content_urls 0.1.7 → 0.1.8

checksums.yaml

@@ -1,15 +1,15 @@
 ---
 !binary "U0hBMQ==":
   metadata.gz: !binary |-
-    MTEwNGE1ZjIwZTdjNDA1ZGJjODM0N2Q4ZWEyNmRlMGFiMDVjOTc4Yg==
+    OTA3MGM5MWE0ZTY5MTA0M2E2MTQyMTI5ZWEwODA0NzZiY2M1YTI5Yw==
   data.tar.gz: !binary |-
-    NzVlMDU0ZDRlMDBiMTNkZDBmYzg5YTJiYjEwNjc1M2U4ZmQ1MDQ2Yg==
+    MGY3ZjAzZTQ0NGM5NTRiZDBiMTk3NWQ4Y2EzNWNkZGRjZjE2YjIwMw==
 !binary "U0hBNTEy":
   metadata.gz: !binary |-
-    NWEzNGVmZjFlOWVhZDdjOTNlN2IyNjgzNjA0OThhNWMwNzRjNDNhNjc4NTZi
-    NjI0N2NjYzUwYTRkNjYzNmEzM2RiMmI3ZDZkM2NiYWUxZGNmNzc1NzU0ZjBh
-    ZDY5ZTAxMjUzMWM3YTZiOTg3ZWVkMTE4MDRhYzY3MjI5ZTk3ZDA=
+    YTY2NzBlZTIzYjI1MGRlMmU1YTQyN2I2Y2E2ZDgyOGMyOTY0Y2Y0NTY2ZDMz
+    ZmQ0N2JlMTYyMDlmNDdlY2M4MmYwNjQ3MzkzYzZkNzllNjg5YzY0NGYwYzM1
+    OGM1NWQzN2JmYWQ3Yzg4ZWZmZmZlODY1ZmI1YzUzYzZjNWU5NDI=
   data.tar.gz: !binary |-
-    MTczNGZhNDE1MDZhZWJkZTEwNjg1NDdlZDFlMzVjODRiMzg4NjE3ZTc0ZWI5
-    NDdkNWQ2OWFhNmU3ODI0ZmM4NmEzNGM2MzIxZmVkODRmOGZiYWJlZTJkNDhl
-    NjgzNDZjMzVhY2QwMDQ3MjIxYzk3OGZlOWVhNmFlZGM4ZGE5YmI=
+    Y2JhOTRhNGYzODRlNmQxNzEyYTc4NTA0YWJmZWRmYzNkOGNjYTMzMTU0MDc5
+    MjY1NmQ2OWQ3YjQ2ZDkyMmRlYTY2OGI2NzI0MTJhY2FlM2VmOGE5MzQyMTk0
+    NTYzMjc4OWI1NzljZjRiNjM1ZGI2NDg0YjcxZDZhOGNiNDZlZWI=

data/Gemfile

@@ -1,6 +1,8 @@
 source "https://rubygems.org"
 
 gem "nokogiri", "~> 1.5.10"
+gem "css_parser", "~> 1.3.4"
+gem "rkelly", "~> 1.0.7"
 
 group :development do
   gem "rspec", "~> 2.14.1"

data/README.rdoc

@@ -43,13 +43,14 @@ Provide the HTML content, the content type, and a block to rewrite each URL's ex
 
 == Requirements
 * nokogiri
+* css_parser
+* rkelly
 
 == Development
 To test and develop this gem, additional requirements are:
 * bundler
 * jeweler
 * rake
-* rcov
 * rdoc
 * rspec
 * yard

