giteadmin/datatools-dev
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(pdf): drop statement_period_start/end columns from output

Browse Source 
User asked to remove them — the two columns repeated the same
value on every row from a given statement, took up screen space
in the editor, and offered limited value once the date column
already carries the inferred full date.

What's kept:
- ``account_number`` — still stamped onto every row so multi-
  statement CSVs are self-attributing
- ``extract_statement_metadata`` — still runs every scan because
  ``period_end`` is the source of the year inference that binds
  Chase-style short ``01/13`` dates to ``20250113``
- ``_extract_statement_period`` and its tests — period
  detection itself isn't going anywhere, just its appearance in
  the output rows

What's removed:
- ``record["statement_period_start"]`` / ``record["statement_period_end"]``
  assignments in ``scan_pdf_for_transactions``
- The two columns from the page's column-ordering setup
- Tests pinning their presence; replaced with assertions that
  they're explicitly absent

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Michael
2026-05-20 01:28:32 +00:00
parent ad7c22d7fb
commit 34b56b404a
3 changed files with 34 additions and 33 deletions
Download Patch File Download Diff File Expand all files Collapse all files

30
tests/test_pdf_extract_smoke.py
View File

@@ -153,16 +153,16 @@ class TestScanPdfForTransactions:
"2026-01-15", "2026-01-16", "2026-01-17",
]
def test_metadata_fields_present_on_every_row(self, pdf_bytes):
def test_account_number_field_present_on_every_row(self, pdf_bytes):
from src.pdf_extract import scan_pdf_for_transactions
rows, _ = scan_pdf_for_transactions(pdf_bytes)
# The fixture PDF has no statement-period or account
# header, so the metadata fields exist but are empty
# strings — the contract is: ALWAYS present on every row.
# ``account_number`` is the only per-row metadata field that
# surfaces in the CSV; the period fields are extracted but
# used only for internal year inference.
for r in rows:
assert "account_number" in r
assert "statement_period_start" in r
assert "statement_period_end" in r
assert "statement_period_start" not in r
assert "statement_period_end" not in r
def test_parses_amounts_with_signs(self, pdf_bytes):
from src.pdf_extract import scan_pdf_for_transactions
@@ -214,30 +214,36 @@ class TestStatementHeaderEndToEnd:
def pdf_bytes(self) -> bytes:
return _build_statement_pdf_with_header()
def test_metadata_extracted_and_stamped(self, pdf_bytes):
def test_account_number_stamped(self, pdf_bytes):
from src.pdf_extract import scan_pdf_for_transactions
rows, _ = scan_pdf_for_transactions(pdf_bytes)
assert rows, "expected at least one transaction"
for r in rows:
assert r["account_number"] == "****5678"
assert r["statement_period_start"] == "20250101"
assert r["statement_period_end"] == "20250131"
def test_short_dates_get_year_from_period(self, pdf_bytes):
from src.pdf_extract import scan_pdf_for_transactions
rows, _ = scan_pdf_for_transactions(pdf_bytes)
# Short ``01/13`` + period ending in 2025 → 20250113
# Short ``01/13`` + period ending in 2025 → 20250113.
# The period itself isn't surfaced as a column anymore, but
# the year inference that depends on it still works because
# extraction happens internally before the per-row stamp.
assert rows[0]["date"] == "20250113"
assert rows[1]["date"] == "20250116"
def test_period_fields_not_in_output(self, pdf_bytes):
from src.pdf_extract import scan_pdf_for_transactions
rows, _ = scan_pdf_for_transactions(pdf_bytes)
for r in rows:
assert "statement_period_start" not in r
assert "statement_period_end" not in r
def test_iso_format_round_trip(self, pdf_bytes):
from src.pdf_extract import scan_pdf_for_transactions
rows, _ = scan_pdf_for_transactions(
pdf_bytes, output_date_format="%Y-%m-%d",
)
assert rows[0]["date"] == "2025-01-13"
assert rows[0]["statement_period_start"] == "2025-01-01"
assert rows[0]["statement_period_end"] == "2025-01-31"
class TestMultiDateRow: