def span_tokenize(self, s):
if self._blanklines == 'keep':
for span in string_span_tokenize(s, r'\n'):
yield span
else:
for span in regexp_span_tokenize(s, r'\n(\s+\n)*'):
yield span
def span_tokenize(self, s):
if self._blanklines == 'keep':
for span in string_span_tokenize(s, r'\n'):
yield span
else:
for span in regexp_span_tokenize(s, r'\n(\s+\n)*'):
yield span
def span_tokenize(self, s):
if self._blanklines == "keep":
for span in string_span_tokenize(s, r"\n"):
yield span
else:
for span in regexp_span_tokenize(s, r"\n(\s+\n)*"):
yield span
def span_tokenize(self, s):
if self._blanklines == "keep":
for span in string_span_tokenize(s, r"\n"):
yield span
else:
for span in regexp_span_tokenize(s, r"\n(\s+\n)*"):
yield span
def span_tokenizer(sent):
spans = string_span_tokenize(sent, " ")
list_span_tok = list()
for span in spans:
list_span_tok.append((span[0], span[1], sent[span[0]:span[1]]))
return list_span_tok
def fun_1_1_5():
import nltk
from nltk.tokenize import RegexpTokenizer
from nltk.tokenize import regexp_tokenize
tokenizer = RegexpTokenizer("[\w]+")
print "RegexpTokenizer:", tokenizer.tokenize(
"Don't hesitate to ask questions")
print "regexp_tokenizer:", regexp_tokenize(
"Don't hesitate to ask questions", pattern="\w+|\$[\d\.]+|\S+")
# 通过空格来执行切分
tokenizer = RegexpTokenizer('\s+', gaps=True)
print "RegexpTokenizer:", tokenizer.tokenize(
"Don't hesitate to ask questions")
# 筛选以大写字母开头的单词
sent = " She secured 90.56 % in class X \n. She is a meritorious student"
capt = RegexpTokenizer('[A-Z]\w+')
print "RegexpTokenizer:", capt.tokenize(sent)
# RegexpTokenizer 的一个子类是如何使用预定义正则表达式的
from nltk.tokenize import BlanklineTokenizer
print "BlanklineTokenizer:", BlanklineTokenizer().tokenize(sent)
# 字符串的切分可以通过空格、间隔、换行等来完成
from nltk.tokenize import WhitespaceTokenizer
print "WhitespaceTokenizer:", WhitespaceTokenizer().tokenize(sent)
# WordPunctTokenizer 使用正则表达式\w+|[^\w\s]+来执行文本的切分,并将其
# 切分为字母与非字母字符
from nltk.tokenize import WordPunctTokenizer
print "WordPunctTokenizer:", WordPunctTokenizer().tokenize(sent)
# 使用 split()方法进行切分
print "split():", sent.split()
print "split(' '):", sent.split(' ')
print "split('\n'):", sent.split('\n')
# 类似于 sent.split('\n')方法,LineTokenizer 通过将文本切分为行来执行切分
from nltk.tokenize import LineTokenizer
print "LineTokenizer:", LineTokenizer().tokenize(sent)
print "LineTokenizer:", LineTokenizer(blanklines='keep').tokenize(sent)
print "LineTokenizer:", LineTokenizer(blanklines='discard').tokenize(sent)
# SpaceTokenizer 与 sent.split('')方法的工作原理类似
from nltk.tokenize import SpaceTokenizer
print "SpaceTokenizer:", SpaceTokenizer().tokenize(sent)
# nltk.tokenize.util 模块通过返回元组形式的序列来执行切分,该序列为标识符
# 在语句中的位置和偏移量
print "标识符序列：", list(WhitespaceTokenizer().span_tokenize(sent))
# 给定一个标识符的序列,则可以返回其跨度序列
from nltk.tokenize.util import spans_to_relative
print "位置和偏移：", list(
spans_to_relative(WhitespaceTokenizer().span_tokenize(sent)))
# 通过在每一个分隔符的连接处进行分割,nltk.tokenize.util.string_span_tokenize(sent,separator)将返回 sent 中标识符的偏移量:
from nltk.tokenize.util import string_span_tokenize
print "标识符序列：", list(string_span_tokenize(sent, " "))
def token_to_char(text: str, sep=" ") -> np.ndarray:
"""Takes a string, space tokenizes the string, and returns a mapping from tokens to chars.
Examples:
>>> token_to_char("testing 1, 2, 3")
# produces a (m) token by (M) char matrix:
t e s t i n g 1 , 2 , 3
testing [[1 1 1 1 1 1 1 0 0 0 0 0 0 0 0]
1, [0 0 0 0 0 0 0 0 1 1 0 0 0 0 0]
2, [0 0 0 0 0 0 0 0 0 0 0 1 1 0 0]
3 [0 0 0 0 0 0 0 0 0 0 0 0 0 0 1]]
Args:
text (str): string to tokenize and build the token to char mapping.
Returns:
np.ndarray mapping from (m) tokens to (M) chars.
"""
spans = string_span_tokenize(text, sep=sep)
return _mat_from_spans_dense(tuple(spans), len(text))
def span_tokenize(self, s):
for span in string_span_tokenize(s, self._string):
yield span
import nltk from nltk.tokenize.util import string_span_tokenize sent=" She secured 90.56 % in class X \n. She is a meritorious student\n" print(list(string_span_tokenize(sent, " ")))
def span_tokenize(self, s):
if self._blanklines == "keep":
yield from string_span_tokenize(s, r"\n")
else:
yield from regexp_span_tokenize(s, r"\n(\s+\n)*")
def span_tokenize(self, s):
yield from string_span_tokenize(s, self._string)
import nltk from nltk.tokenize.util import string_span_tokenize sent = " She secured 90.56 % in class X \n. She is a meritorious student\n" print(list(string_span_tokenize(sent, " ")))
print regexp_tokenize(text, pattern='\w+|\$[\d\.]+\S+')
# Tokenize whitespace
tokenizer = RegexpTokenizer('\s+', gaps=True)
print tokenizer.tokenize(text)
# Select only words starting with capital letters
capt = RegexpTokenizer('[A-Z]\w+')
print capt.tokenize(text2)
print BlanklineTokenizer().tokenize(text2)
print WhitespaceTokenizer().tokenize(text2)
print LineTokenizer(blanklines='keep').tokenize(text2)
print LineTokenizer(blanklines='discard').tokenize(text2)
# SpaceTokenizer works similar to .split('')
print SpaceTokenizer().tokenize(text2)
# Returns the sequence of tuples that are offsets of the tokens
# in a sentence:
print list(WhitespaceTokenizer().span_tokenize(text2))
# Returns the sequence of relative spans
print list(spans_to_relative(WhitespaceTokenizer().span_tokenize(text2)))
# Returns the offsets of tokens in text2 by splitting at each incidence of the separator:
print list(string_span_tokenize(text2, ""))
