henkei 1.21.0 → 1.23.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: dcd47b09b6fe957b09566d905fa0f1800baa3bd385bf5ecb57996f5d5d49d531
-  data.tar.gz: 961c762ff76e4be1356f5d3ac8af80385a2f811d4099afe98b461228b6bce374
+  metadata.gz: 7ee68ad858a48fb82526d230d1d49788be9eee8e0d27562276fd6b18c11e4923
+  data.tar.gz: ebedf682b5ef4f979d02eb6cec23d4bdbdf581b958873dc80469fb0bfa15560d
 SHA512:
-  metadata.gz: 7017ca74a03708360c2e89decec78eff6e681f61819398374ed85a456674fedcf6e5eedf83008d224686c4e716d7e9228b2f54521862e44bbd4d98f50729a76d
-  data.tar.gz: 6b2f718bbea1af08e0ee4ed96ed84b8d0bd423ab0596f8d9d09e7a32d11a242188edd7f48c6df46ce52b4e28964c1ca40642318ef4f48b0ffc5aea999f844371
+  metadata.gz: 724b7788968a98cf2120912eccfd49b761b25b01666f20f58334eedec44537d9b2238006df3f3fee26f048e54d36213d168152d6809b25466d41ae055566add6
+  data.tar.gz: e867f325855b63232d86ab1208c6c35c4b71ad620fab893451f33c1590eaaf3622e72ea5ea71ce60d7486a3bffac9c4f54829cc30683cbe8af20b3c969b4745f

data/.rubocop.yml

@@ -1,10 +1,31 @@
+AllCops:
+  NewCops: enable
+
+Layout/EmptyLinesAroundAttributeAccessor:
+  Enabled: true
+
+Layout/LineLength:
+  Max: 120
+
+Layout/SpaceAroundMethodCallOperator:
+  Enabled: true
+
+Lint/DeprecatedOpenSSLConstant:
+  Enabled: true
+
+Lint/MixedRegexpCaptureTypes:
+  Enabled: true
+
+Lint/RaiseException:
+  Enabled: true
+
+Lint/StructNewOverride:
+  Enabled: true
+
 Metrics/BlockLength:
   Exclude:
     - 'spec/**/*'
 
-Metrics/LineLength:
-  Max: 120
-
 Metrics/MethodLength:
   Max: 15
 
@@ -13,3 +34,24 @@ Style/ClassVars:
 
 Style/DoubleNegation:
   Enabled: false
+
+Style/ExponentialNotation:
+  Enabled: true
+
+Style/HashEachMethods:
+  Enabled: true
+
+Style/HashTransformKeys:
+  Enabled: true
+
+Style/HashTransformValues:
+  Enabled: true
+
+Style/RedundantRegexpCharacterClass:
+  Enabled: true
+
+Style/RedundantRegexpEscape:
+  Enabled: true
+
+Style/SlicingWithRange:
+  Enabled: true

data/.travis.yml

@@ -1,13 +1,17 @@
 env:
   global:
     - CC_TEST_REPORTER_ID=bb96c1ff9dc66724c38fb4eb54486dd72dc88a7fd6e727c034b9cf8d747d069e
+  jobs:
+    - INCLUDE_RAILS=false
+    - INCLUDE_RAILS=true
 
 language: ruby
 rvm:
-  - 2.3
   - 2.4
   - 2.5
   - 2.6
+  - 2.7
+  - 3.0
 
 before_install:
   - gem update bundler
@@ -22,7 +26,7 @@ before_script:
   - ./cc-test-reporter before-build
 
 script:
-  - rubocop
+  - bundle exec rubocop
   - bundle exec rspec
 
 after_script:

data/bin/console

@@ -0,0 +1,8 @@
+#!/usr/bin/env ruby
+# frozen_string_literal: true
+
+require 'bundler/setup'
+require 'henkei'
+
+require 'irb'
+IRB.start

