def translate_search(self, search_string, settings=None):
dashes = ['-', '——', '—', '～']
sentences = self._sentence_split(search_string, settings=settings)
dictionary = self._get_dictionary(settings=settings)
translated = []
original = []
for sentence in sentences:
original_tokens, simplified_tokens = self._simplify_split_align(
sentence, settings=settings)
translated_chunk = []
original_chunk = []
for i, word in enumerate(simplified_tokens):
if word == '' or word == ' ':
translated_chunk.append(word)
original_chunk.append(original_tokens[i])
elif word in dictionary and word not in dashes:
translated_chunk.append(dictionary[word])
original_chunk.append(original_tokens[i])
elif word.strip(
'()\"\'{}[],.،') in dictionary and word not in dashes:
punct = word[len(word.strip('()\"\'{}[],.،')):]
if punct and dictionary[word.strip('()\"\'{}[],.،')]:
translated_chunk.append(
dictionary[word.strip('()\"\'{}[],.،')] + punct)
else:
translated_chunk.append(
dictionary[word.strip('()\"\'{}[],.،')])
original_chunk.append(original_tokens[i])
elif self._token_with_digits_is_ok(word):
translated_chunk.append(word)
original_chunk.append(original_tokens[i])
# Use original token because word_is_tz is case sensitive
elif translated_chunk and word_is_tz(original_tokens[i]):
translated_chunk.append(word)
original_chunk.append(original_tokens[i])
else:
if translated_chunk:
translated.append(translated_chunk)
translated_chunk = []
original.append(original_chunk)
original_chunk = []
if translated_chunk:
translated.append(translated_chunk)
original.append(original_chunk)
for i in range(len(translated)):
if "in" in translated[i]:
translated[i] = self._clear_future_words(translated[i])
translated[i] = self._join_chunk(list(filter(bool, translated[i])),
settings=settings)
original[i] = self._join_chunk(list(filter(bool, original[i])),
settings=settings)
return translated, original
def translate_search(self, search_string, settings=None):
dashes = ['-', '——', '—', '～']
word_joint_unsupported_languages = ["zh", "ja"]
sentences = self._sentence_split(search_string, settings=settings)
dictionary = self._get_dictionary(settings=settings)
translated = []
original = []
for sentence in sentences:
original_tokens, simplified_tokens = self._simplify_split_align(
sentence, settings=settings)
translated_chunk = []
original_chunk = []
last_token_index = len(simplified_tokens) - 1
skip_next_token = False
for i, word in enumerate(simplified_tokens):
next_word = simplified_tokens[
i + 1] if i < last_token_index else ""
current_and_next_joined = self._join_chunk([word, next_word],
settings=settings)
if skip_next_token:
skip_next_token = False
continue
if word == '' or word == ' ':
translated_chunk.append(word)
original_chunk.append(original_tokens[i])
elif (current_and_next_joined in dictionary
and word not in dashes and self.shortname
not in word_joint_unsupported_languages):
translated_chunk.append(
dictionary[current_and_next_joined])
original_chunk.append(
self._join_chunk(
[original_tokens[i], original_tokens[i + 1]],
settings=settings))
skip_next_token = True
elif word in dictionary and word not in dashes:
translated_chunk.append(dictionary[word])
original_chunk.append(original_tokens[i])
elif word.strip(
'()\"\'{}[],.،') in dictionary and word not in dashes:
punct = word[len(word.strip('()\"\'{}[],.،')):]
if punct and dictionary[word.strip('()\"\'{}[],.،')]:
translated_chunk.append(
dictionary[word.strip('()\"\'{}[],.،')] + punct)
else:
translated_chunk.append(
dictionary[word.strip('()\"\'{}[],.،')])
original_chunk.append(original_tokens[i])
elif self._token_with_digits_is_ok(word):
translated_chunk.append(word)
original_chunk.append(original_tokens[i])
# Use original token because word_is_tz is case sensitive
elif translated_chunk and word_is_tz(original_tokens[i]):
translated_chunk.append(word)
original_chunk.append(original_tokens[i])
else:
if translated_chunk:
translated.append(translated_chunk)
translated_chunk = []
original.append(original_chunk)
original_chunk = []
if translated_chunk:
translated.append(translated_chunk)
original.append(original_chunk)
for i in range(len(translated)):
if "in" in translated[i]:
translated[i] = self._clear_future_words(translated[i])
translated[i] = self._join_chunk(list(filter(bool, translated[i])),
settings=settings)
original[i] = self._join_chunk(list(filter(bool, original[i])),
settings=settings)
return translated, original
