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 from test_support import verify, verbose
   9 import sha
  10
  11 encoding = 'utf-8'
  12
  13 def test_methods():
  14
  15     h = sha.sha()
  16     for i in range(65536):
  17         char = unichr(i)
  18         data = [
  19
  20             # Predicates (single char)
  21             char.isalnum() and u'1' or u'0',
  22             char.isalpha() and u'1' or u'0',
  23             char.isdecimal() and u'1' or u'0',
  24             char.isdigit() and u'1' or u'0',
  25             char.islower() and u'1' or u'0',
  26             char.isnumeric() and u'1' or u'0',
  27             char.isspace() and u'1' or u'0',
  28             char.istitle() and u'1' or u'0',
  29             char.isupper() and u'1' or u'0',
  30
  31             # Predicates (multiple chars)
  32             (char + u'abc').isalnum() and u'1' or u'0',
  33             (char + u'abc').isalpha() and u'1' or u'0',
  34             (char + u'123').isdecimal() and u'1' or u'0',
  35             (char + u'123').isdigit() and u'1' or u'0',
  36             (char + u'abc').islower() and u'1' or u'0',
  37             (char + u'123').isnumeric() and u'1' or u'0',
  38             (char + u' \t').isspace() and u'1' or u'0',
  39             (char + u'abc').istitle() and u'1' or u'0',
  40             (char + u'ABC').isupper() and u'1' or u'0',
  41
  42             # Mappings (single char)
  43             char.lower(),
  44             char.upper(),
  45             char.title(),
  46
  47             # Mappings (multiple chars)
  48             (char + u'abc').lower(),
  49             (char + u'ABC').upper(),
  50             (char + u'abc').title(),
  51             (char + u'ABC').title(),
  52
  53             ]
  54         h.update(u''.join(data).encode(encoding))
  55     return h.hexdigest()
  56
  57 def test_unicodedata():
  58
  59     h = sha.sha()
  60     for i in range(65536):
  61         char = unichr(i)
  62         data = [
  63             # Properties
  64             str(unicodedata.digit(char, -1)),
  65             str(unicodedata.numeric(char, -1)),
  66             str(unicodedata.decimal(char, -1)),
  67             unicodedata.category(char),
  68             unicodedata.bidirectional(char),
  69             unicodedata.decomposition(char),
  70             str(unicodedata.mirrored(char)),
  71             str(unicodedata.combining(char)),
  72             ]
  73         h.update(''.join(data))
  74     return h.hexdigest()
  75
  76 ### Run tests
  77
  78 print 'Testing Unicode Database...'
  79 print 'Methods:',
  80 print test_methods()
  81
  82 # In case unicodedata is not available, this will raise an ImportError,
  83 # but still test the above cases...
  84 import unicodedata
  85 print 'Functions:',
  86 print test_unicodedata()
  87
  88 # Some additional checks of the API:
  89 print 'API:',
  90
  91 verify(unicodedata.digit(u'A',None) is None)
  92 verify(unicodedata.digit(u'9') == 9)
  93 verify(unicodedata.digit(u'\u215b',None) is None)
  94 verify(unicodedata.digit(u'\u2468') == 9)
  95
  96 verify(unicodedata.numeric(u'A',None) is None)
  97 verify(unicodedata.numeric(u'9') == 9)
  98 verify(unicodedata.numeric(u'\u215b') == 0.125)
  99 verify(unicodedata.numeric(u'\u2468') == 9.0)
 100
 101 verify(unicodedata.decimal(u'A',None) is None)
 102 verify(unicodedata.decimal(u'9') == 9)
 103 verify(unicodedata.decimal(u'\u215b',None) is None)
 104 verify(unicodedata.decimal(u'\u2468',None) is None)
 105
 106 verify(unicodedata.category(u'\uFFFE') == 'Cn')
 107 verify(unicodedata.category(u'a') == 'Ll')
 108 verify(unicodedata.category(u'A') == 'Lu')
 109
 110 verify(unicodedata.bidirectional(u'\uFFFE') == '')
 111 verify(unicodedata.bidirectional(u' ') == 'WS')
 112 verify(unicodedata.bidirectional(u'A') == 'L')
 113
 114 verify(unicodedata.decomposition(u'\uFFFE') == '')
 115 verify(unicodedata.decomposition(u'\u00bc') == '<fraction> 0031 2044 0034')
 116
 117 verify(unicodedata.mirrored(u'\uFFFE') == 0)
 118 verify(unicodedata.mirrored(u'a') == 0)
 119 verify(unicodedata.mirrored(u'\u2201') == 1)
 120
 121 verify(unicodedata.combining(u'\uFFFE') == 0)
 122 verify(unicodedata.combining(u'a') == 0)
 123 verify(unicodedata.combining(u'\u20e1') == 230)
 124
 125 print 'ok'