def __init__(self, sep="/",
# Note that . needs to be escaped
pattern = chinese_pattern,
root=None, fileids=None):
"""docstring for __init__"""
TaggedCorpusReader.__init__(
self,
sep=sep, root=root, fileids=fileids,
sent_tokenizer = RegexpTokenizer(pattern, gaps=True),
encoding="utf-8")
def __init__(self, root=None, fileids=None, encoding='utf8'):
"""
Construct a new MTECorpusreader for a set of documents
located at the given root directory. Example usage:
>>> root = '/...path to corpus.../'
>>> reader = MTECorpusReader(root, 'oana-*.xml', 'utf8')
:param root: The root directory for this corpus. (default points to location in multext config file)
:param fileids: A list or regexp specifying the fileids in this corpus. (default is oana-en.xml)
:param enconding: The encoding of the given files (default is utf8)
"""
TaggedCorpusReader.__init__(self, root, fileids, encoding)
def __init__(self, root=None, fileids=None, encoding='utf8'):
"""
Construct a new MTECorpusreader for a set of documents
located at the given root directory. Example usage:
>>> root = '/...path to corpus.../'
>>> reader = MTECorpusReader(root, 'oana-*.xml', 'utf8') # doctest: +SKIP
:param root: The root directory for this corpus. (default points to location in multext config file)
:param fileids: A list or regexp specifying the fileids in this corpus. (default is oana-en.xml)
:param enconding: The encoding of the given files (default is utf8)
"""
TaggedCorpusReader.__init__(self, root, fileids, encoding)
def __init__(self,
file_name,
language='',
separator='_',
ws_delim=True,
number_of_groups=10,
encoding='utf-8'):
"""Initialize the corpus reader."""
TaggedCorpusReader.__init__(self,
root='.',
fileids=[file_name],
sep=separator,
encoding=encoding)
def __init__(
self,
sep="/",
# Note that . needs to be escaped
pattern=chinese_pattern,
root=None,
fileids=None):
"""docstring for __init__"""
TaggedCorpusReader.__init__(self,
sep=sep,
root=root,
fileids=fileids,
sent_tokenizer=RegexpTokenizer(pattern,
gaps=True),
encoding="utf-8")
def __init__(self, file_name, language="", separator="_", ws_delim=True, number_of_groups=10, encoding="utf-8"):
"""Initialize the corpus reader."""
TaggedCorpusReader.__init__(self, root=".", fileids=[file_name], sep=separator, encoding=encoding)
