tests/gen-casefold-txt.pl

   1 #! /usr/bin/perl -w
   2
   3 #    Copyright (C) 1998, 1999 Tom Tromey
   4 #    Copyright (C) 2001 Red Hat Software
   5
   6 #    This program is free software; you can redistribute it and/or modify
   7 #    it under the terms of the GNU General Public License as published by
   8 #    the Free Software Foundation; either version 2, or (at your option)
   9 #    any later version.
  10
  11 #    This program is distributed in the hope that it will be useful,
  12 #    but WITHOUT ANY WARRANTY; without even the implied warranty of
  13 #    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  14 #    GNU General Public License for more details.
  15
  16 #    You should have received a copy of the GNU General Public License
  17 #    along with this program; if not, see <http://www.gnu.org/licenses/>.
  18
  19 # gen-casefold-test.pl - Generate test cases for casefolding from Unicode data.
  20 # See http://www.unicode.org/Public/UNIDATA/UnicodeCharacterDatabase.html
  21 # Usage:
  22 # I consider the output of this program to be unrestricted.  Use it as
  23 # you will.
  24
  25 require 5.006;
  26
  27 # Names of fields in the CaseFolding table
  28 $FOLDING_CODE = 0;
  29 $FOLDING_STATUS = 1;
  30 $FOLDING_MAPPING = 2;
  31
  32 my $casefoldlen = 0;
  33 my @casefold;
  34
  35 if (@ARGV != 2) {
  36     $0 =~ s@.*/@@;
  37     die "Usage: $0 UNICODE-VERSION  CaseFolding.txt\n";
  38 }
  39
  40 print <<EOT;
  41 # Test cases generated from Unicode $ARGV[0] data
  42 # by gen-casefold-test.pl. Do not edit.
  43 #
  44 # Some special hand crafted tests
  45 #
  46 AaBbCc@@\taabbcc@@
  47 #
  48 # Now the automatic tests
  49 #
  50 EOT
  51
  52 binmode STDOUT, ":utf8";
  53 open (INPUT, "< $ARGV[1]") || exit 1;
  54
  55 while (<INPUT>)
  56 {
  57     chop;
  58
  59     next if /^#/;
  60     next if /^\s*$/;
  61
  62     s/\s*#.*//;
  63
  64     my @fields = split ('\s*;\s*', $_, 30);
  65
  66     my $raw_code = $fields[$FOLDING_CODE];
  67     my $code = hex ($raw_code);
  68
  69     if ($#fields != 3)
  70     {
  71         printf STDERR ("Entry for $raw_code has wrong number of fields (%d)\n", $#fields);
  72         next;
  73     }
  74
  75     # skip simple and Turkic mappings
  76     next if ($fields[$FOLDING_STATUS] =~ /^[ST]$/);
  77
  78     @values = map { hex ($_) } split /\s+/, $fields[$FOLDING_MAPPING];
  79     printf ("%s\t%s\n", pack ("U", $code), pack ("U*", @values));
  80 }
  81
  82 close INPUT;