def _get_part_matcher():
"""Return the part matcher."""
# Transistor Naming Conventions as Regular Expressions
eeca_rgx = (r"([ABC][A-Z][WXYZ]?[0-9]{3,5}(?:[A-Z]){0,5}[0-9]?[A-Z]?"
r"(?:-[A-Z0-9]{1,7})?(?:[-][A-Z0-9]{1,2})?(?:\/DG)?)")
jedec_rgx = r"(2N\d{3,4}[A-Z]{0,5}[0-9]?[A-Z]?)"
jis_rgx = r"(2S[ABCDEFGHJKMQRSTVZ]{1}[\d]{2,4})"
others_rgx = (
r"((?:NSVBC|SMBT|MJ|MJE|MPS|MRF|RCA|TIP|ZTX|ZT|ZXT|TIS|TIPL|DTC|MMBT"
r"|SMMBT|PZT|FZT|STD|BUV|PBSS|KSC|CXT|FCX|CMPT){1}[\d]{2,4}[A-Z]{0,5}"
r"(?:-[A-Z0-9]{0,6})?(?:[-][A-Z0-9]{0,1})?)")
part_rgx = "|".join([eeca_rgx, jedec_rgx, jis_rgx, others_rgx])
add_rgx = r"^[A-Z0-9\-]{5,15}$"
part_file_name_lambda_matcher = LambdaFunctionMatcher(
func=_part_file_name_conditions)
part_rgx_matcher = RegexMatchSpan(rgx=part_rgx, longest_match_only=True)
part_dict_matcher = DictionaryMatch(d=_get_digikey_parts_set(DICT_PATH))
part_file_name_matcher = Intersect(
RegexMatchSpan(rgx=add_rgx, longest_match_only=True),
part_file_name_lambda_matcher,
)
return Union(part_rgx_matcher, part_dict_matcher, part_file_name_matcher)
def test_dictionary_match(doc_setup):
"""Test DictionaryMatch matcher."""
doc = doc_setup
space = MentionNgrams(n_min=1, n_max=1)
# Test with a list of str
matcher = DictionaryMatch(d=["this"])
assert set(tc.get_span() for tc in matcher.apply(space.apply(doc))) == {"This"}
# Test without a dictionary
with pytest.raises(Exception):
DictionaryMatch()
# TODO: test with plural words
matcher = DictionaryMatch(d=["is"], stemmer=PorterStemmer())
assert set(tc.get_span() for tc in matcher.apply(space.apply(doc))) == {"is"}
# Test if matcher raises an error when _f is given non-TemporarySpanMention
matcher = DictionaryMatch(d=["this"])
with pytest.raises(ValueError):
list(matcher.apply(doc.sentences[0].words))
def test_do_not_use_stemmer_when_UnicodeDecodeError():
"""Test DictionaryMatch when stemmer causes UnicodeDecodeError."""
stemmer = PorterStemmer()
matcher = DictionaryMatch(d=["is"], stemmer=stemmer)
# _stem(w) should return a word stem.
assert matcher._stem("caresses") == "caress"
stemmer.stem = Mock(side_effect=UnicodeDecodeError(
"dummycodec", b"\x00\x00", 1, 2, "Dummy !"))
matcher = DictionaryMatch(d=["is"], stemmer=stemmer)
# _stem(w) should return w as stemmer.stem raises UnicodeDecodeError.
assert matcher._stem("caresses") == "caresses"
def get_digikey_parts_set(path):
"""Get all transistor parts from digikey part dictionary."""
all_parts = set()
with open(path, "r") as csvinput:
reader = csv.reader(csvinput)
for line in reader:
(part, url) = line
all_parts.add(part)
return all_parts
# Dictionary of known transistor parts ###
dict_path = "tests/data/digikey_part_dictionary.csv"
part_dict_matcher = DictionaryMatch(d=get_digikey_parts_set(dict_path))
def common_prefix_length_diff(str1, str2):
"""Calculate common prefix length difference."""
for i in range(min(len(str1), len(str2))):
if str1[i] != str2[i]:
return min(len(str1), len(str2)) - i
return 0
def part_file_name_conditions(attr):
"""Check part file name conditions."""
file_name = attr.sentence.document.name
if len(file_name.split("_")) != 2:
return False