kindle-feeds 1.0.0

data/History.txt

@@ -0,0 +1,6 @@
+=== 1.0.0 / 2008-08-22
+
+* 1 major enhancement
+
+  * Initial release.
+

data/Manifest.txt

@@ -0,0 +1,14 @@
+History.txt
+Manifest.txt
+README.txt
+Rakefile
+bin/kindle-feeds
+lib/kindle-feeds.rb
+lib/htmlentities.rb
+lib/htmlentities/html4.rb
+lib/htmlentities/legacy.rb
+lib/htmlentities/string.rb
+lib/htmlentities/xhtml1.rb
+lib/kindle-feeds.erb.html
+
+

data/README.txt

@@ -0,0 +1,48 @@
+= kindle-feeds
+
+* FIX (url)
+
+== DESCRIPTION:
+
+FIX (describe your package)
+
+== FEATURES/PROBLEMS:
+
+* FIX (list of features or problems)
+
+== SYNOPSIS:
+
+  FIX (code sample of usage)
+
+== REQUIREMENTS:
+
+* FIX (list of requirements)
+
+== INSTALL:
+
+* FIX (sudo gem install, anything else)
+
+== LICENSE:
+
+(The MIT License)
+
+Copyright (c) 2008 FIX
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+'Software'), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED 'AS IS', WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
+CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
+TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
+SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/Rakefile

@@ -0,0 +1,21 @@
+# -*- ruby -*-
+
+require 'rubygems'
+require 'hoe'
+$: << 'lib/'
+require './lib/kindle-feeds.rb'
+require './lib/htmlentities.rb'
+
+Hoe.new('kindle-feeds', KindleFeeds::VERSION) do |p|
+  # p.rubyforge_name = 'kindle-feedsx' # if different than lowercase project name
+  p.author = 'Daniel Choi'
+  p.email = 'dhchoi@gmail.com'
+  p.description = "Format Atom and RSS feeds for the Kindle."
+  p.summary = "Format Atom and RSS feeds for the Kindle."
+  p.url = "http://danielchoi.com/software/kindle-feeds.html"
+  p.extra_deps << ['feed-normalizer', '>= 1.5.1'] 
+  p.extra_deps << ['hpricot', '>= 0.6'] 
+  p.post_install_message = 'Type kindle-feeds -h for instructions.'
+end
+
+# vim: syntax=Ruby

data/bin/kindle-feeds

@@ -0,0 +1,4 @@
+#!/usr/bin/env ruby
+require 'kindle-feeds'
+KindleFeeds.run ARGV
+

