rika 1.11.1-java → 2.0.0-java

data/spec/rika/tika_loader_spec.rb

@@ -0,0 +1,57 @@
+# frozen_string_literal: true
+
+require 'spec_helper'
+require 'rika/tika_loader'
+
+describe Rika::TikaLoader do
+  describe '.require_tika' do
+    it 'returns the correct Tika jar file path' do
+      expect(described_class.require_tika).to match(/tika-app-.*\.jar/)
+    end
+
+    it 'calls print_message_and_exit if the Tika jar file cannot be loaded' do
+      allow(ENV).to receive(:[]).with('TIKA_JAR_FILESPEC').and_return('nonexistent_file')
+      expect { described_class.require_tika }.to raise_error(Rika::TikaLoadError) \
+        .with_message(/Unable to load Tika jar file from 'nonexistent_file'./)
+    end
+  end
+
+  describe '.specified_tika_filespec' do
+    it 'returns the correct Tika jar file path' do
+      expect(described_class.send(:specified_tika_filespec)).to match(/tika-app-.*\.jar/)
+    end
+
+    it 'raises a TikaLoadError if the Tika jar filespec is not specified at all in TIKA_JAR_FILESPEC' do
+      allow(ENV).to receive(:[]).with('TIKA_JAR_FILESPEC').and_return(nil)
+      expect { described_class.send(:specified_tika_filespec) }.to raise_error(Rika::TikaLoadError) \
+        .with_message(/Environment variable TIKA_JAR_FILESPEC is not set./)
+    end
+  end
+
+  describe '.print_message_and_exit' do
+    it 'prints the correct message and exits with an exit code of 1' do
+      stderr_orig = $stderr
+      $stderr = StringIO.new
+
+      begin
+        expect { described_class.send(:print_message_and_exit, 'message') }.to raise_error(SystemExit) do |error|
+          expect(error.status).to eq(1)
+        end
+        expect($stderr.string).to match(/message/)
+      ensure
+        $stderr = stderr_orig
+      end
+    end
+  end
+
+  describe '.formatted_error_message' do
+    it 'returns the correct message' do
+      message = 'This is a test message.'
+      expect(described_class.send(:formatted_error_message, message)).to match(/#{message}/)
+    end
+
+    it 'returns the correct banner' do
+      expect(described_class.send(:formatted_error_message, 'message').lines.grep(/!{79}/).size).to be >= 2
+    end
+  end
+end

data/spec/spec_helper.rb

@@ -1,15 +1,22 @@
-require "rika"
+# frozen_string_literal: true
 
-def file_path( *paths )
+require 'simplecov'
+SimpleCov.start { add_filter '/spec/' }
+
+require 'rika'
+
+def fixture_path(*paths)
   File.expand_path(File.join(File.dirname(__FILE__), 'fixtures', *paths))
 end
 
 # See http://rubydoc.info/gems/rspec-core/RSpec/Core/Configuration
 RSpec.configure do |config|
-
   # Enable the line below if you want ", focus: true" after a test declaration to
   # denote the only tests that will be run:
   # config.filter_run :focus
 
   config.order = 'random'
+  config.example_status_persistence_file_path = 'spec/rspec-failed-tests-control-file.txt'
 end
+
+Rika.init

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: rika
 version: !ruby/object:Gem::Version
-  version: 1.11.1
+  version: 2.0.0
 platform: java
 authors:
 - Richard Nyström
@@ -9,56 +9,48 @@ authors:
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2020-07-24 00:00:00.000000000 Z
+date: 2023-09-08 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '3.9'
-  name: rspec
-  type: :development
+        version: '0'
+  name: awesome_print
   prerelease: false
+  type: :runtime
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '3.9'
-- !ruby/object:Gem::Dependency
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '13.0'
-  name: rake
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '13.0'
-description: " A JRuby wrapper for Apache Tika to extract text and metadata from files\
-  \ of various formats. "
+        version: '0'
+description: A JRuby wrapper for Apache Tika to extract text and metadata from files
+  of various formats.
 email:
 - ricny046@gmail.com
 - keithrbennett@gmail.com
-executables: []
+executables:
+- rika
 extensions: []
 extra_rdoc_files: []
 files:
 - ".gitignore"
 - ".rspec"
-- ".travis.yml"
+- ".rubocop.yml"
 - Gemfile
 - LICENSE.txt
 - README.md
 - RELEASE_NOTES.md
 - Rakefile
-- java-lib/tika-app-1.24.1.jar
+- bin/rika
 - lib/rika.rb
+- lib/rika/cli/args_parser.rb
+- lib/rika/cli/rika_command.rb
+- lib/rika/formatters.rb
+- lib/rika/parse_result.rb
 - lib/rika/parser.rb
+- lib/rika/tika_loader.rb
 - lib/rika/version.rb
 - pom.xml
 - rika.gemspec
@@ -67,22 +59,36 @@ files:
 - spec/fixtures/document.doc
 - spec/fixtures/document.docx
 - spec/fixtures/document.pdf
+- spec/fixtures/document.txt
 - spec/fixtures/en.txt
 - spec/fixtures/es.txt
 - spec/fixtures/fr.txt
 - spec/fixtures/image.jpg
+- spec/fixtures/image_jpg_without_extension
 - spec/fixtures/lang_cant_be_determined.txt
 - spec/fixtures/ru.txt
-- spec/fixtures/text_file.txt
-- spec/fixtures/text_file_without_extension
+- spec/fixtures/tiny.txt
 - spec/fixtures/unknown.bin
-- spec/rika_spec.rb
+- spec/rika/cli/args_parser_spec.rb
+- spec/rika/cli/rika_command_spec.rb
+- spec/rika/formatters_spec.rb
+- spec/rika/parse_result_spec.rb
+- spec/rika/parser_spec.rb
+- spec/rika/rika_spec.rb
+- spec/rika/tika_loader_spec.rb
 - spec/spec_helper.rb
 homepage: https://github.com/keithrbennett/rika
 licenses:
 - Apache-2.0
-metadata: {}
-post_install_message:
+metadata:
+  rubygems_mfa_required: 'true'
+post_install_message: |2+
+
+  Using the rika gem requires that you:
+    1) download the Apache Tika tika-app jar file from https://tika.apache.org/download.html
+    2) place it somewhere accessible to the running application
+    3) specify its location in the TIKA_JAR_FILESPEC environment variable
+
 rdoc_options: []
 require_paths:
 - lib
@@ -97,24 +103,9 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.0.6
+rubygems_version: 3.3.26
 signing_key:
 specification_version: 4
 summary: A JRuby wrapper for Apache Tika to extract text and metadata from files of
   various formats.
-test_files:
-- spec/fixtures/de.txt
-- spec/fixtures/document.doc
-- spec/fixtures/document.docx
-- spec/fixtures/document.pdf
-- spec/fixtures/en.txt
-- spec/fixtures/es.txt
-- spec/fixtures/fr.txt
-- spec/fixtures/image.jpg
-- spec/fixtures/lang_cant_be_determined.txt
-- spec/fixtures/ru.txt
-- spec/fixtures/text_file.txt
-- spec/fixtures/text_file_without_extension
-- spec/fixtures/unknown.bin
-- spec/rika_spec.rb
-- spec/spec_helper.rb
+test_files: []

data/.travis.yml

@@ -1,7 +0,0 @@
-language: ruby
-rvm:
-  - jruby-9.2.12.0
-notifications:
-  recipients:
-    - ricny046@gmail.com
-    - keithrbennett@gmail.com

data/spec/fixtures/text_file_without_extension

@@ -1,23 +0,0 @@
-Stopping by Woods on a Snowy Evening
-
-By Robert Frost
-
-Whose woods these are I think I know.   
-His house is in the village though;   
-He will not see me stopping here   
-To watch his woods fill up with snow.   
-
-My little horse must think it queer   
-To stop without a farmhouse near   
-Between the woods and frozen lake   
-The darkest evening of the year.   
-
-He gives his harness bells a shake   
-To ask if there is some mistake.   
-The only other sound’s the sweep   
-Of easy wind and downy flake.   
-
-The woods are lovely, dark and deep,   
-But I have promises to keep,   
-And miles to go before I sleep,   
-And miles to go before I sleep.

