epub-parser 0.1.6 → 0.1.7

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 65f7f0d3749c5bf1d34ab527c94ac0905a3fa30f
-  data.tar.gz: d88e97de68e8b5d81c27d5921ce2fbe3ebd99e7f
+  metadata.gz: 02abe0846123f8f3d218581a102f69c2972a80e1
+  data.tar.gz: 510bddcca86f789add0ecc4193b424063a5d23d6
 SHA512:
-  metadata.gz: 1e2a88587ff96a480845cee7a99b624b4ee86d373ac659ace2f89b1cd597fed87156c9ffb487ee37b7a87f81a225f0f86b0f47c17d45c4150a70b594638afbdc
-  data.tar.gz: b7634902c0e838a66e4852c62d1356d8cfeb9b9ab84b371a8cba654057fd2c440f8b14e1a92e14311c42670c9557ac3f51e2638d118abdf330de9d750417d7a0
+  metadata.gz: 8c46c39e8031ab857e968dc3826e4ce0fb6d65588ef8d8e61f05672628feaaa58d25a829c1b39826cf1a04b458dcdcd2f0898578f92768bd9db866b4a5f1f6aa
+  data.tar.gz: feea20e63185013eea0c9d5bdd0b8c0e80a4e06646b8bd106095a9eb967a0c067113915ad70458d9332d3efab120875447c90032fa4f4dedf2465d72532f1d3e

data/.yardopts

@@ -8,3 +8,4 @@ docs/FixedLayout.markdown
 docs/Epubinfo.markdown
 docs/EpubOpen.markdown
 docs/Navigation.markdown
+docs/Searcher.markdown

data/CHANGELOG.markdown

@@ -1,5 +1,12 @@
 CHANGELOG
 =========
+
+0.1.7
+-----
+
+* [Experimental]Add `EPUB::Searcher` module. See {file:Searcher.markdown} for details
+* Detect and set character encoding in `EPUB::Publication::Package::Item#read`
+
 0.1.6
 -----
 * Remove `EPUB.parse` method

data/Gemfile

@@ -1,2 +1,2 @@
-source "https://rubygems.org"
+source 'https://rubygems.org'
 gemspec

data/README.markdown

@@ -93,6 +93,7 @@ See {file:docs/EpubOpen} for more info.
 REQUIREMENTS
 ------------
 * Ruby 1.9.3 or later
+* `patch` command to install Nokogiri
 * C compiler to compile Zip/Ruby and Nokogiri
 
 Related Gems
@@ -108,6 +109,12 @@ If you find other gems, please tell me or request a pull request.
 
 RECENT CHANGES
 --------------
+
+### 0.1.7
+
+* [Experimental]Add `EPUB::Searcher` module. See {file:Searcher.markdown} for details
+* Detect and set character encoding in `EPUB::Publication::Package::Item#read`
+
 ### 0.1.6
 * Remove `EPUB.parse` method
 * Remove `EPUB::Publication::Package::Metadata#to_hash`
@@ -134,14 +141,6 @@ RECENT CHANGES
 * Add `ContentDocument::XHTML#rexml` and `#nokogiri`
 * Inspect more readably
 
-### 0.1.4
-* [Fixed-Layout Documents][fixed-layout] support
-* Define `ContentDocument::XHTML#top_level?`
-* Define `Spine::Itemref#page_spread` and `#page_spread=`
-* Define some utility methods around `Manifest::Item` and `Spine::Itemref`
-
-[fixed-layout]: http://www.idpf.org/epub/fxl/
-
 See {file:CHANGELOG.markdown} for older changelogs and details.
 
