upmark 0.1.2 → 0.1.3

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    upmark (0.1.2)
+    upmark (0.1.3)
       parslet
 
 GEM
@@ -10,7 +10,7 @@ GEM
     blankslate (2.1.2.4)
     diff-lcs (1.1.3)
     multi_json (1.0.3)
-    parslet (1.2.1)
+    parslet (1.2.3)
       blankslate (~> 2.0)
     rspec (2.6.0)
       rspec-core (~> 2.6.0)

data/README.md

@@ -8,12 +8,45 @@ A HTML to Markdown converter.
 
 ## Usage
 
-    require "upmark"
+In ruby:
 
+    require "upmark"
     html = %q{<p>messenger <strong>bag</strong> skateboard</p>}
     markdown = Upmark.convert(html)
     puts markdown
 
+From the command-line:
+
+    > upmark foo.html
+
+You can also pipe poorly formatted HTML documents through `tidy` before piping them into `upmark`:
+
+    > cat bar.html | tidy -asxhtml -indent -quiet --show-errors 0 --show-warnings 0 --show-body-only 1 --wrap 0 | upmark
+
+## Features
+
+Upmark will convert the following (arbitrarily nested) HTML elements to Markdown:
+
+* `strong`
+* `em`
+* `p`
+* `a`
+* `h1`, `h2`, `h3`
+* `ul`
+* `ol`
+* `br`
+
+It will also pass through block and span-level HTML elements (e.g. `table`, `div`, `span`, etc) which aren't used by Markdown.
+
+## How it works
+
+Upmark defines a parsing expression grammar (PEG) using the very awesome [Parslet](http://kschiess.github.com/parslet/) gem. This PEG is then used to convert HTML into Markdown in 4 steps:
+
+1. Parse the XHTML into an abstract syntax tree (AST).
+2. Normalize the AST into a nested hash of HTML elements.
+3. Mark the block and span-level subtrees which should be ignored (`table`, `div`, `span`, etc).
+4. Convert the AST leaves into Markdown.
+
 ## License
 
 Upmark is Copyright (c) 2011 The Conversation Media Group and distributed under the MIT license.

data/Rakefile

@@ -13,7 +13,7 @@ namespace :spec do
   end
 
   desc "Run unit and acceptance specs"
-  task :all => [:"spec:unit", :"spec:acceptance"]
+  task all: [:"spec:unit", :"spec:acceptance"]
 end
 
 task default: :"spec:all"

data/lib/upmark/parser/xml.rb

@@ -66,9 +66,11 @@ module Upmark
       }
 
       rule(:attribute_value) {
-        (match(/['"]/).absent? >> match(/[^<&]/)).repeat
+        (match(/['"]/).absent? >> (match(/[^<&]/) | entity_ref)).repeat
       }
 
+      rule(:entity_ref) { match("&") >> name >> match(";") }
+
       rule(:space)  { match(/\s/).repeat(1) }
       rule(:space?) { space.maybe }
     end

data/lib/upmark/version.rb

@@ -1,3 +1,3 @@
 module Upmark
-  VERSION = "0.1.2"
+  VERSION = "0.1.3"
 end

data/spec/acceptance/upmark_spec.rb

@@ -13,6 +13,16 @@ describe Upmark, ".convert" do
     MD
   end
 
+  context "<a> hard" do
+    let(:html) { <<-HTML.strip }
+<p><a href="http://jobs.latrobe.edu.au/jobDetails.asp?sJobIDs=545808&amp;sKeywords=business">Manager, Business Solutions</a></p>
+    HTML
+
+    it { should == <<-MD.strip }
+[Manager, Business Solutions](http://jobs.latrobe.edu.au/jobDetails.asp?sJobIDs=545808&amp;sKeywords=business "")
+    MD
+  end
+
   context "<img>" do
     let(:html) { <<-HTML.strip }
 <img src="http://helvetica.com/image.gif" title="art party organic" alt="messenger bag skateboard" />

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: upmark
 version: !ruby/object:Gem::Version
-  version: 0.1.2
+  version: 0.1.3
   prerelease: 
 platform: ruby
 authors:
@@ -10,11 +10,11 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2011-09-26 00:00:00.000000000 Z
+date: 2012-03-28 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rspec
-  requirement: &70263069806220 !ruby/object:Gem::Requirement
+  requirement: &70329857124760 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -22,10 +22,10 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *70263069806220
+  version_requirements: *70329857124760
 - !ruby/object:Gem::Dependency
   name: simplecov
-  requirement: &70263069805760 !ruby/object:Gem::Requirement
+  requirement: &70329857124340 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -33,10 +33,10 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *70263069805760
+  version_requirements: *70329857124340
 - !ruby/object:Gem::Dependency
   name: parslet
-  requirement: &70263069779220 !ruby/object:Gem::Requirement
+  requirement: &70329857123920 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -44,7 +44,7 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *70263069779220
+  version_requirements: *70329857123920
 description: Upmark has the skills to convert your HTML to Markdown.
 email: dev@theconversation.edu.au
 executables:
@@ -95,7 +95,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: upmark
-rubygems_version: 1.8.10
+rubygems_version: 1.8.11
 signing_key: 
 specification_version: 3
 summary: A HTML to Markdown converter.