"campus_name": "campus"}) + fks = compound_db.table("courses").foreign_keys assert len(fks) == 1 fk = fks[0] assert fk.is_compound is True @@ -230,9 +233,9 @@ def test_transform_rename_member_column_updates_compound_foreign_key(compound_db def test_transform_drop_member_column_drops_compound_foreign_key(compound_db): # Matches single-column behavior: dropping the column silently # drops the foreign key that used it - compound_db["courses"].transform(drop={"dept_code"}) - assert compound_db["courses"].foreign_keys == [] - assert "FOREIGN KEY" not in compound_db["courses"].schema + compound_db.table("courses").transform(drop={"dept_code"}) + assert compound_db.table("courses").foreign_keys == [] + assert "FOREIGN KEY" not in compound_db.table("courses").schema @pytest.mark.parametrize( @@ -245,11 +248,11 @@ def test_transform_drop_member_column_drops_compound_foreign_key(compound_db): ), ) def test_transform_drop_compound_foreign_key(compound_db, drop_foreign_keys): - compound_db["courses"].transform(drop_foreign_keys=drop_foreign_keys) - assert compound_db["courses"].foreign_keys == [] + compound_db.table("courses").transform(drop_foreign_keys=drop_foreign_keys) + assert compound_db.table("courses").foreign_keys == [] # The columns themselves survive assert {"campus_name", "dept_code"} <= set( - compound_db["courses"].columns_dict.keys() + compound_db.table("courses").columns_dict.keys() ) @@ -264,12 +267,12 @@ def courses_db(departments_db): def test_add_compound_foreign_key(courses_db): - t = courses_db["courses"].add_foreign_key( + t = courses_db.table("courses").add_foreign_key( ("campus_name", "dept_code"), "departments", ("campus_name", "dept_code") ) # Returns self assert t.name == "courses" - fks = courses_db["courses"].foreign_keys + fks = courses_db.table("courses").foreign_keys assert len(fks) == 1 fk = fks[0] assert fk.is_compound is True @@ -280,27 +283,33 @@ def test_add_compound_foreign_key(courses_db): def test_add_compound_foreign_key_guesses_other_columns(courses_db): # Lists work here too, though tuples are the documented form - courses_db["courses"].add_foreign_key(["campus_name", "dept_code"], "departments") - fk = courses_db["courses"].foreign_keys[0] + courses_db.table("courses").add_foreign_key( + ["campus_name", "dept_code"], "departments" + ) + fk = courses_db.table("courses").foreign_keys[0] assert fk.other_columns == ("campus_name", "dept_code") def test_add_compound_foreign_key_error_if_already_exists(courses_db): - courses_db["courses"].add_foreign_key(("campus_name", "dept_code"), "departments") + courses_db.table("courses").add_foreign_key( + ("campus_name", "dept_code"), "departments" + ) with pytest.raises(AlterError) as ex: - courses_db["courses"].add_foreign_key( + courses_db.table("courses").add_foreign_key( ("campus_name", "dept_code"), "departments" ) assert "already exists" in ex.value.args[0] # ignore=True should not raise - courses_db["courses"].add_foreign_key( + courses_db.table("courses").add_foreign_key( ("campus_name", "dept_code"), "departments", ignore=True ) def test_add_compound_foreign_key_error_if_column_missing(courses_db): with pytest.raises(AlterError): - courses_db["courses"].add_foreign_key(("campus_name", "nope"), "departments") + courses_db.table("courses").add_foreign_key( + ("campus_name", "nope"), "departments" + ) def test_db_add_foreign_keys_compound(courses_db): @@ -314,14 +323,14 @@ def test_db_add_foreign_keys_compound(courses_db): ) ] ) - fk = courses_db["courses"].foreign_keys[0] + fk = courses_db.table("courses").foreign_keys[0] assert fk.is_compound is True assert fk.columns == ("campus_name", "dept_code") def test_index_foreign_keys_compound_creates_composite_index(compound_db): compound_db.index_foreign_keys() - index_columns = [i.columns for i in compound_db["courses"].indexes] + index_columns = [i.columns for i in compound_db.table("courses").indexes] assert ["campus_name", "dept_code"] in index_columns # No separate single-column indexes for the members assert ["campus_name"] not in index_columns @@ -338,22 +347,22 @@ def test_foreign_key_captures_on_delete_and_on_update(): ON DELETE CASCADE ON UPDATE RESTRICT ); """) - fk = db["books"].foreign_keys[0] + fk = db.table("books").foreign_keys[0] assert fk.on_delete == "CASCADE" assert fk.on_update == "RESTRICT" def test_foreign_key_on_delete_defaults_to_no_action(fresh_db): - fresh_db["authors"].insert({"id": 1}, pk="id") - fresh_db["books"].insert({"id": 1, "author_id": 1}, pk="id") - fresh_db["books"].add_foreign_key("author_id", "authors", "id") - fk = fresh_db["books"].foreign_keys[0] + fresh_db.table("authors").insert({"id": 1}, pk="id") + fresh_db.table("books").insert({"id": 1, "author_id": 1}, pk="id") + fresh_db.table("books").add_foreign_key("author_id", "authors", "id") + fk = fresh_db.table("books").foreign_keys[0] assert fk.on_delete == "NO ACTION" assert fk.on_update == "NO ACTION" def test_create_table_foreign_key_with_on_delete(fresh_db): - fresh_db["authors"].insert({"id": 1}, pk="id") + fresh_db.table("authors").insert({"id": 1}, pk="id") fresh_db.create_table( "books", {"id": int, "author_id": int}, @@ -368,8 +377,8 @@ def test_create_table_foreign_key_with_on_delete(fresh_db): ) ], ) - assert "ON DELETE CASCADE" in fresh_db["books"].schema - assert fresh_db["books"].foreign_keys[0].on_delete == "CASCADE" + assert "ON DELETE CASCADE" in fresh_db.table("books").schema + assert fresh_db.table("books").foreign_keys[0].on_delete == "CASCADE" def test_transform_preserves_on_delete_cascade(): @@ -382,11 +391,11 @@ def test_transform_preserves_on_delete_cascade(): author_id INTEGER REFERENCES authors(id) ON DELETE CASCADE ); """) - db["books"].transform(rename={"title": "book_title"}) - fk = db["books"].foreign_keys[0] + db.table("books").transform(rename={"title": "book_title"}) + fk = db.table("books").foreign_keys[0] assert fk.on_delete == "CASCADE" assert fk.on_update == "NO ACTION" - assert "ON DELETE CASCADE" in db["books"].schema + assert "ON DELETE CASCADE" in db.table("books").schema def test_transform_preserves_compound_foreign_key_on_delete(): @@ -405,11 +414,11 @@ def test_transform_preserves_compound_foreign_key_on_delete(): REFERENCES departments(campus_name, dept_code) ON DELETE CASCADE ); """) - db["courses"].transform(rename={"course_code": "code"}) - fk = db["courses"].foreign_keys[0] + db.table("courses").transform(rename={"course_code": "code"}) + fk = db.table("courses").foreign_keys[0] assert fk.is_compound is True assert fk.on_delete == "CASCADE" - assert "ON DELETE CASCADE" in db["courses"].schema + assert "ON DELETE CASCADE" in db.table("courses").schema def test_implicit_primary_key_reference_is_resolved(): @@ -423,7 +432,7 @@ def test_implicit_primary_key_reference_is_resolved(): author_id INTEGER REFERENCES authors ); """) - fk = db["books"].foreign_keys[0] + fk = db.table("books").foreign_keys[0] assert fk.is_compound is False assert fk.other_column == "author_id" assert fk.other_columns == ("author_id",) @@ -444,7 +453,7 @@ def test_implicit_compound_primary_key_reference_is_resolved(): FOREIGN KEY (campus_name, dept_code) REFERENCES departments ); """) - fk = db["courses"].foreign_keys[0] + fk = db.table("courses").foreign_keys[0] assert fk.is_compound is True assert fk.other_columns == ("campus_name", "dept_code") @@ -469,14 +478,14 @@ def test_add_foreign_keys_preserves_actions(fresh_db): # https://github.com/simonw/sqlite-utils/issues/594 review finding: # ForeignKey objects passed to db.add_foreign_keys() were flattened # to plain tuples, losing on_delete/on_update - fresh_db["authors"].insert({"id": 1}, pk="id") - fresh_db["books"].insert({"id": 1, "author_id": 1}, pk="id") + fresh_db.table("authors").insert({"id": 1}, pk="id") + fresh_db.table("books").insert({"id": 1, "author_id": 1}, pk="id") fresh_db.add_foreign_keys( [ForeignKey("books", "author_id", "authors", "id", on_delete="CASCADE")] ) - fk = fresh_db["books"].foreign_keys[0] + fk = fresh_db.table("books").foreign_keys[0] assert fk.on_delete == "CASCADE" - assert "ON DELETE CASCADE" in fresh_db["books"].schema + assert "ON DELETE CASCADE" in fresh_db.table("books").schema def test_add_foreign_keys_preserves_actions_compound(courses_db): @@ -494,36 +503,36 @@ def test_add_foreign_keys_preserves_actions_compound(courses_db): ) ] ) - fk = courses_db["courses"].foreign_keys[0] + fk = courses_db.table("courses").foreign_keys[0] assert fk.is_compound is True assert fk.on_delete == "CASCADE" - assert "ON DELETE CASCADE" in courses_db["courses"].schema + assert "ON DELETE CASCADE" in courses_db.table("courses").schema def test_add_foreign_key_on_delete_on_update(fresh_db): - fresh_db["authors"].insert({"id": 1}, pk="id") - fresh_db["books"].insert({"id": 1, "author_id": 1}, pk="id") - fresh_db["books"].add_foreign_key( + fresh_db.table("authors").insert({"id": 1}, pk="id") + fresh_db.table("books").insert({"id": 1, "author_id": 1}, pk="id") + fresh_db.table("books").add_foreign_key( "author_id", "authors", "id", on_delete="CASCADE", on_update="RESTRICT" ) - fk = fresh_db["books"].foreign_keys[0] + fk = fresh_db.table("books").foreign_keys[0] assert fk.on_delete == "CASCADE" assert fk.on_update == "RESTRICT" - assert "ON UPDATE RESTRICT ON DELETE CASCADE" in fresh_db["books"].schema + assert "ON UPDATE RESTRICT ON DELETE CASCADE" in fresh_db.table("books").schema # The cascade should actually fire fresh_db.execute("PRAGMA foreign_keys = ON") fresh_db.execute("delete from authors where id = 1") - assert fresh_db["books"].count == 0 + assert fresh_db.table("books").count == 0 def test_add_compound_foreign_key_on_delete(courses_db): - courses_db["courses"].add_foreign_key( + courses_db.table("courses").add_foreign_key( ("campus_name", "dept_code"), "departments", on_delete="SET NULL" ) - fk = courses_db["courses"].foreign_keys[0] + fk = courses_db.table("courses").foreign_keys[0] assert fk.is_compound is True assert fk.on_delete == "SET NULL" - assert "ON DELETE SET NULL" in courses_db["courses"].schema + assert "ON DELETE SET NULL" in courses_db.table("courses").schema def test_implicit_compound_foreign_key_resolves_pk_declaration_order(fresh_db): @@ -535,7 +544,7 @@ def test_implicit_compound_foreign_key_resolves_pk_declaration_order(fresh_db): fresh_db.execute( "create table child (x text, y text, foreign key (x, y) references other)" ) - fk = fresh_db["child"].foreign_keys[0] + fk = fresh_db.table("child").foreign_keys[0] assert fk.other_columns == ("a", "b") @@ -548,46 +557,46 @@ def test_transform_implicit_compound_foreign_key_stays_valid(fresh_db): "create table child (x text, y text, foreign key (x, y) references other)" ) fresh_db.execute("PRAGMA foreign_keys = ON") - fresh_db["other"].insert({"a": "A", "b": "B"}) - fresh_db["child"].insert({"x": "A", "y": "B"}) - fresh_db["child"].transform(types={"x": str}) - assert fresh_db["child"].foreign_keys[0].other_columns == ("a", "b") + fresh_db.table("other").insert({"a": "A", "b": "B"}) + fresh_db.table("child").insert({"x": "A", "y": "B"}) + fresh_db.table("child").transform(types={"x": str}) + assert fresh_db.table("child").foreign_keys[0].other_columns == ("a", "b") # The constraint still points the right way around - fresh_db["child"].insert({"x": "A", "y": "B"}) + fresh_db.table("child").insert({"x": "A", "y": "B"}) with pytest.raises(sqlite3.IntegrityError): - fresh_db["child"].insert({"x": "B", "y": "A"}) + fresh_db.table("child").insert({"x": "B", "y": "A"}) def test_create_compound_foreign_key_guesses_pk_declaration_order(fresh_db): fresh_db.execute("create table other (b text, a text, primary key (a, b))") - fresh_db["other"].insert({"a": "A", "b": "B"}) - fresh_db["child"].create( + fresh_db.table("other").insert({"a": "A", "b": "B"}) + fresh_db.table("child").create( {"id": int, "x": str, "y": str}, pk="id", foreign_keys=[(("x", "y"), "other")], ) - assert fresh_db["child"].foreign_keys[0].other_columns == ("a", "b") + assert fresh_db.table("child").foreign_keys[0].other_columns == ("a", "b") fresh_db.execute("PRAGMA foreign_keys = ON") - fresh_db["child"].insert({"id": 1, "x": "A", "y": "B"}) + fresh_db.table("child").insert({"id": 1, "x": "A", "y": "B"}) with pytest.raises(sqlite3.IntegrityError): - fresh_db["child"].insert({"id": 2, "x": "B", "y": "A"}) + fresh_db.table("child").insert({"id": 2, "x": "B", "y": "A"}) def test_add_compound_foreign_key_guesses_pk_declaration_order(fresh_db): fresh_db.execute("create table other (b text, a text, primary key (a, b))") - fresh_db["child"].insert({"id": 1, "x": "A", "y": "B"}, pk="id") - fresh_db["child"].add_foreign_key(("x", "y"), "other") - assert fresh_db["child"].foreign_keys[0].other_columns == ("a", "b") + fresh_db.table("child").insert({"id": 1, "x": "A", "y": "B"}, pk="id") + fresh_db.table("child").add_foreign_key(("x", "y"), "other") + assert fresh_db.table("child").foreign_keys[0].other_columns == ("a", "b") def test_foreign_keys_are_hashable(fresh_db): # set() over foreign_keys worked with the 3.x namedtuple and must # keep working with the dataclass - fresh_db["p"].insert({"id": 1}, pk="id") - fresh_db["c"].insert( + fresh_db.table("p").insert({"id": 1}, pk="id") + fresh_db.table("c").insert( {"id": 1, "pid": 1}, pk="id", foreign_keys=[("pid", "p", "id")] ) - fks = set(fresh_db["c"].foreign_keys) + fks = set(fresh_db.table("c").foreign_keys) assert len(fks) == 1 assert ForeignKey("c", "pid", "p", "id") in fks # Usable as dict keys too @@ -599,7 +608,7 @@ def test_foreign_key_is_immutable(): fk = ForeignKey("c", "pid", "p", "id") with pytest.raises(dataclasses.FrozenInstanceError): - fk.table = "other" + setattr(fk, "table", "other") def test_foreign_key_equality_and_hash_include_actions(): @@ -616,9 +625,9 @@ def test_create_table_mixed_foreign_keys_list(fresh_db): # 3.x accepted a mix of ForeignKey objects, tuples and bare column # strings in foreign_keys= (ForeignKey was a namedtuple, so it passed # the tuple check) - keep accepting the mix - fresh_db["authors"].insert({"id": 1}, pk="id") - fresh_db["publishers"].insert({"id": 1}, pk="id") - fresh_db["books"].create( + fresh_db.table("authors").insert({"id": 1}, pk="id") + fresh_db.table("publishers").insert({"id": 1}, pk="id") + fresh_db.table("books").create( {"id": int, "author_id": int, "publisher_id": int}, pk="id", foreign_keys=[ @@ -626,14 +635,14 @@ def test_create_table_mixed_foreign_keys_list(fresh_db): ("publisher_id", "publishers", "id"), ], ) - fks = {fk.column: fk.other_table for fk in fresh_db["books"].foreign_keys} + fks = {fk.column: fk.other_table for fk in fresh_db.table("books").foreign_keys} assert fks == {"author_id": "authors", "publisher_id": "publishers"} def test_create_table_mixed_foreign_keys_with_string(fresh_db): - fresh_db["authors"].insert({"id": 1}, pk="id") - fresh_db["publishers"].insert({"id": 1}, pk="id") - fresh_db["books"].create( + fresh_db.table("authors").insert({"id": 1}, pk="id") + fresh_db.table("publishers").insert({"id": 1}, pk="id") + fresh_db.table("books").create( {"id": int, "author_id": int, "publisher_id": int}, pk="id", foreign_keys=[ @@ -641,15 +650,15 @@ def test_create_table_mixed_foreign_keys_with_string(fresh_db): ("publisher_id", "publishers", "id"), ], ) - fks = {fk.column: fk.other_table for fk in fresh_db["books"].foreign_keys} + fks = {fk.column: fk.other_table for fk in fresh_db.table("books").foreign_keys} assert fks == {"author_id": "authors", "publisher_id": "publishers"} def test_add_foreign_keys_existing_with_different_actions_errors(fresh_db): # Requesting an existing foreign key with different ON DELETE/ON UPDATE # actions was silently skipped, dropping the requested change - fresh_db["authors"].insert({"id": 1}, pk="id") - fresh_db["books"].insert( + fresh_db.table("authors").insert({"id": 1}, pk="id") + fresh_db.table("books").insert( {"id": 1, "author_id": 1}, pk="id", foreign_keys=[("author_id", "authors", "id")], @@ -659,19 +668,21 @@ def test_add_foreign_keys_existing_with_different_actions_errors(fresh_db): [ForeignKey("books", "author_id", "authors", "id", on_delete="CASCADE")] ) assert "ON DELETE" in str(ex.value) - assert fresh_db["books"].foreign_keys[0].on_delete == "NO ACTION" + assert fresh_db.table("books").foreign_keys[0].on_delete == "NO ACTION" def test_add_foreign_keys_identical_existing_is_noop(fresh_db): # An exact match, including actions, is silently skipped so repeated # calls stay idempotent - fresh_db["authors"].insert({"id": 1}, pk="id") - fresh_db["books"].insert({"id": 1, "author_id": 1}, pk="id") - fresh_db["books"].add_foreign_key("author_id", "authors", "id", on_delete="CASCADE") + fresh_db.table("authors").insert({"id": 1}, pk="id") + fresh_db.table("books").insert({"id": 1, "author_id": 1}, pk="id") + fresh_db.table("books").add_foreign_key( + "author_id", "authors", "id", on_delete="CASCADE" + ) fresh_db.add_foreign_keys( [ForeignKey("books", "author_id", "authors", "id", on_delete="CASCADE")] ) - fks = fresh_db["books"].foreign_keys + fks = fresh_db.table("books").foreign_keys assert len(fks) == 1 assert fks[0].on_delete == "CASCADE" @@ -679,13 +690,13 @@ def test_add_foreign_keys_identical_existing_is_noop(fresh_db): def test_add_foreign_keys_compound_column_count_mismatch_errors(fresh_db): # Previously the extra other-column was silently discarded, creating # a single-column foreign key to just ("id") - fresh_db["departments"].insert( + fresh_db.table("departments").insert( {"campus": "north", "code": "cs"}, pk=("campus", "code") ) - fresh_db["courses"].insert({"id": 1, "campus": "north"}, pk="id") + fresh_db.table("courses").insert({"id": 1, "campus": "north"}, pk="id") with pytest.raises(ValueError) as ex: fresh_db.add_foreign_keys( [("courses", ("campus",), "departments", ("campus", "code"))] ) assert "same number of columns" in str(ex.value) - assert fresh_db["courses"].foreign_keys == [] + assert fresh_db.table("courses").foreign_keys == [] diff --git a/tests/test_fts.py b/tests/test_fts.py index 64ec645..04b5bc3 100644 --- a/tests/test_fts.py +++ b/tests/test_fts.py @@ -1,7 +1,9 @@ +from unittest.mock import ANY + import pytest + from sqlite_utils import Database from sqlite_utils.utils import sqlite3 -from unittest.mock import ANY search_records = [ { @@ -18,7 +20,7 @@ search_records = [ def test_enable_fts(fresh_db): - table = fresh_db["searchable"] + table = fresh_db.table("searchable") table.insert_all(search_records) assert ["searchable"] == fresh_db.table_names() table.enable_fts(["text", "country"], fts_version="FTS4") @@ -52,7 +54,7 @@ def test_enable_fts(fresh_db): def test_enable_fts_escape_table_names(fresh_db): # Table names with restricted chars are handled correctly. # colons and dots are restricted characters for table names. - table = fresh_db["http://example.com"] + table = fresh_db.table("http://example.com") table.insert_all(search_records) assert ["http://example.com"] == fresh_db.table_names() table.enable_fts(["text", "country"], fts_version="FTS4") @@ -85,7 +87,7 @@ def test_enable_fts_escape_table_names(fresh_db): def test_search_duplicate_columns_are_deduped(fresh_db): # https://github.com/simonw/sqlite-utils/issues/624 - table = fresh_db["t"] + table = fresh_db.table("t") table.insert_all(search_records) table.enable_fts(["text", "country"], fts_version="FTS4") rows = list(table.search("tanuki", columns=["text", "text"])) @@ -98,20 +100,32 @@ def test_search_duplicate_columns_are_deduped(fresh_db): def test_search_limit_offset(fresh_db): - table = fresh_db["t"] + table = fresh_db.table("t") table.insert_all(search_records) table.enable_fts(["text", "country"], fts_version="FTS4") assert len(list(table.search("are"))) == 2 assert len(list(table.search("are", limit=1))) == 1 - assert