henkei 1.28.5.2 → 2.2.0.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 5c4d344ed0b3e34f58c4fa5c5e8694b50acc9fb2765b2923aa342a2aeb37f924
-  data.tar.gz: 1bde6cdf92d957e707e71bb4763230e1a39e128efc447f842538c42f35e945c9
+  metadata.gz: 64f2ec330c97bf77b16e2f7e14e08f90c405ae42c7aeddce733c0d889eeb4782
+  data.tar.gz: c3b3b91c569c7093bf22a5c751153426f1fdaa62da61f8c40f8b8cabc6ce072c
 SHA512:
-  metadata.gz: 14a19c09c4fbde49ce7774392793f26dbdcb8c9af5418cda6ce58b7583b6a0edc16640a55348ff1f7d64b7153359055fbaba91bfcd3217a285f2aafa5c7f4dc1
-  data.tar.gz: eaad5644f3e69cb7b1720284f6eac900e4598b7cec0c6745a622473176568b110f4a280c21213ecf55185b9ee304ea9574279a9cb5fd34a65578af0a89d2fe91
+  metadata.gz: b9f2263c057cb9e958039930aa3c0244c31b5bcc5e636515a757e3b1c5d43a6b52c932a76a8c132af73707453df1e2652e6f02d9926276a75bceb4deb69ffa59
+  data.tar.gz: f8ea0d87ad2bc75213483824a30edba37507110fc721434f0a40477500dc4674d8ce8d1c2a47b06624249b48228bbe9c9a9f9c86bb19e5cb2dcc18a8dec23dbe

data/.rubocop.yml

@@ -1,11 +1,5 @@
-require:
-  - rubocop-performance
-  - rubocop-rake
-  - rubocop-rspec
-
 AllCops:
   NewCops: enable
-  TargetRubyVersion: 3.0
 
 Layout/EmptyLinesAroundAttributeAccessor:
   Enabled: true
@@ -35,12 +29,6 @@ Metrics/BlockLength:
 Metrics/MethodLength:
   Max: 15
 
-RSpec/ExampleLength:
-  Max: 12
-
-RSpec/MultipleExpectations:
-  Max: 4
-
 Style/ClassVars:
   Enabled: false
 

data/.travis.yml

@@ -0,0 +1,32 @@
+env:
+  global:
+    - CC_TEST_REPORTER_ID=bb96c1ff9dc66724c38fb4eb54486dd72dc88a7fd6e727c034b9cf8d747d069e
+  jobs:
+    - INCLUDE_RAILS=false
+    - INCLUDE_RAILS=true
+
+language: ruby
+rvm:
+  - 2.5
+  - 2.6
+  - 2.7
+  - 3.0
+
+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

data/Gemfile

@@ -4,12 +4,3 @@ source 'https://rubygems.org'
 
 # Specify your gem's dependencies in henkei.gemspec
 gemspec
-
-gem 'bundler', '~> 2.0'
-gem 'rake', '~> 12.3'
-gem 'rspec', '~> 3.7'
-gem 'rubocop', '~> 1.26'
-gem 'rubocop-performance', '~> 1.13'
-gem 'rubocop-rake', '~> 0.6'
-gem 'rubocop-rspec', '~> 2.9'
-gem 'simplecov', '~> 0.15', '< 0.18'

data/README.md

@@ -1,4 +1,4 @@
-[![Github Build Status](https://github.com/abrom/henkei/actions/workflows/test.yml/badge.svg)](https://github.com/abrom/henkei/actions/workflows/test.yml)
+[![Travis Build Status](http://img.shields.io/travis/abrom/henkei.svg?style=flat)](https://travis-ci.org/abrom/henkei)
 [![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)](#)
@@ -21,6 +21,15 @@ Here are some of the formats supported:
 For the complete list of supported formats, please visit the Apache Tika
 [Supported Document Formats](http://tika.apache.org/0.9/formats.html) page.
 
+## Upgrading from v1.x to v2.x
+
+Apache Tika v2.x brings with it some changes. One key change is that the Tika client and server applications have
+been split up. To keep the gem size down Henkei will only include the client app. That is to say, each time you
+call to Henkei, a new Java process will be started, run your command, then terminate.
+
+Another change is the metadata keys. A lot of duplicate keys have been removed in favour of a more standards
+based approach. A list of the old vs new key names can be found [here](https://cwiki.apache.org/confluence/display/TIKA/Migrating+to+Tika+2.0.0#MigratingtoTika2.0.0-Metadata) 
+
 ## Usage
 
