epub-parser 0.2.7 → 0.2.8

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: e92165c76652996a441e9996bb9bdee8bb0e7b04
-  data.tar.gz: c7a62b70d282f9b8343c0b850db21d7f078961d9
+  metadata.gz: 84aac696d82b7eb55bf80b1448685ac4c210abdd
+  data.tar.gz: a32f0e557b928502e0825cbb6b2d808f0fc9dd1d
 SHA512:
-  metadata.gz: f56160b8148faf112e6ff8941a380223f1ce4d0ad114b2375f8e9793fe4eb0d7d9e18dda540f36c1ce702c90c7791006f5fa65c270498d5d6e5b341862e6aa37
-  data.tar.gz: f139ae34069e6bcfe85d23ae5b4db32cecd99ae90cfc1fbe12ba1b2541f31d93329a6215cf099074b0fc0a3b03996ea6fca2508ad9b3165f27522be5fb8c759e
+  metadata.gz: 5a28c163db08c10c57f733d6ffc9a68a768b30a5fe84439bff1fbb03941448c822eb916f3338016b1cd8f2a96954f69a775be0f65bb629231767dfb995318934
+  data.tar.gz: f5535095748701b940555ca424f3488b4e7b007c39d6e2688cf16d00394a9e03c2c6f12290c820ca15aee2a11ce0ed43e5745225507c6baab9c2a7e33bf513ab

data/.gitlab-ci.yml

@@ -0,0 +1,19 @@
+before_script:
+  - apt-get update -qq && apt-get install -y zip
+  - ruby -v
+  - which ruby
+  - gem install bundler --no-document
+  - bundle install --jobs=$(nproc) "${FLAGS[@]}"
+
+test:2.2:
+  image: ruby:2.2
+  script:
+    - bundle exec rake test
+
+test:2.3:
+  image: ruby:2.3
+  script: bundle exec rake test
+
+test:2.4:
+  image: ruby:2.4
+  script: bundle exec rake test

data/.travis.yml

@@ -1,4 +1,4 @@
 rvm:
-  - "2.1.10"
   - "2.2.5"
   - "2.3.1"
+  - "2.4.0"

data/CHANGELOG.markdown

@@ -1,6 +1,12 @@
 CHANGELOG
 =========
 
+0.2.8
+-----
+
+* Change Searcher API: #search -> #search_text
+* Add Searcher.search_element
+
 0.2.7
 -----
 

data/Gemfile

@@ -1,2 +1,6 @@
 source 'https://rubygems.org'
 gemspec
+
+if RUBY_PLATFORM.match /darwin/
+  gem 'terminal-notifier'
+end

data/README.markdown

@@ -1,6 +1,7 @@
 EPUB Parser
 ===========
 [![Build Status](https://secure.travis-ci.org/KitaitiMakoto/epub-parser.png?branch=master)](http://travis-ci.org/KitaitiMakoto/epub-parser)
+[![build status](https://gitlab.com/KitaitiMakoto/epub-parser/badges/master/build.svg)](https://gitlab.com/KitaitiMakoto/epub-parser/commits/master)
 [![Dependency Status](https://gemnasium.com/KitaitiMakoto/epub-parser.png)](https://gemnasium.com/KitaitiMakoto/epub-parser)
 [![Gem Version](https://badge.fury.io/rb/epub-parser.svg)](http://badge.fury.io/rb/epub-parser)
 
@@ -31,7 +32,7 @@ USAGE
 
 See document's {file:docs/Home.markdown} or [API Documentation][rubydoc] for more info.
 
-[rubydoc]: http://rubydoc.info/gems/epub-parser
+[rubydoc]: http://www.rubydoc.info/gems/epub-parser
 
 ### `epubinfo` command-line tool
 
@@ -114,7 +115,7 @@ It will show you path to generated documentation(`/path/to/gempath/ruby/2.2.0/do
 
 Or, generating by yardoc command is possible, too:
 
-    $ git clone https://github.com/KitaitiMakoto/epub-parser.git
+    $ git clone https://gitlab.com/KitaitiMakoto/epub-parser.git
     $ cd epub-parser
     $ bundle install --path=deps
     $ bundle exec rake doc:yard
@@ -151,6 +152,11 @@ If you find other gems, please tell me or request a pull request.
 RECENT CHANGES
 --------------
 
