henkei 2.3.0.1 → 2.4.0.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: ad6513ead7b83776d281da0be4b857428812109d3cda95f98a6504434bb0c91f
-  data.tar.gz: 1a0c9db6ca53ea23e5b28c1a0bdd2415d1dbcb284d1f9958ab0529b2e9e96f5a
+  metadata.gz: a039368aaffaee95c3d48c5b56fc30b81babafc7b996986e56c788bb12c20bc0
+  data.tar.gz: d31e08f66e605ea99209911edebbb62fce65e75c328043a9ed3e53f1eac4d80d
 SHA512:
-  metadata.gz: 9f270bdc844331e88a96b57f24d949ef3517345a3c6907b374945ac3f7a72066bc1eab81993ea61ae823d91a0e922ae5a08d382ac4b3e420662f9471299ea5cb
-  data.tar.gz: 58ef5f1d2157d6de60d35817238cdb966e92ac880763ac077510efe5ebcd497cf6a231a5deab1510d680ed9bc0acdbf33217126a68feaea2592a0508682ab133
+  metadata.gz: 1daffbde6948f1e8d9c8003c8ab60a3f86051c307b04a0aa3a654bdf05efd830c3148e17a555fee4cd4f52d85ed80eb6071e4df54754e5458b7e1caa1a9b2474
+  data.tar.gz: a230d09cde52cbedbc0b67ed025a7666119b5c66f7611cb730b1558aba5b77f5f50cc878e17f8d11a14d9840d0b379aeedb00d141fbde924ec30f3fe42414747

data/.github/workflows/test.yml

@@ -0,0 +1,37 @@
+name: Test Henkei Ruby gem
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+    
+env:
+  CI: true
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        ruby-version: ['2.7', '3.0', '3.1', '3.2']
+
+    steps:
+      - uses: actions/checkout@v3
+
+      - name: Set up Ruby
+        uses: ruby/setup-ruby@v1
+        with:
+          ruby-version: ${{ matrix.ruby-version }}
+          bundler-cache: true
+
+      - name: Lint code - Rubocop
+        run: bundle exec rubocop
+
+      - name: Run tests
+        run: bundle exec rspec
+
+      - name: Test & publish code coverage
+        uses: paambaati/codeclimate-action@v3.2.0
+        env:
+          CC_TEST_REPORTER_ID: bb96c1ff9dc66724c38fb4eb54486dd72dc88a7fd6e727c034b9cf8d747d069e

data/.rubocop.yml

@@ -1,6 +1,10 @@
+require:
+  - rubocop-rake
+  - rubocop-rspec
+
 AllCops:
   NewCops: enable
-  TargetRubyVersion: 2.6
+  TargetRubyVersion: 2.7
 
 Layout/EmptyLinesAroundAttributeAccessor:
   Enabled: true
@@ -30,6 +34,12 @@ Metrics/BlockLength:
 Metrics/MethodLength:
   Max: 15
 
+RSpec/ExampleLength:
+  Max: 10
+
+RSpec/MultipleExpectations:
+  Max: 3
+
 Style/ClassVars:
   Enabled: false
 

data/README.md

@@ -1,4 +1,4 @@
-[![Travis Build Status](http://img.shields.io/travis/abrom/henkei.svg?style=flat)](https://travis-ci.org/abrom/henkei)
+[![Github Build Status](https://github.com/abrom/henkei/actions/workflows/test.yml/badge.svg)](https://github.com/abrom/henkei/actions/workflows/test.yml)
 [![Maintainability](https://api.codeclimate.com/v1/badges/d06e8c917cf7d8c07234/maintainability)](https://codeclimate.com/github/abrom/henkei/maintainability)
 [![Test Coverage](https://api.codeclimate.com/v1/badges/d06e8c917cf7d8c07234/test_coverage)](https://codeclimate.com/github/abrom/henkei/test_coverage)
 [![Gem Version](http://img.shields.io/gem/v/henkei.svg?style=flat)](#)

