epub-parser 0.4.1 → 0.4.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: db9d1db7323d581efa9dd08265ed17adc0aff3c176ef87c783968c99dc8b14b2
-  data.tar.gz: c8eed1c594124b4bf9ba8bed18562840a9199c4e8dcac234e0cbc615601c16a5
+  metadata.gz: 0d2b5eaf4a6fef5b3d223872db25abb9a087c3ba4e3aabc8dae4f5e854313e42
+  data.tar.gz: 94f742b2babd8fb916ff2ac38af7e6989fdb7ffad4da0be72ffefbb0015464d4
 SHA512:
-  metadata.gz: cb742185c933cfdbee595d9d777cef56a928933838e66d68383a1cdddb330b28ce514808ef292d1d90d5885957ff0cd2e8bd7905d0319b9e8f4548bb4c23fe17
-  data.tar.gz: 4fc71e9d5a20a1a8e1c610c8c0dd389639f4fe9ad01212944f5a11ab1e29be980bb296049d3f99228db9e595183911e13cb22c6a30e6437d5aca8f6ad71621cd
+  metadata.gz: 6f79e57d8876ddaad3a43ac633e09e313926272e9d028b33075decb2ca6180c22ca16698d311be958834f83c01c67ce976e53e34a63ef05fa6f326e47a994222
+  data.tar.gz: f21296e38086c227e4cb2423e3961e80099404b43a9a13327ddd350e1642152ff19bb08f23d4b21b4bc4873d2fb0bc9ed20cd8febfbbcb6f51e4c4cafb5a51dd

data/.gitlab-ci.yml

@@ -7,7 +7,7 @@ before_script:
 
 test:2.3:
   image: ruby:2.3
-  script: bundle exec rake test XML_BACKEND=REXML 2>/dev/null && bundle exec rake test XML_BACKEND=Oga 2>/dev/null && bundle exec rake test XML_BACKEND=Nokogiri
+  script: bundle exec rake test XML_BACKEND=REXML 2>/dev/null && bundle exec rake test XML_BACKEND=Oga 2>/dev/null && bundle exec rake test XML_BACKEND=Nokogiri 2>/dev/null
   except:
     - tags
   cache:
@@ -17,7 +17,7 @@ test:2.3:
 
 test:2.4:
   image: ruby:2.4
-  script: bundle exec rake test XML_BACKEND=REXML 2>/dev/null && bundle exec rake test XML_BACKEND=Oga 2>/dev/null && bundle exec rake test XML_BACKEND=Nokogiri
+  script: bundle exec rake test XML_BACKEND=REXML 2>/dev/null && bundle exec rake test XML_BACKEND=Oga 2>/dev/null && bundle exec rake test XML_BACKEND=Nokogiri 2>/dev/null
   except:
     - tags
   cache:
@@ -27,7 +27,7 @@ test:2.4:
 
 test:2.5:
   image: ruby:2.5
-  script: bundle exec rake test XML_BACKEND=REXML 2>/dev/null && bundle exec rake test XML_BACKEND=Oga 2>/dev/null && bundle exec rake test XML_BACKEND=Nokogiri
+  script: bundle exec rake test XML_BACKEND=REXML 2>/dev/null && bundle exec rake test XML_BACKEND=Oga 2>/dev/null && bundle exec rake test XML_BACKEND=Nokogiri 2>/dev/null
   except:
     - tags
   artifacts:
@@ -40,7 +40,7 @@ test:2.5:
 
 test:2.6:
   image: ruby:2.6
-  script: bundle exec rake test XML_BACKEND=REXML 2>/dev/null && bundle exec rake test XML_BACKEND=Oga 2>/dev/null && bundle exec rake test XML_BACKEND=Nokogiri
+  script: bundle exec rake test XML_BACKEND=REXML 2>/dev/null && bundle exec rake test XML_BACKEND=Oga 2>/dev/null && bundle exec rake test XML_BACKEND=Nokogiri 2>/dev/null
   except:
     - tags
   cache:
@@ -48,9 +48,19 @@ test:2.6:
     paths:
       - deps
 
+test:2.7:
+  image: ruby:2.7
+  script: bundle exec rake test XML_BACKEND=REXML 2>/dev/null && bundle exec rake test XML_BACKEND=Oga 2>/dev/null && bundle exec rake test XML_BACKEND=Nokogiri 2>/dev/null
+  except:
+    - tags
+  cache:
+    key: ruby:2.7
+    paths:
+      - deps
+
 pages:
   stage: deploy
-  image: ruby:2.6
+  image: ruby:2.7
   dependencies:
     - test:2.6
   script:
@@ -63,6 +73,6 @@ pages:
   only:
     - master
   cache:
-    key: ruby:2.6
+    key: ruby:2.7
     paths:
       - deps

data/CHANGELOG.adoc

@@ -1,5 +1,12 @@
 = CHANGELOG
 
+== 0.4.2
+
+* [BUG FIX]Fix a bug that epub-cover refers out of scope variable
+
+* [BUG FIX]Fix a bug that `epubinfo` command with `--words` or `--chars` option causes load error if there is not Nokogiri in environment
+* [BUG FIX]Fix a bug that REXML::Element#content ignores descendant nodes
+
 == 0.4.1
 
 * Add Oga backend for XML document

data/README.adoc

@@ -174,6 +174,13 @@ If you find other gems, please tell me or request a pull request.
 