+### 0.2.8
+
+* Change Searcher API: #search -> #search_text
+* Add Searcher.search_element
+
 ### 0.2.7
 
 * Add `EPUB::Metadata#children`
@@ -169,11 +175,6 @@ RECENT CHANGES
 
 [multi-rendition]: http://www.idpf.org/epub/renditions/multiple/
 
-### 0.2.5
-
-* [BUG FIX]Don't load Zip/Ruby if unneccessary
-* Add `EPUB::CFI::PhysicalContainer.find_adapter`
-
 See {file:CHANGELOG.markdown} for older changelogs and details.
 
 TODOS

data/docs/Home.markdown

@@ -122,7 +122,7 @@ It will show you path to generated documentation(`/path/to/gempath/ruby/2.2.0/do
 
 Or, generating yardoc command is possible, too:
 
-    $ git clone https://github.com/KitaitiMakoto/epub-parser.git
+    $ git clone https://gitlab.com/KitaitiMakoto/epub-parser.git
     $ cd epub-parser
     $ bundle install --path=deps
     $ bundle exec rake doc:yard

data/docs/Searcher.markdown

@@ -8,37 +8,37 @@ Searcher
 Example
 -------
 
-    epub = EPUB::Parser.parse('childrens-literature-20130206.epub')
+    epub = EPUB::Parser.parse('childrens-literature.epub')
     search_word = 'INTRODUCTORY'
-    results = EPUB::Searcher.search(epub, search_word)
-    # => [#<EPUB::Searcher::Result:0x007f938ed517a8
-    #   @end_steps=[#<EPUB::Searcher::Result::Step:0x007f938ed51a50 @index=12, @info={}, @type=:character>],
+    results = EPUB::Searcher.search_text(epub, search_word)
+    # => [#<EPUB::Searcher::Result:0x007f80ccde9528
+    #   @end_steps=[#<EPUB::Searcher::Result::Step:0x007f80ccde9730 @index=12, @info={}, @type=:character>],
     #   @parent_steps=
-    #    [#<EPUB::Searcher::Result::Step:0x007f938f1c1e78 @index=2, @info={:name=>"spine", :id=>nil}, @type=:element>,
-    #     #<EPUB::Searcher::Result::Step:0x007f938f1caa78 @index=1, @info={:id=>nil}, @type=:itemref>,
-    #     #<EPUB::Searcher::Result::Step:0x007f938ed521d0 @index=1, @info={:name=>"body", :id=>nil}, @type=:element>,
-    #     #<EPUB::Searcher::Result::Step:0x007f938ed52158 @index=0, @info={:name=>"nav", :id=>"toc"}, @type=:element>,
-    #     #<EPUB::Searcher::Result::Step:0x007f938ed52108 @index=1, @info={:name=>"ol", :id=>"tocList"}, @type=:element>,
-    #     #<EPUB::Searcher::Result::Step:0x007f938ed52090 @index=0, @info={:name=>"li", :id=>"np-313"}, @type=:element>,
-    #     #<EPUB::Searcher::Result::Step:0x007f938ed52040 @index=1, @info={:name=>"ol", :id=>nil}, @type=:element>,
-    #     #<EPUB::Searcher::Result::Step:0x007f938ed51ff0 @index=1, @info={:name=>"li", :id=>"np-317"}, @type=:element>,
-    #     #<EPUB::Searcher::Result::Step:0x007f938ed51f78 @index=0, @info={:name=>"a", :id=>nil}, @type=:element>,
-    #     #<EPUB::Searcher::Result::Step:0x007f938ed51f28 @index=0, @info={}, @type=:text>],
-    #   @start_steps=[#<EPUB::Searcher::Result::Step:0x007f938ed51e88 @index=0, @info={}, @type=:character>]>,
-    #  #<EPUB::Searcher::Result:0x007f938ef8f5d8
-    #   @end_steps=[#<EPUB::Searcher::Result::Step:0x007f938ef8f808 @index=12, @info={}, @type=:character>],
+    #    [#<EPUB::Searcher::Result::Step:0x007f80ccf571d0 @index=2, @info={:name=>"spine", :id=>nil}, @type=:element>,
+    #     ##<EPUB::Searcher::Result::Step:0x007f80ccf3d3e8 @index=1, @info={:id=>nil}, @type=:itemref>,
+    #     ##<EPUB::Searcher::Result::Step:0x007f80ccde9e88 @index=1, @info={:name=>"body", :id=>nil}, @type=:element>,
