diff options
author | ser <ser@b2dd03c8-39d4-4d8f-98ff-823fe69b080e> | 2003-12-09 02:41:33 +0000 |
---|---|---|
committer | ser <ser@b2dd03c8-39d4-4d8f-98ff-823fe69b080e> | 2003-12-09 02:41:33 +0000 |
commit | e6636fe890ab7cf8f8f1b86ca54a3e10f98d43e6 (patch) | |
tree | 97264c7f6a6c1eb2af6909f8432a6631b4d2ccbb /lib/rexml/encodings | |
parent | 31963249b96e11ea1df66be8a91f016af4364d14 (diff) | |
download | ruby-e6636fe890ab7cf8f8f1b86ca54a3e10f98d43e6.tar.gz |
* Added the lower-case Shift-JIS files to the manifest. The upper-case ones
should be deprecated, but I need a Shift-JIS encoded XML file to test
against, first.
* Added support for maintaining external entity occurances in DTDs
* Deprecated the use of Document::DECLARATION. The new default declaration
can be gotten with XMLDecl::default()
* Refactored the encoding support code. It should be more robust now,
and fixes a few bugs.
* The XPath string() function now deals with Element nodes properly.
* Serialization with Output objects now works as would be expected.
* Various code cleanups, some reducing the number of warnings that Ruby 1.8.x
produces with REXML.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@5144 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
Diffstat (limited to 'lib/rexml/encodings')
-rw-r--r-- | lib/rexml/encodings/EUC-JP.rb | 49 | ||||
-rw-r--r-- | lib/rexml/encodings/ICONV.rb | 18 | ||||
-rw-r--r-- | lib/rexml/encodings/ISO-8859-1.rb | 42 | ||||
-rw-r--r-- | lib/rexml/encodings/UNILE.rb | 50 | ||||
-rw-r--r-- | lib/rexml/encodings/US-ASCII.rb | 42 | ||||
-rw-r--r-- | lib/rexml/encodings/UTF-16.rb | 50 | ||||
-rw-r--r-- | lib/rexml/encodings/UTF-8.rb | 18 |
7 files changed, 143 insertions, 126 deletions
diff --git a/lib/rexml/encodings/EUC-JP.rb b/lib/rexml/encodings/EUC-JP.rb index 8b146e5f0a..a1314d0856 100644 --- a/lib/rexml/encodings/EUC-JP.rb +++ b/lib/rexml/encodings/EUC-JP.rb @@ -1,31 +1,36 @@ begin - require 'uconv' + require 'iconv' - module REXML - module Encoding - def decode(str) - return Uconv::euctou8(str) - end + module REXML + module Encoding + @@__REXML_encoding_methods =<<-EOL + def decode(str) + return Iconv::iconv("utf-8", "euc-jp", str)[0] + end - def encode content - return Uconv::u8toeuc(content) - end - end - end + def encode content + return Iconv::iconv("euc-jp", "utf-8", content)[0] + end + EOL + end + end rescue LoadError begin - require 'iconv' - module REXML - module Encoding - def decode(str) - return Iconv::iconv("utf-8", "euc-jp", str)[0] - end + require 'uconv' + + module REXML + module Encoding + @@__REXML_encoding_methods =<<-EOL + def decode(str) + return Uconv::euctou8(str) + end - def encode content - return Iconv::iconv("euc-jp", "utf-8", content)[0] - end - end - end + def encode content + return Uconv::u8toeuc(content) + end + EOL + end + end rescue LoadError raise "uconv or iconv is required for Japanese encoding support." end diff --git a/lib/rexml/encodings/ICONV.rb b/lib/rexml/encodings/ICONV.rb index f1b5c80b87..384758d7b2 100644 --- a/lib/rexml/encodings/ICONV.rb +++ b/lib/rexml/encodings/ICONV.rb @@ -2,13 +2,15 @@ require "iconv" raise LoadError unless defined? Iconv module REXML - module Encoding - def decode( str ) - return Iconv::iconv(UTF_8, @encoding, str)[0] - end + module Encoding + @@__REXML_encoding_methods =<<-EOL + def decode( str ) + return Iconv::iconv("utf-8", @encoding, str)[0] + end - def encode( content ) - return Iconv::iconv(@encoding, UTF_8, content)[0] - end - end + def encode( content ) + return Iconv::iconv(@encoding, "utf-8", content)[0] + end + EOL + end end diff --git a/lib/rexml/encodings/ISO-8859-1.rb b/lib/rexml/encodings/ISO-8859-1.rb index 0cb9afd147..5beefbd408 100644 --- a/lib/rexml/encodings/ISO-8859-1.rb +++ b/lib/rexml/encodings/ISO-8859-1.rb @@ -1,23 +1,25 @@ module REXML - module Encoding - # Convert from UTF-8 - def encode content - array_utf8 = content.unpack('U*') - array_enc = [] - array_utf8.each do |num| - if num <= 0xFF - array_enc << num - else - # Numeric entity (&#nnnn;); shard by Stefan Scholl - array_enc.concat "&\##{num};".unpack('C*') - end - end - array_enc.pack('C*') - end + module Encoding + @@__REXML_encoding_methods =<<-EOL + # Convert from UTF-8 + def encode content + array_utf8 = content.unpack('U*') + array_enc = [] + array_utf8.each