feat(pdf): default output date format to YYYY-MM-DD
User asked to flip the default from YYYYMMDD to YYYY-MM-DD. ISO is the better default for an accountant CSV workflow: - Lexicographic sort = chronological sort (no parsing needed). - Every spreadsheet tool the user might import into recognises it as a real date with no ambiguity (US vs EU readers can't disagree on the order). - Hyphens make the year/month/day boundaries scan-able by eye. Concrete changes: - New module constant ``DEFAULT_DATE_FORMAT = "%Y-%m-%d"``, used as the default for ``format_date()`` and the ``output_date_format`` keyword on ``scan_pdf_for_transactions``. - Page's ``_DATE_FORMAT_CHOICES`` reordered so the ISO entry is first (index 0 = default Streamlit selection); YYYYMMDD drops to second. - Custom-strftime input default also flips to ``%Y-%m-%d``. Tests updated to reflect the new default (``test_dates_formatted_iso_by_default``, ``test_short_dates_get_year_from_period``, ``test_compact_format_round_trip``, plus a new ``test_default_is_iso`` for the format_date helper). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
@@ -520,6 +520,13 @@ def _find_amount_tokens(
|
||||
return out
|
||||
|
||||
|
||||
DEFAULT_DATE_FORMAT = "%Y-%m-%d"
|
||||
"""ISO-8601-style ``YYYY-MM-DD``. Default for output date columns
|
||||
because it sorts lexicographically, parses in every spreadsheet
|
||||
tool the user might import the CSV into, and is unambiguous
|
||||
across US/EU readers."""
|
||||
|
||||
|
||||
def format_amount(value, places: int = 2) -> str:
|
||||
"""Render an amount value as a fixed-precision string.
|
||||
|
||||
@@ -549,7 +556,7 @@ def format_amount(value, places: int = 2) -> str:
|
||||
return str(value)
|
||||
|
||||
|
||||
def format_date(iso_str: str | None, fmt: str = "%Y%m%d") -> str:
|
||||
def format_date(iso_str: str | None, fmt: str = DEFAULT_DATE_FORMAT) -> str:
|
||||
"""Convert an ISO ``YYYY-MM-DD`` date string to *fmt*.
|
||||
|
||||
Returns the input unchanged if it's not parseable as ISO,
|
||||
@@ -840,7 +847,7 @@ def scan_pdf_for_transactions(
|
||||
date_formats: list[str] | None = None,
|
||||
y_tolerance: float = 3.0,
|
||||
merge_multiline_descriptions: bool = True,
|
||||
output_date_format: str = "%Y%m%d",
|
||||
output_date_format: str = DEFAULT_DATE_FORMAT,
|
||||
filename_year_hint: int | None = None,
|
||||
year_override: int | None = None,
|
||||
) -> tuple[list[dict[str, Any]], list[str]]:
|
||||
@@ -850,7 +857,7 @@ def scan_pdf_for_transactions(
|
||||
amount pattern. Each returned record looks like::
|
||||
|
||||
{
|
||||
"date": "20260115", # output_date_format applied
|
||||
"date": "2026-01-15", # output_date_format applied
|
||||
"description": "...",
|
||||
"amount_1": 4.50,
|
||||
"amount_2": 1000.00, # if a second amount was found
|
||||
|
||||
Reference in New Issue
Block a user