epub-parser 0.4.5 → 0.4.6

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 25b4d1e1300bee0055f6bf79b79c7c3404e1a18752a558160ef4978c38cd1e46
-  data.tar.gz: e467ba867b6fd5e9959e35bdec9c896f2c361f7cceb93fcb6c42539f55213ecc
+  metadata.gz: 2373a741e554fee584d9b3562e655a33e34420c6dd335ffc32f041da5507c1d5
+  data.tar.gz: 2224f8bf83deed854f8181f791bf0e5e58b0feaa40e39a5d94b754acef6f841c
 SHA512:
-  metadata.gz: c1af1a66faccb0812659841be637d51e0e70cbf41d2fd3672287dded4bf147adfa131eba6b4297eadb108d4aa7c6f1414ad932861b3963ff6cab9a235d4b9b78
-  data.tar.gz: 6561f63c30009f4e333e99189966aeeceb6c8c190b541d2c0b12711c565a8cb51bcaa1ee37d3623806693981250739371b9006a9e7d8776343b94b5f47c4f65e
+  metadata.gz: 5c9eeed9058f10661e27e42ad1366d831ebdebe06879b80c8e44114d0ea74de8f2b15e2909d9602a7deacc351ef1074cf37c5a2e7f4592a141ef2b336474efeb
+  data.tar.gz: c2b8c9f85ed82c2720816b80d393884be55c258084b89723adc84cdf490d6e721926df931ff660bb0d06234650018f09f8ef85604cacae5f4b0575c6c691168f

data/.gitlab-ci.yml

@@ -58,6 +58,16 @@ test:2.7:
     paths:
       - deps
 
+test:3.0:
+  image: ruby:3.0-rc
+  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:3.0
+    paths:
+      - deps
+
 pages:
   stage: deploy
   image: ruby:2.7

data/CHANGELOG.adoc

@@ -1,8 +1,17 @@
 = CHANGELOG
 
+== 0.4.7
+
+* Remove version specification from Nokogiri to migrate to Ruby 3.1
+
+== 0.4.6
+
+* [BUG FIX]Prevent epubinfo tool raise exception when no nav elements
+* Tiny modifcation on Zip archive manipulation
+
 == 0.4.5
 
-[BUG FIX]Handle the case EPUB path is a Pathname
+* [BUG FIX]Handle the case EPUB path is a Pathname
 
 == 0.4.4
 

data/README.adoc

@@ -176,9 +176,18 @@ If you find other gems, please tell me or request a pull request.
 
 == RECENT CHANGES
 
+=== 0.4.7
+
+* Remove version specification from Nokogiri to migrate to Ruby 3.1
+
+=== 0.4.6
+
+* [BUG FIX]Prevent epubinfo tool raise exception when no nav elements
+* Tiny modifcation on Zip archive manipulation
+
 === 0.4.5
 
-[BUG FIX]Handle the case EPUB path is a Pathname
+* [BUG FIX]Handle the case EPUB path is a Pathname
 
 === 0.4.4
 

data/bin/epubinfo

@@ -65,7 +65,8 @@ data.merge!(book.metadata.to_h)
 data['modified'] = book.modified
 data['unique identifier'] = book.metadata.unique_identifier
 data['epub version'] = book.package.version
-data["navigations"] = book.manifest.navs.first&.content_document.navigations.collect(&:type).join(", ")
+nav = book.manifest.navs.first
+data["navigations"] = nav ? nav.book.manifest.navs.first&.content_document&.navigations&.collect(&:type)&.join(", ") : []
 
 data.each_pair do |(key, value)|
   data[key] = value.respond_to?(:join) ? value.join(", ") : value.to_s
@@ -99,12 +100,17 @@ if options[:format] == :line
     if options[key]
       puts ""
       puts "=== #{name} ==="
-      nav = book.manifest.nav.content_document.navigations.find {|nav| nav.type == key.to_s.sub("-", "_")}
-      if nav
-        nav.traverse do |item, depth|
-          text = item.text || "(No heading)"
-          text += "(#{item.types.sort.join(', ')})" unless item.types.empty?
-          puts "#{'  ' * depth}#{text}"
+      nav_item = book.manifest.nav
+      if nav_item
+        nav = nav_item.content_document.navigations.find {|nav| nav.type == key.to_s.sub("-", "_")}
+        if nav
+          nav.traverse do |item, depth|
+            text = item.text || "(No heading)"
+            text += "(#{item.types.sort.join(', ')})" unless item.types.empty?
+            puts "#{'  ' * depth}#{text}"
+          end
+        else
+          puts "(No #{name})"
         end
       else
         puts "(No #{name})"

