Class: TopicEmbed
- Inherits:
-
ActiveRecord::Base
- Object
- ActiveRecord::Base
- TopicEmbed
- Includes:
- Trashable
- Defined in:
- app/models/topic_embed.rb
Defined Under Namespace
Classes: FetchResponse
Class Method Summary collapse
-
.absolutize_urls(url, contents) ⇒ Object
Convert any relative URLs to absolute.
- .expanded_for(post) ⇒ Object
- .find_remote(url) ⇒ Object
- .first_paragraph_from(html) ⇒ Object
-
.import(user, url, title, contents, category_id: nil, cook_method: nil, tags: nil) ⇒ Object
Import an article from a source (RSS/Atom/Other).
- .import_remote(url, opts = nil) ⇒ Object
- .imported_from_html(url) ⇒ Object
- .normalize_url(url) ⇒ Object
- .parse_html(html, url) ⇒ Object
- .topic_embed_by_url(embed_url) ⇒ Object
- .topic_id_for_embed(embed_url) ⇒ Object
Methods included from Trashable
Class Method Details
.absolutize_urls(url, contents) ⇒ Object
Convert any relative URLs to absolute. RSS is annoying for this.
233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 |
# File 'app/models/topic_embed.rb', line 233 def self.absolutize_urls(url, contents) url = normalize_url(url) begin uri = URI(UrlHelper.normalized_encode(url)) rescue URI::Error return contents end prefix = "#{uri.scheme}://#{uri.host}" prefix += ":#{uri.port}" if uri.port != 80 && uri.port != 443 fragment = Nokogiri::HTML5.fragment("<div>#{contents}</div>") fragment .css("a") .each do |a| if a["href"].present? begin a["href"] = URI.join(prefix, a["href"]).to_s rescue URI::InvalidURIError # NOOP, URL is malformed end end end fragment .css("img") .each do |a| if a["src"].present? begin a["src"] = URI.join(prefix, a["src"]).to_s rescue URI::InvalidURIError # NOOP, URL is malformed end end end fragment.at("div").inner_html end |
.expanded_for(post) ⇒ Object
299 300 301 302 303 304 305 306 307 308 309 310 |
# File 'app/models/topic_embed.rb', line 299 def self.(post) Discourse .cache .fetch("embed-topic:#{post.topic_id}", expires_in: 10.minutes) do url = TopicEmbed.where(topic_id: post.topic_id).pick(:embed_url) response = TopicEmbed.find_remote(url) body = response.body body << TopicEmbed.imported_from_html(url) body end end |
.find_remote(url) ⇒ Object
120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 |
# File 'app/models/topic_embed.rb', line 120 def self.find_remote(url) url = UrlHelper.normalized_encode(url) URI.parse(url) # ensure url parses, will raise if not fd = FinalDestination.new(url, validate_uri: true, max_redirects: 5, follow_canonical: true) uri = fd.resolve return if uri.blank? begin html = uri.read rescue OpenURI::HTTPError, Net::OpenTimeout return end parse_html(html, uri.to_s) end |
.first_paragraph_from(html) ⇒ Object
281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 |
# File 'app/models/topic_embed.rb', line 281 def self.first_paragraph_from(html) doc = Nokogiri.HTML5(html) result = +"" doc .css("p") .each do |p| if p.text.present? result << p.to_s return result if result.size >= 100 end end return result unless result.blank? # If there is no first paragraph, return the first div (onebox) doc.css("div").first.to_s end |
.import(user, url, title, contents, category_id: nil, cook_method: nil, tags: nil) ⇒ Object
Import an article from a source (RSS/Atom/Other)
43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 |
# File 'app/models/topic_embed.rb', line 43 def self.import(user, url, title, contents, category_id: nil, cook_method: nil, tags: nil) return unless url =~ %r{\Ahttps?\://} contents = first_paragraph_from(contents) if SiteSetting. && cook_method.nil? contents ||= "" contents = contents.dup << imported_from_html(url) url = normalize_url(url) = (url) content_sha1 = Digest::SHA1.hexdigest(contents) post = nil # If there is no embed, create a topic, post and the embed. if .blank? Topic.transaction do eh = EmbeddableHost.record_for_url(url) cook_method ||= if SiteSetting. Post.cook_methods[:regular] else Post.cook_methods[:raw_html] end create_args = { title: title, raw: absolutize_urls(url, contents), skip_validations: true, cook_method: cook_method, category: category_id || eh.try(:category_id), tags: SiteSetting.tagging_enabled ? : nil, } create_args[:visible] = false if SiteSetting. creator = PostCreator.new(user, create_args) post = creator.create if post.present? TopicEmbed.create!