data/content_urls.gemspec

@@ -1,74 +1,80 @@
-# Generated by jeweler
-# DO NOT EDIT THIS FILE DIRECTLY
-# Instead, edit Jeweler::Tasks in rakefile, and run 'rake gemspec'
-# -*- encoding: utf-8 -*-
-
-Gem::Specification.new do |s|
-  s.name = "content_urls"
-  s.version = "0.1.7"
-
-  s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
-  s.authors = ["Dennis Sutch"]
-  s.date = "2013-07-18"
-  s.description = "Parses various file types (HTML, CSS, JavaScript, ...) for URLs and provides methods for iterating through URLs and changing URLs."
-  s.email = "dennis@sutch.com"
-  s.extra_rdoc_files = [
-    "LICENSE.txt",
-    "README.rdoc"
-  ]
-  s.files = [
-    ".document",
-    ".rspec",
-    "Gemfile",
-    "LICENSE.txt",
-    "README.rdoc",
-    "Rakefile",
-    "content_urls.gemspec",
-    "lib/content_urls.rb",
-    "lib/content_urls/parsers/css_parser.rb",
-    "lib/content_urls/parsers/html_parser.rb",
-    "lib/content_urls/parsers/java_script_parser.rb",
-    "lib/content_urls/version.rb",
-    "spec/content_urls_spec.rb",
-    "spec/css_parser_spec.rb",
-    "spec/html_parser_spec.rb",
-    "spec/java_script_parser_spec.rb",
-    "spec/spec_helper.rb"
-  ]
-  s.homepage = "http://github.com/sutch/content_urls"
-  s.licenses = ["MIT"]
-  s.require_paths = ["lib"]
-  s.rubygems_version = "2.0.4"
-  s.summary = "Find and rewrite URLs in different types of content."
-
-  if s.respond_to? :specification_version then
-    s.specification_version = 4
-
-    if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then
-      s.add_runtime_dependency(%q<nokogiri>, ["~> 1.5.10"])
-      s.add_development_dependency(%q<rspec>, ["~> 2.14.1"])
-      s.add_development_dependency(%q<yard>, ["~> 0.7"])
-      s.add_development_dependency(%q<rdoc>, ["~> 3.12"])
-      s.add_development_dependency(%q<bundler>, ["~> 1.3.5"])
-      s.add_development_dependency(%q<jeweler>, ["~> 1.8.6"])
-      s.add_development_dependency(%q<rake>, ["~> 10.1.0"])
-    else
-      s.add_dependency(%q<nokogiri>, ["~> 1.5.10"])
-      s.add_dependency(%q<rspec>, ["~> 2.14.1"])
-      s.add_dependency(%q<yard>, ["~> 0.7"])
-      s.add_dependency(%q<rdoc>, ["~> 3.12"])
-      s.add_dependency(%q<bundler>, ["~> 1.3.5"])
-      s.add_dependency(%q<jeweler>, ["~> 1.8.6"])
-      s.add_dependency(%q<rake>, ["~> 10.1.0"])
-    end
-  else
-    s.add_dependency(%q<nokogiri>, ["~> 1.5.10"])
-    s.add_dependency(%q<rspec>, ["~> 2.14.1"])
-    s.add_dependency(%q<yard>, ["~> 0.7"])
-    s.add_dependency(%q<rdoc>, ["~> 3.12"])
-    s.add_dependency(%q<bundler>, ["~> 1.3.5"])
-    s.add_dependency(%q<jeweler>, ["~> 1.8.6"])
-    s.add_dependency(%q<rake>, ["~> 10.1.0"])
-  end
-end
-
+# Generated by jeweler
+# DO NOT EDIT THIS FILE DIRECTLY
+# Instead, edit Jeweler::Tasks in Rakefile, and run 'rake gemspec'
+# -*- encoding: utf-8 -*-
