def __find_candidates_to_anaphora_in_chapter(chapter, total_words, candidates,
stop_word_check):
""" Finds candidates to anaphora in the specified chapter"""
word_count = 0
i = 0
while i < len(chapter.sentences):
if len(chapter.sentences[i]) > 1:
candidate = Feature('anaphora')
candidate.add_word(total_words + word_count)
candidate.add_context(
total_words + word_count,
total_words + word_count + len(chapter.sentences[i]) - 1)
word_count += len(chapter.sentences[i])
first_anaphora_word = chapter.sentences[i][0].lower()
i += 1
if stop_word_check(first_anaphora_word):
continue
context_length = 1
while i < len(chapter.sentences) and chapter.sentences[i][0].lower(
) == first_anaphora_word:
candidate.extend_context(total_words + word_count +
len(chapter.sentences[i]) - 1)
candidate.add_word(total_words + word_count)
word_count += len(chapter.sentences[i])
i += 1
context_length += 1
if context_length > 1:
if candidate not in candidates:
candidates.append(candidate)
else:
if len(chapter.sentences[i]) > 0 and chapter.sentences[i][0]:
word_count += len(chapter.sentences[i])
i += 1
return word_count
def __find_epiphora_inside_chapter(chapter: Chapter, start_count: int,
stop_word_check) -> list:
"""
Parses epiphora from chapter
:param chapter: chapter to find epiphora from (list of sentences as list of words)
:param start_count: index of first word in chapter
:param stop_word_check: function checking if word is stop word
:return: list with epiphora(Feature objects)
"""
res = []
word_count = start_count
current_feature = None
for i in range(len(chapter.sentences) - 1):
if __test_sentences_for_epiphora(chapter[i], chapter[i + 1],
stop_word_check):
if current_feature is None:
current_feature = Feature(
"epiphora",
words=[
word_count + len(chapter.sentences[i]) - 1,
word_count + len(chapter.sentences[i]) +
len(chapter.sentences[i + 1]) - 1
],
context=[
word_count, word_count + len(chapter.sentences[i]) +
len(chapter.sentences[i + 1]) - 1
])
res.append(current_feature)
else:
current_feature.add_word(word_count + len(chapter[i]) +
len(chapter[i + 1]) - 1)
current_feature.extend_context(word_count + len(chapter[i]) +
len(chapter[i + 1]) - 1)
else:
current_feature = None
word_count += len(chapter[i])
return res