+    #     ##<EPUB::Searcher::Result::Step:0x007f80ccde9e38 @index=0, @info={:name=>"nav", :id=>"toc"}, @type=:element>,
+    #     ##<EPUB::Searcher::Result::Step:0x007f80ccde9de8 @index=1, @info={:name=>"ol", :id=>"tocList"}, @type=:element>,
+    #     ##<EPUB::Searcher::Result::Step:0x007f80ccde9d98 @index=0, @info={:name=>"li", :id=>"np-313"}, @type=:element>,
+    #     ##<EPUB::Searcher::Result::Step:0x007f80ccde9d48 @index=1, @info={:name=>"ol", :id=>nil}, @type=:element>,
+    #     ##<EPUB::Searcher::Result::Step:0x007f80ccde9ca8 @index=1, @info={:name=>"li", :id=>"np-317"}, @type=:element>,
+    #     ##<EPUB::Searcher::Result::Step:0x007f80ccde9c08 @index=0, @info={:name=>"a", :id=>nil}, @type=:element>,
+    #     ##<EPUB::Searcher::Result::Step:0x007f80ccde9bb8 @index=0, @info={}, @type=:text>],
+    #   @start_steps=[#<EPUB::Searcher::Result::Step:0x007f80ccde9af0 @index=0, @info={}, @type=:character>]>,
+    #  #<EPUB::Searcher::Result:0x007f80ccebcb30
+    #   @end_steps=[#<EPUB::Searcher::Result::Step:0x007f80ccebcdb0 @index=12, @info={}, @type=:character>],
     #   @parent_steps=
-    #    [#<EPUB::Searcher::Result::Step:0x007f938f1c1e78 @index=2, @info={:name=>"spine", :id=>nil}, @type=:element>,
-    #     #<EPUB::Searcher::Result::Step:0x007f938ed51730 @index=2, @info={:id=>nil}, @type=:itemref>,
-    #     #<EPUB::Searcher::Result::Step:0x007f938ef8fce0 @index=1, @info={:name=>"body", :id=>nil}, @type=:element>,
-    #     #<EPUB::Searcher::Result::Step:0x007f938ef8fc90 @index=0, @info={:name=>"section", :id=>"pgepubid00492"}, @type=:element>,
-    #     #<EPUB::Searcher::Result::Step:0x007f938ef8fc40 @index=3, @info={:name=>"section", :id=>"pgepubid00498"}, @type=:element>,
-    #     #<EPUB::Searcher::Result::Step:0x007f938ef8fbf0 @index=1, @info={:name=>"h3", :id=>nil}, @type=:element>,
-    #     #<EPUB::Searcher::Result::Step:0x007f938ef8fb28 @index=0, @info={}, @type=:text>],
-    #   @start_steps=[#<EPUB::Searcher::Result::Step:0x007f938ef8fa88 @index=0, @info={}, @type=:character>]>]
-    puts results.collect(&:to_cfi_s)
-    # /6/4!/4/2[toc]/4[tocList]/2[np-313]/4/4[np-317]/2/1,:0,:12
-    # /6/6!/4/2[pgepubid00492]/8[pgepubid00498]/4/1,:0,:12
+    #    [#<EPUB::Searcher::Result::Step:0x007f80ccf571d0 @index=2, @info={:name=>"spine", :id=>nil}, @type=:element>,
+    #     ##<EPUB::Searcher::Result::Step:0x007f80ccde94b0 @index=2, @info={:id=>nil}, @type=:itemref>,
+    #     ##<EPUB::Searcher::Result::Step:0x007f80ccebd328 @index=1, @info={:name=>"body", :id=>nil}, @type=:element>,
+    #     ##<EPUB::Searcher::Result::Step:0x007f80ccebd2d8 @index=0, @info={:name=>"section", :id=>"pgepubid00492"}, @type=:element>,
+    #     ##<EPUB::Searcher::Result::Step:0x007f80ccebd260 @index=3, @info={:name=>"section", :id=>"pgepubid00498"}, @type=:element>,
+    #     ##<EPUB::Searcher::Result::Step:0x007f80ccebd210 @index=1, @info={:name=>"h3", :id=>nil}, @type=:element>,
+    #     ##<EPUB::Searcher::Result::Step:0x007f80ccebd198 @index=0, @info={}, @type=:text>],
+    #   @start_steps=[#<EPUB::Searcher::Result::Step:0x007f80ccebd0d0 @index=0, @info={}, @type=:character>]>]
+    puts results.collect(&:to_cfi).collect(&:to_fragment)
+    # epubcfi(/6/4!/4/2[toc]/4[tocList]/2[np-313]/4/4[np-317]/2/1,:0,:12)
+    # epubcfi(/6/6!/4/2[pgepubid00492]/8[pgepubid00498]/4/1,:0,:12)
     # => nil
 