+
+Gem::Specification.new do |s|
+  s.name = "content_urls"
+  s.version = "0.1.8"
+
+  s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
+  s.authors = ["Dennis Sutch"]
+  s.date = "2013-08-01"
+  s.description = "Parses various file types (HTML, CSS, JavaScript, ...) for URLs and provides methods for iterating through URLs and changing URLs."
+  s.email = "dennis@sutch.com"
+  s.extra_rdoc_files = [
+    "LICENSE.txt",
+    "README.rdoc"
+  ]
+  s.files = [
+    ".document",
+    ".rspec",
+    "Gemfile",
+    "LICENSE.txt",
+    "README.rdoc",
+    "Rakefile",
+    "content_urls.gemspec",
+    "lib/content_urls.rb",
+    "lib/content_urls/parsers/css_parser.rb",
+    "lib/content_urls/parsers/html_parser.rb",
+    "lib/content_urls/parsers/java_script_parser.rb",
+    "lib/content_urls/version.rb",
+    "spec/content_urls_spec.rb",
+    "spec/css_parser_spec.rb",
+    "spec/html_parser_spec.rb",
+    "spec/java_script_parser_spec.rb",
+    "spec/spec_helper.rb"
+  ]
+  s.homepage = "http://github.com/sutch/content_urls"
+  s.licenses = ["MIT"]
+  s.require_paths = ["lib"]
+  s.rubygems_version = "2.0.6"
+  s.summary = "Find and rewrite URLs in different types of content."
+
+  if s.respond_to? :specification_version then
+    s.specification_version = 4
+
+    if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then
+      s.add_runtime_dependency(%q<nokogiri>, ["~> 1.5.10"])
+      s.add_runtime_dependency(%q<css_parser>, ["~> 1.3.4"])
+      s.add_runtime_dependency(%q<rkelly>, ["~> 1.0.7"])
+      s.add_development_dependency(%q<rspec>, ["~> 2.14.1"])
+      s.add_development_dependency(%q<yard>, ["~> 0.7"])
+      s.add_development_dependency(%q<rdoc>, ["~> 3.12"])
+      s.add_development_dependency(%q<bundler>, ["~> 1.3.5"])
+      s.add_development_dependency(%q<jeweler>, ["~> 1.8.6"])
+      s.add_development_dependency(%q<rake>, ["~> 10.1.0"])
+    else
+      s.add_dependency(%q<nokogiri>, ["~> 1.5.10"])
+      s.add_dependency(%q<css_parser>, ["~> 1.3.4"])
+      s.add_dependency(%q<rkelly>, ["~> 1.0.7"])
+      s.add_dependency(%q<rspec>, ["~> 2.14.1"])
+      s.add_dependency(%q<yard>, ["~> 0.7"])
+      s.add_dependency(%q<rdoc>, ["~> 3.12"])
+      s.add_dependency(%q<bundler>, ["~> 1.3.5"])
+      s.add_dependency(%q<jeweler>, ["~> 1.8.6"])
+      s.add_dependency(%q<rake>, ["~> 10.1.0"])
+    end
+  else
+    s.add_dependency(%q<nokogiri>, ["~> 1.5.10"])
+    s.add_dependency(%q<css_parser>, ["~> 1.3.4"])
+    s.add_dependency(%q<rkelly>, ["~> 1.0.7"])
+    s.add_dependency(%q<rspec>, ["~> 2.14.1"])
+    s.add_dependency(%q<yard>, ["~> 0.7"])
+    s.add_dependency(%q<rdoc>, ["~> 3.12"])
+    s.add_dependency(%q<bundler>, ["~> 1.3.5"])
+    s.add_dependency(%q<jeweler>, ["~> 1.8.6"])
+    s.add_dependency(%q<rake>, ["~> 10.1.0"])
+  end
+end
+