 TODOS

data/docs/Searcher.markdown

@@ -0,0 +1,74 @@
+{file:docs/Home.markdown} > **{file:docs/Searcher.markdown}**
+
+Searcher
+========
+
+*Searcher is experimental now. Note that all interfaces are not stable at all.*
+
+Example
+-------
+
+    epub = EPUB::Parser.parse('childrens-literature-20130206.epub')
+    search_word = 'INTRODUCTORY'
+    results = EPUB::Searcher.search(epub.package, search_word)
+    # => [#<EPUB::Searcher::Result:0x007f74d2b31548
+    #   @end_steps=[#<EPUB::Searcher::Result::Step:0x007f74d2b7baa8 @index=12, @type=:character>],
+    #   @parent_steps=
+    #    [#<EPUB::Searcher::Result::Step:0x007f74d2b81318 @index=2, @name="spine", @type=:element>,
+    #     # #<EPUB::Searcher::Result::Step:0x007f74d2b7f4c8 @index=1, @type=:itemref>,
+    #     # #<EPUB::Searcher::Result::Step:0x007f74d2b7d560 @index=1, @name="body", @type=:element>,
+    #     # #<EPUB::Searcher::Result::Step:0x007f74d2b7d308 @index=0, @name="nav", @type=:element>,
+    #     # #<EPUB::Searcher::Result::Step:0x007f74d2b7cdb8 @index=1, @name="ol", @type=:element>,
+    #     # #<EPUB::Searcher::Result::Step:0x007f74d2b7cb38 @index=0, @name="li", @type=:element>,
+    #     # #<EPUB::Searcher::Result::Step:0x007f74d2b7c5e8 @index=1, @name="ol", @type=:element>,
+    #     # #<EPUB::Searcher::Result::Step:0x007f74d2b7bf80 @index=1, @name="li", @type=:element>,
+    #     # #<EPUB::Searcher::Result::Step:0x007f74d2b7bd28 @index=0, @name="a", @type=:element>,
+    #     # #<EPUB::Searcher::Result::Step:0x007f74d2b7bb70 @index=0, @type=:text>],
+    #   @start_steps=[#<EPUB::Searcher::Result::Step:0x007f74d2b7baf8 @index=0, @type=:character>]>,
+    #  #<EPUB::Searcher::Result:0x007f74d294e258
+    #   @end_steps=[#<EPUB::Searcher::Result::Step:0x007f74d2b0f8d0 @index=12, @type=:character>],
+    #   @parent_steps=
+    #    [#<EPUB::Searcher::Result::Step:0x007f74d2b81318 @index=2, @name="spine", @type=:element>,
+    #     # #<EPUB::Searcher::Result::Step:0x007f74d2b314f8 @index=2, @type=:itemref>,
+    #     # #<EPUB::Searcher::Result::Step:0x007f74d2b2fb80 @index=1, @name="body", @type=:element>,
+    #     # #<EPUB::Searcher::Result::Step:0x007f74d2b2f900 @index=0, @name="section", @type=:element>,
+    #     # #<EPUB::Searcher::Result::Step:0x007f74d2b10578 @index=3, @name="section", @type=:element>,
+    #     # #<EPUB::Searcher::Result::Step:0x007f74d2b0fb50 @index=1, @name="h3", @type=:element>,
+    #     # #<EPUB::Searcher::Result::Step:0x007f74d2b0f998 @index=0, @type=:text>],
+    #   @start_steps=[#<EPUB::Searcher::Result::Step:0x007f74d2b0f920 @index=0, @type=:character>]>]
+    puts results.collect(&:to_cfi_s)
+    # /6/4!/4/2/4/2/4/4/2/1,:0,:12
+    # /6/6!/4/2/8/4/1,:0,:12
+    # => nil
+
+Search result
+-------------
+
+Search result is an array of {EPUB::Searcher::Result} and it may be converted to an EPUBCFI string by {EPUB::Searcher::Result#to_cfi_s}.
+
+Restricted XHTML Searcher
+-------------------------
+
+Now searcher for XHTML documents is *restricted*, which means that it can search from only single elements. For instance, it can find 'search word' from XHTML document below:
+
+    <html>
+      <head>
+        <title>Sample document</title>
+      </head>
+      <body>
+        <p>search word</p>
+      </body>
+    </html>
+
+But cannot from document below:
+
+    <html>
+      <head>
+        <title>Sample document</title>
+      </head>
+      <body>
+        <p><em>search</em> word</p>
+      </body>
+    </html>
+
+because the words 'search' and 'word' are not in the same element.

