html2rss 0.30.0 → 0.32.0

data/schema/html2rss-config.schema.json

@@ -281,6 +281,18 @@
               },
               "required": []
             },
+            "json_document": {
+              "type": "object",
+              "properties": {
+                "enabled": {
+                  "type": "boolean",
+                  "not": {
+                    "type": "null"
+                  }
+                }
+              },
+              "required": []
+            },
             "xhr_articles": {
               "type": "object",
               "properties": {
@@ -402,6 +414,9 @@
           "json_state": {
             "enabled": true
           },
+          "json_document": {
+            "enabled": true
+          },
           "xhr_articles": {
             "enabled": true
           },
@@ -434,7 +449,8 @@
           "properties": {
             "selector": {
               "type": "string",
-              "minLength": 1
+              "minLength": 1,
+              "default": "a[href]"
             },
             "order": {
               "enum": [
@@ -507,9 +523,7 @@
               ]
             }
           },
-          "required": [
-            "selector"
-          ],
+          "required": [],
           "description": "Defines the items selector and list-card enhance settings."
         },
         "enclosure": {
@@ -848,7 +862,7 @@
       "gsub": {
         "type": "object",
         "title": "gsub",
-        "description": "Replace matches of `pattern` in the extracted string with `replacement` (Ruby String#gsub; pattern may be a regexp-like string).",
+        "description": "Replace matches of `pattern` in the extracted string with `replacement` (Ruby String#gsub; pattern may be a regexp-like string). Patterns over 256 characters as written, or with nested quantifiers, are rejected.",
         "examples": [
           {
             "name": "gsub",
@@ -862,10 +876,14 @@
             "const": "gsub"
           },
           "pattern": {
-            "type": "string"
+            "type": "string",
+            "maxLength": 256
           },
           "replacement": {
-            "type": "string"
+            "type": [
+              "string",
+              "object"
+            ]
           }
         },
         "required": [
@@ -1024,7 +1042,7 @@
         "type": "string",
         "const": "href",
         "title": "href",
-        "description": "Return the absolute URL from the selected element's `href` attribute (relative hrefs are resolved against the channel URL).",
+        "description": "Return the absolute URL from the selected element's `href` attribute (relative hrefs are resolved against the page base URL).",
         "examples": [
           "href"
         ]

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: html2rss
 version: !ruby/object:Gem::Version
-  version: 0.30.0
+  version: 0.32.0
 platform: ruby
 authors:
 - Gil Desmarais
@@ -275,6 +275,7 @@ files:
 - lib/html2rss/auto_source/cleanup.rb
 - lib/html2rss/auto_source/scraper.rb
 - lib/html2rss/auto_source/scraper/html.rb
+- lib/html2rss/auto_source/scraper/json_document.rb
 - lib/html2rss/auto_source/scraper/json_state.rb
 - lib/html2rss/auto_source/scraper/json_state/article_normalizer.rb
 - lib/html2rss/auto_source/scraper/json_state/candidate_detector.rb
@@ -314,13 +315,17 @@ files:
 - lib/html2rss/config.rb
 - lib/html2rss/config/auto_source_contract.rb
 - lib/html2rss/config/dynamic_params.rb
+- lib/html2rss/config/issue_mapper.rb
 - lib/html2rss/config/multiple_feeds_config.rb
 - lib/html2rss/config/request_controls.rb
 - lib/html2rss/config/request_headers.rb
 - lib/html2rss/config/schema.rb
 - lib/html2rss/config/selectors_validator.rb
+- lib/html2rss/config/validation_issue.rb
+- lib/html2rss/config/validation_report.rb
 - lib/html2rss/config/validator.rb
 - lib/html2rss/defaults.rb
+- lib/html2rss/doctor.rb
 - lib/html2rss/doctor/botasaurus.rb
 - lib/html2rss/error.rb
 - lib/html2rss/feed_builder.rb
@@ -421,15 +426,18 @@ files:
 - lib/html2rss/scoring/ranked_segment.rb
 - lib/html2rss/scoring/score.rb
 - lib/html2rss/scrape_target.rb
+- lib/html2rss/selector_candidates.rb
 - lib/html2rss/selectors.rb
+- lib/html2rss/selectors/README.md
 - lib/html2rss/selectors/extractors.rb
 - lib/html2rss/selectors/extractors/attribute.rb
 - lib/html2rss/selectors/extractors/href.rb
 - lib/html2rss/selectors/extractors/html.rb
 - lib/html2rss/selectors/extractors/static.rb
 - lib/html2rss/selectors/extractors/text.rb
-- lib/html2rss/selectors/item_scope.rb
-- lib/html2rss/selectors/object_to_xml_converter.rb
+- lib/html2rss/selectors/item_env.rb
+- lib/html2rss/selectors/json_xml.rb
+- lib/html2rss/selectors/option_spec.rb
 - lib/html2rss/selectors/post_processors.rb
 - lib/html2rss/selectors/post_processors/base.rb
 - lib/html2rss/selectors/post_processors/gsub.rb
@@ -441,7 +449,8 @@ files:
 - lib/html2rss/selectors/post_processors/sanitize_html.rb
 - lib/html2rss/selectors/post_processors/substring.rb
 - lib/html2rss/selectors/post_processors/template.rb
-- lib/html2rss/selectors/schema_doc.rb
+- lib/html2rss/selectors/schema_export.rb
+- lib/html2rss/selectors/step_env.rb
 - lib/html2rss/sst.rb
 - lib/html2rss/sst/attrs.rb
 - lib/html2rss/sst/document.rb
@@ -459,6 +468,7 @@ files:
 - lib/html2rss/syndication/parser.rb
 - lib/html2rss/test.rb
 - lib/html2rss/test/enhance_audit.rb
+- lib/html2rss/test/policy.rb
 - lib/html2rss/url.rb
 - lib/html2rss/version.rb
 - lib/tasks/config_schema.rake
@@ -468,7 +478,7 @@ licenses:
 - MIT
 metadata:
   allowed_push_host: https://rubygems.org
-  changelog_uri: https://github.com/html2rss/html2rss/releases/tag/v0.30.0
+  changelog_uri: https://github.com/html2rss/html2rss/releases/tag/v0.32.0
   rubygems_mfa_required: 'true'
 rdoc_options: []
 require_paths:
@@ -484,7 +494,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 4.0.16
+rubygems_version: 4.0.20
 specification_version: 4
 summary: Generates RSS feeds from websites by scraping a URL and using CSS selectors
   to extract item.

data/lib/html2rss/selectors/item_scope.rb

@@ -1,30 +0,0 @@
-# frozen_string_literal: true
-
-module Html2rss
-  class Selectors
-    ##
-    # Per-item extraction scope: owns the article node and page +base_url+ for one
-    # extraction pass. Channel hashes are injected (and cached) by {Selectors}.
-    #
-    # Distinct from {Context}, which is the post-processor invocation bag (+options+).
-    # Post-processor +config+ is derived from {#channel} — not a parallel bag.
-    ItemScope = Data.define(:item, :base_url, :scraper, :channel) do
-      ##
-      # Selects an attribute using this scope's item and base_url.
-      #
-      # @param name [Symbol, String]
-      # @return [Object, Array<Object>]
-      def select(name) = scraper.select_in_scope(name, self)
-
-      ##
-      # Builds a post-processor {Context} carrying this scope for nested selects.
-      #
-      # @param options [Hash] post-processor options from the selector config
-      # @option options [String] :name post-processor name
-      # @return [Context]
-      def context_for(options:)
-        Context.new(options:, item:, config: { channel: }, scraper:, item_scope: self)
-      end
-    end
-  end
-end