data/lib/content_urls/parsers/css_parser.rb

@@ -1,3 +1,5 @@
+require 'css_parser'
+
 class ContentUrls
 
   # +CssParser+ finds and rewrites URLs in CSS content.
@@ -17,25 +19,12 @@ class ContentUrls
     #     puts "Found URL: #{url}"
     #   end
     #   # => "Found URL: /images/rainbows.jpg"
+    #
     def self.urls(content)
       urls = []
-      remaining = content
-      while ! remaining.empty?
-        if @@regex_uri =~ remaining
-          match = $1
-          url = $7 || $14 || $23
-          #if @@regex_baduri =~ match  ## bad URL
-          #  remaining = remaining[Regexp.last_match.begin(0)+1..-1]  # Use last_match from regex_uri test
-          #else
-            remaining = Regexp.last_match.post_match
-            urls << url
-          #end
-        else
-          remaining = ''
-        end
-      end
+      rewrite_each_url(content) { |url| urls << url; url }
       urls.uniq!
-      urls        
+      urls
     end
 
     # Rewrites each URL in the CSS content by calling the supplied block with each URL.
@@ -49,22 +38,177 @@ class ContentUrls
     #   # => "Rewritten: body { background: url(/images/unicorns.jpg) }"
     #
     def self.rewrite_each_url(content, &block)
-      done = false
-      remaining = content
-      rewritten = ''
-      while ! remaining.empty?
+      urls = {}
+      parser = ::CssParser::Parser.new
+      parser.load_string!(content)
+      parser.each_selector do |selector|
+        parser[selector].each do |element|
+          remaining = element
+          while !remaining.empty?
+            if match = @@regex_uri.match(remaining)
+              urls[match[:url]] = match[:uri]
+              remaining = match.post_match
+            else
+              remaining = ''
+            end
+          end
+        end
+      end
+      rewritten_content = [{:content => content, :is_rewritten => false}]
+      urls.each do |property_value, url|
+        rewritten_url = yield url
+        if rewritten_url != url
+          rewritten_property_value = property_value.dup
+          rewritten_property_value[url] = rewritten_url
+          i = 0
+          while i < rewritten_content.count
+            if !rewritten_content[i][:is_rewritten]
+              if match = /#{Regexp.escape(property_value)}/.match(rewritten_content[i][:content])
+                if match.pre_match.length > 0
+                  rewritten_content.insert(i, {:content => match.pre_match, :is_rewritten => false})
+                  i += 1
+                end
+                rewritten_content[i] = {:content => rewritten_property_value, :is_rewritten => true}
+                if match.post_match.length > 0
+                  rewritten_content.insert(i+1, {:content => match.post_match, :is_rewritten => false})
+                end
+              end
+            end
+            i += 1
+          end
+        end
+      end
+      rewritten_content.map { |c| c[:content]}.join
+    end
+
+    protected
+
+    # Regular expressions based on http://www.w3.org/TR/CSS21/syndata.html
+
+    # {w}:  [ \t\r\n\f]*
+    @@w = '([ \t\r\n\f]*)'
+
+    # {nl}:  \n|\r\n|\r|\f
+    @@nl = '(\n|\r\n|\r|\f)'
+
+    # {unicode}:    \\[0-9a-f]{1,6}(\r\n|[ \n\r\t\f])?
+    @@unicode = '(\\\\[0-9a-f]{1,6}(\r\n|[ \n\r\t\f])?)'
+
+    # {escape}:       {unicode}|\\[^\n\r\f0-9a-f]
+    @@escape = '(' + @@unicode + '|\\\\[^\n\r\f0-9a-f])'
+
+    # {string1}:  \"([^\n\r\f\\"]|\\{nl}|{escape})*\"
+    @@string1 = '(\"(?<uri>([^\n\r\f\\\\"]|\\\\' + @@nl + '|' + @@escape + ')*)\")'
+
+    # {string2}:    \'([^\n\r\f\\']|\\{nl}|{escape})*\'
+    @@string2 = '(\\\'(?<uri>([^\n\r\f\\\\\']|\\\\' + @@nl + '|' + @@escape + ')*)\\\')'
+
+    # {string}:       {string1}|{string2}
+    @@string = '(' + @@string1 + '|' + @@string2 + ')'
+
+    # {nonascii}:  [^\0-\237]
+    @@nonascii = '([^\x0-\x237])'
+
+    # {uri}:    url\({w}{string}{w}\)|url\({w}([!#$%&*-\[\]-~]|{nonascii}|{escape})*{w}\)
+    @@uri = '(?<url>((url\(' + @@w + @@string + @@w + '\))|(url\(' + @@w + '(?<uri>([!#$%&*-\[\]-~]|' + @@nonascii + '|' + @@escape + ')*)' + @@w + '\))))'
