本文整理汇总了Python中nltk.data.SeekableUnicodeStreamReader方法的典型用法代码示例。如果您正苦于以下问题：Python data.SeekableUnicodeStreamReader方法的具体用法？Python data.SeekableUnicodeStreamReader怎么用？Python data.SeekableUnicodeStreamReader使用的例子？那么, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类nltk.data的用法示例。
在下文中一共展示了data.SeekableUnicodeStreamReader方法的2个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: _open
# 需要导入模块: from nltk import data [as 别名]
# 或者: from nltk.data import SeekableUnicodeStreamReader [as 别名]
def _open(self):
"""
Open the file stream associated with this corpus view. This
will be called performed if any value is read from the view
while its file stream is closed.
"""
if isinstance(self._fileid, PathPointer):
self._stream = self._fileid.open(self._encoding)
elif self._encoding:
self._stream = SeekableUnicodeStreamReader(
open(self._fileid, 'rb'), self._encoding)
else:
self._stream = open(self._fileid, 'rb') 示例2: _read_xml_fragment
# 需要导入模块: from nltk import data [as 别名]
# 或者: from nltk.data import SeekableUnicodeStreamReader [as 别名]
def _read_xml_fragment(self, stream):
"""
Read a string from the given stream that does not contain any
un-closed tags. In particular, this function first reads a
block from the stream of size ``self._BLOCK_SIZE``. It then
checks if that block contains an un-closed tag. If it does,
then this function either backtracks to the last '<', or reads
another block.
"""
fragment = ''
if isinstance(stream, SeekableUnicodeStreamReader):
startpos = stream.tell()
while True:
# Read a block and add it to the fragment.
xml_block = stream.read(self._BLOCK_SIZE)
fragment += xml_block
# Do we have a well-formed xml fragment?
if self._VALID_XML_RE.match(fragment):
return fragment
# Do we have a fragment that will never be well-formed?
if re.search('[<>]', fragment).group(0) == '>':
pos = stream.tell() - (
len(fragment)-re.search('[<>]', fragment).end())
raise ValueError('Unexpected ">" near char %s' % pos)
# End of file?
if not xml_block:
raise ValueError('Unexpected end of file: tag not closed')
# If not, then we must be in the middle of a <..tag..>.
# If appropriate, backtrack to the most recent '<'
# character.
last_open_bracket = fragment.rfind('<')
if last_open_bracket > 0:
if self._VALID_XML_RE.match(fragment[:last_open_bracket]):
if isinstance(stream, SeekableUnicodeStreamReader):
stream.seek(startpos)
stream.char_seek_forward(last_open_bracket)
else:
stream.seek(-(len(fragment)-last_open_bracket), 1)
return fragment[:last_open_bracket]
# Otherwise, read another block. (i.e., return to the
# top of the loop.)