data/epub-parser.gemspec

@@ -46,4 +46,5 @@ Gem::Specification.new do |s|
   s.add_runtime_dependency 'zipruby'
   s.add_runtime_dependency 'nokogiri', '~> 1.6'
   s.add_runtime_dependency 'addressable', '>= 2.3.5'
+  s.add_runtime_dependency 'rchardet'
 end

data/lib/epub/parser/version.rb

@@ -1,5 +1,5 @@
 module EPUB
   class Parser
-    VERSION = "0.1.6"
+    VERSION = "0.1.7"
   end
 end

data/lib/epub/publication/package/manifest.rb

@@ -1,5 +1,6 @@
 require 'set'
 require 'enumerabler'
+require 'rchardet'
 require 'epub/constants'
 require 'epub/parser/content_document'
 
@@ -91,9 +92,21 @@ module EPUB
           end
 
           def read
-            Zip::Archive.open(manifest.package.book.epub_file) {|zip|
+            raw_content = Zip::Archive.open(manifest.package.book.epub_file) {|zip|
               zip.fopen(entry_name).read
             }
+            # CharDet.detect doesn't raise Encoding::CompatibilityError
+            # that is caused when trying compare CharDet's internal
+            # ASCII-8BIT RegExp with a String with other encoding
+            # because Zip::File#read returns a String with encoding ASCII-8BIT.
+            # So, no need to rescue the error here.
+            encoding = CharDet.detect(raw_content)['encoding']
+            if encoding
+              raw_content.force_encoding(encoding)
+            else
+              warn "No encoding detected for #{entry_name}. Set to ASCII-8BIT" if $DEBUG || $VERBOSE
+              raw_content
+            end
           end
 
           def xhtml?

data/lib/epub/searcher.rb

@@ -0,0 +1,3 @@
+require 'epub/searcher/result'
+require 'epub/searcher/publication'
+require 'epub/searcher/xhtml'

data/lib/epub/searcher/publication.rb

@@ -0,0 +1,32 @@
+require 'epub/publication'
+
+module EPUB
+  module Searcher
+    class Publication
+      class << self
+        def search(package, word)
+          new(word).search(package)
+        end
+      end
+
+      def initialize(word)
+        @word = word
+      end
+
+      def search(package)
+        results = []
+
+        spine = package.spine
+        spine_step = Result::Step.new(:element, 2, {:name => 'spine', :id => spine.id})
+        spine.each_itemref.with_index do |itemref, index|
+          itemref_step = Result::Step.new(:itemref, index, {:id => itemref.id})
+          XHTML::Restricted.search(Nokogiri.XML(itemref.item.read), @word).each do |sub_result|
+            results << Result.new([spine_step, itemref_step] + sub_result.parent_steps, sub_result.start_steps, sub_result.end_steps)
+          end
+        end
+
+        results
+      end
+    end
+  end
+end

data/lib/epub/searcher/result.rb

@@ -0,0 +1,73 @@
+module EPUB
+  module Searcher
+    class Result
+      attr_reader :parent_steps, :start_steps, :end_steps
+
+      # @param parent_steps [Array<Step>] common steps between start and end
+      # @param start_steps [Array<Step>] steps to start from +parent_steps+
+      # @param end_steps [Array<Step>] steps to end from +parent_steps+
+      def initialize(parent_steps, start_steps, end_steps)
+        @parent_steps, @start_steps, @end_steps = parent_steps, start_steps, end_steps
+      end
+
+      def to_xpath_and_offset(with_xmlns=false)
+        xpath = (@parent_steps + @start_steps).reduce('.') {|path, step|
+          case step.type
+          when :element
+            path + '/%s*[%d]' % [with_xmlns ? 'xhtml:' : nil, step.index + 1]
+          when :text
+            path + '/text()[%s]' % [step.index + 1]
+          else
+            path
+          end
+        }
+
+        [xpath, @start_steps.last.index]
+      end
+
+      def to_cfi_s
+        [@parent_steps, @start_steps, @end_steps].collect {|steps|
+          steps ? steps.collect(&:to_cfi_s).join : nil
+        }.compact.join(',')
+      end
+
+      def ==(other)
+        [@parent_steps + @start_steps.to_a] == [other.parent_steps + other.start_steps.to_a] and
+          [@parent_steps + @end_steps.to_a] == [other.parent_steps + other.end_steps.to_a]
+      end
+
+      class Step
+        attr_reader :type, :index, :info
+
+        def initialize(type, index, info={})
+          @type, @index, @info = type, index, info
+        end
+
+        def ==(other)
+          self.type == other.type and
+            self.index == other.index and
+            self.info == other.info
+        end
+
+        def to_cfi_s
+          case type
+          when :element
+            '/%d%s' % [(index + 1) * 2, id_assertion]
+          when :text
+            '/%d' % [(index + 1)]
+          when :character
+            ':%d' % [index]
+          when :itemref
+            '/%d%s!' % [(index + 1) * 2, id_assertion]
+          end
+        end
+
+        private
+
+        def id_assertion
+          info[:id] ? "[#{info[:id]}]" : nil
+        end
+      end
+    end
+  end
+end

data/lib/epub/searcher/xhtml.rb

@@ -0,0 +1,57 @@
+require 'epub'
+require 'epub/parser/utils'
+
+module EPUB
+  module Searcher
+    class XHTML
+      class Restricted
+        class << self
+          # @param element [Nokogiri::XML::Element, Nokogiri::XML::Document]
+          # @param word [String]
+          # @return [Array<Result>]
+          def search(element, word)
+            new(word).search(element.respond_to?(:root) ? element.root : element)
+          end
+        end
+
+        # @param word [String]
+        def initialize(word)
+          @word = word
+        end
+
+        # @param element [Nokogiri::XML::Element]
+        # @return [Array<Result>]
+        def search(element)
+          results = []
+
+          elem_index = 0
+          element.children.each do |child|
+            if child.element?
+              child_step = Result::Step.new(:element, elem_index, {:name => child.name, :id => Parser::Utils.extract_attribute(child, 'id')})
+              if child.name == 'img'
+                if Parser::Utils.extract_attribute(child, 'alt').index(@word)
+                  results << Result.new([child_step], nil, nil)
+                end
+              else
+                search(child).each do |sub_result|
+                  results << Result.new([child_step] + sub_result.parent_steps, sub_result.start_steps, sub_result.end_steps)
+                end
+              end
+              elem_index += 1
+            elsif child.text?
+              text_index = elem_index
+              char_index = 0
+              text_step = Result::Step.new(:text, text_index)
+              while char_index = child.text.index(@word, char_index)
+                results << Result.new([text_step], [Result::Step.new(:character, char_index)], [Result::Step.new(:character, char_index + @word.length)])
+                char_index += 1
+              end
+            end
+          end
+
+          results
+        end
+      end
+    end
+  end
+end

data/test/fixtures/book/OPS/japanese.eucjp.xhtml

@@ -0,0 +1,10 @@
+<?xml version="1.0" encoding="EUC-JP"?>
+<html xmlns="http://www.w3.org/1999/xhtml" xmlns:epub="http://www.idpf.org/2007/ops">
+  <head>
+    <meta charset="EUC-JP" />
+    <title>���ܸ�</title>
+  </head>
+  <body>
+    <h1>���ܸ�</h1>
+  </body>
+</html>

