kristin 0.2.1 → 0.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 65a0699a6c0e9749bac8e60eb9d2ff371349c976
-  data.tar.gz: c84b34baf200cba7e91f79c27540cd2efd2cbc63
+  metadata.gz: 422f4e6c184d84f8cdcf0053cbf10758de9a7b29
+  data.tar.gz: 2d2ea0e029670d144066ec395710312bb3963527
 SHA512:
-  metadata.gz: ea335a10193a365eba695b94d928fb98a24b4ae578d926cd0f26ffb410cda20b8d90ab4ae191b68e2e1e0dc901292822e19f873c2be17ee588155fd2271349d5
-  data.tar.gz: b2db188faed3fecdc17be055e3e665a139ccf34881fe636f9a1935720a9db031aba9ba3b26a82c3cf536c7eab4cbfc90ea6311cea5f28ed5c6b8e50d8e9aa079
+  metadata.gz: 2b250bdf7abafd32f9a755a5eeec912024deeb1205c6a9876f0ca5a51dacb0d82cc4e078b803171c46d5c3611c9d977d70a4e894d28027a65fc58c81bd3656e9
+  data.tar.gz: b8014ba3d553d0e55a0757ace66bc0c546723de4cd1cfa6b11899528bfc38c3746d6b0f7baa48d5574e25189a5aeda3f632414001c64e4029156104cf8283011

data/.gitignore

@@ -17,3 +17,5 @@ test/version_tmp
 tmp
 
 .DS_Store
+
+TODO

data/README.md

@@ -30,6 +30,18 @@ Kristin.convert('document.pdf', 'document.html')
 
 # You can also convert a source file directly from an URL
 Kristin.convert('http://myserver.com/123/document.pdf', 'document.html')
+
+# You can also specify options for fine grained conversion:
+Kristin.convert('document.pdf', 'document.html', { first_page: 2, last_page: 4, hdpi: 72, vdpi: 72})
+
+# Available options:
+
+# process_outline - show outline in HTML. Default: true
+# first_page - first page to convert. Default: 1
+# last_page - last page to convert. Default: 2147483647
+# hdpi - horizontal resolution for graphics in DPI. Default: 144
+# vdpi - vertical resolution for graphics in DPI. Default: 144
+
 ```
 
 ## Contributing
@@ -38,4 +50,4 @@ Kristin.convert('http://myserver.com/123/document.pdf', 'document.html')
 2. Create your feature branch (`git checkout -b my-new-feature`)
 3. Commit your changes (`git commit -am 'Add some feature'`)
 4. Push to the branch (`git push origin my-new-feature`)
-5. Create new Pull Request
+5. Create new Pull Request

data/kristin.gemspec

@@ -20,4 +20,5 @@ Gem::Specification.new do |spec|
 
   spec.add_development_dependency "bundler", "~> 1.3"
   spec.add_development_dependency "rake"
+  spec.add_development_dependency "nokogiri"
 end

data/lib/kristin.rb

@@ -3,60 +3,84 @@ require 'open-uri'
 require "net/http"
 
 module Kristin
-  def self.convert(source, target)
-    raise IOError, "Can't find pdf2htmlex executable in PATH" if not command_available?
-    src = determine_source(source)
-    cmd = "#{pdf2htmlex_command} #{src} #{target}"
-    pid = Process.spawn(cmd, [:out, :err] => "/dev/null")
-    Process.waitpid(pid)
-    ## TODO: Grab error message from pdf2htmlex and raise a better error
-    raise IOError, "Could not convert #{src}" if $?.exitstatus != 0
-  end
+  class Converter
+    def initialize(source, target, options = {})
+      @options = options
+      @source = source
+      @target = target
+    end
 
-  private
+    def convert
+      raise IOError, "Can't find pdf2htmlex executable in PATH" if not command_available?