 Text, metadata and MIME type information can be extracted by calling `Henkei.read` directly:
@@ -69,6 +78,20 @@ post '/:name/:filename' do
 end
 ```
 
+### Reading text from inside images (OCR)
+
+You can enable OCR by specifying the optional `include_ocr: true` when calling to the `text` or `html` instance methods,
+as well as the `read` class method. Note that Tika does indicate this will greatly increase processing time.
+
+```ruby
+henkei = Henkei.new 'sample.pages'
+text_with_ocr = henkei.text(include_ocr: true)
+html_with_ocr = henkei.html(include_ocr: true)
+
+data = File.read 'sample.pages'
+text_with_ocr = Henkei.read :text, data, include_ocr: true
+```
+
 ### Reading metadata
 
 Metadata is returned as a hash.

data/henkei.gemspec

@@ -13,21 +13,23 @@ 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      = 'https://github.com/abrom/henkei'
+  spec.homepage      = 'http://github.com/abrom/henkei'
   spec.license       = 'MIT'
-  spec.required_ruby_version = ['>= 3.0.0', '< 3.4.0']
-
-  # 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.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) }
+  spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
   spec.require_paths = ['lib']
 
   spec.add_runtime_dependency 'json', '>= 1.8', '< 3'
   spec.add_runtime_dependency 'mini_mime', '>= 0.1.1', '< 2'
+
+  spec.add_development_dependency 'bundler', '~> 2.0'
+  spec.add_development_dependency 'nokogiri', '~> 1.12'
+  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'
 end

data/jar/tika-config-without-ocr.xml

@@ -0,0 +1,9 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<properties>
+  <service-loader initializableProblemHandler="ignore"/>
+  <parsers>
+    <parser class="org.apache.tika.parser.DefaultParser">
+      <parser-exclude class="org.apache.tika.parser.ocr.TesseractOCRParser"/>
+    </parser>
+  </parsers>
+</properties>

data/lib/henkei/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 class Henkei
-  VERSION = '1.28.5.2'
+  VERSION = '2.2.0.1'
 end

data/lib/henkei.rb

@@ -25,17 +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-1.28.5.jar')
+  JAR_PATH = File.join(Henkei::GEM_PATH, 'jar', 'tika-app-2.2.0.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
+  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|
@@ -50,11 +47,12 @@ class Henkei # rubocop:disable Metrics/ClassLength
   #   text = Henkei.read :text, data
   #   metadata = Henkei.read :metadata, data
   #
-  def self.read(type, data)
-    result = @@server_pid ? server_read(data) : client_read(type, data)
+  def self.read(type, data, include_ocr: false)
+    result = client_read(type, data, include_ocr: include_ocr)
 
     case type
-    when :text, :html then result
+    when :text then result
+    when :html then result
     when :metadata then JSON.parse(result)
     when :mimetype then Henkei.mimetype(JSON.parse(result)['Content-Type'])
     end
@@ -78,7 +76,7 @@ class Henkei # rubocop:disable Metrics/ClassLength
     if input.is_a? String
       if File.exist? input
         @path = input
-      elsif input&.match?(URI::DEFAULT_PARSER.make_regexp)
+      elsif input =~ URI::DEFAULT_PARSER.make_regexp
         @uri = URI.parse input
       else
         raise Errno::ENOENT, "missing file or invalid URI - #{input}"
@@ -95,10 +93,14 @@ class Henkei # rubocop:disable Metrics/ClassLength
   #   henkei = Henkei.new 'sample.pages'
   #   henkei.text
   #
-  def text
+  # Include OCR results from images (includes embedded images in pages/docx/pdf etc)
+  #
+  #   henkei.text(include_ocr: true)
+  #
+  def text(include_ocr: false)
     return @text if defined? @text
 
-    @text = Henkei.read :text, data
+    @text = Henkei.read :text, data, include_ocr: include_ocr
   end
 
   # Returns the text content of the Henkei document in HTML.
@@ -106,10 +108,14 @@ class Henkei # rubocop:disable Metrics/ClassLength
   #   henkei = Henkei.new 'sample.pages'
   #   henkei.html
   #
-  def html
+  # Include OCR results from images (includes embedded images in pages/docx/pdf etc)
+  #
+  #   henkei.html(include_ocr: true)
+  #
+  def html(include_ocr: false)
     return @html if defined? @html
 
-    @html = Henkei.read :html, data
+    @html = Henkei.read :html, data, include_ocr: include_ocr
   end
 
   # Returns the metadata hash of the Henkei document.
@@ -143,9 +149,9 @@ class Henkei # rubocop:disable Metrics/ClassLength
   #
   def creation_date
     return @creation_date if defined? @creation_date
-    return unless metadata['Creation-Date']
+    return unless metadata['dcterms:created']
 
-    @creation_date = Time.parse(metadata['Creation-Date'])
