jekyll-lunr-js-search 0.1.1

checksums.yaml

@@ -0,0 +1,15 @@
+---
+!binary "U0hBMQ==":
+  metadata.gz: !binary |-
+    MTU1YjcxZmY2NjBlYzY2M2RlM2RiYjQ4ZGYwNjI1ZmZmYzM4ODRjMA==
+  data.tar.gz: !binary |-
+    M2Y3ZWI1NTQzMWRjZThhMjI2MjI4YjA0MWE0MzgzNDY4ZWU0NjFmZA==
+SHA512:
+  metadata.gz: !binary |-
+    YWQ2NGExZTAyOWIxZmQ4MzU3NTNhZTc2ZDI2NGFhNzNiMzExZTkzMDg5MDY0
+    MDdhNGFhYmE1ZjlmMDdjMWI0ZDk2ZGI1NjAxMmQ2MzAzNTYzMTFlNjRjZTBk
+    MDEyOGVmMTRlMDliZGRmMjBmNWYwMDJjZGI4ZWE1NDAzNmE1YWY=
+  data.tar.gz: !binary |-
+    ZjcxNjEwY2MzODhiN2I4ODdjNmQyODg3ZDdlMDllNTRmNTU0ODAzMjJhMTc3
+    YjkwNjYyY2Q4NmRjOWFlNzliNjhkYjk3NzM0MTdhNjA4NzUxNTA1ZTU4Yzk2
+    ZDQ2OWM2NTgzODRhMzk1MjgxNWNmMTM0MWIwMWFkY2IxMGFhMDc=

data/lib/jekyll-lunr-js-search.rb

@@ -0,0 +1,5 @@
+require 'jekyll_lunr_js_search/version'
+require 'jekyll_lunr_js_search/indexer'
+require 'jekyll_lunr_js_search/page_renderer'
+require 'jekyll_lunr_js_search/search_entry'
+require 'jekyll_lunr_js_search/search_index_file'

data/lib/jekyll_lunr_js_search/indexer.rb

@@ -0,0 +1,91 @@
+require 'json'
+
+module Jekyll
+  module LunrJsSearch
+    class Indexer < Jekyll::Generator
+      def initialize(config = {})
+        super(config)
+        
+        lunr_config = { 
+          'excludes' => [],
+          'strip_index_html' => false,
+          'min_length' => 3,
+          'stopwords' => 'stopwords.txt'
+        }.merge!(config['lunr_search'] || {})
+        
+        @excludes = lunr_config['excludes']
+        
+        # if web host supports index.html as default doc, then optionally exclude it from the url 
+        @strip_index_html = lunr_config['strip_index_html']
+
+        # stop word exclusion configuration
+        @min_length = lunr_config['min_length']
+        @stopwords_file = lunr_config['stopwords']
+      end
+
+      # Index all pages except pages matching any value in config['lunr_excludes'] or with date['exclude_from_search']
+      # The main content from each page is extracted and saved to disk as json
+      def generate(site)
+        puts 'Running the search indexer...'
+
+        # gather pages and posts
+        items = pages_to_index(site)
+        content_renderer = PageRenderer.new(site)
+        index = []
+
+        items.each do |item|
+          entry = SearchEntry.create(item, content_renderer)
+
+          entry.strip_index_suffix_from_url! if @strip_index_html
+          entry.strip_stopwords!(stopwords, @min_length) if File.exists?(@stopwords_file) 
+          
+          index << {
+            :title => entry.title, 
+            :url => entry.url,
+            :date => entry.date,
+            :categories => entry.categories,
+            :body => entry.body
+          }
+          
+          puts 'Indexed ' << "#{entry.title} (#{entry.url})"
+        end
+        
+        json = JSON.generate({:entries => index})
+        
+        # Create destination directory if it doesn't exist yet. Otherwise, we cannot write our file there.
+        Dir::mkdir(site.dest) unless File.directory?(site.dest)
+        
+        # File I/O: create search.json file and write out pretty-printed JSON
+        filename = 'search.json'
+        
+        File.open(File.join(site.dest, filename), "w") do |file|
+          file.write(json)
+        end
+
+        # Keep the search.json file from being cleaned by Jekyll
+        site.static_files << SearchIndexFile.new(site, site.dest, "/", filename)
+      end
+
+    private
+      
+      # load the stopwords file
+      def stopwords
+        @stopwords ||= IO.readlines(@stopwords_file).map { |l| l.strip }
+      end
+      
+      def pages_to_index(site)
+        items = []
+        
+        # deep copy pages
+        site.pages.each {|page| items << page.dup }
+        site.posts.each {|post| items << post.dup }
+
+        # only process files that will be converted to .html and only non excluded files 
+        items.select! {|i| i.output_ext == '.html' && ! @excludes.any? {|s| (i.url =~ Regexp.new(s)) != nil } } 
+        items.reject! {|i| i.data['exclude_from_search'] } 
+        
+        items
+      end
+    end
+  end
+end

