lib/UnicodeCD.t

   1 use UnicodeCD;
   2
   3 use Test;
   4 use strict;
   5
   6 BEGIN { plan tests => 111 };
   7
   8 use UnicodeCD 'charinfo';
   9
  10 my $charinfo;
  11
  12 $charinfo = charinfo(0x41);
  13
  14 ok($charinfo->{code},           '0041');
  15 ok($charinfo->{name},           'LATIN CAPITAL LETTER A');
  16 ok($charinfo->{category},       'Lu');
  17 ok($charinfo->{combining},      '0');
  18 ok($charinfo->{bidi},           'L');
  19 ok($charinfo->{decomposition},  '');
  20 ok($charinfo->{decimal},        '');
  21 ok($charinfo->{digit},          '');
  22 ok($charinfo->{numeric},        '');
  23 ok($charinfo->{mirrored},       'N');
  24 ok($charinfo->{unicode10},      '');
  25 ok($charinfo->{comment},        '');
  26 ok($charinfo->{upper},          '');
  27 ok($charinfo->{lower},          '0061');
  28 ok($charinfo->{title},          '');
  29 ok($charinfo->{block},          'Basic Latin');
  30 ok($charinfo->{script},         'Latin');
  31
  32 $charinfo = charinfo(0x100);
  33
  34 ok($charinfo->{code},           '0100');
  35 ok($charinfo->{name},           'LATIN CAPITAL LETTER A WITH MACRON');
  36 ok($charinfo->{category},       'Lu');
  37 ok($charinfo->{combining},      '0');
  38 ok($charinfo->{bidi},           'L');
  39 ok($charinfo->{decomposition},  '0041 0304');
  40 ok($charinfo->{decimal},        '');
  41 ok($charinfo->{digit},          '');
  42 ok($charinfo->{numeric},        '');
  43 ok($charinfo->{mirrored},       'N');
  44 ok($charinfo->{unicode10},      'LATIN CAPITAL LETTER A MACRON');
  45 ok($charinfo->{comment},        '');
  46 ok($charinfo->{upper},          '');
  47 ok($charinfo->{lower},          '0101');
  48 ok($charinfo->{title},          '');
  49 ok($charinfo->{block},          'Latin Extended-A');
  50 ok($charinfo->{script},         'Latin');
  51
  52 # 0x0590 is in the Hebrew block but unused.
  53
  54 $charinfo = charinfo(0x590);
  55
  56 ok($charinfo->{code},          undef);
  57 ok($charinfo->{name},          undef);
  58 ok($charinfo->{category},      undef);
  59 ok($charinfo->{combining},     undef);
  60 ok($charinfo->{bidi},          undef);
  61 ok($charinfo->{decomposition}, undef);
  62 ok($charinfo->{decimal},       undef);
  63 ok($charinfo->{digit},         undef);
  64 ok($charinfo->{numeric},       undef);
  65 ok($charinfo->{mirrored},      undef);
  66 ok($charinfo->{unicode10},     undef);
  67 ok($charinfo->{comment},       undef);
  68 ok($charinfo->{upper},         undef);
  69 ok($charinfo->{lower},         undef);
  70 ok($charinfo->{title},         undef);
  71 ok($charinfo->{block},         undef);
  72 ok($charinfo->{script},        undef);
  73
  74 # 0x05d0 is in the Hebrew block and used.
  75
  76 $charinfo = charinfo(0x5d0);
  77
  78 ok($charinfo->{code},           '05D0');
  79 ok($charinfo->{name},           'HEBREW LETTER ALEF');
  80 ok($charinfo->{category},       'Lo');
  81 ok($charinfo->{combining},      '0');
  82 ok($charinfo->{bidi},           'R');
  83 ok($charinfo->{decomposition},  '');
  84 ok($charinfo->{decimal},        '');
  85 ok($charinfo->{digit},          '');
  86 ok($charinfo->{numeric},        '');
  87 ok($charinfo->{mirrored},       'N');
  88 ok($charinfo->{unicode10},      '');
  89 ok($charinfo->{comment},        '');
  90 ok($charinfo->{upper},          '');
  91 ok($charinfo->{lower},          '');
  92 ok($charinfo->{title},          '');
  93 ok($charinfo->{block},          'Hebrew');
  94 ok($charinfo->{script},         'Hebrew');
  95
  96 use UnicodeCD qw(charblock charscript);
  97
  98 # 0x0590 is in the Hebrew block but unused.