+    @creation_date = Time.parse(metadata['dcterms:created'])
   end
 
   # Returns +true+ if the Henkei document was specified using a file path.
@@ -195,44 +201,6 @@ class Henkei # rubocop:disable Metrics/ClassLength
     @data
   end
 
-  # Returns pid of Tika server, started as a new spawned process.
-  #
-  #  type :html, :text or :metadata
-  #  custom_port e.g. 9293
-  #
-  #  Henkei.server(:text, 9294)
-  #
-  def self.server(type, custom_port = nil)
-    @@server_port = custom_port || DEFAULT_SERVER_PORT
-
-    @@server_pid = Process.spawn(*tika_command(type, server: true))
-    sleep(2) # Give the server 2 seconds to spin up.
-    @@server_pid
-  end
-
-  # Kills server started by Henkei.server
-  #
-  #  Always run this when you're done, or else Tika might run until you kill it manually
-  #  You might try putting your extraction in a begin..rescue...ensure...end block and
-  #    putting this method in the ensure block.
-  #
-  #  Henkei.server(:text)
-  #  reports = ["report1.docx", "report2.doc", "report3.pdf"]
-  #  begin
-  #    my_texts = reports.map{ |report_path| Henkei.new(report_path).text }
-  #  rescue
-  #  ensure
-  #    Henkei.kill_server!
-  #  end
-  #
-  def self.kill_server!
-    return unless @@server_pid
-
-    Process.kill('INT', @@server_pid)
-    @@server_pid = nil
-    @@server_port = nil
-  end
-
   ### Private class methods
 
   # Provide the path to the Java binary
@@ -244,44 +212,21 @@ class Henkei # rubocop:disable Metrics/ClassLength
 
   # Internal helper for calling to Tika library directly
   #
-  def self.client_read(type, data)
-    filter_response Open3.capture2(*tika_command(type), stdin_data: data, binmode: true).first
+  def self.client_read(type, data, include_ocr: false)
+    Open3.capture2(*tika_command(type, include_ocr: include_ocr), stdin_data: data, binmode: true).first
   end
   private_class_method :client_read
 
-  # Internal helper for calling to running Tika server
-  #
-  def self.server_read(data)
-    s = TCPSocket.new('localhost', @@server_port)
-    file = StringIO.new(data, 'r')
-
-    loop do
-      chunk = file.read(65_536)
-      break unless chunk
-
-      s.write(chunk)
-    end
-
-    # tell Tika that we're done sending data
-    s.shutdown(Socket::SHUT_WR)
-
-    resp = +''
-    loop do
-      chunk = s.recv(65_536)
-      break if !chunk || chunk.empty?
-
-      resp << chunk
-    end
-    filter_response resp
-  end
-  private_class_method :server_read
-
   # 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.to_s] if server
-    command + switch_for_type(type)
+  def self.tika_command(type, include_ocr: false)
+    [
+      java_path,
+      '-Djava.awt.headless=true',
+      '-jar',
+      Henkei::JAR_PATH,
+      "--config=#{include_ocr ? Henkei::CONFIG_PATH : Henkei::CONFIG_WITHOUT_OCR_PATH}"
+    ] + switch_for_type(type)
   end
   private_class_method :tika_command
 
@@ -296,13 +241,4 @@ class Henkei # rubocop:disable Metrics/ClassLength
     }[type]
   end
   private_class_method :switch_for_type
-
-  # Internal helper to remove erroneous output
-  #
-  def self.filter_response(response)
-    response.delete_prefix(
-      "WARNING: sun.reflect.Reflection.getCallerClass is not supported. This will impact performance.\n"
-    )
-  end
-  private_class_method :filter_response
 end

data/spec/henkei_spec.rb

@@ -2,10 +2,15 @@
 
 require 'helper'
 require 'henkei'
+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'
+end
+
 describe Henkei do
   let(:data) { File.read 'spec/samples/sample.docx' }
 
@@ -15,13 +20,13 @@ describe Henkei do
 
   describe '.read' do
     it 'reads text' do
-      text = described_class.read :text, data
+      text = Henkei.read :text, data
 
       expect(text).to include 'The quick brown fox jumped over the lazy cat.'
     end
 
     it 'reads metadata' do
-      metadata = described_class.read :metadata, data
+      metadata = Henkei.read :metadata, data
 
       expect(metadata['Content-Type']).to(
         eq 'application/vnd.openxmlformats-officedocument.wordprocessingml.document'
@@ -30,13 +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 = described_class.read :metadata, data
+      metadata = Henkei.read :metadata, data
 
       expect(metadata['dc:title']).to eq 'problem: test'
     end
 
     it 'reads mimetype' do
-      mimetype = described_class.read :mimetype, data
+      mimetype = Henkei.read :mimetype, data
 
       expect(mimetype.content_type).to(
         eq 'application/vnd.openxmlformats-officedocument.wordprocessingml.document'
@@ -48,20 +53,37 @@ describe Henkei do