data/lib/htmlentities/html4.rb

@@ -0,0 +1,257 @@
+class HTMLEntities
+  MAPPINGS = {} unless defined? MAPPINGS
+  MAPPINGS['html4'] = {
+    'Aacute' => 193,
+    'aacute' => 225,
+    'Acirc' => 194,
+    'acirc' => 226,
+    'acute' => 180,
+    'AElig' => 198,
+    'aelig' => 230,
+    'Agrave' => 192,
+    'agrave' => 224,
+    'alefsym' => 8501,
+    'Alpha' => 913,
+    'alpha' => 945,
+    'amp' => 38,
+    'and' => 8743,
+    'ang' => 8736,
+    'Aring' => 197,
+    'aring' => 229,
+    'asymp' => 8776,
+    'Atilde' => 195,
+    'atilde' => 227,
+    'Auml' => 196,
+    'auml' => 228,
+    'bdquo' => 8222,
+    'Beta' => 914,
+    'beta' => 946,
+    'brvbar' => 166,
+    'bull' => 8226,
+    'cap' => 8745,
+    'Ccedil' => 199,
+    'ccedil' => 231,
+    'cedil' => 184,
+    'cent' => 162,
+    'Chi' => 935,
+    'chi' => 967,
+    'circ' => 710,
+    'clubs' => 9827,
+    'cong' => 8773,
+    'copy' => 169,
+    'crarr' => 8629,
+    'cup' => 8746,
+    'curren' => 164,
+    'Dagger' => 8225,
+    'dagger' => 8224,
+    'dArr' => 8659,
+    'darr' => 8595,
+    'deg' => 176,
+    'Delta' => 916,
+    'delta' => 948,
+    'diams' => 9830,
+    'divide' => 247,
+    'Eacute' => 201,
+    'eacute' => 233,
+    'Ecirc' => 202,
+    'ecirc' => 234,
+    'Egrave' => 200,
+    'egrave' => 232,
+    'empty' => 8709,
+    'emsp' => 8195,
+    'ensp' => 8194,
+    'Epsilon' => 917,
+    'epsilon' => 949,
+    'equiv' => 8801,
+    'Eta' => 919,
+    'eta' => 951,
+    'ETH' => 208,
+    'eth' => 240,
+    'Euml' => 203,
+    'euml' => 235,
+    'euro' => 8364,
+    'exist' => 8707,
+    'fnof' => 402,
+    'forall' => 8704,
+    'frac12' => 189,
+    'frac14' => 188,
+    'frac34' => 190,
+    'frasl' => 8260,
+    'Gamma' => 915,
+    'gamma' => 947,
+    'ge' => 8805,
+    'gt' => 62,
+    'hArr' => 8660,
+    'harr' => 8596,
+    'hearts' => 9829,
+    'hellip' => 8230,
+    'Iacute' => 205,
+    'iacute' => 237,
+    'Icirc' => 206,
+    'icirc' => 238,
+    'iexcl' => 161,
+    'Igrave' => 204,
+    'igrave' => 236,
+    'image' => 8465,
+    'infin' => 8734,
+    'int' => 8747,
+    'Iota' => 921,
+    'iota' => 953,
+    'iquest' => 191,
+    'isin' => 8712,
+    'Iuml' => 207,
+    'iuml' => 239,
+    'Kappa' => 922,
+    'kappa' => 954,
+    'Lambda' => 923,
+    'lambda' => 955,
+    'lang' => 9001,
+    'laquo' => 171,
+    'lArr' => 8656,
+    'larr' => 8592,
+    'lceil' => 8968,
+    'ldquo' => 8220,
+    'le' => 8804,
+    'lfloor' => 8970,
+    'lowast' => 8727,
+    'loz' => 9674,
+    'lrm' => 8206,
+    'lsaquo' => 8249,
+    'lsquo' => 8216,
+    'lt' => 60,
+    'macr' => 175,
+    'mdash' => 8212,
+    'micro' => 181,
+    'middot' => 183,
+    'minus' => 8722,
+    'Mu' => 924,
+    'mu' => 956,
+    'nabla' => 8711,
+    'nbsp' => 160,
+    'ndash' => 8211,
+    'ne' => 8800,
+    'ni' => 8715,
+    'not' => 172,
+    'notin' => 8713,
+    'nsub' => 8836,
+    'Ntilde' => 209,
+    'ntilde' => 241,
+    'Nu' => 925,
+    'nu' => 957,
+    'Oacute' => 211,
+    'oacute' => 243,
+    'Ocirc' => 212,
+    'ocirc' => 244,
+    'OElig' => 338,
+    'oelig' => 339,
+    'Ograve' => 210,
+    'ograve' => 242,
+    'oline' => 8254,
+    'Omega' => 937,
+    'omega' => 969,
+    'Omicron' => 927,
+    'omicron' => 959,
+    'oplus' => 8853,
+    'or' => 8744,
+    'ordf' => 170,
+    'ordm' => 186,
+    'Oslash' => 216,
+    'oslash' => 248,
+    'Otilde' => 213,
+    'otilde' => 245,
+    'otimes' => 8855,
+    'Ouml' => 214,
+    'ouml' => 246,
+    'para' => 182,
+    'part' => 8706,
+    'permil' => 8240,
+    'perp' => 8869,
+    'Phi' => 934,
+    'phi' => 966,
+    'Pi' => 928,
+    'pi' => 960,
+    'piv' => 982,
+    'plusmn' => 177,
+    'pound' => 163,
+    'Prime' => 8243,
+    'prime' => 8242,
+    'prod' => 8719,
+    'prop' => 8733,
+    'Psi' => 936,
+    'psi' => 968,
+    'quot' => 34,
+    'radic' => 8730,
+    'rang' => 9002,
+    'raquo' => 187,
+    'rArr' => 8658,
+    'rarr' => 8594,
+    'rceil' => 8969,
+    'rdquo' => 8221,
+    'real' => 8476,
+    'reg' => 174,
+    'rfloor' => 8971,
+    'Rho' => 929,
+    'rho' => 961,
+    'rlm' => 8207,
+    'rsaquo' => 8250,
+    'rsquo' => 8217,
+    'sbquo' => 8218,
+    'Scaron' => 352,
+    'scaron' => 353,
+    'sdot' => 8901,
+    'sect' => 167,
+    'shy' => 173,
+    'Sigma' => 931,
+    'sigma' => 963,
+    'sigmaf' => 962,
+    'sim' => 8764,
+    'spades' => 9824,
+    'sub' => 8834,
+    'sube' => 8838,
+    'sum' => 8721,
+    'sup' => 8835,
+    'sup1' => 185,
+    'sup2' => 178,
+    'sup3' => 179,
+    'supe' => 8839,
+    'szlig' => 223,
+    'Tau' => 932,
+    'tau' => 964,
+    'there4' => 8756,
+    'Theta' => 920,
+    'theta' => 952,
+    'thetasym' => 977,
+    'thinsp' => 8201,
+    'THORN' => 222,
+    'thorn' => 254,
+    'tilde' => 732,
+    'times' => 215,
+    'trade' => 8482,
+    'Uacute' => 218,
+    'uacute' => 250,
+    'uArr' => 8657,
+    'uarr' => 8593,
+    'Ucirc' => 219,
+    'ucirc' => 251,
+    'Ugrave' => 217,
+    'ugrave' => 249,
+    'uml' => 168,
+    'upsih' => 978,
+    'Upsilon' => 933,
+    'upsilon' => 965,
+    'Uuml' => 220,
+    'uuml' => 252,
+    'weierp' => 8472,
+    'Xi' => 926,
+    'xi' => 958,
+    'Yacute' => 221,
+    'yacute' => 253,
+    'yen' => 165,
+    'Yuml' => 376,
+    'yuml' => 255,
+    'Zeta' => 918,
+    'zeta' => 950,
+    'zwj' => 8205,
+    'zwnj' => 8204
+  }
+end