 == RECENT CHANGES
 
+=== 0.4.2
+
+* [BUG FIX]Fix a bug that epub-cover refers out of scope variable
+
+* [BUG FIX]Fix a bug that `epubinfo` command with `--words` or `--chars` option causes load error if there is not Nokogiri in environment
+* [BUG FIX]Fix a bug that REXML::Element#content ignores descendant nodes
+
 === 0.4.1
 
 * Add Oga backend for XML document
@@ -182,18 +189,6 @@ If you find other gems, please tell me or request a pull request.
 
 * [BUG FIX]Make epub:type a Set
 
-=== 0.3.9
-
-* [BUG FIX]Set {EPUB::Metadata::DCMES#lang} properly from xml:lang attribute
-* Change default XML backend from REXML to Nokogiri
-
-=== 0.3.8
-
-* [REFACTORING]Add {EPUB::Parser::NokogiriAttributeWithPrefix} and use `Nokogiri::XML::Node#attribute_with_prefix` instead of `EPUB::Parser::Utils#extract_attribute`
-* Set default value for detect_encoding argument for {EPUB::Publication::Package::Manifest::Item#read} to false
-* Make XML library switchable between REXML and Nokogiri
-* Make REXML a default XML backend
-
 See {file:CHANGELOG.adoc} for older changelogs and details.
 
 == TODOS

data/Rakefile

@@ -3,7 +3,6 @@ require 'rake/testtask'
 require 'rubygems/tasks'
 require 'yard'
 require 'rdoc/task'
-require 'epub/parser/version'
 require 'archive/zip'
 require 'epub/maker'
 require "tmpdir"
@@ -19,6 +18,8 @@ namespace :test do
 
   file "test/fixtures/book.epub" => "test/fixtures/book" do |task|
     EPUB::Maker.archive task.source
+    # We cannot include "CASE-SENSITIVE.xhtml" in Git repository because
+    # macOS remove it or case-sensitive.xhtml from file system.
     small_file = File.read("#{task.source}/OPS/case-sensitive.xhtml")
     Dir.mktmpdir do |dir|
       upcase_file_path = File.join(dir, "CASE-SENSITIVE.xhtml")

data/bin/epub-cover

@@ -32,7 +32,7 @@ EOB
   end
   error "output not a directory" if options["output"] && !File.directory?(options["output"])
   cover_image = EPUB::Parser.parse(path).cover_image
-  error "cover image not found" unless cover_image
+  error "cover image not found", option_parser.program_name, option_parser.help unless cover_image
   path = File.basename(cover_image.href.to_s)
   path = File.join(options["output"], path) if options["output"]
   File.write path, cover_image.read
@@ -41,10 +41,12 @@ EOB
   $stderr.puts ""
 end
 
-def error(message)
+def error(message, program_name, help)
   $stderr.puts "Error: #{message}"
   $stderr.puts ""
-  $stderr.puts option_parser.help
+  $stderr.puts program_name
+  $stderr.puts "=" * program_name.length
+  $stderr.puts help
   abort
 end
 

data/bin/epub-open

@@ -29,6 +29,6 @@ unless File.readable? file
     file = uri
   end
 end
-EPUB::Parser.parse(file, :book => self)
+EPUB::Parser.parse(file, book: self)
 $stderr.puts "Enter \"exit\" to exit #{shell}"
 shell.start

data/bin/epubinfo

@@ -1,6 +1,8 @@
 require 'optparse'
 require 'epub/parser'
 
+using EPUB::Parser::XMLDocument::Refinements
+
 options = {:format => :line}
 opt = OptionParser.new do |opt|
   opt.banner = <<EOB
@@ -51,12 +53,13 @@ end
 
 counts = {:chars => 0, :words => 0}
 if options[:words] or options[:chars]
+  namespaces = {"xhtml" => "http://www.w3.org/1999/xhtml"}
   book.resources.select(&:xhtml?).each do |xhtml|
     begin
-      doc = xhtml.content_document.nokogiri
-      body = doc.search('body').first
-      content = body.content
+      doc = EPUB::Parser::XMLDocument.new(xhtml.read)
+      body = doc.each_element_by_xpath('//xhtml:body', namespaces).first
       if body
+        content = body.content
         counts[:words] += content.scan(/\S+/).length
         counts[:chars] += content.gsub(/\r|\n/, '').length
       end