( topic_id: post.topic_id, embed_url: url, content_sha1: content_sha1, post_id: post.id, ) end end else absolutize_urls(url, contents) post = .post # Update the topic if it changed if post&.topic if post.user != user PostOwnerChanger.new( post_ids: [post.id], topic_id: post.topic_id, new_owner: user, acting_user: Discourse.system_user, ).change_owner! # make sure the post returned has the right author post.reload end if (content_sha1 != .content_sha1) || (title && title != post&.topic&.title) changes = { raw: absolutize_urls(url, contents) } changes[:title] = title if title.present? post.revise(user, changes, skip_validations: true, bypass_rate_limiter: true) .update!(content_sha1: content_sha1) end end end post end |
.import_remote(url, opts = nil) ⇒ Object
219 220 221 222 223 224 225 226 227 228 229 230 |
# File 'app/models/topic_embed.rb', line 219 def self.import_remote(url, opts = nil) opts = opts || {} response = find_remote(url) return if response.nil? response.title = opts[:title] if opts[:title].present? import_user = opts[:user] if opts[:user].present? import_user = response. if response..present? url = normalize_url(response.url) if response.url.present? TopicEmbed.import(import_user, url, response.title, response.body) end |
.imported_from_html(url) ⇒ Object
35 36 37 38 39 40 |
# File 'app/models/topic_embed.rb', line 35 def self.imported_from_html(url) url = UrlHelper.normalized_encode(url) I18n.with_locale(SiteSetting.default_locale) do "\n<hr>\n<small>#{I18n.t("embed.imported_from", link: "<a href='#{url}'>#{url}</a>")}</small>\n" end end |
.normalize_url(url) ⇒ Object
27 28 29 30 31 32 33 |
# File 'app/models/topic_embed.rb', line 27 def self.normalize_url(url) # downcase # remove trailing forward slash/ # remove consecutive hyphens # remove leading and trailing whitespace url.downcase.sub(%r{/\z}, "").sub(/\-+/, "-").strip end |
.parse_html(html, url) ⇒ Object
137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 |
# File 'app/models/topic_embed.rb', line 137 def self.parse_html(html, url) require "ruby-readability" opts = { tags: %w[div p code pre h1 h2 h3 b em i strong a img ul li ol blockquote figure figcaption], attributes: %w[href src class], remove_empty_nodes: false, } opts[ :whitelist ] = SiteSetting. if SiteSetting..present? opts[ :blacklist ] = SiteSetting. if SiteSetting..present? = SiteSetting. if SiteSetting..present? response = FetchResponse.new raw_doc = Nokogiri.HTML5(html) response.url = url auth_element = raw_doc.at('meta[@name="discourse-username"]') || raw_doc.at('meta[@name="author"]') if auth_element.present? response. = User.where(username_lower: auth_element[:content].strip).first end read_doc = Readability::Document.new(html, opts) title = +(raw_doc.title || "") title.strip! if SiteSetting..present? title.sub!(Regexp.new(SiteSetting.), "") title.strip! end response.title = title doc = Nokogiri.HTML5(read_doc.content) = { "img" => "src", "script" => "src", "a" => "href" } doc .search(.keys.join(",")) .each do |node| url_param = [node.name] src = node[url_param] unless (src.nil? || src.empty?) begin # convert URL to absolute form node[url_param] = URI.join(url, UrlHelper.normalized_encode(src)).to_s rescue URI::Error, Addressable::URI::InvalidURIError # If there is a mistyped URL, just do nothing end end # only allow classes in the allowlist allowed_classes = if .blank? [] else .split(/[ ,]+/i) end doc .search('[class]:not([class=""])') .each do |classnode| classes = classnode[:class] .split(" ") .select { |classname| allowed_classes.include?(classname) } if classes.length === 0 classnode.delete("class") else classnode[:class] = classes.join(" ") end end end response.body = doc.at("body").children.to_html response end |
.topic_embed_by_url(embed_url) ⇒ Object
271 272 273 274 |
# File 'app/models/topic_embed.rb', line 271 def self.() = normalize_url().sub(%r{\Ahttps?\://}, "") TopicEmbed.where("embed_url ~* ?", "^https?://#{Regexp.escape()}$").first end |
.topic_id_for_embed(embed_url) ⇒ Object
276 277 278 279 |
# File 'app/models/topic_embed.rb', line 276 def self.() = () &.topic_id end |