remote/sqlite-utils
1
0
Fork 0
mirror of https://github.com/simonw/sqlite-utils.git synced 2026-10-31 07:27:50 +01:00
Code Issues Projects Releases Packages Wiki Activity

Forward ignore_extras= and extras_key= from the TSV and auto-detect paths

Browse source 
Both branches that recurse into the CSV branch called rows_from_file()
without forwarding the two arguments, so the inner call applied its own
defaults and raised RowError even when the caller had explicitly asked
to ignore or capture the extras. The outer _extra_key_strategy wrapper
in each branch was dead code as a result.

Forward both arguments and drop the redundant wrapper, so the strategy
is applied once on the shared CSV path. With no options passed the
behaviour is unchanged.

Fixes #892
This commit is contained in:
feiiiiii5 2026-09-30 19:29:23 +08:00
commit d5d01b3f9e
2 changed files with 50 additions and 18 deletions
Download patch file Download diff file Expand all files Collapse all files

35
sqlite_utils/utils.py
View file

@ -358,17 +358,18 @@ def rows_from_file(
)
return _CloseableIterator(iter(rows), decoded_fp), Format.CSV
elif format == Format.TSV:
# The inner call applies the extra-field strategy, so the
# ignore_extras= and extras_key= arguments must be passed to it -
# see https://github.com/simonw/sqlite-utils/issues/892
rows, _ = rows_from_file(
fp, format=Format.CSV, dialect=csv.excel_tab, encoding=encoding
)
return (
_extra_key_strategy(
cast(Iterable[dict[str | None, object]], rows),
ignore_extras,
extras_key,
),
Format.TSV,
fp,
format=Format.CSV,
dialect=csv.excel_tab,
encoding=encoding,
ignore_extras=ignore_extras,
extras_key=extras_key,
)
return rows, Format.TSV
elif format is None:
# Detect the format, then call this recursively
buffered = io.BufferedReader(cast(io.RawIOBase, fp), buffer_size=4096)
@ -393,18 +394,16 @@ def rows_from_file(
first_bytes.decode(encoding or "utf-8-sig", "ignore")
)
rows, _ = rows_from_file(
buffered, format=Format.CSV, dialect=dialect, encoding=encoding
buffered,
format=Format.CSV,
dialect=dialect,
encoding=encoding,
ignore_extras=ignore_extras,
extras_key=extras_key,
)
# Make sure we return the format we detected
detected_format = Format.TSV if dialect.delimiter == "\t" else Format.CSV
return (
_extra_key_strategy(
cast(Iterable[dict[str | None, object]], rows),
ignore_extras,
extras_key,
),
detected_format,
)
return rows, detected_format
else:
raise RowsFromFileError("Bad format")