yomu 0.2.1 → 0.2.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 763e0175f0348e0128b7a24344c58ef9580991c2
-  data.tar.gz: 3ac16148db3fbe1f3f464745156e42ec490228dd
+  metadata.gz: 2b10bc01c33add15e33c6dc602f7a511c43ae5d2
+  data.tar.gz: e8a3e57a23dcea65214dee6bc66888ab6ef8edc2
 SHA512:
-  metadata.gz: c6cbd2370dfa5569e9d5efdc8214c24788d60a3f33981a07e603a45442e48781452004a76a0d5f75484dbb825320caa7a8f7314e7d8a19d807abb4178edb6849
-  data.tar.gz: c425f26e52562d5690f5bd8a104dd0763101b191983a6b58f2f10f3e1c278fa146d668f4e2dbce5b144a6a76125684b4139cee48550c793bb2b9d3ba53d0f0fd
+  metadata.gz: bfcc975fb5fd48b23bfbfc9ea8c22e536e0539e1a2783babdcfb07675c9409be446eb8ed3ee005d34d14df11d83686a72b1a5ae7f310dffffaa09140f3ff2ec5
+  data.tar.gz: 903302d0a7dd19cca22a37cc8311131fb1b7282cef3a9e8be0271bbb5c9f47516431adac606b8e44fd09e67f858daa25445fc35919f11873ce684e81be4f5f61

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-1.6.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/lib/yomu/version.rb

@@ -1,3 +1,3 @@
 class Yomu
-  VERSION = '0.2.1'
+  VERSION = '0.2.2'
 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: 0.2.1
+  version: 0.2.2
 platform: ruby
 authors:
 - Erol Fornoles
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-12-19 00:00:00.000000000 Z
+date: 2014-12-20 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: mime-types
@@ -126,7 +126,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.2.0
+rubygems_version: 2.2.2
 signing_key: 
 specification_version: 4
 summary: Read text and metadata from files and documents (.doc, .docx, .pages, .odt,