data/lib/htmlentities/legacy.rb

@@ -0,0 +1,27 @@
+class HTMLEntities
+  class << self
+    
+    #
+    # Legacy compatibility class method allowing direct encoding of XHTML1 entities.
+    # See HTMLEntities#encode for description of parameters.
+    #
+    def encode_entities(*args)
+      xhtml1_entities.encode(*args)
+    end
+    
+    #
+    # Legacy compatibility class method allowing direct decoding of XHTML1 entities.
+    # See HTMLEntities#decode for description of parameters.
+    #
+    def decode_entities(*args)
+      xhtml1_entities.decode(*args)
+    end
+    
+  private
+  
+    def xhtml1_entities
+      @xhtml1_entities ||= new('xhtml1')
+    end
+    
+  end
+end

data/lib/htmlentities/string.rb

@@ -0,0 +1,26 @@
+require 'htmlentities'
+
+#
+# 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
+
+end

data/lib/htmlentities/xhtml1.rb

@@ -0,0 +1,258 @@
+class HTMLEntities
+  MAPPINGS = {} unless defined? MAPPINGS
+  MAPPINGS['xhtml1'] = {
+    'Aacute' => 193,
+    'aacute' => 225,
+    'Acirc' => 194,
+    'acirc' => 226,
+    'acute' => 180,
+    'AElig' => 198,
+    'aelig' => 230,
+    'Agrave' => 192,
+    'agrave' => 224,
+    'alefsym' => 8501,
+    'Alpha' => 913,
+    'alpha' => 945,
+    'amp' => 38,
+    'and' => 8743,
+    'ang' => 8736,
+    'apos' => 39,
+    'Aring' => 197,
+    'aring' => 229,
+    'asymp' => 8776,
+    'Atilde' => 195,
+    'atilde' => 227,
+    'Auml' => 196,
+    'auml' => 228,
+    'bdquo' => 8222,
+    'Beta' => 914,
+    'beta' => 946,
+    'brvbar' => 166,
+    'bull' => 8226,
+    'cap' => 8745,
+    'Ccedil' => 199,
+    'ccedil' => 231,
+    'cedil' => 184,
+    'cent' => 162,
+    'Chi' => 935,
+    'chi' => 967,
+    'circ' => 710,
+    'clubs' => 9827,
+    'cong' => 8773,
+    'copy' => 169,
+    'crarr' => 8629,
+    'cup' => 8746,
+    'curren' => 164,
+    'Dagger' => 8225,
+    'dagger' => 8224,
+    'dArr' => 8659,
+    'darr' => 8595,
+    'deg' => 176,
+    'Delta' => 916,
+    'delta' => 948,
+    'diams' => 9830,
+    'divide' => 247,
+    'Eacute' => 201,
+    'eacute' => 233,
+    'Ecirc' => 202,
+    'ecirc' => 234,
+    'Egrave' => 200,
+    'egrave' => 232,
+    'empty' => 8709,
+    'emsp' => 8195,
+    'ensp' => 8194,
+    'Epsilon' => 917,
+    'epsilon' => 949,
+    'equiv' => 8801,
+    'Eta' => 919,
+    'eta' => 951,
+    'ETH' => 208,
+    'eth' => 240,
+    'Euml' => 203,
+    'euml' => 235,
+    'euro' => 8364,
+    'exist' => 8707,
+    'fnof' => 402,
+    'forall' => 8704,
+    'frac12' => 189,
+    'frac14' => 188,
+    'frac34' => 190,
+    'frasl' => 8260,
+    'Gamma' => 915,
+    'gamma' => 947,
+    'ge' => 8805,
+    'gt' => 62,
+    'hArr' => 8660,
+    'harr' => 8596,
+    'hearts' => 9829,
+    'hellip' => 8230,
+    'Iacute' => 205,
+    'iacute' => 237,
+    'Icirc' => 206,
+    'icirc' => 238,
+    'iexcl' => 161,
+    'Igrave' => 204,
+    'igrave' => 236,
+    'image' => 8465,
+    'infin' => 8734,
+    'int' => 8747,
+    'Iota' => 921,
+    'iota' => 953,
+    'iquest' => 191,
+    'isin' => 8712,
+    'Iuml' => 207,
+    'iuml' => 239,
+    'Kappa' => 922,
+    'kappa' => 954,
