Mercurial > hg > nginx
view contrib/unicode2nginx/unicode-to-nginx.pl @ 3427:612436ad775a stable-0.7
merge r3153, r3154, r3288, r3382:
request header processing fixes:
*) $host is always in low case:
*) move low case convertation from ngx_http_find_virtual_server()
to ngx_http_validate_host()
*) add in ngx_http_validate_host() capability to copy host name in the pool
allocated memory
*) fix segfault if there is single large_client_header_buffers
and a request line fills it completely
*) default large_client_header_buffers' buffer size should be 8K as compatible
with Apache's one
author | Igor Sysoev <igor@sysoev.ru> |
---|---|
date | Mon, 01 Feb 2010 14:16:45 +0000 |
parents | 63a820b0bc6c |
children | 8752257e883f |
line wrap: on
line source
#!/usr/bin/perl -w # Convert unicode mappings to nginx configuration file format. # You may find useful mappings in various places, including # unicode.org official site: # # http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1251.TXT # http://www.unicode.org/Public/MAPPINGS/VENDORS/MISC/KOI8-R.TXT # Needs perl 5.6 or later. # Written by Maxim Dounin, mdounin@rambler-co.ru ############################################################################### require 5.006; while (<>) { # Skip comments and empty lines next if /^#/; next if /^\s*$/; 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 ; $un_name\n"; } else { warn "Unrecognized line: '$_'"; } } ###############################################################################