epub-parser 0.3.2 → 0.3.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: 0061ced06336ffbf3bcdeecdd56d91dd92d7dc01
-  data.tar.gz: 0ff0efba6754a25c31550f318f60041591e67729
+SHA256:
+  metadata.gz: e95e303cf2c03479fdc655b8c4ea3c0b668b421f9d63082c40d984542312804b
+  data.tar.gz: 680b503b44bf23e82374da6afc18439762289eeaf87d58c6b0db5588d6ad59b5
 SHA512:
-  metadata.gz: 6fa942fad606d5722c09abac9caac938c3b364a3c44707940493a3aa7838ec2b6cb740bf696fbfb41c212fce44cb51d16b8ba919d4b1cd2bb72ce77a8b3f47be
-  data.tar.gz: ca69eb60e0ce44329c276eb3d33b6e3f564ac8432570fce70a0131dcbc2635a651249c2009d64417857bdd1c7bd4fd1bbb239b800b9574b1dff5329c6e5418db
+  metadata.gz: dc201c61dc61f7f56e4690c4b669bf0bee8e098f6025ceea17bc8604fb8b0b4a49a9937a4c34972d5b4584c83064fdf78d9b1831c75706c7f94ad01eebb23a8f
+  data.tar.gz: 7d08504f668f371dbef455f1498214b3f7bec305f3095638986441a2d6d8800932c329b65c7c62913f4ec126b02db892bbe10a3c22e0a316933f613d5cf7a8d7

data/.gitlab-ci.yml

@@ -1,15 +1,9 @@
 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
@@ -17,3 +11,7 @@ test:2.3:
 test:2.4:
   image: ruby:2.4
   script: bundle exec rake test
+
+test:2.5:
+  image: ruby:2.5
+  script: bundle exec rake test

data/CHANGELOG.markdown

@@ -1,6 +1,13 @@
 CHANGELOG
 =========
 
+0.3.3
+-----
+
+* [BUG FIX]Use UnpackedURI adapter for URI
+* [BREAKING CHANGE]Remove deprecated second argument from `EPUB::Parser::Publication#initialize`
+* Add `detect_encoding` keyword argument to `Publication::Package::Manifest::Item#read` and `ContentDocument::XHTML#read`
+
 0.3.2
 -----
 

data/README.markdown

@@ -1,9 +1,9 @@
 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)
+[![coverage report](https://gitlab.com/KitaitiMakoto/epub-parser/badges/master/coverage.svg)](https://gitlab.com/KitaitiMakoto/epub-parser/commits/master)
 
 INSTALLATION
 -------
@@ -134,11 +134,11 @@ Then documentation will be available in `doc` directory.
 
 REQUIREMENTS
 ------------
-* Ruby 2.2.0 or later
+* Ruby 2.3.0 or later
 * `patch` command to install Nokogiri
 * C compiler to compile Nokogiri
 
-Similar Efforts
+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.
@@ -153,6 +153,12 @@ If you find other gems, please tell me or request a pull request.
 RECENT CHANGES
 --------------
 
+### 0.3.3
+
+* [BUG FIX]Use UnpackedURI adapter for URI
+* [BREAKING CHANGE]Remove deprecated second argument from `EPUB::Parser::Publication#initialize`
+* Add `detect_encoding` keyword argument to `Publication::Package::Manifest::Item#read` and `ContentDocument::XHTML#read`
+
 ### 0.3.2
 
 * Use epub-cfi gem for EPUB CFI

data/Rakefile

@@ -5,6 +5,7 @@ require 'yard'
 require 'rdoc/task'
 require 'epub/parser/version'
 require 'zipruby'
+require 'epub/maker'
 
 task :default => :test
 task :test => 'test:default'
@@ -18,7 +19,7 @@ namespace :test do
   desc 'Build test fixture EPUB file'
   task :build => :clean do
     input_dir  = 'test/fixtures/book'
-    sh "epzip #{input_dir}"
+    EPUB::Maker.archive input_dir
     small_file = File.read("#{input_dir}/OPS/case-sensitive.xhtml")
     Zip::Archive.open "#{input_dir}.epub" do |archive|
       archive.add_buffer 'OPS/CASE-SENSITIVE.xhtml', small_file.sub('small file name', 'LARGE FILE NAME')

data/docs/Home.markdown

@@ -90,6 +90,23 @@ You are also able to find YourBook object for the first:
     ret == book # => true; this API is not good I feel... Welcome suggestion!
     # do something with your book
 