+      src = determine_source(@source)
+      opts = process_options
+      cmd = "#{pdf2htmlex_command} #{opts} #{src} #{@target}"
+      pid = Process.spawn(cmd, [:out, :err] => "/dev/null")
+      Process.waitpid(pid)
+      
+      ## TODO: Grab error message from pdf2htmlex and raise a better error
+      raise IOError, "Could not convert #{src}" if $?.exitstatus != 0
+    end
 
-  def self.command_available?
-    pdf2htmlex_command
-  end
+    private
 
-  def self.pdf2htmlex_command
-    cmd = nil
-    cmd = "pdf2htmlex" if which("pdf2htmlex")
-    cmd = "pdf2htmlEX" if which("pdf2htmlEX")
-  end
+    def process_options
+      opts = []
+      opts.push("--process-outline 0") if @options[:process_outline] == false
+      opts.push("--first-page #{@options[:first_page]}") if @options[:first_page]
+      opts.push("--last-page #{@options[:last_page]}") if @options[:last_page]
+      opts.push("--hdpi #{@options[:hdpi]}") if @options[:hdpi]
+      opts.push("--vdpi #{@options[:vdpi]}") if @options[:vdpi]
+    
+      opts.join(" ")
+    end
 
-  def self.which(cmd)
-    exts = ENV['PATHEXT'] ? ENV['PATHEXT'].split(';') : ['']
-    ENV['PATH'].split(File::PATH_SEPARATOR).each do |path|
-      exts.each do |ext|
-        exe = File.join(path, "#{cmd}#{ext}")
-        return exe if File.executable? exe
-      end
+    def command_available?
+      pdf2htmlex_command
     end
-    
-    return nil
-  end
 
-  def self.random_source_name
-    rand(16**16).to_s(16)
-  end
+    def pdf2htmlex_command
+      cmd = nil
+      cmd = "pdf2htmlex" if which("pdf2htmlex")
+      cmd = "pdf2htmlEX" if which("pdf2htmlEX")
+    end
+
+    def which(cmd)
+      exts = ENV['PATHEXT'] ? ENV['PATHEXT'].split(';') : ['']
+        ENV['PATH'].split(File::PATH_SEPARATOR).each do |path|
+          exts.each do |ext|
+            exe = File.join(path, "#{cmd}#{ext}")
+            return exe if File.executable? exe
+          end
+        end
+      return nil
+    end
+
+    def random_source_name
+      rand(16**16).to_s(16)
+    end
 
-  def self.download_file(source)
-    tmp_file = "/tmp/#{random_source_name}.pdf"
-    File.open(tmp_file, "wb") do |saved_file|
-      open(source, 'rb') do |read_file|
-        saved_file.write(read_file.read)
+    def download_file(source)
+      tmp_file = "/tmp/#{random_source_name}.pdf"
+      File.open(tmp_file, "wb") do |saved_file|
+        open(source, 'rb') do |read_file|
+          saved_file.write(read_file.read)
+        end
       end
+
+      tmp_file
     end
 
-    tmp_file
+    def determine_source(source)
+      is_file = File.exists?(source) && !File.directory?(source)
+      is_http = (URI(source).scheme == "http" || URI(source).scheme == "https") && Net::HTTP.get_response(URI(source)).is_a?(Net::HTTPSuccess)
+      raise IOError, "Source (#{source}) is neither a file nor an URL." unless is_file || is_http
+    
+      is_file ? source : download_file(source)
+    end
   end
 
-  def self.determine_source(source)
-    is_file = File.exists?(source) && !File.directory?(source)
-    is_http = (URI(source).scheme == "http" || URI(source).scheme == "https") && Net::HTTP.get_response(URI(source)).is_a?(Net::HTTPSuccess)
-    raise IOError, "Source (#{source}) is neither a file nor an URL." unless is_file || is_http
-    
-    is_file ? source : download_file(source)
+  def self.convert(source, target, options = {})
+    Converter.new(source, target, options).convert
   end
 end

data/lib/kristin/version.rb

@@ -1,3 +1,3 @@
 module Kristin
-  VERSION = "0.2.1"
+  VERSION = "0.3.0"
 end

data/spec/kristin_spec.rb

@@ -6,49 +6,125 @@ describe Kristin do
     @one_page_pdf = file_path("one.pdf")
     @multi_page_pdf = file_path("multi.pdf")
     @no_pdf = file_path("image.png")
+    @large_pdf = file_path("large.pdf")
     @target_path = "tmp/kristin"
+  end
