epub-parser 0.2.8 → 0.2.9

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 84aac696d82b7eb55bf80b1448685ac4c210abdd
-  data.tar.gz: a32f0e557b928502e0825cbb6b2d808f0fc9dd1d
+  metadata.gz: b2347178e16da38f1e13e9886ef7e54ba0357288
+  data.tar.gz: f5b32b2028baca3868b4a7a63925c6a6c446511b
 SHA512:
-  metadata.gz: 5a28c163db08c10c57f733d6ffc9a68a768b30a5fe84439bff1fbb03941448c822eb916f3338016b1cd8f2a96954f69a775be0f65bb629231767dfb995318934
-  data.tar.gz: f5535095748701b940555ca424f3488b4e7b007c39d6e2688cf16d00394a9e03c2c6f12290c820ca15aee2a11ce0ed43e5745225507c6baab9c2a7e33bf513ab
+  metadata.gz: 268416ae749188d638b04fb912dec3b2204f0a721de59072f58f812c365f5339c698769bba021f3547638090178fdd6da593e7f3e04b4e30c7d2e17637099313
+  data.tar.gz: dbf6ca7dafed30e6a950f737f2bec8b96588199a4cac14fd9d9e78398698a80eadcbf8f0e627dcd07fade31b4d133ccfe8fc49c97bbd8e05c170dea741f57692

data/CHANGELOG.markdown

@@ -1,6 +1,12 @@
 CHANGELOG
 =========
 
+0.2.9
+-----
+
+* Fix a bug that `Searcher.search_element` returns wrong CFI
+* Add `Searcher.search_by_cfi`
+
 0.2.8
 -----
 

data/README.markdown

@@ -138,8 +138,8 @@ REQUIREMENTS
 * `patch` command to install Nokogiri
 * C compiler to compile Nokogiri
 
-Related Gems
-------------
+Similar Efforts
+---------------
 * [gepub](https://github.com/skoji/gepub) - a generic EPUB library for Ruby
 * [epubinfo](https://github.com/chdorner/epubinfo) - Extracts metadata information from EPUB files. Supports EPUB2 and EPUB3 formats.
 * [ReVIEW](https://github.com/kmuto/review) - ReVIEW is a easy-to-use digital publishing system for books and ebooks.
@@ -152,6 +152,11 @@ If you find other gems, please tell me or request a pull request.
 RECENT CHANGES
 --------------
 
+### 0.2.9
+
+* Fix a bug that `Searcher.search_element` returns wrong CFI
+* Add `Searcher.search_by_cfi`
+
 ### 0.2.8
 
 * Change Searcher API: #search -> #search_text

data/epub-parser.gemspec

@@ -24,7 +24,6 @@ Gem::Specification.new do |s|
   s.test_files    = s.files & Dir['{test,spec,features}/**/*.{rb,feature}']
   s.executables   = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
   s.require_paths = ["lib"]
-  s.has_rdoc = 'yard'
 
   s.add_development_dependency 'rake'
   s.add_development_dependency 'rubygems-tasks'

data/lib/epub/parser/version.rb

@@ -1,5 +1,5 @@
 module EPUB
   class Parser
-    VERSION = "0.2.8"
+    VERSION = "0.2.9"
   end
 end

data/lib/epub/searcher.rb

@@ -12,6 +12,10 @@ module EPUB
       def search_element(epub, css: nil, xpath: nil, namespaces: {})
         Publication.search_element(epub.package, css: css, xpath: xpath, namespaces: namespaces)
       end
+
+      def search_by_cfi(epub, cfi)
+        Publication.search_by_cfi(epub.package, cfi)
+      end
     end
   end
 end

data/lib/epub/searcher/publication.rb

@@ -11,6 +11,10 @@ module EPUB
         def search_element(package, css: nil, xpath: nil, namespaces: {})
           new(package).search_element(css: css, xpath: xpath, namespaces: namespaces)
         end
+
+        def search_by_cfi(package, cfi)
+          new(package).search_by_cfi(cfi)
+        end
       end
 
       def initialize(package)
@@ -33,13 +37,17 @@ module EPUB
       end
 
       # @todo: Refactoring
+      # @return [Array<Hash>] An array of rearch results. Each result is composed of:
+      #   :element: [Nokogiri::XML::ELement] Found element
+      #   :location: [EPUB::CFI::Location] CFI that indicates the element
+      #   :package: [EPUB::Publication::Package] Package that the element belongs to
       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)
+        spine_step = EPUB::CFI::Step.new((EPUB::Publication::Package::CONTENT_MODELS.index(:spine) + 1) * 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)
@@ -65,6 +73,47 @@ module EPUB
         results
       end
 
