pdf_reader 0.0.1

data/MIT-LICENSE

@@ -0,0 +1,20 @@
+Copyright (c) 2009 [name of plugin creator]
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/Manifest

@@ -0,0 +1,9 @@
+Manifest
+Rakefile
+README.rdoc
+MIT-LICENSE
+pdf_reader.gemspec
+lib/pdf_reader.rb
+spec/pdf_reader_spec.rb
+spec/test.html
+spec/test.pdf

data/README.rdoc

@@ -0,0 +1,21 @@
+= PDF Reader plugin
+
+Gem that gives you the "power" to extract raw text from a PDF.
+
+== Installation
+
+Type:
+  sudo gem install finalist-pdf_reader
+
+And... done!
+
+== Usage
+
+Create a new object and call +raw_text+:
+  p = PDFReader.new('test.pdf')
+  puts p.raw_text
+
+... Done!
+
+== Credits
+Copyright 2009, Diederick Lawson - Finalist IT Group. Released under the MIT License.

data/Rakefile

@@ -0,0 +1,23 @@
+require 'rake'
+require 'spec/rake/spectask'
+require 'echoe'
+
+Echoe.new('pdf_reader', '0.0.1') do |p|
+  p.description     = "PDF reader"
+  p.url             = "http://github.com/finalist/pdf_reader"
+  p.author          = "Diederick Lawson"
+  p.email           = "diederick@finalist.com"
+  p.ignore_pattern  = ["tmp/*", "script/*"]
+  p.development_dependencies = []
+end
+
+Dir["#{File.dirname(__FILE__)}/tasks/*.rake"].sort.each { |ext| load ext }
+
+desc 'Default: run specs.'
+task :default => :spec
+
+desc 'Run the specs'
+Spec::Rake::SpecTask.new(:spec) do |t|
+  t.spec_opts = ['--colour --format progress --loadby mtime --reverse']
+  t.spec_files = FileList['spec/**/*_spec.rb']
+end

data/lib/pdf_reader.rb

@@ -0,0 +1,141 @@
+require 'zlib'
+
+class PDFReader
+  def initialize(file)
+    @file = file
+  end
+
+  # extracts all raw text
+  def raw_text
+    text = ''
+
+    objects = get_objects(get_data(@file))
+    objects = decode_objects(objects)
+
+    objects.each { |o| text += o[:data] if(o[:data] and is_text_header?(o[:header])) }
+
+    text
+  end
+
+  private
+
+    # decodes all given chunks to readable text
+    def decode_objects(objects)
+      objects.collect do |o|
+        if(o[:data])
+          o = inflate_object(o) if(is_object_deflated?(o))
+          o[:data] = postscript_to_text(o[:data])
+        end
+      end
+
+      objects.compact
+    end
+
+    # checks whetever the PDF header is a textual header or not
+    def is_text_header?(header)
+      not header.include?('/Subtype') and not header.match(/\/Length[1-3]+/)
+    end
+
+    # parse postscript
+    def postscript_to_text(data)
+      #result      = ''
+      #get_block_data(data, /BT\s/, /\sET/, 3).each do |b|
+      #  result += get_text(data)
+      #end
+      get_text(data)
+    end
+
+    # extracts text from a chunk
+    def get_text(chunk)
+      text_parts  = get_block_data(chunk, /\(/, /\)/, 1)
+      result      = ''
+
+      # everything between ()'s is text
+      unless text_parts.empty?
+        text_parts.each do |t|
+          result += t[1..-2]
+        end
+      end
+
+      return result
+    end
+
+    # deflates a chunk if it is compressed
+    def inflate_object(object)
+      z = Zlib::Inflate.new()
+      object[:data] = z.inflate(object[:data])
+      z.close
+
+      return object
+    end
+
+    # tests if a chunk is compressed
+    def is_object_deflated?(object)
+      object[:header].include?('FlateDecode')
+    end
+
+    # retrieve raw chunks from given string
+    def get_objects(data)
+      get_block_data(data, /obj/, /endobj/, 6).collect { |o| get_chunk(o) }.compact
+    end
+
+    # retrieves a chunk from an extracted object
+    def get_chunk(object)
+      chunk_headers = get_block_data(object, /<</, />>/, 2)
+
+      return { :header => chunk_headers[0], :data => get_stream_data(object) } unless(chunk_headers.empty?)
+    end
+
+    # retrieves data beteween "stream" and "endstream" word
+    def get_stream_data(object)
+      start_word        = /stream(\n|\r\n)/
+      end_word          = /endstream/
+      start_word_length = 7
+      end_word_length   = 9
+      stream_objects    = get_block_data(object, start_word, end_word, end_word_length)
+
+      unless(stream_objects.empty?)
+        start_index   = stream_objects[0].index(start_word)
+        end_index     = stream_objects[0].index(end_word)
+
+        # tricky stuff
+        start_word_length = 8 if(stream_objects[0][1..8] == "stream\r\n")
+
+        # extract 1 byte extra because endstream can have 1 random byte as end character (rtfm)
+        data = stream_objects[0].slice(start_word_length, stream_objects[0].length - start_word_length - end_word_length - 1)
+      end
+
+      return data unless data.nil?
+    end
+
+    # returns whole file contents
+    def get_data(file)
+      f = File.open(file, 'rb')
+      buffer = f.read
+      f.close
+
+      buffer
+    end
+
+    # retrieves objects from given string
+    def get_block_data(data, start_word, end_word, end_word_length)
+      objects     = []
+      start_index = 0
+      end_index   = 0
+
+      # this is a bit of cheesy... if someone knows a better way to do this?
+      while(not start_index.nil? and not end_index.nil?) do
+        start_index = data.index(start_word, end_index)
+
+        unless(start_index.nil?)
+          end_index = data.index(end_word, start_index)
+
+          unless(end_index.nil?)
+            objects.push(data.slice(start_index, end_index - start_index + end_word_length))
+          end
+        end
+      end
+
+      objects
+    end
+end

