view contrib/unicode2nginx/unicode-to-nginx.pl @ 6298:8f6d753c1953

Adjusted file->sys_offset after the write() syscall. This fixes suboptimal behavior caused by surplus lseek() for sequential writes on systems without pwrite(). A consecutive read after write might result in an error on systems without pread() and pwrite(). Fortunately, at the moment there are no widely used systems without these syscalls.
author Valentin Bartenev <vbart@nginx.com>
date Tue, 17 Nov 2015 19:01:41 +0300
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: '$_'";
	}
}

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