validate-website 1.5.7 → 1.5.8

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 19b5caf5684592eb5e6b49412c7f8a0e4db8c2b2
-  data.tar.gz: 76593f1fe75dcc5c8bbb774c3ea5d808e6ef87d5
+  metadata.gz: b113a6d49dafd4312e90c91b90ef823a7783b2a6
+  data.tar.gz: 81f4d59065bd48c9a2e1deb8fc13454c351269fd
 SHA512:
-  metadata.gz: 903af9e5534dab24012acd929314cd451f2ef07aee8037acac3c0add88fc33b8671888abb8d2739fb88f770a847847f264a22011e68103b90b9b00073e916ec1
-  data.tar.gz: 8a0725fa75523673943e960bd304febbefd2d5ff106b9820fc8975bd44e0e059d81ae38313d7df3590f937e4a986c45d63386e323138c151575c8c7d6d90454a
+  metadata.gz: 0653c9131b9f42af196335d230f80edd08429f5e7405034404e7632d8df71523491c9445e28da1a5aecd5462af23390db3346bbb39b3748042a18ebd060d1e99
+  data.tar.gz: 557e7164a448d99ebda6256f7fb73157a785f509844fc9b02878fafcc103334fbb80737676765d00da27ed3ea47cca3eeccbfc88a99aed5b45cd845465e1fe81

data/History.md

@@ -1,6 +1,13 @@
 
+v1.5.8 / 2016-06-27
+===================
+
+  * Update manpages
+  * Exclude urls on static crawl
+  * Fix warning: instance variable not initialized
+
 v1.5.7 / 2016-06-13
-==================
+===================
 
   * Fix JRuby CI build
   * Update JRuby and other rubies on Travis
@@ -8,7 +15,7 @@ v1.5.7 / 2016-06-13
   * Add env variable VALIDATOR_NU_URL support
 
 v1.5.6 / 2016-03-02
-==================
+===================
 
   * Fix error with redirect and extract images (see #16)
   * Display version number
@@ -16,12 +23,12 @@ v1.5.6 / 2016-03-02
   * Updates deps
 
 v1.5.4 / 2015-12-08
-==================
+===================
 
   * Fix URI must be ascii only error
 
 v1.5.3 / 2015-11-08
-==================
+===================
 
   * Fix test_files on gemspec
   * Use File.expand_path for jruby

data/lib/validate_website/core.rb

@@ -17,7 +17,7 @@ module ValidateWebsite
   # Core class for static or website validation
   class Core
     attr_accessor :site
-    attr_reader :options, :crawler, :errors_count, :not_founds_count, :host
+    attr_reader :options, :host, :errors_count, :not_founds_count
 
     include ColorfulMessages
 

data/lib/validate_website/crawl.rb

@@ -4,10 +4,16 @@ require 'validate_website/utils'
 module ValidateWebsite
   # Class for http website validation
   class Crawl < Core
+    attr_reader :crawler
+
     def initialize(options = {}, validation_type = :crawl)
       super
     end
 
+    def history_count
+      crawler.history.size
+    end
+
     # @param [Hash] options
     #   :color [Boolean] color output (true, false)
     #   :exclude [String] a String used by Regexp.new

data/lib/validate_website/option_parser.rb

@@ -117,6 +117,7 @@ module ValidateWebsite
         o.string('-p', '--pattern',
                  "Filename pattern (default: #{DEFAULT_OPTIONS[:pattern]})",
                  default: DEFAULT_OPTIONS[:pattern])
+        o.regexp('-e', '--exclude', 'Url to exclude (ex: "redirect|news")')
       end
     end
   end

data/lib/validate_website/static.rb

@@ -6,7 +6,10 @@ module ValidateWebsite
   class Static < Core
     CONTENT_TYPES = ['text/html', 'text/xhtml+xml'].freeze
 
+    attr_reader :history_count
+
     def initialize(options = {}, validation_type = :static)
+      @history_count = 0
       super
     end
 
@@ -19,6 +22,8 @@ module ValidateWebsite
       files = Dir.glob(@options[:pattern])
       files.each do |f|
         next unless File.file?(f)
+        next if @options[:exclude].is_a?(Regexp) && @options[:exclude].match(f)
+        @history_count += 1
         check_static_file(f)
       end
       print_status_line(files.size, 0, @not_founds_count, @errors_count)

data/lib/validate_website/validator.rb

@@ -14,7 +14,7 @@ module ValidateWebsite
       attr_accessor :html5_validator_service_url
     end
 
-    attr_reader :original_doc, :body, :dtd, :doc, :namespace, :xsd
+    attr_reader :original_doc, :body, :dtd, :doc, :namespace
 
     ##
     # @param [Nokogiri::HTML::Document] original_doc
@@ -22,12 +22,13 @@ module ValidateWebsite
     # @param [Regexp] Errors to ignore
     #
     def initialize(original_doc, body, ignore = nil)
+      @errors = []
+      @document, @dtd_uri = nil
       @original_doc = original_doc
       @body = body
       @ignore = ignore
       @dtd = @original_doc.internal_subset
       @namespace = init_namespace(@dtd)
-      @errors = []
     end
 