+    'Lambda' => 923,
+    'lambda' => 955,
+    'lang' => 9001,
+    'laquo' => 171,
+    'lArr' => 8656,
+    'larr' => 8592,
+    'lceil' => 8968,
+    'ldquo' => 8220,
+    'le' => 8804,
+    'lfloor' => 8970,
+    'lowast' => 8727,
+    'loz' => 9674,
+    'lrm' => 8206,
+    'lsaquo' => 8249,
+    'lsquo' => 8216,
+    'lt' => 60,
+    'macr' => 175,
+    'mdash' => 8212,
+    'micro' => 181,
+    'middot' => 183,
+    'minus' => 8722,
+    'Mu' => 924,
+    'mu' => 956,
+    'nabla' => 8711,
+    'nbsp' => 160,
+    'ndash' => 8211,
+    'ne' => 8800,
+    'ni' => 8715,
+    'not' => 172,
+    'notin' => 8713,
+    'nsub' => 8836,
+    'Ntilde' => 209,
+    'ntilde' => 241,
+    'Nu' => 925,
+    'nu' => 957,
+    'Oacute' => 211,
+    'oacute' => 243,
+    'Ocirc' => 212,
+    'ocirc' => 244,
+    'OElig' => 338,
+    'oelig' => 339,
+    'Ograve' => 210,
+    'ograve' => 242,
+    'oline' => 8254,
+    'Omega' => 937,
+    'omega' => 969,
+    'Omicron' => 927,
+    'omicron' => 959,
+    'oplus' => 8853,
+    'or' => 8744,
+    'ordf' => 170,
+    'ordm' => 186,
+    'Oslash' => 216,
+    'oslash' => 248,
+    'Otilde' => 213,
+    'otilde' => 245,
+    'otimes' => 8855,
+    'Ouml' => 214,
+    'ouml' => 246,
+    'para' => 182,
+    'part' => 8706,
+    'permil' => 8240,
+    'perp' => 8869,
+    'Phi' => 934,
+    'phi' => 966,
+    'Pi' => 928,
+    'pi' => 960,
+    'piv' => 982,
+    'plusmn' => 177,
+    'pound' => 163,
+    'Prime' => 8243,
+    'prime' => 8242,
+    'prod' => 8719,
+    'prop' => 8733,
+    'Psi' => 936,
+    'psi' => 968,
+    'quot' => 34,
+    'radic' => 8730,
+    'rang' => 9002,
+    'raquo' => 187,
+    'rArr' => 8658,
+    'rarr' => 8594,
+    'rceil' => 8969,
+    'rdquo' => 8221,
+    'real' => 8476,
+    'reg' => 174,
+    'rfloor' => 8971,
+    'Rho' => 929,
+    'rho' => 961,
+    'rlm' => 8207,
+    'rsaquo' => 8250,
+    'rsquo' => 8217,
+    'sbquo' => 8218,
+    'Scaron' => 352,
+    'scaron' => 353,
+    'sdot' => 8901,
+    'sect' => 167,
+    'shy' => 173,
+    'Sigma' => 931,
+    'sigma' => 963,
+    'sigmaf' => 962,
+    'sim' => 8764,
+    'spades' => 9824,
+    'sub' => 8834,
+    'sube' => 8838,
+    'sum' => 8721,
+    'sup' => 8835,
+    'sup1' => 185,
+    'sup2' => 178,
+    'sup3' => 179,
+    'supe' => 8839,
+    'szlig' => 223,
+    'Tau' => 932,
+    'tau' => 964,
+    'there4' => 8756,
+    'Theta' => 920,
+    'theta' => 952,
+    'thetasym' => 977,
+    'thinsp' => 8201,
+    'THORN' => 222,
+    'thorn' => 254,
+    'tilde' => 732,
+    'times' => 215,
+    'trade' => 8482,
+    'Uacute' => 218,
+    'uacute' => 250,
+    'uArr' => 8657,
+    'uarr' => 8593,
+    'Ucirc' => 219,
+    'ucirc' => 251,
+    'Ugrave' => 217,
+    'ugrave' => 249,
+    'uml' => 168,
+    'upsih' => 978,
+    'Upsilon' => 933,
+    'upsilon' => 965,
+    'Uuml' => 220,
+    'uuml' => 252,
+    'weierp' => 8472,
+    'Xi' => 926,
+    'xi' => 958,
+    'Yacute' => 221,
+    'yacute' => 253,
+    'yen' => 165,
+    'Yuml' => 376,
+    'yuml' => 255,
+    'Zeta' => 918,
+    'zeta' => 950,
+    'zwj' => 8205,
+    'zwnj' => 8204
+  }
+end