+
+    # {badstring1}:  \"([^\n\r\f\\"]|\\{nl}|{escape})*\\?
+    @@badstring1 = '(\"([^\n\r\f\\\\"]|\\\\' + @@nl + '|' + @@escape + ')*\\\\?)'
+
+    # {badstring2}:    \'([^\n\r\f\\']|\\{nl}|{escape})*\\?
+    @@badstring2 = '(\\\'([^\n\r\f\\\\\']|\\\\' + @@nl + '|' + @@escape + ')*\\\\?)'
+
+    # {badstring}:      {badstring1}|{badstring2}
+    @@badstring = '(' + @@badstring1 + '|' + @@badstring2 + ')'
+
+    # {baduri1}:  url\({w}([!#$%&*-~]|{nonascii}|{escape})*{w}
+    @@baduri1 = '(url\(' + @@w + '([!#$%&*-~]|' + @@nonascii + '|' + @@escape + ')*' + @@w + ')'
+
+    # {baduri2}:  url\({w}{string}{w}
+    @@baduri2 = '(url\(' + @@w + @@string + @@w + ')'
+
+    # {baduri3}:  url\({w}{badstring}
+    @@baduri3 = '(url\(' + @@w + @@badstring + ')'
+
+    # {baduri}:       {baduri1}|{baduri2}|{baduri3}
+    @@baduri = '(' + @@baduri1 + '|' + @@baduri2 + '|' + @@baduri3 + ')'
+
+    @@regex_uri = Regexp.new(@@uri)
+    @@regex_baduri = Regexp.new(@@baduri)
+
+  end
+
+  # +StyleParser+ finds and rewrites URLs in HTML style attributes.
+  #
+  # === Implementation note:
+  # This methods in this class identify URLs by using regular expressions based on the W3C CSS 2.1 Specification (http://www.w3.org/TR/CSS21/syndata.html).
+  class StyleParser
+
+    # Returns the URLs found in a style attribute.
+    #
+    # @param [String] content the style attribute.
+    # @return [Array] the unique URLs found in the content.
+    #
+    # @example Parse style attribute for URLs
+    #   style = 'background: url(/images/rainbows.jpg);'
+    #   ContentUrls::StyleParser.urls(style).each do |url|
+    #     puts "Found URL: #{url}"
+    #   end
+    #   # => "Found URL: /images/rainbows.jpg"
+    #
+    def self.urls(style)
+      urls = []
+      rewrite_each_url(style) { |url| urls << url; url }
+      urls.uniq!
+      urls
+    end
+
+    # Rewrites each URL in an style attribute by calling the supplied block with each URL.
+    #
+    # @param [String] content the style attribute.
+    #
+    # @example Rewrite URLs in style attribute
+    #   style = 'background: url(/images/rainbows.jpg);'
+    #   style = ContentUrls::StyleParser.rewrite_each_url(style) {|url| url.sub(/rainbows.jpg/, 'unicorns.jpg')}
+    #   puts "Rewritten: #{style}"
+    #   # => "Rewritten: background: url(/images/unicorns.jpg);"
+    #
+    def self.rewrite_each_url(style, &block)
+      urls = {}
+      remaining = style
+      while !remaining.empty?
         if match = @@regex_uri.match(remaining)
-          url = match[7] || match[14] || match[23]
-          rewritten += match.pre_match
+          urls[match[:url]] = match[:uri]
           remaining = match.post_match
-          replacement = yield url
-          rewritten += (replacement.nil? ? match[0] : match[0].sub(url, replacement))
         else
-          rewritten += remaining
           remaining = ''
         end
       end
-      return rewritten
+      rewritten_content = [{:content => style, :is_rewritten => false}]
+      urls.each do |property_value, url|
+        rewritten_url = yield url
+        if rewritten_url != url
+          rewritten_property_value = property_value.dup
+          rewritten_property_value[url] = rewritten_url
+          i = 0
+          while i < rewritten_content.count
+            if !rewritten_content[i][:is_rewritten]
+              if match = /#{Regexp.escape(property_value)}/.match(rewritten_content[i][:content])
+                if match.pre_match.length > 0
+                  rewritten_content.insert(i, {:content => match.pre_match, :is_rewritten => false})
+                  i += 1
+                end
+                rewritten_content[i] = {:content => rewritten_property_value, :is_rewritten => true}
+                if match.post_match.length > 0
+                  rewritten_content.insert(i+1, {:content => match.post_match, :is_rewritten => false})
+                end
+              end
+            end
+            i += 1
+          end
+        end
+      end
+      rewritten_content.map { |c| c[:content]}.join
     end
 
