pdftohtmlr 0.4 → 0.4.1

data/Rakefile

@@ -55,7 +55,7 @@ spec = Gem::Specification.new do |s|
   s.requirements << 'none'
   s.require_path = 'lib'
   s.autorequire = 'pdftohtml'
-
+  s.add_dependency("nokogiri", ">= 1.3.3")
   s.files = [ "Rakefile", "README.textile", "MIT-LICENSE" ]
   s.files = s.files + Dir.glob( "lib/**/*" ).delete_if { |item| item.include?( "\.svn" ) }
   s.files = s.files + Dir.glob( "test/**/*" ).delete_if { |item| item.include?( "\.svn" ) || item.include?("\.png") }

data/lib/pdftohtmlr.rb

@@ -20,7 +20,7 @@ module PDFToHTMLR
   # Simple local error abstraction
   class PDFToHTMLRError < RuntimeError; end
   
-  VERSION = '0.4'
+  VERSION = '0.4.1'
 
   # Provides facilities for converting PDFs to HTML from Ruby code.
   class PdfFile
@@ -28,7 +28,8 @@ module PDFToHTMLR
     attr :target
     attr :user_pwd
     attr :owner_pwd
-
+    attr :format
+    
     def initialize(input_path, target_path=nil, user_pwd=nil, owner_pwd=nil)
       @path = input_path
       @target = target_path
@@ -40,12 +41,13 @@ module PDFToHTMLR
     def convert()
       errors = ""
       output = ""
+      
       if @user_pwd 
-        cmd = "pdftohtml -stdout -upw #{@user_pwd}" + ' "' + @path + '"'    
+        cmd = "pdftohtml -stdout #{@format} -upw #{@user_pwd}" + ' "' + @path + '"'    
       elsif @owner_pwd 
-        cmd = "pdftohtml -stdout -opw #{@owner_pwd}" + ' "' + @path + '"'
+        cmd = "pdftohtml -stdout #{@format} -opw #{@owner_pwd}" + ' "' + @path + '"'
       else
-        cmd = "pdftohtml -stdout" + ' "' + @path + '"'
+        cmd = "pdftohtml -stdout #{@format}" + ' "' + @path + '"'
       end
       
       output = `#{cmd} 2>&1`
@@ -63,6 +65,16 @@ module PDFToHTMLR
     def convert_to_document() 
       Nokogiri::HTML.parse(convert())
     end
+    
+    def convert_to_xml()
+      @format = "-xml"
+      convert()
+    end
+    
+    def convert_to_xml_document()
+      @format = "-xml"
+      Nokogiri::XML.parse(convert())
+    end
   end
   
   # Handle a string-based local path as input, extends PdfFile

data/test/pdftohtmlr_test.rb

@@ -64,6 +64,21 @@ class PdfFileTest < Test::Unit::TestCase
        file.convert_to_document().css('body').first.to_s
   end
   
+  def test_return_xml
+    file = PdfFilePath.new(TEST_PDF_PATH, ".", nil, nil)
+    assert_equal "String", file.convert_to_xml().class.to_s
+  end
+  
+  def test_return_xml_document
+    file = PdfFilePath.new(TEST_PDF_PATH, ".", nil, nil)
+    assert_equal "Nokogiri::XML::Document",
+     file.convert_to_xml_document().class.to_s
+    assert_equal Nokogiri::XML.parse(
+        `pdftohtml -stdout -xml "#{TEST_PDF_PATH}"`
+      ).css('text').first.to_s,
+       file.convert_to_document().css('text').first.to_s
+  end
+  
   def test_invalid_URL_pdffile
     e = assert_raise PDFToHTMLRError do
       file = PdfFileUrl.new("blah", ".", nil, nil)

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification 
 name: pdftohtmlr
 version: !ruby/object:Gem::Version 
-  version: "0.4"
+  version: 0.4.1
 platform: ruby
 authors: 
 - Kit Plummer
@@ -11,8 +11,17 @@ cert_chain: []
 
 date: 2009-12-18 00:00:00 -07:00
 default_executable: 
-dependencies: []
-
+dependencies: 
+- !ruby/object:Gem::Dependency 
+  name: nokogiri
+  type: :runtime
+  version_requirement: 
+  version_requirements: !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: 1.3.3
+    version: 
 description: Uses command-line pdftohtml tools to convert PDF files to HTML.
 email: kitplummer@gmail.com
 executables: []