data/lib/htmlentities.rb

@@ -0,0 +1,165 @@
+require 'htmlentities/legacy'
+
+#
+# HTML entity encoding and decoding for Ruby
+#
+
+class HTMLEntities
+
+  VERSION = '4.0.0'
+  FLAVORS = %w[html4 xhtml1]
+  INSTRUCTIONS = [:basic, :named, :decimal, :hexadecimal]
+
+  class InstructionError < RuntimeError
+  end
+  class UnknownFlavor < RuntimeError
+  end
+
+  #
+  # Create a new HTMLEntities coder for the specified flavor.
+  # Available flavors are 'html4' and 'xhtml1' (the default).
+  # The only difference in functionality between the two is in the handling of the apos
+  # (apostrophe) named entity, which is not defined in HTML4.
+  #
+  def initialize(flavor='xhtml1')
+    @flavor = flavor.to_s.downcase
+    raise UnknownFlavor, "Unknown flavor #{flavor}" unless FLAVORS.include?(@flavor)
+  end
+
+  #
+  # Decode entities in a string into their UTF-8
+  # equivalents.  Obviously, if your string is not already in UTF-8, you'd
+  # better convert it before using this method, or the output will be mixed
+  # up.
+  #
+  # Unknown named entities will not be converted
+  #
+  def decode(source)
+    return source.to_s.gsub(named_entity_regexp) {
+      (cp = 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')
+    }
+  end
+
+  #
+  # Encode codepoints into their corresponding entities.  Various operations
+  # are possible, and may be specified in order:
+  #
+  # :basic :: Convert the five XML entities ('"<>&)
+  # :named :: Convert non-ASCII characters to their named HTML 4.01 equivalent
+  # :decimal :: Convert non-ASCII characters to decimal entities (e.g. &#1234;)
+  # :hexadecimal :: Convert non-ASCII characters to hexadecimal entities (e.g. # &#x12ab;)
+  #
+  # You can specify the commands in any order, but they will be executed in
+  # the order listed above to ensure that entity ampersands are not
+  # clobbered and that named entities are replaced before numeric ones.
+  #
+  # If no instructions are specified, :basic will be used.
+  #
+  # Examples:
+  #   encode_entities(str) - XML-safe
+  #   encode_entities(str, :basic, :decimal) - XML-safe and 7-bit clean
+  #   encode_entities(str, :basic, :named, :decimal) - 7-bit clean, with all
+  #   non-ASCII characters replaced with their named entity where possible, and
+  #   decimal equivalents otherwise.
+  #
+  # Note: It is the program's responsibility to ensure that the source
+  # contains valid UTF-8 before calling this method.
+  #
+  def encode(source, *instructions)
+    string = source.to_s.dup
+    if (instructions.empty?)
+      instructions = [:basic]
+    elsif (unknown_instructions = instructions - INSTRUCTIONS) != []
+      raise InstructionError,
+      "unknown encode_entities command(s): #{unknown_instructions.inspect}"
+    end
+    
+    basic_entity_encoder =
+    if instructions.include?(:basic) || instructions.include?(:named)
+      :encode_named
+    elsif instructions.include?(:decimal)
+      :encode_decimal
+    else instructions.include?(:hexadecimal)
+      :encode_hexadecimal
+    end
+    string.gsub!(basic_entity_regexp){ __send__(basic_entity_encoder, $&) }
+    
+    extended_entity_encoders = []
+    if instructions.include?(:named)
+      extended_entity_encoders << :encode_named
+    end
+    if instructions.include?(:decimal)
+      extended_entity_encoders << :encode_decimal
+    elsif instructions.include?(:hexadecimal)
+      extended_entity_encoders << :encode_hexadecimal
+    end
+    unless extended_entity_encoders.empty?
+      string.gsub!(extended_entity_regexp){
+        encode_extended(extended_entity_encoders, $&)
+      }
+    end
+    
+    return string
+  end
+
+private
+
+  def map
+    @map ||= (require "htmlentities/#{@flavor}"; HTMLEntities::MAPPINGS[@flavor])
+  end
+
+  def basic_entity_regexp
+    @basic_entity_regexp ||= (
+      case @flavor
+      when /^html/
+        /[<>"&]/
+      else
+        /[<>'"&]/
+      end
+    )
+  end
+  
+  def extended_entity_regexp
+    @extended_entity_regexp ||= (
+      regexp = '[\x00-\x1f]|[\xc0-\xfd][\x80-\xbf]+'
+      regexp += "|'" if @flavor == 'html4'
+      Regexp.new(regexp)
+    )
+  end
+
+  def named_entity_regexp
+    @named_entity_regexp ||= (
+      min_length = map.keys.map{ |a| a.length }.min
+      max_length = map.keys.map{ |a| a.length }.max
+      /&([a-z][a-z0-9]{#{min_length-1},#{max_length-1}});/i
+    )
+  end
+
+  def reverse_map
+    @reverse_map ||= map.invert
+  end
+
+  def encode_named(char)
+    cp = char.unpack('U')[0]
+    (e = reverse_map[cp]) && "&#{e};"
+  end
+
+  def encode_decimal(char)
+    "&##{char.unpack('U')[0]};"
+  end
+
+  def encode_hexadecimal(char)
+    "&#x#{char.unpack('U')[0].to_s(16)};"
+  end
+  
+  def encode_extended(encoders, char)
+    encoders.each do |encoder|
+      encoded = __send__(encoder, char)
+      return encoded if encoded
+    end
+    return char
+  end
+
+end