 Search result
@@ -91,4 +91,19 @@ because the words 'search' and 'word' are not in the same element.
 
 To use restricted searcher, specify `algorithm` option for `search` method:
 
-    results = EPUB::Searcher.search(epub, search_word, algorithm: :restricted)
+    results = EPUB::Searcher.search_text(epub, search_word, algorithm: :restricted)
+
+Element Searcher
+----------------
+
+You can search XHTML elements by CSS selector or XPath.
+
+    EPUB::Searcher::Publication.search_element(@package, css: 'ol > li').collect {|result| result[:location]}.map(&:to_fragment)
+    # => ["epubcfi(/4/4!/4/2[toc]/4[tocList]/2[np-313])",
+    #  "epubcfi(/4/4!/4/2[toc]/4[tocList]/2[np-313]/4/2[np-315])",
+    #  "epubcfi(/4/4!/4/2[toc]/4[tocList]/2[np-313]/4/4[np-317])",
+    #  "epubcfi(/4/4!/4/2[toc]/4[tocList]/2[np-313]/4/6)",
+    #  "epubcfi(/4/4!/4/2[toc]/4[tocList]/2[np-313]/4/6/4/2[np-319])",
+    #  "epubcfi(/4/4!/4/2[toc]/4[tocList]/2[np-313]/4/6/4/2[np-319]/4/2)",
+    #    :
+    #    :

data/examples/find-elements-and-cfis.rb

@@ -23,10 +23,6 @@ def main(argv)
 
   epub = EPUB::Parser.parse(epub_path)
   epub.package.spine.each_itemref.with_index do |itemref, i|
-    itemref_step = {
-      :step => (i + 1) * 2,
-      :id => itemref.id
-    }
     assertion = itemref.id ? EPUB::CFI::IDAssertion.new(itemref.id) : nil
     itemref_step = EPUB::CFI::Step.new((i + 1) * 2, assertion)
     path_to_itemref = EPUB::CFI::Path.new([spine_step, itemref_step])

data/lib/epub/content_document/navigation.rb

@@ -5,6 +5,8 @@ module EPUB
 
       def initialize
         @navigations = []
+        @hidden = false
+        @parent = nil
         super
       end
 

data/lib/epub/ocf/physical_container.rb

@@ -7,7 +7,15 @@ module EPUB
   class OCF
     # @todo: Make thread save
     class PhysicalContainer
-      class NoEntry < StandardError; end
+      class NoEntry < StandardError
+        class << self
+          def from_error(error)
+            no_entry = new(error.message)
+            no_entry.set_backtrace error.backtrace
+            no_entry
+          end
+        end
+      end
 