data/spec/rika_spec.rb

@@ -1,245 +0,0 @@
-# encoding: utf-8
-
-require 'spec_helper'
-require 'webrick'
-
-include WEBrick
-
-describe Rika::Parser do
-
-    let (:txt_parser)       { Rika::Parser.new(file_path('text_file.txt')) }
-    let (:docx_parser)      { Rika::Parser.new(file_path('document.docx')) }
-    let (:doc_parser)       { Rika::Parser.new(file_path('document.doc'))  }
-    let (:pdf_parser)       { Rika::Parser.new(file_path('document.pdf'))  }
-    let (:image_parser)     { Rika::Parser.new(file_path('image.jpg'))     }
-    let (:unknown_parser)   { Rika::Parser.new(file_path('unknown.bin'))   }
-    let (:dir)              { File.expand_path(File.join(File.dirname(__FILE__), 'fixtures')) }
-    let (:quote_first_line) { 'Stopping by Woods on a Snowy Evening' }
-
-    port = 50515
-    let (:url) { "http://#{Socket.gethostname}:#{port}" }
-
-    let (:sample_pdf_filespec) { file_path('document.pdf') }
-
-    let(:first_line) { ->(string) { string.split("\n").first.strip } }
-
-    let(:server_runner) do
-      # returns a lambda that, when passed an action, will wrap it in an HTTP server
-      ->(action) do
-        server = nil
-        server_thread = Thread.new do
-          server = HTTPServer.new(
-              Port:         port,
-              DocumentRoot: dir,
-              AccessLog:    [],
-              Logger:       WEBrick::Log::new('/dev/null')
-          )
-          server.start
-        end
-
-        # Wait for server to become ready on its new thread
-        sleep 0.01 while server.nil?
-        begin
-          action.call
-        ensure
-          server.shutdown
-          server_thread.exit
-        end
-      end
-    end
-
-
-  it 'should raise error if file does not exist' do
-    expect(-> { Rika::Parser.new(file_path('nonexistent_file.txt')) }).to raise_error(IOError)
-  end
-
-  it 'should raise error if URL does not exist' do
-    unavailable_server = 'http://k6075sd0dfkr8nvfw0zvwfwckucf2aba.com'
-    unavailable_file_on_web = File.join(unavailable_server, 'x.pdf')
-    expect(-> { Rika::Parser.new(unavailable_file_on_web) }).to raise_error(SocketError)
-  end
-
-  it 'should detect file type without a file extension' do
-    parser = Rika::Parser.new(file_path('text_file_without_extension'))
-    expect(parser.metadata['Content-Type']).to eq('text/plain; charset=UTF-8')
-  end
-
-  describe '#content' do
-    it 'should return the content in a text file' do
-      expect(first_line.(txt_parser.content)).to eq(quote_first_line)
-    end
-
-    it 'should return the content in a docx file' do
-      expect(first_line.(docx_parser.content)).to eq(quote_first_line)
-    end
-
-    it 'should return the content in a pdf file' do
-      expect(first_line.(pdf_parser.content)).to eq(quote_first_line)
-    end
-
-    it 'should return no content for an image' do
-      expect(image_parser.metadata.keys).to_not be_empty
-    end
-
-    it 'should only return max content length' do
-      expect(Rika::Parser.new(file_path('text_file.txt'), 9).content).to eq('Stopping')
-    end
-
-    it 'should only return max content length for file over http', focus: true do
-      server_runner.call( -> do
-        expect(Rika::Parser.new(File.join(url, 'document.pdf'), 9).content).to eq('Stopping')
-      end)
-    end
-
-    it 'should return the content from a file over http' do
-      server_runner.call( -> do
-        content = Rika::Parser.new(File.join(url, 'document.pdf')).content
-        expect(first_line.(content)).to eq(quote_first_line)
-      end)
-    end
-
-    it 'should return empty string for unknown file' do
-      expect(unknown_parser.content).to be_empty
-    end
-  end
-
-  # We just test a few of the metadata fields for some common file formats
-  # to make sure the integration with Apache Tika works. Apache Tika already
-  # have tests for all file formats it supports so we won't retest that
-  describe '#metadata' do
-    it 'should return nil if metadata field does not exist' do
-      expect(txt_parser.metadata['nonsense']).to be_nil
-    end
-
-    it 'should return metadata from a docx file' do
-      expect(docx_parser.metadata['Page-Count']).to eq('1')
-    end
-
-    it 'should return metadata from a pdf file' do
-      expect(pdf_parser.metadata['Author']).to eq('Robert Frost')
-    end
-
