algolia_html_extractor 2.5.2 → 2.6.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: 0fa007eca9fdbcf5c0774e04f78f05cdd370622f
-  data.tar.gz: 2d926696b683b4481bbc531f7dadcf129511e2d3
+SHA256:
+  metadata.gz: 1496286d1762c4231f9f38e42549b0128c53d1ff5cf86ffc5b0da04c3c9934bb
+  data.tar.gz: 6af72f32fa6e8e86064677688a2268a02a1ad2a8bdd9fc44146f2e72f527eb3f
 SHA512:
-  metadata.gz: 40372848ec0a92e1b826ac651b69a075840b32921c46a060c675592c0038342c4e8548c0d42ab0e6353f0d0fae1f7cf2b844bae0aa414a3f5f4f1f5cba51840a
-  data.tar.gz: f847e9ac884dba1331c64b8f3e611de3a9a5d221606fc885c05822deeb37b719c493d5c8e3e2f8d4a8dc032d98bf860856b03bbe34f084216a9b960b3579a2ee
+  metadata.gz: 70bdd12e5e15d62cf9c5a5c992180b2491c090cdcca4e671ff8039c7ae91c91817fd38dcf6a4b54e09f59082dfa2157cd4ca44513cf83c64aad8e1f8c771a258
+  data.tar.gz: b5111d1f7fbc948a1186daf0c2c3760cb2a6ea0a7b1b64ae677f96f4ff849a8e99a30f31efb75807e1d509f131c236f6c750a4f94384180df8b70c0736b3c2c1

data/lib/algolia_html_extractor.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require 'nokogiri'
 require 'digest/md5'
 
@@ -8,7 +10,8 @@ module AlgoliaHTMLExtractor
   def self.default_options(options)
     default_options = {
       css_selector: 'p',
-      heading_selector: 'h1,h2,h3,h4,h5,h6'
+      heading_selector: 'h1,h2,h3,h4,h5,h6',
+      tags_to_exclude: ''
     }
     default_options.merge(options)
   end
@@ -22,6 +25,7 @@ module AlgoliaHTMLExtractor
     options = default_options(options)
     heading_selector = options[:heading_selector]
     css_selector = options[:css_selector]
+    tags_to_exclude = options[:tags_to_exclude]
 
     items = []
     current_hierarchy = {
@@ -56,6 +60,9 @@ module AlgoliaHTMLExtractor
       # Stop if node is not to be extracted
       next unless node.matches?(css_selector)
 
+      # Removing excluded child from the node
+      node.search(tags_to_exclude).each(&:remove) unless tags_to_exclude.empty?
+
       # Stop if node is empty
       content = extract_text(node)
       next if content.empty?
@@ -148,6 +155,7 @@ module AlgoliaHTMLExtractor
   def self.heading_weight(heading_level)
     weight = 100
     return weight if heading_level.nil?
+
     weight - ((heading_level + 1) * 10)
   end
 end

data/lib/version.rb

@@ -1,6 +1,8 @@
+# frozen_string_literal: true
+
 # Expose gem version
 # rubocop:disable Style/SingleLineMethods
 class AlgoliaHTMLExtractorVersion
-  def self.to_s; '2.5.2' end
+  def self.to_s; '2.6.4' end
 end
 # rubocop:enable Style/SingleLineMethods

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: algolia_html_extractor
 version: !ruby/object:Gem::Version
-  version: 2.5.2
+  version: 2.6.4
 platform: ruby
 authors:
 - Tim Carry
-autorequire: 
+autorequire:
 bindir: bin
 cert_chain: []
-date: 2018-03-20 00:00:00.000000000 Z
+date: 2021-01-06 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: json
@@ -30,14 +30,14 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 1.8.2
+        version: '1.10'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 1.8.2
+        version: '1.10'
 - !ruby/object:Gem::Dependency
   name: coveralls
   requirement: !ruby/object:Gem::Requirement
@@ -180,7 +180,7 @@ homepage: https://github.com/algolia/html-extractor
 licenses:
 - MIT
 metadata: {}
-post_install_message: 
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -195,9 +195,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.6.13
-signing_key: 
+rubygems_version: 3.1.2
+signing_key:
 specification_version: 4
 summary: Convert HTML content into Algolia records
 test_files: []