Merge pull request #1606 from MasterEnoc/cpp

C/C++ update

assets/stylesheets/application.css.scss

@@ -39,7 +39,7 @@
         'pages/async',
         'pages/bash',
         'pages/bootstrap',
-        'pages/c',
+        'pages/cppref',
         'pages/cakephp',
         'pages/clojure',
         'pages/codeception',

assets/stylesheets/pages/_cppref.scss

@@ -1,4 +1,4 @@
-._c {
+._cppref {
   > h2, > h3 { @extend %block-heading; }
   > h4 { @extend %block-label, %label-blue; }
   .fmbox { @extend %note; }

lib/docs/filters/c/entries.rb

@@ -22,6 +22,9 @@ module Docs
       end
 
       def get_type
+
+        return "C keywords" if slug =~ /keyword/
+
         type = at_css('.t-navbar > div:nth-child(4) > :first-child').try(:content)
         type.strip!
         type.remove! ' library'

lib/docs/filters/c/fix_urls.rb

@@ -1,11 +0,0 @@
-module Docs
-  class C
-    class FixUrlsFilter < Filter
-      def call
-        html.gsub! File.join(C.base_url, C.root_path), C.base_url[0..-2]
-        html.gsub! %r{#{C.base_url}([^"']+?)\.html}, "#{C.base_url}\\1"
-        html
-      end
-    end
-  end
-end

lib/docs/filters/cpp/entries.rb

@@ -1,6 +1,8 @@
 module Docs
   class Cpp
     class EntriesFilter < Docs::EntriesFilter
+      @@duplicate_names = []
+
       REPLACE_NAMES = {
         'Error directive' => '#error directive',
         'Filename and line information' => '#line directive',
@@ -11,7 +13,8 @@ module Docs
       def get_name
         name = at_css('#firstHeading').content.strip
         name = format_name(name)
-        name.split(',').first
+        name = name.split(',').first
+        name
       end
 
       def get_type
@@ -61,6 +64,21 @@ module Docs
 
         REPLACE_NAMES[name] || name
       end
+
+      # Avoid duplicate pages, these duplicate page are the same page for
+      # multiple functions that are organized in the same page because provide
+      # similar behavior but have different name.
+      def entries
+        entries = []
+
+        if !(@@duplicate_names.include?(name))
+          @@duplicate_names.push(name)
+          entries << default_entry if root_page? || include_default_entry?
+          entries.concat(additional_entries)
+          build_entries(entries)
+        end
+      end
+
     end
   end
 end

lib/docs/filters/cpp/fix_urls.rb

@@ -1,11 +0,0 @@
-module Docs
-  class Cpp
-    class FixUrlsFilter < Filter
-      def call
-        html.gsub! File.join(Cpp.base_url, Cpp.root_path), Cpp.base_url[0..-2]
-        html.gsub! %r{#{Cpp.base_url}([^"']+?)\.html}, "#{Cpp.base_url}\\1"
-        html
-      end
-    end
-  end
-end

lib/docs/filters/cppref/clean_html.rb

@@ -1,5 +1,5 @@
 module Docs
-  class C
+  class Cppref
     class CleanHtmlFilter < Filter
       def call
         css('h1').remove if root_page?
@@ -109,6 +109,20 @@ module Docs
           node['src'] = node['src'].sub! %r{http://en.cppreference.com/common/([^"']+?)\.svg}, 'http://upload.cppreference.com/mwiki/\1.svg'
         end
 
+        # temporary solution due lack of mathjax/mathml support
+        css('.t-mfrac').each do |node|
+          fraction = Nokogiri::XML::Node.new('span', doc)
+
+          node.css('td').each do |node|
+            fraction.add_child("<span>#{node.content}</span>")
+          end
+
+          fraction.last_element_child().before("<span>/</span>")
+
+          node.before(fraction)
+          node.remove
+        end
+
         doc
       end
     end

lib/docs/filters/cppref/fix_code.rb

@@ -1,5 +1,5 @@
 module Docs
-  class C
+  class Cppref
     class FixCodeFilter < Filter
       def call
         css('div > span.source-c', 'div > span.source-cpp').each do |node|

lib/docs/scrapers/c.rb

@@ -1,42 +0,0 @@
-module Docs
-  class C < FileScraper
-    self.type = 'c'
-    self.base_url = 'http://en.cppreference.com/w/c/'
-    self.root_path = 'header.html'
-
-    html_filters.insert_before 'clean_html', 'c/fix_code'
-    html_filters.push 'c/entries', 'c/clean_html', 'title'
-    text_filters.push 'c/fix_urls'
-
-    options[:decode_and_clean_paths] = true
-    options[:container] = '#content'
-    options[:title] = false
-    options[:root_title] = 'C Programming Language'
-    options[:skip] = %w(language/history.html)
-    options[:skip_patterns] = [/experimental/]
-
-    options[:fix_urls] = ->(url) do
-      url.sub! %r{\A.+/http%3A/}, 'http://'
-      url.sub! 'http://en.cppreference.com/upload.cppreference.com', 'http://upload.cppreference.com'
-      url
-    end
-
-    options[:attribution] = <<-HTML
-      &copy; cppreference.com<br>
-      Licensed under the Creative Commons Attribution-ShareAlike Unported License v3.0.
-    HTML
-
-    def get_latest_version(opts)
-      doc = fetch_doc('https://en.cppreference.com/w/Cppreference:Archives', opts)
-      link = doc.at_css('a[title^="File:"]')
-      date = link.content.scan(/(\d+)\./)[0][0]
-      DateTime.strptime(date, '%Y%m%d').to_time.to_i
-    end
-
-    private
-
-    def file_path_for(*)
-      URI.unescape(super)
-    end
-  end
-end

