pdftohtmlr 0.2.0 → 0.3.0

data/README.textile

@@ -8,13 +8,22 @@ h1. requirements
 
 Just pdftohtml and Ruby (1.8.6+ as far as I know).
 
+h1. install
+
+"http://gemcutter.org/gems/pdftohtmlr":http://gemcutter.org/gems/pdftohtmlr
+
+<pre><code>gem install pdftohtmlr</code></pre>
+    
 h1. using
-<pre>
-<code>
+<pre><code lang="ruby">require 'pdftohtmlr'
+require 'nokogiri'
 file = PdfFile.new([Path to Source PDF], 
                    [Target File (not implemented yet)], 
                    [user password], 
                    [owner password])
-doc = file.convert
-</code>
-</pre>
+string = file.convert
+doc = file.convert_to_document()</code></pre>
+
+h1. license
+
+MIT

data/lib/pdftohtmlr.rb

@@ -1,10 +1,26 @@
+# The library has a single method for converting PDF files into HTML. The
+# method current takes in the source path, and either/both the user and owner
+# passwords set on the source PDF document.  The convert method returns the
+# HTML as a string for further manipulation of loading into a Document.
+#
+# Requires that pdftohtml be installed and on the path
+#
+# Author:: Kit Plummer (mailto:kitplummer@gmail.com)
+# Copyright:: Copyright (c) 2009 Kit Plummer
+# License:: MIT
+
 require 'rubygems'
 require 'open3'
+require 'nokogiri'
 
 module PDFToHTMLR
+  
+  # Simple local error abstraction
   class PDFToHTMLRError < RuntimeError; end
-  VERSION = '0.2.0'
+  
+  VERSION = '0.3.0'
 
+  # Provides facilities for converting PDFs to HTML from Ruby code.
   class PdfFile
     attr :path
     attr :target
@@ -24,6 +40,7 @@ module PDFToHTMLR
       
     end
 
+    # Convert the PDF document to HTML.  Returns a string
     def convert()
       errors = ""
       output = ""
@@ -49,5 +66,10 @@ module PDFToHTMLR
       end
     end
     
+    # Convert the PDF document to HTML.  Returns a Nokogiri::HTML:Document
+    def convert_to_document() 
+      Nokogiri::HTML.parse(convert())
+    end
+    
   end
 end

data/test/pdftohtmlr_test.rb

@@ -20,7 +20,6 @@ class PdfFileTest < Test::Unit::TestCase
       file = PdfFile.new(TEST_NON_PDF, ".", nil, nil)
       file.convert
     end
-    puts e
   end
 
   def test_bad_pdffile_new
@@ -48,5 +47,15 @@ class PdfFileTest < Test::Unit::TestCase
     assert_equal `pdftohtml -stdout -upw user #{TEST_PWD_PDF_PATH}`,
     file.convert()
   end
-
+  
+  def test_return_document
+    file = PdfFile.new(TEST_PDF_PATH, ".", nil, nil)
+    assert_equal "Nokogiri::HTML::Document",
+     file.convert_to_document().class.to_s
+    assert_equal Nokogiri::HTML.parse(
+        `pdftohtml -stdout -upw user #{TEST_PWD_PDF_PATH}`
+      ).css('body').first.to_s,
+       file.convert_to_document().css('body').first.to_s
+  end
+  
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification 
 name: pdftohtmlr
 version: !ruby/object:Gem::Version 
-  version: 0.2.0
+  version: 0.3.0
 platform: ruby
 authors: 
 - Kit Plummer
@@ -9,7 +9,7 @@ autorequire: pdftohtml
 bindir: bin
 cert_chain: []
 
-date: 2009-12-10 00:00:00 -07:00
+date: 2009-12-13 00:00:00 -07:00
 default_executable: 
 dependencies: []