     ##
@@ -74,7 +75,7 @@ module ValidateWebsite
 
     # @return [Array] contain result errors
     def validate(xml_doc, document_body)
-      if xsd
+      if !xsd.nil?
         xsd.validate(xml_doc)
       elsif document_body =~ /^\<!DOCTYPE html\>/i
         html5_validate(document_body)

data/lib/validate_website/version.rb

@@ -2,5 +2,5 @@
 
 # Version file for ValidateWebsite
 module ValidateWebsite
-  VERSION = '1.5.7'.freeze
+  VERSION = '1.5.8'.freeze
 end

data/man/man1/validate-website-static.1

@@ -1,13 +1,13 @@
 '\" t
 .\"     Title: validate-website-static
 .\"    Author: [see the "AUTHOR" section]
-.\" Generator: DocBook XSL Stylesheets v1.78.1 <http://docbook.sf.net/>
-.\"      Date: 07/21/2015
+.\" Generator: DocBook XSL Stylesheets v1.79.1 <http://docbook.sf.net/>
+.\"      Date: 06/19/2016
 .\"    Manual: \ \&
 .\"    Source: \ \&
 .\"  Language: English
 .\"
-.TH "VALIDATE\-WEBSITE\-S" "1" "07/21/2015" "\ \&" "\ \&"
+.TH "VALIDATE\-WEBSITE\-S" "1" "06/19/2016" "\ \&" "\ \&"
 .\" -----------------------------------------------------------------
 .\" * Define some portability stuff
 .\" -----------------------------------------------------------------
@@ -48,6 +48,12 @@ http://www\&.example\&.com/)
 Change filenames pattern (Default: **/*\&.html)
 .RE
 .PP
+\fB\-e\fR, \fB\-\-exclude\fR \fIEXCLUDE\fR
+.RS 4
+Url to exclude (ex:
+\fIredirect|news\fR)
+.RE
+.PP
 \fB\-i\fR, \fB\-\-ignore\fR \fIIGNORE\fR
 .RS 4
 Ignore certain validation errors (ex:

data/man/man1/validate-website.1

@@ -1,13 +1,13 @@
 '\" t
 .\"     Title: validate-website
 .\"    Author: [see the "AUTHOR" section]
-.\" Generator: DocBook XSL Stylesheets v1.78.1 <http://docbook.sf.net/>
-.\"      Date: 07/21/2015
+.\" Generator: DocBook XSL Stylesheets v1.79.1 <http://docbook.sf.net/>
+.\"      Date: 06/19/2016
 .\"    Manual: \ \&
 .\"    Source: \ \&
 .\"  Language: English
 .\"
-.TH "VALIDATE\-WEBSITE" "1" "07/21/2015" "\ \&" "\ \&"
+.TH "VALIDATE\-WEBSITE" "1" "06/19/2016" "\ \&" "\ \&"
 .\" -----------------------------------------------------------------
 .\" * Define some portability stuff
 .\" -----------------------------------------------------------------

data/test/crawler_test.rb

@@ -54,7 +54,7 @@ describe ValidateWebsite::Crawl do
       _out, _err = capture_io do
         @validate_website.crawl
       end
-      @validate_website.crawler.history.size.must_equal 5
+      @validate_website.history_count.must_equal 5
     end
 
     it 'extract link' do
@@ -67,7 +67,7 @@ describe ValidateWebsite::Crawl do
       _out, _err = capture_io do
         @validate_website.crawl
       end
-      @validate_website.crawler.history.size.must_equal 98
+      @validate_website.history_count.must_equal 98
     end
 
     it 'crawl when URLs are not ascii only' do
@@ -114,7 +114,7 @@ describe ValidateWebsite::Crawl do
         _out, _err = capture_io do
           @validate_website.crawl
         end
-        @validate_website.crawler.history.size.must_equal 5
+        @validate_website.history_count.must_equal 5
       end
 
       it 'should extract url with single quote' do
@@ -125,7 +125,7 @@ describe ValidateWebsite::Crawl do
         _out, _err = capture_io do
           @validate_website.crawl
         end
-        @validate_website.crawler.history.size.must_equal 2
+        @validate_website.history_count.must_equal 2
       end
 
       it 'should extract url with double quote' do
@@ -136,7 +136,7 @@ describe ValidateWebsite::Crawl do
         _out, _err = capture_io do
           @validate_website.crawl
         end
-        @validate_website.crawler.history.size.must_equal 2
+        @validate_website.history_count.must_equal 2
       end
 
       it 'should extract url with params' do
@@ -147,7 +147,7 @@ describe ValidateWebsite::Crawl do
         _out, _err = capture_io do
           @validate_website.crawl
         end
-        @validate_website.crawler.history.size.must_equal 2
+        @validate_website.history_count.must_equal 2
       end
 
       it 'should not extract invalid urls' do
@@ -158,7 +158,7 @@ describe ValidateWebsite::Crawl do
         _out, _err = capture_io do
           @validate_website.crawl
         end
-        @validate_website.crawler.history.size.must_equal 1
+        @validate_website.history_count.must_equal 1
       end
     end
 

data/test/static_test.rb

@@ -7,6 +7,18 @@ describe ValidateWebsite::Static do
     end
   end
 
+  it 'exclude directories' do
+    pattern = File.join(File.dirname(__FILE__), '**/*.html')
+    _out, _err = capture_io do
+      @validate_website.crawl(pattern: pattern,
+                              site: 'http://spkdev.net/',
+                              markup: false,
+                              not_found: false,
+                              exclude: /data|example/)
+    end
+    @validate_website.history_count.must_equal 0
+  end
+
   it 'no space in directory name' do
     pattern = File.join(File.dirname(__FILE__), 'example/**/*.html')
     _out, _err = capture_io do

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: validate-website
 version: !ruby/object:Gem::Version
-  version: 1.5.7
+  version: 1.5.8
 platform: ruby
 authors:
 - Laurent Arnoud
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2016-06-13 00:00:00.000000000 Z
+date: 2016-06-27 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: spidr