       @adapter = ArchiveZip
 

data/lib/epub/ocf/physical_container/unpacked_directory.rb

@@ -9,9 +9,7 @@ module EPUB
         def read(path_name)
           ::File.read(::File.join(@container_path, path_name))
         rescue ::Errno::ENOENT => error
-          no_entry = NoEntry.new(error.message)
-          no_entry.set_backtrace error.backtrace
-          raise no_entry
+          raise NoEntry.from_error(error)
         end
       end
     end

data/lib/epub/ocf/physical_container/unpacked_uri.rb

@@ -20,9 +20,7 @@ module EPUB
         def read(path_name)
           (@container_path + path_name).read
         rescue ::OpenURI::HTTPError => error
-          no_entry = NoEntry.new(error.message)
-          no_entry.set_backtrace error.backtrace
-          raise no_entry
+          raise NoEntry.from_error(error)
         end
       end
     end

data/lib/epub/ocf/physical_container/zipruby.rb

@@ -11,9 +11,7 @@ module EPUB
                 @archive = archive
                 yield self
               rescue ::Zip::Error => error
-                no_entry = NoEntry.new(error.message)
-                no_entry.set_backtrace error.backtrace
-                raise no_entry
+                raise NoEntry.from_error(error)
               ensure
                 @archive = nil
               end
@@ -28,9 +26,7 @@ module EPUB
             open {|container| container.read(path_name)}
           end
         rescue ::Zip::Error => error
-          no_entry = NoEntry.new(error.message)
-          no_entry.set_backtrace error.backtrace
-          raise no_entry
+          raise NoEntry.from_error(error)
         ensure
           @archive = nil
         end

data/lib/epub/parser/version.rb

@@ -1,5 +1,5 @@
 module EPUB
   class Parser
-    VERSION = "0.2.7"
+    VERSION = "0.2.8"
   end
 end

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

@@ -101,6 +101,7 @@ module EPUB
 
           def initialize
             @properties = Set.new
+            @full_path = nil
           end
 
           def properties=(props)

data/lib/epub/searcher.rb

@@ -5,8 +5,12 @@ require 'epub/searcher/xhtml'
 module EPUB
   module Searcher
     class << self
-      def search(epub, word, **options)
-        Publication.search(epub.package, word, options)
+      def search_text(epub, word, **options)
+        Publication.search_text(epub.package, word, options)
+      end
+
+      def search_element(epub, css: nil, xpath: nil, namespaces: {})
+        Publication.search_element(epub.package, css: css, xpath: xpath, namespaces: namespaces)
       end
     end
   end

data/lib/epub/searcher/publication.rb

@@ -4,29 +4,79 @@ module EPUB
   module Searcher
     class Publication
       class << self
-        def search(package, word, **options)
-          new(word).search(package, options)
+        def search_text(package, word, **options)
+          new(package).search_text(word, options)
+        end
+
+        def search_element(package, css: nil, xpath: nil, namespaces: {})
+          new(package).search_element(css: css, xpath: xpath, namespaces: namespaces)
         end
       end
 
-      def initialize(word)
-        @word = word
+      def initialize(package)
+        @package = package
       end
 
-      def search(package, algorithm: :seamless)
+      def search_text(word, algorithm: :seamless)
         results = []
 
-        spine = package.spine
+        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::ALGORITHMS[algorithm].search(Nokogiri.XML(itemref.item.read), @word).each do |sub_result|
+          XHTML::ALGORITHMS[algorithm].search_text(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
+
+      # @todo: Refactoring
+      def search_element(css: nil, xpath: nil, namespaces: {})
+        raise ArgumentError, 'Both css and xpath are nil' if css.nil? && xpath.nil?
+
+        namespaces = EPUB::NAMESPACES.merge(namespaces)
+        results = []
+
+        spine_step = EPUB::CFI::Step.new(EPUB::Publication::Package::CONTENT_MODELS.index(:spine) * 2)
+        @package.spine.each_itemref.with_index do |itemref, index|
+          assertion = itemref.id ? EPUB::CFI::IDAssertion.new(itemref.id) : nil
+          itemref_step = EPUB::CFI::Step.new((index + 1) * 2, assertion)
+          path_to_itemref = EPUB::CFI::Path.new([spine_step, itemref_step])
+          content_document = itemref.item.content_document
+          next unless content_document
+          doc = content_document.nokogiri
+          elems = if xpath
+                    doc.xpath(xpath, namespaces)
+                  else
+                    doc.css(css)
+                  end
+          elems.each do |elem|
+            path = find_path(elem)
+            results << {
+              location: EPUB::CFI::Location.new([path_to_itemref, path]),
+              package: @package,
+              element: elem
+            }
+          end
+        end
+
+        results
+      end
+
+      private
+
+      def find_path(elem)
+        steps = []
+        until elem.parent.document?
+          index = elem.parent.element_children.index(elem)
+          assertion = elem["id"] ? EPUB::CFI::IDAssertion.new(elem["id"]) : nil
+          steps.unshift EPUB::CFI::Step.new((index + 1) * 2, assertion)
+          elem = elem.parent
+        end
+        EPUB::CFI::Path.new(steps)
+      end
     end
   end
 end

