htmlentities 3.0.0 → 3.0.1

data/CHANGES

@@ -1,29 +1,32 @@
+== 3.0.1 (2005-04-08)
+* Improved documentation.
+
 == 3.0.0 (2005-04-08)
 * Changed licence to MIT due to confusion with previous 'Fair' licence (my
   intention was to be liberal, not obscure).
 * Moved basic functionality out of String class; for previous behaviour,
-  require 'htmlentities/string'
-* Changed version numbering scheme
-* Now available as a Gem
+  require 'htmlentities/string'.
+* Changed version numbering scheme.
+* Now available as a Gem.
 
 == 2.2 (2005-11-07)
-* Important bug fixes -- thanks to Moonwolf
+* Important bug fixes -- thanks to Moonwolf.
 * Decoding hexadecimal entities now accepts 'f' as a hex digit. (D'oh!)
-* Decimal decoding edge cases addressed
-* Test cases added
+* Decimal decoding edge cases addressed.
+* Test cases added.
 
 == 2.1 (2005-10-31)
-* Removed some unnecessary code in basic entity encoding
+* Removed some unnecessary code in basic entity encoding.
 * Improved handling of encoding: commands are now automatically sorted, so the
-  user doesn't have to worry about their order
-* Now using setup.rb
-* Tests moved to separate file
+  user doesn't have to worry about their order.
+* Now using setup.rb.
+* Tests moved to separate file.
 
 == 2.0 (2005-08-23)
-* Added encoding to entities
-* Decoding interface unchanged
-* Fixed a bug with handling high codepoints
+* Added encoding to entities.
+* Decoding interface unchanged.
+* Fixed a bug with handling high codepoints.
 
 == 1.0 (2005-08-03)
-* Initial release
-* Decoding only
+* Initial release.
+* Decoding only.