list(table.search("are", limit=1, order_by="rowid"))[0]["rowid"] == 1 + assert next(iter(table.search("are", limit=1, order_by="rowid")))["rowid"] == 1 assert ( - list(table.search("are", limit=1, offset=1, order_by="rowid"))[0]["rowid"] == 2 + next(iter(table.search("are", limit=1, offset=1, order_by="rowid")))["rowid"] + == 2 ) +def test_search_offset_without_limit(fresh_db): + table = fresh_db.table("t") + table.insert_all(search_records) + table.enable_fts(["text", "country"], fts_version="FTS4") + assert [row["rowid"] for row in table.search("are", order_by="rowid")] == [1, 2] + assert [ + row["rowid"] for row in table.search("are", offset=1, order_by="rowid") + ] == [2] + assert table.search_sql(offset=1).strip().endswith("limit -1 offset 1") + + @pytest.mark.parametrize("fts_version", ("FTS4", "FTS5")) def test_search_where(fresh_db, fts_version): - table = fresh_db["t"] + table = fresh_db.table("t") table.insert_all(search_records) table.enable_fts(["text", "country"], fts_version=fts_version) results = list( @@ -128,7 +142,7 @@ def test_search_where(fresh_db, fts_version): def test_search_where_args_disallows_query(fresh_db): - table = fresh_db["t"] + table = fresh_db.table("t") with pytest.raises(ValueError) as ex: list( table.search( @@ -142,7 +156,7 @@ def test_search_where_args_disallows_query(fresh_db): def test_search_include_rank(fresh_db): - table = fresh_db["t"] + table = fresh_db.table("t") table.insert_all(search_records) table.enable_fts(["text", "country"], fts_version="FTS5") results = list(table.search("are", include_rank=True)) @@ -168,7 +182,7 @@ def test_search_include_rank(fresh_db): def test_enable_fts_table_names_containing_spaces(fresh_db): - table = fresh_db["test"] + table = fresh_db.table("test") table.insert({"column with spaces": "in its name"}) table.enable_fts(["column with spaces"]) assert [ @@ -182,7 +196,7 @@ def test_enable_fts_table_names_containing_spaces(fresh_db): def test_populate_fts(fresh_db): - table = fresh_db["populatable"] + table = fresh_db.table("populatable") table.insert(search_records[0]) table.enable_fts(["text", "country"], fts_version="FTS4") assert [] == list(table.search("trash pandas")) @@ -203,7 +217,7 @@ def test_populate_fts(fresh_db): def test_populate_fts_escape_table_names(fresh_db): # Restricted characters such as colon and dots should be escaped. - table = fresh_db["http://example.com"] + table = fresh_db.table("http://example.com") table.insert(search_records[0]) table.enable_fts(["text", "country"], fts_version="FTS4") assert [] == list(table.search("trash pandas")) @@ -223,20 +237,20 @@ def test_populate_fts_escape_table_names(fresh_db): @pytest.mark.parametrize("fts_version", ("4", "5")) def test_fts_tokenize(fresh_db, fts_version): - table_name = "searchable_{}".format(fts_version) - table = fresh_db[table_name] + table_name = f"searchable_{fts_version}" + table = fresh_db.table(table_name) table.insert_all(search_records) # Test without porter stemming table.enable_fts( ["text", "country"], - fts_version="FTS{}".format(fts_version), + fts_version=f"FTS{fts_version}", ) assert [] == list(table.search("bite")) # Test WITH stemming table.disable_fts() table.enable_fts( ["text", "country"], - fts_version="FTS{}".format(fts_version), + fts_version=f"FTS{fts_version}", tokenize="porter", ) rows = list(table.search("bite", order_by="rowid")) @@ -249,12 +263,24 @@ def test_fts_tokenize(fresh_db, fts_version): }.items() <= rows[0].items() +def test_fts_tokenize_escaped(fresh_db): + # A malicious tokenize value must not be able to break out of the + # string literal in the CREATE VIRTUAL TABLE statement. + table = fresh_db.table("searchable") + table.insert_all(search_records) + malicious = "porter'); CREATE TABLE injected(x); --" + with pytest.raises(Exception): + table.enable_fts(["text"], tokenize=malicious) + # The injected statement must not have executed + assert "injected" not in fresh_db.table_names() + + def test_optimize_fts(fresh_db): for fts_version in ("4", "5"): - table_name = "searchable_{}".format(fts_version) - table = fresh_db[table_name] + table_name = f"searchable_{fts_version}" + table = fresh_db.table(table_name) table.insert_all(search_records) - table.enable_fts(["text", "country"], fts_version="FTS{}".format(fts_version)) + table.enable_fts(["text", "country"], fts_version=f"FTS{fts_version}") # You can call optimize successfully against the tables OR their _fts equivalents: for table_name in ( "searchable_4", @@ -262,11 +288,11 @@ def test_optimize_fts(fresh_db): "searchable_4_fts", "searchable_5_fts", ): - fresh_db[table_name].optimize() + fresh_db.table(table_name).optimize() def test_enable_fts_with_triggers(fresh_db): - table = fresh_db["searchable"] + table = fresh_db.table("searchable") table.insert(search_records[0]) table.enable_fts(["text", "country"], fts_version="FTS4", create_triggers=True) rows1 = list(table.search("tanuki")) @@ -295,7 +321,7 @@ def test_enable_fts_with_triggers(fresh_db): @pytest.mark.parametrize("create_triggers", [True, False]) def test_disable_fts(fresh_db, create_triggers): - table = fresh_db["searchable"] + table = fresh_db.table("searchable") table.insert(search_records[0]) table.enable_fts(["text", "country"], create_triggers=create_triggers) assert { @@ -310,12 +336,12 @@ def test_disable_fts(fresh_db, create_triggers): expected_triggers = {"searchable_ai", "searchable_ad", "searchable_au"} else: expected_triggers = set() - assert expected_triggers == set( + assert expected_triggers == { r[0] for r in fresh_db.execute( "select name from sqlite_master where type = 'trigger'" ).fetchall() - ) + } # Now run .disable_fts() and confirm it worked table.disable_fts() assert ( @@ -328,7 +354,7 @@ def test_disable_fts(fresh_db, create_triggers): def test_rebuild_fts(fresh_db): - table = fresh_db["searchable"] + table = fresh_db.table("searchable") table.insert(search_records[0]) table.enable_fts(["text", "country"]) # Run a search @@ -354,7 +380,7 @@ def test_rebuild_fts(fresh_db): def test_optimize_and_rebuild_fts_commit(tmpdir, method): path = str(tmpdir / "test.db") db = Database(path) - table = db["searchable"] + table = db.table("searchable") table.insert(search_records[0]) table.enable_fts(["text", "country"]) getattr(table, method)() @@ -364,16 +390,16 @@ def test_optimize_and_rebuild_fts_commit(tmpdir, method): table.insert(search_records[1]) db.close() db2 = Database(path) - assert db2["searchable"].count == 2 + assert db2.table("searchable").count == 2 db2.close() @pytest.mark.parametrize("invalid_table", ["does_not_exist", "not_searchable"]) def test_rebuild_fts_invalid(fresh_db, invalid_table): - fresh_db["not_searchable"].insert({"foo": "bar"}) + fresh_db.table("not_searchable").insert({"foo": "bar"}) # Raise OperationalError on invalid table with pytest.raises(sqlite3.OperationalError): - fresh_db[invalid_table].rebuild_fts() + fresh_db.table(invalid_table).rebuild_fts() @pytest.mark.parametrize("fts_version", ["FTS4", "FTS5"]) @@ -382,15 +408,17 @@ def test_rebuild_removes_junk_docsize_rows(tmpdir, fts_version): path = tmpdir / "test.db" db = Database(str(path), recursive_triggers=False) licenses = [{"key": "apache2", "name": "Apache 2"}, {"key": "bsd", "name": "BSD"}] - db["licenses"].insert_all(licenses, pk="key", replace=True) - db["licenses"].enable_fts(["name"], create_triggers=True, fts_version=fts_version) - assert db["licenses_fts_docsize"].count == 2 + db.table("licenses").insert_all(licenses, pk="key", replace=True) + db.table("licenses").enable_fts( + ["name"], create_triggers=True, fts_version=fts_version + ) + assert db.table("licenses_fts_docsize").count == 2 # Bug: insert with replace increases the number of rows in _docsize: - db["licenses"].insert_all(licenses, pk="key", replace=True) - assert db["licenses_fts_docsize"].count == 4 + db.table("licenses").insert_all(licenses, pk="key", replace=True) + assert db.table("licenses_fts_docsize").count == 4 # rebuild should fix this: - db["licenses_fts"].rebuild_fts() - assert db["licenses_fts_docsize"].count == 2 + db.table("licenses_fts").rebuild_fts() + assert db.table("licenses_fts_docsize").count == 2 @pytest.mark.parametrize( @@ -404,7 +432,7 @@ def test_rebuild_removes_junk_docsize_rows(tmpdir, fts_version): ) def test_enable_fts_replace(kwargs): db = Database(memory=True) - db["books"].insert( + db.table("books").insert( { "id": 1, "title": "Habits of Australian Marsupials", @@ -412,31 +440,31 @@ def test_enable_fts_replace(kwargs): }, pk="id", ) - db["books"].enable_fts(["title", "author"]) - assert not db["books"].triggers - assert db["books_fts"].columns_dict.keys() == {"title", "author"} - assert "FTS5" in db["books_fts"].schema - assert "porter" not in db["books_fts"].schema + db.table("books").enable_fts(["title", "author"]) + assert not db.table("books").triggers + assert db.table("books_fts").columns_dict.keys() == {"title", "author"} + assert "FTS5" in db.table("books_fts").schema + assert "porter" not in db.table("books_fts").schema # Now modify the FTS configuration should_have_changed_columns = "columns" in kwargs if "columns" not in kwargs: kwargs["columns"] = ["title", "author"] - db["books"].enable_fts(**kwargs, replace=True) + db.table("books").enable_fts(**kwargs, replace=True) # Check that the new configuration is correct if should_have_changed_columns: - assert db["books_fts"].columns_dict.keys() == set(["title"]) + assert db.table("books_fts").columns_dict.keys() == {"title"} if "create_triggers" in kwargs: - assert db["books"].triggers + assert db.table("books").triggers if "fts_version" in kwargs: - assert "FTS4" in db["books_fts"].schema + assert "FTS4" in db.table("books_fts").schema if "tokenize" in kwargs: - assert "porter" in db["books_fts"].schema + assert "porter" in db.table("books_fts").schema def test_enable_fts_replace_does_nothing_if_args_the_same(): queries = [] db = Database(memory=True, tracer=lambda sql, params: queries.append((sql, params))) - db["books"].insert( + db.table("books").insert( { "id": 1, "title": "Habits of Australian Marsupials", @@ -444,17 +472,19 @@ def test_enable_fts_replace_does_nothing_if_args_the_same(): }, pk="id", ) - db["books"].enable_fts(["title", "author"], create_triggers=True) + db.table("books").enable_fts(["title", "author"], create_triggers=True) queries.clear() # Running that again shouldn't run much SQL: - db["books"].enable_fts(["title", "author"], create_triggers=True, replace=True) + db.table("books").enable_fts( + ["title", "author"], create_triggers=True, replace=True + ) # The only SQL that executed should be select statements assert all(q[0].startswith("select ") for q in queries) def test_enable_fts_replace_handles_legacy_bracket_quoted_content_table(): db = Database(memory=True) - db["books"].insert( + db.table("books").insert( { "id": 1, "title": "Habits of Australian Marsupials", @@ -469,10 +499,10 @@ def test_enable_fts_replace_handles_legacy_bracket_quoted_content_table(): ); """) - db["books"].enable_fts(["title", "author"], replace=True) + db.table("books").enable_fts(["title", "author"], replace=True) - assert db["books_fts"].columns_dict.keys() == {"title", "author"} - assert 'content="books"' in db["books_fts"].schema + assert db.table("books_fts").columns_dict.keys() == {"title", "author"} + assert 'content="books"' in db.table("books_fts").schema def test_view_has_no_enable_fts(): @@ -480,7 +510,7 @@ def test_view_has_no_enable_fts(): db.create_view("hello", "select 1 + 1") # Views deliberately do not have an enable_fts() method with pytest.raises(AttributeError): - db["hello"].enable_fts() # type: ignore[union-attr] + db.view("hello").enable_fts() # type: ignore[attr-defined] @pytest.mark.parametrize( @@ -686,14 +716,14 @@ def test_view_has_no_enable_fts(): ) def test_search_sql(kwargs, fts, expected): db = Database(memory=True) - db["books"].insert( + db.table("books").insert( { "title": "Habits of Australian Marsupials", "author": "Marlee Hawkins", } ) - db["books"].enable_fts(["title", "author"], fts_version=fts) - sql = db["books"].search_sql(**kwargs) + db.table("books").enable_fts(["title", "author"], fts_version=fts) + sql = db.table("books").search_sql(**kwargs) assert sql == expected @@ -714,7 +744,7 @@ def test_search_sql(kwargs, fts, expected): ), ) def test_quote_fts_query(fresh_db, input, expected): - table = fresh_db["searchable"] + table = fresh_db.table("searchable") table.insert_all(search_records) table.enable_fts(["text", "country"]) quoted = fresh_db.quote_fts(input) @@ -724,7 +754,7 @@ def test_quote_fts_query(fresh_db, input, expected): def test_search_quote(fresh_db): - table = fresh_db["searchable"] + table = fresh_db.table("searchable") table.insert_all(search_records) table.enable_fts(["text", "country"]) query = "cat's" @@ -737,10 +767,11 @@ def test_search_quote(fresh_db): def test_enable_fts_cli_on_view_errors(tmpdir): db_path = str(tmpdir / "test.db") db = Database(db_path) - db["t"].insert({"text": "hello"}) + db.table("t").insert({"text": "hello"}) db.create_view("v", "select * from t") db.close() from click.testing import CliRunner + from sqlite_utils import cli as cli_module result = CliRunner().invoke(cli_module.cli, ["enable-fts", db_path, "v", "text"]) diff --git a/tests/test_get.py b/tests/test_get.py index 63c4a2e..5e29506 100644 --- a/tests/test_get.py +++ b/tests/test_get.py @@ -1,16 +1,17 @@ import pytest + from sqlite_utils.db import NotFoundError def test_get_rowid(fresh_db): - dogs = fresh_db["dogs"] + dogs = fresh_db.table("dogs") cleo = {"name": "Cleo", "age": 4} row_id = dogs.insert(cleo).last_rowid assert cleo == dogs.get(row_id) def test_get_primary_key(fresh_db): - dogs = fresh_db["dogs"] + dogs = fresh_db.table("dogs") cleo = {"name": "Cleo", "age": 4, "id": 5} last_pk = dogs.insert(cleo, pk="id").last_pk assert 5 == last_pk @@ -22,10 +23,10 @@ def test_get_primary_key(fresh_db): [(100, None), (None, None), ((1, 2), "Need 1 primary key value"), ("2", None)], ) def test_get_not_found(argument, expected_msg, fresh_db): - fresh_db["dogs"].insert( + fresh_db.table("dogs").insert( {"id": 1, "name": "Cleo", "age": 4, "is_good": True}, pk="id" ) with pytest.raises(NotFoundError) as excinfo: - fresh_db["dogs"].get(argument) + fresh_db.table("dogs").get(argument) if expected_msg is not None: assert expected_msg == excinfo.value.args[0] diff --git a/tests/test_gis.py b/tests/test_gis.py index f39554e..592af4c 100644 --- a/tests/test_gis.py +++ b/tests/test_gis.py @@ -1,7 +1,8 @@ import json -import pytest +import pytest from click.testing import CliRunner + from sqlite_utils.cli import cli from sqlite_utils.db import Database from sqlite_utils.utils import find_spatialite, sqlite3 @@ -44,7 +45,7 @@ def test_add_geometry_column(): coord_dimension="XY", ) - assert db["geometry_columns"].get(["locations", "geometry"]) == { + assert db.table("geometry_columns").get(["locations", "geometry"]) == { "f_table_name": "locations", "f_geometry_column": "geometry", "geometry_type": 1, # point @@ -104,7 +105,7 @@ def test_query_load_extension(use_spatialite_shortcut): [ ":memory:", "select spatialite_version()", - "--load-extension={}".format(load_extension), + f"--load-extension={load_extension}", ], ) assert result.exit_code == 0, result.stdout @@ -132,7 +133,7 @@ def test_cli_add_geometry_column(tmpdir): db = Database(str(db_path)) db.init_spatialite() - table = db["locations"].create({"name": str}) + table = db.table("locations").create({"name": str}) result = CliRunner().invoke( cli, @@ -148,7 +149,7 @@ def test_cli_add_geometry_column(tmpdir): assert result.exit_code == 0 - assert db["geometry_columns"].get(["locations", "geometry"]) == { + assert db.table("geometry_columns").get(["locations", "geometry"]) == { "f_table_name": "locations", "f_geometry_column": "geometry", "geometry_type": 1, # point @@ -163,7 +164,7 @@ def test_cli_add_geometry_column_options(tmpdir): db_path = tmpdir / "spatial.db" db = Database(str(db_path)) db.init_spatialite() - table = db["locations"].create({"name": str}) + table = db.table("locations").create({"name": str}) result = CliRunner().invoke( cli, @@ -182,7 +183,7 @@ def test_cli_add_geometry_column_options(tmpdir): assert result.exit_code == 0 - assert db["geometry_columns"].get(["locations", "geometry"]) == { + assert db.table("geometry_columns").get(["locations", "geometry"]) == { "f_table_name": "locations", "f_geometry_column": "geometry", "geometry_type": 3, # polygon @@ -201,7 +202,7 @@ def test_cli_add_geometry_column_invalid_type(tmpdir): db = Database(str(db_path)) db.init_spatialite() - table = db["locations"].create({"name": str}) + table = db.table("locations").create({"name": str}) result = CliRunner().invoke( cli, @@ -224,7 +225,7 @@ def test_cli_create_spatial_index(tmpdir): db = Database(str(db_path)) db.init_spatialite() - table = db["locations"].create({"name": str}) + table = db.table("locations").create({"name": str}) table.add_geometry_column("geometry", "POINT") result = CliRunner().invoke( diff --git a/tests/test_hypothesis.py b/tests/test_hypothesis.py index f12f865..d017f1f 100644 --- a/tests/test_hypothesis.py +++ b/tests/test_hypothesis.py @@ -1,5 +1,6 @@ -from hypothesis import given import hypothesis.strategies as st +from hypothesis import given + import sqlite_utils @@ -10,8 +11,8 @@ def test_roundtrip_integers(integer): row = { "integer": integer, } - db["test"].insert(row) - assert list(db["test"].rows) == [row] + db.table("test").insert(row) + assert list(db.table("test").rows) == [row] @given(st.text()) @@ -20,8 +21,8 @@ def test_roundtrip_text(text): row = { "text": text, } - db["test"].insert(row) - assert list(db["test"].rows) == [row] + db.table("test").insert(row) + assert list(db.table("test").rows) == [row] @given(st.binary(max_size=1024 * 1024)) @@ -30,8 +31,8 @@ def test_roundtrip_binary(binary): row = { "binary": binary, } - db["test"].insert(row) - assert list(db["test"].rows) == [row] + db.table("test").insert(row) + assert list(db.table("test").rows) == [row] @given(st.floats(allow_nan=False)) @@ -40,5 +41,5 @@ def test_roundtrip_floats(floats): row = { "floats": floats, } - db["test"].insert(row) - assert list(db["test"].rows) == [row] + db.table("test").insert(row) + assert list(db.table("test").rows) == [row] diff --git a/tests/test_insert_files.py b/tests/test_insert_files.py index 88e49a8..93c4daf 100644 --- a/tests/test_insert_files.py +++ b/tests/test_insert_files.py @@ -1,10 +1,12 @@ -from sqlite_utils import cli, Database -from click.testing import CliRunner import os import pathlib -import pytest import sys +import pytest +from click.testing import CliRunner + +from sqlite_utils import Database, cli + @pytest.mark.parametrize("silent", (False, True)) @pytest.mark.parametrize( @@ -44,7 +46,7 @@ def test_insert_files(silent, pk_args, expected_pks): ) cols = [] for coltype in coltypes: - cols += ["-c", "{}:{}".format(coltype, coltype)] + cols += ["-c", f"{coltype}:{coltype}"] result = runner.invoke( cli.cli, ["insert-files", db_path, "files", str(tmpdir)] @@ -55,7 +57,7 @@ def test_insert_files(silent, pk_args, expected_pks): ) assert result.exit_code == 0, result.stdout db = Database(db_path) - rows_by_path = {r["path"]: r for r in db["files"].rows} + rows_by_path = {r["path"]: r for r in db.table("files").rows} one, two, three = ( rows_by_path["one.txt"], rows_by_path["two.txt"], @@ -112,7 +114,7 @@ def test_insert_files(silent, pk_args, expected_pks): for colname, expected_type in expected_types.items(): for row in (one, two, three): assert isinstance(row[colname], expected_type) - assert set(db["files"].pks) == set(expected_pks) + assert set(db.table("files").pks) == set(expected_pks) @pytest.mark.parametrize( @@ -142,7 +144,7 @@ def test_insert_files_stdin(use_text, encoding, input, expected): ) assert result.exit_code == 0, result.stdout db = Database(db_path) - row = list(db["files"].rows)[0] + row = next(iter(db.table("files").rows)) key = "content" if use_text: key = "content_text" @@ -167,5 +169,5 @@ def test_insert_files_bad_text_encoding_error(): ) assert result.exit_code == 1, result.output assert result.output.strip().startswith( - "Error: Could not read file '{}' as text".format(str(latin.resolve())) + f"Error: Could not read file '{latin.resolve()!s}' as text" ) diff --git a/tests/test_introspect.py b/tests/test_introspect.py index 8b6765d..343424d 100644 --- a/tests/test_introspect.py +++ b/tests/test_introspect.py @@ -1,6 +1,7 @@ -from sqlite_utils.db import Index, View, Database, XIndex, XIndexColumn import pytest +from sqlite_utils.db import Check, Database, Index, Table, View, XIndex, XIndexColumn + def _check_supports_strict(): """Check if SQLite supports strict tables without leaking the database.""" @@ -20,10 +21,10 @@ def test_view_names(fresh_db): def test_table_names_fts4(existing_db): - existing_db["woo"].insert({"title": "Hello"}).enable_fts( + existing_db.table("woo").insert({"title": "Hello"}).enable_fts( ["title"], fts_version="FTS4" ) - existing_db["woo2"].insert({"title": "Hello"}).enable_fts( + existing_db.table("woo2").insert({"title": "Hello"}).enable_fts( ["title"], fts_version="FTS5" ) assert ["woo_fts"] == existing_db.table_names(fts4=True) @@ -31,17 +32,17 @@ def test_table_names_fts4(existing_db): def test_detect_fts(existing_db): - existing_db["woo"].insert({"title": "Hello"}).enable_fts( + existing_db.table("woo").insert({"title": "Hello"}).enable_fts( ["title"], fts_version="FTS4" ) - existing_db["woo2"].insert({"title": "Hello"}).enable_fts( + existing_db.table("woo2").insert({"title": "Hello"}).enable_fts( ["title"], fts_version="FTS5" ) - assert "woo_fts" == existing_db["woo"].detect_fts() - assert "woo_fts" == existing_db["woo_fts"].detect_fts() - assert "woo2_fts" == existing_db["woo2"].detect_fts() - assert "woo2_fts" == existing_db["woo2_fts"].detect_fts() - assert existing_db["foo"].detect_fts() is None + assert "woo_fts" == existing_db.table("woo").detect_fts() + assert "woo_fts" == existing_db.table("woo_fts").detect_fts() + assert "woo2_fts" == existing_db.table("woo2").detect_fts() + assert "woo2_fts" == existing_db.table("woo2_fts").detect_fts() + assert existing_db.table("foo").detect_fts() is None @pytest.mark.parametrize("reverse_order", (True, False)) @@ -51,14 +52,14 @@ def test_detect_fts_similar_tables(fresh_db, reverse_order): if reverse_order: table1, table2 = table2, table1 - fresh_db[table1].insert({"title": "Hello"}).enable_fts( + fresh_db.table(table1).insert({"title": "Hello"}).enable_fts( ["title"], fts_version="FTS4" ) - fresh_db[table2].insert({"title": "Hello"}).enable_fts( + fresh_db.table(table2).insert({"title": "Hello"}).enable_fts( ["title"], fts_version="FTS4" ) - assert fresh_db[table1].detect_fts() == "{}_fts".format(table1) - assert fresh_db[table2].detect_fts() == "{}_fts".format(table2) + assert fresh_db.table(table1).detect_fts() == f"{table1}_fts" + assert fresh_db.table(table2).detect_fts() == f"{table2}_fts" def test_tables(existing_db): @@ -76,26 +77,34 @@ def test_views(fresh_db): assert view.columns_dict == {"1": str} +def test_getitem_returns_table_or_view(fresh_db): + fresh_db.table("items").insert({"id": 1}, pk="id") + fresh_db.create_view("item_ids", "select id from items") + + assert isinstance(fresh_db["items"], Table) + assert isinstance(fresh_db["item_ids"], View) + + def test_count(existing_db): - assert existing_db["foo"].count == 3 - assert existing_db["foo"].count_where() == 3 - assert existing_db["foo"].execute_count() == 3 + assert existing_db.table("foo").count == 3 + assert existing_db.table("foo").count_where() == 3 + assert existing_db.table("foo").execute_count() == 3 def test_count_where(existing_db): - assert existing_db["foo"].count_where("text != ?", ["two"]) == 2 - assert existing_db["foo"].count_where("text != :t", {"t": "two"}) == 2 + assert existing_db.table("foo").count_where("text != ?", ["two"]) == 2 + assert existing_db.table("foo").count_where("text != :t", {"t": "two"}) == 2 def test_columns(existing_db): - table = existing_db["foo"] + table = existing_db.table("foo") assert [{"name": "text", "type": "TEXT"}] == [ {"name": col.name, "type": col.type} for col in table.columns ] def test_table_schema(existing_db): - assert existing_db["foo"].schema == "CREATE TABLE foo (text TEXT)" + assert existing_db.table("foo").schema == "CREATE TABLE foo (text TEXT)" def test_database_schema(existing_db): @@ -103,9 +112,9 @@ def test_database_schema(existing_db): def test_table_repr(fresh_db): - table = fresh_db["dogs"].insert({"name": "Cleo", "age": 4}) + table = fresh_db.table("dogs").insert({"name": "Cleo", "age": 4}) assert "
" == repr(table) - assert "
" == repr(fresh_db["cats"]) + assert "
" == repr(fresh_db.table("cats")) def test_indexes(fresh_db): @@ -124,7 +133,7 @@ def test_indexes(fresh_db): columns=["c2", "c3"], ), Index(seq=1, name="Gosh_c1", unique=0, origin="c", partial=0, columns=["c1"]), - ] == fresh_db["Gosh"].indexes + ] == fresh_db.table("Gosh").indexes def test_xindexes(fresh_db): @@ -133,7 +142,7 @@ def test_xindexes(fresh_db): create index Gosh_c1 on Gosh(c1); create index Gosh_c2c3 on Gosh(c2, c3 desc); """) - assert fresh_db["Gosh"].xindexes == [ + assert fresh_db.table("Gosh").xindexes == [ XIndex( name="Gosh_c2c3", columns=[ @@ -152,6 +161,31 @@ def test_xindexes(fresh_db): ] +def test_indexes_with_double_quotes_in_identifiers(fresh_db): + fresh_db['Go"sh'].insert({"id": 1, 'c"1': 2}, pk="id") + fresh_db['Go"sh'].create_index(['c"1']) + assert [(index.name, index.columns) for index in fresh_db['Go"sh'].indexes] == [ + ('idx_Go"sh_c"1', ['c"1']) + ] + assert fresh_db['Go"sh'].xindexes == [ + XIndex( + name='idx_Go"sh_c"1', + columns=[ + XIndexColumn(seqno=0, cid=1, name='c"1', desc=0, coll="BINARY", key=1), + XIndexColumn(seqno=1, cid=-1, name=None, desc=0, coll="BINARY", key=0), + ], + ) + ] + + +def test_transform_table_with_double_quotes_in_identifiers(fresh_db): + fresh_db['Go"sh'].insert({"id": 1, 'c"1': 2, "c2": 3}, pk="id") + fresh_db['Go"sh'].create_index(['c"1']) + fresh_db['Go"sh'].transform(types={"c2": str}) + assert fresh_db['Go"sh'].columns_dict["c2"] is str + assert [index.columns for index in fresh_db['Go"sh'].indexes] == [['c"1']] + + @pytest.mark.parametrize( "column,expected_table_guess", ( @@ -165,30 +199,55 @@ def test_xindexes(fresh_db): def test_guess_foreign_table(fresh_db, column, expected_table_guess): fresh_db.create_table("authors", {"name": str}) fresh_db.create_table("genre", {"name": str}) - assert expected_table_guess == fresh_db["books"].guess_foreign_table(column) + assert expected_table_guess == fresh_db.table("books").guess_foreign_table(column) @pytest.mark.parametrize( "pk,expected", ((None, ["rowid"]), ("id", ["id"]), (["id", "id2"], ["id", "id2"])) ) def test_pks(fresh_db, pk, expected): - fresh_db["foo"].insert_all([{"id": 1, "id2": 2}], pk=pk) - assert expected == fresh_db["foo"].pks + fresh_db.table("foo").insert_all([{"id": 1, "id2": 2}], pk=pk) + assert expected == fresh_db.table("foo").pks + + +def test_checks(fresh_db): + fresh_db.execute(""" + CREATE TABLE scores ( + score INTEGER CONSTRAINT positive CHECK(score > 0), + maximum INTEGER, + CONSTRAINT within_maximum CHECK(score <= maximum) + ) + """) + scores = fresh_db.table("scores") + expected_column = Check("score > 0", name="positive", column="score") + expected_table = Check("score <= maximum", name="within_maximum") + assert scores.checks == [expected_column, expected_table] + assert scores.column_checks == {"score": [expected_column]} + assert scores.table_checks == [expected_table] + assert scores.checks[0].sql == "CONSTRAINT positive CHECK(score > 0)" + + +def test_checks_nonexistent_and_virtual_tables(fresh_db): + assert fresh_db.table("does_not_exist").checks == [] + fresh_db.table("searchable").insert({"text": "hello"}).enable_fts( + ["text"], fts_version="FTS5" + ) + assert fresh_db.table("searchable_fts").checks == [] def test_triggers_and_triggers_dict(fresh_db): assert [] == fresh_db.triggers - authors = fresh_db["authors"] + authors = fresh_db.table("authors") authors.insert_all( [ {"name": "Frank Herbert", "famous_works": "Dune"}, {"name": "Neal Stephenson", "famous_works": "Cryptonomicon"}, ] ) - fresh_db["other"].insert({"foo": "bar"}) + fresh_db.table("other").insert({"foo": "bar"}) assert authors.triggers == [] assert authors.triggers_dict == {} - assert fresh_db["other"].triggers == [] + assert fresh_db.table("other").triggers == [] assert fresh_db.triggers_dict == {} authors.enable_fts( ["name", "famous_works"], fts_version="FTS4", create_triggers=True @@ -200,7 +259,7 @@ def test_triggers_and_triggers_dict(fresh_db): } assert expected_triggers == {(t.name, t.table) for t in fresh_db.triggers} assert expected_triggers == { - (t.name, t.table) for t in fresh_db["authors"].triggers + (t.name, t.table) for t in fresh_db.table("authors").triggers } expected_triggers = { "authors_ai": ( @@ -220,13 +279,13 @@ def test_triggers_and_triggers_dict(fresh_db): ), } assert authors.triggers_dict == expected_triggers - assert fresh_db["other"].triggers == [] - assert fresh_db["other"].triggers_dict == {} + assert fresh_db.table("other").triggers == [] + assert fresh_db.table("other").triggers_dict == {} assert fresh_db.triggers_dict == expected_triggers def test_has_counts_triggers(fresh_db): - authors = fresh_db["authors"] + authors = fresh_db.table("authors") authors.insert({"name": "Frank Herbert"}) assert not authors.has_counts_triggers authors.enable_counts() @@ -275,14 +334,14 @@ def test_has_counts_triggers(fresh_db): ) def test_virtual_table_using(fresh_db, sql, expected_name, expected_using): fresh_db.execute(sql) - assert fresh_db[expected_name].virtual_table_using == expected_using + assert fresh_db.table(expected_name).virtual_table_using == expected_using def test_use_rowid(fresh_db): - fresh_db["rowid_table"].insert({"name": "Cleo"}) - fresh_db["regular_table"].insert({"id": 1, "name": "Cleo"}, pk="id") - assert fresh_db["rowid_table"].use_rowid - assert not fresh_db["regular_table"].use_rowid + fresh_db.table("rowid_table").insert({"name": "Cleo"}) + fresh_db.table("regular_table").insert({"id": 1, "name": "Cleo"}, pk="id") + assert fresh_db.table("rowid_table").use_rowid + assert not fresh_db.table("regular_table").use_rowid @pytest.mark.skipif( @@ -301,7 +360,7 @@ def test_use_rowid(fresh_db): ) def test_table_strict(fresh_db, create_table, expected_strict): fresh_db.execute(create_table) - table = fresh_db["t"] + table = fresh_db.table("t") assert table.strict == expected_strict @@ -311,28 +370,54 @@ def test_table_strict(fresh_db, create_table, expected_strict): 1, 1.3, "foo", + "O'Brien", True, b"binary", ), ) def test_table_default_values(fresh_db, value): - fresh_db["default_values"].insert( + fresh_db.table("default_values").insert( {"nodefault": 1, "value": value}, defaults={"value": value} ) - default_values = fresh_db["default_values"].default_values + default_values = fresh_db.table("default_values").default_values assert default_values == {"value": value} +def test_table_default_values_escaped_quotes(fresh_db): + # SQLite stores string defaults with single quotes doubled, so + # introspection needs to unescape them again + fresh_db.execute( + "create table t (id integer primary key, name text default 'O''Brien')" + ) + assert "default 'O''Brien'" in fresh_db.table("t").schema + assert fresh_db.table("t").default_values == {"name": "O'Brien"} + + +def test_table_default_values_keyword_literals(fresh_db): + fresh_db.execute( + "create table t (" + "enabled integer default TRUE, " + "disabled integer default false, " + "nullable text default NULL" + ")" + ) + assert fresh_db.table("t").default_values == { + "enabled": True, + "disabled": False, + "nullable": None, + } + + def test_pks_use_primary_key_declaration_order(fresh_db): # PRIMARY KEY (a, b) declared against columns stored in order (b, a) - # pks must follow the declaration order, which is what SQLite uses to # resolve implicit foreign key references and compound pk lookups fresh_db.execute("create table t (b text, a text, primary key (a, b))") - assert fresh_db["t"].pks == ["a", "b"] + assert fresh_db.table("t").pks == ["a", "b"] def test_transform_preserves_compound_pk_declaration_order(fresh_db): fresh_db.execute("create table t (a text, b text, c text, primary key (b, a))") - fresh_db["t"].transform(drop={"c"}) - assert fresh_db["t"].pks == ["b", "a"] - assert 'PRIMARY KEY ("b", "a")' in fresh_db["t"].schema + fresh_db.table("t").transform(drop={"c"}) + assert fresh_db.table("t").pks == ["b", "a"] + assert 'PRIMARY KEY ("b", "a")' in fresh_db.table("t").schema diff --git a/tests/test_list_mode.py b/tests/test_list_mode.py index 746c9c1..75f5a76 100644 --- a/tests/test_list_mode.py +++ b/tests/test_list_mode.py @@ -3,6 +3,7 @@ Tests for list-based iteration in insert_all and upsert_all """ import pytest + from sqlite_utils import Database @@ -18,9 +19,9 @@ def test_insert_all_list_mode_basic(): yield [2, "Bob", 25] yield [3, "Charlie", 35] - db["people"].insert_all(data_generator()) + db.table("people").insert_all(data_generator()) - rows = list(db["people"].rows) + rows = list(db.table("people").rows) assert len(rows) == 3 assert rows[0] == {"id": 1, "name": "Alice", "age": 30} assert rows[1] == {"id": 2, "name": "Bob", "age": 25} @@ -36,10 +37,10 @@ def test_insert_all_list_mode_with_pk(): yield [1, "Alice", 95] yield [2, "Bob", 87] - db["scores"].insert_all(data_generator(), pk="id") + db.table("scores").insert_all(data_generator(), pk="id") - assert db["scores"].pks == ["id"] - rows = list(db["scores"].rows) + assert db.table("scores").pks == ["id"] + rows = list(db.table("scores").rows) assert len(rows) == 2 @@ -53,7 +54,7 @@ def test_upsert_all_list_mode(): yield [1, "Alice", 100] yield [2, "Bob", 200] - db["data"].insert_all(initial_data(), pk="id") + db.table("data").insert_all(initial_data(), pk="id") # Upsert with some updates and new records def upsert_data(): @@ -61,9 +62,9 @@ def test_upsert_all_list_mode(): yield [1, "Alice", 150] # Update existing yield [3, "Charlie", 300] # Insert new - db["data"].upsert_all(upsert_data(), pk="id") + db.table("data").upsert_all(upsert_data(), pk="id") - rows = list(db["data"].rows_where(order_by="id")) + rows = list(db.table("data").rows_where(order_by="id")) assert len(rows) == 3 assert rows[0] == {"id": 1, "name": "Alice", "value": 150} assert rows[1] == {"id": 2, "name": "Bob", "value": 200} @@ -80,9 +81,9 @@ def test_list_mode_with_various_types(): yield [2, "Bob", 87.3, False] yield [3, "Charlie", None, True] - db["mixed"].insert_all(data_generator()) + db.table("mixed").insert_all(data_generator()) - rows = list(db["mixed"].rows) + rows = list(db.table("mixed").rows) assert len(rows) == 3 assert rows[0]["score"] == 95.5 assert rows[1]["active"] == 0 # SQLite stores boolean as int @@ -98,7 +99,7 @@ def test_list_mode_error_non_string_columns(): yield ["a", "b", "c"] with pytest.raises(ValueError, match="must be a list of column name strings"): - db["bad"].insert_all(bad_data()) + db.table("bad").insert_all(bad_data()) # type: ignore[arg-type] def test_list_mode_error_mixed_types(): @@ -110,7 +111,7 @@ def test_list_mode_error_mixed_types(): yield {"id": 1, "name": "Alice"} # Should be a list, not dict with pytest.raises(ValueError, match="must also be lists"): - db["bad"].insert_all(bad_data()) + db.table("bad").insert_all(bad_data()) # type: ignore[arg-type] def test_list_mode_empty_after_headers(): @@ -121,9 +122,9 @@ def test_list_mode_empty_after_headers(): yield ["id", "name", "age"] # No data rows - result = db["people"].insert_all(data_generator()) + result = db.table("people").insert_all(data_generator()) assert result is not None - assert not db["people"].exists() + assert not db.table("people").exists() def test_list_mode_batch_processing(): @@ -135,7 +136,7 @@ def test_list_mode_batch_processing(): for i in range(1000): yield [i, f"value_{i}"] - db["large"].insert_all(large_data(), batch_size=100) + db.table("large").insert_all(large_data(), batch_size=100) count = db.execute("SELECT COUNT(*) as c FROM large").fetchone()[0] assert count == 1000 @@ -151,9 +152,9 @@ def test_list_mode_shorter_rows(): yield [2, "Bob"] # Missing age and city yield [3, "Charlie", 35] # Missing city - db["people"].insert_all(data_generator()) + db.table("people").insert_all(data_generator()) - rows = list(db["people"].rows_where(order_by="id")) + rows = list(db.table("people").rows_where(order_by="id")) assert rows[0] == {"id": 1, "name": "Alice", "age": 30, "city": "NYC"} assert rows[1] == {"id": 2, "name": "Bob", "age": None, "city": None} assert rows[2] == {"id": 3, "name": "Charlie", "age": 35, "city": None} @@ -169,9 +170,9 @@ def test_backwards_compatibility_dict_mode(): {"id": 2, "name": "Bob", "age": 25}, ] - db["people"].insert_all(data) + db.table("people").insert_all(data) - rows = list(db["people"].rows) + rows = list(db.table("people").rows) assert len(rows) == 2 assert rows[0] == {"id": 1, "name": "Alice", "age": 30} @@ -188,9 +189,9 @@ def test_insert_all_tuple_mode_basic(): yield (2, "Bob", 25) yield (3, "Charlie", 35) - db["people"].insert_all(data_generator()) + db.table("people").insert_all(data_generator()) - rows = list(db["people"].rows) + rows = list(db.table("people").rows) assert len(rows) == 3 assert rows[0] == {"id": 1, "name": "Alice", "age": 30} assert rows[1] == {"id": 2, "name": "Bob", "age": 25} @@ -210,9 +211,9 @@ def test_insert_all_mixed_list_tuple(): yield [3, "Charlie", 35] yield (4, "Diana", 40) - db["people"].insert_all(data_generator()) + db.table("people").insert_all(data_generator()) - rows = list(db["people"].rows) + rows = list(db.table("people").rows) assert len(rows) == 4 assert rows[0] == {"id": 1, "name": "Alice", "age": 30} assert rows[1] == {"id": 2, "name": "Bob", "age": 25} @@ -230,7 +231,7 @@ def test_upsert_all_tuple_mode(): yield (1, "Alice", 100) yield (2, "Bob", 200) - db["data"].insert_all(initial_data(), pk="id") + db.table("data").insert_all(initial_data(), pk="id") # Upsert with tuples def upsert_data(): @@ -238,9 +239,9 @@ def test_upsert_all_tuple_mode(): yield (1, "Alice", 150) # Update existing yield (3, "Charlie", 300) # Insert new - db["data"].upsert_all(upsert_data(), pk="id") + db.table("data").upsert_all(upsert_data(), pk="id") - rows = list(db["data"].rows_where(order_by="id")) + rows = list(db.table("data").rows_where(order_by="id")) assert len(rows) == 3 assert rows[0] == {"id": 1, "name": "Alice", "value": 150} assert rows[1] == {"id": 2, "name": "Bob", "value": 200} @@ -257,9 +258,9 @@ def test_tuple_mode_shorter_rows(): yield 2, "Bob" # Missing age and city yield 3, "Charlie", 35 # Missing city - db["people"].insert_all(data_generator()) + db.table("people").insert_all(data_generator()) - rows = list(db["people"].rows_where(order_by="id")) + rows = list(db.table("people").rows_where(order_by="id")) assert rows[0] == {"id": 1, "name": "Alice", "age": 30, "city": "NYC"} assert rows[1] == {"id": 2, "name": "Bob", "age": None, "city": None} assert rows[2] == {"id": 3, "name": "Charlie", "age": 35, "city": None} @@ -270,18 +271,18 @@ def test_list_mode_single_record_upsert_last_pk(): db = Database(memory=True) # Create table first - db["data"].insert({"id": 1, "name": "Alice", "value": 100}, pk="id") + db.table("data").insert({"id": 1, "name": "Alice", "value": 100}, pk="id") # Now