summaryrefslogtreecommitdiff
path: root/tests/gen-casefold-txt.pl
diff options
context:
space:
mode:
authorOwen Taylor <otaylor@redhat.com>2001-07-02 00:49:21 +0000
committerOwen Taylor <otaylor@src.gnome.org>2001-07-02 00:49:21 +0000
commit4f96a13cba0fc1d445c76d30a7cb90b2971de06a (patch)
tree815b4a733bf96b7da6d4dd217cff264b6be31b60 /tests/gen-casefold-txt.pl
parentb37e7bbb53afd0f8d3386065aff0d74195737fd1 (diff)
Use G_N_ELEMENTS rather than a custom macro.
Sun Jul 1 20:16:25 2001 Owen Taylor <otaylor@redhat.com> * glib/guniprop.c (g_unichar_totitle): Use G_N_ELEMENTS rather than a custom macro. * glib/gen-unicode-tables.pl: Adapt to changes in table formats for Unicode 3.1 * glib/gunicode.h glib/guniprop.c glib/gunichartables.h glib/gen-unicode-tables.pl: Add case conversion functions g_utf8_casefold, g_utf8_strup, g_utf8_strdown. * tests/unicode-caseconv.c tests/gen-casefold-txt.pl tests/gen-casemap-txt.pl tests/casefold.txt tests/casemap.txt: Test cases for case conversion. * glib/gunicode.h glib/gunidecomp.[ch] glib/gunicomp.h glib/gen-unicode-tables.pl: Add function to do Unicode normalization g_utf8_normalize(). * tests/unicode-normalize.c: Test program for case conversion. * glib/gunicode.h glib/gunicollate.c: Add collation functions g_utf8_collate, g_utf8_collate_key. * test/unicode-collate.c: Test program for collation. * glib/gdate.c (g_date_fill_parse_tokens): Fix uninitialized variable. * glib/gdate.c (g_date_strftime) docs/Changes-2.0.txt: Make work with UTF-8 even if the locale isn't UTF-8 based. Still somewhat of broken, if the format string contains characters not representable in the current locale, will warn and not work. * glib/gdate.c: Use UTF-8 normalization and casefolding.
Diffstat (limited to 'tests/gen-casefold-txt.pl')
-rwxr-xr-xtests/gen-casefold-txt.pl82
1 files changed, 82 insertions, 0 deletions
diff --git a/tests/gen-casefold-txt.pl b/tests/gen-casefold-txt.pl
new file mode 100755
index 000000000..9301d73a3
--- /dev/null
+++ b/tests/gen-casefold-txt.pl
@@ -0,0 +1,82 @@
+#! /usr/bin/perl -w
+
+# Copyright (C) 1998, 1999 Tom Tromey
+# Copyright (C) 2001 Red Hat Software
+
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2, or (at your option)
+# any later version.
+
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+# GNU General Public License for more details.
+
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, write to the Free Software
+# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA
+# 02111-1307, USA.
+
+# gen-casefold-test.pl - Generate test cases for casefolding from Unicode data.
+# See http://www.unicode.org/Public/UNIDATA/UnicodeCharacterDatabase.html
+# Usage:
+# I consider the output of this program to be unrestricted. Use it as
+# you will.
+
+# Names of fields in the CaseFolding table
+$FOLDING_CODE = 0;
+$FOLDING_STATUS = 1;
+$FOLDING_MAPPING = 2;
+
+my $casefoldlen = 0;
+my @casefold;
+
+if (@ARGV != 2) {
+ $0 =~ s@.*/@@;
+ die "Usage: $0 UNICODE-VERSION CaseFolding.txt\n";
+}
+
+print <<EOT;
+# Test cases generated from Unicode $ARGV[0] data
+# by gen-casefold-test.pl. Do not edit.
+#
+# Some special hand crafted tests
+#
+AaBbCc@@\taabbcc@@
+#
+# Now the automatic tests
+#
+EOT
+
+open (INPUT, "< $ARGV[1]") || exit 1;
+
+while (<INPUT>)
+{
+ chop;
+
+ next if /^#/;
+ next if /^\s*$/;
+
+ s/\s*#.*//;
+
+ my @fields = split ('\s*;\s*', $_, 30);
+
+ my $raw_code = $fields[$FOLDING_CODE];
+ my $code = hex ($raw_code);
+
+ next if $code > 0xffff; # FIXME!
+
+ if ($#fields != 3)
+ {
+ printf STDERR ("Entry for $raw_code has wrong number of fields (%d)\n", $#fields);
+ next;
+ }
+
+ next if ($fields[$FOLDING_STATUS] eq 'S');
+
+ @values = map { hex ($_) } split /\s+/, $fields[$FOLDING_MAPPING];
+ printf ("%s\t%s\n", pack ("U", $code), pack ("U*", @values));
+}
+
+close INPUT;