w3clove 0.7.1 → 0.7.2

data/README.rdoc

@@ -22,6 +22,21 @@ This will validate all the internal URLs found on the starting URL, up to a maxi
 
 You can pass w3clove an XML sitemap or the URL of a website; it will scrape it in search of URLs to validate.
 
+= Timeouts:
+
+By default, the w3clove gem will set a 20 seconds timeout for each individual request. If you want to set a different timeout, pass it as a third parameter like this:
+
+  w3clove http://ryanair.com/sitemap.xml report.html 60
+
+= Using an alternate validation server
+
+By default, the w3clove gem will use the official W3C Validator server at http://validator.w3.org but you can use an alternate server if you want.
+To do this, define an environment variable on your machine, like:
+
+  ENV['W3C_MARKUP_VALIDATOR_URI'] = 'http://example.com/validator'
+
+Follow this guide to know how to setup your own validation server: https://github.com/tlvince/w3c-validator-guide
+
 = Notes:
 
 This gem requires Ruby 1.9, and has been tested on Ruby 1.9.2-p0

data/bin/w3clove

@@ -4,10 +4,12 @@
 require_relative '../lib/w3clove'
 
 begin
-  if ARGV.length == 2
-    W3Clove::Validator.check(ARGV[0], ARGV[1])
+  if ARGV.length >= 2
+    W3Clove::Validator.check(ARGV[0], ARGV[1], ARGV[2])
   else
     puts "USAGE:  w3clove  url_of_sitemap  output_file.html"
+    puts " OR "
+    puts "USAGE:  w3clove  url_of_sitemap  output_file.html  timeout_in_seconds"
   end
 rescue
   puts "There was an error processing your request"

data/lib/w3clove/page.rb

@@ -10,10 +10,11 @@ module W3Clove
   # In case of an exception happens when validating, it is tracked
   #
   class Page
-    attr_accessor :url, :exception
+    attr_accessor :url, :timeout, :exception
 
-    def initialize(url)
-      @url = url
+    def initialize(url, timeout = 20)
+      @url      = url
+      @timeout  = timeout
     end
 
     ##
@@ -61,7 +62,13 @@ module W3Clove
     ##
     # Gets the validations for this page, ensuring it times out soon
     def validations
-      @validations ||= Timeout::timeout(10) { MarkupValidator.new.validate_uri(url) }
+      @validations ||= Timeout::timeout(timeout) { markup_validator.validate_uri(url) }
+    end
+
+    ##
+    # Returns an instance of MarkupValidator, with the URL set to the one in ENV or its default
+    def markup_validator
+      @markup_validator ||= MarkupValidator.new(:validator_uri => ENV['W3C_MARKUP_VALIDATOR_URI'] || 'http://validator.w3.org/check')
     end
   end
 end

data/lib/w3clove/sitemap.rb

@@ -3,16 +3,18 @@
 require 'open-uri'
 require 'nokogiri'
 require 'metainspector'
+require 'timeout'
 
 module W3Clove
   ##
   # A sitemap has an URL, and holds a collection of pages to be validated
   #
   class Sitemap
-    attr_accessor :url
+    attr_accessor :url, :timeout
 
-    def initialize(url)
-      @url = url
+    def initialize(url, timeout = 20)
+      @url      = url
+      @timeout  = timeout
     end
 
     ##
@@ -53,7 +55,7 @@ module W3Clove
     def pages_in_sitemap
       pages = xml_locations.map {|loc| W3Clove::Page.new(loc.text)}
       if pages.empty?
-        m     = MetaInspector.new(url)
+        m     = MetaInspector.new(url, timeout)
         links = m.absolute_links.select {|l| l.start_with?(m.url) && looks_like_html?(l)}.map {|l| l.split('#')[0]}.uniq
         links << m.url unless (links.include?(m.url) || links.include?("#{m.url}/"))
         pages = links.map {|link| W3Clove::Page.new(link)}

data/lib/w3clove/validator.rb

@@ -15,8 +15,8 @@ module W3Clove
     # Shows progress on dot-style (...F...FFE..). A dot is a valid page,
     # an F is a page with errors, and an E is an exception
     # After the checking is done, a detailed summary is written to filename
-    def check(url, filename)
-      sitemap = W3Clove::Sitemap.new(url)
+    def check(url, filename, timeout)
+      sitemap = W3Clove::Sitemap.new(url, timeout.to_f)
       say "Validating #{sitemap.pages.length} pages"
 
       sitemap.pages.each do |page|

data/lib/w3clove/version.rb

@@ -1,5 +1,5 @@
 # -*- encoding: utf-8 -*-
 
 module W3Clove
-  VERSION = "0.7.1"
+  VERSION = "0.7.2"
 end

data/w3clove.gemspec

@@ -18,7 +18,7 @@ and outputs a detailed report with all errors and warnings}
 
   gem.add_dependency 'w3c_validators', '~> 1.2'
   gem.add_dependency 'nokogiri', '~> 1.5.3'
-  gem.add_dependency 'metainspector', '~> 1.9.0'
+  gem.add_dependency 'metainspector', '1.9.1'
 
   gem.add_development_dependency 'rspec', '~> 2.5.0'
   gem.add_development_dependency 'mocha', '~> 0.11.4'

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: w3clove
 version: !ruby/object:Gem::Version 
-  hash: 1
+  hash: 7
   prerelease: 
   segments: 
   - 0
   - 7
-  - 1
-  version: 0.7.1
+  - 2
+  version: 0.7.2
 platform: ruby
 authors: 
 - Jaime Iniesta
@@ -15,7 +15,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2012-06-22 00:00:00 Z
+date: 2012-07-12 00:00:00 Z
 dependencies: 
 - !ruby/object:Gem::Dependency 
   name: w3c_validators
@@ -54,14 +54,14 @@ dependencies:
   requirement: &id003 !ruby/object:Gem::Requirement 
     none: false
     requirements: 
-    - - ~>
+    - - "="
       - !ruby/object:Gem::Version 
-        hash: 51
+        hash: 49
         segments: 
         - 1
         - 9
-        - 0
-        version: 1.9.0
+        - 1
+        version: 1.9.1
   type: :runtime
   version_requirements: *id003
 - !ruby/object:Gem::Dependency