data/lib/htmlentities.rb

@@ -2,85 +2,84 @@
 # HTML entity encoding and decoding for Ruby
 #
 
-module HTMLEntities # :nodoc:
+module HTMLEntities
   
   class InstructionError < RuntimeError
   end
 
-  #
-  # MAP is a hash of all the HTML entities I could discover, as taken
-  # from the w3schools page on the subject:
-  # http://www.w3schools.com/html/html_entitiesref.asp
-  # The format is 'entity name' => codepoint where entity name is given
-  # without the surrounding ampersand and semicolon.
-  #
-  MAP = {
-    'quot'      => 34,        'apos'      => 39,        'amp'       => 38,
-    'lt'        => 60,        'gt'        => 62,        'nbsp'      => 160,
-    'iexcl'     => 161,       'curren'    => 164,       'cent'      => 162,
-    'pound'     => 163,       'yen'       => 165,       'brvbar'    => 166,
-    'sect'      => 167,       'uml'       => 168,       'copy'      => 169,
-    'ordf'      => 170,       'laquo'     => 171,       'not'       => 172,
-    'shy'       => 173,       'reg'       => 174,       'trade'     => 8482,
-    'macr'      => 175,       'deg'       => 176,       'plusmn'    => 177,
-    'sup2'      => 178,       'sup3'      => 179,       'acute'     => 180,
-    'micro'     => 181,       'para'      => 182,       'middot'    => 183,
-    'cedil'     => 184,       'sup1'      => 185,       'ordm'      => 186,
-    'raquo'     => 187,       'frac14'    => 188,       'frac12'    => 189,
-    'frac34'    => 190,       'iquest'    => 191,       'times'     => 215,
-    'divide'    => 247,       'Agrave'    => 192,       'Aacute'    => 193,
-    'Acirc'     => 194,       'Atilde'    => 195,       'Auml'      => 196,
-    'Aring'     => 197,       'AElig'     => 198,       'Ccedil'    => 199,
-    'Egrave'    => 200,       'Eacute'    => 201,       'Ecirc'     => 202,
-    'Euml'      => 203,       'Igrave'    => 204,       'Iacute'    => 205,
-    'Icirc'     => 206,       'Iuml'      => 207,       'ETH'       => 208,
-    'Ntilde'    => 209,       'Ograve'    => 210,       'Oacute'    => 211,
-    'Ocirc'     => 212,       'Otilde'    => 213,       'Ouml'      => 214,
-    'Oslash'    => 216,       'Ugrave'    => 217,       'Uacute'    => 218,
-    'Ucirc'     => 219,       'Uuml'      => 220,       'Yacute'    => 221,
-    'THORN'     => 222,       'szlig'     => 223,       'agrave'    => 224,
-    'aacute'    => 225,       'acirc'     => 226,       'atilde'    => 227,
-    'auml'      => 228,       'aring'     => 229,       'aelig'     => 230,
-    'ccedil'    => 231,       'egrave'    => 232,       'eacute'    => 233,
-    'ecirc'     => 234,       'euml'      => 235,       'igrave'    => 236,
-    'iacute'    => 237,       'icirc'     => 238,       'iuml'      => 239,
-    'eth'       => 240,       'ntilde'    => 241,       'ograve'    => 242,
-    'oacute'    => 243,       'ocirc'     => 244,       'otilde'    => 245,
-    'ouml'      => 246,       'oslash'    => 248,       'ugrave'    => 249,
-    'uacute'    => 250,       'ucirc'     => 251,       'uuml'      => 252,
-    'yacute'    => 253,       'thorn'     => 254,       'yuml'      => 255,
-    'OElig'     => 338,       'oelig'     => 339,       'Scaron'    => 352,
-    'scaron'    => 353,       'Yuml'      => 376,       'circ'      => 710,
-    'tilde'     => 732,       'ensp'      => 8194,      'emsp'      => 8195,
-    'thinsp'    => 8201,      'zwnj'      => 8204,      'zwj'       => 8205,
-    'lrm'       => 8206,      'rlm'       => 8207,      'ndash'     => 8211,
-    'mdash'     => 8212,      'lsquo'     => 8216,      'rsquo'     => 8217,
-    'sbquo'     => 8218,      'ldquo'     => 8220,      'rdquo'     => 8221,
-    'bdquo'     => 8222,      'dagger'    => 8224,      'Dagger'    => 8225,
-    'hellip'    => 8230,      'permil'    => 8240,      'lsaquo'    => 8249,
-    'rsaquo'    => 8250,      'euro'      => 8364 
-  }
+  module Data #:nodoc:
 
