Python all_words示例

示例#1

文件： reversion.py 项目： Sindbag/ruscorpora_tagging

def _reverse(doc, attr, rev_attr):
    for word in all_words(doc):
        if attr == "lex":
            for ana in word["Anas"]:
                val = ana["lex"]
                if val:
                    _insert_attr(word, rev_attr, val[::-1])
        elif attr == "form":
            val = word["Text"]
            if val:
                 _insert_attr(word, rev_attr, val[::-1])

示例#2

文件： reversion.py 项目： alzobnin/ruscorpora_tagging

def _reverse(doc, attr, rev_attr):
    for word in all_words(doc):
        if attr == "lex":
            for ana in word["Anas"]:
                val = ana["lex"]
                if val:
                    _insert_attr(word, rev_attr, val[::-1])
        elif attr == "form":
            val = word["Text"]
            if val:
                _insert_attr(word, rev_attr, val[::-1])

示例#3

def set_capital(doc):
    for word in all_words(doc):
        if word["Text"] and word["Text"][0].isupper():
            _insert_flag(word, "capital")

示例#4

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"])

示例#5

def normalize_accents(doc):
    for word in all_words(doc):
        word["Text"] = normalize_accents_str(word["Text"])

示例#6

文件： marks.py 项目： alzobnin/ruscorpora_tagging

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"])

示例#7

文件： normalization.py 项目： Sindbag/ruscorpora_tagging

def normalize_accents(doc):
    for word in all_words(doc):
        word["Text"] = normalize_accents_str(word["Text"])