eric-rfeedparser 0.9.951.2

data/LICENSE

@@ -0,0 +1,68 @@
+I include this license in good faith effort, and it should be considered the license for the code herein.  
+    - Jeff Hodges < jeff at somethingsimilar.com >
+--
+Universal Feed Parser (feedparser.py), its testing harness (feedparsertest.py),
+and its unit tests (everything in the tests/ directory) are released under the
+following license:
+
+----- begin license block -----
+
+Copyright (c) 2002-2005, Mark Pilgrim
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without modification,
+are permitted provided that the following conditions are met:
+
+* Redistributions of source code must retain the above copyright notice,
+  this list of conditions and the following disclaimer.
+* Redistributions in binary form must reproduce the above copyright notice,
+  this list of conditions and the following disclaimer in the documentation
+  and/or other materials provided with the distribution.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS 'AS IS'
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGE.
+
+----- end license block -----
+
+
+
+
+
+Universal Feed Parser documentation (everything in the docs/ directory) is
+released under the following license:
+
+----- begin license block -----
+
+Copyright 2004-2005 Mark Pilgrim. All rights reserved.
+
+Redistribution and use in source (XML DocBook) and "compiled" forms (SGML,
+HTML, PDF, PostScript, RTF and so forth) with or without modification, are
+permitted provided that the following conditions are met:
+
+* Redistributions of source code (XML DocBook) must retain the above copyright
+  notice, this list of conditions and the following disclaimer.
+* Redistributions in compiled form (transformed to other DTDs, converted to
+  PDF, PostScript, RTF and other formats) must reproduce the above copyright
+  notice, this list of conditions and the following disclaimer in the
+  documentation and/or other materials provided with the distribution.
+
+THIS DOCUMENTATION IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS 'AS IS'
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ARISING IN ANY WAY OUT OF THE USE OF THIS DOCUMENTATION, EVEN IF ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGE.

data/README

@@ -0,0 +1,50 @@
+= Universal Feed Parser
+  http://rfeedparser.rubyforge.org
+  Original Python code Copyright (c) 2002-5 by Mark Pilgrim
+  Ruby port by Jeff Hodges.
+
+== Description
+
+Parse nearly any RSS and Atom feeds in Ruby.  3000 unit tests.  Open source.
+
+== Installation
+
+For Debian-based systems:
+
+  $ sudo apt-get install libxml-ruby1.8 # or libxml-parser-ruby1.8
+
+TODO: dependency installation instructions for other platforms.
+
+And then:
+
+  $ sudo gem install rfeedparser
+
+Or for the latest development version:
+
+  $ git clone git://github.com/technomancy/rfeedparser.git
+
+Dependencies on other gems are handled by rubygems, but rfeedparser
+also relies on having bindings to a native XML parsing library. The
+recommended choice is libxml, which is installable with the
+libxml-ruby1.8 package in Debian-based systems. But it can also fall
+back to expat (the libxml-parser-ruby1.8 Debian package) if libxml is
+not installed.
+
+== Usage
+
+   require 'rubygems' # may omit if installed manually
+   require 'rfeedparser'
+
+   feed = FeedParser.parse("some-feed-stream-filepath-or-url")
+
+   feed.entries.each do |e|
+     puts e.title
+     puts e.content
+     puts e.published
+     puts '----'
+   end
+
+== Contributing
+
+Clone the git repository at git://github.com/jmhodges/rfeedparser.git and
+which has a webpage at http://github.com/jmhodges/rfeedparser/tree/master.

data/RUBY-TESTING

@@ -0,0 +1,66 @@
+=== Testing rFeedParser ===
+Simply run rake to run all of the FeedParser tests.
+
+Optionally, you can start up rfeedparserserver.rb and, in another shell, run rfeedparser.rb
+against "http://localhost:8097/tests/path/to/testcase.xml" if you want
+to try a test individually.  You can, of course, run rfeedparser.rb with
+the file path to the testcase, but there may be HTTP headers required for
+a successful run that can only be given by running rfeedparser against
+the HTTP server path. I'll probably merge feedparserserver.rb into
+rfeedparsertest.rb soon.  Note that there are many test failures that occur
+solely because of problems with a platforms iconv installation.  Inconsistency
+in iconv is the leading cause of errors in rfp's test cases.
