escapement 0.1.3 → 1.0.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 8b604ba6771ae474416704ecb17863b56124b7af
-  data.tar.gz: 9ac1bfe3ed661721f0dd3dc2ce9f1abcf7cbb6ee
+  metadata.gz: 6fa90e5289492fd35e77857b9caac7a9d70f2bee
+  data.tar.gz: e1786a0edbbb18ec4aa741cd762d73abdd6f20bf
 SHA512:
-  metadata.gz: 7fa8d148809ec2c2acb8cdbea56aefa4e223e3cc4358aaec98838269fce3133a8f44efc63cee191a88d4fb94bd25cef8c119cfdec3e27fb9a498a5041d54af4a
-  data.tar.gz: 3bef38a534826c355c8ceaebd539f5fd427749a6851b0cddfbea43863f9c8a2bdc9ca870aeb050710119dfe1629b8ea78c63aba916c725483eaf1f7a03361a17
+  metadata.gz: a11eca3bcb49edf065e4c5caec62dd61588e77febaea83cbbe757ac8e701ae544aaa1336e6294a69a92899c8e0b5aba4d87d592e543eae3f78f5a276b3ce7750
+  data.tar.gz: a82bf4073571a62cbcac6416680271e253d5d55af1624f9b916a27288d846d803e9434c48f04f8919655d7c49c522102bd9067d684d8548b7773ef3e4fe478a2

data/.travis.yml

@@ -0,0 +1,6 @@
+language: ruby
+rvm:
+  - 2.0.0
+  - 2.1.6
+  - 2.2.1
+  - 2.3.1

data/README.md

@@ -37,15 +37,9 @@ html.results
 
 From a high level, Escapement uses [Nokogiri](https://github.com/sparklemotion/nokogiri) to recursively traverse the DOM tree. As it traverses, it keeps track of the current position of the node relative to the text content in order to determine entity position. There are no regular expression hacks involved.
 
-## Development
-
-After checking out the repo, run `bin/setup` to install dependencies. Then, run `bin/console` for an interactive prompt that will allow you to experiment.
-
-To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release` to create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
-
 ## Contributing
 
-1. Fork it ( https://github.com/[my-github-username]/escapement/fork )
+1. Fork it ( https://github.com/hodinkee/escapement/fork )
 2. Create your feature branch (`git checkout -b my-new-feature`)
 3. Commit your changes (`git commit -am 'Add some feature'`)
 4. Push to the branch (`git push origin my-new-feature`)

data/Rakefile

@@ -1 +1,9 @@
 require "bundler/gem_tasks"
+
+begin
+  require 'rspec/core/rake_task'
+  RSpec::Core::RakeTask.new(:spec)
+
+  task default: :spec
+rescue LoadError
+end

data/escapement.gemspec

@@ -22,7 +22,7 @@ Gem::Specification.new do |spec|
 
   spec.add_dependency "nokogiri", "~> 1.6"
 
-  spec.add_development_dependency "bundler", "~> 1.9"
+  spec.add_development_dependency "bundler"
   spec.add_development_dependency "rake", "~> 10.0"
   spec.add_development_dependency "rspec", "~> 3"
 end

data/lib/escapement/html.rb

@@ -13,8 +13,27 @@ module Escapement
 
     # Extracts all of the entities for each paragraph/block.
     def extract!
+      preprocess!
+
       @blocks = doc.css('body').children.map { |child| Block.new(child).tap(&:process!) }
       @results = @blocks.reject { |b| b.result.nil? }.map(&:result)
     end
+
+    private
+
+    # Run a preprocess pass on the HTML in order to format certain entities
+    # before we start recording entity positions.
+    def preprocess!(node = @doc)
+      node.children.each do |child|
+        preprocess_node(child)
+        preprocess!(child)
+      end
+    end
+
+    def preprocess_node(node)
+      if node.name == 'br'
+        node.replace Nokogiri::XML::Text.new("\n", @doc)
+      end
+    end
   end
 end

data/lib/escapement/tag.rb

@@ -40,7 +40,6 @@ module Escapement
       when 'li' then 'list_item'
       when 'sup' then 'superscript'
       when 'sub' then 'subscript'
-      when 'br' then 'line_break'
       when /h\d/ then 'header'
       else node.name
       end

data/lib/escapement/version.rb

@@ -1,3 +1,3 @@
 module Escapement
-  VERSION = "0.1.3"
+  VERSION = "1.0.0"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: escapement
 version: !ruby/object:Gem::Version
-  version: 0.1.3
+  version: 1.0.0
 platform: ruby
 authors:
 - Ryan LeFevre
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2015-07-15 00:00:00.000000000 Z
+date: 2016-06-30 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
@@ -28,16 +28,16 @@ dependencies:
   name: bundler
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '1.9'
+        version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '1.9'
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
@@ -77,6 +77,7 @@ extra_rdoc_files: []
 files:
 - ".gitignore"
 - ".rspec"
+- ".travis.yml"
 - Gemfile
 - LICENSE
 - README.md
@@ -110,7 +111,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.4.6
+rubygems_version: 2.5.1
 signing_key: 
 specification_version: 4
 summary: Extract child entities from an HTML string.