Lib/test/test_unicodedata.py

   1 """ Test script for the unicodedata module.
   2
   3     Written by Marc-Andre Lemburg (mal@lemburg.com).
   4
   5     (c) Copyright CNRI, All Rights Reserved. NO WARRANTY.
   6
   7 """#"
   8 import sha
   9
  10 encoding = 'utf-8'
  11
  12 def test_methods():
  13
  14     h = sha.sha()
  15     for i in range(65536):
  16         char = unichr(i)
  17         data = [
  18
  19             # Predicates (single char)
  20             char.isalnum() and u'1' or u'0',
  21             char.isalpha() and u'1' or u'0',
  22             char.isdecimal() and u'1' or u'0',
  23             char.isdigit() and u'1' or u'0',
  24             char.islower() and u'1' or u'0',
  25             char.isnumeric() and u'1' or u'0',
  26             char.isspace() and u'1' or u'0',
  27             char.istitle() and u'1' or u'0',
  28             char.isupper() and u'1' or u'0',
  29
  30             # Predicates (multiple chars)
  31             (char + u'abc').isalnum() and u'1' or u'0',
  32             (char + u'abc').isalpha() and u'1' or u'0',
  33             (char + u'123').isdecimal() and u'1' or u'0',
  34             (char + u'123').isdigit() and u'1' or u'0',
  35             (char + u'abc').islower() and u'1' or u'0',
  36             (char + u'123').isnumeric() and u'1' or u'0',
  37             (char + u' \t').isspace() and u'1' or u'0',
  38             (char + u'abc').istitle() and u'1' or u'0',
  39             (char + u'ABC').isupper() and u'1' or u'0',
  40
  41             # Mappings (single char)
  42             char.lower(),
  43             char.upper(),
  44             char.title(),
  45
  46             # Mappings (multiple chars)
  47             (char + u'abc').lower(),
  48             (char + u'ABC').upper(),
  49             (char + u'abc').title(),
  50             (char + u'ABC').title(),
  51
  52             ]
  53         h.update(u''.join(data).encode(encoding))
  54     return h.hexdigest()
  55
  56 def test_unicodedata():
  57
  58     h = sha.sha()
  59     for i in range(65536):
  60         char = unichr(i)
  61         data = [
  62             # Properties
  63             str(unicodedata.digit(char, -1)),
  64             str(unicodedata.numeric(char, -1)),
  65             str(unicodedata.decimal(char, -1)),
  66             unicodedata.category(char),
  67             unicodedata.bidirectional(char),
  68             unicodedata.decomposition(char),
  69             str(unicodedata.mirrored(char)),
  70             str(unicodedata.combining(char)),
  71             ]
  72         h.update(''.join(data))
  73     return h.hexdigest()
  74
  75 ### Run tests
  76
  77 print 'Testing Unicode Database...'
  78 print 'Methods:',
  79 print test_methods()
  80
  81 # In case unicodedata is not available, this will raise an ImportError,
  82 # but still test the above cases...
  83 import unicodedata
  84 print 'Functions:',
  85 print test_unicodedata()
  86
  87 # Some additional checks of the API:
  88 print 'API:',
  89
  90 assert unicodedata.digit(u'A',None) is None
  91 assert unicodedata.digit(u'9') == 9
  92 assert unicodedata.digit(u'\u215b',None) is None
  93 assert unicodedata.digit(u'\u2468') == 9
  94
  95 assert unicodedata.numeric(u'A',None) is None
  96 assert unicodedata.numeric(u'9') == 9
  97 assert unicodedata.numeric(u'\u215b') == 0.125
  98 assert unicodedata.numeric(u'\u2468') == 9.0
  99
 100 assert unicodedata.decimal(u'A',None) is None
 101 assert unicodedata.decimal(u'9') == 9
 102 assert unicodedata.decimal(u'\u215b',None) is None
 103 assert unicodedata.decimal(u'\u2468',None) is None
 104
 105 assert unicodedata.category(u'\uFFFE') == 'Cn'
 106 assert unicodedata.category(u'a') == 'Ll'
 107 assert unicodedata.category(u'A') == 'Lu'
 108
 109 assert unicodedata.bidirectional(u'\uFFFE') == ''
 110 assert unicodedata.bidirectional(u' ') == 'WS'
 111 assert unicodedata.bidirectional(u'A') == 'L'
 112
 113 assert unicodedata.decomposition(u'\uFFFE') == ''
 114 assert unicodedata.decomposition(u'\u00bc') == '<fraction> 0031 2044 0034'
 115
 116 assert unicodedata.mirrored(u'\uFFFE') == 0
 117 assert unicodedata.mirrored(u'a') == 0
 118 assert unicodedata.mirrored(u'\u2201') == 1
 119
 120 assert unicodedata.combining(u'\uFFFE') == 0
 121 assert unicodedata.combining(u'a') == 0
 122 assert unicodedata.combining(u'\u20e1') == 230
 123
 124 print 'ok'