def __init__(self, lemmatizer_type=LemmatizerType.english_nltk):
self._lemmatizer_type = lemmatizer_type
self._lemmatizer = None
if lemmatizer_type == self.LemmatizerType.english_nltk:
self._lemmatizer = WordNetLemmatizer()
elif lemmatizer_type == self.LemmatizerType.english_spacy:
# Use precalculated files for spacy since free google colab can't handle fasttext model and spacy lemmatizer at once
if not FileUtil.file_exists(PRECALCULATED_SPACY_ENGLISH_LEMMA_CSV):
log.error(
f"{PRECALCULATED_SPACY_ENGLISH_LEMMA_CSV} does not exists. The spacy lemmatizer needs an precalculated lemma file."
)
self._lemmatizer = PandasUtil.read_csv_to_dataframe(
PRECALCULATED_SPACY_ENGLISH_LEMMA_CSV)
elif lemmatizer_type == self.LemmatizerType.italian_nltk:
self._lemmatizer = SnowballStemmer("italian")
elif lemmatizer_type == self.LemmatizerType.italian_spacy:
# Use precalculated files for spacy since free google colab can't handle fasttext model and spacy lemmatizer at once
if not FileUtil.file_exists(PRECALCULATED_SPACY_ITALIAN_LEMMA_CSV):
log.error(
f"{PRECALCULATED_SPACY_ITALIAN_LEMMA_CSV} does not exists. The spacy lemmatizer needs an precalculated lemma file."
)
self._lemmatizer = PandasUtil.read_csv_to_dataframe(
PRECALCULATED_SPACY_ITALIAN_LEMMA_CSV)
else:
log.error(f"Unknown case for LemmatizerType: {lemmatizer_type}")
def _run(self,
final_thresholds,
maj_thresholds,
matrix_file_path=None,
artifact_map_file_path=None):
if not matrix_file_path:
matrix_file_path = self.default_matrix_path()
if not artifact_map_file_path:
artifact_map_file_path = self._default_a2eMap_path()
if not FileUtil.file_exists(matrix_file_path):
log.error(
f"File does not exists: {matrix_file_path}\n"
f"Please pass a valid file path or call {self.__class__.__name__}().precalculate() first"
)
if not FileUtil.file_exists(artifact_map_file_path):
log.error(
f"File does not exists: {artifact_map_file_path}\n"
f"Please pass a valid file path or call {self.__class__.__name__}().precalculate() first"
)
trace_link_data_structure = ElementLevelTraceLinkDataStructure.load_data_from(
matrix_file_path, artifact_map_file_path)
trace_link_processor = MajProcessor(trace_link_data_structure,
self.similarity_filter,
self.req_reduce_func,
self.code_reduce_function,
final_thresholds, maj_thresholds,
self.callgraph_aggregator)
return trace_link_processor.run()