-  MIN_LENGTH = MAP.keys.map{ |a| a.length }.min
-  MAX_LENGTH = MAP.keys.map{ |a| a.length }.max
-  
-  # Precompile the regexp
-  NAMED_ENTITY_REGEXP = 
-    /&([a-z]{#{HTMLEntities::MIN_LENGTH},#{HTMLEntities::MAX_LENGTH}});/i
+    #
+    # MAP is a hash of all the HTML entities I could discover, as taken
+    # from the w3schools page on the subject:
+    # http://www.w3schools.com/html/html_entitiesref.asp
+    # The format is 'entity name' => codepoint where entity name is given
+    # without the surrounding ampersand and semicolon.
+    #
+    MAP = {
+      'quot'      => 34,        'apos'      => 39,        'amp'       => 38,
+      'lt'        => 60,        'gt'        => 62,        'nbsp'      => 160,
+      'iexcl'     => 161,       'curren'    => 164,       'cent'      => 162,
+      'pound'     => 163,       'yen'       => 165,       'brvbar'    => 166,
+      'sect'      => 167,       'uml'       => 168,       'copy'      => 169,
+      'ordf'      => 170,       'laquo'     => 171,       'not'       => 172,
+      'shy'       => 173,       'reg'       => 174,       'trade'     => 8482,
+      'macr'      => 175,       'deg'       => 176,       'plusmn'    => 177,
+      'sup2'      => 178,       'sup3'      => 179,       'acute'     => 180,
+      'micro'     => 181,       'para'      => 182,       'middot'    => 183,
+      'cedil'     => 184,       'sup1'      => 185,       'ordm'      => 186,
+      'raquo'     => 187,       'frac14'    => 188,       'frac12'    => 189,
+      'frac34'    => 190,       'iquest'    => 191,       'times'     => 215,
+      'divide'    => 247,       'Agrave'    => 192,       'Aacute'    => 193,
+      'Acirc'     => 194,       'Atilde'    => 195,       'Auml'      => 196,
+      'Aring'     => 197,       'AElig'     => 198,       'Ccedil'    => 199,
+      'Egrave'    => 200,       'Eacute'    => 201,       'Ecirc'     => 202,
+      'Euml'      => 203,       'Igrave'    => 204,       'Iacute'    => 205,
+      'Icirc'     => 206,       'Iuml'      => 207,       'ETH'       => 208,
+      'Ntilde'    => 209,       'Ograve'    => 210,       'Oacute'    => 211,
+      'Ocirc'     => 212,       'Otilde'    => 213,       'Ouml'      => 214,
+      'Oslash'    => 216,       'Ugrave'    => 217,       'Uacute'    => 218,
+      'Ucirc'     => 219,       'Uuml'      => 220,       'Yacute'    => 221,
+      'THORN'     => 222,       'szlig'     => 223,       'agrave'    => 224,
+      'aacute'    => 225,       'acirc'     => 226,       'atilde'    => 227,
+      'auml'      => 228,       'aring'     => 229,       'aelig'     => 230,
+      'ccedil'    => 231,       'egrave'    => 232,       'eacute'    => 233,
+      'ecirc'     => 234,       'euml'      => 235,       'igrave'    => 236,
+      'iacute'    => 237,       'icirc'     => 238,       'iuml'      => 239,
+      'eth'       => 240,       'ntilde'    => 241,       'ograve'    => 242,
+      'oacute'    => 243,       'ocirc'     => 244,       'otilde'    => 245,
+      'ouml'      => 246,       'oslash'    => 248,       'ugrave'    => 249,
+      'uacute'    => 250,       'ucirc'     => 251,       'uuml'      => 252,
+      'yacute'    => 253,       'thorn'     => 254,       'yuml'      => 255,
+      'OElig'     => 338,       'oelig'     => 339,       'Scaron'    => 352,
+      'scaron'    => 353,       'Yuml'      => 376,       'circ'      => 710,
+      'tilde'     => 732,       'ensp'      => 8194,      'emsp'      => 8195,
+      'thinsp'    => 8201,      'zwnj'      => 8204,      'zwj'       => 8205,
+      'lrm'       => 8206,      'rlm'       => 8207,      'ndash'     => 8211,
+      'mdash'     => 8212,      'lsquo'     => 8216,      'rsquo'     => 8217,
+      'sbquo'     => 8218,      'ldquo'     => 8220,      'rdquo'     => 8221,
+      'bdquo'     => 8222,      'dagger'    => 8224,      'Dagger'    => 8225,
+      'hellip'    => 8230,      'permil'    => 8240,      'lsaquo'    => 8249,
+      'rsaquo'    => 8250,      'euro'      => 8364 
+    }
 
-  # Reverse map for converting characters to named entities
-  REVERSE_MAP = MAP.invert
+    MIN_LENGTH = MAP.keys.map{ |a| a.length }.min
+    MAX_LENGTH = MAP.keys.map{ |a| a.length }.max
+    NAMED_ENTITY_REGEXP = /&([a-z]{#{MIN_LENGTH},#{MAX_LENGTH}});/i
+    REVERSE_MAP = MAP.invert
 
-  BASIC_ENTITY_REGEXP = /[<>'"&]/
+    BASIC_ENTITY_REGEXP = /[<>'"&]/
 
-  UTF8_NON_ASCII_REGEXP = /[\x00-\x1f]|[\xc0-\xfd][\x80-\xbf]+/
+    UTF8_NON_ASCII_REGEXP = /[\x00-\x1f]|[\xc0-\xfd][\x80-\xbf]+/
 
-  ENCODE_ENTITIES_COMMAND_ORDER = { 
-    :basic => 0,
-    :named => 1,
-    :decimal => 2,
-    :hexadecimal => 3
-  }
+    ENCODE_ENTITIES_COMMAND_ORDER = { 
+      :basic => 0,
+      :named => 1,
+      :decimal => 2,
+      :hexadecimal => 3
+    }
+  
+  end
   