       let(:data) { File.read 'spec/samples/pipe-error.png' }
 
       it 'returns an empty result' do
-        text = described_class.read :text, data
+        text = Henkei.read :text, data
 
         expect(text).to eq ''
       end
+
+      unless travis_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
+
+            expect(text).to include <<~TEXT
+              West Side
+    
+              Sea Island
+              PP
+    
+              Richmond
+            TEXT
+          end
+        end
+      end
     end
   end
 
   describe '.new' do
     it 'requires parameters' do
-      expect { described_class.new }.to raise_error ArgumentError
+      expect { Henkei.new }.to raise_error ArgumentError
     end
 
     it 'accepts a root path' do
-      henkei = described_class.new File.join(Henkei::GEM_PATH, 'spec/samples/sample.pages')
+      henkei = Henkei.new 'spec/samples/sample.pages'
 
       expect(henkei).to be_path
       expect(henkei).not_to be_uri
@@ -69,7 +91,7 @@ describe Henkei do
     end
 
     it 'accepts a relative path' do
-      henkei = described_class.new 'spec/samples/sample.pages'
+      henkei = Henkei.new 'spec/samples/sample.pages'
 
       expect(henkei).to be_path
       expect(henkei).not_to be_uri
@@ -77,7 +99,7 @@ describe Henkei do
     end
 
     it 'accepts a path with spaces' do
-      henkei = described_class.new 'spec/samples/sample filename with spaces.pages'
+      henkei = Henkei.new 'spec/samples/sample filename with spaces.pages'
 
       expect(henkei).to be_path
       expect(henkei).not_to be_uri
@@ -85,7 +107,7 @@ describe Henkei do
     end
 
     it 'accepts a URI' do
-      henkei = described_class.new 'http://svn.apache.org/repos/asf/poi/trunk/test-data/document/sample.docx'
+      henkei = Henkei.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 +116,7 @@ describe Henkei do
 
     it 'accepts a stream or object that can be read' do
       File.open 'spec/samples/sample.pages', 'r' do |file|
-        henkei = described_class.new file
+        henkei = Henkei.new file
 
         expect(henkei).to be_stream
         expect(henkei).not_to be_path
@@ -103,38 +125,38 @@ describe Henkei do
     end
 
     it 'refuses a path to a missing file' do
-      expect { described_class.new 'test/sample/missing.pages' }.to raise_error Errno::ENOENT
+      expect { Henkei.new 'test/sample/missing.pages' }.to raise_error Errno::ENOENT
     end
 
     it 'refuses other objects' do
       [nil, 1, 1.1].each do |object|
-        expect { described_class.new object }.to raise_error TypeError
+        expect { Henkei.new object }.to raise_error TypeError
       end
     end
   end
 
   describe '.creation_date' do
-    let(:henkei) { described_class.new 'spec/samples/sample.pages' }
+    let(:henkei) { Henkei.new 'spec/samples/sample.pages' }
 
-    it 'returns Time' do
+    it 'should return Time' do
       expect(henkei.creation_date).to be_a Time
     end
   end
 
   describe '.java' do
     specify 'with no specified JAVA_HOME' do
-      expect(described_class.send(:java_path)).to eq 'java'
+      expect(Henkei.send(:java_path)).to eq 'java'
     end
 
     specify 'with a specified JAVA_HOME' do
       ENV['JAVA_HOME'] = '/path/to/java/home'
 
-      expect(described_class.send(:java_path)).to eq '/path/to/java/home/bin/java'
+      expect(Henkei.send(:java_path)).to eq '/path/to/java/home/bin/java'
     end
   end
 
-  context 'when initialized with a given path' do
-    let(:henkei) { described_class.new 'spec/samples/sample.pages' }
+  context 'initialized with a given path' do
+    let(:henkei) { Henkei.new 'spec/samples/sample.pages' }
 
     specify '#text reads text' do
       expect(henkei.text).to include 'The quick brown fox jumped over the lazy cat.'
@@ -145,7 +167,7 @@ describe Henkei do
     end
 
     context 'when passing in the `pipe-error.png` test file' do
-      let(:henkei) { described_class.new 'spec/samples/pipe-error.png' }
+      let(:henkei) { Henkei.new 'spec/samples/pipe-error.png' }
 
       it '#text returns an empty result' do
         expect(henkei.text).to eq ''
@@ -159,11 +181,35 @@ describe Henkei do
       it '#mimetype returns `image/png`' do
         expect(henkei.mimetype.content_type).to eq 'image/png'
       end
+
+      unless travis_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
+
+          it '#html returns HTML of parsed text in the image' 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|
+              expect(html_body.text).to include location
+            end
+          end
+        end
+      end
     end
   end
 