lib/docs/scrapers/cpp.rb

@@ -1,52 +0,0 @@
-module Docs
-  class Cpp < FileScraper
-    self.name = 'C++'
-    self.slug = 'cpp'
-    self.type = 'c'
-    self.base_url = 'http://en.cppreference.com/w/cpp/'
-    self.root_path = 'header.html'
-
-    html_filters.insert_before 'clean_html', 'c/fix_code'
-    html_filters.push 'cpp/entries', 'c/clean_html', 'title'
-    text_filters.push 'cpp/fix_urls'
-
-    options[:decode_and_clean_paths] = true
-    options[:container] = '#content'
-    options[:title] = false
-    options[:root_title] = 'C++ Programming Language'
-    options[:skip] = %w(
-      language/extending_std.html
-      language/history.html
-      regex/ecmascript.html
-      regex/regex_token_iterator/operator_cmp.html
-    )
-    options[:skip_patterns] = [/experimental/]
-    options[:only_patterns] = [/\.html\z/]
-
-    options[:fix_urls] = ->(url) do
-      url = CGI.unescape(url)
-      url.sub! %r{\A.+/http%3A/}, 'http://'
-      url.sub! 'http://en.cppreference.com/upload.cppreference.com', 'http://upload.cppreference.com'
-      url
-    end
-
-    options[:attribution] = <<-HTML
-      &copy; cppreference.com<br>
-      Licensed under the Creative Commons Attribution-ShareAlike Unported License v3.0.
-    HTML
-
-    # Same as get_latest_version in lib/docs/scrapers/c.rb
-    def get_latest_version(opts)
-      doc = fetch_doc('https://en.cppreference.com/w/Cppreference:Archives', opts)
-      link = doc.at_css('a[title^="File:"]')
-      date = link.content.scan(/(\d+)\./)[0][0]
-      DateTime.strptime(date, '%Y%m%d').to_time.to_i
-    end
-
-    private
-
-    def file_path_for(*)
-      URI.unescape(super)
-    end
-  end
-end

lib/docs/scrapers/cppref/c.rb

@@ -0,0 +1,12 @@
+module Docs
+  class C < Cppref
+    self.name = 'c'
+    self.slug = 'c'
+    self.base_url = 'https://en.cppreference.com/w/c/'
+
+    html_filters.insert_before 'cppref/clean_html', 'c/entries'
+
+    options[:root_title] = 'C Programming Language'
+
+  end
+end

lib/docs/scrapers/cppref/cpp.rb

@@ -0,0 +1,19 @@
+module Docs
+  class Cpp < Cppref
+    self.name = 'C++'
+    self.slug = 'cpp'
+    self.base_url = 'https://en.cppreference.com/w/cpp/'
+
+    html_filters.insert_before 'cppref/clean_html', 'cpp/entries'
+
+    options[:root_title] = 'C++ Programming Language'
+
+    options[:skip] = %w(
+      language/extending_std.html
+      language/history.html
+      regex/ecmascript.html
+      regex/regex_token_iterator/operator_cmp.html
+    )
+
+  end
+end

lib/docs/scrapers/cppref/cppref.rb

@@ -0,0 +1,33 @@
+module Docs
+  class Cppref < UrlScraper
+    self.abstract = true
+    self.type = 'cppref'
+    self.root_path = 'header'
+
+    html_filters.insert_before 'clean_html', 'cppref/fix_code'
+    html_filters.push  'cppref/clean_html', 'title'
+
+    options[:decode_and_clean_paths] = true
+    options[:container] = '#content'
+    options[:title] = false
+    options[:skip] = %w(language/history.html)
+
+    options[:skip_patterns] = [
+      /experimental/
+    ]
+
+    options[:attribution] = <<-HTML
+      &copy; cppreference.com<br>
+      Licensed under the Creative Commons Attribution-ShareAlike Unported License v3.0.
+    HTML
+
+    # Check if the 'headers' page has changed
+    def get_latest_version(opts)
+      doc = fetch_doc(self.base_url + self.root_path, opts)
+      date = doc.at_css('#footer-info-lastmod').content
+      date = date.match(/[[:digit:]]{1,2} .* [[:digit:]]{4}/).to_s
+      date = DateTime.strptime(date, '%e %B %Y').to_time.to_i
+    end
+
+  end
+end