Source Code for Module prest.char

 1  #!/usr/bin/env python3 
 2  # -*- coding: utf-8 -*- 
 3   
 4  """Some variables and functions to help handling characters categories.""" 
 5   
 6   
 7  from __future__ import absolute_import, unicode_literals 
 8  import unicodedata 
 9   
10   
11  blankspaces = ' \f\n\c\r\t\v…' 
12  """@var: A string containing every blankspaces characters.""" 
13   
14  separators = '`~!@#$%^&*()_-+=\\|]}[{\";:/?.>,<†„“।॥ו–´’‘‚י0123456789ः' 
15  """@var: A string containing every separators characters.""" 
16   
17   
18 -def first_word_char(string): 
19      """Return the index of the first word character in a string. 
20   
21      @return: 
22          The index of the first word character in the string 'string' or -1 if 
23          the string contains no word character. 
24      @rtype: int 
25      """ 
26      for i, ch in enumerate(string): 
27          if is_word_char(ch): 
28              return i 
29      return -1 
30   
31   
32 -def last_word_char(string): 
33      """Return the index of the last word character in a string. 
34   
35      @return: 
36          The index of the last word character in the string 'string' or -1 if 
37          the string contains no word character. 
38      @rtype: int 
39      """ 
40      result = first_word_char(string[::-1]) 
41      if result == -1: 
42          return -1 
43      return len(string) - result - 1 
44   
45   
46 -def is_word_char(char): 
47      """Check if a character is a word character. 
48   
49      @return: 
50          True or False weither the character 'char' is a word character, i.e. a 
51          printable non-ponctuation character. 
52      @rtype: bool 
53      """ 
54      if unicodedata.category(char)[0] == "L": 
55          return True 
56      return False 
57