ruby--ruby/lib/rexml/encodings/CP-1252.rb

104 lines
4.0 KiB
Ruby
Raw Normal View History

#
# This class was contributed by Mikko Tiihonen mikko DOT tiihonen AT hut DOT fi
#
module REXML
module Encoding
Merges upstream changes for REXML v3.1.7 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
2007-07-25 12:47:23 +00:00
register( "CP-1252" ) do |o|
class << o
alias encode encode_cp1252
alias decode decode_cp1252
end
end
# Convert from UTF-8
Merges upstream changes for REXML v3.1.7 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
2007-07-25 12:47:23 +00:00
def encode_cp1252(content)
array_utf8 = content.unpack('U*')
array_enc = []
array_utf8.each do |num|
case num
# shortcut first bunch basic characters
when 0..0xFF; array_enc << num
# characters added compared to iso-8859-1
when 0x20AC; array_enc << 0x80 # 0xe2 0x82 0xac
when 0x201A; array_enc << 0x82 # 0xe2 0x82 0x9a
when 0x0192; array_enc << 0x83 # 0xc6 0x92
when 0x201E; array_enc << 0x84 # 0xe2 0x82 0x9e
when 0x2026; array_enc << 0x85 # 0xe2 0x80 0xa6
when 0x2020; array_enc << 0x86 # 0xe2 0x80 0xa0
when 0x2021; array_enc << 0x87 # 0xe2 0x80 0xa1
when 0x02C6; array_enc << 0x88 # 0xcb 0x86
when 0x2030; array_enc << 0x89 # 0xe2 0x80 0xb0
when 0x0160; array_enc << 0x8A # 0xc5 0xa0
when 0x2039; array_enc << 0x8B # 0xe2 0x80 0xb9
when 0x0152; array_enc << 0x8C # 0xc5 0x92
when 0x017D; array_enc << 0x8E # 0xc5 0xbd
when 0x2018; array_enc << 0x91 # 0xe2 0x80 0x98
when 0x2019; array_enc << 0x92 # 0xe2 0x80 0x99
when 0x201C; array_enc << 0x93 # 0xe2 0x80 0x9c
when 0x201D; array_enc << 0x94 # 0xe2 0x80 0x9d
when 0x2022; array_enc << 0x95 # 0xe2 0x80 0xa2
when 0x2013; array_enc << 0x96 # 0xe2 0x80 0x93
when 0x2014; array_enc << 0x97 # 0xe2 0x80 0x94
when 0x02DC; array_enc << 0x98 # 0xcb 0x9c
when 0x2122; array_enc << 0x99 # 0xe2 0x84 0xa2
when 0x0161; array_enc << 0x9A # 0xc5 0xa1
when 0x203A; array_enc << 0x9B # 0xe2 0x80 0xba
when 0x0152; array_enc << 0x9C # 0xc5 0x93
when 0x017E; array_enc << 0x9E # 0xc5 0xbe
when 0x0178; array_enc << 0x9F # 0xc5 0xb8
else
# all remaining basic characters can be used directly
if num <= 0xFF
array_enc << num
else
# Numeric entity (&#nnnn;); shard by Stefan Scholl
array_enc.concat "&\##{num};".unpack('C*')
end
end
end
array_enc.pack('C*')
end
# Convert to UTF-8
Merges upstream changes for REXML v3.1.7 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
2007-07-25 12:47:23 +00:00
def decode_cp1252(str)
array_latin9 = str.unpack('C*')
array_enc = []
array_latin9.each do |num|
case num
# characters that added compared to iso-8859-1
when 0x80; array_enc << 0x20AC # 0xe2 0x82 0xac
when 0x82; array_enc << 0x201A # 0xe2 0x82 0x9a
when 0x83; array_enc << 0x0192 # 0xc6 0x92
when 0x84; array_enc << 0x201E # 0xe2 0x82 0x9e
when 0x85; array_enc << 0x2026 # 0xe2 0x80 0xa6
when 0x86; array_enc << 0x2020 # 0xe2 0x80 0xa0
when 0x87; array_enc << 0x2021 # 0xe2 0x80 0xa1
when 0x88; array_enc << 0x02C6 # 0xcb 0x86
when 0x89; array_enc << 0x2030 # 0xe2 0x80 0xb0
when 0x8A; array_enc << 0x0160 # 0xc5 0xa0
when 0x8B; array_enc << 0x2039 # 0xe2 0x80 0xb9
when 0x8C; array_enc << 0x0152 # 0xc5 0x92
when 0x8E; array_enc << 0x017D # 0xc5 0xbd
when 0x91; array_enc << 0x2018 # 0xe2 0x80 0x98
when 0x92; array_enc << 0x2019 # 0xe2 0x80 0x99
when 0x93; array_enc << 0x201C # 0xe2 0x80 0x9c
when 0x94; array_enc << 0x201D # 0xe2 0x80 0x9d
when 0x95; array_enc << 0x2022 # 0xe2 0x80 0xa2
when 0x96; array_enc << 0x2013 # 0xe2 0x80 0x93
when 0x97; array_enc << 0x2014 # 0xe2 0x80 0x94
when 0x98; array_enc << 0x02DC # 0xcb 0x9c
when 0x99; array_enc << 0x2122 # 0xe2 0x84 0xa2
when 0x9A; array_enc << 0x0161 # 0xc5 0xa1
when 0x9B; array_enc << 0x203A # 0xe2 0x80 0xba
when 0x9C; array_enc << 0x0152 # 0xc5 0x93
when 0x9E; array_enc << 0x017E # 0xc5 0xbe
when 0x9F; array_enc << 0x0178 # 0xc5 0xb8
else
array_enc << num
end
end
array_enc.pack('U*')
end
end
end