data/henkei.gemspec

@@ -15,6 +15,7 @@ Gem::Specification.new do |spec|
                        '(.doc, .docx, .pages, .odt, .rtf, .pdf) using Apache Tika toolkit'
   spec.homepage      = 'http://github.com/abrom/henkei'
   spec.license       = 'MIT'
+  spec.required_ruby_version = ['>= 2.4.0', '< 3.1.0']
 
   spec.files         = `git ls-files`.split("\n")
   spec.executables   = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
@@ -22,9 +23,10 @@ Gem::Specification.new do |spec|
   spec.require_paths = ['lib']
 
   spec.add_runtime_dependency 'json', '>= 1.8', '< 3'
-  spec.add_runtime_dependency 'mime-types', '>= 1.23', '< 4'
+  spec.add_runtime_dependency 'mini_mime', '>= 0.1.1', '< 2'
 
   spec.add_development_dependency 'bundler', '~> 2.0'
+  spec.add_development_dependency 'rails', '~> 5.0'
   spec.add_development_dependency 'rake', '~> 12.3'
   spec.add_development_dependency 'rspec', '~> 3.7'
   spec.add_development_dependency 'rubocop', '~> 0.71'

data/lib/henkei.rb

@@ -2,25 +2,48 @@
 
 require 'henkei/version'
 require 'henkei/yomu'
+require 'henkei/configuration'
 
 require 'net/http'
-require 'mime/types'
+require 'mini_mime'
+
+# require 'mime/types' if available
+begin
+  require 'mime/types'
+rescue LoadError
+  nil
+end
+
 require 'time'
 require 'json'
 
 require 'socket'
 require 'stringio'
 
+require 'open3'
+
 # Read text and metadata from files and documents using Apache Tika toolkit
 class Henkei # rubocop:disable Metrics/ClassLength
   GEM_PATH = File.dirname(File.dirname(__FILE__))
-  JAR_PATH = File.join(Henkei::GEM_PATH, 'jar', 'tika-app-1.21.jar')
+  JAR_PATH = File.join(Henkei::GEM_PATH, 'jar', 'tika-app-1.23.jar')
   CONFIG_PATH = File.join(Henkei::GEM_PATH, 'jar', 'tika-config.xml')
   DEFAULT_SERVER_PORT = 9293 # an arbitrary, but perfectly cromulent, port
 
   @@server_port = nil
   @@server_pid = nil
 
+  def self.mimetype(content_type)
+    if Henkei.configuration.mime_library == 'mime/types' && defined?(MIME::Types)
+      warn '[DEPRECATION] `mime/types` is deprecated. Please use `mini_mime` instead.'\
+        ' Use Henkei.configure and assign "mini_mime" to `mime_library`.'
+      MIME::Types[content_type].first
+    else
+      MiniMime.lookup_by_content_type(content_type).tap do |object|
+        object.define_singleton_method(:extensions) { [extension] }
+      end
+    end
+  end
+
   # Read text or metadata from a data buffer.
   #
   #   data = File.read 'sample.pages'
@@ -34,7 +57,7 @@ class Henkei # rubocop:disable Metrics/ClassLength
     when :text then result
     when :html then result
     when :metadata then JSON.parse(result)
-    when :mimetype then MIME::Types[JSON.parse(result)['Content-Type']].first
+    when :mimetype then Henkei.mimetype(JSON.parse(result)['Content-Type'])
     end
   end
 
@@ -110,9 +133,8 @@ class Henkei # rubocop:disable Metrics/ClassLength
   def mimetype
     return @mimetype if defined? @mimetype
 
-    type = metadata['Content-Type'].is_a?(Array) ? metadata['Content-Type'].first : metadata['Content-Type']
-
-    @mimetype = MIME::Types[type].first
+    content_type = metadata['Content-Type'].is_a?(Array) ? metadata['Content-Type'].first : metadata['Content-Type']
+    @mimetype = Henkei.mimetype(content_type)
   end
 
   # Returns +true+ if the Henkei document was specified using a file path.
@@ -184,7 +206,7 @@ class Henkei # rubocop:disable Metrics/ClassLength
   def self.server(type, custom_port = nil)
     @@server_port = custom_port || DEFAULT_SERVER_PORT
 