+
+  before(:each) do
     FileUtils.mkdir_p @target_path
   end
 
-  after(:all) do
+  after(:each) do
     FileUtils.rm_rf @target_path
   end
 
-  describe ".convert" do
-    it "should raise error if source file does not exists" do
-      lambda { Kristin.convert("nonsense.pdf", "nonsense.html") }.should raise_error(IOError)
-    end
+  describe "#convert" do
+    describe "with no options" do
+      it "should raise error if source file does not exists" do
+        c = Kristin::Converter.new("nonsense.pdf", "nonsense.html")
+        lambda { c.convert }.should raise_error(IOError)
+      end
 
-    it "should convert a one page pdf to one html file" do
-      target = @target_path + "/one.html"
-      Kristin.convert(@one_page_pdf, target)
-      File.exists?(target).should == true
-    end
+      it "should convert a one page pdf to one html file" do
+        target = @target_path + "/one.html"
+        Kristin::Converter.new(@one_page_pdf, target).convert
+        File.exists?(target).should == true
+      end
 
-    it "should convert a multi page pdf to one html file" do
-      target = @target_path + "/multi.html"
-      Kristin.convert(@multi_page_pdf, target)
-      File.exists?(target).should == true
-    end
+      it "should convert a multi page pdf to one html file" do
+        target = @target_path + "/multi.html"
+        Kristin::Converter.new(@multi_page_pdf, target).convert
+        File.exists?(target).should == true
+      end
+
+      it "should raise error if pdf is not a real pdf" do
+        lambda { Kristin::Converter.new(@no_pdf, "nonsense.html").convert }.should raise_error(IOError)
+      end
+
+      it "should convert a pdf from an URL" do
+        target = @target_path + "/from_url.html"
+        Kristin::Converter.new("https://www.filepicker.io/api/file/vR0btUfRQiCF9ntRkW6Q", target).convert
+        File.exists?(target).should == true
+      end
+
+      it "should raise an error if URL does not exist" do
+        target = @target_path + "/from_url.html"
+        lambda { Kristin::Converter.new("https://www.filepicker.io/api/file/donotexist.pdf", target).convert }.should raise_error(IOError)
+      end
 
-    it "should raise error if pdf is not a real pdf" do
-      lambda { Kristin.convert(@no_pdf, "nonsense.html") }.should raise_error(IOError)
+      it "should raise an error if URL file is not a real pdf" do
+        target = @target_path + "/from_url.html"
+        lambda { Kristin::Converter.new("https://www.filepicker.io/api/file/agxKeTfQSWKvMR4CDXMq", target).convert }.should raise_error(IOError)
+      end
     end
 
-    it "should convert a pdf from an URL" do
-      target = @target_path + "/from_url.html"
-      Kristin.convert("https://www.filepicker.io/api/file/vR0btUfRQiCF9ntRkW6Q", target)
-      File.exists?(target).should == true
+    describe "options" do
+      #TODO: Only convert file once for performance
+      
+      it "should process outline by default" do
+        target = @target_path + "/large.html"
+        Kristin::Converter.new(@large_pdf, target, { process_outline: false }).convert
+        doc = Nokogiri::HTML(File.open(target))
+        el = doc.css("#pdf-outline").first
+        el.children.should_not be_empty
+      end
+
+      it "should be possible to disable outline" do
+        target = @target_path + "/large.html"
+        Kristin::Converter.new(@large_pdf, target, { process_outline: false }).convert
+        doc = Nokogiri::HTML(File.open(target))
+        el = doc.css("#pdf-outline").first
+        el.children.first.text.strip.should be_empty
+      end
+
+      it "should be possible to specify first page" do
+        target = @target_path + "/multi.html"
+        Kristin::Converter.new(@multi_page_pdf, target, { first_page: 2 }).convert
+        doc = Nokogiri::HTML(File.open(target))