do |num| + if num <= 0xFF + array_enc << num + else + # Numeric entity (&#nnnn;); shard by Stefan Scholl + array_enc.concat "&\##{num};".unpack('C*') + end + end + array_enc.pack('C*') + end - # Convert to UTF-8 - def decode(str) - str.unpack('C*').pack('U*') - end - end + # Convert to UTF-8 + def decode(str) + str.unpack('C*').pack('U*') + end + EOL + end end diff --git a/lib/rexml/encodings/UNILE.rb b/lib/rexml/encodings/UNILE.rb index e57a784061..3ff9b2b53c 100644 --- a/lib/rexml/encodings/UNILE.rb +++ b/lib/rexml/encodings/UNILE.rb @@ -1,27 +1,29 @@ module REXML - module Encoding - def encode content - array_utf8 = content.unpack("U*") - array_enc = [] - array_utf8.each do |num| - if ((num>>16) > 0) - array_enc << ?? - array_enc << 0 - else - array_enc << (num & 0xFF) - array_enc << (num >> 8) - end - end - array_enc.pack('C*') - end + module Encoding + @@__REXML_encoding_string =<<-EOL + def encode content + array_utf8 = content.unpack("U*") + array_enc = [] + array_utf8.each do |num| + if ((num>>16) > 0) + array_enc << ?? + array_enc << 0 + else + array_enc << (num & 0xFF) + array_enc << (num >> 8) + end + end + array_enc.pack('C*') + end - def decode(str) - array_enc=str.unpack('C*') - array_utf8 = [] - 2.step(array_enc.size-1, 2){|i| - array_utf8 << (array_enc.at(i) + array_enc.at(i+1)*0x100) - } - array_utf8.pack('U*') - end - end + def decode(str) + array_enc=str.unpack('C*') + array_utf8 = [] + 2.step(array_enc.size-1, 2){|i| + array_utf8 << (array_enc.at(i) + array_enc.at(i+1)*0x100) + } + array_utf8.pack('U*') + end + EOL + end end diff --git a/lib/rexml/encodings/US-ASCII.rb b/lib/rexml/encodings/US-ASCII.rb index 0cb9afd147..618e0ad613 100644 --- a/lib/rexml/encodings/US-ASCII.rb +++ b/lib/rexml/encodings/US-ASCII.rb @@ -1,23 +1,25 @@ module REXML - module Encoding - # Convert from UTF-8 - def encode content - array_utf8 = content.unpack('U*') - array_enc = [] - array_utf8.each do |num| - if num <= 0xFF - array_enc << num - else - # Numeric entity (&#nnnn;); shard by Stefan Scholl - array_enc.concat "&\##{num};".unpack('C*') - end - end - array_enc.pack('C*') - end + module Encoding + @@__REXML_encoding_string =<<-EOL + # Convert from UTF-8 + def encode content + array_utf8 = content.unpack('U*') + array_enc = [] + array_utf8.each do |num| + if num <= 0xFF + array_enc << num + else + # Numeric entity (&#nnnn;); shard by Stefan Scholl + array_enc.concat "&\##{num};".unpack('C*') + end + end + array_enc.pack('C*') + end - # Convert to UTF-8 - def decode(str) - str.unpack('C*').pack('U*') - end - end + # Convert to UTF-8 + def decode(str) + str.unpack('C*').pack('U*') + end + EOL + end end diff --git a/lib/rexml/encodings/UTF-16.rb b/lib/rexml/encodings/UTF-16.rb index 31f2d81a5b..ecfc4f9945 100644 --- a/lib/rexml/encodings/UTF-16.rb +++ b/lib/rexml/encodings/UTF-16.rb @@ -1,27 +1,29 @@ module REXML - module Encoding - def encode content - array_utf8 = content.unpack("U*") - array_enc = [] - array_utf8.each do |num| - if ((num>>16) > 0) - array_enc << 0 - array_enc << ?? - else - array_enc << (num >> 8) - array_enc << (num & 0xFF) - end - end - array_enc.pack('C*') - end + module Encoding + @@__REXML_encoding_string =<<-EOL + def encode content + array_utf8 = content.unpack("U*") + array_enc = [] + array_utf8.each do |num| + if ((num>>16) > 0) + array_enc << 0 + array_enc << ?? + else + array_enc << (num >> 8) + array_enc << (num & 0xFF) + end + end + array_enc.pack('C*') + end - def decode(str) - array_enc=str.unpack('C*') - array_utf8 = [] - 2.step(arrayEnc.size-1, 2){|i| - array_utf8 << (array_enc.at(i+1) + array_enc.at(i)*0x100) - } - array_utf8.pack('U*') - end - end + def decode(str) + array_enc=str.unpack('C*') + array_utf8 = [] + 2.step(array_enc.size-1, 2){|i| + array_utf8 << (array_enc.at(i+1) + array_enc.at(i)*0x100) + } + array_utf8.pack('U*') + end + EOL + end end diff --git a/lib/rexml/encodings/UTF-8.rb b/lib/rexml/encodings/UTF-8.rb index 96fee4c4c0..33a7e490c4 100644 --- a/lib/rexml/encodings/UTF-8.rb +++ b/lib/rexml/encodings/UTF-8.rb @@ -1,11 +1,13 @@ module REXML - module Encoding - def encode content - content - end + module Encoding + @@__REXML_encoding_methods =<<-EOL + def encode content + content + end - def decode(str) - str - end - end + def decode(str) + str + end + EOL + end end |