upsert a single record using list mode def upsert_data(): yield ["id", "name", "value"] yield [1, "Alice", 150] # Update existing - table = db["data"] + table = db.table("data") table.upsert_all(upsert_data(), pk="id") # Verify the data was updated - rows = list(db["data"].rows) + rows = list(db.table("data").rows) assert rows == [{"id": 1, "name": "Alice", "value": 150}] # Verify last_pk is populated correctly diff --git a/tests/test_lookup.py b/tests/test_lookup.py index da4f18b..f96cfef 100644 --- a/tests/test_lookup.py +++ b/tests/test_lookup.py @@ -1,9 +1,10 @@ -from sqlite_utils.db import Index import pytest +from sqlite_utils.db import Index + def test_lookup_new_table(fresh_db): - species = fresh_db["species"] + species = fresh_db.table("species") palm_id = species.lookup({"name": "Palm"}) oak_id = species.lookup({"name": "Oak"}) cherry_id = species.lookup({"name": "Cherry"}) @@ -25,7 +26,7 @@ def test_lookup_new_table(fresh_db): def test_lookup_new_table_compound_key(fresh_db): - species = fresh_db["species"] + species = fresh_db.table("species") palm_id = species.lookup({"name": "Palm", "type": "Tree"}) oak_id = species.lookup({"name": "Oak", "type": "Tree"}) assert palm_id == species.lookup({"name": "Palm", "type": "Tree"}) @@ -69,7 +70,7 @@ def test_lookup_fails_if_constraint_cannot_be_added(fresh_db): def test_lookup_with_extra_values(fresh_db): - species = fresh_db["species"] + species = fresh_db.table("species") id = species.lookup({"name": "Palm", "type": "Tree"}, {"first_seen": "2020-01-01"}) assert species.get(id) == { "id": 1, @@ -89,9 +90,9 @@ def test_lookup_with_extra_values(fresh_db): def test_lookup_with_extra_insert_parameters(fresh_db): - other_table = fresh_db["other_table"] + other_table = fresh_db.table("other_table") other_table.insert({"id": 1, "name": "Name"}, pk="id") - species = fresh_db["species"] + species = fresh_db.table("species") id = species.lookup( {"name": "Palm", "type": "Tree"}, { @@ -155,15 +156,15 @@ def test_lookup_with_extra_insert_parameters(fresh_db): @pytest.mark.parametrize("strict", (False, True)) def test_lookup_new_table_strict(fresh_db, strict): - fresh_db["species"].lookup({"name": "Palm"}, strict=strict) - assert fresh_db["species"].strict == strict or not fresh_db.supports_strict + fresh_db.table("species").lookup({"name": "Palm"}, strict=strict) + assert fresh_db.table("species").strict == strict or not fresh_db.supports_strict def test_lookup_null_value_idempotent(fresh_db): # https://github.com/simonw/sqlite-utils/issues/186 # Repeated lookups of a null value should return the same row, # not insert a duplicate row each time - species = fresh_db["species"] + species = fresh_db.table("species") first_id = species.lookup({"name": None}) second_id = species.lookup({"name": None}) assert first_id == second_id @@ -171,7 +172,7 @@ def test_lookup_null_value_idempotent(fresh_db): def test_lookup_compound_key_with_null_idempotent(fresh_db): - species = fresh_db["species"] + species = fresh_db.table("species") palm_id = species.lookup({"name": "Palm", "type": None}) oak_id = species.lookup({"name": "Oak", "type": "Tree"}) assert palm_id == species.lookup({"name": "Palm", "type": None}) diff --git a/tests/test_m2m.py b/tests/test_m2m.py index d613bb9..4dde7e4 100644 --- a/tests/test_m2m.py +++ b/tests/test_m2m.py @@ -1,47 +1,48 @@ -from sqlite_utils.db import ForeignKey, NoObviousTable import pytest +from sqlite_utils.db import ForeignKey, NoObviousTable + def test_insert_m2m_single(fresh_db): - dogs = fresh_db["dogs"] + dogs = fresh_db.table("dogs") dogs.insert({"id": 1, "name": "Cleo"}, pk="id").m2m( "humans", {"id": 1, "name": "Natalie D"}, pk="id" ) assert {"dogs_humans", "humans", "dogs"} == set(fresh_db.table_names()) - humans = fresh_db["humans"] - dogs_humans = fresh_db["dogs_humans"] + humans = fresh_db.table("humans") + dogs_humans = fresh_db.table("dogs_humans") assert [{"id": 1, "name": "Natalie D"}] == list(humans.rows) assert [{"humans_id": 1, "dogs_id": 1}] == list(dogs_humans.rows) def test_insert_m2m_alter(fresh_db): - dogs = fresh_db["dogs"] + dogs = fresh_db.table("dogs") dogs.insert({"id": 1, "name": "Cleo"}, pk="id").m2m( "humans", {"id": 1, "name": "Natalie D"}, pk="id" ) dogs.update(1).m2m( "humans", {"id": 2, "name": "Simon W", "nerd": True}, pk="id", alter=True ) - assert list(fresh_db["humans"].rows) == [ + assert list(fresh_db.table("humans").rows) == [ {"id": 1, "name": "Natalie D", "nerd": None}, {"id": 2, "name": "Simon W", "nerd": 1}, ] - assert list(fresh_db["dogs_humans"].rows) == [ + assert list(fresh_db.table("dogs_humans").rows) == [ {"humans_id": 1, "dogs_id": 1}, {"humans_id": 2, "dogs_id": 1}, ] def test_insert_m2m_list(fresh_db): - dogs = fresh_db["dogs"] + dogs = fresh_db.table("dogs") dogs.insert({"id": 1, "name": "Cleo"}, pk="id").m2m( "humans", [{"id": 1, "name": "Natalie D"}, {"id": 2, "name": "Simon W"}], pk="id", ) assert {"dogs", "humans", "dogs_humans"} == set(fresh_db.table_names()) - humans = fresh_db["humans"] - dogs_humans = fresh_db["dogs_humans"] + humans = fresh_db.table("humans") + dogs_humans = fresh_db.table("dogs_humans") assert [{"humans_id": 1, "dogs_id": 1}, {"humans_id": 2, "dogs_id": 1}] == list( dogs_humans.rows ) @@ -65,10 +66,9 @@ def test_insert_m2m_iterable(fresh_db): iterable_records = ({"id": 1, "name": "Phineas"}, {"id": 2, "name": "Ferb"}) def iterable(): - for record in iterable_records: - yield record + yield from iterable_records - platypuses = fresh_db["platypuses"] + platypuses = fresh_db.table("platypuses") platypuses.insert({"id": 1, "name": "Perry"}, pk="id").m2m( "humans", iterable(), @@ -76,8 +76,8 @@ def test_insert_m2m_iterable(fresh_db): ) assert {"platypuses", "humans", "humans_platypuses"} == set(fresh_db.table_names()) - humans = fresh_db["humans"] - humans_platypuses = fresh_db["humans_platypuses"] + humans = fresh_db.table("humans") + humans_platypuses = fresh_db.table("humans_platypuses") assert [ {"humans_id": 1, "platypuses_id": 1}, {"humans_id": 2, "platypuses_id": 1}, @@ -111,14 +111,14 @@ def test_m2m_with_table_objects(fresh_db): assert expected_tables == set(fresh_db.table_names()) assert dogs.count == 1 assert humans.count == 2 - assert fresh_db["dogs_humans"].count == 2 + assert fresh_db.table("dogs_humans").count == 2 def test_m2m_lookup(fresh_db): people = fresh_db.table("people", pk="id") people.insert({"name": "Wahyu"}).m2m("tags", lookup={"tag": "Coworker"}) - people_tags = fresh_db["people_tags"] - tags = fresh_db["tags"] + people_tags = fresh_db.table("people_tags") + tags = fresh_db.table("tags") assert people_tags.exists() assert tags.exists() assert [ @@ -150,9 +150,9 @@ def test_m2m_explicit_table_name_argument(fresh_db): people.insert({"name": "Wahyu"}).m2m( "tags", lookup={"tag": "Coworker"}, m2m_table="tagged" ) - assert fresh_db["tags"].exists - assert fresh_db["tagged"].exists - assert not fresh_db["people_tags"].exists() + assert fresh_db.table("tags").exists + assert fresh_db.table("tagged").exists + assert not fresh_db.table("people_tags").exists() def test_m2m_table_candidates(fresh_db): @@ -181,25 +181,25 @@ def test_uses_existing_m2m_table_if_exists(fresh_db): # Code should look for an existing table with fks to both tables # and use that if it exists. people = fresh_db.create_table("people", {"id": int, "name": str}, pk="id") - fresh_db["tags"].lookup({"tag": "Coworker"}) + fresh_db.table("tags").lookup({"tag": "Coworker"}) fresh_db.create_table( "tagged", {"people_id": int, "tags_id": int}, foreign_keys=["people_id", "tags_id"], ) people.insert({"name": "Wahyu"}).m2m("tags", lookup={"tag": "Coworker"}) - assert fresh_db["tags"].exists() - assert fresh_db["tagged"].exists() - assert not fresh_db["people_tags"].exists() - assert not fresh_db["tags_people"].exists() - assert [{"people_id": 1, "tags_id": 1}] == list(fresh_db["tagged"].rows) + assert fresh_db.table("tags").exists() + assert fresh_db.table("tagged").exists() + assert not fresh_db.table("people_tags").exists() + assert not fresh_db.table("tags_people").exists() + assert [{"people_id": 1, "tags_id": 1}] == list(fresh_db.table("tagged").rows) def test_requires_explicit_m2m_table_if_multiple_options(fresh_db): # If the code scans for m2m tables and finds more than one candidate # it should require that the m2m_table=x argument is used people = fresh_db.create_table("people", {"id": int, "name": str}, pk="id") - fresh_db["tags"].lookup({"tag": "Coworker"}) + fresh_db.table("tags").lookup({"tag": "Coworker"}) fresh_db.create_table( "tagged", {"people_id": int, "tags_id": int}, diff --git a/tests/test_migrations.py b/tests/test_migrations.py index 04185fc..fa419ec 100644 --- a/tests/test_migrations.py +++ b/tests/test_migrations.py @@ -1,4 +1,5 @@ import pytest + import sqlite_utils from sqlite_utils import Migrations @@ -9,11 +10,11 @@ def migrations(): @migrations() def m001(db): - db["dogs"].insert({"name": "Cleo"}) + db.table("dogs").insert({"name": "Cleo"}) @migrations() def m002(db): - db["cats"].create({"name": str}) + db.table("cats").create({"name": str}) db.execute("insert into dogs (name) values ('Pancakes')") return migrations @@ -27,11 +28,11 @@ def migrations_not_ordered_alphabetically(): @migrations() def m002(db): - db["dogs"].insert({"name": "Cleo"}) + db.table("dogs").insert({"name": "Cleo"}) @migrations() def m001(db): - db["cats"].create({"name": str}) + db.table("cats").create({"name": str}) db.execute("insert into dogs (name) values ('Pancakes')") return migrations @@ -43,7 +44,7 @@ def migrations2(): @migrations() def m001(db): - db["dogs2"].insert({"name": "Cleo"}) + db.table("dogs2").insert({"name": "Cleo"}) return migrations @@ -95,7 +96,7 @@ def test_applied_at_is_a_string(migrations): def test_failing_migration_rolls_back(migrations): @migrations() def m003(db): - db["birds"].create({"name": str}) + db.table("birds").create({"name": str}) db.execute("insert into dogs (name) values ('Dozer')") raise ValueError("boom") @@ -104,7 +105,7 @@ def test_failing_migration_rolls_back(migrations): migrations.apply(db) # m001 and m002 committed before the failure and stay applied assert set(db.table_names()) == {"_sqlite_migrations", "dogs", "cats"} - assert [r["name"] for r in db["dogs"].rows] == ["Cleo", "Pancakes"] + assert [r["name"] for r in db.table("dogs").rows] == ["Cleo", "Pancakes"] assert [m.name for m in migrations.applied(db)] == ["m001", "m002"] # Everything m003 did was rolled back and it is still pending assert [m.name for m in migrations.pending(db)] == ["m003"] @@ -116,11 +117,11 @@ def test_rerun_after_failure_applies_each_migration_once(): @migrations() def m001(db): - db["dogs"].insert({"name": "Cleo"}) + db.table("dogs").insert({"name": "Cleo"}) @migrations() def m002(db): - db["dogs"].insert({"name": "Pancakes"}) + db.table("dogs").insert({"name": "Pancakes"}) if state["fail"]: raise ValueError("boom") @@ -130,7 +131,7 @@ def test_rerun_after_failure_applies_each_migration_once(): state["fail"] = False migrations.apply(db) # m001 must not have been re-applied, m002 applied exactly once - assert [r["name"] for r in db["dogs"].rows] == ["Cleo", "Pancakes"] + assert [r["name"] for r in db.table("dogs").rows] == ["Cleo", "Pancakes"] assert [m.name for m in migrations.applied(db)] == ["m001", "m002"] @@ -141,7 +142,7 @@ def test_non_transactional_migration_allows_vacuum(tmpdir): @migrations() def m001(db): - db["dogs"].insert({"name": "Cleo"}) + db.table("dogs").insert({"name": "Cleo"}) @migrations(transactional=False) def m002(db): @@ -154,10 +155,9 @@ def test_non_transactional_migration_allows_vacuum(tmpdir): def test_apply_composes_inside_outer_transaction(migrations): db = sqlite_utils.Database(memory=True) - with pytest.raises(ZeroDivisionError): - with db.atomic(): - migrations.apply(db) - raise ZeroDivisionError + with pytest.raises(ZeroDivisionError), db.atomic(): + migrations.apply(db) + raise ZeroDivisionError # The outer transaction rolled back, taking the migrations with it assert db.table_names() == [] @@ -185,11 +185,13 @@ def test_apply_composes_inside_outer_transaction(migrations): ) def test_upgrades_sqlite_migrations(migrations, create_table, pk): db = sqlite_utils.Database(memory=True) - db["_sqlite_migrations"].create(create_table, pk=pk) + db.table("_sqlite_migrations").create(create_table, pk=pk) assert db.table_names() == ["_sqlite_migrations"] - assert db["_sqlite_migrations"].pks == ([pk] if isinstance(pk, str) else list(pk)) + assert db.table("_sqlite_migrations").pks == ( + [pk] if isinstance(pk, str) else list(pk) + ) migrations.apply(db) - assert db["_sqlite_migrations"].pks == ["id"] + assert db.table("_sqlite_migrations").pks == ["id"] def test_pending_and_applied_are_read_only(migrations): @@ -227,7 +229,7 @@ def test_stop_before_applied_migration_errors(migrations): assert "m001" in str(ex.value) assert "already been applied" in str(ex.value) # Nothing else was applied - assert not db["cats"].exists() + assert not db.table("cats").exists() def test_stop_before_applied_migration_errors_before_any_apply(migrations): @@ -238,9 +240,9 @@ def test_stop_before_applied_migration_errors_before_any_apply(migrations): @only_second() def m002(db): - db["cats"].create({"name": str}) + db.table("cats").create({"name": str}) only_second.apply(db) # m002 applied, m001 still pending with pytest.raises(ValueError): migrations.apply(db, stop_before="m002") - assert not db["dogs"].exists() + assert not db.table("dogs").exists() diff --git a/tests/test_mutator_transactions.py b/tests/test_mutator_transactions.py new file mode 100644 index 0000000..3f13c6b --- /dev/null +++ b/tests/test_mutator_transactions.py @@ -0,0 +1,154 @@ +import pytest + +from sqlite_utils import Database +from sqlite_utils.utils import sqlite3 + +BASELINE_ROWS = [(1, "one"), (2, "two")] + + +def insert(table): + table.insert({"id": 3, "value": "three"}, pk="id") + + +def insert_all(table): + table.insert_all( + [ + {"id": 3, "value": "three"}, + {"id": 4, "value": "four"}, + ], + pk="id", + batch_size=1, + ) + + +def upsert(table): + table.upsert({"id": 2, "value": "TWO"}, pk="id") + + +def upsert_all(table): + table.upsert_all( + [ + {"id": 2, "value": "TWO"}, + {"id": 3, "value": "three"}, + ], + pk="id", + batch_size=1, + ) + + +def update(table): + table.update(2, {"value": "TWO"}) + + +def delete(table): + table.delete(2) + + +def delete_where(table): + table.delete_where("id > ?", [1]) + + +MUTATOR_CASES = ( + pytest.param( + insert, + [(1, "one"), (2, "two"), (3, "three")], + id="insert", + ), + pytest.param( + insert_all, + [(1, "one"), (2, "two"), (3, "three"), (4, "four")], + id="insert_all", + ), + pytest.param( + upsert, + [(1, "one"), (2, "TWO")], + id="upsert", + ), + pytest.param( + upsert_all, + [(1, "one"), (2, "TWO"), (3, "three")], + id="upsert_all", + ), + pytest.param( + update, + [(1, "one"), (2, "TWO")], + id="update", + ), + pytest.param(delete, [(1, "one")], id="delete"), + pytest.param(delete_where, [(1, "one")], id="delete_where"), +) + + +class RollbackTest(Exception): + pass + + +def seed_database(path): + conn = sqlite3.connect(str(path)) + try: + conn.execute("create table items (id integer primary key, value text)") + conn.executemany("insert into items values (?, ?)", BASELINE_ROWS) + conn.commit() + finally: + conn.close() + return Database(path) + + +def current_rows(db): + return db.conn.execute("select id, value from items order by id").fetchall() + + +def persisted_rows(path): + conn = sqlite3.connect(str(path)) + try: + return conn.execute("select id, value from items order by id").fetchall() + finally: + conn.close() + + +@pytest.mark.parametrize("mutate,expected_rows", MUTATOR_CASES) +def test_mutator_commits_by_default(tmp_path, mutate, expected_rows): + path = tmp_path / "default.db" + db = seed_database(path) + + assert not db.conn.in_transaction + mutate(db.table("items")) + assert current_rows(db) == expected_rows + assert not db.conn.in_transaction + + db.close() + assert persisted_rows(path) == expected_rows + + +@pytest.mark.parametrize("mutate,expected_rows", MUTATOR_CASES) +def test_mutator_commits_with_outer_atomic(tmp_path, mutate, expected_rows): + path = tmp_path / "atomic.db" + db = seed_database(path) + + with db.atomic(): + assert db.conn.in_transaction + mutate(db.table("items")) + assert current_rows(db) == expected_rows + assert db.conn.in_transaction + + assert current_rows(db) == expected_rows + assert not db.conn.in_transaction + db.close() + assert persisted_rows(path) == expected_rows + + +@pytest.mark.parametrize("mutate,expected_rows", MUTATOR_CASES) +def test_mutator_rolls_back_outer_atomic(tmp_path, mutate, expected_rows): + path = tmp_path / "rollback.db" + db = seed_database(path) + + with pytest.raises(RollbackTest), db.atomic(): + mutate(db.table("items")) + assert current_rows(db) == expected_rows + assert db.conn.in_transaction + raise RollbackTest + + assert current_rows(db) == BASELINE_ROWS + assert not db.conn.in_transaction + db.close() + assert persisted_rows(path) == BASELINE_ROWS diff --git a/tests/test_plugins.py b/tests/test_plugins.py index c793e32..ef202be 100644 --- a/tests/test_plugins.py +++ b/tests/test_plugins.py @@ -1,9 +1,12 @@ -from click.testing import CliRunner -import click import importlib -import pytest +import sqlite3 import sys -from sqlite_utils import cli, Database, hookimpl, plugins + +import click +import pytest +from click.testing import CliRunner + +from sqlite_utils import Database, cli, hookimpl, plugins def _supports_pragma_function_list(): @@ -11,7 +14,7 @@ def _supports_pragma_function_list(): try: db.execute("select * from pragma_function_list()") return True - except Exception: + except sqlite3.DatabaseError: return False finally: db.close() diff --git a/tests/test_query.py b/tests/test_query.py index 06847da..ac0d924 100644 --- a/tests/test_query.py +++ b/tests/test_query.py @@ -1,11 +1,12 @@ -import pytest import types +import pytest + from sqlite_utils.utils import sqlite3 def test_query(fresh_db): - fresh_db["dogs"].insert_all([{"name": "Cleo"}, {"name": "Pancakes"}]) + fresh_db.table("dogs").insert_all([{"name": "Cleo"}, {"name": "Pancakes"}]) results = fresh_db.query("select * from dogs order by name desc") assert isinstance(results, types.GeneratorType) assert list(results) == [{"name": "Pancakes"}, {"name": "Cleo"}] @@ -19,13 +20,13 @@ def test_query_executes_eagerly(fresh_db): def test_query_rejects_statements_that_return_no_rows(fresh_db): - fresh_db["dogs"].insert({"name": "Cleo"}) + fresh_db.table("dogs").insert({"name": "Cleo"}) with pytest.raises(ValueError) as ex: fresh_db.query("update dogs set name = 'Cleopaws'") assert "execute()" in str(ex.value) # The rejected update was rolled back, and no transaction is left open assert not fresh_db.conn.in_transaction - assert [row["name"] for row in fresh_db["dogs"].rows] == ["Cleo"] + assert [row["name"] for row in fresh_db.table("dogs").rows] == ["Cleo"] def test_query_rejected_ddl_is_rolled_back(fresh_db): @@ -36,7 +37,7 @@ def test_query_rejected_ddl_is_rolled_back(fresh_db): def test_query_rejected_write_inside_transaction_is_rolled_back(fresh_db): - fresh_db["dogs"].insert({"name": "Cleo"}) + fresh_db.table("dogs").insert({"name": "Cleo"}) fresh_db.begin() fresh_db.execute("insert into dogs (name) values ('Pancakes')") with pytest.raises(ValueError): @@ -44,7 +45,7 @@ def test_query_rejected_write_inside_transaction_is_rolled_back(fresh_db): # The transaction is still open and the earlier insert is intact assert fresh_db.conn.in_transaction fresh_db.commit() - assert [row["name"] for row in fresh_db["dogs"].rows] == ["Cleo", "Pancakes"] + assert [row["name"] for row in