  99
 100 ok(charblock(0x590),          'Hebrew');
 101 ok(charscript(0x590),         undef);
 102
 103 $charinfo = charinfo(0xbe);
 104
 105 ok($charinfo->{code},           '00BE');
 106 ok($charinfo->{name},           'VULGAR FRACTION THREE QUARTERS');
 107 ok($charinfo->{category},       'No');
 108 ok($charinfo->{combining},      '0');
 109 ok($charinfo->{bidi},           'ON');
 110 ok($charinfo->{decomposition},  '<fraction> 0033 2044 0034');
 111 ok($charinfo->{decimal},        '');
 112 ok($charinfo->{digit},          '');
 113 ok($charinfo->{numeric},        '3/4');
 114 ok($charinfo->{mirrored},       'N');
 115 ok($charinfo->{unicode10},      'FRACTION THREE QUARTERS');
 116 ok($charinfo->{comment},        '');
 117 ok($charinfo->{upper},          '');
 118 ok($charinfo->{lower},          '');
 119 ok($charinfo->{title},          '');
 120 ok($charinfo->{block},          'Latin-1 Supplement');
 121 ok($charinfo->{script},         undef);
 122
 123 use UnicodeCD qw(charblocks charscripts);
 124
 125 my $charblocks = charblocks();
 126
 127 ok(exists $charblocks->{Thai});
 128 ok($charblocks->{Thai}->[0]->[0], hex('0e00'));
 129 ok(!exists $charblocks->{PigLatin});
 130
 131 my $charscripts = charscripts();
 132
 133 ok(exists $charscripts->{Armenian});
 134 ok($charscripts->{Armenian}->[0]->[0], hex('0531'));
 135 ok(!exists $charscripts->{PigLatin});
 136
 137 my $charscript;
 138
 139 $charscript = charscript("12ab");
 140 ok($charscript, 'Ethiopic');
 141
 142 $charscript = charscript("0x12ab");
 143 ok($charscript, 'Ethiopic');
 144
 145 $charscript = charscript("U+12ab");
 146 ok($charscript, 'Ethiopic');
 147
 148 my $ranges;
 149
 150 $ranges = charscript('Ogham');
 151 ok($ranges->[0]->[0], hex('1681'));
 152 ok($ranges->[0]->[1], hex('169a'));
 153
 154 use UnicodeCD qw(charinrange);
 155
 156 $ranges = charscript('Cherokee');
 157 ok(!charinrange($ranges, "139f"));
 158 ok( charinrange($ranges, "13a0"));
 159 ok( charinrange($ranges, "13f4"));
 160 ok(!charinrange($ranges, "13f5"));
 161
 162 ok(UnicodeCD::UnicodeVersion, 3.1);
 163
 164 use UnicodeCD qw(compexcl);
 165
 166 ok(!compexcl(0x0100));
 167 ok( compexcl(0x0958));
 168
 169 use UnicodeCD qw(casefold);
 170
 171 my $casefold;
 172
 173 $casefold = casefold(0x41);
 174
 175 ok($casefold->{code} eq '0041' &&
 176    $casefold->{status} eq 'C'  &&
 177    $casefold->{mapping} eq '0061');
 178
 179 $casefold = casefold(0xdf);
 180
 181 ok($casefold->{code} eq '00DF' &&
 182    $casefold->{status} eq 'F'  &&
 183    $casefold->{mapping} eq '0073 0073');
 184
 185 ok(!casefold(0x20));
 186
 187 use UnicodeCD qw(casespec);
 188
 189 my $casespec;
 190
 191 ok(!casespec(0x41));
 192
 193 $casespec = casespec(0xdf);
 194
 195 ok($casespec->{code} eq '00DF' &&
 196    $casespec->{lower} eq '00DF'  &&
 197    $casespec->{title} eq '0053 0073'  &&
 198    $casespec->{upper} eq '0053 0053' &&
 199    $casespec->{condition} eq undef);
 200
 201 $casespec = casespec(0x307);
 202
 203 ok($casespec->{code} eq '0307' &&
 204    $casespec->{lower} eq '0307'  &&
 205    $casespec->{title} eq ''  &&
 206    $casespec->{upper} eq '' &&
 207    $casespec->{condition} eq 'lt AFTER_i');