def tagged(files = items):
if type(files) is str: files = (files,)
for file in files:
path = os.path.join(get_basedir(), "conll2000", file + ".txt")
s = open(path).read()
for sent in tokenize.blankline(s):
yield [(word, tag) for (word, tag, chunk) in _list_sent(sent)]
def chunked(files = items, chunk_types=('NP',)):
if type(files) is str: files = (files,)
for file in files:
path = os.path.join(get_basedir(), "conll2000", file + ".txt")
s = open(path).read()
for sent in tokenize.blankline(s):
yield tree.conll_chunk(sent, chunk_types)
def demo():
"""
A demonstration that shows the output of several different
tokenizers on the same string.
"""
from en.parser.nltk_lite import tokenize
# Define the test string.
s = "Good muffins cost $3.88\nin New York. Please buy me\ntwo of them.\n\nThanks."
print 'Input text:'
print `s`
print
print 'Tokenize using whitespace:'
_display(tokenize.whitespace(s))
print
print 'Tokenize sequences of alphanumeric characters:'
_display(tokenize.regexp(s, pattern=r'\w+', gaps=False))
print
print 'Tokenize sequences of letters and sequences of nonletters:'
_display(tokenize.wordpunct(s))
print
print 'Tokenize by lines:'
_display(tokenize.line(s))
print
print 'Tokenize by blank lines:'
_display(tokenize.blankline(s))
print
print 'A simple sentence tokenizer:'
_display(tokenize.regexp(s, pattern=r'\.(\s+|$)', gaps=True))
print
def demo():
"""
A demonstration that shows the output of several different
tokenizers on the same string.
"""
from en.parser.nltk_lite import tokenize
# Define the test string.
s = "Good muffins cost $3.88\nin New York. Please buy me\ntwo of them.\n\nThanks."
print 'Input text:'
print ` s `
print
print 'Tokenize using whitespace:'
_display(tokenize.whitespace(s))
print
print 'Tokenize sequences of alphanumeric characters:'
_display(tokenize.regexp(s, pattern=r'\w+', gaps=False))
print
print 'Tokenize sequences of letters and sequences of nonletters:'
_display(tokenize.wordpunct(s))
print
print 'Tokenize by lines:'
_display(tokenize.line(s))
print
print 'Tokenize by blank lines:'
_display(tokenize.blankline(s))
print
print 'A simple sentence tokenizer:'
_display(tokenize.regexp(s, pattern=r'\.(\s+|$)', gaps=True))
print
def _read(files, conversion_function):
if type(files) is str: files = (files,)
for file in files:
path = os.path.join(get_basedir(), "brown", file)
f = open(path).read()
for sent in tokenize.blankline(f):
yield conversion_function(sent)
def _read(files, conversion_function):
if type(files) is str: files = (files, )
for file in files:
path = os.path.join(get_basedir(), "brown", file)
f = open(path).read()
for sent in tokenize.blankline(f):
yield conversion_function(sent)
def chunked(files=items, chunk_types=("NP",)):
if type(files) is str:
files = (files,)
for file in files:
path = os.path.join(get_basedir(), "conll2000", file + ".txt")
s = open(path).read()
for sent in tokenize.blankline(s):
yield tree.conll_chunk(sent, chunk_types)
def tagged(files=items):
if type(files) is str:
files = (files,)
for file in files:
path = os.path.join(get_basedir(), "conll2000", file + ".txt")
s = open(path).read()
for sent in tokenize.blankline(s):
yield [(word, tag) for (word, tag, chunk) in _list_sent(sent)]
def chunked(files='chunked'):
"""
@param files: One or more treebank files to be processed
@type files: L{string} or L{tuple(string)}
@rtype: iterator over L{tree}
"""
# Just one file to process? If so convert to a tuple so we can iterate
if type(files) is str: files = (files, )
for file in files:
path = os.path.join(get_basedir(), "treebank", file)
s = open(path).read()
for t in tokenize.blankline(s):
yield tree.chunk(t)
def _read(files, conversion_function):
if type(files) is str: files = (files,)
for file in files:
path = os.path.join(get_basedir(), "ycoe/pos", file)
f = open(path).read()
rx_pattern = re.compile(r"""
<.*>_CODE
|\s.*_ID
""", re.VERBOSE|re.UNICODE)
mySents = tokenize.blankline(f)
for sent in mySents:
sent= re.sub(rx_pattern, '', sent)
if sent != "":
yield conversion_function(sent, sep="_")
def _read(files, conversion_function):
if type(files) is str: files = (files, )
for file in files:
path = os.path.join(get_basedir(), "ycoe/pos", file)
f = open(path).read()
rx_pattern = re.compile(
r"""
<.*>_CODE
|\s.*_ID
""", re.VERBOSE | re.UNICODE)
mySents = tokenize.blankline(f)
for sent in mySents:
sent = re.sub(rx_pattern, '', sent)
if sent != "":
yield conversion_function(sent, sep="_")
def raw(files='raw'):
"""
@param files: One or more treebank files to be processed
@type files: L{string} or L{tuple(string)}
@rtype: iterator over L{list(string)}
"""
# Just one file to process? If so convert to a tuple so we can iterate
if type(files) is str: files = (files, )
for file in files:
path = os.path.join(get_basedir(), "treebank", file)
f = open(path).read()
for sent in tokenize.blankline(f):
l = []
for t in tokenize.whitespace(sent):
l.append(t)
yield l
