Module: Onebox::Helpers
- Defined in:
- lib/onebox/helpers.rb
Defined Under Namespace
Classes: DownloadTooLarge
Class Method Summary collapse
- .audio_placeholder_html ⇒ Object
- .blank?(value) ⇒ Boolean
- .clean(html) ⇒ Object
- .click_to_scroll_div(width = 690, height = 400) ⇒ Object
- .fetch_content_length(location) ⇒ Object
- .fetch_html_doc(url, headers = nil) ⇒ Object
- .fetch_response(location, limit = nil, domain = nil, headers = nil) ⇒ Object
- .generic_placeholder_html ⇒ Object
- .get(meta, attr) ⇒ Object
- .get_absolute_image_url(src, url) ⇒ Object
- .map_placeholder_html ⇒ Object
- .normalize_url_for_output(url) ⇒ Object
- .pretty_filesize(size) ⇒ Object
- .sanitize(value, length = 50) ⇒ Object
- .symbolize_keys(hash) ⇒ Object
- .truncate(string, length = 50) ⇒ Object
-
.uri_encode(url) ⇒ Object
Percent-encodes a URI string per RFC3986 - tools.ietf.org/html/rfc3986.
- .uri_unencode(url) ⇒ Object
- .video_placeholder_html ⇒ Object
Class Method Details
.audio_placeholder_html ⇒ Object
224 225 226 |
# File 'lib/onebox/helpers.rb', line 224 def self.audio_placeholder_html "<div class='onebox-placeholder-container'><span class='placeholder-icon audio'></span></div>" end |
.blank?(value) ⇒ Boolean
149 150 151 152 153 154 155 156 157 |
# File 'lib/onebox/helpers.rb', line 149 def self.blank?(value) if value.nil? true elsif String === value value.empty? || !(/[[:^space:]]/ === value) else value.respond_to?(:empty?) ? !!value.empty? : !value end end |
.clean(html) ⇒ Object
23 24 25 |
# File 'lib/onebox/helpers.rb', line 23 def self.clean(html) html.gsub(/<[^>]+>/, ' ').gsub(/\n/, '') end |
.click_to_scroll_div(width = 690, height = 400) ⇒ Object
145 146 147 |
# File 'lib/onebox/helpers.rb', line 145 def self.click_to_scroll_div(width = 690, height = 400) "<div style=\"background:transparent;position:relative;width:#{width}px;height:#{height}px;top:#{height}px;margin-top:-#{height}px;\" onClick=\"style.pointerEvents='none'\"></div>" end |
.fetch_content_length(location) ⇒ Object
106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 |
# File 'lib/onebox/helpers.rb', line 106 def self.fetch_content_length(location) uri = URI(location) Net::HTTP.start(uri.host, uri.port, use_ssl: uri.is_a?(URI::HTTPS)) do |http| http.open_timeout = Onebox..connect_timeout http.read_timeout = Onebox..timeout if uri.is_a?(URI::HTTPS) http.use_ssl = true http.verify_mode = OpenSSL::SSL::VERIFY_NONE end http.request_head([uri.path, uri.query].join("?")) do |response| code = response.code.to_i unless code === 200 || Onebox::Helpers.blank?(response.header['content-length']) return nil end return response.header['content-length'] end end end |
.fetch_html_doc(url, headers = nil) ⇒ Object
27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 |
# File 'lib/onebox/helpers.rb', line 27 def self.fetch_html_doc(url, headers = nil) response = (fetch_response(url, nil, nil, headers) rescue nil) doc = Nokogiri::HTML(response) uri = Addressable::URI.parse(url) ignore_canonical_tag = doc.at('meta[property="og:ignore_canonical"]') should_ignore_canonical = IGNORE_CANONICAL_DOMAINS.map { |hostname| uri.hostname.match?(hostname) }.any? unless (ignore_canonical_tag && ignore_canonical_tag['content'].to_s == 'true') || should_ignore_canonical # prefer canonical link canonical_link = doc.at('//link[@rel="canonical"]/@href') canonical_uri = Addressable::URI.parse(canonical_link) if canonical_link && "#{canonical_uri.host}#{canonical_uri.path}" != "#{uri.host}#{uri.path}" response = (fetch_response(canonical_uri.to_s, nil, nil, headers) rescue nil) doc = Nokogiri::HTML(response) if response end end doc end |
.fetch_response(location, limit = nil, domain = nil, headers = nil) ⇒ Object
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 |
# File 'lib/onebox/helpers.rb', line 48 def self.fetch_response(location, limit = nil, domain = nil, headers = nil) limit ||= 5 limit = Onebox..redirect_limit if limit > Onebox..redirect_limit raise Net::HTTPError.new('HTTP redirect too deep', location) if limit == 0 uri = Addressable::URI.parse(location) uri = Addressable::URI.join(domain, uri) if !uri.host result = StringIO.new Net::HTTP.start(uri.host, uri.port, use_ssl: uri.normalized_scheme == 'https') do |http| http.open_timeout = Onebox..connect_timeout http.read_timeout = Onebox..timeout http.verify_mode = OpenSSL::SSL::VERIFY_NONE # Work around path building bugs headers ||= {} if Onebox..user_agent && !headers['User-Agent'] headers['User-Agent'] = Onebox..user_agent end request = Net::HTTP::Get.new(uri.request_uri, headers) start_time = Time.now size_bytes = Onebox..max_download_kb * 1024 http.request(request) do |response| if = response.get_fields('set-cookie') # HACK: If this breaks again in the future, use HTTP::CookieJar from gem 'http-cookie' # See test: it "does not send cookies to the wrong domain" redir_header = { 'Cookie' => .join('; ') } end redir_header = nil unless redir_header.is_a? Hash code = response.code.to_i unless code === 200 response.error! unless [301, 302].include?(code) return fetch_response( response['location'], limit - 1, "#{uri.scheme}://#{uri.host}", redir_header ) end response.read_body do |chunk| result.write(chunk) raise DownloadTooLarge.new if result.size > size_bytes raise Timeout::Error.new if (Time.now - start_time) > Onebox..timeout end return result.string end end end |
.generic_placeholder_html ⇒ Object