+#### Switching ZIP library
+
+EPUB Parser uses [Archive::Zip][], a pure Ruby ZIP library, by default. You can use [Zip/Ruby][], a Ruby bindings for [libzip][] if you have already installed Zip/Ruby gem by RubyGems or Bundler.
+
+Globally:
+
+    EPUB::OCF::PhysicalContainer.adapter = :Zipruby
+    book = EPUB::Parser.parse("path/to/book.epub")
+
+For each EPUB book:
+
+    book = EPUB::Parser.parse("path/to/book.epub", container_adapter: :Zipruby)
+
+[Archive::Zip]: https://github.com/javanthropus/archive-zip
+[Zip/Ruby]: https://bitbucket.org/winebarrel/zip-ruby/wiki/Home
+[libzip]: https://nih.at/libzip/
+
 Documentation
 -------------
 
@@ -146,6 +163,11 @@ Requirements
 * `patch` command to install Nokogiri
 * C compiler to compile Zip/Ruby and Nokogiri
 
+History
+-------
+
+See {file:CHANGELOG.markdown}.
+
 Note
 ----
 

data/epub-parser.gemspec

@@ -11,7 +11,7 @@ Gem::Specification.new do |s|
   s.summary     = %q{EPUB 3 Parser}
   s.description = %q{Parse EPUB 3 book loosely}
   s.license     = 'MIT'
-  s.required_ruby_version = '> 2'
+  s.required_ruby_version = '>= 2.3'
 
   s.files         = `git ls-files`.split("\n")
                     .push('test/fixtures/book/OPS/ルートファイル.opf')
@@ -36,13 +36,11 @@ Gem::Specification.new do |s|
   s.add_development_dependency 'yard'
   s.add_development_dependency 'gem-man'
   s.add_development_dependency 'ronn'
-  s.add_development_dependency 'epzip'
-  s.add_development_dependency 'racc'
-  s.add_development_dependency 'nokogiri-diff'
   s.add_development_dependency 'pretty_backtrace'
+  s.add_development_dependency 'epub-maker'
 
   s.add_runtime_dependency 'archive-zip'
-  s.add_runtime_dependency 'nokogiri', '~> 1.6'
+  s.add_runtime_dependency 'nokogiri', '>= 1.6.0', '< 1.9'
   s.add_runtime_dependency 'addressable', '>= 2.3.5'
   s.add_runtime_dependency 'rchardet', '>= 1.6.1'
   s.add_runtime_dependency 'epub-cfi'

data/lib/epub/content_document/xhtml.rb

@@ -3,9 +3,10 @@ module EPUB
     class XHTML
       attr_accessor :item
 
+      # @param [Boolean] detect_encoding See {Publication::Package::Manifest::Item#read}
       # @return [String] Returns the content string.
-      def read
-        item.read
+      def read(detect_encoding: true)
+        item.read(detect_encoding: detect_encoding)
       end
       alias raw_document read
 

data/lib/epub/ocf/physical_container.rb

@@ -5,7 +5,6 @@ require 'epub/ocf/physical_container/unpacked_uri'
 
 module EPUB
   class OCF
-    # @todo: Make thread save
     class PhysicalContainer
       class NoEntry < StandardError
         class << self

data/lib/epub/parser.rb

@@ -51,7 +51,9 @@ module EPUB
 
       @filepath = path_is_uri ? filepath : File.realpath(filepath)
       @book = create_book(options)
-      if File.directory? @filepath
+      if path_is_uri
+        @book.container_adapter = :UnpackedURI
+      elsif File.directory? @filepath
         @book.container_adapter = :UnpackedDirectory
       end
       @book.epub_file = @filepath

data/lib/epub/parser/publication.rb

@@ -18,8 +18,7 @@ module EPUB
         end
       end
 
-      def initialize(opf, rootfile=nil)
-        warn "Second argument for #{self.class}.new is deprecated" if rootfile
+      def initialize(opf)
         @doc = Nokogiri.XML(opf)
       end
 

data/lib/epub/parser/version.rb

@@ -1,5 +1,5 @@
 module EPUB
   class Parser
-    VERSION = "0.3.2"
+    VERSION = "0.3.3"
   end
 end