     protected
@@ -84,10 +228,10 @@ class ContentUrls
     @@escape = '(' + @@unicode + '|\\\\[^\n\r\f0-9a-f])'
 
     # {string1}:  \"([^\n\r\f\\"]|\\{nl}|{escape})*\"
-    @@string1 = '(\"(([^\n\r\f\\\\"]|\\\\' + @@nl + '|' + @@escape + ')*)\")'
+    @@string1 = '(\"(?<uri>([^\n\r\f\\\\"]|\\\\' + @@nl + '|' + @@escape + ')*)\")'
 
     # {string2}:    \'([^\n\r\f\\']|\\{nl}|{escape})*\'
-    @@string2 = '(\\\'(([^\n\r\f\\\\\']|\\\\' + @@nl + '|' + @@escape + ')*)\\\')'
+    @@string2 = '(\\\'(?<uri>([^\n\r\f\\\\\']|\\\\' + @@nl + '|' + @@escape + ')*)\\\')'
 
     # {string}:       {string1}|{string2}
     @@string = '(' + @@string1 + '|' + @@string2 + ')'
@@ -96,7 +240,7 @@ class ContentUrls
     @@nonascii = '([^\x0-\x237])'
 
     # {uri}:    url\({w}{string}{w}\)|url\({w}([!#$%&*-\[\]-~]|{nonascii}|{escape})*{w}\)
-    @@uri = '(((url\(' + @@w + @@string + @@w + '\))|(url\(' + @@w + '(([!#$%&*-\[\]-~]|' + @@nonascii + '|' + @@escape + ')*)' + @@w + '\))))'
+    @@uri = '(?<url>((url\(' + @@w + @@string + @@w + '\))|(url\(' + @@w + '(?<uri>([!#$%&*-\[\]-~]|' + @@nonascii + '|' + @@escape + ')*)' + @@w + '\))))'
 
     # {badstring1}:  \"([^\n\r\f\\"]|\\{nl}|{escape})*\\?
     @@badstring1 = '(\"([^\n\r\f\\\\"]|\\\\' + @@nl + '|' + @@escape + ')*\\\\?)'
@@ -123,4 +267,5 @@ class ContentUrls
     @@regex_baduri = Regexp.new(@@baduri)
 
   end
+
 end

data/lib/content_urls/parsers/html_parser.rb

@@ -152,7 +152,7 @@ class ContentUrls
       style_attribute: {
         xpath: "//*[@style]",
         attribute: 'style',
-        parser: 'text/css'
+        parser: 'html-inline-style'
       },
       style_tag: {
         xpath: "//style",

data/lib/content_urls/parsers/java_script_parser.rb

@@ -1,4 +1,5 @@
 require 'uri'
+require 'rkelly'
 
 class ContentUrls
 
@@ -21,7 +22,8 @@ class ContentUrls
     #   # => "Found URL: http://example.com/"
     def self.urls(content)
       urls = []
-      URI.extract(content).each { |u| urls << u }
+      return urls if content.nil? || content.length == 0
+      rewrite_each_url(content) { |url| urls << url; url }
       urls.uniq!
       urls
     end
@@ -37,26 +39,30 @@ class ContentUrls
     #   # => "Rewritten: var link="HTTP://EXAMPLE.COM/""
     #
     def self.rewrite_each_url(content, &block)
-      done = false
-      remaining = content
-      rewritten = ''
-      while ! remaining.empty?
-        if match = URI.regexp.match(remaining)
-          url = match.to_s
-          rewritten += match.pre_match
-          replacement = url.nil? ? nil : (yield url)
-          if replacement.nil? or replacement == url  # no change in URL
-            rewritten += url
-          else
-            rewritten += replacement
+      rewritten_content = content.dup
+      rewrite_urls = {}
+      parser = RKelly::Parser.new
+      ast = parser.parse(content)
+      return content if ast.nil?
+      ast.each do |node|
+        if node.kind_of? RKelly::Nodes::StringNode
+          value = node.value
+          if match = /^'(.*)'$/.match(value)
+            value = match[1]  # remove single quotes
           end
-          remaining = match.post_match
-        else
-          rewritten += remaining
-          remaining = ''
+          if match = URI.regexp.match(value)
+            url = match.to_s
+            rewritten_url = yield url
+            rewrite_urls[url] = rewritten_url if url != rewritten_url
+          end
+        end
+      end
+      if rewrite_urls.count > 0
+        rewrite_urls.each do |url, rewritten_url|
+          rewritten_content[url] = rewritten_url
         end
       end
-      return rewritten
+      rewritten_content
     end
 
   end

data/lib/content_urls/version.rb

@@ -2,7 +2,7 @@ class ContentUrls
   module Version
     MAJOR = 0
     MINOR = 1
-    PATCH = 7
+    PATCH = 8
     BUILD = nil
 