232 233 234 |
# File 'lib/onebox/helpers.rb', line 232 def self.generic_placeholder_html "<div class='onebox-placeholder-container'><span class='placeholder-icon generic'></span></div>" end |
.get(meta, attr) ⇒ Object
164 165 166 |
# File 'lib/onebox/helpers.rb', line 164 def self.get(, attr) ( && !blank?([attr])) ? sanitize([attr]) : nil end |
.get_absolute_image_url(src, url) ⇒ Object
184 185 186 187 188 189 190 191 192 193 194 195 196 197 |
# File 'lib/onebox/helpers.rb', line 184 def self.get_absolute_image_url(src, url) if src && !!(src =~ /^\/\//) uri = URI(url) src = "#{uri.scheme}:#{src}" elsif src && src.match(/^https?:\/\//i).nil? uri = URI(url) src = if !src.start_with?("/") && uri.path.present? "#{uri.scheme}://#{uri.host.sub(/\/$/, '')}#{uri.path.sub(/\/$/, '')}/#{src.sub(/^\//, '')}" else "#{uri.scheme}://#{uri.host.sub(/\/$/, '')}/#{src.sub(/^\//, '')}" end end src end |
.map_placeholder_html ⇒ Object
228 229 230 |
# File 'lib/onebox/helpers.rb', line 228 def self.map_placeholder_html "<div class='onebox-placeholder-container'><span class='placeholder-icon map'></span></div>" end |
.normalize_url_for_output(url) ⇒ Object
173 174 175 176 177 178 179 180 181 182 |
# File 'lib/onebox/helpers.rb', line 173 def self.normalize_url_for_output(url) return "" unless url url = url.dup # expect properly encoded url, remove any unsafe chars url.gsub!(' ', '%20') url.gsub!("'", "'") url.gsub!('"', """) url.gsub!(/[^\w\-`.~:\/?#\[\]@!$&'\(\)*+,;=%\p{M}’]/, "") url end |
.pretty_filesize(size) ⇒ Object
127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 |
# File 'lib/onebox/helpers.rb', line 127 def self.pretty_filesize(size) conv = [ 'B', 'KB', 'MB', 'GB', 'TB', 'PB', 'EB' ] scale = 1024 ndx = 1 if (size < 2 * (scale**ndx)) then return "#{(size)} #{conv[ndx - 1]}" end size = size.to_f [2, 3, 4, 5, 6, 7].each do |i| if (size < 2 * (scale**i)) then return "#{'%.2f' % (size / (scale**(i - 1)))} #{conv[i - 1]}" end end ndx = 7 "#{'%.2f' % (size / (scale**(ndx - 1)))} #{conv[ndx - 1]}" end |
.sanitize(value, length = 50) ⇒ Object
168 169 170 171 |
# File 'lib/onebox/helpers.rb', line 168 def self.sanitize(value, length = 50) return nil if blank?(value) Sanitize.fragment(value).strip end |
.symbolize_keys(hash) ⇒ Object
12 13 14 15 16 17 18 19 20 21 |
# File 'lib/onebox/helpers.rb', line 12 def self.symbolize_keys(hash) return {} if hash.nil? hash.inject({}) do |result, (key, value)| new_key = key.is_a?(String) ? key.to_sym : key new_value = value.is_a?(Hash) ? symbolize_keys(value) : value result[new_key] = new_value result end end |
.truncate(string, length = 50) ⇒ Object
159 160 161 162 |
# File 'lib/onebox/helpers.rb', line 159 def self.truncate(string, length = 50) return string if string.nil? string.size > length ? string[0...(string.rindex(" ", length) || length)] + "..." : string end |
.uri_encode(url) ⇒ Object
Percent-encodes a URI string per RFC3986 - tools.ietf.org/html/rfc3986
200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 |
# File 'lib/onebox/helpers.rb', line 200 def self.uri_encode(url) return "" unless url uri = Addressable::URI.parse(url) encoded_uri = Addressable::URI.new( scheme: Addressable::URI.encode_component(uri.scheme, Addressable::URI::CharacterClasses::SCHEME), authority: Addressable::URI.encode_component(uri., Addressable::URI::CharacterClasses::AUTHORITY), path: Addressable::URI.encode_component(uri.path, Addressable::URI::CharacterClasses::PATH + "\\%"), query: Addressable::URI.encode_component(uri.query, "a-zA-Z0-9\\-\\.\\_\\~\\$\\&\\*\\,\\=\\:\\@\\?\\%"), fragment: Addressable::URI.encode_component(uri.fragment, "a-zA-Z0-9\\-\\.\\_\\~\\!\\$\\&\\'\\(\\)\\*\\+\\,\\;\\=\\:\\/\\?\\%") ) encoded_uri.to_s end |
.uri_unencode(url) ⇒ Object
216 217 218 |
# File 'lib/onebox/helpers.rb', line 216 def self.uri_unencode(url) Addressable::URI.unencode(url) end |
.video_placeholder_html ⇒ Object
220 221 222 |
# File 'lib/onebox/helpers.rb', line 220 def self.video_placeholder_html "<div class='onebox-placeholder-container'><span class='placeholder-icon video'></span></div>" end |