   #
   # Decode XML and HTML 4.01 entities in a string into their UTF-8
@@ -91,8 +90,8 @@ module HTMLEntities # :nodoc:
   # Unknown named entities are not converted
   #
   def decode_entities(string)
-    return string.gsub(NAMED_ENTITY_REGEXP) { 
-      (cp = MAP[$1]) ? [cp].pack('U') : $& 
+    return string.gsub(Data::NAMED_ENTITY_REGEXP) { 
+      (cp = Data::MAP[$1]) ? [cp].pack('U') : $& 
     }.gsub(/&#([0-9]{1,7});|&#x([0-9a-f]{1,6});/i) { 
       $1 ? [$1.to_i].pack('U') : [$2.to_i(16)].pack('U') 
     }
@@ -129,7 +128,7 @@ module HTMLEntities # :nodoc:
       instructions = [:basic] 
     else
       instructions = instructions.sort_by { |instruction| 
-        ENCODE_ENTITIES_COMMAND_ORDER[instruction] || 
+        Data::ENCODE_ENTITIES_COMMAND_ORDER[instruction] || 
         (raise InstructionError, "unknown encode_entities command `#{instruction.inspect}'")
       }
     end
@@ -137,23 +136,23 @@ module HTMLEntities # :nodoc:
       case instruction
       when :basic
         # Handled as basic ASCII
-        output = (output || string).gsub(BASIC_ENTITY_REGEXP) {
+        output = (output || string).gsub(Data::BASIC_ENTITY_REGEXP) {
           # It's safe to use the simpler [0] here because we know
           # that the basic entities are ASCII.
-          '&' << REVERSE_MAP[$&[0]] << ';'
+          '&' << Data::REVERSE_MAP[$&[0]] << ';'
         }
       when :named
         # Test everything except printable ASCII 
-        output = (output || string).gsub(UTF8_NON_ASCII_REGEXP) {
+        output = (output || string).gsub(Data::UTF8_NON_ASCII_REGEXP) {
           cp = $&.unpack('U')[0]
-          (e = REVERSE_MAP[cp]) ?  "&#{e};" : $&
+          (e = Data::REVERSE_MAP[cp]) ?  "&#{e};" : $&
         }
       when :decimal
-        output = (output || string).gsub(UTF8_NON_ASCII_REGEXP) {
+        output = (output || string).gsub(Data::UTF8_NON_ASCII_REGEXP) {
           "&##{$&.unpack('U')[0]};"
         }
       when :hexadecimal
-        output = (output || string).gsub(UTF8_NON_ASCII_REGEXP) {
+        output = (output || string).gsub(Data::UTF8_NON_ASCII_REGEXP) {
           "&#x#{$&.unpack('U')[0].to_s(16)};"
         }
       end 

data/lib/htmlentities/string.rb

@@ -1,15 +1,24 @@
 require 'htmlentities'
 
 #
-# This library extends the String class with methods to allow encoding and decoding of
+# This file extends the String class with methods to allow encoding and decoding of
 # HTML/XML entities from/to their corresponding UTF-8 codepoints.
 #
 class String
 
+  #
+  # Decode XML and HTML 4.01 entities in a string into their UTF-8
+  # equivalents.
+  #
   def decode_entities
     return HTMLEntities.decode_entities(self)
   end
   
+  #
+  # Encode codepoints in a string into their corresponding entities. See
+  # the documentation of HTMLEntities.encode_entities for a list of possible
+  # instructions.
+  #
   def encode_entities(*instructions)
     return HTMLEntities.encode_entities(self, *instructions)
   end

metadata

@@ -3,8 +3,8 @@ rubygems_version: 0.8.11
 specification_version: 1
 name: htmlentities
 version: !ruby/object:Gem::Version 
-  version: 3.0.0
-date: 2006-04-08 00:00:00 +01:00
+  version: 3.0.1
+date: 2006-04-09 00:00:00 +01:00
 summary: A module for encoding and decoding of HTML/XML entities from/to their corresponding UTF-8 codepoints. Optional String class extension for same.
 require_paths: 
 - lib