fix test helper for build_table's three-value return
build_table returns (table, reverts_column, wikitext_parser) but the
jsonl test helper still unpacked two values, so test_jsonl_noargs and
test_jsonl_tsv_equivalence failed with a ValueError before reading any
output. Also update the docstring, which still described the two-value
return.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
(cherry picked from commit 7c27942cb0)
This commit is contained in:
@@ -122,8 +122,10 @@ def build_table(
|
|||||||
"""Build the RevisionTable with appropriate columns based on flags.
|
"""Build the RevisionTable with appropriate columns based on flags.
|
||||||
|
|
||||||
Returns:
|
Returns:
|
||||||
(table, reverts_column) - the table and a reference to the reverts column
|
(table, reverts_column, wikitext_parser) - the table, a reference to
|
||||||
(which process() needs for setting the revert detector).
|
the reverts column (which process() needs for setting the revert
|
||||||
|
detector), and the wikitext parser (None unless a wikitext-parsing
|
||||||
|
column was requested).
|
||||||
"""
|
"""
|
||||||
reverts_column = tables.RevisionReverts()
|
reverts_column = tables.RevisionReverts()
|
||||||
|
|
||||||
|
|||||||
@@ -38,7 +38,7 @@ setup()
|
|||||||
|
|
||||||
def read_jsonl_with_schema(filepath: str, **schema_kwargs) -> pd.DataFrame:
|
def read_jsonl_with_schema(filepath: str, **schema_kwargs) -> pd.DataFrame:
|
||||||
"""Read JSONL file using PyArrow with explicit schema from wikiq."""
|
"""Read JSONL file using PyArrow with explicit schema from wikiq."""
|
||||||
table, _ = build_table(**schema_kwargs)
|
table, _, _ = build_table(**schema_kwargs)
|
||||||
schema = build_schema(table, **schema_kwargs)
|
schema = build_schema(table, **schema_kwargs)
|
||||||
pa_table = pj.read_json(
|
pa_table = pj.read_json(
|
||||||
filepath,
|
filepath,
|
||||||
|
|||||||
Reference in New Issue
Block a user