def set_repetitions(doc):
for sent in all_sents(doc):
words = sent["Words"]
if not words:
continue
_check_grammeme_repetition(words, 1, "posred", PARTS_OF_SPEECH)
_check_grammeme_repetition(words, 1, "genderred", GENDERS)
_check_grammeme_repetition(words, 1, "numberred", NUMBERS)
_check_grammeme_repetition(words, 1, "casered", CASES)
_check_grammeme_repetition(words, 1, "tensered", TENSES)
_check_grammeme_repetition(words, 1, "personred", PERSONS)
_check_attr_repetition(words, 1, "lexred", "lex")
def set_marks(doc):
for sent in all_sents(doc):
words = sent["Words"]
for i in xrange(len(words)):
values = _inspect_marks(words[i]["Punct"])
if values:
_insert_flags(words[i], "a", values)
if i > 0:
_insert_flags(words[i - 1], "b", values)
values = _inspect_marks(sent["Punct"])
if values and words:
_insert_flags(words[-1], "b", values)
def set_marks(doc):
for sent in all_sents(doc):
words = sent["Words"]
for i in xrange(len(words)):
values = _inspect_marks(words[i]["Punct"])
if values:
_insert_flags(words[i], "a", values)
if i > 0:
_insert_flags(words[i-1], "b", values)
values = _inspect_marks(sent["Punct"])
if values and words:
_insert_flags(words[-1], "b", values)
def set_first_last(doc):
for sent in all_sents(doc):
if not sent["Words"]:
continue
_insert_flag(sent["Words"][0], "first")
_insert_flag(sent["Words"][-1], "last")
def normalize_punct(doc):
for word in all_words(doc):
word["Punct"] = _normalize_punct_str(word["Punct"])
for sent in all_sents(doc):
sent["Punct"] = _normalize_punct_str(sent["Punct"])
def normalize_punct(doc):
for word in all_words(doc):
word["Punct"] = _normalize_punct_str(word["Punct"])
for sent in all_sents(doc):
sent["Punct"] = _normalize_punct_str(sent["Punct"])