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

@@ -135,7 +135,16 @@ module EPUB
             Addressable::URI.unencode(full_path)
           end
 
-          def read
+          # Read content from EPUB archive
+          #
+          # @param detect_encoding [Boolean] Whether #read tries auto-detection of character encoding. The default value will become +false+ in the near future.
+          # @return [String] Content with encoding:
+          #   US-ASCII when the content is not in text format such images.
+          #   UTF-8 when the content is in text format and +detect_encoding+ is +false+.
+          #   auto-detected encoding when the content is in text format and +detect_encoding+ is +true+.
+          def read(detect_encoding: true)
+            warn "[#{self.class}##{__method__}]Autodetection of character encoding is deprecated. Pass keyword argument detect_encoding with true explicitly." if detect_encoding
+
             raw_content = manifest.package.book.container_adapter.read(manifest.package.book.epub_file, entry_name)
 
             unless media_type.start_with?('text/') or
@@ -143,17 +152,21 @@ module EPUB
                 ['application/json', 'application/javascript', 'application/ecmascript', 'application/xml-dtd'].include?(media_type)
               return raw_content
             end
-            # 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)
+            if detect_encoding
+              # 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
             else
-              warn "No encoding detected for #{entry_name}. Set to ASCII-8BIT" if $DEBUG || $VERBOSE
-              raw_content
+              raw_content.force_encoding("UTF-8");
             end
           end
 

data/lib/epub/searcher/publication.rb

@@ -82,7 +82,6 @@ module EPUB
       # @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]

data/test/test_publication.rb

@@ -337,14 +337,20 @@ class TestPublication < Test::Unit::TestCase
         end
       end
 
+      def test_read_without_detect_encoding_resturns_utf_8_string
+        epub = EPUB::Parser.parse("test/fixtures/book.epub")
+        item = epub.package.manifest["utf-8-encoded"]
+        assert_equal Encoding::UTF_8, item.read(detect_encoding: false).encoding
+      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)
+      def test_read_with_detect_encoding_detects_encoding(data)
         encoding, id = data
         epub = EPUB::Parser.parse('test/fixtures/book.epub')
         item = epub.package.manifest[id]
-        assert_equal encoding, item.read.encoding
+        assert_equal encoding, item.read(detect_encoding: true).encoding
       end
 
       def test_entry_name_returns_normalized_iri

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: epub-parser
 version: !ruby/object:Gem::Version
-  version: 0.3.2
+  version: 0.3.3
 platform: ruby
 authors:
 - KITAITI Makoto
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2017-08-08 00:00:00.000000000 Z
+date: 2018-03-02 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake
@@ -179,7 +179,7 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
-  name: epzip
+  name: pretty_backtrace
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
@@ -193,7 +193,7 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
-  name: racc
+  name: epub-maker
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
@@ -207,13 +207,13 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
-  name: nokogiri-diff
+  name: archive-zip
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
-  type: :development
+  type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
@@ -221,47 +221,25 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
-  name: pretty_backtrace
+  name: nokogiri
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: '0'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
+        version: 1.6.0
+    - - "<"
       - !ruby/object:Gem::Version
-        version: '0'
-- !ruby/object:Gem::Dependency
-  name: archive-zip
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
+        version: '1.9'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: '0'
-- !ruby/object:Gem::Dependency
-  name: nokogiri
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
+        version: 1.6.0
+    - - "<"
       - !ruby/object:Gem::Version
-        version: '1.6'
-  type: :runtime
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '1.6'
+        version: '1.9'
 - !ruby/object:Gem::Dependency
   name: addressable
   requirement: !ruby/object:Gem::Requirement
@@ -416,9 +394,9 @@ require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
-  - - ">"
+  - - ">="
     - !ruby/object:Gem::Version
-      version: '2'
+      version: '2.3'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
@@ -426,7 +404,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.6.11
+rubygems_version: 2.7.4
 signing_key: 
 specification_version: 4
 summary: EPUB 3 Parser