iudex-html 1.2.b.1-java → 1.2.b.2-java

data/History.rdoc

@@ -1,3 +1,7 @@
+=== 1.2.b.2 (2012-6-23)
+* Fix #8: Add Neko parser check for empty (malformed) attribute names.
+* Extend/upgrade to gravitext-xmlprod [1.5.1,1.7)
+
 === 1.2.b.1 (2012-5-31)
 * Add support for HTML 5 (draft) tags, attributes
 * Neko parser support for HTML 5 <meta charset>

data/Manifest.txt

@@ -25,4 +25,4 @@ test/test_parse_filter.rb
 test/test_stax_parser.rb
 test/test_tree_walker.rb
 test/test_word_counters.rb
-lib/iudex-html/iudex-html-1.2.b.1.jar
+lib/iudex-html/iudex-html-1.2.b.2.jar

data/lib/iudex-html/base.rb

@@ -16,6 +16,6 @@
 
 module Iudex
   module HTML
-    VERSION = '1.2.b.1'
+    VERSION = '1.2.b.2'
   end
 end

data/pom.xml

@@ -3,7 +3,7 @@
   <groupId>iudex</groupId>
   <artifactId>iudex-html</artifactId>
   <packaging>jar</packaging>
-  <version>1.2.b.1</version>
+  <version>1.2.b.2</version>
   <name>Iudex HTML parsing/filtering and text extraction</name>
 
   <parent>
@@ -24,7 +24,7 @@
     <dependency>
       <groupId>com.gravitext</groupId>
       <artifactId>gravitext-xmlprod</artifactId>
-      <version>[1.5.1,1.5.9999)</version>
+      <version>[1.5.1,1.6.9999)</version>
     </dependency>
 
     <dependency>

data/test/test_html_parser.rb

@@ -150,4 +150,20 @@ HTML
     assert_fragment( html[ :out ], tree )
   end
 
+  import 'iudex.html.neko.NekoHTMLParser'
+
+  # Neko yields attributes with empty localName, given this invalid
+  # input (#8)
+  def test_invalid_attribute
+    html = { :in  => '<div><img alt=""wns : next class="artwork" /></div>',
+             :out => '<div><img alt="" wns="" next="" class="artwork"/></div>' }
+
+    parser = NekoHTMLParser.new
+    parser.parse_as_fragment = true
+    parser.skip_banned = false # required to reproduce empty localName
+
+    tree = inner( parser.parse( source( html[ :in ], "UTF-8" ) ) )
+    assert_fragment( html[ :out ], tree )
+  end
+
 end

metadata

@@ -2,7 +2,7 @@
 name: iudex-html
 version: !ruby/object:Gem::Version 
   prerelease: 4
-  version: 1.2.b.1
+  version: 1.2.b.2
 platform: java
 authors: 
   - David Kellum
@@ -10,7 +10,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2012-06-01 00:00:00 Z
+date: 2012-06-23 00:00:00 Z
 dependencies: 
   - !ruby/object:Gem::Dependency 
     name: iudex-core
@@ -39,9 +39,12 @@ dependencies:
     version_requirements: &id003 !ruby/object:Gem::Requirement 
       none: false
       requirements: 
-        - - ~>
+        - - ">="
           - !ruby/object:Gem::Version 
             version: 1.5.1
+        - - <
+          - !ruby/object:Gem::Version 
+            version: "1.7"
     requirement: *id003
     prerelease: false
     type: :runtime
@@ -117,7 +120,7 @@ files:
   - test/test_stax_parser.rb
   - test/test_tree_walker.rb
   - test/test_word_counters.rb
-  - lib/iudex-html/iudex-html-1.2.b.1.jar
+  - lib/iudex-html/iudex-html-1.2.b.2.jar
 homepage: http://github.com/dekellum/iudex
 licenses: []