fresh_db.table("dogs").rows] == ["Cleo", "Pancakes"] @pytest.mark.parametrize( @@ -76,7 +77,7 @@ def test_query_comment_prefixed_commit_does_not_commit_transaction(fresh_db): # A COMMIT hidden behind a leading comment must not slip past the # keyword check - previously it committed the caller's open # transaction before the ValueError was raised - fresh_db["dogs"].insert({"name": "Cleo"}) + fresh_db.table("dogs").insert({"name": "Cleo"}) fresh_db.begin() fresh_db.execute("insert into dogs (name) values ('Pancakes')") with pytest.raises(ValueError): @@ -84,7 +85,7 @@ def test_query_comment_prefixed_commit_does_not_commit_transaction(fresh_db): # The explicit transaction is still open and can still be rolled back assert fresh_db.conn.in_transaction fresh_db.rollback() - assert [row["name"] for row in fresh_db["dogs"].rows] == ["Cleo"] + assert [row["name"] for row in fresh_db.table("dogs").rows] == ["Cleo"] @pytest.mark.parametrize("sql", ["; COMMIT", "\ufeffCOMMIT"]) @@ -93,7 +94,7 @@ def test_query_prefixed_commit_does_not_commit_transaction(fresh_db, sql): # real token, so the keyword scanner must skip them too - previously # '; COMMIT' slipped past the check and committed the caller's open # transaction before raising OperationalError - fresh_db["dogs"].insert({"name": "Cleo"}) + fresh_db.table("dogs").insert({"name": "Cleo"}) fresh_db.begin() fresh_db.execute("insert into dogs (name) values ('Pancakes')") with pytest.raises(ValueError): @@ -101,7 +102,7 @@ def test_query_prefixed_commit_does_not_commit_transaction(fresh_db, sql): # The explicit transaction is still open and can still be rolled back assert fresh_db.conn.in_transaction fresh_db.rollback() - assert [row["name"] for row in fresh_db["dogs"].rows] == ["Cleo"] + assert [row["name"] for row in fresh_db.table("dogs").rows] == ["Cleo"] def test_query_error_leaves_no_transaction_open(fresh_db): @@ -189,12 +190,12 @@ def test_first_keyword(sql, expected): reason="RETURNING requires SQLite 3.35.0 or higher", ) def test_query_insert_returning(fresh_db): - fresh_db["dogs"].insert({"name": "Cleo"}) + fresh_db.table("dogs").insert({"name": "Cleo"}) rows = list( fresh_db.query("insert into dogs (name) values ('Pancakes') returning name") ) assert rows == [{"name": "Pancakes"}] - assert fresh_db["dogs"].count == 2 + assert fresh_db.table("dogs").count == 2 @pytest.mark.skipif( @@ -206,7 +207,7 @@ def test_query_insert_returning_commits_without_iteration(tmpdir): path = str(tmpdir / "test.db") db = Database(path) - db["dogs"].insert({"name": "Cleo"}) + db.table("dogs").insert({"name": "Cleo"}) # Never iterate over the results db.query("insert into dogs (name) values ('Pancakes') returning name") assert not db.conn.in_transaction @@ -226,7 +227,7 @@ def test_query_insert_returning_partial_iteration_still_commits(tmpdir): path = str(tmpdir / "test.db") db = Database(path) - db["dogs"].insert({"name": "Cleo"}) + db.table("dogs").insert({"name": "Cleo"}) row = next( db.query( "insert into dogs (name) values ('Pancakes'), ('Marnie') returning name" @@ -245,7 +246,7 @@ def test_query_insert_returning_partial_iteration_still_commits(tmpdir): reason="RETURNING requires SQLite 3.35.0 or higher", ) def test_query_insert_returning_respects_explicit_transaction(fresh_db): - fresh_db["dogs"].insert({"name": "Cleo"}) + fresh_db.table("dogs").insert({"name": "Cleo"}) fresh_db.begin() rows = list( fresh_db.query("insert into dogs (name) values ('Pancakes') returning name") @@ -254,13 +255,13 @@ def test_query_insert_returning_respects_explicit_transaction(fresh_db): # Still inside the explicit transaction - not committed assert fresh_db.conn.in_transaction fresh_db.rollback() - assert [row["name"] for row in fresh_db["dogs"].rows] == ["Cleo"] + assert [row["name"] for row in fresh_db.table("dogs").rows] == ["Cleo"] def test_query_duplicate_column_names_are_deduped(fresh_db): # https://github.com/simonw/sqlite-utils/issues/624 - fresh_db["one"].insert({"id": 1, "value": "left"}) - fresh_db["two"].insert({"id": 2, "value": "right"}) + fresh_db.table("one").insert({"id": 1, "value": "left"}) + fresh_db.table("two").insert({"id": 2, "value": "right"}) rows = list( fresh_db.query("select one.id, two.id, one.value, two.value from one, two") ) @@ -276,7 +277,7 @@ def test_query_deduped_column_avoids_existing_names(fresh_db): def test_execute_returning_dicts(fresh_db): # Like db.query() but returns a list, included for backwards compatibility # see https://github.com/simonw/sqlite-utils/issues/290 - fresh_db["test"].insert({"id": 1, "bar": 2}, pk="id") + fresh_db.table("test").insert({"id": 1, "bar": 2}, pk="id") assert fresh_db.execute_returning_dicts("select * from test") == [ {"id": 1, "bar": 2} ] diff --git a/tests/test_recipes.py b/tests/test_recipes.py index a7c7ef7..c6a548c 100644 --- a/tests/test_recipes.py +++ b/tests/test_recipes.py @@ -1,12 +1,14 @@ +import json + +import pytest + from sqlite_utils import recipes from sqlite_utils.utils import sqlite3 -import json -import pytest @pytest.fixture def dates_db(fresh_db): - fresh_db["example"].insert_all( + fresh_db.table("example").insert_all( [ {"id": 1, "dt": "5th October 2019 12:04"}, {"id": 2, "dt": "6th October 2019 00:05:06"}, @@ -19,8 +21,8 @@ def dates_db(fresh_db): def test_parsedate(dates_db): - dates_db["example"].convert("dt", recipes.parsedate) - assert list(dates_db["example"].rows) == [ + dates_db.table("example").convert("dt", recipes.parsedate) + assert list(dates_db.table("example").rows) == [ {"id": 1, "dt": "2019-10-05"}, {"id": 2, "dt": "2019-10-06"}, {"id": 3, "dt": ""}, @@ -29,8 +31,8 @@ def test_parsedate(dates_db): def test_parsedatetime(dates_db): - dates_db["example"].convert("dt", recipes.parsedatetime) - assert list(dates_db["example"].rows) == [ + dates_db.table("example").convert("dt", recipes.parsedatetime) + assert list(dates_db.table("example").rows) == [ {"id": 1, "dt": "2019-10-05T12:04:00"}, {"id": 2, "dt": "2019-10-06T00:05:06"}, {"id": 3, "dt": ""}, @@ -48,16 +50,16 @@ def test_parsedatetime(dates_db): ), ) def test_dayfirst_yearfirst(fresh_db, recipe, kwargs, expected): - fresh_db["example"].insert_all( + fresh_db.table("example").insert_all( [ {"id": 1, "dt": "03/04/05"}, ], pk="id", ) - fresh_db["example"].convert( + fresh_db.table("example").convert( "dt", lambda value: getattr(recipes, recipe)(value, **kwargs) ) - assert list(fresh_db["example"].rows) == [ + assert list(fresh_db.table("example").rows) == [ {"id": 1, "dt": expected}, ] @@ -66,7 +68,7 @@ def test_dayfirst_yearfirst(fresh_db, recipe, kwargs, expected): @pytest.mark.parametrize("fn", ("parsedate", "parsedatetime")) def test_dateparse_errors_raises(fresh_db, fn): """Test that invalid dates raise errors when errors=None""" - fresh_db["example"].insert_all( + fresh_db.table("example").insert_all( [ {"id": 1, "dt": "invalid"}, ], @@ -74,30 +76,32 @@ def test_dateparse_errors_raises(fresh_db, fn): ) # Exception in SQLite callback surfaces as OperationalError with pytest.raises(sqlite3.OperationalError): - fresh_db["example"].convert("dt", lambda value: getattr(recipes, fn)(value)) + fresh_db.table("example").convert( + "dt", lambda value: getattr(recipes, fn)(value) + ) @pytest.mark.parametrize("fn", ("parsedate", "parsedatetime")) @pytest.mark.parametrize("errors", (recipes.SET_NULL, recipes.IGNORE)) def test_dateparse_errors_handled(fresh_db, fn, errors): """Test error handling modes for invalid dates""" - fresh_db["example"].insert_all( + fresh_db.table("example").insert_all( [ {"id": 1, "dt": "invalid"}, ], pk="id", ) - fresh_db["example"].convert( + fresh_db.table("example").convert( "dt", lambda value: getattr(recipes, fn)(value, errors=errors) ) - rows = list(fresh_db["example"].rows) + rows = list(fresh_db.table("example").rows) expected = [{"id": 1, "dt": None if errors is recipes.SET_NULL else "invalid"}] assert rows == expected @pytest.mark.parametrize("delimiter", [None, ";", "-"]) def test_jsonsplit(fresh_db, delimiter): - fresh_db["example"].insert_all( + fresh_db.table("example").insert_all( [ {"id": 1, "tags": (delimiter or ",").join(["foo", "bar"])}, {"id": 2, "tags": (delimiter or ",").join(["bar", "baz"])}, @@ -112,8 +116,8 @@ def test_jsonsplit(fresh_db, delimiter): else: fn = recipes.jsonsplit - fresh_db["example"].convert("tags", fn) - assert list(fresh_db["example"].rows) == [ + fresh_db.table("example").convert("tags", fn) + assert list(fresh_db.table("example").rows) == [ {"id": 1, "tags": '["foo", "bar"]'}, {"id": 2, "tags": '["bar", "baz"]'}, ] @@ -128,7 +132,7 @@ def test_jsonsplit(fresh_db, delimiter): ), ) def test_jsonsplit_type(fresh_db, type, expected): - fresh_db["example"].insert_all( + fresh_db.table("example").insert_all( [ {"id": 1, "records": "1,2,3"}, ], @@ -142,5 +146,5 @@ def test_jsonsplit_type(fresh_db, type, expected): else: fn = recipes.jsonsplit - fresh_db["example"].convert("records", fn) - assert json.loads(fresh_db["example"].get(1)["records"]) == expected + fresh_db.table("example").convert("records", fn) + assert json.loads(fresh_db.table("example").get(1)["records"]) == expected diff --git a/tests/test_recreate.py b/tests/test_recreate.py index bce53d5..d8b846e 100644 --- a/tests/test_recreate.py +++ b/tests/test_recreate.py @@ -1,8 +1,10 @@ -from sqlite_utils import Database -import sqlite3 import pathlib +import sqlite3 + import pytest +from sqlite_utils import Database + def test_recreate_ignored_for_in_memory(): # None of these should raise an exception: @@ -31,8 +33,8 @@ def test_recreate(tmp_path, use_path, create_file_first): filepath = pathlib.Path(filepath) if create_file_first: db = Database(filepath) - db["t1"].insert({"foo": "bar"}) + db.table("t1").insert({"foo": "bar"}) assert ["t1"] == db.table_names() db.close() - Database(filepath, recreate=True)["t2"].insert({"foo": "bar"}) + Database(filepath, recreate=True).table("t2").insert({"foo": "bar"}) assert ["t2"] == Database(filepath).table_names() diff --git a/tests/test_register_function.py b/tests/test_register_function.py index 618bf1e..63f0570 100644 --- a/tests/test_register_function.py +++ b/tests/test_register_function.py @@ -86,21 +86,21 @@ def test_register_function_deterministic_tries_again_if_exception_raised(fresh_d def test_register_function_replace(fresh_db): @fresh_db.register_function() - def one(): + def one(): # pyright: ignore[reportRedeclaration] return "one" assert "one" == fresh_db.execute("select one()").fetchone()[0] # This will silently fail to replaec the function @fresh_db.register_function() - def one(): # noqa + def one(): # pyright: ignore[reportRedeclaration] return "two" assert "one" == fresh_db.execute("select one()").fetchone()[0] # This will replace it @fresh_db.register_function(replace=True) - def one(): # noqa + def one(): # pyright: ignore[reportRedeclaration] return "two" assert "two" == fresh_db.execute("select one()").fetchone()[0] diff --git a/tests/test_rows.py b/tests/test_rows.py index 46d4f53..476569e 100644 --- a/tests/test_rows.py +++ b/tests/test_rows.py @@ -3,7 +3,7 @@ import pytest def test_rows(existing_db): assert [{"text": "one"}, {"text": "two"}, {"text": "three"}] == list( - existing_db["foo"].rows + existing_db.table("foo").rows ) @@ -18,7 +18,7 @@ def test_rows(existing_db): ], ) def test_rows_where(where, where_args, expected_ids, fresh_db): - table = fresh_db["dogs"] + table = fresh_db.table("dogs") table.insert_all( [ {"id": 1, "name": "Cleo", "age": 4, "is_good": True}, @@ -41,7 +41,7 @@ def test_rows_where(where, where_args, expected_ids, fresh_db): ], ) def test_rows_where_order_by(where, order_by, expected_ids, fresh_db): - table = fresh_db["dogs"] + table = fresh_db.table("dogs") table.insert_all( [ {"id": 1, "name": "Cleo", "age": 4}, @@ -59,10 +59,13 @@ def test_rows_where_order_by(where, order_by, expected_ids, fresh_db): (None, 3, [1, 2, 3]), (0, 3, [1, 2, 3]), (3, 3, [4, 5, 6]), + # offset without limit should return every remaining row + (97, None, [98, 99, 100]), + (0, None, list(range(1, 101))), ], ) def test_rows_where_offset_limit(fresh_db, offset, limit, expected): - table = fresh_db["rows"] + table = fresh_db.table("rows") table.insert_all([{"id": id} for id in range(1, 101)], pk="id") assert table.count == 100 assert expected == [ @@ -70,8 +73,14 @@ def test_rows_where_offset_limit(fresh_db, offset, limit, expected): ] +def test_pks_and_rows_where_offset_without_limit(fresh_db): + table = fresh_db.table("rows") + table.insert_all([{"id": id} for id in range(1, 6)], pk="id") + assert [pk for pk, _ in table.pks_and_rows_where(offset=3, order_by="id")] == [4, 5] + + def test_pks_and_rows_where_rowid(fresh_db): - table = fresh_db["rowid_table"] + table = fresh_db.table("rowid_table") table.insert_all({"number": i + 10} for i in range(3)) pks_and_rows = list(table.pks_and_rows_where()) assert pks_and_rows == [ @@ -82,7 +91,7 @@ def test_pks_and_rows_where_rowid(fresh_db): def test_pks_and_rows_where_simple_pk(fresh_db): - table = fresh_db["simple_pk_table"] + table = fresh_db.table("simple_pk_table") table.insert_all(({"id": i + 10} for i in range(3)), pk="id") pks_and_rows = list(table.pks_and_rows_where()) assert pks_and_rows == [ @@ -93,7 +102,7 @@ def test_pks_and_rows_where_simple_pk(fresh_db): def test_pks_and_rows_where_compound_pk(fresh_db): - table = fresh_db["compound_pk_table"] + table = fresh_db.table("compound_pk_table") table.insert_all( ({"type": "number", "number": i, "plusone": i + 1} for i in range(3)), pk=("type", "number"), @@ -108,8 +117,8 @@ def test_pks_and_rows_where_compound_pk(fresh_db): def test_rows_where_duplicate_select_columns_are_deduped(fresh_db): # https://github.com/simonw/sqlite-utils/issues/624 - fresh_db["t"].insert({"id": 1, "name": "Cleo"}) - rows = list(fresh_db["t"].rows_where(select="id, id, name")) + fresh_db.table("t").insert({"id": 1, "name": "Cleo"}) + rows = list(fresh_db.table("t").rows_where(select="id, id, name")) assert rows == [{"id": 1, "id_2": 1, "name": "Cleo"}] @@ -121,10 +130,10 @@ def test_pks_and_rows_where_view(fresh_db): # an AttributeError from View lacking Table-only properties from sqlite_utils.utils import sqlite3 - fresh_db["dogs"].insert({"id": 1, "name": "Cleo"}, pk="id") + fresh_db.table("dogs").insert({"id": 1, "name": "Cleo"}, pk="id") fresh_db.create_view("dog_names", "select name from dogs") try: - result = list(fresh_db["dog_names"].pks_and_rows_where()) + result = list(fresh_db.view("dog_names").pks_and_rows_where()) except sqlite3.OperationalError: pass # SQLite 3.36+: no such column: rowid else: @@ -135,6 +144,6 @@ def test_pks_and_rows_where_view(fresh_db): def test_pks_and_rows_where_compound_pk_declaration_order(fresh_db): # Compound pks are returned in PRIMARY KEY declaration order fresh_db.execute("create table t (b text, a text, primary key (a, b))") - fresh_db["t"].insert({"a": "A", "b": "B"}) - pks_and_rows = list(fresh_db["t"].pks_and_rows_where()) + fresh_db.table("t").insert({"a": "A", "b": "B"}) + pks_and_rows = list(fresh_db.table("t").pks_and_rows_where()) assert pks_and_rows == [(("A", "B"), {"b": "B", "a": "A"})] diff --git a/tests/test_rows_from_file.py b/tests/test_rows_from_file.py index a19fed6..3de3582 100644 --- a/tests/test_rows_from_file.py +++ b/tests/test_rows_from_file.py @@ -1,7 +1,9 @@ -from sqlite_utils.utils import rows_from_file, Format, RowError from io import BytesIO, StringIO + import pytest +from sqlite_utils.utils import Format, RowError, rows_from_file + @pytest.mark.parametrize( "input,expected_format", @@ -18,6 +20,13 @@ def test_rows_from_file_detect_format(input, expected_format): assert rows_list == [{"id": "1", "name": "Cleo"}] +@pytest.mark.parametrize("input", (b"", b" \n\t")) +def test_rows_from_file_empty_input(input): + rows, format = rows_from_file(BytesIO(input)) + assert format == Format.CSV + assert list(rows) == [] + + @pytest.mark.parametrize( "ignore_extras,extras_key,expected", ( @@ -29,7 +38,7 @@ def test_rows_from_file_detect_format(input, expected_format): ) def test_rows_from_file_extra_fields_strategies(ignore_extras, extras_key, expected): try: - rows, format = rows_from_file( + rows, _format = rows_from_file( BytesIO(b"id,name\r\n1,Cleo,oops"), format=Format.CSV, ignore_extras=ignore_extras, diff --git a/tests/test_sniff.py b/tests/test_sniff.py index 4bbdb66..029a7fc 100644 --- a/tests/test_sniff.py +++ b/tests/test_sniff.py @@ -1,7 +1,9 @@ -from sqlite_utils import cli, Database -from click.testing import CliRunner import pathlib + import pytest +from click.testing import CliRunner + +from sqlite_utils import Database, cli sniff_dir = pathlib.Path(__file__).parent / "sniff" @@ -17,7 +19,7 @@ def test_sniff(tmpdir, filepath): ) assert result.exit_code == 0, result.stdout db = Database(db_path) - assert list(db["creatures"].rows) == [ + assert list(db.table("creatures").rows) == [ {"id": "1", "species": "dog", "name": "Cleo", "age": "5"}, {"id": "2", "species": "dog", "name": "Pancakes", "age": "4"}, {"id": "3", "species": "cat", "name": "Mozie", "age": "8"}, diff --git a/tests/test_suggest_column_types.py b/tests/test_suggest_column_types.py index e36c58f..d4f28d3 100644 --- a/tests/test_suggest_column_types.py +++ b/tests/test_suggest_column_types.py @@ -1,5 +1,7 @@ -import pytest from collections import OrderedDict + +import pytest + from sqlite_utils.utils import suggest_column_types diff --git a/tests/test_tracer.py b/tests/test_tracer.py index d14697d..ec81f2f 100644 --- a/tests/test_tracer.py +++ b/tests/test_tracer.py @@ -53,16 +53,18 @@ def test_with_tracer(): assert len(collected) == 4 assert collected == [ ( - "SELECT name FROM sqlite_master\n" - " WHERE rootpage = 0\n" - " AND (\n" - " sql LIKE :like\n" - " OR sql LIKE :like2\n" - " OR (\n" - " tbl_name = :table\n" - " AND sql LIKE '%VIRTUAL TABLE%USING FTS%'\n" - " )\n" - " )", + ( + "SELECT name FROM sqlite_master\n" + " WHERE rootpage = 0\n" + " AND (\n" + " sql LIKE :like\n" + " OR sql LIKE :like2\n" + " OR (\n" + " tbl_name = :table\n" + " AND sql LIKE '%VIRTUAL TABLE%USING FTS%'\n" + " )\n" + " )" + ), { "like": "%VIRTUAL TABLE%USING FTS%content=[dogs]%", "like2": '%VIRTUAL TABLE%USING FTS%content="dogs"%', @@ -72,21 +74,23 @@ def test_with_tracer(): ("select name from sqlite_master where type = 'view'", None), ("select sql from sqlite_master where name = ?", ("dogs_fts",)), ( - 'with "original" as (\n' - " select\n" - " rowid,\n" - " *\n" - ' from "dogs"\n' - ")\n" - "select\n" - ' "original".*\n' - "from\n" - ' "original"\n' - ' join "dogs_fts" on "original".rowid = "dogs_fts".rowid\n' - "where\n" - ' "dogs_fts" match :query\n' - "order by\n" - ' "dogs_fts".rank', + ( + 'with "original" as (\n' + " select\n" + " rowid,\n" + " *\n" + ' from "dogs"\n' + ")\n" + "select\n" + ' "original".