Python util.concat函数代码示例

 def words(self, fileids=None, **kwargs):
     return concat(
         [
             self._view(fileid, tags=False, **kwargs)
             for fileid in self._list_morph_files(fileids)
         ]
     )

 def raw(self, fileids=None, **kwargs):
     """
     Returns words in specified fileids.
     """
     return concat([self._view(self.add_root(fileid),
                               mode=NKJPCorpusReader.RAW_MODE, **kwargs).handle_query()
                    for fileid in fileids])

 def header(self, fileids=None, **kwargs):
     """
     Returns header(s) of specified fileids.
     """
     return concat([self._view(self.add_root(fileid),
                               mode=NKJPCorpusReader.HEADER_MODE, **kwargs).handle_query()
                    for fileid in fileids])

 def sents(self, fileids=None, **kwargs):
     """
     Returns sentences in specified fileids.
     """
     return concat([self._view(self.add_root(fileid),
                               mode=NKJPCorpusReader.SENTS_MODE, **kwargs).handle_query()
                    for fileid in fileids])

 def tagged_paras(self, fileids=None, **kwargs):
     return concat(
         [
             self._view(fileid, mode=IPIPANCorpusView.PARAS_MODE, **kwargs)
             for fileid in self._list_morph_files(fileids)
         ]
     )

 def raw(self, fileids=None):
     """
     :return: the given file(s) as a single string.
     :rtype: str
     """
     if fileids is None: fileids = self._fileids
     elif isinstance(fileids, basestring): fileids = [fileids]
     return concat([self.open(f).read() for f in fileids])

 def parsed_sents2(self, fileids=None):
   return concat([JapaneseCorpusView(fileid, enc,
                                     False, False, False, True,
                                     self._syntax_parser,
                                     self._word_tokenizer,
                                     self._sent_tokenizer,
                                     self._case_parser)
                  for (fileid, enc) in self.abspaths(fileids, True)])

def fixed_parsed_sents(self, fileids=None, top_label="root"):
    from nltk.corpus.reader.util import concat
    from nltk.corpus.reader.dependency import DependencyCorpusView
    from nltk.parse import DependencyGraph
    
    sents=concat([DependencyCorpusView(fileid, False, True, True, encoding=enc)
                  for fileid, enc in self.abspaths(fileids, include_encoding=True)])
    return [DependencyGraph(sent, top_relation_label=top_label, cell_separator="\t") for sent in sents]

 def tagged_words(self, fileids=None, **kwargs):
     """
     Call with specified tags as a list, e.g. tags=['subst', 'comp'].
     Returns tagged words in specified fileids.
     """
     tags = kwargs.pop('tags', [])
     return concat([self._view(self.add_root(fileid),
                               mode=NKJPCorpusReader.WORDS_MODE, tags=tags, **kwargs).handle_query()
                    for fileid in fileids])

 def _views(self, fileids=None, sent=False, tag=False, strip_space=True, stem=False):
     """A helper function that instantiates BNCWordViews or the list of words/sentences."""
     f = BNCWordView if self._lazy else self._words
     return concat(
         [
             f(fileid, sent, tag, strip_space, stem)
             for fileid in self.abspaths(fileids)
         ]
     )

 def raw(self, fileids=None):
     """
     Return the corpora in their raw form.
     """
     if fileids is None:
         fileids = self._fileids
     elif isinstance(fileids, string_types):
         fileids = [fileids]
     return concat([self.open(f).read() for f in fileids])

 def sents(self, fileids=None, **kwargs):
     return concat(
         [
             self._view(
                 fileid, mode=IPIPANCorpusView.SENTS_MODE, tags=False, **kwargs
             )
             for fileid in self._list_morph_files(fileids)
         ]
     )

 def aligned_sents(self, fileids=None):
     """
     :return: the given file(s) as a list of AlignedSent objects.
     :rtype: list of C{AlignedSent}
     """
     return concat([AlignedSentCorpusView(fileid, enc, True, True,
                                          self._word_tokenizer,
                                          self._sent_tokenizer,
                                          self._alignedsent_block_reader)
                    for (fileid, enc) in self.abspaths(fileids, True)])

 def words(self, fileids=None):
     """
     @return: the given file(s) as a list of words
         and punctuation symbols.
     @rtype: C{list} of C{str}
     """
     return concat([self._alignedsent_corpus_view(fileid, enc, False, False,
                                          self._word_tokenizer,
                                          self._sent_tokenizer,
                                          self._alignedsent_block_reader)
                    for (fileid, enc) in self.abspaths(fileids, True)])

 def parsed_docs(self, fileids=None):
     """
     @return: A list of parsed corpus documents.
     @rtype: C{list} of C{StreamBackedCorpusView}
     @param fileids: A list of corpus files.
     @type fileids: C{list} of C{str} or regular expression
     """        
     return concat([StreamBackedCorpusView(fileid,
                                           self._read_parsed_block,
                                           encoding=enc)
                    for (fileid, enc) in self.abspaths(fileids, True)])