mirror of
https://github.com/MadsLorentzen/ai-job-search.git
synced 2026-09-17 00:26:26 +00:00
Erik Pastor RiosandClaude Opus 4.8
a278ad7a50
* refactor(salary): make compound-word matching locale-agnostic The Excel column detector hardcoded a DANISH_COMPOUND_PATTERNS set inside header_matches(), so the compound-word matching that helps Danish headers (e.g. "lønindeks") was baked into the algorithm by name and unavailable to any other locale without editing the source. Rename it to COMPOUND_PATTERNS and pass it as a parameter (default unchanged, so the Danish demonstration data behaves identically). A different-locale spreadsheet can now supply its own compound tokens via header_matches(..., compound_patterns=...). Add a test covering both the preserved default and the parameterized path. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * refactor(salary): drop unused compound_patterns parameter Per review: keep the DANISH_COMPOUND_PATTERNS -> COMPOUND_PATTERNS rename (universal template naming, defaults still Danish), but remove the compound_patterns= parameter. No caller passes a custom set, and a fork adapting another locale edits the module-level constant either way, so parameterizing it is speculative generality per CONTRIBUTING.md. header_matches() now reads COMPOUND_PATTERNS directly. Test updated to verify compound-vs-whole-token matching against the constant. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
83 lines
3.0 KiB
Python
83 lines
3.0 KiB
Python
import unittest
|
|
from types import SimpleNamespace
|
|
|
|
from tools.convert_salary_excel import (
|
|
INDEX_PATTERNS,
|
|
detect_column_type,
|
|
header_matches,
|
|
parse_sheet,
|
|
)
|
|
|
|
|
|
class FakeWorksheet:
|
|
title = "Sheet1"
|
|
|
|
def __init__(self, rows):
|
|
self.rows = rows
|
|
|
|
def iter_rows(self, min_row=1, max_row=None, values_only=False):
|
|
rows = self.rows[min_row - 1:max_row]
|
|
for row in rows:
|
|
if values_only:
|
|
yield row
|
|
else:
|
|
yield [SimpleNamespace(value=value) for value in row]
|
|
|
|
def __getitem__(self, row_number):
|
|
return [SimpleNamespace(value=value) for value in self.rows[row_number - 1]]
|
|
|
|
|
|
class DetectColumnTypeTests(unittest.TestCase):
|
|
def test_index_headers_are_not_misclassified_as_count(self):
|
|
for header in ("Index", "Salary Index", "Engineering Index", "Median salary"):
|
|
with self.subTest(header=header):
|
|
self.assertEqual(detect_column_type(header), "index")
|
|
|
|
def test_single_letter_n_only_matches_as_a_token(self):
|
|
self.assertEqual(detect_column_type("Employee n"), "count")
|
|
self.assertEqual(detect_column_type("Engineering"), None)
|
|
|
|
def test_count_headers_still_match_common_labels(self):
|
|
for header in ("Count", "Engineering Count", "Antal medarbejdere"):
|
|
with self.subTest(header=header):
|
|
self.assertEqual(detect_column_type(header), "count")
|
|
|
|
def test_count_inside_word_does_not_make_count_header(self):
|
|
self.assertIsNone(detect_column_type("Accounting Total"))
|
|
self.assertEqual(detect_column_type("Accounting Index"), "index")
|
|
|
|
def test_danish_compound_headers_still_match(self):
|
|
self.assertEqual(detect_column_type("Lønindeks"), "index")
|
|
|
|
def test_compound_patterns_match_as_substring_but_others_do_not(self):
|
|
# A compound token (Danish "løn") matches inside a glued header word.
|
|
self.assertTrue(header_matches("lønindeks", INDEX_PATTERNS))
|
|
# A pattern that is not a compound token ("salary") only matches as a
|
|
# whole token, so it must not match inside an unrelated glued word.
|
|
self.assertFalse(header_matches("salaryindex", INDEX_PATTERNS))
|
|
self.assertTrue(header_matches("salary index", INDEX_PATTERNS))
|
|
|
|
def test_parse_sheet_preserves_category_name_with_letter_n(self):
|
|
ws = FakeWorksheet([
|
|
("Company", "Engineering Count", "Engineering Index"),
|
|
("Example Corp", 12, 105.5),
|
|
])
|
|
|
|
companies = parse_sheet(ws)
|
|
|
|
self.assertEqual(companies[0]["categories"]["engineering"], {"count": 12, "index": 105.5})
|
|
|
|
def test_parse_sheet_groups_accounting_count_index_pair(self):
|
|
ws = FakeWorksheet([
|
|
("Company", "Accounting Count", "Accounting Index"),
|
|
("Example Corp", 12, 105.5),
|
|
])
|
|
|
|
companies = parse_sheet(ws)
|
|
|
|
self.assertEqual(companies[0]["categories"]["accounting"], {"count": 12, "index": 105.5})
|
|
|
|
|
|
if __name__ == "__main__":
|
|
unittest.main()
|