readability-rb 0.5.0 → 0.6.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: d1b1f82a83ce6cdeb11e08496ffdac052e828ae70938e9febf1f054cf0fffff1
-  data.tar.gz: 26b68d2cf32967ea3e0aaa486eb591639001831b461f2ad0b86015d26b9c41f7
+  metadata.gz: c451d1e4e2e12c168b323f813a36594c25177e7a8fa4c1999cd55fd652128413
+  data.tar.gz: be5c5fe5aef9cc1186c25112f6e3ca11220aec7b4cb122682092fe3db14c4008
 SHA512:
-  metadata.gz: ccabf0a76b0f48e7047e97303e13314801159fa368329729ab34079f7f679ab92e86fe3a055a0251c3b4c13dd9028d447c3f560d4762e58b770f7853966f96f3
-  data.tar.gz: 7ac4044347dc3f4efc7e24ce182a0b3cfd53504ebf9429a8ca6950f4a140663a3a5f84e19578692d0fc8ba1299bf730d9b1c127b14cc2d0b6bb266d1d5d39cf2
+  metadata.gz: 210bd7531212e4c9ad91ec6da99e3bd0a74eb1dd62040b646bc7e90a07daadc13e19c9681d2bd6c7e2412c2ef3f30752671b52472f22b26fbc263eaf2f473e64
+  data.tar.gz: 692bcc0189b89d1b440d7a5bf0cf4bd53a313ef30cebab92ca93d2c6f6d88a81fb531d1cabe85c07487748467e17a1e591b6f32237b5f01ed89eb14f7f5ea329

data/lib/readability/document.rb

@@ -170,7 +170,7 @@ module Readability
                 nxt = get_next_node(nxt)
               end
             end
-            @article_byline = (item_prop_name_node || node).text.strip
+            @article_byline = js_trim((item_prop_name_node || node).text)
             node = remove_and_get_next(node)
             next
           end

data/lib/readability/metadata.rb

@@ -41,7 +41,7 @@ module Readability
 
           if parsed.is_a?(Array)
             parsed = parsed.find do |it|
-              Array(it["@type"]).any? { |t| t.match?(JSON_LD_ARTICLE_TYPES) }
+              Array(it["@type"]).any? { |t| t.is_a?(String) && t.match?(JSON_LD_ARTICLE_TYPES) }
             end
             next unless parsed
           end
@@ -64,6 +64,8 @@ module Readability
             end
           end
 
+          # Unlike JS, accept an array @type, which schema.org allows. JS calls
+          # @type.match, which throws for an array, so it skips the script.
           next if !parsed || !parsed["@type"] || !Array(parsed["@type"]).any? { |t| t.is_a?(String) && t.match?(JSON_LD_ARTICLE_TYPES) }
 
           metadata = {}
@@ -88,13 +90,13 @@ module Readability
 
           if parsed["author"]
             if parsed["author"].is_a?(Hash) && parsed["author"]["name"].is_a?(String)
-              metadata["byline"] = parsed["author"]["name"].strip
+              metadata["byline"] = js_trim(parsed["author"]["name"])
             elsif parsed["author"].is_a?(Array) &&
-                parsed["author"][0] &&
+                parsed["author"][0].is_a?(Hash) &&
                 parsed["author"][0]["name"].is_a?(String)
               metadata["byline"] = parsed["author"]
-                .select { |author| author && author["name"].is_a?(String) }
-                .map { |author| author["name"].strip }
+                .select { |author| author.is_a?(Hash) && author["name"].is_a?(String) }
+                .map { |author| js_trim(author["name"]) }
                 .join(", ")
             end
           end
@@ -110,8 +112,8 @@ module Readability
           if parsed["datePublished"].is_a?(String)
             metadata["date_published"] = parsed["datePublished"].strip
           end
-        rescue JSON::ParserError => e
-          # Handle malformed JSON gracefully
+        rescue => e
+          # Skip malformed JSON or JSON with an unexpected shape, as JS does
           log(e.message) if respond_to?(:log, true)
         end
       end
@@ -225,7 +227,7 @@ module Readability
           if matches
             # Convert to lowercase, and remove any whitespace
             name = matches[0].downcase.gsub(/\s/, "")
-            values[name] = content.strip
+            values[name] = js_trim(content)
           end
         end
 
@@ -234,7 +236,7 @@ module Readability
           if content
             # Convert to lowercase, remove whitespace, convert dots to colons
             name = name.downcase.gsub(/\s/, "").gsub(".", ":")
-            values[name] = content.strip
+            values[name] = js_trim(content)
           end
         end
       end

data/lib/readability/utils.rb

@@ -33,10 +33,10 @@ module Readability
     end
 
     # JS-compatible trim that also strips Unicode whitespace like \u00A0 (NBSP)
-    # JS's String.prototype.trim() strips all Unicode whitespace including NBSP.
+    # JS's String.prototype.trim() strips all Unicode whitespace and \uFEFF (BOM).
     # Ruby's String#strip only removes ASCII whitespace.
     def js_trim(str)
-      str.gsub(/\A[\s\u00A0]+|[\s\u00A0]+\z/, "")
+      str.gsub(/\A[[:space:]\uFEFF]+|[[:space:]\uFEFF]+\z/, "")
     end
 
     # Port of _getInnerText (JS line 2084)
@@ -211,9 +211,9 @@ module Readability
     end
 
     # Port of _isUrl (JS line 442)
+    # JS's URL constructor accepts any absolute URL, so any scheme counts.
     def is_url?(str)
-      uri = URI.parse(str)
-      uri.is_a?(URI::HTTP) || uri.is_a?(URI::HTTPS)
+      !URI.parse(str).scheme.nil?
     rescue URI::InvalidURIError, URI::InvalidComponentError
       false
     end

data/lib/readability/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Readability
-  VERSION = "0.5.0"
+  VERSION = "0.6.0"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: readability-rb
 version: !ruby/object:Gem::Version
-  version: 0.5.0
+  version: 0.6.0
 platform: ruby
 authors:
 - Andy Croll
@@ -58,14 +58,14 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: '3.2'
+      version: '3.3'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.6.9
+rubygems_version: 4.0.20
 specification_version: 4
 summary: Extract readable article content from HTML pages
 test_files: []