docsplit 0.1.3 → 0.2.0

data/LICENSE

@@ -1,3 +1,6 @@
+JODConverter ius licensed under the LGPL: gnu.org/licenses/lgpl.html
+PDFBox is licensed under the Apache 2 License: apache.org/licenses/LICENSE-2.0
+
 Copyright (c) 2009 Jeremy Ashkenas, DocumentCloud
 
 Permission is hereby granted, free of charge, to any person

data/docsplit.gemspec

@@ -1,7 +1,7 @@
 Gem::Specification.new do |s|
   s.name      = 'docsplit'
-  s.version   = '0.1.3'         # Keep version in sync with jammit.rb
-  s.date      = '2010-4-27'
+  s.version   = '0.2.0'         # Keep version in sync with docsplit.rb
+  s.date      = '2010-7-29'
 
   s.homepage    = "http://documentcloud.github.com/docsplit/"
   s.summary     = "Break Apart Documents into Images, Text, Pages and PDFs"
@@ -12,7 +12,7 @@ Gem::Specification.new do |s|
     metadata (title, author, number of pages...)
   EOS
 
-  s.authors           = ['Jeremy Ashkenas']
+  s.authors           = ['Jeremy Ashkenas', 'Samuel Clay']
   s.email             = 'jeremy@documentcloud.org'
   s.rubyforge_project = 'docsplit'
   s.has_rdoc          = false

data/lib/docsplit.rb

@@ -1,7 +1,7 @@
 # The Docsplit module delegates to the Java PDF extractors.
 module Docsplit
 
-  VERSION       = '0.1.3' # Keep in sync with gemspec.
+  VERSION       = '0.2.0' # Keep in sync with gemspec.
 
   ROOT          = File.expand_path(File.dirname(__FILE__) + '/..')
 
@@ -26,7 +26,7 @@ module Docsplit
   # Use the ExtractText Java class to write out all embedded text.
   def self.extract_text(pdfs, opts={})
     pdfs = ensure_pdfs(pdfs)
-    run "org.documentcloud.ExtractText", pdfs, opts
+    TextExtractor.new.extract(pdfs, opts)
   end
 
   # Use the ExtractImages Java class to rasterize a PDF into each page's image.
@@ -76,3 +76,4 @@ require 'fileutils'
 require "#{Docsplit::ROOT}/lib/docsplit/image_extractor"
 require "#{Docsplit::ROOT}/lib/docsplit/argument_parser"
 require "#{Docsplit::ROOT}/lib/docsplit/transparent_pdfs"
+require "#{Docsplit::ROOT}/lib/docsplit/text_extractor"

data/lib/docsplit/text_extractor.rb

@@ -0,0 +1,53 @@
+module Docsplit
+  
+  class TextExtractor
+    
+    PAGE_COUNT_MATCHER = /Pages:\s+(\d+?)\n/
+    
+    def extract(pdfs, opts)
+      extract_options opts
+      pdfs = [pdfs].flatten
+      pdfs.each do |pdf|
+        pdf_name = File.basename(pdf, File.extname(pdf))
+        text_path = File.join(@output, "#{pdf_name}.txt")
+        FileUtils.mkdir_p @output
+      
+        if @pages
+          pages = (@pages == 'all') ? 1..get_pages(pdf) : @pages
+          pages.each do |page| 
+            extract_page pdf, page, pdf_name
+          end
+        else
+          cmd = "pdftotext -enc UTF-8 #{pdf} #{text_path}"
+          result = `#{cmd}`.chomp
+          raise ExtractionFailed, result if $? != 0
+        end
+      end
+    end
+  
+    def extract_page(pdf, page, pdf_name)
+      text_path = File.join(@output, "#{pdf_name}_#{page}.txt")
+      cmd = "pdftotext -enc UTF-8 -f #{page} -l #{page} #{pdf} #{text_path}"
+      result = `#{cmd}`.chomp
+      raise ExtractionFailed, result if $? != 0
+      result
+    end
+
+    def get_pages(pdf_path)
+      info = `pdfinfo #{pdf_path}`
+      raise ExtractionFailed, result if $? != 0
+      match = info.match(PAGE_COUNT_MATCHER)
+      raise ExtractionFailed if match.nil?
+      match[1].to_i
+    end
+    
+    private
+    
+    def extract_options(options)
+      @output  = options[:output] || '.'
+      @pages   = options[:pages]
+    end
+
+  end
+  
+end

metadata

@@ -1,20 +1,22 @@
 --- !ruby/object:Gem::Specification 
 name: docsplit
 version: !ruby/object:Gem::Version 
+  hash: 23
   prerelease: false
   segments: 
   - 0
-  - 1
-  - 3
-  version: 0.1.3
+  - 2
+  - 0
+  version: 0.2.0
 platform: ruby
 authors: 
 - Jeremy Ashkenas
+- Samuel Clay
 autorequire: 
 bindir: bin
 cert_chain: []
 
-date: 2010-04-27 00:00:00 -04:00
+date: 2010-07-29 00:00:00 -04:00
 default_executable: 
 dependencies: []
 
@@ -40,6 +42,7 @@ files:
 - lib/docsplit/ExtractPages.java
 - lib/docsplit/ExtractText.java
 - lib/docsplit/image_extractor.rb
+- lib/docsplit/text_extractor.rb
 - lib/docsplit/transparent_pdfs.rb
 - lib/docsplit.rb
 - bin/docsplit
@@ -62,7 +65,7 @@ files:
 - docsplit.gemspec
 - LICENSE
 - README
-has_rdoc: false
+has_rdoc: true
 homepage: http://documentcloud.github.com/docsplit/
 licenses: []
 
@@ -72,23 +75,27 @@ rdoc_options: []
 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: 3
       segments: 
       - 0
       version: "0"
 requirements: []
 
 rubyforge_project: docsplit
-rubygems_version: 1.3.6
+rubygems_version: 1.3.7
 signing_key: 
 specification_version: 3
 summary: Break Apart Documents into Images, Text, Pages and PDFs