tika-masala 1.5.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 0fb65303c39a65b4aa4c400c6799b29191129312
+  data.tar.gz: 243d05f8cf30c689d816eac20cbd2e623781cb20
+SHA512:
+  metadata.gz: 63b7b6cff214a93f4dc4b8469e037d2ca9c2a106fe428aed195c7673e11974ba396fd9d121e68916b10a5c8211f0391f76a60c41ffff316ea6a5ba50fcb46758
+  data.tar.gz: a7ae5316c4f9aa14408af801dd9365728346afbff5387349ac4a14c8ca3867a3e86522884cc9b62fcee45dcbac5629bd8a225d887cb57025e2228ba5143a9d1c

data/Gemfile

@@ -0,0 +1,7 @@
+source 'https://rubygems.org'
+
+gemspec
+
+group :test do
+  gem 'pry'
+end

data/Gemfile.lock

@@ -0,0 +1,36 @@
+PATH
+  remote: .
+  specs:
+    tika-masala (1.5.0)
+
+GEM
+  remote: https://rubygems.org/
+  specs:
+    coderay (1.1.0)
+    diff-lcs (1.2.5)
+    method_source (0.8.2)
+    pry (0.9.12.3)
+      coderay (~> 1.0)
+      method_source (~> 0.8)
+      slop (~> 3.4)
+    rspec (3.0.0)
+      rspec-core (~> 3.0.0)
+      rspec-expectations (~> 3.0.0)
+      rspec-mocks (~> 3.0.0)
+    rspec-core (3.0.4)
+      rspec-support (~> 3.0.0)
+    rspec-expectations (3.0.4)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.0.0)
+    rspec-mocks (3.0.4)
+      rspec-support (~> 3.0.0)
+    rspec-support (3.0.4)
+    slop (3.4.7)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  pry
+  rspec (~> 3.0)
+  tika-masala!

data/README.md

@@ -0,0 +1,37 @@
+# TikaMasala
+
+Simple Wrapper around Tika to parse documents.
+
+## Usage
+
+```ruby
+parser = TikaMasala::Parser.new('/path/to/tika/jar/file')
+parser.parse('/path/to/pdf')
+```
+
+Everything uses `options` behind the scene to pass arguments:
+
+```ruby
+parser.options('--detect', '/path/to/file')
+```
+
+## What if tika can't parse a document?
+
+The exception thrown contain both the stdout and stderr output. Which means
+that you can still retrieve part of the content you were trying to extract.
+
+```ruby
+parser = TikaMasala::Parser.new('/path/to/tika/jar/file')
+
+begin
+  parser.parse('/path/to/pdf')
+rescue TikaMasala::TikaError => e
+  # Let's say it produced an error
+  e.stdout # contains the parsed text until it reached an error
+  e.stderr # contains the exception raised by Java
+end
+```
+
+## Versions
+
+The version match the version of tika distributed.

data/lib/tika-masala.rb

@@ -0,0 +1 @@
+require_relative 'tika-masala/parser'

data/lib/tika-masala/exceptions/tika_error.rb

@@ -0,0 +1,11 @@
+module TikaMasala
+  class TikaError < StandardError
+    attr_reader :stdout
+
+    def initialize(options = {})
+      @stdout = options.fetch(:stdout, '')
+
+      super("Non-zero exit code (#{options[:exitstatus]}): #{options[:stderr]}")
+    end
+  end
+end

data/lib/tika-masala/parser.rb

@@ -0,0 +1,53 @@
+require 'open3'
+require_relative 'exceptions/tika_error'
+
+module TikaMasala
+  class FileNotFound < StandardError; end
+
+  class Parser
+    attr_reader :jar_path
+
+    def initialize(jar_path = nil)
+      if jar_path.nil?
+        jar_path = File.expand_path(File.join('..', '..', '..', 'dependencies', 'tika-app-1.5.jar'), __FILE__)
+      end
+
+      raise FileNotFound, "Jar #{jar_path} does not exist" unless File.exists?(jar_path)
+
+      @jar_path = jar_path
+    end
+
+    def parse(file)
+      java_exec('--text', file)
+    end
+
+    def metadata(file)
+      java_exec('--metadata', file)
+    end
+
+    def detect_type(file)
+      java_exec('--detect', file)
+    end
+
+    def java_exec(*args)
+      stdin, stdout, stderr, wait_thr = Open3.popen3("java -jar #{@jar_path.shellescape} #{args.shelljoin}")
+
+      exitstatus = wait_thr.value
+
+      if exitstatus != 0
+        expection = TikaError.new(
+          stdout: stdout.read,
+          stderr: stderr.read,
+          exitstatus: exitstatus
+        )
+        raise expection
+      else
+        stdout.read
+      end
+    ensure
+      stdin.close
+      stdout.close
+      stderr.close
+    end
+  end
+end

