def test_parser_variant_lands_in_comment(caplog):
caplog.set_level(logging.INFO)
dataset = pycldf.Dataset.from_metadata(
Path(__file__).parent /
"data/cldf/smallmawetiguarani/cldf-metadata.json")
dataset.remove_columns("FormTable", "variants")
parser = c.CellParser(
dataset=dataset,
element_semantics=[
("/", "/", "phonemic", True),
("[", "]", "phonetic", True),
("<", ">", "orthographic", True),
("{", "}", "source", False),
("(", ")", "comment", False),
],
)
form = parser.parse_form(" {2} [dʒi'tɨka] ~[ʒi'tɨka] {2}", "language")
assert re.search(
"No 'variants' column found .* will be added to #comment.*",
caplog.text) and form == {
"Language_ID": "language",
"Value": " {2} [dʒi'tɨka] ~[ʒi'tɨka] {2}",
"phonetic": "dʒi'tɨka",
"Comment": "~[ʒi'tɨka]\t2",
"Source": {"language_s2"},
"Form": "dʒi'tɨka",
}
def test_fields_of_formtable_no_transcription(no_dialect):
dataset = no_dialect
dataset.add_columns("FormTable", "value")
dataset.add_columns("FormTable", "form")
dataset.add_columns("FormTable", "languageReference")
dataset.add_columns("FormTable", "comment")
dataset.add_columns("FormTable", "source")
# missing transcription element
with pytest.raises(
AssertionError,
match=
r"Your metadata json file and your cell parser don’t match.*transcriptions \(at least one of "
r"'orthographic', 'phonemic', and 'phonetic'\) to derive a #form.*",
):
c.CellParser(
dataset=dataset,
element_semantics=[
# ("[", "]", "phonetic", True),
("<", ">", "form", False),
# ("/", "/", "phonemic", True),
("(", ")", "comment", False),
("{", "}", "source", False),
],
)
def test_fields_of_formtable_no_source(no_dialect):
dataset = no_dialect
dataset.add_columns("FormTable", "value")
dataset.add_columns("FormTable", "form")
dataset.add_columns("FormTable", "languageReference")
dataset.add_columns("FormTable", "comment")
# missing field #source
with pytest.raises(
ValueError,
match=
"Your metadata json file and your cell parser don’t match.*#source.*",
):
c.CellParser(dataset=dataset)
def parser():
dataset = pycldf.Dataset.from_metadata(
Path(__file__).parent /
"data/cldf/smallmawetiguarani/cldf-metadata.json")
return c.CellParser(
dataset,
element_semantics=[
("/", "/", "phonemic", True),
("[", "]", "phonetic", True),
("<", ">", "orthographic", True),
("{", "}", "source", False),
("(", ")", "comment", False),
],
)