data/lib/kindle-feeds.erb.html

@@ -0,0 +1,76 @@
+<html>
+<head>
+<title>kindle feeds</title>
+<meta http-equiv="content-type" content="text/html; charset=ISO-8859-1"/>
+</head>
+<body>
+  <a name="start"></a>
+
+  <h1>Kindle Feeds</h1>
+  <p>copyright 2008 Daniel Choi</p>
+  <p>contact: dhchoi@gmail.com</p>
+  <p>open source license: <a href="http://www.opensource.org/licenses/mit-license.php">MIT License</a></p>
+  <p>homepage: <a href="http://danielchoi.com/software/kindle-feeds.html">http://danielchoi.com/software/kindle-feeds.html</a></p>
+  <br/>
+  <br/>
+
+  <a name="toc"></a>
+  <h2>Table of Contents</h2>
+  <ul>
+    <% @sections.each_with_index do |x, i| %>
+    <li><a href="#section-<%= i %>"><%= x.title %></li>
+    <% end %>
+  </ul>
+<% @sections.each_with_index do |s, i| %>
+
+  <br/>
+  <br/>
+  <div class="section details">
+    <a name="section-<%= i %>" ></a>
+    <div style="text-align:right">
+      <ul style="list-style-type:none">
+        <li><a href="#toc">table of contents</a></li>
+      </ul>
+    </div>
+    <h2>Section: <%= s.title %></h2>
+    <p>Feeds in this section:<p>
+    <ol>
+      <% s.feeds.each_with_index do |f, m| %>
+      <li><a href="#section-<%= i %>-feed-<%= m %>"><%= f.title %></li>
+      <% end %>
+    </ol>
+    <% s.feeds.each_with_index do |f, j| %>
+      <a name="section-<%= i%>-feed-<%= j %>"></a>
+      <h2>Feed: <a href="<%= f.url %>"><%= f.title %></a></h2>
+      <p><%= f.entries.size %> Entries:</p>
+      <ol>
+        <% f.entries.each_with_index do |e, n| %>
+        <li><a href="#section-<%= i %>-feed-<%= j %>-entry-<%= n %>"><%= e.title %></li>
+        <% end %>
+      </ol>
+
+      <% f.entries.each_with_index do |e, n| %>
+        <a name="section-<%= i %>-feed-<%= j %>-entry-<%= n %>"></a>
+        <h3>(<%= n + 1 %>/<%= f.entries.size %>) <a href="<%= e.url %>"><%= e.title %></a></h3>
+        <div style="text-align:right"><i><%= e.date_published ? e.date_published.strftime('%B %d, %Y') : nil %></i></div>
+        <div>
+          <%= e.content %>
+        </div>
+        <div style="text-align:right">
+          <ul style="list-style-type:none">
+            <li><a href="#toc">table of contents</a></li>
+            <li><a href="#section-<%= i%>"><%= s.title %></a></li>
+            <li><a href="#section-<%= i%>-feed-<%= j %>"><%= f.title %></a></li> 
+          </ul>
+        </div>
+        <br/>
+        <br/>
+      <% end %>
+    <% end %>
+  </div>
+
+<% end %>
+</body>
+</html>
+
+