+        # Content only present on page 1
+        content_from_page_1 = doc.search("//span").map(&:content).select {|c| c.include? "Geometric series"}
+        # Content only present on page 2
+        content_from_page_2 = doc.search("//span").map(&:content).select {|c| c.include? "Generating functions"}
+        content_from_page_1.should be_empty
+        content_from_page_2.should_not be_empty
+      end
+
+      it "should be possible to specify last page" do
+        target = @target_path + "/multi.html"
+        Kristin::Converter.new(@multi_page_pdf, target, { last_page: 9 }).convert
+        doc = Nokogiri::HTML(File.open(target))
+        # Content only present on page 1
+        content_from_page_1 = doc.search("//span").map(&:content).select {|c| c.include? "Geometric series"}
+        # Content only present on page 10
+        content_from_page_10 = doc.search("//span").map(&:content).select {|c| c.include? "William Blake"}
+        content_from_page_1.should_not be_empty
+        content_from_page_10.should be_empty
+      end
+
+      it "should be possible to specify hdpi and vdpi" do
+        target = @target_path + "/one.html"
+        Kristin::Converter.new(@one_page_pdf, target, { hdpi: 1, vdpi: 1 }).convert
+        doc = Nokogiri::HTML(File.open(target))
+        doc.xpath("//img[@class='bi']/@src").first.content.size.should == 538 # The size you get when hdpi and vdpi is 1 on @one_page_pdf
+      end
+
+      it "should be possible to specify vdpi" do
+      
+      end
     end
+  end
 
-    it "should raise an error if URL does not exist" do
-      target = @target_path + "/from_url.html"
-      lambda { Kristin.convert("https://www.filepicker.io/api/file/donotexist.pdf", target) }.should raise_error(IOError)
+  describe ".convert" do
+    it "should convert without options" do
+      target = @target_path + "/one.html"
+      Kristin.convert(@one_page_pdf, target)
+      File.exists?(target).should == true
     end
 
-    it "should raise an error if URL file is not a real pdf" do
-      target = @target_path + "/from_url.html"
-      lambda { Kristin.convert("https://www.filepicker.io/api/file/agxKeTfQSWKvMR4CDXMq", target) }.should raise_error(IOError)
+    it "should convert with options" do
+      target = @target_path + "/one.html"
+      Kristin.convert(@one_page_pdf, target, { hdpi: 1, vdpi: 1 })
+      File.exists?(target).should == true
     end
   end
 end

data/spec/spec_helper.rb

@@ -1,4 +1,5 @@
 require 'kristin'
+require 'nokogiri'
 
 def file_path( *paths )
   File.expand_path(File.join(File.dirname(__FILE__), 'fixtures', *paths))

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: kristin
 version: !ruby/object:Gem::Version
-  version: 0.2.1
+  version: 0.3.0
 platform: ruby
 authors:
 - Richard Nyström
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-03-31 00:00:00.000000000 Z
+date: 2013-04-03 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -38,6 +38,20 @@ dependencies:
     - - '>='
       - !ruby/object:Gem::Version
         version: '0'
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
 description: ' Convert PDF docs to beautiful HTML files without losing text or format.
   This gem uses pdf2htmlEX to do the conversion.'
 email:
@@ -56,6 +70,7 @@ files:
 - lib/kristin.rb
 - lib/kristin/version.rb
 - spec/fixtures/image.png
+- spec/fixtures/large.pdf
 - spec/fixtures/multi.pdf
 - spec/fixtures/one.pdf
 - spec/kristin_spec.rb
@@ -80,13 +95,14 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.0.0
+rubygems_version: 2.0.3
 signing_key: 
 specification_version: 4
 summary: Convert PDF docs to beautiful HTML files without losing text or format. This
   gem uses pdf2htmlEX to do the conversion.
 test_files:
 - spec/fixtures/image.png
+- spec/fixtures/large.pdf
 - spec/fixtures/multi.pdf
 - spec/fixtures/one.pdf
 - spec/kristin_spec.rb