Mercurial > hg > nginx-vendor-current

diff contrib/unicode2nginx/unicode-to-nginx.pl @ 216:fa32d59d9a15 NGINX_0_3_55

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
nginx 0.3.55 *) Feature: the "stub" parameter in the "include" SSI command. *) Feature: the "block" SSI command. *) Feature: the unicode2nginx script was added to contrib. *) Bugfix: if a "root" was specified by variable only, then the root was relative to a server prefix. *) Bugfix: if the request contained "//" or "/./" and escaped symbols after them, then the proxied request was sent unescaped. *) Bugfix: the $r->headers_in("Cookie") of the ngx_http_perl_module now returns all "Cookie" header lines. *) Bugfix: a segmentation fault occurred if "client_body_in_file_only on" was used and nginx switched to a next upstream. *) Bugfix: on some condition while reconfiguration character codes inside the "charset_map" may be treated invalid; bug appeared in 0.3.50.
author Igor Sysoev <http://sysoev.ru>
date Fri, 28 Jul 2006 00:00:00 +0400
parents
children
line wrap: on
line diff
new file mode 100755
--- /dev/null
+++ b/contrib/unicode2nginx/unicode-to-nginx.pl
@@ -0,0 +1,45 @@
+#!/usr/bin/perl -w
+
+# Convert unicode mappings to nginx configuration file format.
+
+# You may find useful mappings in various places, including
+# unicode.org official site:
+#
+# http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1251.TXT
+# http://www.unicode.org/Public/MAPPINGS/VENDORS/MISC/KOI8-R.TXT
+
+# Needs perl 5.6 or later.
+
+# Written by Maxim Dounin, mdounin@rambler-co.ru
+
+###############################################################################
+
+require 5.006;
+
+while (<>) {
+	# Skip comments and empty lines
+
+	next if /^#/;
+	next if /^\s*$/;
+	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 ; $un_name\n";
+
+	} else {
+		warn "Unrecognized line: '$_'";
+	}
+}
+
+###############################################################################