data/lib/epub/searcher/result.rb

@@ -1,3 +1,6 @@
+require 'epub/cfi'
+require 'epub/parser/cfi'
+
 module EPUB
   module Searcher
     class Result
@@ -9,7 +12,7 @@ module EPUB
         #   # Note that c here is not included in the first element of returned value.
         # @param steps1 [Array<Step>, Array<Array>]
         # @param steps2 [Array<Step>, Array<Array>]
-        # @return [Array<Array<Array>>] Thee arrays:
+        # @return [Array<Array<Array>>] Three arrays:
         #   1. "intersection" of +steps1+ and +steps2+. "intersection" here is not the term of mathmatics
         #   2. remaining steps of +steps1+
         #   3. remaining steps of +steps2+
@@ -41,25 +44,11 @@ module EPUB
         @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
+      def to_cfi
+        str = [@parent_steps, @start_steps, @end_steps].collect {|steps|
+          steps ? steps.collect(&:to_cfi).join : nil
         }.compact.join(',')
+        EPUB::CFI(str)
       end
 
       def ==(other)
@@ -80,7 +69,7 @@ module EPUB
             self.info == other.info
         end
 
-        def to_cfi_s
+        def to_cfi
           case type
           when :element
             '/%d%s' % [(index + 1) * 2, id_assertion]

data/lib/epub/searcher/xhtml.rb

@@ -10,8 +10,8 @@ module EPUB
         # @param element [Nokogiri::XML::Element, Nokogiri::XML::Document]
         # @param word [String]
         # @return [Array<Result>]
-        def search(element, word)
-          new(element.respond_to?(:root) ? element.root : element).search(word)
+        def search_text(element, word)
+          new(element.respond_to?(:root) ? element.root : element).search_text(word)
         end
       end
 
@@ -23,7 +23,7 @@ module EPUB
       class Restricted < self
         # @param element [Nokogiri::XML::Element]
         # @return [Array<Result>]
-        def search(word, element=nil)
+        def search_text(word, element=nil)
           results = []
 
           elem_index = 0
@@ -35,7 +35,7 @@ module EPUB
                   results << Result.new([child_step], nil, nil)
                 end
               else
-                search(word, child).each do |sub_result|
+                search_text(word, child).each do |sub_result|
                   results << Result.new([child_step] + sub_result.parent_steps, sub_result.start_steps, sub_result.end_steps)
                 end
               end
@@ -62,7 +62,7 @@ module EPUB
           @indices = nil
         end
 
-        def search(word)
+        def search_text(word)
           unless @indices
             @indices, @content = build_indices(@element)
           end

data/test/helper.rb

@@ -1,3 +1,4 @@
+Encoding.default_external = 'UTF-8'
 require 'simplecov'
 SimpleCov.start do
   add_filter '/test|deps/'

