view contrib/unicode2nginx/unicode-to-nginx.pl @ 570:8246d8a2c2be NGINX_0_8_37

nginx 0.8.37 *) Feature: the ngx_http_split_clients_module. *) Feature: the "map" directive supports keys more than 255 characters. *) Bugfix: nginx ignored the "private" and "no-store" values in the "Cache-Control" backend response header line. *) Bugfix: a "stub" parameter of an "include" SSI directive was not used, if empty response has 200 status code. *) Bugfix: if a proxied or FastCGI request was internally redirected to another proxied or FastCGI location, then a segmentation fault might occur in a worker process; the bug had appeared in 0.8.33. Thanks to Yichun Zhang. *) Bugfix: IMAP connections may hang until they timed out while talking to Zimbra server. Thanks to Alan Batie.
author Igor Sysoev <http://sysoev.ru>
date Mon, 17 May 2010 00:00:00 +0400
parents fa32d59d9a15
children
line wrap: on
line source

#!/usr/bin/perl -w

# Convert unicode mappings to nginx configuration file format.

# You may find useful mappings in various places, including
# unicode.org official site:
#
# http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1251.TXT
# http://www.unicode.org/Public/MAPPINGS/VENDORS/MISC/KOI8-R.TXT

# Needs perl 5.6 or later.

# Written by Maxim Dounin, mdounin@rambler-co.ru

###############################################################################

require 5.006;

while (<>) {
	# Skip comments and empty lines

	next if /^#/;
	next if /^\s*$/;
	chomp;

	# Convert mappings

	if (/^\s*0x(..)\s*0x(....)\s*(#.*)/) {
		# Mapping <from-code> <unicode-code> "#" <unicode-name>
		my $cs_code = $1;
		my $un_code = $2;
		my $un_name = $3;

		# Produce UTF-8 sequence from character code;

		my $un_utf8 = join('', map { sprintf("%02X", $_) } unpack("C*", pack("U", hex($un_code))));

		print "    $cs_code  $un_utf8 ; $un_name\n";

	} else {
		warn "Unrecognized line: '$_'";
	}
}

###############################################################################