+
+=== Last Count 20070321 ===
+By my last count, rfeedparsertest.rb says that there are 45 assertions
+that fail, and 4 that error out. I've included here a few tests that
+"Failed, Sort Of".  By that I mean, the behaviors the tests are meant to
+check are correct, but the test fails because of some other superficial
+or unrelated behavior.
+
+=== Tests Failed, Sort Of ===
+
+Problem: 
+    Hpricot adds end tags when it sees an unclosed tag.  This means that
+    certain tests that rely on feedparser.py's _HTMLSanitizer not closing
+    tags will fail.  Many of the tests affected (actually, all the ones
+    affected, AFAICT) would otherwise passed.
+
+Tests Affected:
+    * tests/wellformed/rss/item_description_not_a_doctype.xml  (extraneous trailing </a>)
+    * tests/illformed/rss/item_description_not_a_doctype.xml   (ditto)
+==
+Problem:
+    The Hpricot#scrub method I've written does not remove the dangerous
+    markup in the same way feedparser.py does, but the output is still safe.
+
+Tests Affected:
+    * tests/wellformed/sanitize/entry_content_crazy.xml
+    * tests/wellformed/sanitize/entry_summary_crazy.xml
+    * tests/wellformed/sanitize/entry_title_crazy.xml
+    * tests/wellformed/sanitize/feed_copyright_crazy.xml
+    * tests/wellformed/sanitize/feed_info_crazy.xml
+    * tests/wellformed/sanitize/feed_subtitle_crazy.xml
+    * tests/wellformed/sanitize/feed_tagline_crazy.xml
+    * tests/wellformed/sanitize/feed_title_crazy.xml
+    * tests/wellformed/sanitize/item_content_encoded_crazy.xml
+    * tests/wellformed/sanitize/item_description_crazy.xml
+    * tests/wellformed/sanitize/item_fullitem_crazy.xml
+    * tests/illformed/sanitize/entry_content_crazy.xml
+    * tests/illformed/sanitize/entry_summary_crazy.xml
+    * tests/illformed/sanitize/entry_title_crazy.xml
+    * tests/illformed/sanitize/feed_copyright_crazy.xml
+    * tests/illformed/sanitize/feed_info_crazy.xml
+    * tests/illformed/sanitize/feed_subtitle_crazy.xml
+    * tests/illformed/sanitize/feed_tagline_crazy.xml
+    * tests/illformed/sanitize/feed_title_crazy.xml
+    * tests/illformed/sanitize/item_content_encoded_crazy.xml
+    * tests/illformed/sanitize/item_description_crazy.xml
+    * tests/illformed/sanitize/item_fullitem_crazy.xml
+==
+
+Problem: 
+    My current system lacks a few encodings that rfeedparser and Iconv need.
+    This results in failures that will probably not occur on other machines.
+
+Tests Affected:

data/lib/rfeedparser/aliases.rb

@@ -0,0 +1,432 @@
+#!/usr/bin/env ruby
+
+module FeedParserUtilities
+  # Adapted from python2.4's encodings/aliases.py
+
+  Encoding_Aliases = {     
+    'unicode'		 => 'utf-16',  
+
+    # MacOSX does not have Unicode as a separate encoding nor even
+    # aliased. My Ubuntu box has it as a separate encoding but I cannot
+    # for the life of me figure out where the source code for UNICODE.so
+    # is (supposedly, in libc6 .deb but that's a damn lie), so I don't
+    # know what it expects. After some extensive research, I've decided
+    # to alias it to utf-16 much like Python does when it is built with
+    # --enable-unicode=ucs2. This could be seriously wrong. I have no idea.