data/spec/lib/parser_spec.rb

@@ -0,0 +1,126 @@
+require 'spec_helper'
+
+RSpec.describe TikaMasala::Parser do
+  subject { described_class.new(tika_jar) }
+
+  let(:tika_jar) { jar_path('tika-app-1.5.jar') }
+  let(:pdf_file) { fixtures_path('test.pdf') }
+  let(:word_file) { fixtures_path('test.docx') }
+
+  it { respond_to(:parse) }
+
+  describe 'initialize' do
+    subject { described_class }
+
+    let(:fake_path) { '/no/such/file/exist' }
+
+    it 'raises an exception if the file does not exist' do
+      expect {
+        subject.new(fake_path)
+      }.to raise_error TikaMasala::FileNotFound, "Jar #{fake_path} does not exist"
+    end
+
+    context 'when no parameters are passed' do
+      it 'sets the jar to the one in our dependencies folder' do
+        expect(subject.new.jar_path).to eq(jar_path('tika-app-1.5.jar'))
+      end
+    end
+  end
+
+  describe '#parse' do
+    it 'parses pdf files properly' do
+      expect(subject.parse(pdf_file)).to match(/hello world/i)
+    end
+
+    it 'parses word files properly' do
+      expect(subject.parse(word_file)).to match(/hello world/i)
+    end
+
+    context 'when the file does not exist' do
+      it 'raises an exception' do
+        expect { subject.parse(fixtures_path('file-dont-exist.ppt')) }.to raise_error(TikaMasala::TikaError)
+      end
+    end
+
+    context 'when the file url contains reserved shell words' do
+      let(:file_path) { 'http://example.com/?token=123&param=a' }
+      let(:file_path_escaped) { 'http://example.com/\\?token\\=123\\&param\\=a' }
+      let(:popen_result_double) do
+        [
+          double('stdin', close: true),
+          double('stdout', close: true, read: ''),
+          double('stderr', close: true),
+          double('wait_thr', value: 0)
+        ]
+      end
+
+      it 'escapes the string properly' do
+        expect(Open3).to receive(:popen3).with("java -jar #{tika_jar} --text #{file_path_escaped}") do
+          popen_result_double
+        end
+
+        subject.parse(file_path)
+      end
+    end
+  end
+
+  describe '#metadata' do
+    it 'checks the metadata from the file' do
+      expect(subject.metadata(word_file)).to match(/Content-Type.*word/i)
+    end
+  end
+
+  describe '#detect_type' do
+    it 'finds the file type' do
+      expect(subject.detect_type(pdf_file)).to match(/application.pdf/i)
+    end
+  end
+
+  describe '#java_exec' do
+    it 'takes option directly to tika' do
+      expect(subject.java_exec('--text', word_file)).to match(/hello world/i)
+    end
+
+    context 'when exit code is not zero' do
+      let(:command) { "echo '#{normal_message}'; echo '#{error_message}' 1>&2; exit 1;" }
+      let(:error_message) { 'Some nasty error occured' }
+      let(:normal_message) { 'Hello world' }
+
+      before do
+        popen_result = Open3.popen3(command)
+
+        allow(Open3).to receive(:popen3) do |*args, &block|
+          if block_given?
+            block.call(*popen_result)
+          else
+            popen_result
+          end
+        end
+      end
+
+      it 'raises an exception containing stderr' do
+        expect { subject.java_exec }.to raise_error(TikaMasala::TikaError, /#{error_message}/)
+      end
+
+      describe 'the expection raised' do
+        let(:returned_expection) do
+          [].tap do |returned_expection|
+            begin
+              subject.java_exec
+            rescue TikaMasala::TikaError => e
+              returned_expection << e
+            end
+          end.first
+        end
+
+        it 'does not contain the normal message' do
+          expect(returned_expection.message).to_not include(normal_message)
+        end
+
+        it 'provides another attribute which contains the ouput of stdout' do
+          expect(returned_expection.stdout).to include(normal_message)
+        end
+      end
+    end
+  end
+end

data/spec/spec_helper.rb

@@ -0,0 +1,7 @@
+require_relative '../lib/tika-masala'
+
+Dir[File.dirname(__FILE__) + "/support/**/*.rb"].each {|f| require f}
+
+RSpec.configure do |config|
+  config.include SpecPaths
+end

data/spec/support/spec_paths.rb

@@ -0,0 +1,13 @@
+module SpecPaths
+  def fixtures_path(*file)
+    root_path('spec', 'fixtures', *file)
+  end
+
+  def jar_path(*file)
+    root_path('dependencies', *file)
+  end
+
+  def root_path(*file)
+    File.expand_path(File.join('..', '..', '..', *file), __FILE__)
+  end
+end

data/tika-masala.gemspec

@@ -0,0 +1,15 @@
+Gem::Specification.new do |s|
+  s.name        = 'tika-masala'
+  s.version     = '1.5.0'
+  s.date        = '2014-03-31'
+  s.summary     = "Tika wrapper for MRI"
+  s.description = "Provides ruby wrapper around tika command line tools"
+  s.authors     = ["Vincent Bonmalais"]
+  s.email       = 'vincent.bonmalais@econsultancy.com'
+  s.files       = `git ls-files`.split("\n")
+  s.test_files  = `git ls-files -- spec`.split("\n")
+  s.homepage    = 'https://github.com/econsultancy/tika-masala'
+  s.license     = 'MIT'
+
+  s.add_development_dependency('rspec', '~>3.0')
+end

metadata

@@ -0,0 +1,75 @@
+--- !ruby/object:Gem::Specification
+name: tika-masala
+version: !ruby/object:Gem::Version
+  version: 1.5.0
+platform: ruby
+authors:
+- Vincent Bonmalais
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2014-03-31 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '3.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '3.0'
+description: Provides ruby wrapper around tika command line tools
+email: vincent.bonmalais@econsultancy.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- Gemfile
+- Gemfile.lock
+- README.md
+- dependencies/tika-app-1.5.jar
+- lib/tika-masala.rb
+- lib/tika-masala/exceptions/tika_error.rb
+- lib/tika-masala/parser.rb
+- spec/fixtures/test.docx
+- spec/fixtures/test.pdf
+- spec/lib/parser_spec.rb
+- spec/spec_helper.rb
+- spec/support/spec_paths.rb
+- tika-masala.gemspec
+homepage: https://github.com/econsultancy/tika-masala
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.2.1
+signing_key: 
+specification_version: 4
+summary: Tika wrapper for MRI
+test_files:
+- spec/fixtures/test.docx
+- spec/fixtures/test.pdf
+- spec/lib/parser_spec.rb
+- spec/spec_helper.rb
+- spec/support/spec_paths.rb