diff --git a/docs/changelog.rst b/docs/changelog.rst index cf9486a..a9dd4a3 100644 --- a/docs/changelog.rst +++ b/docs/changelog.rst @@ -10,6 +10,7 @@ Unreleased ---------- - ``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 insert`` and ``sqlite-utils upsert`` now accept a ``--code`` option for 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`) .. _v4_0: diff --git a/docs/cli-reference.rst b/docs/cli-reference.rst index 5ea9200..5798809 100644 --- a/docs/cli-reference.rst +++ b/docs/cli-reference.rst @@ -230,7 +230,7 @@ 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. @@ -272,8 +272,20 @@ 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 @@ -315,7 +327,7 @@ 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 @@ -332,6 +344,8 @@ See :ref:`cli_upsert`. 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 diff --git a/docs/cli.rst b/docs/cli.rst index e373704..4ed92ed 100644 --- a/docs/cli.rst +++ b/docs/cli.rst @@ -1561,6 +1561,27 @@ 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 diff --git a/sqlite_utils/cli.py b/sqlite_utils/cli.py index b99dcf1..4eefc70 100644 --- a/sqlite_utils/cli.py +++ b/sqlite_utils/cli.py @@ -944,13 +944,19 @@ 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 + ( @@ -1035,11 +1041,118 @@ 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) + + def _insert_docs(docs, tracker=None): + 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, 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( + "{}\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) + + 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: @@ -1147,78 +1260,7 @@ 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, 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( - "{}\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: @@ -1261,6 +1303,7 @@ def insert( table, file, pk, + code, flatten, nl, csv, @@ -1332,6 +1375,17 @@ 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( @@ -1367,6 +1421,7 @@ def insert( not_null=not_null, default=default, strict=strict, + code=code, ) except UnicodeDecodeError as ex: raise click.ClickException(UNICODE_ERROR.format(ex)) @@ -1379,6 +1434,7 @@ def upsert( table, file, pk, + code, flatten, nl, csv, @@ -1450,6 +1506,7 @@ def upsert( load_extension=load_extension, silent=silent, strict=strict, + code=code, ) except UnicodeDecodeError as ex: raise click.ClickException(UNICODE_ERROR.format(ex)) @@ -3669,3 +3726,32 @@ 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("File not found: {}".format(code)) + namespace = {} + try: + exec(code, namespace) + except SyntaxError as ex: + raise click.ClickException("Error in --code: {}".format(ex)) + rows = 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/tests/test_cli_insert.py b/tests/test_cli_insert.py index 5af8a2f..e290f97 100644 --- a/tests/test_cli_insert.py +++ b/tests/test_cli_insert.py @@ -691,3 +691,153 @@ 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["creatures"].pks == ["id"] + assert list(db["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)["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["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["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)["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