+
+    # ascii codec
+    '646'                => 'ascii',
+    'ansi_x3.4_1968'     => 'ascii',
+    'ansi_x3_4_1968'     => 'ascii', # some email headers use this non-standard name
+    'ansi_x3.4_1986'     => 'ascii',
+    'cp367'              => 'ascii',
+    'csascii'            => 'ascii',
+    'ibm367'             => 'ascii',
+    'iso646_us'          => 'ascii',
+    'iso_646.irv_1991'   => 'ascii',
+    'iso_ir_6'           => 'ascii',
+    'us'                 => 'ascii',
+    'us_ascii'           => 'ascii',
+
+    # big5 codec
+    'big5_tw'            => 'big5',
+    'csbig5'             => 'big5',
+
+    # big5hkscs codec
+    'big5_hkscs'         => 'big5hkscs',
+    'hkscs'              => 'big5hkscs',
+
+    # cp037 codec
+    '037'                => 'cp037',
+    'csibm037'           => 'cp037',
+    'ebcdic_cp_ca'       => 'cp037',
+    'ebcdic_cp_nl'       => 'cp037',
+    'ebcdic_cp_us'       => 'cp037',
+    'ebcdic_cp_wt'       => 'cp037',
+    'ibm037'             => 'cp037',
+    'ibm039'             => 'cp037',
+
+    # cp1026 codec
+    '1026'               => 'cp1026',
+    'csibm1026'          => 'cp1026',
+    'ibm1026'            => 'cp1026',
+
+    # cp1140 codec
+    '1140'               => 'cp1140',
+    'ibm1140'            => 'cp1140',
+
+    # cp1250 codec
+    '1250'               => 'cp1250',
+    'windows_1250'       => 'cp1250',
+
+    # cp1251 codec
+    '1251'               => 'cp1251',
+    'windows_1251'       => 'cp1251',
+
+    # cp1252 codec
+    '1252'               => 'cp1252',
+    'windows_1252'       => 'cp1252',
+
+    # cp1253 codec
+    '1253'               => 'cp1253',
+    'windows_1253'       => 'cp1253',
+
+    # cp1254 codec
+    '1254'               => 'cp1254',
+    'windows_1254'       => 'cp1254',
+
+    # cp1255 codec
+    '1255'               => 'cp1255',
+    'windows_1255'       => 'cp1255',
+
+    # cp1256 codec
+    '1256'               => 'cp1256',
+    'windows_1256'       => 'cp1256',
+
+    # cp1257 codec
+    '1257'               => 'cp1257',
+    'windows_1257'       => 'cp1257',
+
+    # cp1258 codec
+    '1258'               => 'cp1258',
+    'windows_1258'       => 'cp1258',
+
+    # cp424 codec
+    '424'                => 'cp424',
+    'csibm424'           => 'cp424',
+    'ebcdic_cp_he'       => 'cp424',
+    'ibm424'             => 'cp424',
+
+    # cp437 codec
+    '437'                => 'cp437',
+    'cspc8codepage437'   => 'cp437',
+    'ibm437'             => 'cp437',
+
+    # cp500 codec
+    '500'                => 'cp500',
+    'csibm500'           => 'cp500',
+    'ebcdic_cp_be'       => 'cp500',
+    'ebcdic_cp_ch'       => 'cp500',
+    'ibm500'             => 'cp500',
+
+    # cp775 codec
+    '775'              => 'cp775',
+    'cspc775baltic'      => 'cp775',
+    'ibm775'             => 'cp775',
+
+    # cp850 codec
+    '850'                => 'cp850',
+    'cspc850multilingual' => 'cp850',
+    'ibm850'             => 'cp850',
+
+    # cp852 codec
+    '852'                => 'cp852',
+    'cspcp852'           => 'cp852',
+    'ibm852'             => 'cp852',
+
+    # cp855 codec
+    '855'                => 'cp855',
+    'csibm855'           => 'cp855',
+    'ibm855'             => 'cp855',