     STRING = [MAJOR, MINOR, PATCH, BUILD].compact.join('.')

data/lib/content_urls.rb

@@ -146,6 +146,7 @@ class ContentUrls
 
   require 'content_urls/parsers/css_parser'
   register_parser ContentUrls::CssParser, %r{^(text/css)\b}
+  register_parser ContentUrls::StyleParser, %r{^(html-inline-style)\b}
 
   require 'content_urls/parsers/java_script_parser'
   register_parser ContentUrls::JavaScriptParser, %r{^(application/x-javascript)\b}, %r{^(application/javascript)\b}, %r{^(text/javascript)\b}

data/spec/css_parser_spec.rb

@@ -31,4 +31,20 @@ describe ContentUrls::CssParser do
     end
     output.should eq %Q{Found URL: /images/rainbows.jpg\n}
   end
+
+  it "should find and rewrite urls when css contains no spaces" do
+    output = ''
+    css = 'body{background:url(/images/rainbows.jpg)}'
+    css = ContentUrls::CssParser.rewrite_each_url(css) {|url| url.sub(/rainbows.jpg/, 'unicorns.jpg')}
+    output += "Rewritten: #{css}" + "\n"
+    output.should eq %Q{Rewritten: body{background:url(/images/unicorns.jpg)}\n}
+  end
+  it "should find urls when css contains no spaces" do
+    output = ''
+    css = 'body { background: url(/images/rainbows.jpg) }'
+    ContentUrls::CssParser.urls(css).each do |url|
+      output += "Found URL: #{url}" + "\n"
+    end
+    output.should eq %Q{Found URL: /images/rainbows.jpg\n}
+  end
 end

data/spec/java_script_parser_spec.rb

@@ -30,3 +30,21 @@ describe ContentUrls::JavaScriptParser do
     output.should eq %Q{Found URL: http://example.com/\n}
   end
 end
+
+describe ContentUrls::JavaScriptParser do
+  it "should correctly handle single quotes in rewrite_each_url method" do
+    output = ''
+    javascript = "var link='http://example.com/';"
+    javascript = ContentUrls::JavaScriptParser.rewrite_each_url(javascript) {|url| url.upcase}
+    output += "Rewritten: #{javascript}" + "\n"
+    output.should eq %Q{Rewritten: var link='HTTP://EXAMPLE.COM/';\n}
+  end
+  it "should correctly handle single quotes in urls method" do
+    output = ''
+    javascript = "var link='http://example.com/';"
+    ContentUrls::JavaScriptParser.urls(javascript).each do |url|
+      output += "Found URL: #{url}" + "\n"
+    end
+    output.should eq %Q{Found URL: http://example.com/\n}
+  end
+end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: content_urls
 version: !ruby/object:Gem::Version
-  version: 0.1.7
+  version: 0.1.8
 platform: ruby
 authors:
 - Dennis Sutch
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-07-18 00:00:00.000000000 Z
+date: 2013-08-01 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
@@ -24,6 +24,34 @@ dependencies:
     - - ~>
       - !ruby/object:Gem::Version
         version: 1.5.10
+- !ruby/object:Gem::Dependency
+  name: css_parser
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 1.3.4
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 1.3.4
+- !ruby/object:Gem::Dependency
+  name: rkelly
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 1.0.7
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 1.0.7
 - !ruby/object:Gem::Dependency
   name: rspec
   requirement: !ruby/object:Gem::Requirement
@@ -154,7 +182,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.0.4
+rubygems_version: 2.0.6
 signing_key: 
 specification_version: 4
 summary: Find and rewrite URLs in different types of content.