C/C++ update
Unified · Split
| @@ -39,7 +39,7 @@ · 38 unmodified lines | |||
| 39 | 'pages/async', | 39 | 'pages/async', |
| 40 | 'pages/bash', | 40 | 'pages/bash', |
| 41 | 'pages/bootstrap', | 41 | 'pages/bootstrap', |
| 42 | 'pages/c', | 42 | 'pages/cppref', |
| 43 | 'pages/cakephp', | 43 | 'pages/cakephp', |
| 44 | 'pages/clojure', | 44 | 'pages/clojure', |
| 45 | 'pages/codeception', | 45 | 'pages/codeception', |
| @@ -1,4 +1,4 @@ | |||
| 1 | ._c { | 1 | ._cppref { |
| 2 | > h2, > h3 { @extend %block-heading; } | 2 | > h2, > h3 { @extend %block-heading; } |
| 3 | > h4 { @extend %block-label, %label-blue; } | 3 | > h4 { @extend %block-label, %label-blue; } |
| 4 | .fmbox { @extend %note; } | 4 | .fmbox { @extend %note; } |
| @@ -22,6 +22,9 @@ module Docs · 21 unmodified lines | |||
| 22 | end | 22 | end |
| 23 | 23 | ||
| 24 | def get_type | 24 | def get_type |
| 25 | |||
| 26 | return "C keywords" if slug =~ /keyword/ | ||
| 27 | |||
| 25 | type = at_css('.t-navbar > div:nth-child(4) > :first-child').try(:content) | 28 | type = at_css('.t-navbar > div:nth-child(4) > :first-child').try(:content) |
| 26 | type.strip! | 29 | type.strip! |
| 27 | type.remove! ' library' | 30 | type.remove! ' library' |
| @@ -1,11 +0,0 @@ | |||
| 1 | module Docs | ||
| 2 | class C | ||
| 3 | class FixUrlsFilter < Filter | ||
| 4 | def call | ||
| 5 | html.gsub! File.join(C.base_url, C.root_path), C.base_url[0..-2] | ||
| 6 | html.gsub! %r{#{C.base_url}([^"']+?)\.html}, "#{C.base_url}\\1" | ||
| 7 | html | ||
| 8 | end | ||
| 9 | end | ||
| 10 | end | ||
| 11 | end | ||
| @@ -1,6 +1,8 @@ | |||
| 1 | module Docs | 1 | module Docs |
| 2 | class Cpp | 2 | class Cpp |
| 3 | class EntriesFilter < Docs::EntriesFilter | 3 | class EntriesFilter < Docs::EntriesFilter |
| 4 | @@duplicate_names = [] | ||
| 5 | |||
| 4 | REPLACE_NAMES = { | 6 | REPLACE_NAMES = { |
| 5 | 'Error directive' => '#error directive', | 7 | 'Error directive' => '#error directive', |
| 6 | 'Filename and line information' => '#line directive', | 8 | 'Filename and line information' => '#line directive', |
| @@ -11,7 +13,8 @@ module Docs · 4 unmodified lines | |||
| 11 | def get_name | 13 | def get_name |
| 12 | name = at_css('#firstHeading').content.strip | 14 | name = at_css('#firstHeading').content.strip |
| 13 | name = format_name(name) | 15 | name = format_name(name) |
| 14 | name.split(',').first | 16 | name = name.split(',').first |
| 17 | name | ||
| 15 | end | 18 | end |
| 16 | 19 | ||
| 17 | def get_type | 20 | def get_type |
| @@ -61,6 +64,21 @@ module Docs · 43 unmodified lines | |||
| 61 | 64 | ||
| 62 | REPLACE_NAMES[name] || name | 65 | REPLACE_NAMES[name] || name |
| 63 | end | 66 | end |
| 67 | |||
| 68 | # Avoid duplicate pages, these duplicate page are the same page for | ||
| 69 | # multiple functions that are organized in the same page because provide | ||
| 70 | # similar behavior but have different name. | ||
| 71 | def entries | ||
| 72 | entries = [] | ||
| 73 | |||
| 74 | if !(@@duplicate_names.include?(name)) | ||
| 75 | @@duplicate_names.push(name) | ||
| 76 | entries << default_entry if root_page? || include_default_entry? | ||
| 77 | entries.concat(additional_entries) | ||
| 78 | build_entries(entries) | ||
| 79 | end | ||
| 80 | end | ||
| 81 | |||
| 64 | end | 82 | end |
| 65 | end | 83 | end |
| 66 | end | 84 | end |
| @@ -1,11 +0,0 @@ | |||
| 1 | module Docs | ||
| 2 | class Cpp | ||
| 3 | class FixUrlsFilter < Filter | ||
| 4 | def call | ||
| 5 | html.gsub! File.join(Cpp.base_url, Cpp.root_path), Cpp.base_url[0..-2] | ||
| 6 | html.gsub! %r{#{Cpp.base_url}([^"']+?)\.html}, "#{Cpp.base_url}\\1" | ||
| 7 | html | ||
| 8 | end | ||
| 9 | end | ||
| 10 | end | ||
| 11 | end | ||
| @@ -1,5 +1,5 @@ | |||