data/bin/epubtotext

@@ -0,0 +1,39 @@
+require "optparse"
+require "epub/parser"
+
+using EPUB::Parser::XMLDocument::Refinements
+
+def main(argv)
+  option_parser = OptionParser.new {|opt|
+    opt.version = EPUB::Parser::VERSION
+    opt.banner = <<EOB
+Extracts text from EPUB and output
+
+Usage: #{opt.program_name} EPUBFILE
+EOB
+  }
+  options = option_parser.getopts(argv)
+  path = argv.shift
+  raise "Specify EPUBFILE" unless path
+  EPUB::Parser.parse(path).each_page_on_spine do |page|
+    unless page.xhtml?
+      $stderr.puts "Cannot parse non-XHTML document(#{page.media_type}): #{page.entry_name}"
+      next
+    end
+    doc = EPUB::Parser::XMLDocument.new(page.read)
+    body = doc.each_element_by_xpath("//xhtml:body", EPUB::NAMESPACES).first
+    unless body
+      $stderr.puts "body element doesn't exist in #{page.entry_name}"
+      next
+    end
+    puts body.content
+    # handle spaces
+    # handle img@alt
+  end
+rescue => err
+  $stderr.puts "Error: #{err}"
+  $stderr.puts
+  abort option_parser.help
+end
+
+main(ARGV)

data/docs/Home.adoc

@@ -118,7 +118,7 @@ ret == book # => true; this API is not good I feel... Welcome suggestion!
 
 ==== Switching XML Library
 
-EPUB Parser tries to load https://gitlab.com/yorickpeterse/oga[Oga] a fast XML parser at first. If Oga is not available, then it tries https://www.nokogiri.org/[Nokogiri], a Ruby bindings for http://xmlsoft.org/[Libxml2] and http://xmlsoft.org/XSLT/[Libxslt] and more. If both are not available, it fallbacks to https://ruby-doc.org/stdlib-2.5.3/libdoc/rexml/rdoc/index.html[REXML], a standard-bundled library. You can also specify REXML explicitly:
+EPUB Parser tries to load https://www.nokogiri.org/[Nokogiri], a Ruby bindings for http://xmlsoft.org/[Libxml2] and http://xmlsoft.org/XSLT/[Libxslt] and more at first. If Nokogiri is not available, then it tries https://gitlab.com/yorickpeterse/oga[Oga] a fast XML parser. If both are not available, it fallbacks to https://github.com/ruby/rexml/[REXML], a standard-bundled library. You can also specify REXML explicitly:
 
 ----
 EPUB::Parser::XMLDocument.backend = :REXML

data/epub-parser.gemspec

@@ -40,10 +40,12 @@ Gem::Specification.new do |s|
   s.add_development_dependency 'pretty_backtrace'
   s.add_development_dependency 'epub-maker'
   s.add_development_dependency 'asciidoctor'
-  s.add_development_dependency 'nokogiri', '>= 1.6.0', '< 1.11'
+  s.add_development_dependency 'nokogiri'
   s.add_development_dependency 'oga', '>= 2.16'
+  s.add_development_dependency 'packnga'
 
   s.add_runtime_dependency 'archive-zip'
+  s.add_runtime_dependency 'rexml'
   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/ocf/physical_container/archive_zip.rb

@@ -44,7 +44,7 @@ module EPUB
               end
             end
 
-            raise NoEntry
+            raise NoEntry, "Entry not found: #{path_name}"
           else
             open {|container| container.read(path_name)}
           end

data/lib/epub/ocf/physical_container.rb

@@ -45,7 +45,7 @@ module EPUB
 
         def read(container_path, path_name)
           open(container_path) {|container|
-            container.read(path_name)
+            container.read(path_name.to_s)
           }
         end
 

data/lib/epub/parser/version.rb

@@ -1,5 +1,5 @@
 module EPUB
   class Parser
-    VERSION = "0.4.5"
+    VERSION = "0.4.6"
   end
 end

data/lib/epub/searcher/publication.rb

@@ -8,7 +8,7 @@ module EPUB
 
       class << self
         def search_text(package, word, **options)
-          new(package).search_text(word, options)
+          new(package).search_text(word, **options)
         end
 
         def search_element(package, css: nil, xpath: nil, namespaces: {})

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: epub-parser
 version: !ruby/object:Gem::Version
-  version: 0.4.5
+  version: 0.4.6
 platform: ruby
 authors:
 - KITAITI Makoto
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2020-01-29 00:00:00.000000000 Z
+date: 2021-12-26 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake
@@ -226,20 +226,14 @@ dependencies:
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 1.6.0
-    - - "<"
-      - !ruby/object:Gem::Version
-        version: '1.11'
+        version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 1.6.0
-    - - "<"
-      - !ruby/object:Gem::Version
-        version: '1.11'
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: oga
   requirement: !ruby/object:Gem::Requirement
@@ -254,6 +248,20 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '2.16'
+- !ruby/object:Gem::Dependency
+  name: packnga
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: archive-zip
   requirement: !ruby/object:Gem::Requirement
@@ -268,6 +276,20 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
+- !ruby/object:Gem::Dependency
+  name: rexml
+  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'
 - !ruby/object:Gem::Dependency
   name: addressable
   requirement: !ruby/object:Gem::Requirement
@@ -317,6 +339,7 @@ executables:
 - epub-cover
 - epub-open
 - epubinfo
+- epubtotext
 extensions: []
 extra_rdoc_files: []
 files:
@@ -332,6 +355,7 @@ files:
 - bin/epub-cover
 - bin/epub-open
 - bin/epubinfo
+- bin/epubtotext
 - docs/AggregateContentsFromWeb.markdown
 - docs/EpubCover.adoc
 - docs/EpubOpen.markdown
@@ -448,7 +472,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.1.2
+rubygems_version: 3.3.3
 signing_key: 
 specification_version: 4
 summary: EPUB 3 Parser