marcel/familienarchiv
1
0
Fork 0
Code Issues 109 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

feat(normalizer): unresolved-names report + fix ambiguous-pair over-flagging

Browse Source 
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
Marcel
2026-05-25 15:54:37 +02:00
parent f10b80a03f
commit 97ab9e38df
4 changed files with 44 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
tools/import-normalizer/tests/test_documents.py
View File

@@ -93,10 +93,17 @@ def test_resolve_one_override_increments_hits():
assert name == "Eugenie de Gruyter" # display comes from the alias index
assert ctx.override_hits == 1
def test_ambiguous_space_pair_flagged_not_split():
# US-PERS-02 AC4: "Ella Anita" is kept as one provisional + flagged, never guessed into two.
ctx = _ctx()
def test_ambiguous_pair_recorded_in_unresolved():
people = persons.parse_register([{"last_name": "de Gruyter", "first_name": "Walter"}])
ctx = persons.ResolutionContext(persons.AliasIndex(people), name_overrides={},
given_names={"ella", "anita"})
raw = documents.RawRow(source_row=7, index="C-0200", sender="", receivers="Ella Anita")
doc = documents.to_canonical(raw, ctx, date_overrides={})
assert len(doc.receiver_person_ids) == 1 # not split
assert any(part == "Ella Anita" for _, part, _ in ctx.ambiguous)
assert len(doc.receiver_person_ids) == 1 # not split — one provisional
assert any(name == "Ella Anita" and cat == "ambiguous_pair" for name, cat, _ in ctx.unresolved)
def test_resolvable_first_surname_pair_not_unresolved():
ctx = persons.ResolutionContext(persons.AliasIndex([]), name_overrides={},
given_names={"ella", "anita"})
ctx.resolve_one("Mieze Schefold", source_row=1) # surname is not a given name
assert ctx.unresolved == [] # RESOLVABLE -> not recorded

7
tools/import-normalizer/tests/test_normalize.py
View File

@@ -10,7 +10,7 @@ def _doc_wb(tmp_path):
"Eugenie Müller", "15.2.1888", "Rotterdam", "Brautbriefe", "Geschäftsreise"])
ws.append(["W-0001x", r"..\__scan\W-0001x.pdf", "", "", "Walter de Gruyter", "Eugenie Müller", "", "", "", ""])
ws.append(["", "", "", "", "Section banner row", "", "", "", "", ""])
ws.append(["C-0001", "", "", "", "Hans Wittkopf", "", "Freitag 1919", "", "", ""])
ws.append(["C-0001", "", "", "", "Hans Wittkopf", "?", "Freitag 1919", "", "", ""])
ws.append(["W-0001", r"..\__scan\W-0001.pdf", "V", "1", "Walter de Gruyter",
"Eugenie Müller", "15.2.1888", "Rotterdam", "Brautbriefe", "dup"])
p = tmp_path / "docs.xlsx"; wb.save(p); return p
@@ -42,6 +42,11 @@ def test_run_end_to_end(tmp_path):
assert (review_dir / "unparsed-dates.csv").exists()
# C-0001's "Freitag 1919" is unparseable -> must appear in the review file (NFR-DATA-01)
assert "Freitag 1919" in (review_dir / "unparsed-dates.csv").read_text(encoding="utf-8")
assert (out_dir / "canonical-documents.xlsx").exists() # (keep existing asserts above)
assert (review_dir / "unresolved-names.csv").exists()
unresolved_text = (review_dir / "unresolved-names.csv").read_text(encoding="utf-8")
assert "unknown" in unresolved_text and "?" in unresolved_text # the "?" receiver
assert not (review_dir / "ambiguous-receivers.csv").exists() # replaced
# determinism (NFR-IDEM-01): a second run yields identical canonical content + review files
def _matrix(p):