familienarchiv/tools/import-normalizer/tests/test_documents.py

import persons
import documents
from documents import Triage

def test_extract_row():
    header = {"index": 0, "file": 1, "box": 2, "folder": 3, "sender": 4,
              "receivers": 5, "date": 6, "location": 7, "tags": 8, "summary": 9}
    cells = ["W-0001", r"..\__scan\W-0001.pdf", "V", "1", "Walter de Gruyter",
             "Eugenie Müller", "15.2.1888", "Rotterdam", "Brautbriefe", "Geschäftsreise"]
    raw = documents.extract_row(cells, header, source_row=3)
    assert raw.index == "W-0001"
    assert raw.sender == "Walter de Gruyter"
    assert raw.date == "15.2.1888"
    assert raw.source_row == 3

def test_triage():
    assert documents.triage(["", "", ""]) == Triage.EMPTY
    assert documents.triage(["", "", "Walter"]) == Triage.BLANK_INDEX  # data but no index
    assert documents.triage(["W-0001x", "x"]) == Triage.X_SUFFIX
    assert documents.triage(["W-0001", "x"]) == Triage.OK

def test_classify_blank_index():
    header = {"sender": 4, "receivers": 5}
    banner = ["", "", "", "", "Brautbriefe von Walter an Eugenie", ""]
    data = ["", "", "V", "1", "", "Eugenie"]
    assert documents.classify_blank_index(banner, header) == "section_banner"
    assert documents.classify_blank_index(data, header) == "data_no_index"

def test_index_file_mismatch():
    assert documents.index_file_mismatch("W-0010x", r"..\__scan\W-0011x.pdf") is True
    assert documents.index_file_mismatch("W-0001", r"..\__scan\W-0001.pdf") is False
    assert documents.index_file_mismatch("W-0001", "") is False
    assert documents.index_file_mismatch("W-0001", "scans/W-0001.pdf") is False  # unix path
    assert documents.index_file_mismatch("W-0001", "W-0001.pdf") is False         # no dir


def _ctx():
    people = persons.parse_register([
        {"last_name": "de Gruyter", "first_name": "Walter"},
        {"last_name": "de Gruyter", "first_name": "Eugenie", "maiden_name": "Müller"},
    ])
    return persons.ResolutionContext(persons.AliasIndex(people), name_overrides={})

def test_to_canonical_resolves_and_flags():
    ctx = _ctx()
    raw = documents.RawRow(source_row=3, index="W-0001", box="V", folder="1",
                           sender="Walter de Gruyter", receivers="Eugenie Müller",
                           date="15.2.1888", location="Rotterdam", tags="Brautbriefe",
                           summary="Geschäftsreise", file=r"..\__scan\W-0001.pdf")
    doc = documents.to_canonical(raw, ctx, date_overrides={})
    assert doc.sender_person_id == "de-gruyter-walter"
    assert doc.receiver_person_ids == ["de-gruyter-eugenie"]   # matched via maiden alias
    assert doc.date_iso == "1888-02-15" and doc.date_precision == "DAY"
    assert doc.tags == ["Themen/Brautbriefe"]
    assert doc.file == r"..\__scan\W-0001.pdf"   # file name carried through for the importer
    assert doc.needs_review == []


def test_to_canonical_carries_file_name():
    ctx = _ctx()
    raw = documents.RawRow(source_row=4, index="H-0730", sender="", receivers="",
                           file="H-0730.pdf")
    doc = documents.to_canonical(raw, ctx, date_overrides={})
    assert doc.file == "H-0730.pdf"


def test_to_canonical_range_carries_date_end():
    ctx = _ctx()
    raw = documents.RawRow(source_row=4, index="H-0730", sender="", receivers="",
                           date="10./11.1.1917")
    doc = documents.to_canonical(raw, ctx, date_overrides={})
    assert doc.date_iso == "1917-01-10"
    assert doc.date_precision == "RANGE"
    assert doc.date_end == "1917-01-11"


def test_to_canonical_non_range_has_empty_date_end():
    ctx = _ctx()
    raw = documents.RawRow(source_row=4, index="H-0730", sender="", receivers="",
                           date="15.2.1888")
    doc = documents.to_canonical(raw, ctx, date_overrides={})
    assert doc.date_precision == "DAY"
    assert doc.date_end == ""

def test_to_canonical_unmatched_and_unparsed():
    ctx = _ctx()
    raw = documents.RawRow(source_row=9, index="C-0001",
                           sender="Hans Wittkopf", receivers="", date="Freitag 1919")
    doc = documents.to_canonical(raw, ctx, date_overrides={})
    assert doc.sender_person_id == "wittkopf-hans"            # provisional
    assert "unmatched_sender" in doc.needs_review
    assert "unparsed_date" in doc.needs_review
    assert ctx.unmatched["Hans Wittkopf"] == [9]
    assert any(p.provisional for p in ctx.provisional.values())

def test_to_canonical_splits_multi_sender():
    # REQ-PERS-01 / IMP-11: a multi-person sender is parsed, primary kept, flagged.
    ctx = _ctx()
    raw = documents.RawRow(source_row=5, index="C-0100", sender="Walter und Eugenie de Gruyter", receivers="")
    doc = documents.to_canonical(raw, ctx, date_overrides={})
    assert doc.sender_person_id == "de-gruyter-walter"   # first part is primary
    assert "multi_sender" in doc.needs_review

def test_provisional_id_never_collides_with_register():
    # A provisional built from an unmatched string must not steal a register person_id.
    people = persons.parse_register([{"last_name": "Xyz", "first_name": "Abc"}])  # id "xyz-abc"
    ctx = persons.ResolutionContext(persons.AliasIndex(people), name_overrides={})
    # "Abc, Xyz" misses the alias index (the comma changes the normalized key) but its
    # provisional slug is "xyz-abc" — already the register person's id, so it MUST be suffixed.
    pid, _, matched = ctx.resolve_one("Abc, Xyz", source_row=1)
    assert matched is False
    assert "xyz-abc" in ctx.index.known_ids
    assert pid == "xyz-abc-2"   # suffixed away from the register id, not reused

def test_resolve_one_override_increments_hits():
    people = persons.parse_register([{"last_name": "de Gruyter", "first_name": "Eugenie"}])
    ctx = persons.ResolutionContext(persons.AliasIndex(people),
                                    name_overrides={"Genie": "de-gruyter-eugenie"})
    pid, name, matched = ctx.resolve_one("Genie", source_row=1)
    assert pid == "de-gruyter-eugenie" and matched is True
    assert name == "Eugenie de Gruyter"   # display comes from the alias index
    assert ctx.override_hits == 1

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 — 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