Add Ruby 3.2.x support (#37)

Remove Ruby 2.6.x support
Fix various code lints

.github/workflows/test.yml

@@ -14,10 +14,10 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        ruby-version: ['2.6', '2.7', '3.0', '3.1']
+        ruby-version: ['2.7', '3.0', '3.1', '3.2']
 
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
 
       - name: Set up Ruby
         uses: ruby/setup-ruby@v1
@@ -32,6 +32,6 @@ jobs:
         run: bundle exec rspec
 
       - name: Test & publish code coverage
-        uses: paambaati/codeclimate-action@v3.0.0
+        uses: paambaati/codeclimate-action@v3.2.0
         env:
           CC_TEST_REPORTER_ID: bb96c1ff9dc66724c38fb4eb54486dd72dc88a7fd6e727c034b9cf8d747d069e

.rubocop.yml

@@ -1,6 +1,11 @@
+require:
+  - rubocop-performance
+  - rubocop-rake
+  - rubocop-rspec
+
 AllCops:
   NewCops: enable
-  TargetRubyVersion: 2.6
+  TargetRubyVersion: 2.7
 
 Layout/EmptyLinesAroundAttributeAccessor:
   Enabled: true
@@ -30,6 +35,12 @@ Metrics/BlockLength:
 Metrics/MethodLength:
   Max: 15
 
+RSpec/ExampleLength:
+  Max: 12
+
+RSpec/MultipleExpectations:
+  Max: 4
+
 Style/ClassVars:
   Enabled: false
 

henkei.gemspec

@@ -5,7 +5,7 @@ $LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
 
 require 'henkei/version'
 
-Gem::Specification.new do |spec| # rubocop:disable Metrics/BlockLength
+Gem::Specification.new do |spec|
   spec.name          = 'henkei'
   spec.version       = Henkei::VERSION
   spec.authors       = ['Erol Fornoles', 'Andrew Bromwich']
@@ -15,7 +15,7 @@ Gem::Specification.new do |spec| # rubocop:disable Metrics/BlockLength
                        '(.doc, .docx, .pages, .odt, .rtf, .pdf) using Apache Tika toolkit'
   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.
@@ -37,7 +37,6 @@ Gem::Specification.new do |spec| # rubocop:disable Metrics/BlockLength
   spec.add_development_dependency 'rspec', '~> 3.7'
   spec.add_development_dependency 'rubocop', '~> 1.26'
   spec.add_development_dependency 'rubocop-performance', '~> 1.13'
-  spec.add_development_dependency 'rubocop-rails', '~> 2.14'
   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'

lib/henkei.rb

@@ -34,8 +34,8 @@ class Henkei # rubocop:disable Metrics/ClassLength
 
   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|
@@ -78,7 +78,7 @@ def initialize(input)
     if input.is_a? String
       if File.exist? input
         @path = input
-      elsif input =~ URI::DEFAULT_PARSER.make_regexp
+      elsif input&.match?(URI::DEFAULT_PARSER.make_regexp)
         @uri = URI.parse input
       else
         raise Errno::ENOENT, "missing file or invalid URI - #{input}"
@@ -265,7 +265,7 @@ def self.server_read(data)
     # tell Tika that we're done sending data
     s.shutdown(Socket::SHUT_WR)
 
-    resp = String.new ''
+    resp = +''
     loop do
       chunk = s.recv(65_536)
       break if chunk.empty? || !chunk
@@ -300,9 +300,8 @@ def self.switch_for_type(type)
   # Internal helper to remove erroneous output
   #
   def self.filter_response(response)
-    response.gsub(
-      /\AWARNING: sun\.reflect\.Reflection\.getCallerClass is not supported\. This will impact performance\.\n/,
-      ''
+    response.delete_prefix(
+      "WARNING: sun.reflect.Reflection.getCallerClass is not supported. This will impact performance.\n"
     )
   end
   private_class_method :filter_response

spec/henkei_spec.rb

@@ -15,13 +15,13 @@
 
   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'
@@ -30,13 +30,13 @@
 
     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'
@@ -48,7 +48,7 @@
       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
@@ -57,35 +57,35 @@
 
   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
       expect(henkei).not_to be_stream
     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
       expect(henkei).not_to be_stream
     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
       expect(henkei).not_to be_stream
     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
@@ -94,7 +94,7 @@
 
     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
@@ -103,37 +103,38 @@
     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' }
-    it 'should return Time' do
+    let(:henkei) { described_class.new 'spec/samples/sample.pages' }
+
+    it 'returns 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.'
@@ -144,7 +145,7 @@
     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 ''
@@ -161,8 +162,8 @@
     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.'
@@ -175,8 +176,8 @@
     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.'
@@ -188,7 +189,7 @@
   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'
@@ -199,35 +200,35 @@
     end
   end
 
-  context 'working as server mode' do
+  context 'when working as server mode' do
     specify '#starts and kills server' do
-      Henkei.server(:text)
-      expect(Henkei.class_variable_get(:@@server_pid)).not_to be_nil
-      expect(Henkei.class_variable_get(:@@server_port)).not_to be_nil
+      described_class.server(:text)
+      expect(described_class.class_variable_get(:@@server_pid)).not_to be_nil
+      expect(described_class.class_variable_get(:@@server_port)).not_to be_nil
 
-      s = TCPSocket.new('localhost', Henkei.class_variable_get(:@@server_port))
+      s = TCPSocket.new('localhost', described_class.class_variable_get(:@@server_port))
       expect(s).to be_a TCPSocket
       s.close
     ensure
-      port = Henkei.class_variable_get(:@@server_port)
-      Henkei.kill_server!
+      port = described_class.class_variable_get(:@@server_port)
+      described_class.kill_server!
       sleep 2
       expect { TCPSocket.new('localhost', port) }.to raise_error Errno::ECONNREFUSED
     end
 
     specify '#runs samples through server mode' do
-      Henkei.server(:text)
-      expect(Henkei.new('spec/samples/sample.pages').text).to(
+      described_class.server(:text)
+      expect(described_class.new('spec/samples/sample.pages').text).to(
         include 'The quick brown fox jumped over the lazy cat.'
       )
-      expect(Henkei.new('spec/samples/sample filename with spaces.pages').text).to(
+      expect(described_class.new('spec/samples/sample filename with spaces.pages').text).to(
         include 'The quick brown fox jumped over the lazy cat.'
       )
-      expect(Henkei.new('spec/samples/sample.docx').text).to(
+      expect(described_class.new('spec/samples/sample.docx').text).to(
         include 'The quick brown fox jumped over the lazy cat.'
       )
     ensure
-      Henkei.kill_server!
+      described_class.kill_server!
     end
   end
 end