-    it 'should return metadata from a file over http', focus: true do
-      server_runner.call( -> do
-        parser = Rika::Parser.new(File.join(url, 'document.pdf'))
-        expect(parser.metadata['Author']).to eq('Robert Frost')
-      end)
-    end
-
-    it 'should return metadata from an image' do
-      expect(image_parser.metadata['Image Height']).to eq('72 pixels')
-      expect(image_parser.metadata['Image Width']).to  eq('72 pixels')
-    end
-  end
-
-  describe '#available_metadata' do
-    it 'should return available metadata fields' do
-      expect(txt_parser.available_metadata).to_not be_empty
-    end
-
-    it 'should be an array' do
-      expect(txt_parser.available_metadata).to be_an(Array)
-    end
-  end
-
-  describe '#metadata_exists?' do
-    it 'should return false if metadata does not exist' do
-      expect(txt_parser.metadata_exists?('title')).to be false
-    end
-
-    it 'should return true if metadata exist' do
-      expect(docx_parser.metadata_exists?('title')).to be true
-    end
-  end
-
-  describe '#media_type' do
-    it 'should return application/pdf for a pdf file' do
-      expect(pdf_parser.media_type).to eq('application/pdf')
-    end
-
-    it 'should return text/plain for a txt file' do
-      expect(txt_parser.media_type).to eq('text/plain')
-    end
-
-    it 'should return application/pdf for a pdf over http' do
-      server_runner.call( -> do
-        parser = Rika::Parser.new(File.join(url, 'document.pdf'))
-        expect(parser.media_type).to eq('application/pdf')
-      end)
-    end
-
-    it 'should return application/octet-stream for unknown file' do
-      expect(unknown_parser.media_type).to eq('application/octet-stream')
-    end
-
-    it 'should return msword for a doc file' do
-      expect(doc_parser.media_type).to eq('application/msword')
-    end
-
-    it 'should return wordprocessingml for a docx file' do
-      expect(docx_parser.media_type).to eq('application/vnd.openxmlformats-officedocument.wordprocessingml.document')
-    end
-  end
-
-  describe '#language' do
-    it 'should return the language of the content' do
-      %w(en de fr ru es).each do |lang|
-        txt = Rika::Parser.new(file_path("#{lang}.txt"))
-        expect(txt.language).to eq(lang)
-      end
-    end
-  end
-
-  # See note in rika.rb #language_is_reasonably_certain? regarding this method's future.
-  describe '#language_is_reasonably_certain?' do
-    it "should return false if lang can't be determined" do
-      lang = Rika::Parser.new(file_path("lang_cant_be_determined.txt"))
-      lang.language_is_reasonably_certain? == false
-    end
-
-    it "should return true if language can be determined" do
-      lang = Rika::Parser.new(file_path("en.txt"))
-      lang.language_is_reasonably_certain? == true
-    end
-  end
-
-  it 'should return valid content using Rika.parse_content' do
-    content = Rika.parse_content(sample_pdf_filespec)
-    expect(content).to be_a(String)
-    expect(content).to_not be_empty
-  end
-
-  it 'should return valid metadata using Rika.parse_metadata' do
-    metadata = Rika.parse_metadata(sample_pdf_filespec)
-    expect(metadata).to be_a(Hash)
-    expect(metadata).to_not be_empty
-  end
-
-  it 'should return valid content and metadata using Rika.parse_content_and_metadata' do
-    content, metadata = Rika.parse_content_and_metadata(sample_pdf_filespec)
-    expect(content).to be_a(String)
-    expect(content).to_not be_empty
-    expect(metadata).to be_a(Hash)
-    expect(metadata).to_not be_empty
-  end
-
-  specify 'both means of getting both content and metadata should return the same values' do
-    content_1, metadata_1 = Rika.parse_content_and_metadata(sample_pdf_filespec)
-
-    h = Rika.parse_content_and_metadata_as_hash(sample_pdf_filespec)
-    content_2  = h[:content]
-    metadata_2 = h[:metadata]
-
-    expect(content_1).to eq(content_2)
-    expect(metadata_1).to eq(metadata_2)
-  end
-
-  specify 'getting content and metadata individually and together should return the same values' do
-    content_1, metadata_1 = Rika.parse_content_and_metadata(sample_pdf_filespec, -1)
-    content_2             = Rika.parse_content(sample_pdf_filespec)
-    metadata_2            = Rika.parse_metadata(sample_pdf_filespec, -1)
-
-    expect(content_1).to eq(content_2)
-    expect(metadata_1).to eq(metadata_2)
-  end
-end