data/test/fixtures/book/OPS/japanese.sjis.xhtml

@@ -0,0 +1,10 @@
+<?xml version="1.0" encoding="Shift_JIS"?>
+<html xmlns="http://www.w3.org/1999/xhtml" xmlns:epub="http://www.idpf.org/2007/ops">
+  <head>
+    <meta charset="Shift_JIS" />
+    <title>���{��</title>
+  </head>
+  <body>
+    <h1>���{��</h1>
+  </body>
+</html>

data/test/fixtures/book/OPS/japanese.utf8.xhtml

@@ -0,0 +1,10 @@
+<?xml version="1.0"?>
+<html xmlns="http://www.w3.org/1999/xhtml" xmlns:epub="http://www.idpf.org/2007/ops">
+  <head>
+    <meta charset="UTF-8" />
+    <title>日本語</title>
+  </head>
+  <body>
+    <h1>日本語</h1>
+  </body>
+</html>

data/test/fixtures/book/OPS//343/203/253/343/203/274/343/203/210/343/203/225/343/202/241/343/202/244/343/203/253.opf

@@ -101,6 +101,15 @@
     <item id="encoded-japanese-filename"
           href="%E6%97%A5%E6%9C%AC%E8%AA%9E.xhtml"
           media-type="application/xhtml+xml"/>
+    <item id="utf-8-encoded"
+          href="japanese.utf8.xhtml"
+          media-type="application/xhtml+xml"/>
+    <item id="euc-jp-encoded"
+          href="japanese.eucjp.xhtml"
+          media-type="application/xhtml+xml"/>
+    <item id="shift_jis-encoded"
+          href="japanese.sjis.xhtml"
+          media-type="application/xhtml+xml"/>
   </manifest>
   <spine>
     <itemref idref="nav"/>
@@ -116,4 +125,4 @@
     <mediaType handler="impl"
                media-type="application/x-demo-slideshow"/>
   </bindings>
-</package>
+</package>

data/test/test_parser_publication.rb

@@ -81,8 +81,8 @@ class TestParserPublication < Test::Unit::TestCase
       @manifest = @parser.parse_manifest
     end
 
-    def test_manifest_has_16_items
-      assert_equal 16, @manifest.items.length
+    def test_manifest_has_19_items
+      assert_equal 19, @manifest.items.length
     end
 
     def test_item_has_relative_path_as_href_attribute

data/test/test_publication.rb

@@ -239,6 +239,16 @@ class TestPublication < Test::Unit::TestCase
 
         assert_nil xhtml_item.find_item_by_relative_iri(Addressable::URI.parse('../image/01.png'))
       end
+
+      data('UTF-8'     => [Encoding::UTF_8,     'utf-8-encoded'],
+           'EUC-JP'    => [Encoding::EUC_JP,    'euc-jp-encoded'],
+           'Shift-JIS' => [Encoding::Shift_JIS, 'shift_jis-encoded'])
+      def test_read_detects_encoding_automatically(data)
+        encoding, id = data
+        epub = EPUB::Parser.parse('test/fixtures/book.epub')
+        item = epub.package.manifest[id]
+        assert_equal encoding, item.read.encoding
+      end
     end
   end
 

