mirror of
https://github.com/ruby/ruby.git
synced 2022-11-09 12:17:21 -05:00
7d21c237cc
for encoding changes. This should be the case on all 1.8 installations. When it isn't found (<1.6), the native REXML encoding mechanism is used. This cleaned out some files, and tightened up the code a bit; and iconv should be faster than the pure Ruby code. * Changed deprecated assert_not_nil to assert throughout the tests. * Parse exceptions are a little more verbose, and extend RuntimeError. * Bug fixes to XPathParser * The Light API is still shifting, like the sands of the desert. * Fixed a new Ruby 1.8.0 warning, added some speed optimizations, and tightened error reporting in the base parser git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@4737 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
50 lines
1.3 KiB
Ruby
50 lines
1.3 KiB
Ruby
module REXML
|
|
module Encoding
|
|
@@uconv_available = false
|
|
|
|
# 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
|
|
return if defined? @encoding and enc == @encoding
|
|
if enc and enc != UTF_8
|
|
@encoding = enc.upcase
|
|
begin
|
|
load 'rexml/encodings/ICONV.rb'
|
|
Iconv::iconv( UTF_8, @encoding, "" )
|
|
rescue LoadError, Exception => err
|
|
enc_file = File.join( "rexml", "encodings", "#@encoding.rb" )
|
|
begin
|
|
load enc_file
|
|
rescue LoadError
|
|
raise Exception.new( "No decoder found for encoding #@encoding. Please install iconv." )
|
|
end
|
|
end
|
|
else
|
|
enc = UTF_8
|
|
@encoding = enc.upcase
|
|
load 'rexml/encodings/UTF-8.rb'
|
|
end
|
|
ensure
|
|
$VERBOSE = old_verbosity
|
|
end
|
|
end
|
|
|
|
def check_encoding str
|
|
# We have to recognize UTF-16, LSB UTF-16, and UTF-8
|
|
return UTF_16 if str[0] == 254 && str[1] == 255
|
|
return UNILE if str[0] == 255 && str[1] == 254
|
|
str =~ /^\s*<?xml\s*version=(['"]).*?\2\s*encoding=(["'])(.*?)\2/um
|
|
return $1.upcase if $1
|
|
return UTF_8
|
|
end
|
|
end
|
|
end
|