yomu 0.2.0 → 0.2.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: ef1ce415813b44ff2a36e29a49b59768dd72f7f3
-  data.tar.gz: 17c69e97c25e156d101e6cef2c5b3f1fb149190d
+  metadata.gz: aa980254ce68ce8915308c43f3df4cc9f83e528a
+  data.tar.gz: ff59cad4c46193986f83cf29aecadba165b3f8dd
 SHA512:
-  metadata.gz: 3ad3d4a04d785d0a31028f91d196d797d98e93f9289693d53987f9f72086c6e1c2a86057bc54055e2eb5db87324d370229cb92e8d2bc1ccccf8ecc09a8764f44
-  data.tar.gz: f1e70048c8c42b9750e14bb0b85250114e0674599663da6418cdc4d893947220247be46e16e002f909170b8f86526bd96c4610a515f1ee0c14728e2a77705a55
+  metadata.gz: 10cd091d61c360f3a9d10a6b94402c362dae43e1c06de1a3b54711d5738b3c89e2b1625f580b783f7eb5960c95bb12fa5cc73dbdff894802f1b63dfc15bcdf25
+  data.tar.gz: 329d48756a77ac689f2247d93b656fd8b772ac1ef617be95a81631d4704030bb17b4765d6df128218efea4fec8fd938470045d9fc0208aa455910977c157331a

data/README.md

@@ -1,8 +1,11 @@
-[![Build Status](https://travis-ci.org/Erol/yomu.png?branch=master)](https://travis-ci.org/Erol/yomu)
-[![Code Climate](https://codeclimate.com/github/Erol/yomu.png)](https://codeclimate.com/github/Erol/yomu)
+[![Travis Build Status](http://img.shields.io/travis/Erol/yomu.svg?style=flat)](https://travis-ci.org/Erol/yomu)
+[![Code Climate Score](http://img.shields.io/codeclimate/github/Erol/yomu.svg?style=flat)](https://codeclimate.com/github/Erol/yomu)
+[![Gem Version](http://img.shields.io/gem/v/yomu.svg?style=flat)](#)
 
 # Yomu 読む
 
+[![Gitter](https://badges.gitter.im/Join%20Chat.svg)](https://gitter.im/Erol/yomu?utm_source=badge&utm_medium=badge&utm_campaign=pr-badge)
+
 [Yomu](http://erol.github.com/yomu) is a library for extracting text and metadata from files and documents using the [Apache Tika](http://tika.apache.org/) content analysis toolkit.
 
 Here are some of the formats supported:
@@ -80,6 +83,12 @@ yomu.mimetype.extensions #=> ['docx']
 
 ## Installation and Dependencies
 
+### Java Runtime
+
+Yomu packages the Apache Tika application jar and requires a working JRE for it to work.
+
+### Gem
+
 Add this line to your application's Gemfile:
 
     gem 'yomu'
@@ -92,8 +101,6 @@ Or install it yourself as:
 
     $ gem install yomu
 
-**Yomu packages the Apache Tika application jar and requires a working JRE for it to work.**
-
 ## Contributing
 
 1. Fork it

data/lib/yomu/version.rb

@@ -1,3 +1,3 @@
 class Yomu
-  VERSION = '0.2.0'
+  VERSION = '0.2.4'
 end

data/lib/yomu.rb

@@ -4,9 +4,16 @@ require 'net/http'
 require 'mime/types'
 require 'json'
 
+require 'socket'
+require 'stringio'
+
 class Yomu
   GEMPATH = File.dirname(File.dirname(__FILE__))
-  JARPATH = File.join(Yomu::GEMPATH, 'jar', 'tika-app-1.5.jar')
+  JARPATH = File.join(Yomu::GEMPATH, 'jar', 'tika-app-1.11.jar')
+  DEFAULT_SERVER_PORT = 9293 # an arbitrary, but perfectly cromulent, port
+
+  @@server_port = nil
+  @@server_pid = nil
 
   # Read text or metadata from a data buffer.
   #
@@ -15,6 +22,21 @@ class Yomu
   #   metadata = Yomu.read :metadata, data
 
   def self.read(type, data)
+    result = @@server_pid ? self._server_read(type, data) : self._client_read(type, data)
+
+    case type
+    when :text
+      result
+    when :html
+      result
+    when :metadata
+      JSON.parse(result)
+    when :mimetype
+      MIME::Types[JSON.parse(result)['Content-Type']].first
+    end
+  end
+
+  def self._client_read(type, data)
     switch = case type
     when :text
       '-t'
@@ -25,23 +47,35 @@ class Yomu
     when :mimetype
       '-m -j'
     end
-    
-    result = IO.popen "#{java} -Djava.awt.headless=true -jar #{Yomu::JARPATH} #{switch}", 'r+' do |io|
+
+    IO.popen "#{java} -Djava.awt.headless=true -jar #{Yomu::JARPATH} #{switch}", 'r+' do |io|
       io.write data
       io.close_write
       io.read
     end
+  end
 