+
+    # cp857 codec
+    '857'                => 'cp857',
+    'csibm857'           => 'cp857',
+    'ibm857'             => 'cp857',
+
+    # cp860 codec
+    '860'                => 'cp860',
+    'csibm860'           => 'cp860',
+    'ibm860'             => 'cp860',
+
+    # cp861 codec
+    '861'                => 'cp861',
+    'cp_is'              => 'cp861',
+    'csibm861'           => 'cp861',
+    'ibm861'             => 'cp861',
+
+    # cp862 codec
+    '862'                => 'cp862',
+    'cspc862latinhebrew' => 'cp862',
+    'ibm862'             => 'cp862',
+
+    # cp863 codec
+    '863'                => 'cp863',
+    'csibm863'           => 'cp863',
+    'ibm863'             => 'cp863',
+
+    # cp864 codec
+    '864'                => 'cp864',
+    'csibm864'           => 'cp864',
+    'ibm864'             => 'cp864',
+
+    # cp865 codec
+    '865'                => 'cp865',
+    'csibm865'           => 'cp865',
+    'ibm865'             => 'cp865',
+
+    # cp866 codec
+    '866'                => 'cp866',
+    'csibm866'           => 'cp866',
+    'ibm866'             => 'cp866',
+
+    # cp869 codec
+    '869'                => 'cp869',
+    'cp_gr'              => 'cp869',
+    'csibm869'           => 'cp869',
+    'ibm869'             => 'cp869',
+
+    # cp932 codec
+    '932'                => 'cp932',
+    'ms932'              => 'cp932',
+    'mskanji'            => 'cp932',
+    'ms_kanji'           => 'cp932',
+
+    # cp949 codec
+    '949'                => 'cp949',
+    'ms949'              => 'cp949',
+    'uhc'                => 'cp949',
+
+    # cp950 codec
+    '950'                => 'cp950',
+    'ms950'              => 'cp950',
+
+    # euc_jp codec
+    'euc_jp'             => 'euc-jp',
+    'eucjp'              => 'euc-jp',
+    'ujis'               => 'euc-jp',
+    'u_jis'              => 'euc-jp',
+
+    # euc_kr codec
+    'euc_kr'             => 'euc-kr',
+    'euckr'              => 'euc-kr',
+    'korean'             => 'euc-kr',
+    'ksc5601'            => 'euc-kr',
+    'ks_c_5601'          => 'euc-kr',
+    'ks_c_5601_1987'     => 'euc-kr',
+    'ksx1001'            => 'euc-kr',
+    'ks_x_1001'          => 'euc-kr',
+
+    # gb18030 codec
+    'gb18030_2000'       => 'gb18030',
+
+    # gb2312 codec
+    'chinese'            => 'gb2312',
+    'csiso58gb231280'    => 'gb2312',
+    'euc_cn'             => 'gb2312',
+    'euccn'              => 'gb2312',
+    'eucgb2312_cn'       => 'gb2312',
+    'gb2312_1980'        => 'gb2312',
+    'gb2312_80'          => 'gb2312',
+    'iso_ir_58'          => 'gb2312',
+
+    # gbk codec
+    '936'                => 'gbk',
+    'cp936'              => 'gbk',
+    'ms936'              => 'gbk',
+
+    # hp-roman8 codec
+    'hp_roman8'          => 'hp-roman8',
+    'roman8'             => 'hp-roman8',
+    'r8'                 => 'hp-roman8',
+    'csHPRoman8'         => 'hp-roman8',
+
+    # iso2022_jp codec
+    'iso2022_jp'         => 'iso-2022-jp',
+    'csiso2022jp'        => 'iso-2022-jp',
+    'iso2022jp'          => 'iso-2022-jp',
+    'iso_2022_jp'        => 'iso-2022-jp',
+
+    # iso2022_jp_1 codec
+    'iso2002_jp_1'       => 'iso-2022-jp-1',
