def test_interleaved_excel_example_header_wrong(caplog):
data = [
["Concept", "", "", "", ""],
["", "Duala", "Ntomba", "Ngombe", "Bushoong"],
["all", "ɓɛ́sɛ̃", "(nk)umá", "ńsò", "kim"],
["", 1, 9, 10, 11],
["arm", "dia", "lobɔ́kɔ", "lò-bókò (PL: màbókò)", "lɔ̀ɔ́"],
["", 7, 1, 1, 1],
["ashes", "mabúdú", "metókó", "búdùlù ~ pùdùlù", "bu-tók"],
["", 17, 16, 17, 16],
[
"bark", "bwelé", "lopoho ~ mpoho ~ lòpòhó", "émpósù ~ ímpósù",
"yooʃ"
],
["", 23, 22, 22, 22],
["belly", "dibum", "ikundú", "lì-bùmù", "ì-kù:n"],
["", 1, 18, 1, 18],
["big", "éndɛ̃nɛ̀", "nɛ́nɛ́", "nɛ́nɛ ~ nɛ́nɛ́nɛ", "nɛ́n"],
["", 1, 1, 1, 1],
["bird", "inɔ̌n", "mpulú", "é-mbùlù ~ í-mbùlù", "pul"],
["", 1, 7, 7, 7],
["bite", "kukwa", "lamata", "kokala", "a-ʃum"],
["", 6, 2, 7, 1],
["black", "wínda", "", "hínda; épííndu", "a-picy; ndwɛɛm"],
["", 21, "", "21, 21", "22, 23"],
]
wb = openpyxl.Workbook()
ws = wb.active
for row in data:
ws.append(row)
with caplog.at_level(logging.ERROR):
with pytest.raises(SystemExit):
for row in excel_interleaved.import_interleaved(ws, ids=set()):
pass
assert "expected one or more forms" in caplog.text
def test_interleaved(interleaved_excel_example):
ids = set()
forms = [
dict(
zip(
[
"ID", "Language_ID", "Concept_ID", "Form", "Comment",
"Cognateset_ID"
],
row,
)) for row in excel_interleaved.import_interleaved(
interleaved_excel_example, logger=logging.Logger, ids=ids)
]
assert len(list(forms)) == 37
assert ids == {
"bushoong_all",
"bushoong_arm",
"bushoong_ashes",
"bushoong_bark",
"bushoong_belly",
"bushoong_big",
"bushoong_bite",
"bushoong_bird",
"bushoong_black",
"bushoong_black_s2",
"duala_all",
"duala_arm",
"duala_ashes",
"duala_bark",
"duala_belly",
"duala_big",
"duala_bird",
"duala_bite",
"duala_black",
"ngombe_all",
"ngombe_arm",
"ngombe_ashes",
"ngombe_bark",
"ngombe_belly",
"ngombe_big",
"ngombe_bird",
"ngombe_bite",
"ngombe_black",
"ngombe_black_s2",
"ntomba_all",
"ntomba_arm",
"ntomba_ashes",
"ntomba_bark",
"ntomba_belly",
"ntomba_big",
"ntomba_bird",
"ntomba_bite",
}
def test_create_metadata_valid(interleaved_excel_example):
forms = [
dict(
zip(
[
"ID", "Language_ID", "Concept_ID", "Form", "Comment",
"Cognateset_ID"
],
row,
)) for row in excel_interleaved.import_interleaved(
interleaved_excel_example)
]
path = Path(tempfile.mkdtemp())
with (path / "forms.csv").open("w", encoding="utf-8",
newline="") as form_table_file:
writer = csv.DictWriter(
form_table_file,
fieldnames=[
"ID",
"Language_ID",
"Concept_ID",
"Form",
"Comment",
"Cognateset_ID",
],
)
writer.writeheader()
writer.writerows(forms)
ds = add_metadata(path / "forms.csv")
ds.write_metadata(path / "Wordlist-metadata.json")
assert {f.name
for f in path.iterdir()
} == {"forms.csv", "Wordlist-metadata.json"}
assert len(ds.tables) == 1, "Expected a single table"
assert [c.name for c in ds["FormTable"].tableSchema.columns] == [
"ID",
"Language_ID",
"Concept_ID",
"Form",
"Comment",
"Cognateset_ID",
"Segments",
"Source",
]
assert ds.validate()
def test_interleaved_import_skips_na():
data = [
["", "Duala", "Ntomba"],
["all", "ɓɛ́sɛ̃(nk)", "umá"],
["", "1", "?"],
["arm", "?", "lobɔ́kɔ"],
["", "7", "1"],
]
# create excel with data
wb = op.Workbook()
ws = wb.active
for row in data:
ws.append(row)
# import excel
forms = [tuple(r) for r in import_interleaved(ws)]
assert forms == [
("duala_all", "Duala", "all", "ɓɛ́sɛ̃(nk)", None, "1"),
("ntomba_arm", "Ntomba", "arm", "lobɔ́kɔ", None, "1"),
]
def test_create_metadata_correct(interleaved_excel_example,
formtable_only_example):
forms = [
dict(
zip(
[
"ID", "Language_ID", "Concept_ID", "Form", "Comment",
"Cognateset_ID"
],
row,
)) for row in excel_interleaved.import_interleaved(
interleaved_excel_example, logger=logging.Logger)
]
path = Path(tempfile.mkdtemp())
with (path / "forms.csv").open("w", encoding="utf-8",
newline="") as form_table_file:
writer = csv.DictWriter(
form_table_file,
fieldnames=[
"ID",
"Language_ID",
"Concept_ID",
"Form",
"Comment",
"Cognateset_ID",
],
)
writer.writeheader()
writer.writerows(forms)
ds = add_metadata(path / "forms.csv")
ds.write_metadata(path / "Wordlist-metadata.json")
# Normalize dataset
ds.write(FormTable=list(ds["FormTable"]))
assert_datasets_are_equal(ds, formtable_only_example)