data/test/test_parser_cfi.rb

@@ -18,6 +18,7 @@ class TestParserCFI < Test::Unit::TestCase
     'epubcfi(/6/4[chap01ref]!/4[body01]/10[para05]/2/1:3[,y])',
     'epubcfi(/6/4[chap01ref]!/4[body01]/10[para05]/2/1:3[;s=b])',
     'epubcfi(/6/4[chap01ref]!/4[body01]/10[para05]/2/1:3[yyy;s=b])',
+    'epubcfi(/6/4[chap01ref]!/4[body01]/10[para05]/2/1:3[^(;s=b])',
     'epubcfi(/6/4[chap01ref]!/4[body01]/10[para05]/2[;s=b])',
     'epubcfi(/6/4[chap01ref]!/4[body01]/10[para05]/3:10)',
     'epubcfi(/6/4[chap01ref]!/4[body01]/16[svgimg])',
@@ -25,7 +26,8 @@ class TestParserCFI < Test::Unit::TestCase
     'epubcfi(/6/4[chap01ref]!/4[body01]/10[para05]/2/1:0)',
     'epubcfi(/6/4[chap01ref]!/4[body01]/10[para05]/2/1:3)',
     'epubcfi(/6/4[chap01ref]!/4[body01]/10[para05],/2/1:1,/3:4)',
-    'epubcfi(/6,:1,:3)'
+    'epubcfi(/6,:1,:3)',
+    'epubcfi(/6/4[chap01ref]!/4[body01]/10[mov01]~23.5@5.75:97.6)'
   ].reduce({}) {|data, cfi|
     data[cfi] = cfi
     data
@@ -35,4 +37,17 @@ class TestParserCFI < Test::Unit::TestCase
       @parser.parse(cfi)
     end
   end
+
+  data([
+    '/6/4[chap01ref]!/4[body01]/10[para05]/2/1:3[(;s=b]',
+    '/6/4[chap01ref]!/4[body01]/10[para05]/2/1:3[);s=b]'
+  ].reduce({}) {|data, cfi|
+    data[cfi] = cfi
+    data
+  })
+  def test_raise_error_on_parsing_invalid_cfi(cfi)
+    assert_raise Racc::ParseError do
+      EPUB::CFI(cfi)
+    end
+  end
 end

data/test/test_searcher.rb

@@ -1,6 +1,7 @@
 # -*- coding: utf-8 -*-
 require_relative 'helper'
 require 'epub/searcher'
+require 'epub/parser/cfi'
 
 class TestSearcher < Test::Unit::TestCase
   class TestPublication < self
@@ -17,7 +18,7 @@ class TestSearcher < Test::Unit::TestCase
     end
 
     def test_no_result
-      assert_empty EPUB::Searcher::Publication.search(@package, 'no result')
+      assert_empty EPUB::Searcher::Publication.search_text(@package, 'no result')
     end
 
     def test_simple
@@ -26,13 +27,53 @@ class TestSearcher < Test::Unit::TestCase
           [[[: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')
+        EPUB::Searcher::Publication.search_text(@package, 'Content')
+      )
+    end
+
+    def test_search_element_xpath_without_namespaces
+      assert_equal(
+        [
+          "epubcfi(/4/2!/4/2/2[idid]/4/2/2)",
+          "epubcfi(/4/2!/4/2/2[idid]/4/4/4/2/2)",
+          "epubcfi(/4/2!/4/2/2[idid]/4/4/4/4/2)",
+          "epubcfi(/4/2!/4/2/2[idid]/4/4/4/6/2)",
+          "epubcfi(/4/2!/4/2/2[idid]/4/4/4/8/2)"
+        ],
+        EPUB::Searcher::Publication.search_element(@package, xpath: './/xhtml:a').collect {|result| result[:location]}.map(&:to_fragment)
+      )
+    end
+
+    def test_search_element_xpath_with_namespaces
+      assert_equal(
+        [
+          "epubcfi(/4/2!/4/2/2[idid]/4/2/2)",
+          "epubcfi(/4/2!/4/2/2[idid]/4/4/4/2/2)",
+          "epubcfi(/4/2!/4/2/2[idid]/4/4/4/4/2)",
+          "epubcfi(/4/2!/4/2/2[idid]/4/4/4/6/2)",
+          "epubcfi(/4/2!/4/2/2[idid]/4/4/4/8/2)"
+        ],
+        EPUB::Searcher::Publication.search_element(@package, xpath: './/customnamespace:a', namespaces: {'customnamespace' => 'http://www.w3.org/1999/xhtml'}).collect {|result| result[:location]}.map(&:to_fragment)
+      )
+    end
+
+    def test_search_element_css_selector
+      assert_equal(
+        [
+          "epubcfi(/4/2!/4/2/2[idid]/4/2)",
+          "epubcfi(/4/2!/4/2/2[idid]/4/4)",
+          "epubcfi(/4/2!/4/2/2[idid]/4/4/4/2)",
+          "epubcfi(/4/2!/4/2/2[idid]/4/4/4/4)",
+          "epubcfi(/4/2!/4/2/2[idid]/4/4/4/6)",
+          "epubcfi(/4/2!/4/2/2[idid]/4/4/4/8)"
+        ],
+        EPUB::Searcher::Publication.search_element(@package, css: 'ol > li').collect {|result| result[:location]}.map(&:to_fragment)
       )
     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
+      def test_to_cfi
+        assert_equal 'epubcfi(/6/2!/4/2/2[idid]/2/4/1,:9,:16)', EPUB::Searcher::Publication.search_text(@package, 'Content').last.to_cfi.to_fragment
       end
     end
   end
@@ -48,35 +89,35 @@ class TestSearcher < Test::Unit::TestCase
 
