Python Parser示例

示例#1

 def find_tags(self, tokens, **kwargs):
     if kwargs.get("tagset") in (PENN, None):
         kwargs.setdefault("map", lambda token, tag: (token, tag))
     if kwargs.get("tagset") == UNIVERSAL:
         kwargs.setdefault(
             "map", lambda token, tag: penntreebank2universal(token, tag))
     return _Parser.find_tags(self, tokens, **kwargs)

示例#2

    def find_tags(self, tokens, **kwargs):

        # Parser.find_tags() can take an optional map(token, tag) function,
        # which returns an updated (token, tag)-tuple for each token. 

        kwargs.setdefault("map", parole2penntreebank)
        return Parser.find_tags(self, tokens, **kwargs)

示例#3

文件： __init__.py 项目： DataBranner/pattern

 def find_tags(self, tokens, **kwargs):
     if kwargs.get("tagset") in (PENN, None):
         kwargs.setdefault("map", lambda token, tag: (token, tag))
     if kwargs.get("tagset") == UNIVERSAL:
         kwargs.setdefault(
             "map", lambda token, tag: penntreebank2universal(token, tag))
     return _Parser.find_tags(self, tokens, **kwargs)

示例#4

 def find_tokens(self, tokens, **kwargs):
     # 's in Dutch preceded by a vowel indicates plural ("auto's"): don't replace.
     kwargs.setdefault("abbreviations", ABBREVIATIONS)
     kwargs.setdefault("replace", {"'n": " 'n"})
     s = _Parser.find_tokens(self, tokens, **kwargs)
     s = [re.sub(r"' s (ochtends|morgens|middags|avonds)", "'s \\1", s) for s in s]
     return s

示例#5

文件： __init__.py 项目： BarcelonaMedia-ViL/pattern

 def find_tokens(self, tokens, **kwargs):
     # 's in Dutch preceded by a vowel indicates plural ("auto's"): don't replace.
     kwargs.setdefault("abbreviations", ABBREVIATIONS)
     kwargs.setdefault("replace", {"'n": " 'n"})
     s = _Parser.find_tokens(self, tokens, **kwargs)
     s = [re.sub(r"' s (ochtends|morgens|middags|avonds)", "'s \\1", s) for s in s]
     return s

示例#6

文件： __init__.py 项目： pattern3/pattern

 def find_tokens(self, tokens, **kwargs):
     kwargs.setdefault("abbreviations", ABBREVIATIONS)
     kwargs.setdefault("replace", replacements)
     s = _Parser.find_tokens(self, tokens, **kwargs)
     s = [s.replace("&rsquo ;", u"’") if isinstance(
         s, unicode) else s for s in s]
     return s

示例#7

 def find_tokens(self, tokens, **kwargs):
     kwargs.setdefault("abbreviations", ABBREVIATIONS)
     kwargs.setdefault("replace", replacements)
     #return _Parser.find_tokens(self, tokens, **kwargs)
     
     s = _Parser.find_tokens(self, tokens, **kwargs)
     s = [s.replace(" &contraction ;", u"'").replace("XXX -", "-") for s in s]
     return s

示例#8

文件： __init__.py 项目： Afey/pattern

 def find_tokens(self, tokens, **kwargs):
     kwargs.setdefault("abbreviations", ABBREVIATIONS)
     kwargs.setdefault("replace", replacements)
     #return _Parser.find_tokens(self, tokens, **kwargs)
     
     s = _Parser.find_tokens(self, tokens, **kwargs)
     s = [s.replace(" &contraction ;", u"'").replace("XXX -", "-") for s in s]
     return s

示例#9

 def find_tags(self, tokens, **kwargs):
     if kwargs.get("tagset") != STTS:
         kwargs.setdefault("map", stts2penntreebank)
     # The lexicon uses Swiss spelling: "ss" instead of "ß".
     # We restore the "ß" after parsing.
     tokens_ss = [t.replace(u"ß", "ss") for t in tokens]
     tokens_ss = _Parser.find_tags(self, tokens_ss, **kwargs)
     return [[w] + tokens_ss[i][1:] for i, w in enumerate(tokens)]

示例#10

 def find_tokens(self, tokens, **kwargs):
     kwargs.setdefault("abbreviations", ABBREVIATIONS)
     kwargs.setdefault("replace", replacements)
     s = _Parser.find_tokens(self, tokens, **kwargs)
     s = [
         s.replace("&rsquo ;", "’") if isinstance(s, str) else s for s in s
     ]
     return s

