view contrib/unicode2nginx/unicode-to-nginx.pl @ 482:392c16f2d858 NGINX_0_7_53

nginx 0.7.53 *) Change: now a log set by --error-log-path is created from the very start-up. *) Feature: now the start up errors and warnings are outputted to an error_log and stderr. *) Feature: the empty --prefix= configure parameter forces nginx to use a directory where it was run as prefix. *) Feature: the -p switch. *) Feature: the -s switch on Unix platforms. *) Feature: the -? and -h switches. Thanks to Jerome Loyet. *) Feature: now switches may be set in condensed form. *) Bugfix: nginx/Windows did not work if configuration file was given by the -c switch. *) Bugfix: temporary files might be not removed if the "proxy_store", "fastcgi_store", "proxy_cache", or "fastcgi_cache" were used. Thanks to Maxim Dounin. *) Bugfix: an incorrect value was passed to mail proxy authentication server in "Auth-Method" header line; the bug had appeared in 0.7.34. Thanks to Simon Lecaille. *) Bugfix: system error text descriptions were not logged on Linux; the bug had appeared in 0.7.45. *) Bugfix: the "fastcgi_cache_min_uses" directive did not work. Thanks to Andrew Vorobyoff.
author Igor Sysoev <http://sysoev.ru>
date Mon, 27 Apr 2009 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: '$_'";
	}
}

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