-    @@server_pid = Process.spawn tika_command(type, true)
+    @@server_pid = Process.spawn(*tika_command(type, server: true))
     sleep(2) # Give the server 2 seconds to spin up.
     @@server_pid
   end
@@ -217,18 +239,14 @@ class Henkei # rubocop:disable Metrics/ClassLength
   # Provide the path to the Java binary
   #
   def self.java_path
-    ENV['JAVA_HOME'] ? ENV['JAVA_HOME'] + '/bin/java' : 'java'
+    ENV['JAVA_HOME'] ? "#{ENV['JAVA_HOME']}/bin/java" : 'java'
   end
   private_class_method :java_path
 
   # Internal helper for calling to Tika library directly
   #
   def self.client_read(type, data)
-    IO.popen tika_command(type), 'r+' do |io|
-      io.write data
-      io.close_write
-      io.read
-    end
+    Open3.capture2(*tika_command(type), stdin_data: data, binmode: true).first
   end
   private_class_method :client_read
 
@@ -261,23 +279,22 @@ class Henkei # rubocop:disable Metrics/ClassLength
 
   # Internal helper for building the Java command to call Tika
   #
-  def self.tika_command(type, server = false)
-    command = ["#{java_path} -Djava.awt.headless=true -jar #{Henkei::JAR_PATH} --config=#{Henkei::CONFIG_PATH}"]
-    command << "--server --port #{@@server_port}" if server
-    command << switch_for_type(type)
-    command.join ' '
+  def self.tika_command(type, server: false)
+    command = [java_path, '-Djava.awt.headless=true', '-jar', Henkei::JAR_PATH, "--config=#{Henkei::CONFIG_PATH}"]
+    command += ['--server', '--port', @@server_port.to_s] if server
+    command + switch_for_type(type)
   end
   private_class_method :tika_command
 
   # Internal helper for building the Java command to call Tika
   #
   def self.switch_for_type(type)
-    case type
-    when :text then '-t'
-    when :html then '-h'
-    when :metadata then '-m -j'
-    when :mimetype then '-m -j'
-    end
+    {
+      text: ['-t'],
+      html: ['-h'],
+      metadata: %w[-m -j],
+      mimetype: %w[-m -j]
+    }[type]
   end
   private_class_method :switch_for_type
 end

data/lib/henkei/configuration.rb

@@ -0,0 +1,21 @@
+# frozen_string_literal: true
+
+# Henkei monkey patch for configuration support
+class Henkei
+  def self.configuration
+    @configuration ||= Configuration.new
+  end
+
+  def self.configure
+    yield(configuration)
+  end
+
+  # Handle Henkei configuration
+  class Configuration
+    attr_accessor :mime_library
+
+    def initialize
+      @mime_library = 'mime/types'
+    end
+  end
+end

data/lib/henkei/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 class Henkei
-  VERSION = '1.21.0'
+  VERSION = '1.23.3'
 end

data/spec/henkei_spec.rb

@@ -1,8 +1,11 @@
 # frozen_string_literal: true
 
-require 'helper.rb'
+require 'helper'
 require 'henkei'
 
+# Some of the tests have been known to fail in weird and wonderful ways when `rails` is included
+require 'rails' if ENV['INCLUDE_RAILS'] == 'true'
+
 describe Henkei do
   let(:data) { File.read 'spec/samples/sample.docx' }
 