| 1 | module Docs | 1 | module Docs |
| 2 | class C | 2 | class Cppref |
| 3 | class CleanHtmlFilter < Filter | 3 | class CleanHtmlFilter < Filter |
| 4 | def call | 4 | def call |
| 5 | css('h1').remove if root_page? | 5 | css('h1').remove if root_page? |
| @@ -109,6 +109,20 @@ module Docs · 103 unmodified lines | |||
| 109 | node['src'] = node['src'].sub! %r{http://en.cppreference.com/common/([^"']+?)\.svg}, 'http://upload.cppreference.com/mwiki/\1.svg' | 109 | node['src'] = node['src'].sub! %r{http://en.cppreference.com/common/([^"']+?)\.svg}, 'http://upload.cppreference.com/mwiki/\1.svg' |
| 110 | end | 110 | end |
| 111 | 111 | ||
| 112 | # temporary solution due lack of mathjax/mathml support | ||
| 113 | css('.t-mfrac').each do |node| | ||
| 114 | fraction = Nokogiri::XML::Node.new('span', doc) | ||
| 115 | |||
| 116 | node.css('td').each do |node| | ||
| 117 | fraction.add_child("<span>#{node.content}</span>") | ||
| 118 | end | ||
| 119 | |||
| 120 | fraction.last_element_child().before("<span>/</span>") | ||
| 121 | |||
| 122 | node.before(fraction) | ||
| 123 | node.remove | ||
| 124 | end | ||
| 125 | |||
| 112 | doc | 126 | doc |
| 113 | end | 127 | end |
| 114 | end | 128 | end |
| @@ -1,5 +1,5 @@ | |||
| 1 | module Docs | 1 | module Docs |
| 2 | class C | 2 | class Cppref |
| 3 | class FixCodeFilter < Filter | 3 | class FixCodeFilter < Filter |
| 4 | def call | 4 | def call |
| 5 | css('div > span.source-c', 'div > span.source-cpp').each do |node| | 5 | css('div > span.source-c', 'div > span.source-cpp').each do |node| |
| @@ -1,42 +0,0 @@ | |||
| 1 | module Docs | ||
| 2 | class C < FileScraper | ||
| 3 | self.type = 'c' | ||
| 4 | self.base_url = 'http://en.cppreference.com/w/c/' | ||
| 5 | self.root_path = 'header.html' | ||
| 6 | |||
| 7 | html_filters.insert_before 'clean_html', 'c/fix_code' | ||
| 8 | html_filters.push 'c/entries', 'c/clean_html', 'title' | ||
| 9 | text_filters.push 'c/fix_urls' | ||
| 10 | |||
| 11 | options[:decode_and_clean_paths] = true | ||
| 12 | options[:container] = '#content' | ||
| 13 | options[:title] = false | ||
| 14 | options[:root_title] = 'C Programming Language' | ||
| 15 | options[:skip] = %w(language/history.html) | ||
| 16 | options[:skip_patterns] = [/experimental/] | ||
| 17 | |||
| 18 | options[:fix_urls] = ->(url) do | ||
| 19 | url.sub! %r{\A.+/http%3A/}, 'http://' | ||
| 20 | url.sub! 'http://en.cppreference.com/upload.cppreference.com', 'http://upload.cppreference.com' | ||
| 21 | url | ||
| 22 | end | ||
| 23 | |||
| 24 | options[:attribution] = <<-HTML | ||
| 25 | © cppreference.com<br> | ||
| 26 | Licensed under the Creative Commons Attribution-ShareAlike Unported License v3.0. | ||
| 27 | HTML | ||
| 28 | |||
| 29 | def get_latest_version(opts) | ||
| 30 | doc = fetch_doc('https://en.cppreference.com/w/Cppreference:Archives', opts) | ||
| 31 | link = doc.at_css('a[title^="File:"]') | ||
| 32 | date = link.content.scan(/(\d+)\./)[0][0] | ||
| 33 | DateTime.strptime(date, '%Y%m%d').to_time.to_i | ||
| 34 | end | ||
| 35 | |||
| 36 | private | ||
| 37 | |||
| 38 | def file_path_for(*) | ||
| 39 | URI.unescape(super) | ||
| 40 | end | ||
| 41 | end | ||
| 42 | end | ||
| @@ -1,52 +0,0 @@ | |||
| 1 | module Docs | ||
| 2 | class Cpp < FileScraper | ||
| 3 | self.name = 'C++' | ||
| 4 | self.slug = 'cpp' | ||
| 5 | self.type = 'c' | ||
| 6 | self.base_url = 'http://en.cppreference.com/w/cpp/' | ||
| 7 | self.root_path = 'header.html' | ||
| 8 | |||
| 9 | html_filters.insert_before 'clean_html', 'c/fix_code' | ||
| 10 | html_filters.push 'cpp/entries', 'c/clean_html', 'title' | ||
| 11 | text_filters.push 'cpp/fix_urls' | ||
| 12 | |||
| 13 | options[:decode_and_clean_paths] = true | ||