data/pdf_reader.gemspec

@@ -0,0 +1,30 @@
+# -*- encoding: utf-8 -*-
+
+Gem::Specification.new do |s|
+  s.name = %q{pdf_reader}
+  s.version = "0.0.1"
+
+  s.required_rubygems_version = Gem::Requirement.new(">= 1.2") if s.respond_to? :required_rubygems_version=
+  s.authors = ["Diederick Lawson"]
+  s.date = %q{2009-07-06}
+  s.description = %q{PDF Reader}
+  s.email = %q{diederick@finalist.com}
+  s.extra_rdoc_files = ["lib/pdf_reader.rb", "README.rdoc"]
+  s.files = ['Manifest', 'Rakefile', 'README.rdoc', 'MIT-LICENSE', 'pdf_reader.gemspec', 'lib/pdf_reader.rb', 'spec/pdf_reader_spec.rb', 'spec/test.html', 'spec/test.pdf']
+  s.homepage = %q{http://github.com/finalist/pdf_reader}
+  s.rdoc_options = ["--line-numbers", "--inline-source", "--title", "Pdf_reader", "--main", "README.rdoc"]
+  s.require_paths = ["lib"]
+  s.rubyforge_project = %q{pdf_reader}
+  s.rubygems_version = %q{1.3.4}
+  s.summary = %q{PDF Reader}
+
+  if s.respond_to? :specification_version then
+    current_version = Gem::Specification::CURRENT_SPECIFICATION_VERSION
+    s.specification_version = 3
+
+    if Gem::Version.new(Gem::RubyGemsVersion) >= Gem::Version.new('1.2.0') then
+    else
+    end
+  else
+  end
+end

data/spec/pdf_reader_spec.rb

@@ -0,0 +1,10 @@
+require 'rubygems'
+require 'spec'
+Dir.glob(File.join(File.dirname(__FILE__), '..', 'lib', '*.rb')).each { |f| require f }
+
+describe PdfReaderSpec do
+  it "should extract raw text from pdf" do
+    p = PDFReader.new('test/test.pdf')
+    p.raw_text.should eql('Test PDF, try and read me!')
+  end
+end

data/spec/test.html

@@ -0,0 +1 @@
+Test PDF, try and read me!

metadata

@@ -0,0 +1,82 @@
+--- !ruby/object:Gem::Specification 
+name: pdf_reader
+version: !ruby/object:Gem::Version 
+  hash: 29
+  prerelease: 
+  segments: 
+  - 0
+  - 0
+  - 1
+  version: 0.0.1
+platform: ruby
+authors: 
+- Diederick Lawson
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2009-07-06 00:00:00 +02:00
+default_executable: 
+dependencies: []
+
+description: PDF Reader
+email: diederick@finalist.com
+executables: []
+
+extensions: []
+
+extra_rdoc_files: 
+- lib/pdf_reader.rb
+- README.rdoc
+files: 
+- Manifest
+- Rakefile
+- README.rdoc
+- MIT-LICENSE
+- pdf_reader.gemspec
+- lib/pdf_reader.rb
+- spec/pdf_reader_spec.rb
+- spec/test.html
+- spec/test.pdf
+has_rdoc: true
+homepage: http://github.com/finalist/pdf_reader
+licenses: []
+
+post_install_message: 
+rdoc_options: 
+- --line-numbers
+- --inline-source
+- --title
+- Pdf_reader
+- --main
+- README.rdoc
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
+      version: "0"
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 11
+      segments: 
+      - 1
+      - 2
+      version: "1.2"
+requirements: []
+
+rubyforge_project: pdf_reader
+rubygems_version: 1.6.2
+signing_key: 
+specification_version: 3
+summary: PDF Reader
+test_files: []
+