data/lib/kindle-feeds.rb

@@ -0,0 +1,267 @@
+# kindle-feeds
+
+# copyright 2008 Daniel Choi
+# dhchoi@gmail.com
+# License: MIT
+
+require 'rubygems'
+require 'optparse'
+require 'open-uri'
+require 'feed-normalizer'
+require 'htmlentities'
+require 'iconv'
+require 'erb'
+require 'hpricot'
+CONFIGFILE = "kindle_feeds.conf"
+ERB_TEMPLATE = File.dirname(__FILE__) + "/kindle-feeds.erb.html"
+DEFAULT_FEEDS = <<END
+# kindle-feeds feed list
+#
+# Please edit this file so that it contains the section titles and feed URLs
+# that you want. Follow the format of the example: section titles immediately
+# followed by a list of URLs. The URLs should either be URLs of RSS or Atom
+# feeds or URLs of web pages that contain links to a RSS or Atom feed. The
+# 'http://' at the beginning of the URL is optional. Sections should be separated
+# by exactly one blank line.
+
+General News
+nytimes.com
+slate.com
+
+Tech News
+techcrunch.com
+http://readwriteweb.com
+slashdot.org
+
+Apple
+macworld.com
+macintouch.com
+
+Ebook 
+teleread.org/blog
+END
+
+class Autodiscovery
+  def initialize(page_html)
+    # Downcase the html because capitalized stuff might mess up the Hpricot matching
+    @doc = Hpricot(page_html)
+  end
+
+  # Returns the url of the feed, or nil if none found
+  def discover
+    # Look for rss link, e.g.
+    # <link rel="alternate" type="application/rss+xml" title="RSS"
+    #       href="http://feeds.feedburner.com/TheRssBlog">
+    # Tricky: Hpricot CSS attribute selectors are written like XPath selectors
+    [:rss, :atom].each do |flavor|
+      if x=@doc.at("head link[@type=application/#{flavor}+xml]")
+        return x[:href]
+      end
+    end
+    if x=@doc.at("head link[@type=text/xml]")
+      return x[:href]
+    end
+    return nil
+  end
+end
+
+class Feed
+  def self.create_feed(xml, feed_url)
+    feed = FeedNormalizer::FeedNormalizer.parse(xml)
+    return nil unless feed.is_a?(FeedNormalizer::Feed)
+    # clean up entries:
+    ic = Iconv.new('ISO-8859-1//TRANSLIT', 'utf-8') 
+    ic2 = Iconv.new('ISO-8859-1//IGNORE', 'utf-8') 
+    #ic = Iconv.new('ASCII//TRANSLIT', 'utf-8') 
+    coder = HTMLEntities.new
+    puts "#{feed.entries.size} entries downloaded."
+    puts
+    feed.entries.each do |e|
+      e.title = coder.decode(e.title)
+      e.content = coder.decode(e.content)
+
+      begin
+        e.title = ic.iconv(e.title) 
+      rescue
+        e.title = ic2.iconv(e.title) 
+      end
+      begin
+        e.content = ic.iconv(e.content) 
+      rescue
+        e.content = ic2.iconv(e.content) 
+      end
+      doc = Hpricot(e.content)
+      doc.search('h1, h2, h3') do |h|
+        h.swap("<h4>#{h.inner_text}</h4>")
+      end
+      doc.search('//font') do |font|
+        font.swap(font.inner_text)
+      end
+      doc.search('//img').remove
+      doc.search('svg, object, embed').remove
+      doc.search('script').remove
+      e.content = doc.to_s
+    end
+    return feed
+  end
+
+  def self.subscribe(feed_url) # try to repair the URL if possible
+    unless feed_url =~ /^http:\/\//
+      feed_url = "http://" + feed_url
+    end
+    puts "Downloading #{feed_url}"
+    begin
+      xml = fetch(feed_url)
+    rescue SocketError
+      puts "Error trying to load page at #{feed_url}"
+      return
+    end
+    if xml.nil?
+      puts "Can't find any resource at #{feed_url}"
+      return
+    end
+    feed = Feed.create_feed( xml, feed_url.strip )
+    if feed.nil?
+      puts "#{feed_url}: Attempting autodiscovery..."
+      feed_url = auto_discover_and_subscribe(feed_url)
+      if feed_url
+        xml = fetch(feed_url)
+        feed = Feed.create_feed( xml, feed_url.strip )
+      end
+    end
+    feed
+  end
+
+  def self.auto_discover_and_subscribe(url)
+    uri = URI.parse(url)
+    feed_url = Autodiscovery.new(fetch(url)).discover
+    if feed_url
+      feed_url = uri.merge(feed_url).to_s
+      puts "Found feed: #{feed_url}" 
+      return feed_url
+    else
+      puts "Can't find feed for #{url}" 
+      return nil
+    end
+  end
+
+  # a simple wrapper over open-uri call. Easier to mock in testing.
+  def self.fetch(url)
+    begin
+      open(url).read
+    rescue Timeout::Error 
+      puts "-> attempt to fetch #{url} timed out"
+    rescue Exception => e
+      puts "-> error trying to fetch #{url}: #{$!}"
+    end
+  end
+end
+
+class Section
+  attr_accessor :title, :uris, :feeds
+  def initialize(title, uris)
+    @feeds = []
+    @title = title
+    @uris = uris
+    # generate the feeds
+    @uris.each do |uri|
+      if (feed=Feed.subscribe(uri))
+        @feeds << feed
+      end
+    end
+  end
+end
+
+class KindleFeeds
+  VERSION = "1.0.0"
+  attr_accessor :sections
+  # config is a text file with a certain format
+  def initialize(config)
+    @sections = [] 
+    raw_sections = config.split(/^\s*$/)
+    results = []
+    raw_sections.each do |section|
+      lines = section.strip.split("\n")
+      title = lines.shift.strip 
+      urls = lines.map {|line| line.strip}
+      results << [title, *urls]
+    end
+    # an array of arrays. each array is composed of a section title followed by urls of the feeds
+    results
+    puts "Fetching feeds:"
+    results.each do |r|
+      puts "- " + r.first
+      r[1..-1].each do |x|
+        puts "  - " + x
+      end
+    end
+    puts
+    # subscribe
+    results.each do |r|
+      @sections << Section.new(r.shift, r)
+    end
+  end
+
+  def to_html
+    puts "Converting feeds into Kindle-compatible and optimized HTML..."
+    puts 
+    erb = ERB.new(File.read(ERB_TEMPLATE))
+    out = erb.result(binding())
+    # TODO put timestamp in filename
+    date = Time.now.strftime('%m-%H-%Y')
+    outfile = "Kindle Feeds #{date}.html"
+    File.open(outfile, "w") do |f|
+      f.write out
+    end
+    puts "Output written to file:"
+    puts outfile
+    puts
+    puts "Email this file as an attachment to YOUR_KINDLE_USERNAME@kindle.com or YOUR_KINDLE_USERNAME@free.kindle.com."
+    puts
+    puts "Visit http://www.amazon.com/gp/help/customer/display.html?nodeId=200140600 for more help."
+    puts "Done."
+  end
+
+  def self.run(argv=ARGV)
+    opts = OptionParser.new do |opt|
+      opt.program_name = File.basename $0
+      opt.version = KindleFeeds::VERSION
+      opt.banner = <<-EOT
+Usage: #{opt.program_name} 
+
+kindle-feeds reads a feed list from #{CONFIGFILE}.conf, downloads the feeds, and
+generates a Kindle-compatiable and optimized HTML file that can be sent to 
+YOUR_KINDLE_USERNAME@kindle.com or YOUR_KINDLE_USERNAME@free.kindle.com for conversion 
+into an .azw file for reading on the Kindle. 
+
+The first time kindle-feeds is run, it will generate a stub #{CONFIGFILE}.conf file
+in the same directory. Please edit this file to specify the feeds you want to
+download and convert for Kindle reading. Further instructions can be found at the
+top of kindle-feeds.conf once it is generated.
+
+Project homepage: 
+http://danielchoi.com/software/kindle-feeds.html
+      EOT
+    end
+    opts.parse! argv
+
+    if ! File.exist?(CONFIGFILE)
+      puts "Can't find #{CONFIGFILE}. Generating..."
+      File.open(CONFIGFILE, "w") do |f|
+        f.write DEFAULT_FEEDS
+      end
+      puts "Please edit #{CONFIGFILE} before running kindle-feeds again."
+      exit
+    end
+    puts "Reading #{CONFIGFILE} for feed URLs."
+    puts 
+    configfile = File.open(CONFIGFILE).readlines
+    configfile = configfile.select {|line| line !~ /^#/}.join
+    kf = KindleFeeds.new(configfile)
+    kf.to_html
+  end
+end
+
+if __FILE__ == $0
+  KindleFeeds.run ARGV
+end