*\n' + "from\n" + ' "original"\n' + ' join "dogs_fts" on "original".rowid = "dogs_fts".rowid\n' + "where\n" + ' "dogs_fts" match :query\n' + "order by\n" + ' "dogs_fts".rank' + ), {"query": "Cleopaws"}, ), ] diff --git a/tests/test_transform.py b/tests/test_transform.py index 71518be..8738713 100644 --- a/tests/test_transform.py +++ b/tests/test_transform.py @@ -1,7 +1,11 @@ -from sqlite_utils.db import ForeignKey, TransformError -from sqlite_utils.utils import OperationalError +import sqlite3 + import pytest +from sqlite_utils import ANY +from sqlite_utils.db import Check, ForeignKey, TransactionError, TransformError +from sqlite_utils.utils import OperationalError + @pytest.mark.parametrize( "params,expected_sql", @@ -13,7 +17,9 @@ import pytest 'CREATE TABLE "dogs_new_suffix" (\n "id" INTEGER PRIMARY KEY,\n "name" TEXT,\n "age" TEXT\n);', 'INSERT INTO "dogs_new_suffix" ("rowid", "id", "name", "age")\n SELECT "rowid", "id", "name", "age" FROM "dogs";', 'DROP TABLE "dogs";', + "PRAGMA legacy_alter_table=ON;", 'ALTER TABLE "dogs_new_suffix" RENAME TO "dogs";', + "PRAGMA legacy_alter_table=OFF;", ], ), # Change column type @@ -21,9 +27,11 @@ import pytest {"types": {"age": int}}, [ 'CREATE TABLE "dogs_new_suffix" (\n "id" INTEGER PRIMARY KEY,\n "name" TEXT,\n "age" INTEGER\n);', - 'INSERT INTO "dogs_new_suffix" ("rowid", "id", "name", "age")\n SELECT "rowid", "id", "name", "age" FROM "dogs";', + 'INSERT INTO "dogs_new_suffix" ("rowid", "id", "name", "age")\n SELECT "rowid", "id", "name", NULLIF("age", \'\') FROM "dogs";', 'DROP TABLE "dogs";', + "PRAGMA legacy_alter_table=ON;", 'ALTER TABLE "dogs_new_suffix" RENAME TO "dogs";', + "PRAGMA legacy_alter_table=OFF;", ], ), # Rename a column @@ -33,7 +41,9 @@ import pytest 'CREATE TABLE "dogs_new_suffix" (\n "id" INTEGER PRIMARY KEY,\n "name" TEXT,\n "dog_age" TEXT\n);', 'INSERT INTO "dogs_new_suffix" ("rowid", "id", "name", "dog_age")\n SELECT "rowid", "id", "name", "age" FROM "dogs";', 'DROP TABLE "dogs";', + "PRAGMA legacy_alter_table=ON;", 'ALTER TABLE "dogs_new_suffix" RENAME TO "dogs";', + "PRAGMA legacy_alter_table=OFF;", ], ), # Drop a column @@ -43,7 +53,9 @@ import pytest 'CREATE TABLE "dogs_new_suffix" (\n "id" INTEGER PRIMARY KEY,\n "name" TEXT\n);', 'INSERT INTO "dogs_new_suffix" ("rowid", "id", "name")\n SELECT "rowid", "id", "name" FROM "dogs";', 'DROP TABLE "dogs";', + "PRAGMA legacy_alter_table=ON;", 'ALTER TABLE "dogs_new_suffix" RENAME TO "dogs";', + "PRAGMA legacy_alter_table=OFF;", ], ), # Convert type AND rename column @@ -51,9 +63,11 @@ import pytest {"types": {"age": int}, "rename": {"age": "dog_age"}}, [ 'CREATE TABLE "dogs_new_suffix" (\n "id" INTEGER PRIMARY KEY,\n "name" TEXT,\n "dog_age" INTEGER\n);', - 'INSERT INTO "dogs_new_suffix" ("rowid", "id", "name", "dog_age")\n SELECT "rowid", "id", "name", "age" FROM "dogs";', + 'INSERT INTO "dogs_new_suffix" ("rowid", "id", "name", "dog_age")\n SELECT "rowid", "id", "name", NULLIF("age", \'\') FROM "dogs";', 'DROP TABLE "dogs";', + "PRAGMA legacy_alter_table=ON;", 'ALTER TABLE "dogs_new_suffix" RENAME TO "dogs";', + "PRAGMA legacy_alter_table=OFF;", ], ), # Change primary key @@ -63,7 +77,9 @@ import pytest 'CREATE TABLE "dogs_new_suffix" (\n "id" INTEGER,\n "name" TEXT,\n "age" TEXT PRIMARY KEY\n);', 'INSERT INTO "dogs_new_suffix" ("rowid", "id", "name", "age")\n SELECT "rowid", "id", "name", "age" FROM "dogs";', 'DROP TABLE "dogs";', + "PRAGMA legacy_alter_table=ON;", 'ALTER TABLE "dogs_new_suffix" RENAME TO "dogs";', + "PRAGMA legacy_alter_table=OFF;", ], ), # Change primary key to a compound pk @@ -73,7 +89,9 @@ import pytest 'CREATE TABLE "dogs_new_suffix" (\n "id" INTEGER,\n "name" TEXT,\n "age" TEXT,\n PRIMARY KEY ("age", "name")\n);', 'INSERT INTO "dogs_new_suffix" ("rowid", "id", "name", "age")\n SELECT "rowid", "id", "name", "age" FROM "dogs";', 'DROP TABLE "dogs";', + "PRAGMA legacy_alter_table=ON;", 'ALTER TABLE "dogs_new_suffix" RENAME TO "dogs";', + "PRAGMA legacy_alter_table=OFF;", ], ), # Remove primary key, creating a rowid table @@ -83,7 +101,9 @@ import pytest 'CREATE TABLE "dogs_new_suffix" (\n "id" INTEGER,\n "name" TEXT,\n "age" TEXT\n);', 'INSERT INTO "dogs_new_suffix" ("rowid", "id", "name", "age")\n SELECT "rowid", "id", "name", "age" FROM "dogs";', 'DROP TABLE "dogs";', + "PRAGMA legacy_alter_table=ON;", 'ALTER TABLE "dogs_new_suffix" RENAME TO "dogs";', + "PRAGMA legacy_alter_table=OFF;", ], ), # Keeping the table @@ -92,8 +112,10 @@ import pytest [ 'CREATE TABLE "dogs_new_suffix" (\n "id" INTEGER PRIMARY KEY,\n "name" TEXT\n);', 'INSERT INTO "dogs_new_suffix" ("rowid", "id", "name")\n SELECT "rowid", "id", "name" FROM "dogs";', + "PRAGMA legacy_alter_table=ON;", 'ALTER TABLE "dogs" RENAME TO "kept_table";', 'ALTER TABLE "dogs_new_suffix" RENAME TO "dogs";', + "PRAGMA legacy_alter_table=OFF;", ], ), ], @@ -107,11 +129,11 @@ def test_transform_sql_table_with_primary_key( def tracer(sql, params): return captured.append((sql, params)) - dogs = fresh_db["dogs"] + dogs = fresh_db.table("dogs") if use_pragma_foreign_keys: fresh_db.conn.execute("PRAGMA foreign_keys=ON") dogs.insert({"id": 1, "name": "Cleo", "age": "5"}, pk="id") - sql = dogs.transform_sql(**{**params, **{"tmp_suffix": "suffix"}}) + sql = dogs.transform_sql(**{**params, "tmp_suffix": "suffix"}) assert sql == expected_sql # Check that .transform() runs without exceptions: with fresh_db.tracer(tracer): @@ -136,7 +158,9 @@ def test_transform_sql_table_with_primary_key( 'CREATE TABLE "dogs_new_suffix" (\n "id" INTEGER,\n "name" TEXT,\n "age" TEXT\n);', 'INSERT INTO "dogs_new_suffix" ("rowid", "id", "name", "age")\n SELECT "rowid", "id", "name", "age" FROM "dogs";', 'DROP TABLE "dogs";', + "PRAGMA legacy_alter_table=ON;", 'ALTER TABLE "dogs_new_suffix" RENAME TO "dogs";', + "PRAGMA legacy_alter_table=OFF;", ], ), # Change column type @@ -144,9 +168,11 @@ def test_transform_sql_table_with_primary_key( {"types": {"age": int}}, [ 'CREATE TABLE "dogs_new_suffix" (\n "id" INTEGER,\n "name" TEXT,\n "age" INTEGER\n);', - 'INSERT INTO "dogs_new_suffix" ("rowid", "id", "name", "age")\n SELECT "rowid", "id", "name", "age" FROM "dogs";', + 'INSERT INTO "dogs_new_suffix" ("rowid", "id", "name", "age")\n SELECT "rowid", "id", "name", NULLIF("age", \'\') FROM "dogs";', 'DROP TABLE "dogs";', + "PRAGMA legacy_alter_table=ON;", 'ALTER TABLE "dogs_new_suffix" RENAME TO "dogs";', + "PRAGMA legacy_alter_table=OFF;", ], ), # Rename a column @@ -156,7 +182,9 @@ def test_transform_sql_table_with_primary_key( 'CREATE TABLE "dogs_new_suffix" (\n "id" INTEGER,\n "name" TEXT,\n "dog_age" TEXT\n);', 'INSERT INTO "dogs_new_suffix" ("rowid", "id", "name", "dog_age")\n SELECT "rowid", "id", "name", "age" FROM "dogs";', 'DROP TABLE "dogs";', + "PRAGMA legacy_alter_table=ON;", 'ALTER TABLE "dogs_new_suffix" RENAME TO "dogs";', + "PRAGMA legacy_alter_table=OFF;", ], ), # Make ID a primary key @@ -166,7 +194,9 @@ def test_transform_sql_table_with_primary_key( 'CREATE TABLE "dogs_new_suffix" (\n "id" INTEGER PRIMARY KEY,\n "name" TEXT,\n "age" TEXT\n);', 'INSERT INTO "dogs_new_suffix" ("rowid", "id", "name", "age")\n SELECT "rowid", "id", "name", "age" FROM "dogs";', 'DROP TABLE "dogs";', + "PRAGMA legacy_alter_table=ON;", 'ALTER TABLE "dogs_new_suffix" RENAME TO "dogs";', + "PRAGMA legacy_alter_table=OFF;", ], ), ], @@ -180,11 +210,11 @@ def test_transform_sql_table_with_no_primary_key( def tracer(sql, params): return captured.append((sql, params)) - dogs = fresh_db["dogs"] + dogs = fresh_db.table("dogs") if use_pragma_foreign_keys: fresh_db.conn.execute("PRAGMA foreign_keys=ON") dogs.insert({"id": 1, "name": "Cleo", "age": "5"}) - sql = dogs.transform_sql(**{**params, **{"tmp_suffix": "suffix"}}) + sql = dogs.transform_sql(**{**params, "tmp_suffix": "suffix"}) assert sql == expected_sql # Check that .transform() runs without exceptions: with fresh_db.tracer(tracer): @@ -200,7 +230,7 @@ def test_transform_sql_table_with_no_primary_key( def test_transform_sql_with_no_primary_key_to_primary_key_of_id(fresh_db): - dogs = fresh_db["dogs"] + dogs = fresh_db.table("dogs") dogs.insert({"id": 1, "name": "Cleo", "age": "5"}) assert ( dogs.schema @@ -215,7 +245,7 @@ def test_transform_sql_with_no_primary_key_to_primary_key_of_id(fresh_db): def test_transform_rename_pk(fresh_db): - dogs = fresh_db["dogs"] + dogs = fresh_db.table("dogs") dogs.insert({"id": 1, "name": "Cleo", "age": "5"}, pk="id") dogs.transform(rename={"id": "pk"}) assert ( @@ -236,7 +266,7 @@ def test_transform_preserves_keyword_literal_defaults(fresh_db): " note TEXT DEFAULT NULL" ")" ) - table = fresh_db["t"] + table = fresh_db.table("t") table.insert({"id": 1}) before = fresh_db.execute("SELECT is_active, flag, note FROM t").fetchone() assert before == (1, 0, None) @@ -259,7 +289,7 @@ def test_transform_preserves_keyword_literal_defaults(fresh_db): def test_transform_not_null(fresh_db): - dogs = fresh_db["dogs"] + dogs = fresh_db.table("dogs") dogs.insert({"id": 1, "name": "Cleo", "age": "5"}, pk="id") dogs.transform(not_null={"name"}) assert ( @@ -269,7 +299,7 @@ def test_transform_not_null(fresh_db): def test_transform_remove_a_not_null(fresh_db): - dogs = fresh_db["dogs"] + dogs = fresh_db.table("dogs") dogs.insert({"id": 1, "name": "Cleo", "age": "5"}, not_null={"age"}, pk="id") dogs.transform(not_null={"name": True, "age": False}) assert ( @@ -280,7 +310,7 @@ def test_transform_remove_a_not_null(fresh_db): @pytest.mark.parametrize("not_null", [{"age"}, {"age": True}]) def test_transform_add_not_null_with_rename(fresh_db, not_null): - dogs = fresh_db["dogs"] + dogs = fresh_db.table("dogs") dogs.insert({"id": 1, "name": "Cleo", "age": "5"}, pk="id") dogs.transform(not_null=not_null, rename={"age": "dog_age"}) assert ( @@ -290,7 +320,7 @@ def test_transform_add_not_null_with_rename(fresh_db, not_null): def test_transform_defaults(fresh_db): - dogs = fresh_db["dogs"] + dogs = fresh_db.table("dogs") dogs.insert({"id": 1, "name": "Cleo", "age": 5}, pk="id") dogs.transform(defaults={"age": 1}) assert ( @@ -300,7 +330,7 @@ def test_transform_defaults(fresh_db): def test_transform_defaults_and_rename_column(fresh_db): - dogs = fresh_db["dogs"] + dogs = fresh_db.table("dogs") dogs.insert({"id": 1, "name": "Cleo", "age": 5}, pk="id") dogs.transform(rename={"age": "dog_age"}, defaults={"age": 1}) assert ( @@ -310,7 +340,7 @@ def test_transform_defaults_and_rename_column(fresh_db): def test_remove_defaults(fresh_db): - dogs = fresh_db["dogs"] + dogs = fresh_db.table("dogs") dogs.insert({"id": 1, "name": "Cleo", "age": 5}, defaults={"age": 1}, pk="id") dogs.transform(defaults={"age": None}) assert ( @@ -321,8 +351,8 @@ def test_remove_defaults(fresh_db): @pytest.fixture def authors_db(fresh_db): - books = fresh_db["books"] - authors = fresh_db["authors"] + books = fresh_db.table("books") + authors = fresh_db.table("authors") authors.insert({"id": 5, "name": "Jane McGonical"}, pk="id") books.insert( {"id": 2, "title": "Reality is Broken", "author_id": 5}, @@ -333,13 +363,13 @@ def authors_db(fresh_db): def test_transform_foreign_keys_persist(authors_db): - assert authors_db["books"].foreign_keys == [ + assert authors_db.table("books").foreign_keys == [ ForeignKey( table="books", column="author_id", other_table="authors", other_column="id" ) ] - authors_db["books"].transform(rename={"title": "book_title"}) - assert authors_db["books"].foreign_keys == [ + authors_db.table("books").transform(rename={"title": "book_title"}) + assert authors_db.table("books").foreign_keys == [ ForeignKey( table="books", column="author_id", other_table="authors", other_column="id" ) @@ -352,8 +382,8 @@ def test_transform_foreign_keys_survive_renamed_column( ): if use_pragma_foreign_keys: authors_db.conn.execute("PRAGMA foreign_keys=ON") - authors_db["books"].transform(rename={"author_id": "author_id_2"}) - assert authors_db["books"].foreign_keys == [ + authors_db.table("books").transform(rename={"author_id": "author_id_2"}) + assert authors_db.table("books").foreign_keys == [ ForeignKey( table="books", column="author_id_2", @@ -364,9 +394,9 @@ def test_transform_foreign_keys_survive_renamed_column( def _add_country_city_continent(db): - db["country"].insert({"id": 1, "name": "France"}, pk="id") - db["continent"].insert({"id": 2, "name": "Europe"}, pk="id") - db["city"].insert({"id": 24, "name": "Paris"}, pk="id") + db.table("country").insert({"id": 1, "name": "France"}, pk="id") + db.table("continent").insert({"id": 2, "name": "Europe"}, pk="id") + db.table("city").insert({"id": 24, "name": "Paris"}, pk="id") _CAVEAU = { @@ -384,11 +414,11 @@ def test_transform_drop_foreign_keys(fresh_db, use_pragma_foreign_keys): fresh_db.conn.execute("PRAGMA foreign_keys=ON") # Create table with three foreign keys so we can drop two of them _add_country_city_continent(fresh_db) - fresh_db["places"].insert( + fresh_db.table("places").insert( _CAVEAU, foreign_keys=("country", "continent", "city"), ) - assert fresh_db["places"].foreign_keys == [ + assert fresh_db.table("places").foreign_keys == [ ForeignKey( table="places", column="city", other_table="city", other_column="id" ), @@ -403,9 +433,9 @@ def test_transform_drop_foreign_keys(fresh_db, use_pragma_foreign_keys): ), ] # Drop two of those foreign keys - fresh_db["places"].transform(drop_foreign_keys=("country", "continent")) + fresh_db.table("places").transform(drop_foreign_keys=("country", "continent")) # Should be only one foreign key now - assert fresh_db["places"].foreign_keys == [ + assert fresh_db.table("places").foreign_keys == [ ForeignKey(table="places", column="city", other_table="city", other_column="id") ] if use_pragma_foreign_keys: @@ -414,31 +444,200 @@ def test_transform_drop_foreign_keys(fresh_db, use_pragma_foreign_keys): def test_transform_verify_foreign_keys(fresh_db): fresh_db.conn.execute("PRAGMA foreign_keys=ON") - fresh_db["authors"].insert({"id": 3, "name": "Tina"}, pk="id") - fresh_db["books"].insert( + fresh_db.table("authors").insert({"id": 3, "name": "Tina"}, pk="id") + fresh_db.table("books").insert( {"id": 1, "title": "Book", "author_id": 3}, pk="id", foreign_keys={"author_id"} ) # Renaming the id column on authors should break everything with pytest.raises(OperationalError) as e: - fresh_db["authors"].transform(rename={"id": "id2"}) + fresh_db.table("authors").transform(rename={"id": "id2"}) assert e.value.args[0] == 'foreign key mismatch - "books" referencing "authors"' # This should have rolled us back assert ( - fresh_db["authors"].schema + fresh_db.table("authors").schema == 'CREATE TABLE "authors" (\n "id" INTEGER PRIMARY KEY,\n "name" TEXT\n)' ) assert fresh_db.conn.execute("PRAGMA foreign_keys").fetchone()[0] +@pytest.mark.parametrize("use_pragma_foreign_keys", [False, True]) +def test_transform_on_delete_cascade_does_not_delete_records( + fresh_db, use_pragma_foreign_keys +): + # Transforming a table drops and recreates it - if another table references + # it with ON DELETE CASCADE and PRAGMA foreign_keys is on, that drop must + # not cascade and delete the referencing records + if use_pragma_foreign_keys: + fresh_db.conn.execute("PRAGMA foreign_keys=ON") + fresh_db.executescript(""" + CREATE TABLE authors (id INTEGER PRIMARY KEY, name TEXT); + CREATE TABLE books ( + id INTEGER PRIMARY KEY, + title TEXT, + author_id INTEGER REFERENCES authors(id) ON DELETE CASCADE + ); + """) + fresh_db.table("authors").insert({"id": 1, "name": "Ursula K. Le Guin"}) + fresh_db.table("books").insert( + {"id": 1, "title": "The Dispossessed", "author_id": 1} + ) + # Transform the table on the other end of the cascading foreign key + fresh_db.table("authors").transform(rename={"name": "author_name"}) + assert list(fresh_db.table("authors").rows) == [ + {"id": 1, "author_name": "Ursula K. Le Guin"} + ] + assert list(fresh_db.table("books").rows) == [ + {"id": 1, "title": "The Dispossessed", "author_id": 1} + ] + # Transforming the table with the cascading foreign key should not + # delete its records either + fresh_db.table("books").transform(rename={"title": "book_title"}) + assert list(fresh_db.table("books").rows) == [ + {"id": 1, "book_title": "The Dispossessed", "author_id": 1} + ] + if use_pragma_foreign_keys: + assert fresh_db.conn.execute("PRAGMA foreign_keys").fetchone()[0] + + +@pytest.mark.parametrize("on_delete", ["CASCADE", "SET NULL", "SET DEFAULT", "cascade"]) +def test_transform_in_transaction_refuses_destructive_on_delete(fresh_db, on_delete): + # PRAGMA foreign_keys is a no-op inside a transaction, so transforming a + # table referenced by ON DELETE CASCADE / SET NULL / SET DEFAULT foreign + # keys inside an open transaction would fire those actions when the old + # table is dropped - transform() should refuse instead + fresh_db.conn.execute("PRAGMA foreign_keys=ON") + fresh_db.executescript(f""" + CREATE TABLE authors (id INTEGER PRIMARY KEY, name TEXT); + CREATE TABLE books ( + id INTEGER PRIMARY KEY, + title TEXT, + author_id INTEGER REFERENCES authors(id) ON DELETE {on_delete} + ); + """) + fresh_db.table("authors").insert({"id": 1, "name": "Ursula K. Le Guin"}) + fresh_db.table("books").insert( + {"id": 1, "title": "The Dispossessed", "author_id": 1} + ) + previous_schema = fresh_db.table("authors").schema + with fresh_db.atomic(), pytest.raises(TransactionError) as excinfo: + fresh_db.table("authors").transform(rename={"name": "author_name"}) + message = str(excinfo.value) + assert "books" in message + assert f"ON DELETE {on_delete.upper()}" in message + # Nothing should have changed + assert fresh_db.table("authors").schema == previous_schema + assert list(fresh_db.table("books").rows) == [ + {"id": 1, "title": "The Dispossessed", "author_id": 1} + ] + assert fresh_db.conn.execute("PRAGMA foreign_keys").fetchone()[0] + + +def test_transform_in_transaction_refuses_self_referential_cascade(fresh_db): + # The copied table carries a foreign key referencing the original table + # name, so a self-referential cascade would wipe the copy too + fresh_db.conn.execute("PRAGMA foreign_keys=ON") + fresh_db.executescript(""" + CREATE TABLE categories ( + id INTEGER PRIMARY KEY, + name TEXT, + parent_id INTEGER REFERENCES categories(id) ON DELETE CASCADE + ); + """) + fresh_db.table("categories").insert_all( + [ + {"id": 1, "name": "Fiction", "parent_id": None}, + {"id": 2, "name": "Science Fiction", "parent_id": 1}, + ] + ) + with fresh_db.atomic(), pytest.raises(TransactionError) as excinfo: + fresh_db.table("categories").transform(rename={"name": "title"}) + assert "categories" in str(excinfo.value) + assert fresh_db.table("categories").count == 2 + + +def test_transform_in_transaction_allowed_with_no_action_foreign_key(fresh_db): + # An inbound foreign key without a destructive ON DELETE action is safe + # inside a transaction thanks to PRAGMA defer_foreign_keys + fresh_db.conn.execute("PRAGMA foreign_keys=ON") + fresh_db.executescript(""" + CREATE TABLE authors (id INTEGER PRIMARY KEY, name TEXT); + CREATE TABLE books ( + id INTEGER PRIMARY KEY, + title TEXT, + author_id INTEGER REFERENCES authors(id) + ); + """) + fresh_db.table("authors").insert({"id": 1, "name": "Ursula K. Le Guin"}) + fresh_db.table("books").insert( + {"id": 1, "title": "The Dispossessed", "author_id": 1} + ) + with fresh_db.atomic(): + fresh_db.table("authors").transform(rename={"name": "author_name"}) + assert list(fresh_db.table("authors").rows) == [ + {"id": 1, "author_name": "Ursula K. Le Guin"} + ] + assert list(fresh_db.table("books").rows) == [ + {"id": 1, "title": "The Dispossessed", "author_id": 1} + ] + assert fresh_db.conn.execute("PRAGMA foreign_keys").fetchone()[0] + + +def test_transform_in_transaction_allowed_for_child_table(fresh_db): + # The table being transformed only has an outbound foreign key - dropping + # it fires no ON DELETE actions, so this is allowed inside a transaction + fresh_db.conn.execute("PRAGMA foreign_keys=ON") + fresh_db.executescript(""" + CREATE TABLE authors (id INTEGER PRIMARY KEY, name TEXT); + CREATE TABLE books ( + id INTEGER PRIMARY KEY, + title TEXT, + author_id INTEGER REFERENCES authors(id) ON DELETE CASCADE + ); + """) + fresh_db.table("authors").insert({"id": 1, "name": "Ursula K. Le Guin"}) + fresh_db.table("books").insert( + {"id": 1, "title": "The Dispossessed", "author_id": 1} + ) + with fresh_db.atomic(): + fresh_db.table("books").transform(rename={"title": "book_title"}) + assert list(fresh_db.table("books").rows) == [ + {"id": 1, "book_title": "The Dispossessed", "author_id": 1} + ] + + +def test_transform_in_transaction_allowed_with_foreign_keys_off(fresh_db): + # With PRAGMA foreign_keys off (the default) no cascades can fire, so + # transform inside a transaction is safe even with a CASCADE schema + fresh_db.executescript(""" + CREATE TABLE authors (id INTEGER PRIMARY KEY, name TEXT); + CREATE TABLE books ( + id INTEGER PRIMARY KEY, + title TEXT, + author_id INTEGER REFERENCES authors(id) ON DELETE CASCADE + ); + """) + fresh_db.table("authors").insert({"id": 1, "name": "Ursula K. Le Guin"}) + fresh_db.table("books").insert( + {"id": 1, "title": "The Dispossessed", "author_id": 1} + ) + with fresh_db.atomic(): + fresh_db.table("authors").transform(rename={"name": "author_name"}) + assert list(fresh_db.table("books").rows) == [ + {"id": 1, "title": "The Dispossessed", "author_id": 1} + ] + + def test_transform_add_foreign_keys_from_scratch(fresh_db): _add_country_city_continent(fresh_db) - fresh_db["places"].insert(_CAVEAU) + fresh_db.table("places").insert(_CAVEAU) # Should have no foreign keys - assert fresh_db["places"].foreign_keys == [] + assert fresh_db.table("places").foreign_keys == [] # Now add them using .transform() - fresh_db["places"].transform(add_foreign_keys=("country", "continent", "city")) + fresh_db.table("places").transform( + add_foreign_keys=("country", "continent", "city") + ) # Should now have all three: - assert fresh_db["places"].foreign_keys == [ + assert fresh_db.table("places").foreign_keys == [ ForeignKey( table="places", column="city", other_table="city", other_column="id" ), @@ -452,7 +651,7 @@ def test_transform_add_foreign_keys_from_scratch(fresh_db): table="places", column="country", other_table="country", other_column="id" ), ] - assert fresh_db["places"].schema == ( + assert fresh_db.table("places").schema == ( 'CREATE TABLE "places" (\n' ' "id" INTEGER,\n' ' "name" TEXT,\n' @@ -476,18 +675,18 @@ def test_transform_add_foreign_keys_from_scratch(fresh_db): ) def test_transform_add_foreign_keys_from_partial(fresh_db, add_foreign_keys): _add_country_city_continent(fresh_db) - fresh_db["places"].insert( + fresh_db.table("places").insert( _CAVEAU, foreign_keys=("city",), ) # Should have one foreign keys - assert fresh_db["places"].foreign_keys == [ + assert fresh_db.table("places").foreign_keys == [ ForeignKey(table="places", column="city", other_table="city", other_column="id") ] # Now add three more using .transform() - fresh_db["places"].transform(add_foreign_keys=add_foreign_keys) + fresh_db.table("places").transform(add_foreign_keys=add_foreign_keys) # Should now have all three: - assert fresh_db["places"].foreign_keys == [ + assert fresh_db.table("places").foreign_keys == [ ForeignKey( table="places", column="city", other_table="city", other_column="id" ), @@ -516,14 +715,14 @@ def test_transform_add_foreign_keys_from_partial(fresh_db, add_foreign_keys): ) def test_transform_replace_foreign_keys(fresh_db, foreign_keys): _add_country_city_continent(fresh_db) - fresh_db["places"].insert( + fresh_db.table("places").insert( _CAVEAU, foreign_keys=("city",), ) - assert len(fresh_db["places"].foreign_keys) == 1 + assert len(fresh_db.table("places").foreign_keys) == 1 # Replace with two different ones - fresh_db["places"].transform(foreign_keys=foreign_keys) - assert fresh_db["places"].schema == ( + fresh_db.table("places").transform(foreign_keys=foreign_keys) + assert fresh_db.table("places").schema == ( 'CREATE TABLE "places" (\n' ' "id" INTEGER,\n' ' "name" TEXT,\n' @@ -543,7 +742,7 @@ def test_transform_preserves_rowids(fresh_db, table_type): pk = ("id", "name") elif table_type == "rowid": pk = None - fresh_db["places"].insert_all( + fresh_db.table("places").insert_all( [ {"id": "1", "name": "Paris", "country": "France"}, {"id": "2", "name": "London", "country": "UK"}, @@ -552,27 +751,126 @@ def test_transform_preserves_rowids(fresh_db, table_type): pk=pk, ) # Now delete and insert a row to mix up the `rowid` sequence - fresh_db["places"].delete_where("id = ?", ["2"]) - fresh_db["places"].insert({"id": "4", "name": "London", "country": "UK"}) - previous_rows = list( + fresh_db.table("places").delete_where("id = ?", ["2"]) + fresh_db.table("places").insert({"id": "4", "name": "London", "country": "UK"}) + previous_rows = [ tuple(row) for row in fresh_db.execute("select rowid, id, name from places") - ) + ] # Transform it - fresh_db["places"].transform(column_order=("country", "name")) + fresh_db.table("places").transform(column_order=("country", "name")) # Should be the same - next_rows = list( + next_rows = [ tuple(row) for row in fresh_db.execute("select rowid, id, name from places") - ) + ] assert previous_rows == next_rows -@pytest.mark.parametrize("strict", (False, True)) -def test_transform_strict(fresh_db, strict): - dogs = fresh_db.table("dogs", strict=strict) +@pytest.mark.parametrize( + "initial_strict,transform_strict,expected_strict", + ( + (False, None, False), + (True, None, True), + (False, True, True), + (True, False, False), + ), +) +def test_transform_strict(fresh_db, initial_strict, transform_strict, expected_strict): + if not fresh_db.supports_strict: + pytest.skip("SQLite version does not support strict tables") + dogs = fresh_db.table("dogs", strict=initial_strict) dogs.insert({"id": 1, "name": "Cleo"}) - assert dogs.strict == strict or not fresh_db.supports_strict - dogs.transform(not_null={"name"}) - assert dogs.strict == strict or not fresh_db.supports_strict + assert dogs.strict is initial_strict + dogs.transform(strict=transform_strict) + assert dogs.strict is expected_strict + + +def test_transform_to_strict_with_invalid_data(fresh_db): + if not fresh_db.supports_strict: + pytest.skip("SQLite version does not support strict tables") + dogs = fresh_db.table("dogs") + dogs.create({"id": int}) + dogs.insert({"id": "not-an-integer"}) + + with pytest.raises(sqlite3.IntegrityError): + dogs.transform(strict=True) + + assert dogs.strict is False + assert list(dogs.rows) == [{"id": "not-an-integer"}] + assert fresh_db.table_names() == ["dogs"] + + +def test_transform_strict_updates_default(fresh_db): + if not fresh_db.supports_strict: + pytest.skip("SQLite version does not support strict tables") + table = fresh_db.table("items", strict=True) + table.create({"id": int}) + + table.transform(strict=False) + assert table.strict is False + + table.create({"id": int}, replace=True) + assert table.strict is False + + +@pytest.mark.parametrize("method_name", ("transform", "transform_sql")) +def test_transform_to_strict_not_supported(fresh_db, method_name): + table = fresh_db.table("items") + table.create({"id": int}) + fresh_db._supports_strict = False + + with pytest.raises(TransformError, match="SQLite does not support STRICT tables"): + getattr(table, method_name)(strict=True) + + assert table.strict is False + + +def test_transform_preserves_any_column_in_strict_table(fresh_db): + if not fresh_db.supports_strict: + pytest.skip("SQLite version does not support strict tables") + fresh_db.execute("create table items (id integer primary key, data any) strict") + fresh_db.conn.executemany( + "insert into items values (?, ?)", + [ + (1, 42), + (2, "000123"), + (3, 3.14), + (4, b"bytes"), + (5, None), + ], + ) + table = fresh_db["items"] + + table.transform() + + assert table.strict is True + assert table.columns_dict == {"id": int, "data": ANY} + assert fresh_db.execute( + "select typeof(data), data from items order by id" + ).fetchall() == [ + ("integer", 42), + ("text", "000123"), + ("real", 3.14), + ("blob", b"bytes"), + ("null", None), + ] + + +def test_transform_any_column_from_strict_to_non_strict(fresh_db): + if not fresh_db.supports_strict: + pytest.skip("SQLite version does not support strict tables") + fresh_db.execute("create table items (data any) strict") + fresh_db.execute("insert into items values (?)", ("000123",)) + table = fresh_db["items"] + + table.transform(strict=False) + + assert table.strict is False + assert table.columns_dict == {"data": ANY} + # Ordinary non-STRICT ANY columns apply NUMERIC affinity + assert fresh_db.execute("select typeof(data), data from items").fetchone() == ( + "integer", + 123, + ) @pytest.mark.parametrize( @@ -587,7 +885,7 @@ def test_transform_strict(fresh_db, strict): def test_transform_indexes(fresh_db, indexes, transform_params): # https://github.com/simonw/sqlite-utils/issues/633 # New table should have same indexes as old table after transformation - dogs = fresh_db["dogs"] + dogs = fresh_db.table("dogs") dogs.insert({"id": 1, "name": "Cleo", "age": 5, "breed": "Labrador"}, pk="id") for index in indexes: @@ -613,13 +911,13 @@ def test_transform_indexes(fresh_db, indexes, transform_params): if "keep_table" in transform_params: assert all( index.origin == "pk" - for index in fresh_db[transform_params["keep_table"]].indexes + for index in fresh_db.table(transform_params["keep_table"]).indexes ) def test_transform_retains_indexes_with_foreign_keys(fresh_db): - dogs = fresh_db["dogs"] - owners = fresh_db["owners"] + dogs = fresh_db.table("dogs") + owners = fresh_db.table("owners") dogs.insert({"id": 1, "name": "Cleo", "owner_id": 1}, pk="id") owners.insert({"id": 1, "name": "Alice"}, pk="id") @@ -645,22 +943,15 @@ def test_transform_retains_indexes_with_foreign_keys(fresh_db): ), f"Indexes before transform: {indexes_before_transform}\nIndexes after transform: {dogs.indexes}" -@pytest.mark.parametrize( - "transform_params", - [ - {"rename": {"age": "dog_age"}}, - {"drop": ["age"]}, - ], -) -def test_transform_with_indexes_errors(fresh_db, transform_params): - # Should error with a compound (name, age) index if age is renamed or dropped - dogs = fresh_db["dogs"] +def test_transform_with_indexes_errors(fresh_db): + # Should error with a compound (name, age) index if age is dropped + dogs = fresh_db.table("dogs") dogs.insert({"id": 1, "name": "Cleo", "age": 5}, pk="id") dogs.create_index(["name", "age"]) with pytest.raises(TransformError) as excinfo: - dogs.transform(**transform_params) + dogs.transform(drop=["age"]) assert ( "Index 'idx_dogs_name_age' column 'age' is not in updated table 'dogs'. " @@ -669,27 +960,515 @@ def test_transform_with_indexes_errors(fresh_db, transform_params): ) +@pytest.mark.parametrize( + ("table_name", "index_name"), + (("name", "idx_name"), ("t", "name")), +) +def test_transform_rename_column_with_index(fresh_db, table_name, index_name): + # https://github.com/simonw/sqlite-utils/issues/822 + # Use the same name for the table, column and index to ensure only the + # indexed column changes. + table = fresh_db.table(table_name) + table.insert({"id": 1, "name": "Cleo"}, pk="id") + table.create_index(["name"], index_name=index_name) + + sqls = table.transform_sql(rename={"name": "full_name"}, tmp_suffix="suffix") + drop_index_sql = f'DROP INDEX IF EXISTS "{index_name}";' + assert drop_index_sql in sqls + assert sqls.index(drop_index_sql) < sqls.index(f'DROP TABLE "{table_name}";') + + table.transform(rename={"name": "full_name"}) + + assert [column.name for column in table.columns] == ["id", "full_name"] + assert [(index.name, index.columns) for index in table.indexes] == [ + (index_name, ["full_name"]) + ] + + +def test_transform_recreates_renamed_index_from_metadata(fresh_db): + table = fresh_db.table("t") + table.insert({"alpha": "one", "beta": "two"}) + # Deliberately use unquoted SQL and index details that need to survive the + # reconstruction. Renaming both columns also guards against cascading + # string substitutions. + fresh_db.execute( + "CREATE UNIQUE INDEX swap_idx ON t(alpha COLLATE NOCASE DESC, beta)" + ) + + table.transform(rename={"alpha": "beta", "beta": "alpha"}) + + assert table.columns_dict == {"beta": str, "alpha": str} + assert [(index.name, index.unique, index.columns) for index in table.indexes] == [ + ("swap_idx", 1, ["beta", "alpha"]) + ] + key_columns = [column for column in table.xindexes[0].columns if column.key] + assert [(column.name, column.desc, column.coll) for column in key_columns] == [ + ("beta", 1, "NOCASE"), + ("alpha", 0, "BINARY"), + ] + + +@pytest.mark.parametrize( + "index_sql", + ( + "CREATE INDEX idx_t_name ON t(lower(name))", + "CREATE INDEX idx_t_name ON t(name) WHERE name IS NOT NULL", + ), +) +def test_transform_rename_complex_index_errors(fresh_db, index_sql): + table = fresh_db.table("t") + table.insert({"id": 1, "name": "Cleo"}, pk="id") + fresh_db.execute(index_sql) + + with pytest.raises(TransformError, match="partial or expression index"): + table.transform(rename={"name": "full_name"}) + + assert table.columns_dict == {"id": int, "name": str} + assert [index.name for index in table.indexes] == ["idx_t_name"] + + def test_transform_with_unique_constraint_implicit_index(fresh_db): - dogs = fresh_db["dogs"] + dogs = fresh_db.table("dogs") # Create a table with a UNIQUE constraint on 'name', which creates an implicit index fresh_db.execute(""" CREATE TABLE dogs ( id INTEGER PRIMARY KEY, - name TEXT UNIQUE, + name TEXT UNIQUE ON CONFLICT IGNORE, age INTEGER ); """) dogs.insert({"id": 1, "name": "Cleo", "age": 5}) - # Attempt to transform the table without modifying 'name' - with pytest.raises(TransformError) as excinfo: - dogs.transform(types={"age": str}) + dogs.transform(types={"age": str}, rename={"name": "dog_name"}) + + assert 'dog_name" TEXT UNIQUE ON CONFLICT IGNORE' in dogs.schema + dogs.insert({"id": 2, "dog_name": "Cleo", "age": "6"}) + assert list(dogs.rows) == [{"id": 1, "dog_name": "Cleo", "age": "5"}] + + +def test_transform_preserves_composite_unique_constraint(fresh_db): + fresh_db.execute(""" + CREATE TABLE memberships ( + account_id INTEGER, + email TEXT, + note TEXT, + CONSTRAINT unique_membership + UNIQUE (account_id DESC, email COLLATE NOCASE) + ON CONFLICT ABORT + ) + """) + memberships = fresh_db.table("memberships") + memberships.insert({"account_id": 1, "email": "one@example.com", "note": "x"}) + + memberships.transform(rename={"account_id": "organization_id"}, types={"note": str}) assert ( - "Index 'sqlite_autoindex_dogs_1' on table 'dogs' does not have a CREATE INDEX statement." - in str(excinfo.value) + 'CONSTRAINT "unique_membership" UNIQUE ' + '("organization_id" DESC, "email" COLLATE "NOCASE") ON CONFLICT ABORT' + in memberships.schema ) - assert ( - "You must manually drop this index prior to running this transformation and manually recreate the new index after running this transformation." - in str(excinfo.value) + with pytest.raises(sqlite3.IntegrityError): + memberships.insert( + {"organization_id": 1, "email": "ONE@example.com", "note": "y"} + ) + + +def test_transform_preserves_column_unique_collation(fresh_db): + fresh_db.execute(""" + CREATE TABLE people ( + id INTEGER PRIMARY KEY, + name TEXT COLLATE NOCASE UNIQUE + ) + """) + people = fresh_db.table("people") + people.insert({"id": 1, "name": "Cleo"}) + + people.transform(rename={"name": "full_name"}) + + assert 'UNIQUE ("full_name" COLLATE "NOCASE")' in people.schema + with pytest.raises(sqlite3.IntegrityError): + people.insert({"id": 2, "full_name": "cleo"}) + + +def test_transform_drops_entire_composite_unique_constraint(fresh_db): + fresh_db.execute(""" + CREATE TABLE memberships ( + account_id INTEGER, + email TEXT, + UNIQUE (account_id, email) + ) + """) + memberships = fresh_db.table("memberships") + memberships.insert({"account_id": 1, "email": "one@example.com"}) + + memberships.transform(drop={"email"}) + + assert "UNIQUE" not in memberships.schema + memberships.insert({"account_id": 1}) + + +def test_transform_preserves_autoincrement_and_sequence(fresh_db): + fresh_db.execute( + "CREATE TABLE entries (id INTEGER PRIMARY KEY AUTOINCREMENT, value TEXT)" ) + entries = fresh_db.table("entries") + entries.insert_all(({"value": "one"}, {"value": "two"})) + entries.delete(2) + + entries.transform(rename={"value": "label"}) + + assert "PRIMARY KEY AUTOINCREMENT" in entries.schema + entries.insert({"label": "three"}) + assert list(entries.rows) == [ + {"id": 1, "label": "one"}, + {"id": 3, "label": "three"}, + ] + + +@pytest.mark.parametrize( + "new_type,expected_value,expected_type", + [ + (int, 42, int), + (float, 42.0, float), + ("integer", 42, int), + ("float", 42.0, float), + ("REAL", 42.0, float), + ], +) +def test_transform_empty_string_to_null_for_numeric_types( + fresh_db, new_type, expected_value, expected_type +): + fresh_db["test"].insert_all( + [ + {"id": 1, "value": "42"}, + {"id": 2, "value": ""}, + {"id": 3, "value": None}, + {"id": 4, "value": " "}, + ] + ) + fresh_db["test"].transform(types={"value": new_type}) + rows = {r["id"]: r["value"] for r in fresh_db["test"].rows} + assert rows[1] == expected_value + assert type(rows[1]) is expected_type + assert rows[2] is None + assert rows[3] is None + assert rows[4] == " " + + +def test_transform_preserves_view(fresh_db): + # https://github.com/simonw/sqlite-utils/issues/831 + dogs = fresh_db.table("dogs") + dogs.insert({"id": 1, "name": "Cleo"}, pk="id") + fresh_db.execute("create view dogs_view as select id, name from dogs") + view_sql_before = fresh_db.execute( + "select sql from sqlite_master where name = 'dogs_view'" + ).fetchone()[0] + dogs.transform(rename={"name": "title"}) + view_sql_after = fresh_db.execute( + "select sql from sqlite_master where name = 'dogs_view'" + ).fetchone()[0] + assert view_sql_before == view_sql_after + + +@pytest.mark.parametrize( + "transform_params", + [ + {"types": {"name": int}}, + {"pk": "name"}, + {"add_foreign_keys": [("other_id", "other", "id")]}, + {"drop_foreign_keys": ["other_id"]}, + ], +) +def test_transform_variants_preserve_view(fresh_db, transform_params): + # Covers retyping, changing primary key and foreign key modifications, + # with a view whose columns are untouched by the transform + fresh_db.table("other").insert({"id": 1}, pk="id") + dogs = fresh_db.table("dogs") + dogs.insert({"id": 1, "name": "Cleo", "other_id": 1}, pk="id") + if "drop_foreign_keys" in transform_params: + dogs.transform(add_foreign_keys=[("other_id", "other", "id")]) + fresh_db.execute("create view dogs_view as select id, name from dogs") + view_sql_before = fresh_db.execute( + "select sql from sqlite_master where name = 'dogs_view'" + ).fetchone()[0] + dogs.transform(**transform_params) + view_sql_after = fresh_db.execute( + "select sql from sqlite_master where name = 'dogs_view'" + ).fetchone()[0] + assert view_sql_before == view_sql_after + assert list(fresh_db.view("dogs_view").rows) == [{"id": 1, "name": "Cleo"}] + + +def test_transform_view_referencing_renamed_column(fresh_db): + # The view survives but querying it raises "no such column" - inherent + # to SQLite views, whose SQL is stored as text + dogs = fresh_db.table("dogs") + dogs.insert({"id": 1, "name": "Cleo"}, pk="id") + fresh_db.execute("create view dogs_view as select id, name from dogs") + dogs.transform(rename={"name": "title"}) + with pytest.raises(OperationalError, match="no such column"): + fresh_db.execute("select * from dogs_view") + + +def test_transform_view_on_view(fresh_db): + dogs = fresh_db.table("dogs") + dogs.insert({"id": 1, "name": "Cleo"}, pk="id") + fresh_db.execute("create view v1 as select id, name from dogs") + fresh_db.execute("create view v2 as select name from v1") + sqls_before = fresh_db.execute( + "select sql from sqlite_master where type = 'view' order by name" + ).fetchall() + dogs.transform(types={"id": str}) + sqls_after = fresh_db.execute( + "select sql from sqlite_master where type = 'view' order by name" + ).fetchall() + assert sqls_before == sqls_after + assert list(fresh_db.view("v2").rows) == [{"name": "Cleo"}] + + +def test_transform_keep_table_does_not_repoint_view(fresh_db): + # Without legacy_alter_table the ALTER TABLE dogs RENAME TO dogs_backup + # step would rewrite the view to select from "dogs_backup" + dogs = fresh_db.table("dogs") + dogs.insert({"id": 1, "name": "Cleo"}, pk="id") + fresh_db.execute("create view dogs_view as select id, name from