+      # @note Currenty can handle only location CFI without offset
+      # @todo Use XHTML module
+      # @todo Handle CFI with offset
+      # @todo Handle range CFI
+      # @param [EPUB::CFI] cfi
+      # @return [Array] Path in EPUB Rendition
+      def search_by_cfi(cfi)
+        # steal from pirka's find_item_and_element
+        path_in_package = cfi.paths.first
+        spine = @package.spine
+        model = [@package.metadata, @package.manifest, spine, @package.guide, @package.bindings].compact[path_in_package.steps.first.value / 2 - 1]
+        raise NotImplementedError, "Currently, #{__method__} supports spine only(#{cfi})" unless model == spine
+        raise ArgumentError, "Cannot identify <itemref>'s child" if path_in_package.steps.length > 2
+
+        step_to_itemref = path_in_package.steps[1]
+        itemref = spine.itemrefs[step_to_itemref.value / 2 - 1]
+
+        doc = itemref.item.content_document.nokogiri
+        path_in_doc = cfi.paths[1]
+        current_node = doc.root
+        path_in_doc.steps.each do |step|
+          if step.element?
+            current_node = current_node.element_children[step.value / 2 - 1]
+          else
+            element_index = (step.value - 1) / 2 - 1
+            if element_index == -1
+              current_node = current_node.children.first
+            else
+              prev = current_node.element_children[element_index]
+              break unless prev
+              current_node = prev.next_sibling
+              break unless current_node
+            end
+          end
+        end
+
+        raise NotImplementedError, "Currently, #{__method__} doesn't support deeper DOM tree such as including <iframe>" if cfi.paths[2]
+
+        [itemref, current_node]
+      end
+
       private
 
       def find_path(elem)

data/test/test_searcher.rb

@@ -34,11 +34,11 @@ class TestSearcher < Test::Unit::TestCase
     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)"
+          "epubcfi(/6/2!/4/2/2[idid]/4/2/2)",
+          "epubcfi(/6/2!/4/2/2[idid]/4/4/4/2/2)",
+          "epubcfi(/6/2!/4/2/2[idid]/4/4/4/4/2)",
+          "epubcfi(/6/2!/4/2/2[idid]/4/4/4/6/2)",
+          "epubcfi(/6/2!/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)
       )
@@ -47,11 +47,11 @@ class TestSearcher < Test::Unit::TestCase
     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)"
+          "epubcfi(/6/2!/4/2/2[idid]/4/2/2)",
+          "epubcfi(/6/2!/4/2/2[idid]/4/4/4/2/2)",
+          "epubcfi(/6/2!/4/2/2[idid]/4/4/4/4/2)",
+          "epubcfi(/6/2!/4/2/2[idid]/4/4/4/6/2)",
+          "epubcfi(/6/2!/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)
       )
@@ -60,12 +60,12 @@ class TestSearcher < Test::Unit::TestCase
     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)"
+          "epubcfi(/6/2!/4/2/2[idid]/4/2)",
+          "epubcfi(/6/2!/4/2/2[idid]/4/4)",
+          "epubcfi(/6/2!/4/2/2[idid]/4/4/4/2)",
+          "epubcfi(/6/2!/4/2/2[idid]/4/4/4/4)",
+          "epubcfi(/6/2!/4/2/2[idid]/4/4/4/6)",
+          "epubcfi(/6/2!/4/2/2[idid]/4/4/4/8)"
         ],
         EPUB::Searcher::Publication.search_element(@package, css: 'ol > li').collect {|result| result[:location]}.map(&:to_fragment)
       )

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: epub-parser
 version: !ruby/object:Gem::Version
-  version: 0.2.8
+  version: 0.2.9
 platform: ruby
 authors:
 - KITAITI Makoto
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2017-02-07 00:00:00.000000000 Z
+date: 2017-02-10 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake