nokogiri 1.6.8.rc1-java → 1.6.8.rc2-java

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 7a0faa24c4ba08a67f6cd8711090bfa7ebff41f0
-  data.tar.gz: 491b9752e6744939a7ca412f81af132ba08fd6e1
+  metadata.gz: 222c1d18ae131bb61d0bddda23df52faacaa128b
+  data.tar.gz: af7331524ffa5d288b547366a9859a6b2441937f
 SHA512:
-  metadata.gz: 1d039a2f0ba85ebd39c8c7cb53e6c5ef8552fd5545ef8efc73f878064e5f3794c4b6b650db1265e32e34ed7c541d0097e85f0b3803053f24064daaf82f3bb274
-  data.tar.gz: 03098294742205f9b0a4acd7818b8c05e65f0dad92ecf8bcf12baff3664ee8e7618245ecc3958162a58b7431247b143935c8b5a7c777e407e67afbc903d02b7a
+  metadata.gz: 42b48a069c53ae94adad96690691d1dff1440e00ba476ac293778069f0140f871bbf28283ecfef1051d3eaa01a009bab46ea8e181b26500128a27abdec84d95a
+  data.tar.gz: 96cb5071f838df0779bc3d8973a798c81eb689e5b067008c15dfd31d6cdfbd099a91091bca692610d62348932421d32320827112145bf6a8e1d02dae1216047c

data/.cross_rubies

@@ -5,3 +5,5 @@
 2.1.6:x86_64-w64-mingw32
 2.2.2:i686-w64-mingw32
 2.2.2:x86_64-w64-mingw32
+2.3.0:i686-w64-mingw32
+2.3.0:x86_64-w64-mingw32

data/CHANGELOG.rdoc

@@ -5,15 +5,29 @@
 * (MRI) Bundled Libxml2 is upgraded to 2.9.3, which fixes a series of security issues. See https://mail.gnome.org/archives/xml/2015-November/msg00012.html
 
 
+==== Features
+
+Several changes were made to improve performance:
+
+* [MRI] Simplify NodeSet#to_a with a minor speed-up. (#1397)
+* XML::Node#ancestors optimization (#1297) (Thanks, Bruno Sutic!)
+* Use Symbol#to_proc where we weren't previously, because Ruby 1.8.7 reasons. (#1296) (Thanks, Bruno Sutic!)
+
+
 ==== Bug Fixes
 
 * [JRuby] fix load errors when deploying to JRuby/Torquebox (#1114) (Thanks, @atambo!)
 * [JRuby] fix NPE when inspecting nodes returned by NodeSet#drop (#1042) (Thanks, @mkristian!)
 * [JRuby] fix nil attriubte node's namespace in reader (#1327) (Thanks, @codekitchen!)
+* [JRuby] fix Nokogiri munging unicode characters that require more than 2 bytes (#1113) (Thanks, @mkristian!)
 * [MRI] fix assertion failure while accessing attribute node's namespace in reader (#843) (Thanks, @2potatocakes!)
 * [MRI] fix issue with GCing namespace nodes returned in an xpath query. (#1155)
+* [MRI] Ensure C strings are null-terminated. (#1381)
 * unescape special characters in CSS queries (#1303) (Thanks, @twalpole!)
 * consistently handle empty documents (#1349)
+* Update to mini_portile2 2.1.0 to address whitespace-handling during patching. (#1402)
+* Fix encoding of xml node namespaces.
+* Work around issue installing Nokogiri on overlayfs (commonly used in Docker containers). (#1370, #1405)
 
 
 === 1.6.7.1 / 2015-12-16
@@ -59,7 +73,7 @@ See #1374 and #1376 for details.
 * [JRuby] reset the namespace cache when replacing the document's innerHtml (#1265) (Thanks, @mkristian!)
 * [JRuby] Document#parse should support IO objects that respond to #read. (#1124) (Thanks, Jake Byman!)
 * [MRI] Duplicate-id errors when setting the `id` attribute on HTML documents are now silenced. (#1262)
-* [JRuby] SAX parser cuts texts in peices when quare brackets exist. (#1261)
+* [JRuby] SAX parser cuts texts in pieces when square brackets exist. (#1261)
 * [JRuby] Namespaced attributes aren't removed by remove_attribute. (#1299)
 
 
@@ -69,7 +83,7 @@ This version pulls in an upstream patch to the vendored libxml2 to address:
 
 * unclosed comment uninitialized access issue (#1376)
 
-This issue does not have a CVE assigned to it as this time.
+This issue was assigned CVE-2015-8710 after the fact. See http://seclists.org/oss-sec/2015/q4/616 for details.
 
 
 === 1.6.6.3 / 2015-11-16

data/Gemfile

@@ -4,7 +4,7 @@
 
 source "https://rubygems.org/"
 
-gem "mini_portile2", "~>2.0.0"
+gem "mini_portile2", "~>2.1.0"
 
 gem "rdoc", "~>4.0", :group => [:development, :test]
 gem "hoe-bundler", ">=1.1", :group => [:development, :test]
@@ -14,7 +14,7 @@ gem "hoe-git", ">=1.4", :group => [:development, :test]
 gem "minitest", "~>2.2.2", :group => [:development, :test]
 gem "rake", ">=0.9", :group => [:development, :test]
 gem "rake-compiler", "~>0.9.2", :group => [:development, :test]
-gem "rake-compiler-dock", "~>0.4.2", :group => [:development, :test]
+gem "rake-compiler-dock", "~>0.5.0", :group => [:development, :test]
 gem "racc", ">=1.4.6", :group => [:development, :test], :platform => :ruby
 gem "rexical", ">=1.0.5", :group => [:development, :test], :platform => :ruby
 gem "hoe", "~>3.14", :group => [:development, :test]

data/LICENSE.txt

@@ -1,6 +1,6 @@
 (The MIT License)
 
-Copyright (c) 2008 - 2015:
+Copyright (c) 2008 - 2016:
 
 * [Aaron Patterson](http://tenderlovemaking.com)
 * [Mike Dalessio](http://mike.daless.io)

data/Manifest.txt

@@ -3,7 +3,6 @@
 .editorconfig
 .gemtest
 .travis.yml
-CHANGELOG.ja.rdoc
 CHANGELOG.rdoc
 CONTRIBUTING.md
 C_CODING_STYLE.rdoc

data/Rakefile

@@ -129,7 +129,7 @@ HOE = Hoe.spec 'nokogiri' do
   unless java?
     self.extra_deps += [
       # Keep this version in sync with the one in extconf.rb !
-      ["mini_portile2",    "~> 2.0.0"],
+      ["mini_portile2",    "~> 2.1.0"],
     ]
   end
 
@@ -141,7 +141,7 @@ HOE = Hoe.spec 'nokogiri' do
     ["minitest",        "~> 2.2.2"],
     ["rake",            ">= 0.9"],
     ["rake-compiler",   "~> 0.9.2"],
-    ["rake-compiler-dock", "~> 0.4.2"],
+    ["rake-compiler-dock", "~> 0.5.0"],
     ["racc",            ">= 1.4.6"],
     ["rexical",         ">= 1.0.5"]
   ]
@@ -184,6 +184,7 @@ if java?
     ext.target_version = '1.6'
     jars = ["#{jruby_home}/lib/jruby.jar"] + FileList['lib/*.jar']
     ext.classpath = jars.map { |x| File.expand_path x }.join ':'
+    ext.debug = true if ENV['JAVA_DEBUG']
   end
 
   task gem_build_path => [:compile] do
@@ -295,7 +296,8 @@ end
 require 'tasks/test'
 
 task :java_debug do
-  ENV['JAVA_OPTS'] = '-Xdebug -Xrunjdwp:transport=dt_socket,address=8000,server=y,suspend=y' if java? && ENV['JAVA_DEBUG']
+  ENV['JRUBY_OPTS'] = "#{ENV['JRUBY_OPTS']} --debug --dev"
+  ENV['JAVA_OPTS'] = '-Xdebug -Xrunjdwp:transport=dt_socket,address=8000,server=y,suspend=y' if ENV['JAVA_DEBUG']
 end
 
 if java?

data/ext/java/nokogiri/HtmlElementDescription.java

@@ -105,9 +105,12 @@ public class HtmlElementDescription extends RubyObject {
     public static IRubyObject get(ThreadContext context,
                                   IRubyObject klazz, IRubyObject name) {
 
-        HTMLElements.Element elem = HTMLElements.getElement(name.toString());
+        // nekohtml will return an element even for invalid names, see
+        // http://sourceforge.net/p/nekohtml/code/HEAD/tree/trunk/src/org/cyberneko/html/HTMLElements.java#l514
+        // which breaks `test_fetch_nonexistent'
+        HTMLElements.Element elem = HTMLElements.getElement(name.asJavaString(), HTMLElements.NO_SUCH_ELEMENT);
         if (elem == HTMLElements.NO_SUCH_ELEMENT)
-            return context.getRuntime().getNil();
+            return context.nil;
 
         HtmlElementDescription desc =
             new HtmlElementDescription(context.getRuntime(), (RubyClass)klazz);

data/ext/java/nokogiri/NokogiriService.java

@@ -36,6 +36,7 @@ import java.util.Collections;
 import java.util.HashMap;
 import java.util.Map;
 
+import org.cyberneko.html.HTMLElements;
 import org.jruby.Ruby;
 import org.jruby.RubyArray;
 import org.jruby.RubyClass;
@@ -53,6 +54,24 @@ import org.jruby.runtime.load.BasicLibraryService;
  * @author Yoko Harada <yokolet@gmail.com>
  */
 public class NokogiriService implements BasicLibraryService {
+
+    // nekohtml from version 1.9.13 they autocomplete tbody around
+    // tr tags of a table - http://sourceforge.net/p/nekohtml/code/241/
+    // this monkey patch undoes this autocompletion
+    static class MonkeyPatchHTMLElements extends HTMLElements {
+        static void patchIt() {
+            Element[] array = ELEMENTS_ARRAY['T'-'A'];
+            for(int i = 0; i < array.length; i++) {
+                if (array[i].name.equals("TR")) {
+                    array[i] = new Element(TR, "TR", Element.BLOCK, TABLE, new short[]{TD,TH,TR,COLGROUP,DIV});
+                }
+            }
+        }
+    }
+    static {
+        MonkeyPatchHTMLElements.patchIt();
+    }
+
     public static final String nokogiriClassCacheGvarName = "$NOKOGIRI_CLASS_CACHE";
 
     public boolean basicLoad(Ruby ruby) {

data/ext/java/nokogiri/XmlNode.java

@@ -806,6 +806,13 @@ public class XmlNode extends RubyObject {
         }
 
         ctx.setInputSource(istream);
+        // TODO: for some reason, document.getEncoding() can be null or nil (don't know why)
+        // run `test_parse_with_unparented_html_text_context_node' few times to see this happen
+        if (document instanceof HtmlDocument && !(document.getEncoding() == null || document.getEncoding().isNil())) {
+        	HtmlDomParserContext htmlCtx= (HtmlDomParserContext) ctx;
+        	htmlCtx.setEncoding(document.getEncoding().asJavaString());
+        }
+        
         XmlDocument doc = ctx.parse(context, klass, runtime.getNil());
 
         RubyArray documentErrors = getErrorArray(document);

data/ext/java/nokogiri/internals/HtmlDomParserContext.java

@@ -65,7 +65,9 @@ import org.w3c.dom.NodeList;
  */
 public class HtmlDomParserContext extends XmlDomParserContext {
 
-    public HtmlDomParserContext(Ruby runtime, IRubyObject options) {
+    private String encoding;
+
+	public HtmlDomParserContext(Ruby runtime, IRubyObject options) {
         super(runtime, options);
     }
     
@@ -102,6 +104,11 @@ public class HtmlDomParserContext extends XmlDomParserContext {
         setFeature("http://cyberneko.org/html/features/report-errors", true);
         setFeature("http://xml.org/sax/features/namespaces", false);
     }
+    
+    @Override
+    public void setEncoding(String encoding) {
+		super.setEncoding(encoding);
+    }
 
     /**
      * Enable NekoHTML feature for balancing tags in a document fragment.

data/ext/java/nokogiri/internals/NokogiriErrorHandler.java

@@ -80,7 +80,6 @@ public abstract class NokogiriErrorHandler implements ErrorHandler, XMLErrorHand
     }
 
     protected boolean usesNekoHtml(String domain) {
-        if ("http://cyberneko.org/html".equals(domain)) return true;
-        else return false;
+        return "http://cyberneko.org/html".equals(domain);
     }
 }

data/ext/java/nokogiri/internals/NokogiriNonStrictErrorHandler4NekoHtml.java

@@ -115,7 +115,7 @@ public class NokogiriNonStrictErrorHandler4NekoHtml extends NokogiriErrorHandler
      * @param e Exception.
      */
     public void warning(String domain, String key, XMLParseException e) {
-        //noop. NekoHtml adds too many warnings.
+        errors.add(e);
     }
 
 }

data/ext/java/nokogiri/internals/NokogiriStrictErrorHandler.java

@@ -75,5 +75,4 @@ public class NokogiriStrictErrorHandler extends NokogiriErrorHandler {
         if (!nowarning) throw e;
         if (!usesNekoHtml(domain)) errors.add(e);
     }
-
 }

data/ext/java/nokogiri/internals/ParserContext.java

@@ -190,6 +190,10 @@ public class ParserContext extends RubyObject {
         }
         return false;
     }
+    
+    protected void setEncoding(String encoding) {
+    	source.setEncoding(encoding);
+    }
 
     /**
      * Set the InputSource to read from <code>file</code>, a String filename.

data/ext/java/nokogiri/internals/SaveContextVisitor.java

@@ -761,24 +761,25 @@ public class SaveContextVisitor {
         return true;
     }
 
-    private String getEncoding(Text text) {
-        if (encoding != null) return encoding;
-        encoding = text.getOwnerDocument().getInputEncoding();
-        return encoding;
-    }
-
     private String encodeStringToHtmlEntity(String text) {
         if (encoding == null)
           return text;
         CharsetEncoder encoder = Charset.forName(encoding).newEncoder();
-        int last = 126; // = U+007E. No need to encode under U+007E.
         StringBuffer sb = new StringBuffer();
-        for (int i = 0; i < text.length(); i++) {
-            char ch = text.charAt(i);
-            if (encoder.canEncode(ch)) sb.append(ch);
-            else sb.append("&#x" + Integer.toHexString(ch) + ";");
+        // make sure we can handle code points that are higher than 2 bytes
+        for (int i = 0; i < text.length();) {
+            int code = text.codePointAt(i);
+            // TODO not sure about bigger offset then 2 ?!
+            int offset = code > 65535 ? 2 : 1;
+            boolean canEncode = encoder.canEncode(text.substring(i, i + offset));
+            if (canEncode) {
+                sb.append(text.substring(i, i + offset));
+            }
+            else {
+                sb.append("&#x" + Integer.toHexString(code) + ";");
+            }
+            i += offset;
         }
         return new String(sb);
     }
-
 }

data/ext/nokogiri/extconf.rb

@@ -57,7 +57,6 @@ def do_clean
     # clean the ports build directory
     Pathname.glob(pwd.join('tmp', '*', 'ports')) { |dir|
       FileUtils.rm_rf(dir, verbose: true)
-      FileUtils.rmdir(dir.parent, parents: true, verbose: true)
     }
 
     if enable_config('static')
@@ -393,7 +392,7 @@ else
 
   # The gem version constraint in the Rakefile is not respected at install time.
   # Keep this version in sync with the one in the Rakefile !
-  gem "mini_portile2", "~> 2.0.0"
+  gem "mini_portile2", "~> 2.1.0"
   require 'mini_portile2'
   message "Using mini_portile version #{MiniPortile::VERSION}\n"
 

data/ext/nokogiri/html_document.c

@@ -18,8 +18,8 @@ static VALUE new(int argc, VALUE *argv, VALUE klass)
   external_id = rb_ary_entry(rest, (long)1);
 
   doc = htmlNewDoc(
-      RTEST(uri) ? (const xmlChar *)StringValuePtr(uri) : NULL,
-      RTEST(external_id) ? (const xmlChar *)StringValuePtr(external_id) : NULL
+      RTEST(uri) ? (const xmlChar *)StringValueCStr(uri) : NULL,
+      RTEST(external_id) ? (const xmlChar *)StringValueCStr(external_id) : NULL
   );
   rb_doc = Nokogiri_wrap_xml_document(klass, doc);
   rb_obj_call_init(rb_doc, argc, argv);
@@ -39,8 +39,8 @@ static VALUE read_io( VALUE klass,
                       VALUE encoding,
                       VALUE options )
 {
-  const char * c_url    = NIL_P(url)      ? NULL : StringValuePtr(url);
-  const char * c_enc    = NIL_P(encoding) ? NULL : StringValuePtr(encoding);
+  const char * c_url    = NIL_P(url)      ? NULL : StringValueCStr(url);
+  const char * c_enc    = NIL_P(encoding) ? NULL : StringValueCStr(encoding);
   VALUE error_list      = rb_ary_new();
   VALUE document;
   htmlDocPtr doc;
@@ -103,8 +103,8 @@ static VALUE read_memory( VALUE klass,
                           VALUE options )
 {
   const char * c_buffer = StringValuePtr(string);
-  const char * c_url    = NIL_P(url)      ? NULL : StringValuePtr(url);
-  const char * c_enc    = NIL_P(encoding) ? NULL : StringValuePtr(encoding);
+  const char * c_url    = NIL_P(url)      ? NULL : StringValueCStr(url);
+  const char * c_enc    = NIL_P(encoding) ? NULL : StringValueCStr(encoding);
   int len               = (int)RSTRING_LEN(string);
   VALUE error_list      = rb_ary_new();
   VALUE document;

data/ext/nokogiri/html_element_description.c

@@ -245,7 +245,7 @@ static VALUE name(VALUE self)
 static VALUE get_description(VALUE klass, VALUE tag_name)
 {
   const htmlElemDesc * description = htmlTagLookup(
-      (const xmlChar *)StringValuePtr(tag_name)
+      (const xmlChar *)StringValueCStr(tag_name)
   );
 
   if(NULL == description) return Qnil;

data/ext/nokogiri/html_entity_lookup.c

@@ -9,7 +9,7 @@
 static VALUE get(VALUE self, VALUE key)
 {
   const htmlEntityDesc * desc =
-    htmlEntityLookup((const xmlChar *)StringValuePtr(key));
+    htmlEntityLookup((const xmlChar *)StringValueCStr(key));
   VALUE klass, args[3];
 
   if(NULL == desc) return Qnil;

data/ext/nokogiri/html_sax_parser_context.c

@@ -31,12 +31,12 @@ parse_memory(VALUE klass, VALUE data, VALUE encoding)
     }
 
     if (RTEST(encoding)) {
-	xmlCharEncodingHandlerPtr enc = xmlFindCharEncodingHandler(StringValuePtr(encoding));
+	xmlCharEncodingHandlerPtr enc = xmlFindCharEncodingHandler(StringValueCStr(encoding));
 	if (enc != NULL) {
 	    xmlSwitchToEncoding(ctxt, enc);
 	    if (ctxt->errNo == XML_ERR_UNSUPPORTED_ENCODING) {
 		rb_raise(rb_eRuntimeError, "Unsupported encoding %s",
-			 StringValuePtr(encoding));
+			 StringValueCStr(encoding));
 	    }
 	}
     }
@@ -47,8 +47,8 @@ parse_memory(VALUE klass, VALUE data, VALUE encoding)
 static VALUE parse_file(VALUE klass, VALUE filename, VALUE encoding)
 {
   htmlParserCtxtPtr ctxt = htmlCreateFileParserCtxt(
-      StringValuePtr(filename),
-      StringValuePtr(encoding)
+      StringValueCStr(filename),
+      StringValueCStr(encoding)
   );
   return Data_Wrap_Struct(klass, NULL, deallocate, ctxt);
 }

data/ext/nokogiri/html_sax_push_parser.c

@@ -46,10 +46,10 @@ static VALUE initialize_native(VALUE self, VALUE _xml_sax, VALUE _filename,
 
   Data_Get_Struct(_xml_sax, xmlSAXHandler, sax);
 
-  if(_filename != Qnil) filename = StringValuePtr(_filename);
+  if(_filename != Qnil) filename = StringValueCStr(_filename);
 
   if (!NIL_P(encoding)) {
-    enc = xmlParseCharEncoding(StringValuePtr(encoding));
+    enc = xmlParseCharEncoding(StringValueCStr(encoding));
     if (enc == XML_CHAR_ENCODING_ERROR)
       rb_raise(rb_eArgError, "Unsupported Encoding");
   }

data/ext/nokogiri/xml_attr.c

@@ -20,7 +20,7 @@ static VALUE set_value(VALUE self, VALUE content)
     xmlNode *tmp;
 
     /* Encode our content */
-    buffer = xmlEncodeEntitiesReentrant(attr->doc, (unsigned char *)StringValuePtr(content));
+    buffer = xmlEncodeEntitiesReentrant(attr->doc, (unsigned char *)StringValueCStr(content));
 
     attr->children = xmlStringGetNodeList(attr->doc, buffer);
     attr->last = NULL;
@@ -61,7 +61,7 @@ static VALUE new(int argc, VALUE *argv, VALUE klass)
 
   node = xmlNewDocProp(
       xml_doc,
-      (const xmlChar *)StringValuePtr(name),
+      (const xmlChar *)StringValueCStr(name),
       NULL
   );
 

data/ext/nokogiri/xml_comment.c

@@ -34,7 +34,7 @@ static VALUE new(int argc, VALUE *argv, VALUE klass)
 
   node = xmlNewDocComment(
       xml_doc,
-      (const xmlChar *)StringValuePtr(content)
+      (const xmlChar *)StringValueCStr(content)
   );
 
   rb_node = Nokogiri_wrap_xml_node(klass, node);