jekyll-blogsearch 0.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: f0b40ac907c5b5dba89e66dcd21a40dd28fd6a3d4db9060205537828ee07ac5a
+  data.tar.gz: daff275e6b58d22d0f3fea2338beb077e48573c38f1aa2c29e53d4124e694042
+SHA512:
+  metadata.gz: d642d53ef7d51942ad62c5677067cb6c72292ee3e3d0002084407e3456ff398e0adc40b438a0b8a979497a5ea130abd5eb7bb3c5d52917d8d33655f03dae9853
+  data.tar.gz: 0a95a6c803630be4f6a222c68f1c9ea2d8b7a004ae66d8d2bdfb4c5f4528c398aded065667278b9bea478f86d1b8a3a4f7c35438ff7e5bfe1143a9715f107f7d

data/README.adoc

@@ -0,0 +1,88 @@
+# BlogSearch index building tool for Jekyll
+
+// Asciidoc references
+// Documentation: https://asciidoctor.org/docs/user-manual/
+// Quick reference: https://asciidoctor.org/docs/asciidoc-syntax-quick-reference/
+// Asciidoc vs Markdown: https://asciidoctor.org/docs/user-manual/#comparison-by-example
+// GitHub Flavored Asciidoc (GFA): https://gist.github.com/dcode/0cfbf2699a1fe9b46ff04c41721dda74
+
+:project-version: 0.0.3
+:rootdir: https://github.com/kbumsik/blogsearch
+
+ifdef::env-github[]
+// Emoji
+:tip-caption: :bulb:
+:note-caption: :information_source:
+:important-caption: :heavy_exclamation_mark:
+:caution-caption: :fire:
+:warning-caption: :warning:
+// URL
+:imagesdir: https://gist.githubusercontent.com/path/to/gist/revision/dir/with/all/images
+endif::[]
+
+CAUTION: This is a part of link:{rootdir}[BlogSearch project]. If you would like to know the overall concept, go to link:{rootdir}[the parent directory].
+
+## 1. Building a search index file
+
+### Installation
+
+.Gemfile
+[source,ruby]
+----
+group :jekyll_plugins do
+  gem 'jekyll-blogsearch'
+
+  ...
+  Other jekyll plugins
+  ...
+end
+----
+
+### Configuration
+
+CAUTION: Go to link:{rootdir}#whats-in-the-index[the "What's in the index file" section of the main project]. For more details on how to configure fields.
+
+._config.yml
+[source,yml,options="nowrap",subs="verbatim,attributes"]
+----
+titie: your-blog-website
+email: your-email@example.com
+
+url: "https://your-website"
+baseurl: "/blog"
+
+...
+Other jekyll config
+...
+
+blogsearch:
+  output: your_website_index.db.wasm # Generated blogsearch database file.
+  fields: # See: {rootdir}#whats-in-the-index
+    title:
+      enabled: true
+      indexed: true
+      hasContent: true
+    body:
+      enabled: true
+      indexed: true
+      hasContent: true
+    url:
+      base: https://your-website/blog # url field has a special 'base' option to set the baseurl.
+      enabled: true
+      indexed: false
+      hasContent: true
+    categories:
+      enabled: true
+      indexed: true
+      hasContent: true
+    tags:
+      enabled: false
+      indexed: false
+      hasContent: false
+----
+
+## 2. Enabling the search engine in the webpage
+
+You need to enable the search engine in the web page. Go to link:../blogsearch[blogsearch Engine].
+
+Again, if you would like to understand the concept of BlogSearch, go to link:{rootdir}[the parent directory].