-    case type
-    when :text
-      result
-    when :html
-      result
-    when :metadata
-      JSON.parse(result)
-    when :mimetype
-      MIME::Types[JSON.parse(result)['Content-Type']].first
+
+  def self._server_read(_, data)
+    s = TCPSocket.new('localhost', @@server_port)
+    file = StringIO.new(data, 'r')
+
+    while 1
+      chunk = file.read(65536)
+      break unless chunk
+      s.write(chunk)
     end
+
+    # tell Tika that we're done sending data
+    s.shutdown(Socket::SHUT_WR)
+
+    resp = ''
+    while 1
+      chunk = s.recv(65536)
+      break if chunk.empty? || !chunk
+      resp << chunk
+    end
+    resp
   end
 
   # Create a new instance of Yomu with a given document.
@@ -137,7 +171,6 @@ class Yomu
     end
   end
 
-
   def path?
     defined? @path
   end
@@ -180,6 +213,54 @@ class Yomu
     @data
   end
 
+  # Returns pid of Tika server, started as a new spawned process.
+  #
+  #  type :html, :text or :metadata
+  #  custom_port e.g. 9293
+  #   
+  #  Yomu.server(:text, 9294)
+  #
+  def self.server(type, custom_port=nil)
+    switch = case type
+    when :text
+      '-t'
+    when :html
+      '-h'
+    when :metadata
+      '-m -j'
+    when :mimetype
+      '-m -j'
+    end
+
+    @@server_port = custom_port || DEFAULT_SERVER_PORT
+    
+    @@server_pid = Process.spawn("#{java} -Djava.awt.headless=true -jar #{Yomu::JARPATH} --server --port #{@@server_port} #{switch}")
+    sleep(2) # Give the server 2 seconds to spin up.
+    @@server_pid
+  end
+
+  # Kills server started by Yomu.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.
+  #
+  #  Yomu.server(:text)
+  #  reports = ["report1.docx", "report2.doc", "report3.pdf"]
+  #  begin
+  #    my_texts = reports.map{|report_path| Yomu.new(report_path).text }
+  #  rescue
+  #  ensure
+  #    Yomu.kill_server!
+  #  end
+  def self.kill_server!
+    if @@server_pid
+      Process.kill('INT', @@server_pid)
+      @@server_pid = nil
+      @@server_port = nil
+    end
+  end
+
   def self.java
     ENV['JAVA_HOME'] ? ENV['JAVA_HOME'] + '/bin/java' : 'java'
   end

data/spec/yomu_spec.rb

@@ -149,4 +149,34 @@ describe Yomu do
       expect( yomu.metadata['Content-Type'] ).to eql ["application/vnd.apple.pages", "application/vnd.apple.pages"]
     end
   end
+
+  context 'working as server mode' do
+    specify '#starts and kills server' do
+      begin
+        Yomu.server(:text)
+        expect(Yomu.class_variable_get(:@@server_pid)).not_to be_nil
+        expect(Yomu.class_variable_get(:@@server_port)).not_to be_nil
+
+        s = TCPSocket.new('localhost', Yomu.class_variable_get(:@@server_port))
+        expect(s).to be_a TCPSocket
+        s.close
+      ensure
+        port = Yomu.class_variable_get(:@@server_port)
+        Yomu.kill_server!
+        sleep 2
+        expect { TCPSocket.new('localhost', port) }.to raise_error Errno::ECONNREFUSED
+      end
+    end
+
+    specify '#runs samples through server mode' do
+      begin
+        Yomu.server(:text)
+        expect(Yomu.new('spec/samples/sample.pages').text).to include 'The quick brown fox jumped over the lazy cat.'
+        expect(Yomu.new('spec/samples/sample filename with spaces.pages').text).to include 'The quick brown fox jumped over the lazy cat.'
+        expect(Yomu.new('spec/samples/sample.docx').text).to include 'The quick brown fox jumped over the lazy cat.'
+      ensure
+        Yomu.kill_server!
+      end
+    end
+  end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: yomu
 version: !ruby/object:Gem::Version
-  version: 0.2.0
+  version: 0.2.4
 platform: ruby
 authors:
 - Erol Fornoles
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-04-30 00:00:00.000000000 Z
+date: 2015-12-02 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: mime-types
@@ -96,7 +96,7 @@ files:
 - NOTICE.txt
 - README.md
 - Rakefile
-- jar/tika-app-1.5.jar
+- jar/tika-app-1.11.jar
 - lib/yomu.rb
 - lib/yomu/version.rb
 - spec/helper.rb
@@ -126,7 +126,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.2.2
+rubygems_version: 2.4.6
 signing_key: 
 specification_version: 4
 summary: Read text and metadata from files and documents (.doc, .docx, .pages, .odt,