data/docs/Home.adoc

@@ -89,7 +89,7 @@ end
 
 book = EPUB::Parser.parse(
   'uploaded-book.epub',
-  :class => YourBook # *************** pass YourBook class
+  class: YourBook # *************** pass YourBook class
 )
 book.instance_of? YourBook # => true
 book.required = 'value for required field'
@@ -110,7 +110,7 @@ You are also able to find YourBook object for the first:
 book = YourBook.find params[:id]
 ret = EPUB::Parser.parse(
   'uploaded-book.epub',
-  :book => book # ******************* pass your book instance
+  book: book # ******************* pass your book instance
 ) # => book
 ret == book # => true; this API is not good I feel... Welcome suggestion!
 # do something with your book

data/lib/epub/parser.rb

@@ -12,14 +12,14 @@ module EPUB
       # 
       # @example
       #   class MyBook
-      #     include EPUB
+      #     include EPUB::Book::Feature
       #   end
       #   book = MyBook.new
-      #   parsed_book = EPUB::Parser.parse('path/to/book.epub', :book => book) # => #<MyBook:0x000000019760e8 @epub_file=..>
+      #   parsed_book = EPUB::Parser.parse('path/to/book.epub', book: book) # => #<MyBook:0x000000019760e8 @epub_file=..>
       #   parsed_book.equal? book # => true
       # 
       # @example
-      #   book = EPUB::Parser.parse('path/to/book.epub', :class => MyBook) # => #<MyBook:0x000000019b0568 @epub_file=...>
+      #   book = EPUB::Parser.parse('path/to/book.epub', class: MyBook) # => #<MyBook:0x000000019b0568 @epub_file=...>
       #   book.instance_of? MyBook # => true
       # 
       # @param [String] filepath
@@ -35,21 +35,21 @@ module EPUB
       #   When option :book passed, returns the same object whose attributes about EPUB are set.
       #   When option :class passed, returns the instance of the class.
       #   Otherwise returns {EPUB::Book} object.
-      def parse(filepath, **options)
-        new(filepath, options).parse
+      def parse(filepath, container_adapter: nil, book: nil, initialize_with: nil, **options)
+        new(filepath, container_adapter: container_adapter, book: book, initialize_with: initialize_with, **options).parse
       end
     end
 
-    def initialize(filepath, **options)
-      path_is_uri = (options[:container_adapter] == EPUB::OCF::PhysicalContainer::UnpackedURI or
-                     options[:container_adapter] == :UnpackedURI or
+    def initialize(filepath, container_adapter: nil, book: nil, initialize_with: nil, **options)
+      path_is_uri = (container_adapter == EPUB::OCF::PhysicalContainer::UnpackedURI or
+                     container_adapter == :UnpackedURI or
                      EPUB::OCF::PhysicalContainer.adapter == EPUB::OCF::PhysicalContainer::UnpackedURI)
 
       raise "File #{filepath} not found" if
         !path_is_uri and !File.exist?(filepath)
 
       @filepath = path_is_uri ? filepath : File.realpath(filepath)
-      @book = create_book(options)
+      @book = create_book(book: book, initialize_with: initialize_with, **options)
       if path_is_uri
         @book.container_adapter = :UnpackedURI
       elsif File.directory? @filepath
@@ -77,13 +77,13 @@ module EPUB
 
     private
 
-    def create_book(params)
+    def create_book(book: nil, initialize_with: nil, **params)
       case
-      when params[:book]
-        params[:book]
+      when book
+        book
       when params[:class]
-        if params[:initialize_with]
-          params[:class].new params[:initialize_with]
+        if initialize_with
+          params[:class].new initialize_with
         else
           params[:class].new
         end

data/lib/epub/parser/version.rb

@@ -1,5 +1,5 @@
 module EPUB
   class Parser
-    VERSION = "0.4.1"
+    VERSION = "0.4.2"
   end
 end

data/lib/epub/parser/xml_document/refinements/rexml.rb

@@ -27,7 +27,14 @@ module EPUB
             alias namespace_uri namespace
 
             def content
-              texts.join
+              each_child.inject("") {|text, node|
+                case node.node_type
+                when :document, :element
+                  text << node.content
+                when :text
+                  text << node.value
+                end
+              }
             end
           end
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: epub-parser
 version: !ruby/object:Gem::Version
-  version: 0.4.1
+  version: 0.4.2
 platform: ruby
 authors:
 - KITAITI Makoto
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2019-12-06 00:00:00.000000000 Z
+date: 2020-01-11 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake
@@ -447,7 +447,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.0.3
+rubygems_version: 3.1.2
 signing_key: 
 specification_version: 4
 summary: EPUB 3 Parser