+    'iso2022jp_1'        => 'iso-2022-jp-1',
+    'iso_2022_jp_1'      => 'iso-2022-jp-1',
+
+    # iso2022_jp_2 codec
+    'iso2022_jp_2'       => 'iso-2002-jp-2',
+    'iso2022jp_2'        => 'iso-2022-jp-2',
+    'iso_2022_jp_2'      => 'iso-2022-jp-2',
+
+    # iso2022_jp_3 codec
+    'iso2002_jp_3'       => 'iso-2022-jp-3',
+    'iso2022jp_3'        => 'iso-2022-jp-3',
+    'iso_2022_jp_3'      => 'iso-2022-jp-3',
+
+    # iso2022_kr codec
+    'iso2022_kr'         => 'iso-2022-kr',
+    'csiso2022kr'        => 'iso-2022-kr',
+    'iso2022kr'          => 'iso-2022-kr',
+    'iso_2022_kr'        => 'iso-2022-kr',
+
+    # iso8859_10 codec
+    'iso8859_10'         => 'iso-8859-10',
+    'csisolatin6'        => 'iso-8859-10',
+    'iso_8859_10'        => 'iso-8859-10',
+    'iso_8859_10_1992'   => 'iso-8859-10',
+    'iso_ir_157'         => 'iso-8859-10',
+    'l6'                 => 'iso-8859-10',
+    'latin6'             => 'iso-8859-10',
+
+    # iso8859_13 codec
+    'iso8859_13'         => 'iso-8859-13',
+    'iso_8859_13'        => 'iso-8859-13',
+
+    # iso8859_14 codec
+    'iso8859_14'         => 'iso-8859-14',
+    'iso_8859_14'        => 'iso-8859-14',
+    'iso_8859_14_1998'   => 'iso-8859-14',
+    'iso_celtic'         => 'iso-8859-14',
+    'iso_ir_199'         => 'iso-8859-14',
+    'l8'                 => 'iso-8859-14',
+    'latin8'             => 'iso-8859-14',
+
+    # iso8859_15 codec
+    'iso8859_15'         => 'iso-8859-15',
+    'iso_8859_15'        => 'iso-8859-15',
+
+    # iso8859_1 codec
+    'latin_1'            => 'iso-8859-1',
+    'cp819'              => 'iso-8859-1',
+    'csisolatin1'        => 'iso-8859-1',
+    'ibm819'             => 'iso-8859-1',
+    'iso8859'            => 'iso-8859-1',
+    'iso_8859_1'         => 'iso-8859-1',
+    'iso_8859_1_1987'    => 'iso-8859-1',
+    'iso_ir_100'         => 'iso-8859-1',
+    'l1'                 => 'iso-8859-1',
+    'latin'              => 'iso-8859-1',
+    'latin1'             => 'iso-8859-1',
+
+    # iso8859_2 codec
+    'iso8859_2'          => 'iso-8859-2',
+    'csisolatin2'        => 'iso-8859-2',
+    'iso_8859_2'         => 'iso-8859-2',
+    'iso_8859_2_1987'    => 'iso-8859-2',
+    'iso_ir_101'         => 'iso-8859-2',
+    'l2'                 => 'iso-8859-2',
+    'latin2'             => 'iso-8859-2',
+
+    # iso8859_3 codec
+    'iso8859_3'          => 'iso-8859-3',
+    'csisolatin3'        => 'iso-8859-3',
+    'iso_8859_3'         => 'iso-8859-3',
+    'iso_8859_3_1988'    => 'iso-8859-3',
+    'iso_ir_109'         => 'iso-8859-3',
+    'l3'                 => 'iso-8859-3',
+    'latin3'             => 'iso-8859-3',
+
+    # iso8859_4 codec
+    'iso8849_4'          => 'iso-8859-4',
+    'csisolatin4'        => 'iso-8859-4',
+    'iso_8859_4'         => 'iso-8859-4',
+    'iso_8859_4_1988'    => 'iso-8859-4',
+    'iso_ir_110'         => 'iso-8859-4',
+    'l4'                 => 'iso-8859-4',
+    'latin4'             => 'iso-8859-4',
+
+    # iso8859_5 codec
+    'iso8859_5'          => 'iso-8859-5',
+    'csisolatincyrillic' => 'iso-8859-5',
+    'cyrillic'           => 'iso-8859-5',
+    'iso_8859_5'         => 'iso-8859-5',
+    'iso_8859_5_1988'    => 'iso-8859-5',
+    'iso_ir_144'         => 'iso-8859-5',
+
+    # iso8859_6 codec
+    'iso8859_6'          => 'iso-8859-6',
+    'arabic'             => 'iso-8859-6',
+    'asmo_708'           => 'iso-8859-6',
+    'csisolatinarabic'   => 'iso-8859-6',
+    'ecma_114'           => 'iso-8859-6',
+    'iso_8859_6'         => 'iso-8859-6',
+    'iso_8859_6_1987'    => 'iso-8859-6',
+    'iso_ir_127'         => 'iso-8859-6',
+
+    # iso8859_7 codec
+    'iso8859_7'          => 'iso-8859-7',
+    'csisolatingreek'    => 'iso-8859-7',
+    'ecma_118'           => 'iso-8859-7',
+    'elot_928'           => 'iso-8859-7',
+    'greek'              => 'iso-8859-7',
+    'greek8'             => 'iso-8859-7',
+    'iso_8859_7'         => 'iso-8859-7',
+    'iso_8859_7_1987'    => 'iso-8859-7',
+    'iso_ir_126'         => 'iso-8859-7',
+
+    # iso8859_8 codec
+    'iso8859_9'          => 'iso8859_8',
+    'csisolatinhebrew'   => 'iso-8859-8',
+    'hebrew'             => 'iso-8859-8',
+    'iso_8859_8'         => 'iso-8859-8',
+    'iso_8859_8_1988'    => 'iso-8859-8',
+    'iso_ir_138'         => 'iso-8859-8',
+
+    # iso8859_9 codec
+    'iso8859_9'          => 'iso-8859-9',
+    'csisolatin5'        => 'iso-8859-9',
+    'iso_8859_9'         => 'iso-8859-9',
+    'iso_8859_9_1989'    => 'iso-8859-9',
+    'iso_ir_148'         => 'iso-8859-9',
+    'l5'                 => 'iso-8859-9',
+    'latin5'             => 'iso-8859-9',
+
+    # iso8859_11 codec
+    'iso8859_11'         => 'iso-8859-11',
+    'thai'               => 'iso-8859-11',
+    'iso_8859_11'        => 'iso-8859-11',
+    'iso_8859_11_2001'   => 'iso-8859-11',
+
+    # iso8859_16 codec
+    'iso8859_16'         => 'iso-8859-16',
+    'iso_8859_16'        => 'iso-8859-16',
+    'iso_8859_16_2001'   => 'iso-8859-16',
+    'iso_ir_226'         => 'iso-8859-16',
+    'l10'                => 'iso-8859-16',
+    'latin10'            => 'iso-8859-16',
+
+    # cskoi8r codec 
+    'koi8_r'             => 'cskoi8r',
+
+    # mac_cyrillic codec
+    'mac_cyrillic'       => 'maccyrillic',
+
+    # shift_jis codec
+    'csshiftjis'         => 'shift_jis',
+    'shiftjis'           => 'shift_jis',
+    'sjis'               => 'shift_jis',
+    's_jis'              => 'shift_jis',
+
+    # shift_jisx0213 codec
+    'shiftjisx0213'      => 'shift_jisx0213',
+    'sjisx0213'          => 'shift_jisx0213',
+    's_jisx0213'         => 'shift_jisx0213',
+
+    # utf_16 codec
+    'utf_16'             => 'utf-16',
+    'u16'                => 'utf-16',
+    'utf16'              => 'utf-16',
+
+    # utf_16_be codec
+    'utf_16_be'          => 'utf-16be',
+    'unicodebigunmarked' => 'utf-16be',
+    'utf_16be'           => 'utf-16be',
+
+    # utf_16_le codec
+    'utf_16_le'          => 'utf-16le',
+    'unicodelittleunmarked' => 'utf-16le',
+    'utf_16le'           => 'utf-16le',
+
+    # utf_7 codec
+    'utf_7'              => 'utf-7',
+    'u7'                 => 'utf-7',
+    'utf7'               => 'utf-7',
+
+    # utf_8 codec
+    'utf_8'              => 'utf-8',
+    'u8'                 => 'utf-8',
+    'utf'                => 'utf-8',
+    'utf8'               => 'utf-8',
+    'utf8_ucs2'          => 'utf-8',
+    'utf8_ucs4'          => 'utf-8',
+  }
+end