data/test/test_searcher.rb

@@ -0,0 +1,117 @@
+# -*- coding: utf-8 -*-
+require_relative 'helper'
+require 'epub/searcher'
+
+class TestSearcher < Test::Unit::TestCase
+  class TestPublication < self
+    def setup
+      super
+      opf_path = File.expand_path('../fixtures/book/OPS/ルートファイル.opf', __FILE__)
+      nav_path = File.expand_path('../fixtures/book/OPS/nav.xhtml', __FILE__)
+      @package = EPUB::Parser::Publication.new(open(opf_path), 'OPS/ルートファイル.opf').parse
+      @package.spine.each_itemref do |itemref|
+        stub(itemref.item).read {
+          itemref.idref == 'nav' ? File.read(nav_path) : '<html></html>'
+        }
+      end
+    end
+
+    def test_no_result
+      assert_empty EPUB::Searcher::Publication.search(@package, 'no result')
+    end
+
+    def test_simple
+      assert_equal(
+        results([
+          [[[:element, 2, {:name => 'spine', :id => nil}], [:itemref, 0, {:id => nil}], [:element, 0, {:name => 'head', :id => nil}], [:element, 0, {:name => 'title', :id => nil}], [:text, 0]], [[:character, 9]], [[:character, 16]]],
+          [[[:element, 2, {:name => 'spine', :id => nil}], [:itemref, 0, {:id => nil}], [:element, 1, {:name => 'body', :id => nil}], [:element, 0, {:name => 'div', :id => nil}], [:element, 0, {:name => 'nav', :id => 'idid'}], [:element, 0, {:name => 'hgroup', :id => nil}], [:element, 1, {:name => 'h1', :id => nil}], [:text, 0]], [[:character, 9]], [[:character, 16]]]
+        ]),
+        EPUB::Searcher::Publication.search(@package, 'Content')
+    )
+    end
+
+    class TesetResult < self
+      def test_to_cfi_s
+        assert_equal '/6/2!/4/2/2[idid]/2/4/1,:9,:16', EPUB::Searcher::Publication.search(@package, 'Content').last.to_cfi_s
+      end
+    end
+  end
+
+  class TestXHTML < self
+    def setup
+      super
+      nav_path = File.expand_path('../fixtures/book/OPS/nav.xhtml', __FILE__)
+      @doc = Nokogiri.XML(open(nav_path))
+      @h1 = @doc.search('h1').first
+      @nav = @doc.search('nav').first
+    end
+
+    def test_no_result
+      assert_empty EPUB::Searcher::XHTML::Restricted.search(@h1, 'no result')
+    end
+
+    def test_simple
+      assert_equal results([[[[:text, 0]], [[:character, 9]], [[:character, 16]]]]), EPUB::Searcher::XHTML::Restricted.search(@h1, 'Content')
+    end
+
+    def test_multiple_text_result
+      assert_equal results([[[[:text, 0]], [[:character, 6]], [[:character, 7]]], [[[:text, 0]], [[:character, 10]], [[:character, 11]]]]), EPUB::Searcher::XHTML::Restricted.search(@h1, 'o')
+    end
+
+    def test_text_after_element
+      elem = Nokogiri.XML('<root><elem>inner</elem>after</root>')
+
+      assert_equal results([[[[:text, 1]], [[:character, 0]], [[:character, 5]]]]), EPUB::Searcher::XHTML::Restricted.search(elem, 'after')
+    end
+
+    def test_entity_reference
+      elem = Nokogiri.XML('<root>before&lt;after</root>')
+
+      assert_equal results([[[[:text, 0]], [[:character, 6]], [[:character, 7]]]]), EPUB::Searcher::XHTML::Restricted.search(elem, '<')
+    end
+
+    def test_nested_result
+      assert_equal results([[[[:element, 1, {:name => 'ol', :id => nil}], [:element, 1, {:name => 'li', :id => nil}], [:element, 1, {:name => 'ol', :id => nil}], [:element, 1, {:name => 'li', :id => nil}], [:element, 0, {:name => 'a', :id => nil}], [:text, 0]], [[:character, 0]], [[:character, 3]]]]), EPUB::Searcher::XHTML::Restricted.search(@nav, '第二節')
+    end
+
+    def test_img