@@ -40,6 +43,16 @@ describe Henkei do
       )
       expect(mimetype.extensions).to include 'docx'
     end
+
+    context 'when passing in the `pipe-error.png` test file' do
+      let(:data) { File.read 'spec/samples/pipe-error.png' }
+
+      it 'returns an empty result' do
+        text = Henkei.read :text, data
+
+        expect(text).to eq ''
+      end
+    end
   end
 
   describe '.new' do
@@ -129,6 +142,23 @@ describe Henkei do
     specify '#metadata reads metadata' do
       expect(henkei.metadata['Content-Type']).to eq %w[application/vnd.apple.pages application/vnd.apple.pages]
     end
+
+    context 'when passing in the `pipe-error.png` test file' do
+      let(:henkei) { Henkei.new 'spec/samples/pipe-error.png' }
+
+      it '#text returns an empty result' do
+        expect(henkei.text).to eq ''
+      end
+
+      it '#html returns an empty body' do
+        expect(henkei.html).to include '<body/>'
+        expect(henkei.html).to include '<meta name="tiff:ImageWidth" content="792"/>'
+      end
+
+      it '#mimetype returns `image/png`' do
+        expect(henkei.mimetype.content_type).to eq 'image/png'
+      end
+    end
   end
 
   context 'initialized with a given URI' do
@@ -157,6 +187,18 @@ describe Henkei do
     end
   end
 
+  context 'when source is a remote PDF' do
+    let(:henkei) { Henkei.new 'https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf' }
+
+    specify '#text reads text' do
+      expect(henkei.text).to include 'Dummy PDF file'
+    end
+
+    specify '#metadata reads metadata' do
+      expect(henkei.metadata['Content-Type']).to eq 'application/pdf'
+    end
+  end
+
   context 'working as server mode' do
     specify '#starts and kills server' do
       begin

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: henkei
 version: !ruby/object:Gem::Version
-  version: 1.21.0
+  version: 1.23.3
 platform: ruby
 authors:
 - Erol Fornoles
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2019-06-20 00:00:00.000000000 Z
+date: 2021-02-02 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: json
@@ -32,25 +32,25 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '3'
 - !ruby/object:Gem::Dependency
-  name: mime-types
+  name: mini_mime
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: '1.23'
+        version: 0.1.1
     - - "<"
       - !ruby/object:Gem::Version
-        version: '4'
+        version: '2'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: '1.23'
+        version: 0.1.1
     - - "<"
       - !ruby/object:Gem::Version
-        version: '4'
+        version: '2'
 - !ruby/object:Gem::Dependency
   name: bundler
   requirement: !ruby/object:Gem::Requirement
@@ -65,6 +65,20 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '2.0'
+- !ruby/object:Gem::Dependency
+  name: rails
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '5.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '5.0'
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
@@ -125,7 +139,8 @@ description: Read text and metadata from files and documents using Apache Tika t
 email:
 - erol.fornoles@gmail.com
 - a.bromwich@gmail.com
-executables: []
+executables:
+- console
 extensions: []
 extra_rdoc_files: []
 files:
@@ -138,14 +153,17 @@ files:
 - NOTICE.txt
 - README.md
 - Rakefile
+- bin/console
 - henkei.gemspec
-- jar/tika-app-1.21.jar
+- jar/tika-app-1.23.jar
 - jar/tika-config.xml
 - lib/henkei.rb
+- lib/henkei/configuration.rb
 - lib/henkei/version.rb
 - lib/henkei/yomu.rb
 - spec/helper.rb
 - spec/henkei_spec.rb
+- spec/samples/pipe-error.png
 - spec/samples/sample filename with spaces.pages
 - spec/samples/sample-metadata-values-with-colons.doc
 - spec/samples/sample.docx
@@ -162,14 +180,17 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: '0'
+      version: 2.4.0
+  - - "<"
+    - !ruby/object:Gem::Version
+      version: 3.1.0
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.0.3
+rubygems_version: 3.0.6
 signing_key: 
 specification_version: 4
 summary: Read text and metadata from files and documents (.doc, .docx, .pages, .odt,
@@ -177,6 +198,7 @@ summary: Read text and metadata from files and documents (.doc, .docx, .pages, .
 test_files:
 - spec/helper.rb
 - spec/henkei_spec.rb
+- spec/samples/pipe-error.png
 - spec/samples/sample filename with spaces.pages
 - spec/samples/sample-metadata-values-with-colons.doc
 - spec/samples/sample.docx