data/lib/jekyll_lunr_js_search/page_renderer.rb

@@ -0,0 +1,19 @@
+require 'nokogiri'
+
+module Jekyll
+  module LunrJsSearch
+    class PageRenderer
+      def initialize(site)
+        @site = site
+      end
+      
+      # render the item, parse the output and get all text inside <p> elements
+      def render(item)
+        item.render({}, @site.site_payload)
+        doc = Nokogiri::HTML(item.output)
+        paragraphs = doc.search('//text()').map {|t| t.content }
+        paragraphs = paragraphs.join(" ").gsub("\r", " ").gsub("\n", " ").gsub("\t", " ").gsub(/\s+/, " ")
+      end
+    end
+  end  
+end

data/lib/jekyll_lunr_js_search/search_entry.rb

@@ -0,0 +1,54 @@
+require 'nokogiri'
+
+module Jekyll
+  module LunrJsSearch
+    class SearchEntry
+      def self.create(page_or_post, renderer)
+        return create_from_post(page_or_post, renderer) if page_or_post.is_a?(Jekyll::Post)
+        return create_from_page(page_or_post, renderer) if page_or_post.is_a?(Jekyll::Page)
+        raise 'Not supported'
+      end
+      
+      def self.create_from_page(page, renderer)
+        title, url = extract_title_and_url(page)
+        body = renderer.render(page)
+        date = nil
+        categories = []
+        
+        SearchEntry.new(title, url, date, categories, body)
+      end
+      
+      def self.create_from_post(post, renderer)
+        title, url = extract_title_and_url(post)
+        body = renderer.render(post)
+        date = post.date
+        categories = post.categories
+        
+        SearchEntry.new(title, url, date, categories, body)
+      end
+
+      def self.extract_title_and_url(item)
+        data = item.to_liquid
+        [ data['title'], data['url'] ]
+      end
+
+      attr_reader :title, :url, :date, :categories, :body
+      
+      def initialize(title, url, date, categories, body)
+        @title, @url, @date, @categories, @body = title, url, date, categories, body
+      end
+      
+      def strip_index_suffix_from_url!
+        @url.gsub!(/index\.html$/, '')
+      end
+      
+      # remove anything that is in the stop words list from the text to be indexed
+      def strip_stopwords!(stopwords, min_length)
+        @body = @body.split.delete_if() do |x| 
+          t = x.downcase.gsub(/[^a-z]/, '')
+          t.length < min_length || stopwords.include?(t)
+        end.join(' ')
+      end
+    end
+  end
+end

data/lib/jekyll_lunr_js_search/search_index_file.rb

@@ -0,0 +1,10 @@
+module Jekyll
+  module LunrJsSearch  
+	  class SearchIndexFile < Jekyll::StaticFile
+	    # Override write as the search.json index file has already been created 
+	    def write(dest)
+	      true
+	    end
+	  end
+  end
+end

data/lib/jekyll_lunr_js_search/version.rb

@@ -0,0 +1,5 @@
+module Jekyll
+	module LunrJsSearch
+  		VERSION = "0.1.1"
+  	end
+end

metadata

@@ -0,0 +1,106 @@
+--- !ruby/object:Gem::Specification
+name: jekyll-lunr-js-search
+version: !ruby/object:Gem::Version
+  version: 0.1.1
+platform: ruby
+authors:
+- Ben Smith
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2014-08-13 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.6'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.6'
+- !ruby/object:Gem::Dependency
+  name: json
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.8'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.8'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '10.3'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '10.3'
+- !ruby/object:Gem::Dependency
+  name: uglifier
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '2.5'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '2.5'
+description: Use lunr.js to provide simple full-text search, using JavaScript in your
+  browser, for your Jekyll static website.
+email: ben@10consulting.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- lib/jekyll-lunr-js-search.rb
+- lib/jekyll_lunr_js_search/indexer.rb
+- lib/jekyll_lunr_js_search/page_renderer.rb
+- lib/jekyll_lunr_js_search/search_entry.rb
+- lib/jekyll_lunr_js_search/search_index_file.rb
+- lib/jekyll_lunr_js_search/version.rb
+homepage: https://github.com/slashdotdash/jekyll-lunr-js-search
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.4.1
+signing_key: 
+specification_version: 4
+summary: Jekyll + lunr.js = static websites with powerful full-text search using JavaScript
+test_files: []