insert/upsert --csv no longer rewrites column types of existing tables

Type detection is the 4.0 default for CSV/TSV data, and the detected-type
transform ran even when the target table already existed - inserting a
CSV into a table with a TEXT zip column converted the column to INTEGER,
corrupting values with leading zeros ('01234' became 1234) with no
warning. Detected types now only apply to tables the command created.

Refs https://github.com/simonw/sqlite-utils/issues/769#issuecomment-4900034150

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Simon Willison 2026-07-06 21:44:56 -07:00
commit 884574685f
4 changed files with 62 additions and 1 deletions

View file

@ -628,3 +628,51 @@ def test_insert_into_view_errors(tmpdir):
)
assert result.exit_code == 1
assert result.output.strip() == "Error: Table v is actually a view"
def test_insert_csv_detect_types_leaves_existing_table_alone(db_path):
# Type detection is the default for CSV/TSV inserts, but it must only
# apply to tables created by this command - transforming a pre-existing
# 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"})
result = CliRunner().invoke(
cli.cli,
["insert", db_path, "places", "-", "--csv"],
catch_exceptions=False,
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) == [
{"name": "Boston", "zip": "01234"},
{"name": "SF", "zip": "94107"},
]
def test_insert_csv_detect_types_new_table(db_path):
# A table created by the insert still gets detected types
result = CliRunner().invoke(
cli.cli,
["insert", db_path, "data", "-", "--csv"],
catch_exceptions=False,
input="name,age,weight\nCleo,5,12.5",
)
assert result.exit_code == 0, result.output
db = Database(db_path)
assert db["data"].columns_dict == {"name": str, "age": int, "weight": float}
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")
result = CliRunner().invoke(
cli.cli,
["upsert", db_path, "places", "-", "--csv", "--pk", "id"],
catch_exceptions=False,
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"