data/lib/jekyll/blogsearch/version.rb

@@ -0,0 +1,7 @@
+# frozen_string_literal: true
+
+module Jekyll
+  module BlogSearch
+    VERSION = '0.0.1'
+  end
+end

data/lib/jekyll-blogsearch.rb

@@ -0,0 +1,118 @@
+require 'jekyll/hooks'
+require 'jekyll/plugin'
+require 'jekyll/generator'
+require 'sqlite3'
+require 'jekyll/blogsearch/version'
+require "nokogiri"
+
+begin
+  fields_config = {}
+  db = {}
+  rowid_counter = 0
+  baseurl = ''
+
+  # Start
+  Jekyll::Hooks.register(:site, :post_read) do |site|
+    # https://www.rubydoc.info/github/jekyll/jekyll/Jekyll/Site
+    fields_config = site.config['blogsearch']['fields']
+    
+    db_path = site.config['blogsearch']['output']
+    db_dir = File.dirname(db_path)
+    Dir.mkdir(db_dir) if not Dir.exist?(db_dir)
+    File.delete(db_path) if File.exist?(db_path)
+    db = SQLite3::Database.new db_path
+
+    if site.config['blogsearch']['fields']['url'].key?('base')
+      baseurl = site.config['blogsearch']['fields']['url']['base']
+    else 
+      baseurl = site.config['url'] ? site.config['url'] : ''
+      baseurl += site.config['baseurl'] ? site.config['baseurl'] : ''
+    end
+
+    # External content table
+    db.execute <<-SQL
+      CREATE TABLE blogsearch_ext_content (
+        rowid INTEGER PRIMARY KEY,
+        title,
+        body,
+        url,
+        categories,
+        tags
+      );
+    SQL
+
+    # FTS5 virtual table
+    db.execute <<-SQL
+      CREATE VIRTUAL TABLE blogsearch
+      USING fts5 (
+        title,
+        body,
+        url,
+        categories,
+        tags,
+        tokenize = 'porter unicode61 remove_diacritics 1',
+        content=blogsearch_ext_content,
+        content_rowid=rowid
+      );
+    SQL
+  end
+
+  # End
+  Jekyll::Hooks.register :site, :post_render do |site|
+    db.close
+  end
+
+  # Post and etc.
+  Jekyll::Hooks.register :documents, :post_render do |document|
+    # https://www.rubydoc.info/github/jekyll/jekyll/Jekyll/Document
+    # [TODO] Add support for document.data['excerpt']
+
+    next if not document.published?
+    rowid_counter += 1
+
+    rowid = rowid_counter
+    title = document.data['title']
+    body = Nokogiri::HTML(document.content).text.to_s.gsub(/\s+/, ' ')
+    url = baseurl + document.url
+    categories = document.data['categories'].join(' , ')
+    tags = document.data['tags'].join(' , ')
+
+    # External content table
+    db.execute <<-SQL,
+      INSERT INTO blogsearch_ext_content
+      VALUES (
+        ?,
+        ?,
+        ?,
+        ?,
+        ?,
+        ?
+      );
+    SQL
+    [rowid, title, body, url, categories, tags]
+    
+    # FTS5 virtual table
+    db.execute <<-SQL,
+      INSERT INTO blogsearch (
+        rowid,
+        title,
+        body,
+        url,
+        categories,
+        tags
+      )
+      VALUES (
+        ?,
+        ?,
+        ?,
+        ?,
+        ?,
+        ?
+      );
+    SQL
+    [rowid, title, body, url, categories, tags]
+  end
+
+rescue => e
+  puts e.message
+end

metadata

@@ -0,0 +1,87 @@
+--- !ruby/object:Gem::Specification
+name: jekyll-blogsearch
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- Bumsik Kim
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2020-05-23 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: jekyll
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: sqlite3
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.4'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.4'
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.10'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.10'
+description: 
+email: k.bumsik@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- README.adoc
+- lib/jekyll-blogsearch.rb
+- lib/jekyll/blogsearch/version.rb
+homepage: https://github.com/kbumsik/blogsearch
+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: []
+rubygems_version: 3.1.2
+signing_key: 
+specification_version: 4
+summary: BlogSearch index building tool for Jekyll
+test_files: []