mirror of
https://github.com/ruby/ruby.git
synced 2022-11-09 12:17:21 -05:00
1d8c98a486
http://www.germane-software.com/repos/rexml/tags/3.1.7 r1278@bean: ser | 2007-06-07 00:53:06 -0400 Fixed a double-encoding bug. This was a regression, related to ticket:48. r1292@bean: ser | 2007-07-25 08:19:36 -0400 r1279@bean: ser | 2007-06-09 23:19:02 -0400 Fixes ticket:89 -- encoding CP-1252 was broken. ISO-8859-15 had the same problem. Also in this patch is a fix to merge.rb (unused, but it should at least contain no errors), and a unit test for ticket:88. r1293@bean: ser | 2007-07-25 08:19:37 -0400 r1281@bean: ser | 2007-07-24 11:08:48 -0400 Addresses ticket:85 This is a major rewrite of the XML formatting code. The XML writers have all been extracted out of the classes and put into their own class containers. This makes writing parsers easier, and cleaner. There are three formatters, which correspond to the previous three XML writing modes: REXML::Formatters::Default Prints the XML document exactly as it was parsed REXML::Formatters::Pretty Pretty prints the XML document, destroying whitespace in the document REXML::Formatters::Transitive Pretty prints the XML document, preserving whitespace All of the write() functions have been deprecated (some are still used, but these will also go away) except the write() function on Document, which is left for convenience. To pretty print an XML document the canonical way: formatter = REXML::Formatters::Pretty.new( 5 ) # indent by 5 spaces formatter.write( document, output ) r1294@bean: ser | 2007-07-25 08:19:38 -0400 r1283@bean: ser | 2007-07-24 19:53:30 -0400 This goes with the previous commit. r1295@bean: ser | 2007-07-25 08:19:39 -0400 r1285@bean: ser | 2007-07-24 20:02:07 -0400 And THIS goes with the previous two patches. Dammit. r1296@bean: ser | 2007-07-25 08:19:40 -0400 r1287@bean: ser | 2007-07-24 20:12:25 -0400 Applied patch from Jeff Barczewski. Note that this changes what the values of the name and IDs are from the previous behavior -- the values no longer include the quotes. This is the correct behavior, so I'm leaving it in, but it is not backwards compatible. Also fixes the serializer so that it outputs the doctype in a correct format (needed as a result of this change). r1297@bean: ser | 2007-07-25 08:38:38 -0400 Version update git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@12844 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
66 lines
2 KiB
Ruby
66 lines
2 KiB
Ruby
# -*- mode: ruby; ruby-indent-level: 2; indent-tabs-mode: t; tab-width: 2 -*- vim: sw=2 ts=2
|
|
module REXML
|
|
module Encoding
|
|
@encoding_methods = {}
|
|
def self.register(enc, &block)
|
|
@encoding_methods[enc] = block
|
|
end
|
|
def self.apply(obj, enc)
|
|
@encoding_methods[enc][obj]
|
|
end
|
|
def self.encoding_method(enc)
|
|
@encoding_methods[enc]
|
|
end
|
|
|
|
# Native, default format is UTF-8, so it is declared here rather than in
|
|
# an encodings/ definition.
|
|
UTF_8 = 'UTF-8'
|
|
UTF_16 = 'UTF-16'
|
|
UNILE = 'UNILE'
|
|
|
|
# ID ---> Encoding name
|
|
attr_reader :encoding
|
|
def encoding=( enc )
|
|
old_verbosity = $VERBOSE
|
|
begin
|
|
$VERBOSE = false
|
|
enc = enc.nil? ? nil : enc.upcase
|
|
return false if defined? @encoding and enc == @encoding
|
|
if enc and enc != UTF_8
|
|
@encoding = enc
|
|
raise ArgumentError, "Bad encoding name #@encoding" unless @encoding =~ /^[\w-]+$/
|
|
@encoding.untaint
|
|
begin
|
|
require 'rexml/encodings/ICONV.rb'
|
|
Encoding.apply(self, "ICONV")
|
|
rescue LoadError, Exception
|
|
begin
|
|
enc_file = File.join( "rexml", "encodings", "#@encoding.rb" )
|
|
require enc_file
|
|
Encoding.apply(self, @encoding)
|
|
rescue LoadError => err
|
|
puts err.message
|
|
raise ArgumentError, "No decoder found for encoding #@encoding. Please install iconv."
|
|
end
|
|
end
|
|
else
|
|
@encoding = UTF_8
|
|
require 'rexml/encodings/UTF-8.rb'
|
|
Encoding.apply(self, @encoding)
|
|
end
|
|
ensure
|
|
$VERBOSE = old_verbosity
|
|
end
|
|
true
|
|
end
|
|
|
|
def check_encoding str
|
|
# We have to recognize UTF-16, LSB UTF-16, and UTF-8
|
|
return UTF_16 if /\A\xfe\xff/n =~ str
|
|
return UNILE if /\A\xff\xfe/n =~ str
|
|
str =~ /^\s*<\?xml\s+version\s*=\s*(['"]).*?\1\s+encoding\s*=\s*(["'])(.*?)\2/um
|
|
return $3.upcase if $3
|
|
return UTF_8
|
|
end
|
|
end
|
|
end
|