data/henkei.gemspec

@@ -13,13 +13,19 @@ Gem::Specification.new do |spec|
   spec.description   = 'Read text and metadata from files and documents using Apache Tika toolkit'
   spec.summary       = 'Read text and metadata from files and documents ' \
                        '(.doc, .docx, .pages, .odt, .rtf, .pdf) using Apache Tika toolkit'
-  spec.homepage      = 'http://github.com/abrom/henkei'
+  spec.homepage      = 'https://github.com/abrom/henkei'
   spec.license       = 'MIT'
-  spec.required_ruby_version = ['>= 2.6.0', '< 3.2.0']
+  spec.required_ruby_version = ['>= 2.7.0', '< 3.3.0']
+
+  # Prevent pushing this gem to RubyGems.org by setting 'allowed_push_host', or
+  # delete this section to allow pushing this gem to any host.
+  raise 'RubyGems 2.0 or newer is required to protect against public gem pushes.' unless spec.respond_to?(:metadata)
+
+  spec.metadata['allowed_push_host'] = 'https://rubygems.org'
+  spec.metadata['rubygems_mfa_required'] = 'true'
 
   spec.files         = `git ls-files`.split("\n")
   spec.executables   = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
-  spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
   spec.require_paths = ['lib']
 
   spec.add_runtime_dependency 'json', '>= 1.8', '< 3'
@@ -30,6 +36,9 @@ Gem::Specification.new do |spec|
   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'
-  spec.add_development_dependency 'simplecov', '~> 0.15'
+  spec.add_development_dependency 'rubocop', '~> 1.26'
+  spec.add_development_dependency 'rubocop-performance', '~> 1.13'
+  spec.add_development_dependency 'rubocop-rake', '~> 0.6'
+  spec.add_development_dependency 'rubocop-rspec', '~> 2.9'
+  spec.add_development_dependency 'simplecov', '~> 0.15', '< 0.18'
 end

data/lib/henkei/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 class Henkei
-  VERSION = '2.3.0.1'
+  VERSION = '2.4.0.2'
 end

data/lib/henkei.rb

@@ -25,14 +25,14 @@ 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-2.3.0.jar')
+  JAR_PATH = File.join(Henkei::GEM_PATH, 'jar', 'tika-app-2.4.0.jar')
   CONFIG_PATH = File.join(Henkei::GEM_PATH, 'jar', 'tika-config.xml')
   CONFIG_WITHOUT_OCR_PATH = File.join(Henkei::GEM_PATH, 'jar', 'tika-config-without-ocr.xml')
 
   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`.'
+      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|
@@ -51,8 +51,7 @@ class Henkei # rubocop:disable Metrics/ClassLength
     result = client_read(type, data, include_ocr: include_ocr)
 
     case type
-    when :text then result
-    when :html then result
+    when :text, :html then result
     when :metadata then JSON.parse(result)
     when :mimetype then Henkei.mimetype(JSON.parse(result)['Content-Type'])
     end

data/spec/henkei_spec.rb

@@ -7,8 +7,8 @@ require 'nokogiri'
 # 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'
 
-def travis_ci?
-  ENV['CI'] == 'true' && ENV['TRAVIS'] == 'true'
+def ci?
+  ENV['CI'] == 'true'
 end
 
 describe Henkei do
@@ -20,13 +20,13 @@ describe Henkei do
 
   describe '.read' do
     it 'reads text' do
-      text = Henkei.read :text, data
+      text = described_class.read :text, data
 
       expect(text).to include 'The quick brown fox jumped over the lazy cat.'
     end
 
     it 'reads metadata' do
-      metadata = Henkei.read :metadata, data
+      metadata = described_class.read :metadata, data
 
       expect(metadata['Content-Type']).to(
         eq 'application/vnd.openxmlformats-officedocument.wordprocessingml.document'
@@ -35,13 +35,13 @@ describe Henkei do
 