dogs") + dogs.transform(types={"name": str}, keep_table="dogs_backup") + view_sql = fresh_db.execute( + "select sql from sqlite_master where name = 'dogs_view'" + ).fetchone()[0] + assert "dogs_backup" not in view_sql + # View reads from the live table, not the frozen backup + dogs.insert({"id": 2, "name": "Pancakes"}) + assert list(fresh_db.view("dogs_view").rows) == [ + {"id": 1, "name": "Cleo"}, + {"id": 2, "name": "Pancakes"}, + ] + + +def test_transform_sql_standalone_statements_work_with_view(fresh_db): + # The documented "run these statements yourself" workflow should be + # standalone-correct, so the pragmas must come from transform_sql() + dogs = fresh_db.table("dogs") + dogs.insert({"id": 1, "name": "Cleo"}, pk="id") + fresh_db.execute("create view dogs_view as select id, name from dogs") + sqls = dogs.transform_sql(types={"name": str}, tmp_suffix="suffix") + assert sqls[-3] == "PRAGMA legacy_alter_table=ON;" + assert sqls[-2] == 'ALTER TABLE "dogs_new_suffix" RENAME TO "dogs";' + assert sqls[-1] == "PRAGMA legacy_alter_table=OFF;" + for sql in sqls: + fresh_db.execute(sql) + assert list(fresh_db.view("dogs_view").rows) == [{"id": 1, "name": "Cleo"}] + + +def test_transform_with_view_in_open_transaction(fresh_db): + fresh_db.conn.execute("PRAGMA foreign_keys=ON") + dogs = fresh_db.table("dogs") + dogs.insert({"id": 1, "name": "Cleo"}, pk="id") + fresh_db.execute("create view dogs_view as select id, name from dogs") + with fresh_db.conn: + fresh_db.execute("insert into dogs (id, name) values (2, 'Pancakes')") + dogs.transform(rename={"name": "title"}) + assert dogs.columns_dict == {"id": int, "title": str} + view_sql = fresh_db.execute( + "select sql from sqlite_master where name = 'dogs_view'" + ).fetchone()[0] + assert view_sql == "CREATE VIEW dogs_view as select id, name from dogs" + + +def test_transform_restores_legacy_alter_table_setting(fresh_db): + if sqlite3.sqlite_version_info < (3, 25, 0): + pytest.skip("legacy_alter_table pragma requires SQLite 3.25 or higher") + dogs = fresh_db.table("dogs") + dogs.insert({"id": 1, "name": "Cleo"}, pk="id") + # Default is OFF, reset to OFF afterwards + dogs.transform(types={"name": str}) + assert fresh_db.execute("PRAGMA legacy_alter_table").fetchone()[0] == 0 + # If the connection has it ON, it should be restored to ON + fresh_db.execute("PRAGMA legacy_alter_table=ON") + sqls = dogs.transform_sql(types={"name": str}, tmp_suffix="suffix") + assert sqls[-1] == "PRAGMA legacy_alter_table=ON;" + dogs.transform(types={"name": str}) + assert fresh_db.execute("PRAGMA legacy_alter_table").fetchone()[0] == 1 + + +def test_transform_preserves_check_constraints(fresh_db): + fresh_db.execute(""" + CREATE TABLE scores ( + id INTEGER PRIMARY KEY, + score INTEGER CONSTRAINT valid_score CHECK(score BETWEEN 0 AND 100), + CONSTRAINT nonzero_id CHECK(id != 0) + ) + """) + scores = fresh_db.table("scores") + scores.insert({"id": 1, "score": 50}) + scores.transform() + assert scores.checks == [ + Check("score BETWEEN 0 AND 100", name="valid_score", column="score"), + Check("id != 0", name="nonzero_id"), + ] + with pytest.raises(sqlite3.IntegrityError, match="CHECK constraint failed"): + scores.insert({"id": 2, "score": 101}) + + +def test_transform_preserves_check_ending_in_line_comment(fresh_db): + fresh_db.execute(""" + CREATE TABLE inventory ( + quantity INTEGER, + CHECK ( + quantity >= 0 -- Quantity cannot be negative + ) + ) + """) + inventory = fresh_db.table("inventory") + inventory.transform(types={"quantity": float}) + assert inventory.checks == [Check("quantity >= 0 -- Quantity cannot be negative")] + with pytest.raises(sqlite3.IntegrityError, match="CHECK constraint failed"): + inventory.insert({"quantity": -1}) + + +def test_transform_preserves_comments_owned_by_columns(fresh_db): + fresh_db.execute(""" + CREATE TABLE people ( + -- Primary identifier + id INTEGER PRIMARY KEY /* IDs are stable */, + /* Displayed to users */ + name TEXT /* May contain spaces */, + -- Age in years + age INTEGER -- May be NULL + ) + """) + people = fresh_db.table("people") + people.insert({"id": 1, "name": "Cleo", "age": 5}) + people.transform( + rename={"name": "display_name"}, + types={"age": float}, + column_order=("age", "id", "name"), + ) + assert people.get(1) == {"age": 5.0, "id": 1, "display_name": "Cleo"} + schema = people.schema + assert schema.index("-- Age in years") < schema.index('"age" REAL') + assert schema.index('"age" REAL') < schema.index("-- May be NULL") + assert schema.index("-- Primary identifier") < schema.index('"id" INTEGER') + assert schema.index('"id" INTEGER') < schema.index("/* IDs are stable */") + assert schema.index("/* Displayed to users */") < schema.index( + '"display_name" TEXT' + ) + assert schema.index('"display_name" TEXT') < schema.index( + "/* May contain spaces */" + ) + + +def test_transform_drops_comments_owned_by_dropped_column(fresh_db): + fresh_db.execute(""" + CREATE TABLE t ( + /* Keep this explanation */ + id INTEGER, + /* Drop this explanation */ + obsolete TEXT /* Drop this too */ + ) + """) + fresh_db.table("t").transform(drop={"obsolete"}) + schema = fresh_db.table("t").schema + assert "Keep this explanation" in schema + assert "Drop this explanation" not in schema + assert "Drop this too" not in schema + + +def test_transform_renames_columns_inside_check_constraints(fresh_db): + fresh_db.execute(""" + CREATE TABLE inventory ( + quantity INTEGER CONSTRAINT positive + CHECK(quantity > 0 AND 'quantity' != ''), + maximum INTEGER, + CONSTRAINT within_maximum CHECK(quantity <= maximum) + ) + """) + inventory = fresh_db.table("inventory") + inventory.insert({"quantity": 2, "maximum": 3}) + inventory.transform(rename={"quantity": "amount"}) + assert inventory.checks == [ + Check( + "amount > 0 AND 'quantity' != ''", + name="positive", + column="amount", + ), + Check("amount <= maximum", name="within_maximum"), + ] + with pytest.raises(sqlite3.IntegrityError, match="CHECK constraint failed"): + inventory.insert({"amount": 4, "maximum": 3}) + + +def test_transform_check_rewrite_preserves_functions_and_quotes(fresh_db): + fresh_db.execute(""" + CREATE TABLE items ( + length TEXT, + "old name" TEXT, + CHECK(length("old name") > 0 AND length != '') + ) + """) + items = fresh_db.table("items") + items.insert({"length": "label", "old name": "hello"}) + items.transform(rename={"length": "description", "old name": "new name"}) + assert items.checks == [Check("length(\"new name\") > 0 AND description != ''")] + + +def test_transform_check_rewrite_quotes_keyword_column(fresh_db): + fresh_db.execute("CREATE TABLE t(old_name TEXT CHECK(old_name != ''))") + fresh_db.table("t").insert({"old_name": "value"}) + fresh_db.table("t").transform(rename={"old_name": "select"}) + assert fresh_db.table("t").checks == [Check("\"select\" != ''", column="select")] + + +def test_transform_check_rewrite_does_not_rename_collations_or_cast_types(fresh_db): + fresh_db.execute(""" + CREATE TABLE t ( + nocase TEXT, + kind TEXT, + other TEXT, + CHECK( + other COLLATE nocase != '' + AND CAST(other AS kind) != '' + AND nocase != '' + AND kind != '' + ) + ) + """) + fresh_db.table("t").insert({"nocase": "n", "kind": "k", "other": "o"}) + fresh_db.table("t").transform(rename={"nocase": "label", "kind": "category"}) + check = fresh_db.table("t").checks[0].check + assert "COLLATE nocase" in check + assert "AS kind" in check + assert "AND label != ''" in check + assert "AND category != ''" in check + + +def test_transform_drops_check_owned_by_dropped_column(fresh_db): + fresh_db.execute(""" + CREATE TABLE t ( + id INTEGER, + obsolete INTEGER CHECK(obsolete > 0), + CHECK(id > 0) + ) + """) + fresh_db.table("t").insert({"id": 1, "obsolete": 2}) + fresh_db.table("t").transform(drop={"obsolete"}) + assert fresh_db.table("t").checks == [Check("id > 0")] + + +def test_transform_refuses_to_drop_column_used_by_remaining_check(fresh_db): + fresh_db.execute(""" + CREATE TABLE ranges ( + minimum INTEGER, + maximum INTEGER, + CHECK(minimum <= maximum) + ) + """) + ranges = fresh_db.table("ranges") + ranges.insert({"minimum": 1, "maximum": 2}) + schema_before = ranges.schema + with pytest.raises( + TransformError, + match="Cannot drop column 'maximum'.*CHECK constraint", + ): + ranges.transform(drop={"maximum"}) + assert ranges.schema == schema_before diff --git a/tests/test_update.py b/tests/test_update.py index 03bec11..44cc098 100644 --- a/tests/test_update.py +++ b/tests/test_update.py @@ -7,14 +7,14 @@ from sqlite_utils.db import NotFoundError def test_update_rowid_table(fresh_db): - table = fresh_db["table"] + table = fresh_db.table("table") rowid = table.insert({"foo": "bar"}).last_pk table.update(rowid, {"foo": "baz"}) assert [{"foo": "baz"}] == list(table.rows) def test_update_pk_table(fresh_db): - table = fresh_db["table"] + table = fresh_db.table("table") pk = table.insert({"foo": "bar", "id": 5}, pk="id").last_pk assert 5 == pk table.update(pk, {"foo": "baz"}) @@ -22,7 +22,7 @@ def test_update_pk_table(fresh_db): def test_update_compound_pk_table(fresh_db): - table = fresh_db["table"] + table = fresh_db.table("table") pk = table.insert({"id1": 5, "id2": 3, "v": 1}, pk=("id1", "id2")).last_pk assert (5, 3) == pk table.update(pk, {"v": 2}) @@ -42,14 +42,14 @@ def test_update_compound_pk_table(fresh_db): ), ) def test_update_invalid_pk(fresh_db, pk, update_pk): - table = fresh_db["table"] - table.insert({"id1": 5, "id2": 3, "v": 1}, pk=pk).last_pk + table = fresh_db.table("table") + table.insert({"id1": 5, "id2": 3, "v": 1}, pk=pk) with pytest.raises(NotFoundError): table.update(update_pk, {"v": 2}) def test_update_alter(fresh_db): - table = fresh_db["table"] + table = fresh_db.table("table") rowid = table.insert({"foo": "bar"}).last_pk table.update(rowid, {"new_col": 1.2}, alter=True) assert [{"foo": "bar", "new_col": 1.2}] == list(table.rows) @@ -72,7 +72,7 @@ def test_update_alter(fresh_db): def test_update_alter_with_special_column_characters(fresh_db): # With double-quote escaping, columns with special characters are now valid - table = fresh_db["table"] + table = fresh_db.table("table") rowid = table.insert({"foo": "bar"}).last_pk table.update(rowid, {"new_col[abc]": 1.2}, alter=True) assert list(table.rows) == [{"foo": "bar", "new_col[abc]": 1.2}] @@ -106,8 +106,8 @@ def test_update_with_no_values_sets_last_pk(fresh_db): ), ) def test_update_dictionaries_and_lists_as_json(fresh_db, data_structure): - fresh_db["test"].insert({"id": 1, "data": ""}, pk="id") - fresh_db["test"].update(1, {"data": data_structure}) + fresh_db.table("test").insert({"id": 1, "data": ""}, pk="id") + fresh_db.table("test").update(1, {"data": data_structure}) row = fresh_db.execute("select id, data from test").fetchone() assert row[0] == 1 assert data_structure == json.loads(row[1]) diff --git a/tests/test_upsert.py b/tests/test_upsert.py index a782b26..8274557 100644 --- a/tests/test_upsert.py +++ b/tests/test_upsert.py @@ -1,20 +1,21 @@ -from sqlite_utils.db import PrimaryKeyRequired -from sqlite_utils import Database import pytest +from sqlite_utils import Database +from sqlite_utils.db import PrimaryKeyRequired + @pytest.mark.parametrize("use_old_upsert", (False, True)) def test_upsert(use_old_upsert): db = Database(memory=True, use_old_upsert=use_old_upsert) - table = db["table"] - table.insert({"id": 1, "name": "Cleo"}, pk="id") + table = db.table("table") + table.insert_all([{"id": 1, "name": "Cleo"}], pk="id", replace=True) table.upsert({"id": 1, "age": 5}, pk="id", alter=True) assert list(table.rows) == [{"id": 1, "name": "Cleo", "age": 5}] assert table.last_pk == 1 def test_upsert_all(fresh_db): - table = fresh_db["table"] + table = fresh_db.table("table") table.upsert_all([{"id": 1, "name": "Cleo"}, {"id": 2, "name": "Nixie"}], pk="id") table.upsert_all([{"id": 1, "age": 5}, {"id": 2, "age": 5}], pk="id", alter=True) assert list(table.rows) == [ @@ -25,7 +26,7 @@ def test_upsert_all(fresh_db): def test_upsert_all_single_column(fresh_db): - table = fresh_db["table"] + table = fresh_db.table("table") table.upsert_all([{"name": "Cleo"}], pk="name") assert list(table.rows) == [{"name": "Cleo"}] assert table.pks == ["name"] @@ -33,16 +34,16 @@ def test_upsert_all_single_column(fresh_db): def test_upsert_all_not_null(fresh_db): # https://github.com/simonw/sqlite-utils/issues/538 - fresh_db["comments"].upsert_all( + fresh_db.table("comments").upsert_all( [{"id": 1, "name": "Cleo"}], pk="id", not_null=["name"], ) - assert list(fresh_db["comments"].rows) == [{"id": 1, "name": "Cleo"}] + assert list(fresh_db.table("comments").rows) == [{"id": 1, "name": "Cleo"}] def test_upsert_error_if_no_pk(fresh_db): - table = fresh_db["table"] + table = fresh_db.table("table") with pytest.raises(PrimaryKeyRequired): table.upsert_all([{"id": 1, "name": "Cleo"}]) with pytest.raises(PrimaryKeyRequired): @@ -52,7 +53,7 @@ def test_upsert_error_if_no_pk(fresh_db): @pytest.mark.parametrize("use_old_upsert", (False, True)) def test_upsert_empty_record_errors(use_old_upsert): db = Database(memory=True, use_old_upsert=use_old_upsert) - table = db["table"] + table = db.table("table") table.insert({"id": 1, "name": "Cleo"}, pk="id") with pytest.raises(PrimaryKeyRequired): table.upsert({}, pk="id") @@ -65,7 +66,7 @@ def test_upsert_empty_record_errors(use_old_upsert): @pytest.mark.parametrize("use_old_upsert", (False, True)) def test_upsert_missing_pk_value_errors(use_old_upsert): db = Database(memory=True, use_old_upsert=use_old_upsert) - table = db["table"] + table = db.table("table") table.insert({"id": 1, "name": "Cleo"}, pk="id") # Records that omit the pk column entirely with pytest.raises(PrimaryKeyRequired): @@ -77,7 +78,7 @@ def test_upsert_missing_pk_value_errors(use_old_upsert): def test_upsert_missing_compound_pk_value_errors(fresh_db): - table = fresh_db["table"] + table = fresh_db.table("table") table.insert({"a": "x", "b": "y", "v": 1}, pk=("a", "b")) # Missing one component of the detected compound primary key with pytest.raises(PrimaryKeyRequired): @@ -104,7 +105,7 @@ def test_upsert_uses_compound_pk_from_existing_table(use_old_upsert): primary key (Source, Object, Category) ) """) - table = db["summary"] + table = db.table("summary") table.upsert( { "Source": "Client A", @@ -133,7 +134,7 @@ def test_upsert_uses_compound_pk_from_existing_table(use_old_upsert): def test_upsert_with_hash_id(fresh_db): - table = fresh_db["table"] + table = fresh_db.table("table") table.upsert({"foo": "bar"}, hash_id="pk") assert [{"pk": "a5e744d0164540d33b1d7ea616c28f2fa97e754a", "foo": "bar"}] == list( table.rows @@ -143,7 +144,7 @@ def test_upsert_with_hash_id(fresh_db): @pytest.mark.parametrize("hash_id", (None, "custom_id")) def test_upsert_with_hash_id_columns(fresh_db, hash_id): - table = fresh_db["table"] + table = fresh_db.table("table") table.upsert({"a": 1, "b": 2, "c": 3}, hash_id=hash_id, hash_id_columns=("a", "b")) assert list(table.rows) == [ { @@ -166,7 +167,7 @@ def test_upsert_with_hash_id_columns(fresh_db, hash_id): def test_upsert_compound_primary_key(fresh_db): - table = fresh_db["table"] + table = fresh_db.table("table") table.upsert_all( [ {"species": "dog", "id": 1, "name": "Cleo", "age": 4}, diff --git a/tests/test_utils.py b/tests/test_utils.py index 3de5e94..360a443 100644 --- a/tests/test_utils.py +++ b/tests/test_utils.py @@ -1,8 +1,10 @@ -from sqlite_utils import utils import csv import io + import pytest +from sqlite_utils import utils + @pytest.mark.parametrize( "input,expected,should_be_is", @@ -57,7 +59,7 @@ def test_maximize_csv_field_size_limit(): # Reset to default in case other tests have changed it csv.field_size_limit(utils.ORIGINAL_CSV_FIELD_SIZE_LIMIT) long_value = "a" * 131073 - long_csv = "id,text\n1,{}".format(long_value) + long_csv = f"id,text\n1,{long_value}" fp = io.BytesIO(long_csv.encode("utf-8")) # Using rows_from_file should error with pytest.raises(csv.Error): diff --git a/tests/test_wal.py b/tests/test_wal.py index 2ddcf54..0e8f332 100644 --- a/tests/test_wal.py +++ b/tests/test_wal.py @@ -1,4 +1,5 @@ import pytest + from sqlite_utils import Database from sqlite_utils.db import TransactionError @@ -11,13 +12,13 @@ def db_path_tmpdir(tmpdir): def test_enable_disable_wal(db_path_tmpdir): - db, path, tmpdir = db_path_tmpdir + db, _path, tmpdir = db_path_tmpdir assert len(tmpdir.listdir()) == 1 assert "delete" == db.journal_mode assert "test.db-wal" not in [f.basename for f in tmpdir.listdir()] db.enable_wal() assert "wal" == db.journal_mode - db["test"].insert({"foo": "bar"}) + db.table("test").insert({"foo": "bar"}) assert "test.db-wal" in [f.basename for f in tmpdir.listdir()] db.disable_wal() assert "delete" == db.journal_mode @@ -25,32 +26,30 @@ def test_enable_disable_wal(db_path_tmpdir): def test_enable_wal_inside_transaction_raises(db_path_tmpdir): - db, path, tmpdir = db_path_tmpdir - db["test"].insert({"id": 1}, pk="id") - with pytest.raises(TransactionError): - with db.atomic(): - db["test"].insert({"id": 2}, pk="id") - db.enable_wal() + db, _path, _tmpdir = db_path_tmpdir + db.table("test").insert({"id": 1}, pk="id") + with pytest.raises(TransactionError), db.atomic(): + db.table("test").insert({"id": 2}, pk="id") + db.enable_wal() # The atomic() block must have rolled back cleanly and the # journal mode must be unchanged assert db.journal_mode == "delete" - assert [r["id"] for r in db["test"].rows] == [1] + assert [r["id"] for r in db.table("test").rows] == [1] def test_disable_wal_inside_transaction_raises(db_path_tmpdir): - db, path, tmpdir = db_path_tmpdir + db, _path, _tmpdir = db_path_tmpdir db.enable_wal() - db["test"].insert({"id": 1}, pk="id") - with pytest.raises(TransactionError): - with db.atomic(): - db["test"].insert({"id": 2}, pk="id") - db.disable_wal() + db.table("test").insert({"id": 1}, pk="id") + with pytest.raises(TransactionError), db.atomic(): + db.table("test").insert({"id": 2}, pk="id") + db.disable_wal() assert db.journal_mode == "wal" - assert [r["id"] for r in db["test"].rows] == [1] + assert [r["id"] for r in db.table("test").rows] == [1] def test_ensure_autocommit_on(db_path_tmpdir): - db, path, tmpdir = db_path_tmpdir + db, _path, _tmpdir = db_path_tmpdir previous_isolation_level = db.conn.isolation_level assert previous_isolation_level is not None with db.ensure_autocommit_on(): @@ -63,26 +62,25 @@ def test_ensure_autocommit_on(db_path_tmpdir): def test_enable_wal_noop_inside_transaction_is_allowed(db_path_tmpdir): # Calling enable_wal() when WAL is already enabled is a no-op, # so it is fine inside a transaction - db, path, tmpdir = db_path_tmpdir + db, _path, _tmpdir = db_path_tmpdir db.enable_wal() with db.atomic(): - db["test"].insert({"id": 1}, pk="id") + db.table("test").insert({"id": 1}, pk="id") db.enable_wal() - assert [r["id"] for r in db["test"].rows] == [1] + assert [r["id"] for r in db.table("test").rows] == [1] def test_ensure_autocommit_on_inside_transaction_raises(db_path_tmpdir): # Setting isolation_level commits any pending transaction as a side # effect, silently breaking the caller's rollback guarantee - so # entering autocommit mode with a transaction open is an error - db, path, tmpdir = db_path_tmpdir - db["test"].insert({"id": 1}, pk="id") + db, _path, _tmpdir = db_path_tmpdir + db.table("test").insert({"id": 1}, pk="id") db.begin() db.execute("insert into test (id) values (2)") - with pytest.raises(TransactionError): - with db.ensure_autocommit_on(): - pass + with pytest.raises(TransactionError), db.ensure_autocommit_on(): + pass # The transaction is still open and can still be rolled back assert db.conn.in_transaction db.rollback() - assert [r["id"] for r in db["test"].rows] == [1] + assert [r["id"] for r in db.table("test").rows] == [1]