From 9b8e9f49c66b0ac0bf8092ce02819bb680dea141 Mon Sep 17 00:00:00 2001
From: Yorick Peterse <yorickpeterse@gmail.com>
Date: Wed, 3 Sep 2014 23:10:50 +0200
Subject: [PATCH] Support for lexing empty attribute values.

This ensures that Oga can lex the following properly:

    <input value="" />

Previously Ragel would stop upon finding the empty string. This was caused due
to the string rules being declared as following:

    string_dquote = (dquote ^dquote+ dquote);
    string_squote = (squote ^squote+ squote);

These rules only match strings _with_ content, not without. Since Ragel stops
consuming input the moment it finds unhandled data this resulted in incorrect
tokens being emitted.
---
 ext/ragel/base_lexer.rl              |  4 ++--
 spec/oga/xml/lexer/elements_spec.rb  | 10 ++++++++++
 spec/oga/xml/parser/elements_spec.rb | 28 ++++++++++++++++++++++++++++
 3 files changed, 40 insertions(+), 2 deletions(-)

diff --git a/ext/ragel/base_lexer.rl b/ext/ragel/base_lexer.rl
index 21f75ad..4b7a4b1 100644
--- a/ext/ragel/base_lexer.rl
+++ b/ext/ragel/base_lexer.rl
@@ -116,8 +116,8 @@
     dquote = '"';
     squote = "'";
 
-    string_dquote = (dquote ^dquote+ dquote);
-    string_squote = (squote ^squote+ squote);
+    string_dquote = (dquote ^dquote* dquote);
+    string_squote = (squote ^squote* squote);
 
     string = string_dquote | string_squote;
 
diff --git a/spec/oga/xml/lexer/elements_spec.rb b/spec/oga/xml/lexer/elements_spec.rb
index 97054ab..3455e2b 100644
--- a/spec/oga/xml/lexer/elements_spec.rb
+++ b/spec/oga/xml/lexer/elements_spec.rb
@@ -53,6 +53,16 @@ describe Oga::XML::Lexer do
       ]
     end
 
+    example 'lex an element with an attribute with an empty value' do
+      lex('<p foo=""></p>').should == [
+        [:T_ELEM_START, nil, 1],
+        [:T_ELEM_NAME, 'p', 1],
+        [:T_ATTR, 'foo', 1],
+        [:T_STRING, '', 1],
+        [:T_ELEM_END, nil, 1]
+      ]
+    end
+
     example 'lex a paragraph element with attributes' do
       lex('<p class="foo">Hello</p>').should == [
         [:T_ELEM_START, nil, 1],
diff --git a/spec/oga/xml/parser/elements_spec.rb b/spec/oga/xml/parser/elements_spec.rb
index 4488594..afe317f 100644
--- a/spec/oga/xml/parser/elements_spec.rb
+++ b/spec/oga/xml/parser/elements_spec.rb
@@ -55,6 +55,34 @@ describe Oga::XML::Parser do
     end
   end
 
+  context 'elements with attributes without values' do
+    before :all do
+      @element = parse('<foo bar></foo>').children[0]
+    end
+
+    example 'return an Element instance' do
+      @element.is_a?(Oga::XML::Element).should == true
+    end
+
+    example 'set the bar attribute' do
+      @element.attribute('bar').value.should be_nil
+    end
+  end
+
+  context 'elements with attributes with empty values' do
+    before :all do
+      @element = parse('<foo bar=""></foo>').children[0]
+    end
+
+    example 'return an Element instance' do
+      @element.is_a?(Oga::XML::Element).should == true
+    end
+
+    example 'set the bar attribute' do
+      @element.attribute('bar').value.should == ''
+    end
+  end
+
   context 'elements with namespaced attributes' do
     before :all do
       @element = parse('<foo xmlns:x="x" x:bar="baz"></foo>').children[0]