metadata

@@ -0,0 +1,96 @@
+--- !ruby/object:Gem::Specification 
+name: kindle-feeds
+version: !ruby/object:Gem::Version 
+  version: 1.0.0
+platform: ruby
+authors: 
+- Daniel Choi
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2008-08-22 00:00:00 -04:00
+default_executable: 
+dependencies: 
+- !ruby/object:Gem::Dependency 
+  name: feed-normalizer
+  type: :runtime
+  version_requirement: 
+  version_requirements: !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: 1.5.1
+    version: 
+- !ruby/object:Gem::Dependency 
+  name: hpricot
+  type: :runtime
+  version_requirement: 
+  version_requirements: !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: "0.6"
+    version: 
+- !ruby/object:Gem::Dependency 
+  name: hoe
+  type: :development
+  version_requirement: 
+  version_requirements: !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: 1.7.0
+    version: 
+description: Format Atom and RSS feeds for the Kindle.
+email: dhchoi@gmail.com
+executables: 
+- kindle-feeds
+extensions: []
+
+extra_rdoc_files: 
+- History.txt
+- Manifest.txt
+- README.txt
+files: 
+- History.txt
+- Manifest.txt
+- README.txt
+- Rakefile
+- bin/kindle-feeds
+- lib/kindle-feeds.rb
+- lib/htmlentities.rb
+- lib/htmlentities/html4.rb
+- lib/htmlentities/legacy.rb
+- lib/htmlentities/string.rb
+- lib/htmlentities/xhtml1.rb
+- lib/kindle-feeds.erb.html
+has_rdoc: true
+homepage: http://danielchoi.com/software/kindle-feeds.html
+post_install_message: Type kindle-feeds -h for instructions.
+rdoc_options: 
+- --main
+- README.txt
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+  version: 
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+  version: 
+requirements: []
+
+rubyforge_project: kindle-feeds
+rubygems_version: 1.2.0
+signing_key: 
+specification_version: 2
+summary: Format Atom and RSS feeds for the Kindle.
+test_files: []
+