algolia_html_extractor 2.2.1 → 2.2.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 49c3023566226660bc3508fd06b177d27d7ad331
-  data.tar.gz: 9c1c0df0b0217dae12946d69bea0b885a3477e38
+  metadata.gz: 3efc015000ed0122ea70417eb8a48a0f6c0ccde6
+  data.tar.gz: 6923bced71dfc762f8cf734efa96229ed55c46a4
 SHA512:
-  metadata.gz: ccc601b3a3499fb7dcc25c366409ff007ad3660518d77de085aa2cc44fba89ef8d2fefd727c869e955a9a9762add797fb1b3aaf51f780cc4fb24d1a677c9ec87
-  data.tar.gz: 06e3b58f8074d40361294d4115ed35cf592667d2ffbf8d170cdce8384ea4a673827f566361002b42e0c8ab88453242758ba39dd44e740511f493a25770547bf8
+  metadata.gz: d352d4b97686377e1869a48b6aa2f97900ae0e958eed630ef4cf103ffce63fac468e44a84e21bfcfb5beb89355a7d14a4974030ba75399778101a75e01d5955d
+  data.tar.gz: 3d7316d8e791a8d9fff538726e2b92de9e6a811190fd68fda3840e79e53f8db5bb4ed6b9752c772ee0a32431fb207cb27b57bfd6f6b1b603772f7cb62b6fdf52

data/lib/algolia_html_extractor.rb

@@ -4,16 +4,24 @@ require 'digest/md5'
 # Extract content from an HTML page in the form of items with associated
 # hierarchy data
 module AlgoliaHTMLExtractor
-  def self.run(input, options: {})
+  # Extractor options, applying default options when none set
+  def self.default_options(options)
     default_options = {
-      css_selector: 'p'
+      css_selector: 'p',
+      heading_selector: 'h1,h2,h3,h4,h5,h6'
     }
-    options = default_options.merge(options)
+    default_options.merge(options)
+  end
 
-    heading_selector = 'h1,h2,h3,h4,h5,h6'
-    # We select all nodes that match either the headings or the elements to
-    # extract. This will allow us to loop over it in order it appears in the DOM
-    all_selector = "#{heading_selector},#{options[:css_selector]}"
+  # Getting a list of HTML nodes from an input and a CSS selector
+  def self.css(input, selector)
+    Nokogiri::HTML(input).css(selector)
+  end
+
+  def self.run(input, options: {})
+    options = default_options(options)
+    heading_selector = options[:heading_selector]
+    css_selector = options[:css_selector]
 
     items = []
     current_hierarchy = {
@@ -28,8 +36,9 @@ module AlgoliaHTMLExtractor
     current_lvl = nil # Current closest hierarchy level
     current_anchor = nil # Current closest anchor
 
-    dom = Nokogiri::HTML(input)
-    dom.css(all_selector).each do |node|
+    # We select all nodes that match either the headings or the elements to
+    # extract. This will allow us to loop over it in order it appears in the DOM
+    css(input, "#{heading_selector},#{css_selector}").each do |node|
       # If it's a heading, we update our current hierarchy
       if node.matches?(heading_selector)
         # Which level heading is it?
@@ -45,7 +54,7 @@ module AlgoliaHTMLExtractor
       end
 
       # Stop if node is not to be extracted
-      next unless node.matches?(options[:css_selector])
+      next unless node.matches?(css_selector)
 
       # Stop if node is empty
       content = extract_text(node)

data/lib/version.rb

@@ -1,5 +1,6 @@
 # Expose gem version
 # rubocop:disable Style/SingleLineMethods
 class AlgoliaHTMLExtractorVersion
-  def self.to_s; '2.2.1' end
+  def self.to_s; '2.2.2' 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: 2.2.1
+  version: 2.2.2
 platform: ruby
 authors:
 - Tim Carry
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2017-12-19 00:00:00.000000000 Z
+date: 2018-02-15 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: awesome_print
@@ -44,14 +44,14 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.8'
+        version: 1.8.2
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.8'
+        version: 1.8.2
 - !ruby/object:Gem::Dependency
   name: coveralls
   requirement: !ruby/object:Gem::Requirement
@@ -136,20 +136,6 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '4.6'
-- !ruby/object:Gem::Dependency
-  name: jeweler
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '2.0'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '2.0'
 - !ruby/object:Gem::Dependency
   name: rspec
   requirement: !ruby/object:Gem::Requirement