| 14 | options[:container] = '#content' | ||
| 15 | options[:title] = false | ||
| 16 | options[:root_title] = 'C++ Programming Language' | ||
| 17 | options[:skip] = %w( | ||
| 18 | language/extending_std.html | ||
| 19 | language/history.html | ||
| 20 | regex/ecmascript.html | ||
| 21 | regex/regex_token_iterator/operator_cmp.html | ||
| 22 | ) | ||
| 23 | options[:skip_patterns] = [/experimental/] | ||
| 24 | options[:only_patterns] = [/\.html\z/] | ||
| 25 | |||
| 26 | options[:fix_urls] = ->(url) do | ||
| 27 | url = CGI.unescape(url) | ||
| 28 | url.sub! %r{\A.+/http%3A/}, 'http://' | ||
| 29 | url.sub! 'http://en.cppreference.com/upload.cppreference.com', 'http://upload.cppreference.com' | ||
| 30 | url | ||
| 31 | end | ||
| 32 | |||
| 33 | options[:attribution] = <<-HTML | ||
| 34 | © cppreference.com<br> | ||
| 35 | Licensed under the Creative Commons Attribution-ShareAlike Unported License v3.0. | ||
| 36 | HTML | ||
| 37 | |||
| 38 | # Same as get_latest_version in lib/docs/scrapers/c.rb | ||
| 39 | def get_latest_version(opts) | ||
| 40 | doc = fetch_doc('https://en.cppreference.com/w/Cppreference:Archives', opts) | ||
| 41 | link = doc.at_css('a[title^="File:"]') | ||
| 42 | date = link.content.scan(/(\d+)\./)[0][0] | ||
| 43 | DateTime.strptime(date, '%Y%m%d').to_time.to_i | ||
| 44 | end | ||
| 45 | |||
| 46 | private | ||
| 47 | |||
| 48 | def file_path_for(*) | ||
| 49 | URI.unescape(super) | ||
| 50 | end | ||
| 51 | end | ||
| 52 | end | ||
| @@ -0,0 +1,12 @@ | |||
| 1 | module Docs | ||
| 2 | class C < Cppref | ||
| 3 | self.name = 'c' | ||
| 4 | self.slug = 'c' | ||
| 5 | self.base_url = 'https://en.cppreference.com/w/c/' | ||
| 6 | |||
| 7 | html_filters.insert_before 'cppref/clean_html', 'c/entries' | ||
| 8 | |||
| 9 | options[:root_title] = 'C Programming Language' | ||
| 10 | |||
| 11 | end | ||
| 12 | end | ||
| @@ -0,0 +1,19 @@ | |||
| 1 | module Docs | ||
| 2 | class Cpp < Cppref | ||
| 3 | self.name = 'C++' | ||
| 4 | self.slug = 'cpp' | ||
| 5 | self.base_url = 'https://en.cppreference.com/w/cpp/' | ||
| 6 | |||
| 7 | html_filters.insert_before 'cppref/clean_html', 'cpp/entries' | ||
| 8 | |||
| 9 | options[:root_title] = 'C++ Programming Language' | ||
| 10 | |||
| 11 | options[:skip] = %w( | ||
| 12 | language/extending_std.html | ||
| 13 | language/history.html | ||
| 14 | regex/ecmascript.html | ||
| 15 | regex/regex_token_iterator/operator_cmp.html | ||
| 16 | ) | ||
| 17 | |||
| 18 | end | ||
| 19 | end | ||
| @@ -0,0 +1,33 @@ | |||
| 1 | module Docs | ||
| 2 | class Cppref < UrlScraper | ||
| 3 | self.abstract = true | ||
| 4 | self.type = 'cppref' | ||
| 5 | self.root_path = 'header' | ||
| 6 | |||
| 7 | html_filters.insert_before 'clean_html', 'cppref/fix_code' | ||
| 8 | html_filters.push 'cppref/clean_html', 'title' | ||
| 9 | |||
| 10 | options[:decode_and_clean_paths] = true | ||
| 11 | options[:container] = '#content' | ||
| 12 | options[:title] = false | ||
| 13 | options[:skip] = %w(language/history.html) | ||
| 14 | |||
| 15 | options[:skip_patterns] = [ | ||
| 16 | /experimental/ | ||
| 17 | ] | ||
| 18 | |||
| 19 | options[:attribution] = <<-HTML | ||
| 20 | © cppreference.com<br> | ||
| 21 | Licensed under the Creative Commons Attribution-ShareAlike Unported License v3.0. | ||
| 22 | HTML | ||
| 23 | |||
| 24 | # Check if the 'headers' page has changed | ||
| 25 | def get_latest_version(opts) | ||
| 26 | doc = fetch_doc(self.base_url + self.root_path, opts) | ||
| 27 | date = doc.at_css('#footer-info-lastmod').content | ||
| 28 | date = date.match(/[[:digit:]]{1,2} .* [[:digit:]]{4}/).to_s | ||
| 29 | date = DateTime.strptime(date, '%e %B %Y').to_time.to_i | ||
| 30 | end | ||
| 31 | |||
| 32 | end | ||
| 33 | end | ||