     module TestSearch
       def test_no_result
-        assert_empty @searcher.search(@h1, 'no result')
+        assert_empty @searcher.search_text(@h1, 'no result')
       end
 
       def test_simple
-        assert_equal results([[[[:text, 0]], [[:character, 9]], [[:character, 16]]]]), @searcher.search(@h1, 'Content')
+        assert_equal results([[[[:text, 0]], [[:character, 9]], [[:character, 16]]]]), @searcher.search_text(@h1, 'Content')
       end
 
       def test_multiple_text_result
-        assert_equal results([[[[:text, 0]], [[:character, 6]], [[:character, 7]]], [[[:text, 0]], [[:character, 10]], [[:character, 11]]]]), @searcher.search(@h1, 'o')
+        assert_equal results([[[[:text, 0]], [[:character, 6]], [[:character, 7]]], [[[:text, 0]], [[:character, 10]], [[:character, 11]]]]), @searcher.search_text(@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]]]]), @searcher.search(elem, 'after')
+        assert_equal results([[[[:text, 1]], [[:character, 0]], [[:character, 5]]]]), @searcher.search_text(elem, 'after')
       end
 
       def test_entity_reference
         elem = Nokogiri.XML('<root>before&lt;after</root>')
 
-        assert_equal results([[[[:text, 0]], [[:character, 6]], [[:character, 7]]]]), @searcher.search(elem, '<')
+        assert_equal results([[[[:text, 0]], [[:character, 6]], [[:character, 7]]]]), @searcher.search_text(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]]]]), @searcher.search(@nav, '第二節')
+        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]]]]), @searcher.search_text(@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])], @searcher.search(@nav, '第三節')
+        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])], @searcher.search_text(@nav, '第三節')
       end
     end
 
@@ -99,27 +140,22 @@ class TestSearcher < Test::Unit::TestCase
 
       def test_seamless
         elem = Nokogiri.XML('<root>This <em>includes</em> a child element.</root>')
-        assert_equal results([[[], [[:text, 0], [:character, 0]], [[:text, 1], [:character, 17]]]]), @searcher.search(elem, 'This includes a child element.')
+        assert_equal results([[[], [[:text, 0], [:character, 0]], [[:text, 1], [:character, 17]]]]), @searcher.search_text(elem, 'This includes a child element.')
       end
     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)
+        @result = EPUB::Searcher::XHTML::Restricted.search_text(@doc, '第二節').first
       end
 
-      def test_to_cfi_s
-        assert_equal '/4/2/2[idid]/4/4/4/4/2/1,:0,:3', @result.to_cfi_s
+      def test_to_cfi
+        assert_equal 'epubcfi(/4/2/2[idid]/4/4/4/4/2/1,:0,:3)', @result.to_cfi.to_fragment
       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
+      def test_to_cfi_img
+        assert_equal 'epubcfi(/4/2/2[idid]/4/4/4/6/2/2)', EPUB::Searcher::XHTML::Restricted.search_text(@doc, '第三節').first.to_cfi.to_fragment
       end
     end
   end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: epub-parser
 version: !ruby/object:Gem::Version
-  version: 0.2.7
+  version: 0.2.8
 platform: ruby
 authors:
 - KITAITI Makoto
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2016-07-30 00:00:00.000000000 Z
+date: 2017-02-07 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake
@@ -301,6 +301,7 @@ extra_rdoc_files: []
 files:
 - ".gemtest"
 - ".gitignore"
+- ".gitlab-ci.yml"
 - ".gitmodules"
 - ".travis.yml"
 - ".yardopts"
@@ -419,7 +420,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.5.1
+rubygems_version: 2.6.8
 signing_key: 
 specification_version: 4
 summary: EPUB 3 Parser