+      assert_equal [result([[[:element, 1, {:name => 'ol', :id => nil}], [:element, 1, {:name => 'li', :id => nil}], [:element, 1, {:name => 'ol', :id => nil}], [:element, 2, {:name => 'li', :id => nil}], [:element, 0, {:name => 'a', :id => nil}], [:element, 0, {:name => 'img', :id => nil}]], nil, nil])], EPUB::Searcher::XHTML::Restricted.search(@nav, '第三節')
+    end
+
+    class TestResult < self
+      def setup
+        super
+        @result = EPUB::Searcher::XHTML::Restricted.search(@doc, '第二節').first
+      end
+
+      def test_to_xpath_and_offset
+        assert_equal ['./*[2]/*[1]/*[1]/*[2]/*[2]/*[2]/*[2]/*[1]/text()[1]', 0], @result.to_xpath_and_offset
+        assert_equal ['./xhtml:*[2]/xhtml:*[1]/xhtml:*[1]/xhtml:*[2]/xhtml:*[2]/xhtml:*[2]/xhtml:*[2]/xhtml:*[1]/text()[1]', 0], @result.to_xpath_and_offset(true)
+      end
+
+      def test_to_cfi_s
+        assert_equal '/4/2/2[idid]/4/4/4/4/2/1,:0,:3', @result.to_cfi_s
+      end
+
+      def test_to_cfi_s_img
+        assert_equal '/4/2/2[idid]/4/4/4/6/2/2', EPUB::Searcher::XHTML::Restricted.search(@doc, '第三節').first.to_cfi_s
+      end
+    end
+  end
+
+  private
+
+  def results(results)
+    results.collect {|res| result(res)}
+  end
+
+  def result(steps_triple)
+    EPUB::Searcher::Result.new(*steps_triple.collect {|steps|
+      steps ? steps.collect {|s| step(s)} : steps
+    })
+  end
+
+  def step(step)
+    EPUB::Searcher::Result::Step.new(*step)
+  end
+end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: epub-parser
 version: !ruby/object:Gem::Version
-  version: 0.1.6
+  version: 0.1.7
 platform: ruby
 authors:
 - KITAITI Makoto
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-04-20 00:00:00.000000000 Z
+date: 2014-09-20 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake
@@ -276,6 +276,20 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: 2.3.5
+- !ruby/object:Gem::Dependency
+  name: rchardet
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
 description: Parse EPUB 3 book loosely
 email:
 - KitaitiMakoto@gmail.com
@@ -304,6 +318,7 @@ files:
 - docs/Item.markdown
 - docs/Navigation.markdown
 - docs/Publication.markdown
+- docs/Searcher.markdown
 - epub-parser.gemspec
 - features/epubinfo.feature
 - features/step_definitions/epubinfo_steps.rb
@@ -337,6 +352,10 @@ files:
 - lib/epub/publication/package/manifest.rb
 - lib/epub/publication/package/metadata.rb
 - lib/epub/publication/package/spine.rb
+- lib/epub/searcher.rb
+- lib/epub/searcher/publication.rb
+- lib/epub/searcher/result.rb
+- lib/epub/searcher/xhtml.rb
 - man/epubinfo.1.ronn
 - schemas/epub-nav-30.rnc
 - schemas/epub-nav-30.sch
@@ -347,6 +366,9 @@ files:
 - test/fixtures/book/OPS/case-sensitive.xhtml
 - test/fixtures/book/OPS/containing space.xhtml
 - test/fixtures/book/OPS/containing%20space.xhtml
+- test/fixtures/book/OPS/japanese.eucjp.xhtml
+- test/fixtures/book/OPS/japanese.sjis.xhtml
+- test/fixtures/book/OPS/japanese.utf8.xhtml
 - test/fixtures/book/OPS/nav.xhtml
 - test/fixtures/book/OPS/ルートファイル.opf
 - test/fixtures/book/OPS/日本語.xhtml
@@ -362,6 +384,7 @@ files:
 - test/test_parser_ocf.rb
 - test/test_parser_publication.rb
 - test/test_publication.rb
+- test/test_searcher.rb
 homepage: https://github.com/KitaitiMakoto/epub-parser
 licenses:
 - MIT
@@ -382,7 +405,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.2.0
+rubygems_version: 2.2.2
 signing_key: 
 specification_version: 4
 summary: EPUB 3 Parser
@@ -401,4 +424,5 @@ test_files:
 - test/test_parser_ocf.rb
 - test/test_parser_publication.rb
 - test/test_publication.rb
+- test/test_searcher.rb
 has_rdoc: yard