     it 'reads metadata values with colons as strings' do
       data = File.read 'spec/samples/sample-metadata-values-with-colons.doc'
-      metadata = Henkei.read :metadata, data
+      metadata = described_class.read :metadata, data
 
       expect(metadata['dc:title']).to eq 'problem: test'
     end
 
     it 'reads mimetype' do
-      mimetype = Henkei.read :mimetype, data
+      mimetype = described_class.read :mimetype, data
 
       expect(mimetype.content_type).to(
         eq 'application/vnd.openxmlformats-officedocument.wordprocessingml.document'
@@ -53,23 +53,20 @@ describe Henkei do
       let(:data) { File.read 'spec/samples/pipe-error.png' }
 
       it 'returns an empty result' do
-        text = Henkei.read :text, data
+        text = described_class.read :text, data
 
         expect(text).to eq ''
       end
 
-      unless travis_ci?
+      unless ci?
         context 'when `include_ocr` is enabled' do
           it 'returns parsed plain text in the image' do
-            text = Henkei.read :text, data, include_ocr: true
+            text = described_class.read :text, data, include_ocr: true
 
             expect(text).to include <<~TEXT
               West Side
-    
+
               Sea Island
-              PP
-    
-              Richmond
             TEXT
           end
         end
@@ -79,11 +76,11 @@ describe Henkei do
 
   describe '.new' do
     it 'requires parameters' do
-      expect { Henkei.new }.to raise_error ArgumentError
+      expect { described_class.new }.to raise_error ArgumentError
     end
 
     it 'accepts a root path' do
-      henkei = Henkei.new 'spec/samples/sample.pages'
+      henkei = described_class.new File.join(Henkei::GEM_PATH, 'spec/samples/sample.pages')
 
       expect(henkei).to be_path
       expect(henkei).not_to be_uri
@@ -91,7 +88,7 @@ describe Henkei do
     end
 
     it 'accepts a relative path' do
-      henkei = Henkei.new 'spec/samples/sample.pages'
+      henkei = described_class.new 'spec/samples/sample.pages'
 
       expect(henkei).to be_path
       expect(henkei).not_to be_uri
@@ -99,7 +96,7 @@ describe Henkei do
     end
 
     it 'accepts a path with spaces' do
-      henkei = Henkei.new 'spec/samples/sample filename with spaces.pages'
+      henkei = described_class.new 'spec/samples/sample filename with spaces.pages'
 
       expect(henkei).to be_path
       expect(henkei).not_to be_uri
@@ -107,7 +104,7 @@ describe Henkei do
     end
 
     it 'accepts a URI' do
-      henkei = Henkei.new 'http://svn.apache.org/repos/asf/poi/trunk/test-data/document/sample.docx'
+      henkei = described_class.new 'http://svn.apache.org/repos/asf/poi/trunk/test-data/document/sample.docx'
 
       expect(henkei).to be_uri
       expect(henkei).not_to be_path
@@ -116,7 +113,7 @@ describe Henkei do
 
     it 'accepts a stream or object that can be read' do
       File.open 'spec/samples/sample.pages', 'r' do |file|
-        henkei = Henkei.new file
+        henkei = described_class.new file
 
         expect(henkei).to be_stream
         expect(henkei).not_to be_path
@@ -125,38 +122,38 @@ describe Henkei do
     end
 
     it 'refuses a path to a missing file' do
-      expect { Henkei.new 'test/sample/missing.pages' }.to raise_error Errno::ENOENT
+      expect { described_class.new 'test/sample/missing.pages' }.to raise_error Errno::ENOENT
     end
 
     it 'refuses other objects' do
       [nil, 1, 1.1].each do |object|
-        expect { Henkei.new object }.to raise_error TypeError
+        expect { described_class.new object }.to raise_error TypeError
       end
     end
   end
 
   describe '.creation_date' do
-    let(:henkei) { Henkei.new 'spec/samples/sample.pages' }
+    let(:henkei) { described_class.new 'spec/samples/sample.pages' }
 
-    it 'should return Time' do
+    it 'returns a Time' do
       expect(henkei.creation_date).to be_a Time
     end
   end
 
   describe '.java' do
     specify 'with no specified JAVA_HOME' do
-      expect(Henkei.send(:java_path)).to eq 'java'
+      expect(described_class.send(:java_path)).to eq 'java'
     end
 
     specify 'with a specified JAVA_HOME' do
       ENV['JAVA_HOME'] = '/path/to/java/home'
 
-      expect(Henkei.send(:java_path)).to eq '/path/to/java/home/bin/java'
+      expect(described_class.send(:java_path)).to eq '/path/to/java/home/bin/java'
     end
   end
 
-  context 'initialized with a given path' do
-    let(:henkei) { Henkei.new 'spec/samples/sample.pages' }
+  context 'when initialized with a given path' do
+    let(:henkei) { described_class.new 'spec/samples/sample.pages' }
 
     specify '#text reads text' do
       expect(henkei.text).to include 'The quick brown fox jumped over the lazy cat.'
@@ -167,7 +164,7 @@ describe Henkei do
     end
 
     context 'when passing in the `pipe-error.png` test file' do
-      let(:henkei) { Henkei.new 'spec/samples/pipe-error.png' }
+      let(:henkei) { described_class.new 'spec/samples/pipe-error.png' }
 
       it '#text returns an empty result' do
         expect(henkei.text).to eq ''
@@ -182,16 +179,13 @@ describe Henkei do
         expect(henkei.mimetype.content_type).to eq 'image/png'
       end
 
-      unless travis_ci?
+      unless ci?
         context 'when `include_ocr` is enabled' do
           it '#text returns plain text of parsed text in the image' do
             expect(henkei.text(include_ocr: true)).to include <<~TEXT
               West Side
-    
+
               Sea Island
-              PP
-    
-              Richmond
             TEXT
           end
 
@@ -199,7 +193,7 @@ describe Henkei do
             expect(henkei.html(include_ocr: true)).to include '<meta name="tiff:ImageWidth" content="792"/>'
 
             html_body = Nokogiri::HTML(henkei.html(include_ocr: true)).at_xpath('//body')
-            ['Anmore', 'Coquitlam', 'West Side', 'Sea Island', 'Richmond', 'Steveston'].each do |location|
+            ['West Side', 'Sea Island', 'Richmond', 'Steveston'].each do |location|
               expect(html_body.text).to include location
             end
           end
@@ -208,8 +202,8 @@ describe Henkei do
     end
   end
 
-  context 'initialized with a given URI' do
-    let(:henkei) { Henkei.new 'http://svn.apache.org/repos/asf/poi/trunk/test-data/document/sample.docx' }
+  context 'when initialized with a given URI' do
+    let(:henkei) { described_class.new 'http://svn.apache.org/repos/asf/poi/trunk/test-data/document/sample.docx' }
 
     specify '#text reads text' do
       expect(henkei.text).to include 'Lorem ipsum dolor sit amet, consectetuer adipiscing elit.'
@@ -222,8 +216,8 @@ describe Henkei do
     end
   end
 
-  context 'initialized with a given stream' do
-    let(:henkei) { Henkei.new File.open('spec/samples/sample.pages', 'rb') }
+  context 'when initialized with a given stream' do
+    let(:henkei) { described_class.new File.open('spec/samples/sample.pages', 'rb') }
 
     specify '#text reads text' do
       expect(henkei.text).to include 'The quick brown fox jumped over the lazy cat.'
@@ -235,7 +229,7 @@ describe Henkei do
   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' }
+    let(:henkei) { described_class.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'