-  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' }
+  context 'initialized with a given URI' do
+    let(:henkei) { Henkei.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.'
@@ -176,8 +222,8 @@ describe Henkei do
     end
   end
 
-  context 'when initialized with a given stream' do
-    let(:henkei) { described_class.new File.open('spec/samples/sample.pages', 'rb') }
+  context 'initialized with a given stream' do
+    let(:henkei) { Henkei.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.'
@@ -189,7 +235,7 @@ describe Henkei do
   end
 
   context 'when source is a remote PDF' do
-    let(:henkei) { described_class.new 'https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf' }
+    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'
@@ -199,36 +245,4 @@ describe Henkei do
       expect(henkei.metadata['Content-Type']).to eq 'application/pdf'
     end
   end
-
-  context 'when working as server mode' do
-    specify '#starts and kills server' do
-      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', described_class.class_variable_get(:@@server_port))
-      expect(s).to be_a TCPSocket
-      s.close
-    ensure
-      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
-      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(described_class.new('spec/samples/sample filename with spaces.pages').text).to(
-        include 'The quick brown fox jumped over the lazy cat.'
-      )
-      expect(described_class.new('spec/samples/sample.docx').text).to(
-        include 'The quick brown fox jumped over the lazy cat.'
-      )
-    ensure
-      described_class.kill_server!
-    end
-  end
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: henkei
 version: !ruby/object:Gem::Version
-  version: 1.28.5.2
+  version: 2.2.0.1
 platform: ruby
 authors:
 - Erol Fornoles
@@ -9,7 +9,7 @@ authors:
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2024-05-01 00:00:00.000000000 Z
+date: 2021-12-27 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: json
@@ -51,6 +51,104 @@ dependencies:
     - - "<"
       - !ruby/object:Gem::Version
         version: '2'
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.0'
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.12'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.12'
+- !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
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '12.3'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '12.3'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.7'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.7'
+- !ruby/object:Gem::Dependency
+  name: rubocop
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.71'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.71'
+- !ruby/object:Gem::Dependency
+  name: simplecov
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.15'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.15'
 description: Read text and metadata from files and documents using Apache Tika toolkit
 email:
 - erol.fornoles@gmail.com
@@ -60,10 +158,10 @@ executables:
 extensions: []
 extra_rdoc_files: []
 files:
-- ".github/workflows/test.yml"
 - ".gitignore"
 - ".rspec"
 - ".rubocop.yml"
+- ".travis.yml"
 - Gemfile
 - LICENSE
 - NOTICE.txt
@@ -71,7 +169,8 @@ files:
 - Rakefile
 - bin/console
 - henkei.gemspec
-- jar/tika-app-1.28.5.jar
+- jar/tika-app-2.2.0.jar
+- jar/tika-config-without-ocr.xml
 - jar/tika-config.xml
 - lib/henkei.rb
 - lib/henkei/configuration.rb
@@ -84,12 +183,10 @@ files:
 - spec/samples/sample-metadata-values-with-colons.doc
 - spec/samples/sample.docx
 - spec/samples/sample.pages
-homepage: https://github.com/abrom/henkei
+homepage: http://github.com/abrom/henkei
 licenses:
 - MIT
-metadata:
-  allowed_push_host: https://rubygems.org
-  rubygems_mfa_required: 'true'
+metadata: {}
 post_install_message:
 rdoc_options: []
 require_paths:
@@ -98,19 +195,26 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: 3.0.0
+      version: 2.4.0
   - - "<"
     - !ruby/object:Gem::Version
-      version: 3.4.0
+      version: 3.1.0
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.3.7
+rubygems_version: 3.0.9
 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: []
+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

data/.github/workflows/test.yml

@@ -1,37 +0,0 @@
-name: Test Henkei Ruby gem
-
-on:
-  push:
-    branches: [1.x]
-  pull_request:
-    branches: [1.x]
-
-env:
-  CI: true
-
-jobs:
-  test:
-    runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        ruby-version: ['3.0', '3.1', '3.2', '3.3']
-
-    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