示例#11

文件： __init__.py 项目： Maulanadurer/pattern

 def find_tags(self, tokens, **kwargs):
     if kwargs.get("tagset") in (PENN, None):
         kwargs.setdefault("map", lambda token, tag: stts2penntreebank(token, tag))
     if kwargs.get("tagset") == UNIVERSAL:
         kwargs.setdefault("map", lambda token, tag: stts2universal(token, tag))
     if kwargs.get("tagset") is STTS:
         kwargs.setdefault("map", lambda token,tag: (token, tag))
     # The lexicon uses Swiss spelling: "ss" instead of "ß".
     # We restore the "ß" after parsing.
     tokens_ss = [t.replace(u"ß", "ss") for t in tokens]
     tokens_ss = _Parser.find_tags(self, tokens_ss, **kwargs)
     return [[w] + tokens_ss[i][1:] for i, w in enumerate(tokens)]

示例#12

 def find_tags(self, tokens, **kwargs):
     if kwargs.get("tagset") in (PENN, None):
         kwargs.setdefault("map", lambda token, tag: stts2penntreebank(token, tag))
     if kwargs.get("tagset") == UNIVERSAL:
         kwargs.setdefault("map", lambda token, tag: stts2universal(token, tag))
     if kwargs.get("tagset") is STTS:
         kwargs.setdefault("map", lambda token,tag: (token, tag))
     # The lexicon uses Swiss spelling: "ss" instead of "ß".
     # We restore the "ß" after parsing.
     tokens_ss = [t.replace(u"ß", "ss") for t in tokens]
     tokens_ss = _Parser.find_tags(self, tokens_ss, **kwargs)
     return [[w] + tokens_ss[i][1:] for i, w in enumerate(tokens)]

示例#13

文件： __init__.py 项目： DevKhokhar/pattern

 def find_chunks(self, tokens, **kwargs):
     return _Parser.find_chunks(self, tokens, **kwargs)

示例#14

文件： __init__.py 项目： DevKhokhar/pattern

 def find_tags(self, tokens, **kwargs):
     kwargs.setdefault("map", tagset2penntreebank)
     return _Parser.find_tags(self, tokens, **kwargs)

示例#15

文件： __init__.py 项目： DevKhokhar/pattern

 def find_tokens(self, tokens, **kwargs):
     kwargs.setdefault("abbreviations", ABBREVIATIONS)
     kwargs.setdefault("replace", REPLACEMENTS)
     return _Parser.find_tokens(self, tokens, **kwargs)

示例#16

 def find_chunks(self, tokens, **kwargs):
     return _Parser.find_chunks(self, tokens, **kwargs)

示例#17

 def find_tags(self, tokens, **kwargs):
     kwargs.setdefault("map", tagset2penntreebank)
     return _Parser.find_tags(self, tokens, **kwargs)

示例#18

 def find_tokens(self, tokens, **kwargs):
     kwargs.setdefault("abbreviations", ABBREVIATIONS)
     kwargs.setdefault("replace", REPLACEMENTS)
     return _Parser.find_tokens(self, tokens, **kwargs)

示例#19

文件： __init__.py 项目： BarcelonaMedia-ViL/pattern

 def find_tags(self, tokens, **kwargs):
     if kwargs.get("tagset") != WOTAN:
         kwargs.setdefault("map", wotan2penntreebank)
     return _Parser.find_tags(self, tokens, **kwargs)

示例#20

文件： __init__.py 项目： BarcelonaMedia-ViL/pattern

 def find_tags(self, tokens, **kwargs):
     if kwargs.get("tagset") != PAROLE:
         kwargs.setdefault("map", parole2penntreebank)
     return _Parser.find_tags(self, tokens, **kwargs)

示例#21

文件： __init__.py 项目： lazycrazyowl/pattern

 def find_tags(self, tokens, **kwargs):
     if kwargs.get("tagset") != WOTAN:
         kwargs.setdefault("map", wotan2penntreebank)
     return _Parser.find_tags(self, tokens, **kwargs)

示例#22

文件： pattern.py 项目： jgsogo/lingwars

 def find_tags(self, tokens, **kwargs):
     # Parser.find_tags() can take an optional map(token, tag) function,
     # which returns an updated (token, tag)-tuple for each token.
     kwargs.setdefault("map", parole2penntreebank)
     return Parser.find_tags(self, tokens, **kwargs)

示例#23

文件： __init__.py 项目： lazycrazyowl/pattern

 def find_tags(self, tokens, **kwargs):
     if kwargs.get("tagset") != PAROLE:
         kwargs.setdefault("map", parole2penntreebank)
     return _Parser.find_tags(self, tokens, **kwargs)

示例#24

文件： Python_Computational_Linguistics_Redefine_Find_Token( ).py 项目： VakinduPhilliam/Python_Computation_Linguistics

    def find_tokens(self, tokens, **kwargs):

        kwargs.setdefault("abbreviations", ABBREVIATIONS)
        kwargs.setdefault("replace", CONTRACTIONS)
        return Parser.find_tokens(self, tokens, **kwargs)