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: henkei
 version: !ruby/object:Gem::Version
-  version: 2.3.0.1
+  version: 2.4.0.2
 platform: ruby
 authors:
 - Erol Fornoles
@@ -9,7 +9,7 @@ authors:
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2022-02-24 00:00:00.000000000 Z
+date: 2023-01-22 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: json
@@ -127,14 +127,56 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.71'
+        version: '1.26'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.71'
+        version: '1.26'
+- !ruby/object:Gem::Dependency
+  name: rubocop-performance
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.13'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.13'
+- !ruby/object:Gem::Dependency
+  name: rubocop-rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.6'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.6'
+- !ruby/object:Gem::Dependency
+  name: rubocop-rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.9'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.9'
 - !ruby/object:Gem::Dependency
   name: simplecov
   requirement: !ruby/object:Gem::Requirement
@@ -142,6 +184,9 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '0.15'
+    - - "<"
+      - !ruby/object:Gem::Version
+        version: '0.18'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
@@ -149,6 +194,9 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '0.15'
+    - - "<"
+      - !ruby/object:Gem::Version
+        version: '0.18'
 description: Read text and metadata from files and documents using Apache Tika toolkit
 email:
 - erol.fornoles@gmail.com
@@ -158,10 +206,10 @@ executables:
 extensions: []
 extra_rdoc_files: []
 files:
+- ".github/workflows/test.yml"
 - ".gitignore"
 - ".rspec"
 - ".rubocop.yml"
-- ".travis.yml"
 - Gemfile
 - LICENSE
 - NOTICE.txt
@@ -169,7 +217,7 @@ files:
 - Rakefile
 - bin/console
 - henkei.gemspec
-- jar/tika-app-2.3.0.jar
+- jar/tika-app-2.4.0.jar
 - jar/tika-config-without-ocr.xml
 - jar/tika-config.xml
 - lib/henkei.rb
@@ -183,10 +231,12 @@ files:
 - spec/samples/sample-metadata-values-with-colons.doc
 - spec/samples/sample.docx
 - spec/samples/sample.pages
-homepage: http://github.com/abrom/henkei
+homepage: https://github.com/abrom/henkei
 licenses:
 - MIT
-metadata: {}
+metadata:
+  allowed_push_host: https://rubygems.org
+  rubygems_mfa_required: 'true'
 post_install_message:
 rdoc_options: []
 require_paths:
@@ -195,26 +245,19 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: 2.6.0
+      version: 2.7.0
   - - "<"
     - !ruby/object:Gem::Version
-      version: 3.2.0
+      version: 3.3.0
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.0.9
+rubygems_version: 3.4.1
 signing_key:
 specification_version: 4
 summary: Read text and metadata from files and documents (.doc, .docx, .pages, .odt,
   .rtf, .pdf) using Apache Tika toolkit
-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
-- spec/samples/sample.pages
+test_files: []

data/.travis.yml

@@ -1,32 +0,0 @@
-env:
-  global:
-    - CC_TEST_REPORTER_ID=bb96c1ff9dc66724c38fb4eb54486dd72dc88a7fd6e727c034b9cf8d747d069e
-  jobs:
-    - INCLUDE_RAILS=false
-    - INCLUDE_RAILS=true
-
-language: ruby
-rvm:
-  - 2.6
-  - 2.7
-  - 3.0
-  - 3.1
-
-before_install:
-  - gem update bundler
-
-install:
-  - bundle install --jobs=3 --retry=3
-  - gem install rubocop
-
-before_script:
-  - curl -L https://codeclimate.com/downloads/test-reporter/test-reporter-latest-linux-amd64 > ./cc-test-reporter
-  - chmod +x ./cc-test-reporter
-  - ./cc-test-reporter before-build
-
-script:
-  - bundle exec rubocop
-  - bundle exec rspec
-
-after_script:
-  - ./cc-test-reporter after-build --exit-code $TRAVIS_TEST_RESULT