1
0
mirror of git://git.gnupg.org/gnupg.git synced 2024-11-04 20:38:50 +01:00
gnupg/regexp/parse-unidata.awk
NIIBE Yutaka 8904b18822 regexp: Fix generation of _unicode_mapping.c.
* configure.ac (AWK_HEX_NUMBER_OPTION): Detect GNU Awk.
* regexp/Makefile.am: Use AWK_HEX_NUMBER_OPTION.
* regexp/parse-unidata.awk: Don't use strtonum.

--

Backport master commit of:
	50b320952e

GnuPG-bug-id: 4915
Signed-off-by: NIIBE Yutaka <gniibe@fsij.org>
2020-07-15 14:18:09 +09:00

63 lines
1.4 KiB
Awk

#
# parse-unidata.awk - generate a table (unicode_case_mapping_upper)
#
# Copyright (C) 2020 g10 Code GmbH
#
# This file is part of GnuPG.
#
# GnuPG 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 3 of the License, or
# (at your option) any later version.
#
# GnuPG 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, see <https://www.gnu.org/licenses/>.
#
# Parse the unicode data from:
# https://www.unicode.org/Public/UCD/latest/ucd/UnicodeData.txt
# to generate case mapping table
BEGIN {
print("/* Generated from UnicodeData.txt */")
print("")
print("static const struct casemap unicode_case_mapping_upper[] = {")
FS = ";"
count = 0
}
{
code = int("0x" $1)
name = $2
class = $3
upper = $13
lower = $14
title = $15
if (code <= 127) {
next
}
if (code > 65535) {
next
}
if ($3 !~ /^L.*/) {
next
}
if (upper != "") {
printf("\t{ 0x" tolower($1) ", 0x" tolower(upper) " },")
count++
if ((count % 4) == 0) {
print("")
}
}
}
END {
print("\n};")
}