srx 0.1.0 → 0.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 18c2fc1da5f4a792393a9dd4955c79d73bc9d00943000f38689a5763d8c8ff4c
-  data.tar.gz: 2385b9f65e61ad291e1419e217b737653bbeea0d4f62dc7fbb4ae35e6948984c
+  metadata.gz: 248fc2b9cd220023564c26a792536b1593b2bdefe77b71e133805658bd169d13
+  data.tar.gz: 7aa58a5e7fa2255219aaf83f7df1b09ebde3711a59c84d0cce7b3811af6f869e
 SHA512:
-  metadata.gz: 915b837e6a239f7de688d51ca3fca2bbdcf898234f825cbd49894223e8c31f71167d6a22d9097a36ab75ea3fc8f383ae790d3df8e0e3fce2fb8210022412fad2
-  data.tar.gz: 326d3de2c328aa49be07c7df62229fe40c8cf3b2c4101f090b9c805b9e3a2fcd1c8eec155b6b3af9c556ff5c548d5263425975bdc9b0368b334342ce47dd71d9
+  metadata.gz: 0af9311397924bf58131fd753e879f63f32c3706998f5cbb9c3c06ab51cb626a2417d31cd52dba2d905b571d5489efc1ad088a334f7b868fdd66e8e82a64f547
+  data.tar.gz: 969da7b926a664411a887948f17ff011d8e4040ef970e71d2ecde92ff05e39039aeb2a51238326be83418fda7bdf279241145c024cf41bccc8d4d515027cc039

data/.github/workflows/main.yml

@@ -13,7 +13,7 @@ jobs:
         ruby-version: 2.7.2
     - name: Install
       run: |
-        gem install bundler -v 2.2.7
+        gem install bundler -v 2.2.9
         bundle install
     - name: Type check
       run: bundle exec solargraph typecheck --level typed

data/.rubocop.yml

@@ -10,4 +10,4 @@ AllCops:
 Layout/LineLength:
   Max: 120
   Exclude:
-    - 'test/srx/golden_rules_test.rb'
+    - 'test/golden_rules_test.rb'

data/CHANGELOG.md

@@ -0,0 +1,9 @@
+## [Unreleased]
+
+## [0.2.0] - 2021-02-13
+
+- Handle HTML void elements correctly
+
+## [0.1.0] - 2021-02-13
+
+- Initial release

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    srx (0.1.0)
+    srx (0.2.0)
       nokogiri (~> 1.11)
 
 GEM
@@ -81,4 +81,4 @@ DEPENDENCIES
   srx!
 
 BUNDLED WITH
-   2.2.7
+   2.2.9

data/README.md

@@ -13,7 +13,10 @@ This gem provides facilities for reading SRX files and an engine for performing
 segmentation.
 
 Only a minimal rule set is supplied by default; for actual usage you are
-encouraged to supply your own SRX rules.
+encouraged to supply your own SRX rules. One such set of rules is that from
+[LanguageTool](https://languagetool.org/); this is conveniently packaged into a
+companion gem:
+[srx-languagetool-ruby](https://github.com/amake/srx-languagetool-ruby).
 
 ## What's different about this gem?
 
@@ -43,7 +46,7 @@ Some disadvantages:
   test](https://github.com/diasks2/pragmatic_segmenter#comparison-of-segmentation-tools-libraries-and-algorithms),
   scoring 47% (English) and 48% (others) with the default rules. However you can
   improve on that with better rules such as
-  [LanguageTool's](https://github.com/languagetool-org/languagetool/blob/05707300df14668e97d064811931e0668f2b695b/languagetool-core/src/main/resources/org/languagetool/resource/segment.srx).
+  [LanguageTool's](https://github.com/amake/srx-languagetool-ruby).
 
 ## Installation
 

data/lib/srx/format.rb

@@ -3,6 +3,7 @@
 require_relative 'format/base_format'
 require_relative 'format/text'
 require_relative 'format/xml'
+require_relative 'format/html'
 
 module Srx
   # Format-specific data and logic
@@ -10,7 +11,7 @@ module Srx
     FORMATS = {
       text: Text.new,
       xml: Xml.new,
-      html: Xml.new # TODO: specialize for HTML
+      html: Html.new
     }.freeze
 
     class << self

data/lib/srx/format/html.rb

@@ -0,0 +1,41 @@
+# frozen_string_literal: true
+
+require 'set'
+require 'English'
+
+module Srx
+  module Format
+    # Support for XML
+    #
+    # @see https://www.w3.org/TR/xml/
+    class Html < Xml
+      START_TAG_CAPTURE = /<(?<name>#{Xml::NAME})(?:#{Xml::SPACE}#{Xml::ATTRIBUTE})*#{Xml::SPACE}?>/.freeze
+
+      # A set of HTML tags that are "void elements", meaning they do not need a
+      # paired closing tag.
+      #
+      # @see https://html.spec.whatwg.org/#void-elements
+      # @see https://developer.mozilla.org/en-US/docs/Web/HTML/Element/command
+      # @see https://developer.mozilla.org/en-US/docs/Web/HTML/Element/keygen
+      # @see https://developer.mozilla.org/en-US/docs/Web/HTML/Element/menuitem
+      VOID_ELEMENTS = Set[
+        'area', 'base', 'br', 'col', 'command', 'embed', 'hr', 'img', 'input',
+        'link', 'meta', 'menuitem', 'param', 'source', 'track', 'wbr'
+      ].freeze
+
+      def start_formatting?(markup)
+        START_TAG_CAPTURE.match(markup) do |m|
+          !VOID_ELEMENTS.include?(m['name'])
+        end
+      end
+
+      def isolated_formatting?(markup)
+        return true if super(markup)
+
+        START_TAG_CAPTURE.match(markup) do |m|
+          VOID_ELEMENTS.include?(m['name'])
+        end
+      end
+    end
+  end
+end

data/lib/srx/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Srx
-  VERSION = '0.1.0'
+  VERSION = '0.2.0'
 end

data/srx.gemspec

@@ -15,6 +15,7 @@ Gem::Specification.new do |spec|
 
   spec.metadata['homepage_uri'] = spec.homepage
   spec.metadata['source_code_uri'] = 'https://github.com/amake/srx-ruby.git'
+  spec.metadata['changelog_uri'] = 'https://github.com/amake/srx-ruby/blob/master/CHANGELOG.md'
 
   # Specify which files should be added to the gem when it is released.
   # The `git ls-files -z` loads the files in the RubyGem that have been added into git.

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: srx
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: 0.2.0
 platform: ruby
 authors:
 - Aaron Madlon-Kay
@@ -135,6 +135,7 @@ files:
 - ".rubocop.yml"
 - ".rubocop_todo.yml"
 - ".solargraph.yml"
+- CHANGELOG.md
 - Gemfile
 - Gemfile.lock
 - LICENSE.txt
@@ -150,6 +151,7 @@ files:
 - lib/srx/engine.rb
 - lib/srx/format.rb
 - lib/srx/format/base_format.rb
+- lib/srx/format/html.rb
 - lib/srx/format/text.rb
 - lib/srx/format/xml.rb
 - lib/srx/icu_regex.rb
@@ -163,6 +165,7 @@ licenses:
 metadata:
   homepage_uri: https://github.com/amake/srx-ruby
   source_code_uri: https://github.com/amake/srx-ruby.git
+  changelog_uri: https://github.com/amake/srx-ruby/blob/master/CHANGELOG.md
 post_install_message: 
 rdoc_options: []
 require_paths: