();
+ subs = new ArrayList<>();
/*
* A bit of a hack. NekoHtml source code shows that
@@ -127,6 +127,7 @@ public class Html4ElementDescription extends RubyObject
ary[i] = ruby.newString(subs.get(i));
}
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
return ruby.newArray(ary);
}
diff --git a/ext/java/nokogiri/Html4EntityLookup.java b/ext/java/nokogiri/Html4EntityLookup.java
index 5d98f1f8c9..e0184d0c54 100644
--- a/ext/java/nokogiri/Html4EntityLookup.java
+++ b/ext/java/nokogiri/Html4EntityLookup.java
@@ -29,7 +29,7 @@ public class Html4EntityLookup extends RubyObject
/**
* Looks up an HTML entity key.
- *
+ *
* The description is a bit lacking.
*/
@JRubyMethod()
@@ -53,11 +53,10 @@ public class Html4EntityLookup extends RubyObject
IRubyObject edClass =
ruby.getClassFromPath("Nokogiri::HTML4::EntityDescription");
- IRubyObject edObj = invoke(context, edClass, "new",
+
+ return invoke(context, edClass, "new",
ruby.newFixnum(val), ruby.newString(name),
ruby.newString(name + " entity"));
-
- return edObj;
}
}
diff --git a/ext/java/nokogiri/Html4SaxParserContext.java b/ext/java/nokogiri/Html4SaxParserContext.java
index e167f11a3a..0bef93be3f 100644
--- a/ext/java/nokogiri/Html4SaxParserContext.java
+++ b/ext/java/nokogiri/Html4SaxParserContext.java
@@ -1,6 +1,5 @@
package nokogiri;
-import java.io.ByteArrayInputStream;
import java.io.InputStream;
import org.apache.xerces.parsers.AbstractSAXParser;
@@ -8,8 +7,6 @@
import org.jruby.Ruby;
import org.jruby.RubyClass;
import org.jruby.RubyEncoding;
-import org.jruby.RubyFixnum;
-import org.jruby.RubyString;
import org.jruby.anno.JRubyClass;
import org.jruby.anno.JRubyMethod;
import org.jruby.runtime.ThreadContext;
@@ -17,7 +14,6 @@
import org.xml.sax.SAXException;
import nokogiri.internals.NokogiriHandler;
-import static nokogiri.internals.NokogiriHelpers.rubyStringToString;
import static org.jruby.runtime.Helpers.invoke;
@@ -65,7 +61,7 @@ public class Html4SaxParserContext extends XmlSaxParserContext
return parser;
} catch (SAXException ex) {
throw new SAXException(
- "Problem while creating HTML4 SAX Parser: " + ex.toString());
+ "Problem while creating HTML4 SAX Parser: " + ex);
}
}
@@ -76,9 +72,10 @@ public class Html4SaxParserContext extends XmlSaxParserContext
String java_encoding = null;
if (encoding != context.runtime.getNil()) {
if (!(encoding instanceof RubyEncoding)) {
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
throw context.runtime.newTypeError("encoding must be kind_of Encoding");
}
- java_encoding = ((RubyEncoding)encoding).toString();
+ java_encoding = encoding.toString();
}
Html4SaxParserContext ctx = Html4SaxParserContext.newInstance(context.runtime, (RubyClass) klazz);
@@ -98,9 +95,10 @@ public class Html4SaxParserContext extends XmlSaxParserContext
String java_encoding = null;
if (encoding != context.runtime.getNil()) {
if (!(encoding instanceof RubyEncoding)) {
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
throw context.runtime.newTypeError("encoding must be kind_of Encoding");
}
- java_encoding = ((RubyEncoding)encoding).toString();
+ java_encoding = encoding.toString();
}
Html4SaxParserContext ctx = Html4SaxParserContext.newInstance(context.runtime, (RubyClass) klass);
@@ -118,15 +116,17 @@ public class Html4SaxParserContext extends XmlSaxParserContext
parse_io(ThreadContext context, IRubyObject klazz, IRubyObject data, IRubyObject encoding)
{
if (!invoke(context, data, "respond_to?", context.runtime.newSymbol("read")).isTrue()) {
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
throw context.runtime.newTypeError("argument expected to respond to :read");
}
String java_encoding = null;
if (encoding != context.runtime.getNil()) {
if (!(encoding instanceof RubyEncoding)) {
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
throw context.runtime.newTypeError("encoding must be kind_of Encoding");
}
- java_encoding = ((RubyEncoding)encoding).toString();
+ java_encoding = encoding.toString();
}
Html4SaxParserContext ctx = Html4SaxParserContext.newInstance(context.runtime, (RubyClass) klazz);
diff --git a/ext/java/nokogiri/Html4SaxPushParser.java b/ext/java/nokogiri/Html4SaxPushParser.java
index c338fd3696..3ef20427be 100644
--- a/ext/java/nokogiri/Html4SaxPushParser.java
+++ b/ext/java/nokogiri/Html4SaxPushParser.java
@@ -24,7 +24,6 @@
/**
* Class for Nokogiri::HTML4::SAX::PushParser
*
- * @author
* @author Piotr Szmielew - based on Nokogiri::XML::SAX::PushParser
*/
@JRubyClass(name = "Nokogiri::HTML4::SAX::PushParser")
@@ -93,6 +92,7 @@ public class Html4SaxPushParser extends RubyObject
setOptions(ThreadContext context, IRubyObject opts)
{
invoke(context, parse_options(context), "options=", opts);
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
options = new ParserContext.Options(opts.convertToInteger().getLongValue());
return getOptions(context);
}
@@ -148,14 +148,11 @@ public class Html4SaxPushParser extends RubyObject
assert saxParser != null : "saxParser null";
parserTask = new ParserTask(context, saxParser, stream);
futureTask = new FutureTask((Callable) parserTask);
- executor = Executors.newSingleThreadExecutor(new ThreadFactory() {
- @Override
- public Thread newThread(Runnable r) {
- Thread t = new Thread(r);
- t.setName("Html4SaxPushParser");
- t.setDaemon(true);
- return t;
- }
+ executor = Executors.newSingleThreadExecutor(r -> {
+ Thread t = new Thread(r);
+ t.setName("Html4SaxPushParser");
+ t.setDaemon(true);
+ return t;
});
executor.submit(futureTask);
}
@@ -168,8 +165,6 @@ public Thread newThread(Runnable r) {
try {
terminateImpl();
- } catch (InterruptedException e) {
- throw runtime.newRuntimeError(e.toString());
} catch (Exception e) {
throw runtime.newRuntimeError(e.toString());
}
diff --git a/ext/java/nokogiri/NokogiriService.java b/ext/java/nokogiri/NokogiriService.java
index 0f792dea62..15d3511f50 100644
--- a/ext/java/nokogiri/NokogiriService.java
+++ b/ext/java/nokogiri/NokogiriService.java
@@ -5,7 +5,6 @@
import java.util.Map;
import org.jruby.Ruby;
-import org.jruby.RubyArray;
import org.jruby.RubyClass;
import org.jruby.RubyFixnum;
import org.jruby.RubyModule;
@@ -33,13 +32,14 @@ public class NokogiriService implements BasicLibraryService
public static Map
getNokogiriClassCache(Ruby ruby)
{
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
return (Map) ruby.getModule("Nokogiri").getInternalVariable("cache");
}
private static Map
populateNokogiriClassCache(Ruby ruby)
{
- Map nokogiriClassCache = new HashMap();
+ Map nokogiriClassCache = new HashMap<>();
nokogiriClassCache.put("Nokogiri::HTML4::Document", (RubyClass)ruby.getClassFromPath("Nokogiri::HTML4::Document"));
nokogiriClassCache.put("Nokogiri::HTML4::ElementDescription",
(RubyClass)ruby.getClassFromPath("Nokogiri::HTML4::ElementDescription"));
@@ -78,6 +78,7 @@ public class NokogiriService implements BasicLibraryService
private void
init(Ruby ruby)
{
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
RubyModule nokogiri = ruby.defineModule("Nokogiri");
RubyModule xmlModule = nokogiri.defineModuleUnder("XML");
RubyModule xmlSaxModule = xmlModule.defineModuleUnder("SAX");
@@ -97,6 +98,7 @@ public class NokogiriService implements BasicLibraryService
private void
createSyntaxErrors(Ruby ruby, RubyModule nokogiri, RubyModule xmlModule)
{
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
RubyClass syntaxError = nokogiri.defineClassUnder("SyntaxError", ruby.getStandardError(),
ruby.getStandardError().getAllocator());
RubyClass xmlSyntaxError = xmlModule.defineClassUnder("SyntaxError", syntaxError, XML_SYNTAXERROR_ALLOCATOR);
@@ -106,6 +108,7 @@ public class NokogiriService implements BasicLibraryService
private RubyClass
createXmlModule(Ruby ruby, RubyModule xmlModule)
{
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
RubyClass node = xmlModule.defineClassUnder("Node", ruby.getObject(), XML_NODE_ALLOCATOR);
node.defineAnnotatedMethods(XmlNode.class);
@@ -183,6 +186,7 @@ public class NokogiriService implements BasicLibraryService
private void
createHtmlModule(Ruby ruby, RubyModule htmlModule)
{
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
RubyClass htmlElemDesc = htmlModule.defineClassUnder("ElementDescription", ruby.getObject(),
HTML_ELEMENT_DESCRIPTION_ALLOCATOR);
htmlElemDesc.defineAnnotatedMethods(Html4ElementDescription.class);
@@ -195,6 +199,7 @@ public class NokogiriService implements BasicLibraryService
private void
createDocuments(Ruby ruby, RubyModule xmlModule, RubyModule htmlModule, RubyClass node)
{
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
RubyClass xmlDocument = xmlModule.defineClassUnder("Document", node, XML_DOCUMENT_ALLOCATOR);
xmlDocument.defineAnnotatedMethods(XmlDocument.class);
@@ -206,6 +211,7 @@ public class NokogiriService implements BasicLibraryService
private void
createSaxModule(Ruby ruby, RubyModule xmlSaxModule, RubyModule htmlSaxModule)
{
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
RubyClass xmlSaxParserContext = xmlSaxModule.defineClassUnder("ParserContext", ruby.getObject(),
XML_SAXPARSER_CONTEXT_ALLOCATOR);
xmlSaxParserContext.defineAnnotatedMethods(XmlSaxParserContext.class);
@@ -225,6 +231,7 @@ public class NokogiriService implements BasicLibraryService
private void
createXsltModule(Ruby ruby, RubyModule xsltModule)
{
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
RubyClass stylesheet = xsltModule.defineClassUnder("Stylesheet", ruby.getObject(), XSLT_STYLESHEET_ALLOCATOR);
stylesheet.defineAnnotatedMethods(XsltStylesheet.class);
}
@@ -259,21 +266,9 @@ public IRubyObject allocate(Ruby runtime, RubyClass klazz) {
}
};
- private static ObjectAllocator HTML_ELEMENT_DESCRIPTION_ALLOCATOR =
- new ObjectAllocator()
- {
- public IRubyObject allocate(Ruby runtime, RubyClass klazz) {
- return new Html4ElementDescription(runtime, klazz);
- }
- };
+ private static final ObjectAllocator HTML_ELEMENT_DESCRIPTION_ALLOCATOR = Html4ElementDescription::new;
- private static ObjectAllocator HTML_ENTITY_LOOKUP_ALLOCATOR =
- new ObjectAllocator()
- {
- public IRubyObject allocate(Ruby runtime, RubyClass klazz) {
- return new Html4EntityLookup(runtime, klazz);
- }
- };
+ private static final ObjectAllocator HTML_ENTITY_LOOKUP_ALLOCATOR = Html4EntityLookup::new;
public static final ObjectAllocator XML_ATTR_ALLOCATOR = new ObjectAllocator()
{
@@ -486,25 +481,12 @@ public IRubyObject allocate(Ruby runtime, RubyClass klazz) {
}
};
- private static ObjectAllocator XML_ATTRIBUTE_DECL_ALLOCATOR = new ObjectAllocator()
- {
- public IRubyObject allocate(Ruby runtime, RubyClass klazz) {
- return new XmlAttributeDecl(runtime, klazz);
- }
- };
+ private static final ObjectAllocator XML_ATTRIBUTE_DECL_ALLOCATOR = XmlAttributeDecl::new;
- private static ObjectAllocator XML_ENTITY_DECL_ALLOCATOR = new ObjectAllocator()
- {
- public IRubyObject allocate(Ruby runtime, RubyClass klazz) {
- return new XmlEntityDecl(runtime, klazz);
- }
- };
+ private static final ObjectAllocator XML_ENTITY_DECL_ALLOCATOR = XmlEntityDecl::new;
- private static ObjectAllocator XML_ELEMENT_CONTENT_ALLOCATOR = new ObjectAllocator()
- {
- public IRubyObject allocate(Ruby runtime, RubyClass klazz) {
- throw runtime.newNotImplementedError("not implemented");
- }
+ private static final ObjectAllocator XML_ELEMENT_CONTENT_ALLOCATOR = (runtime, klazz) -> {
+ throw runtime.newNotImplementedError("not implemented");
};
public static final ObjectAllocator XML_RELAXNG_ALLOCATOR = new ObjectAllocator()
@@ -537,19 +519,9 @@ public IRubyObject allocate(Ruby runtime, RubyClass klazz) {
}
};
- private static final ObjectAllocator XML_SAXPUSHPARSER_ALLOCATOR = new ObjectAllocator()
- {
- public IRubyObject allocate(Ruby runtime, RubyClass klazz) {
- return new XmlSaxPushParser(runtime, klazz);
- }
- };
+ private static final ObjectAllocator XML_SAXPUSHPARSER_ALLOCATOR = XmlSaxPushParser::new;
- private static final ObjectAllocator HTML_SAXPUSHPARSER_ALLOCATOR = new ObjectAllocator()
- {
- public IRubyObject allocate(Ruby runtime, RubyClass klazz) {
- return new Html4SaxPushParser(runtime, klazz);
- }
- };
+ private static final ObjectAllocator HTML_SAXPUSHPARSER_ALLOCATOR = Html4SaxPushParser::new;
public static final ObjectAllocator XML_SCHEMA_ALLOCATOR = new ObjectAllocator()
{
@@ -566,12 +538,7 @@ public IRubyObject allocate(Ruby runtime, RubyClass klazz) {
}
};
- public static final ObjectAllocator XML_SYNTAXERROR_ALLOCATOR = new ObjectAllocator()
- {
- public IRubyObject allocate(Ruby runtime, RubyClass klazz) {
- return new XmlSyntaxError(runtime, klazz);
- }
- };
+ public static final ObjectAllocator XML_SYNTAXERROR_ALLOCATOR = XmlSyntaxError::new;
public static final ObjectAllocator XML_TEXT_ALLOCATOR = new ObjectAllocator()
{
@@ -588,12 +555,7 @@ public IRubyObject allocate(Ruby runtime, RubyClass klazz) {
}
};
- public static final ObjectAllocator XML_XPATHCONTEXT_ALLOCATOR = new ObjectAllocator()
- {
- public IRubyObject allocate(Ruby runtime, RubyClass klazz) {
- return new XmlXpathContext(runtime, klazz);
- }
- };
+ public static final ObjectAllocator XML_XPATHCONTEXT_ALLOCATOR = XmlXpathContext::new;
public static ObjectAllocator XSLT_STYLESHEET_ALLOCATOR = new ObjectAllocator()
{
diff --git a/ext/java/nokogiri/XmlAttr.java b/ext/java/nokogiri/XmlAttr.java
index 029f6f407f..6273086d8e 100644
--- a/ext/java/nokogiri/XmlAttr.java
+++ b/ext/java/nokogiri/XmlAttr.java
@@ -27,6 +27,8 @@ public class XmlAttr extends XmlNode
{
private static final long serialVersionUID = 1L;
+ // unused
+ @Deprecated
public static final String[] HTML_BOOLEAN_ATTRS = {
"checked", "compact", "declare", "defer", "disabled", "ismap",
"multiple", "nohref", "noresize", "noshade", "nowrap", "readonly",
@@ -45,6 +47,8 @@ public class XmlAttr extends XmlNode
super(ruby, rubyClass);
}
+ // unused
+ @Deprecated
public
XmlAttr(Ruby ruby, RubyClass rubyClass, Node attr)
{
@@ -56,6 +60,7 @@ public class XmlAttr extends XmlNode
init(ThreadContext context, IRubyObject[] args)
{
if (args.length < 2) {
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
throw context.runtime.newArgumentError(args.length, 2);
}
diff --git a/ext/java/nokogiri/XmlAttributeDecl.java b/ext/java/nokogiri/XmlAttributeDecl.java
index 242fc804fd..0b7ffc44e6 100644
--- a/ext/java/nokogiri/XmlAttributeDecl.java
+++ b/ext/java/nokogiri/XmlAttributeDecl.java
@@ -32,7 +32,7 @@ public class XmlAttributeDecl extends XmlNode
/**
* Initialize based on an attributeDecl node from a NekoDTD parsed
* DTD.
- *
+ *
* Internally, XmlAttributeDecl combines these into a single node.
*/
public
@@ -102,17 +102,19 @@ public class XmlAttributeDecl extends XmlNode
{
final String atype = ((Element) node).getAttribute("atype");
- if (atype != null && atype.length() != 0 && atype.charAt(0) == '(') {
+ if (!atype.isEmpty() && atype.charAt(0) == '(') {
// removed enclosing parens
String valueStr = atype.substring(1, atype.length() - 1);
String[] values = valueStr.split("\\|");
RubyArray enumVals = RubyArray.newArray(context.runtime, values.length);
- for (int i = 0; i < values.length; i++) {
- enumVals.append(context.runtime.newString(values[i]));
+ for (String value : values) {
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
+ enumVals.append(context.runtime.newString(value));
}
return enumVals;
}
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
return context.runtime.newEmptyArray();
}
diff --git a/ext/java/nokogiri/XmlCdata.java b/ext/java/nokogiri/XmlCdata.java
index f465a56a9e..719feecca8 100644
--- a/ext/java/nokogiri/XmlCdata.java
+++ b/ext/java/nokogiri/XmlCdata.java
@@ -30,6 +30,8 @@ public class XmlCdata extends XmlText
super(ruby, rubyClass);
}
+ // unused
+ @Deprecated
public
XmlCdata(Ruby ruby, RubyClass rubyClass, Node node)
{
@@ -41,16 +43,19 @@ public class XmlCdata extends XmlText
init(ThreadContext context, IRubyObject[] args)
{
if (args.length < 2) {
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
throw getRuntime().newArgumentError(args.length, 2);
}
IRubyObject rbDocument = args[0];
content = args[1];
if (content.isNil()) {
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
throw context.runtime.newTypeError("expected second parameter to be a String, received NilClass");
}
if (!(rbDocument instanceof XmlNode)) {
String msg = "expected first parameter to be a Nokogiri::XML::Document, received " + rbDocument.getMetaClass();
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
throw context.runtime.newTypeError(msg);
}
if (!(rbDocument instanceof XmlDocument)) {
diff --git a/ext/java/nokogiri/XmlComment.java b/ext/java/nokogiri/XmlComment.java
index f77a91e366..c9f53d6b02 100644
--- a/ext/java/nokogiri/XmlComment.java
+++ b/ext/java/nokogiri/XmlComment.java
@@ -23,6 +23,8 @@ public class XmlComment extends XmlNode
{
private static final long serialVersionUID = 1L;
+ // unused
+ @Deprecated
public
XmlComment(Ruby ruby, RubyClass rubyClass, Node node)
{
@@ -40,6 +42,7 @@ public class XmlComment extends XmlNode
init(ThreadContext context, IRubyObject[] args)
{
if (args.length < 2) {
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
throw getRuntime().newArgumentError(args.length, 2);
}
diff --git a/ext/java/nokogiri/XmlDocument.java b/ext/java/nokogiri/XmlDocument.java
index 033a0c64b8..d2ac592050 100644
--- a/ext/java/nokogiri/XmlDocument.java
+++ b/ext/java/nokogiri/XmlDocument.java
@@ -41,7 +41,6 @@
import nokogiri.internals.SaveContextVisitor;
import nokogiri.internals.XmlDomParserContext;
import nokogiri.internals.c14n.CanonicalFilter;
-import nokogiri.internals.c14n.CanonicalizationException;
import nokogiri.internals.c14n.Canonicalizer;
/**
@@ -71,9 +70,6 @@ public class XmlDocument extends XmlNode
private static final ByteList DOCUMENT = ByteList.create("document");
static { DOCUMENT.setEncoding(USASCIIEncoding.INSTANCE); }
- private static boolean substituteEntities = false;
- private static boolean loadExternalSubset = false; // TODO: Verify this.
-
/** cache variables */
protected IRubyObject encoding;
protected IRubyObject url;
@@ -273,7 +269,7 @@ private static class DocumentBuilderFactoryHolder
*
* Create a new document with +version+ (defaults to "1.0")
*/
- @JRubyMethod(name = "new", meta = true, rest = true, required = 0)
+ @JRubyMethod(name = "new", meta = true, rest = true)
public static IRubyObject
rbNew(ThreadContext context, IRubyObject klazz, IRubyObject[] args)
{
@@ -281,6 +277,7 @@ private static class DocumentBuilderFactoryHolder
XmlDocument xmlDocument;
try {
Document docNode = createNewDocument(runtime);
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
if ("Nokogiri::HTML4::Document".equals(((RubyClass)klazz).getName())) {
xmlDocument = new Html4Document(context.runtime, (RubyClass) klazz, docNode);
} else {
@@ -344,7 +341,6 @@ private static class DocumentBuilderFactoryHolder
public static IRubyObject
load_external_subsets_set(ThreadContext context, IRubyObject cls, IRubyObject value)
{
- XmlDocument.loadExternalSubset = value.isTrue();
return context.nil;
}
@@ -395,8 +391,8 @@ private static class DocumentBuilderFactoryHolder
}
}
IRubyObject[] nodes = xmlNode.getChildren();
- for (int i = 0; i < nodes.length; i++) {
- XmlNode childNode = (XmlNode) nodes[i];
+ for (IRubyObject iRubyObject : nodes) {
+ XmlNode childNode = (XmlNode) iRubyObject;
removeNamespaceRecursively(childNode);
}
}
@@ -471,7 +467,6 @@ private static class DocumentBuilderFactoryHolder
public static IRubyObject
substitute_entities_set(ThreadContext context, IRubyObject cls, IRubyObject value)
{
- XmlDocument.substituteEntities = value.isTrue();
return context.nil;
}
@@ -631,16 +626,18 @@ private static class DocumentBuilderFactoryHolder
{
int mode = 0;
String inclusive_namespace = null;
- Boolean with_comments = false;
+ boolean with_comments = false;
if (args.length > 0 && !(args[0].isNil())) {
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
mode = RubyFixnum.fix2int(args[0]);
}
if (args.length > 1) {
if (!args[1].isNil() && !(args[1] instanceof List)) {
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
throw context.runtime.newTypeError("Expected array");
}
if (!args[1].isNil()) {
- inclusive_namespace = ((RubyArray)args[1])
+ inclusive_namespace = ((RubyArray)args[1])
.join(context, context.runtime.newString(" "))
.asString()
.asJavaString(); // OMG I wish I knew JRuby better, this is ugly
diff --git a/ext/java/nokogiri/XmlDocumentFragment.java b/ext/java/nokogiri/XmlDocumentFragment.java
index 406b3d1d1c..59a8b4fd2c 100644
--- a/ext/java/nokogiri/XmlDocumentFragment.java
+++ b/ext/java/nokogiri/XmlDocumentFragment.java
@@ -1,29 +1,13 @@
package nokogiri;
-import static nokogiri.internals.NokogiriHelpers.getLocalNameForNamespace;
import static nokogiri.internals.NokogiriHelpers.getNokogiriClass;
-import static nokogiri.internals.NokogiriHelpers.getPrefix;
-import static nokogiri.internals.NokogiriHelpers.isNamespace;
-import static nokogiri.internals.NokogiriHelpers.rubyStringToString;
-
-import java.util.HashMap;
-import java.util.Map;
-import java.util.regex.Matcher;
-import java.util.regex.Pattern;
import org.jruby.Ruby;
-import org.jruby.RubyArray;
import org.jruby.RubyClass;
-import org.jruby.RubyString;
import org.jruby.anno.JRubyClass;
import org.jruby.anno.JRubyMethod;
-import org.jruby.runtime.Block;
-import org.jruby.runtime.Helpers;
import org.jruby.runtime.ThreadContext;
import org.jruby.runtime.builtin.IRubyObject;
-import org.jruby.util.ByteList;
-import org.w3c.dom.Attr;
-import org.w3c.dom.NamedNodeMap;
/**
* Class for Nokogiri::XML::DocumentFragment
@@ -36,6 +20,8 @@ public class XmlDocumentFragment extends XmlNode
{
private static final long serialVersionUID = 1L;
+ // unused
+ @Deprecated
public
XmlDocumentFragment(Ruby ruby)
{
diff --git a/ext/java/nokogiri/XmlDtd.java b/ext/java/nokogiri/XmlDtd.java
index 7dc96c1316..3417872133 100644
--- a/ext/java/nokogiri/XmlDtd.java
+++ b/ext/java/nokogiri/XmlDtd.java
@@ -138,7 +138,7 @@ public class XmlDtd extends XmlNode
* doc. The attached dtd must be the tree from
* NekoDTD. The owner document of the returned tree will be
* doc.
- *
+ *
* NekoDTD parser returns a new document node containing elements
* representing the dtd declarations. The plan is to get the root
* element and adopt it into the correct document, stripping the
@@ -332,6 +332,7 @@ public class XmlDtd extends XmlNode
public IRubyObject
validate(ThreadContext context, IRubyObject doc)
{
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
RubyArray errors = RubyArray.newArray(context.getRuntime());
if (doc instanceof XmlDocument) {
errors = (RubyArray)((XmlDocument)doc).getInstanceVariable("@errors");
@@ -450,7 +451,7 @@ public class XmlDtd extends XmlNode
* The node is either the first child of the root dtd
* node (as returned by getInternalSubset()) or the first child of
* the external subset node (as returned by getExternalSubset()).
- *
+ *
* This recursive function will not descend into an
* 'externalSubset' node, thus for an internal subset it only
* extracts nodes in the internal subset, and for an external
@@ -460,7 +461,7 @@ public class XmlDtd extends XmlNode
protected IRubyObject[]
extractDecls(ThreadContext context, Node node)
{
- List decls = new ArrayList();
+ List decls = new ArrayList<>();
while (node != null) {
if (isExternalSubset(node)) {
break;
diff --git a/ext/java/nokogiri/XmlElement.java b/ext/java/nokogiri/XmlElement.java
index b8e3225edc..5bcb76f754 100644
--- a/ext/java/nokogiri/XmlElement.java
+++ b/ext/java/nokogiri/XmlElement.java
@@ -4,7 +4,6 @@
import org.jruby.RubyClass;
import org.jruby.anno.JRubyClass;
import org.jruby.runtime.ThreadContext;
-import org.jruby.runtime.builtin.IRubyObject;
import org.w3c.dom.Element;
import org.w3c.dom.Node;
@@ -27,6 +26,8 @@ public class XmlElement extends XmlNode
super(runtime, klazz);
}
+ // unused
+ @Deprecated
public
XmlElement(Ruby runtime, RubyClass klazz, Node element)
{
diff --git a/ext/java/nokogiri/XmlElementContent.java b/ext/java/nokogiri/XmlElementContent.java
index 501a4557be..d2921467e5 100644
--- a/ext/java/nokogiri/XmlElementContent.java
+++ b/ext/java/nokogiri/XmlElementContent.java
@@ -325,7 +325,7 @@ public IRubyObject value(Ruby runtime)
* moves to the parent of previous sibling). The null position is
* used to indicate the end of a list.
*/
- protected static class NodeIter
+ public static class NodeIter
{
protected Node pre;
protected Node cur;
diff --git a/ext/java/nokogiri/XmlElementDecl.java b/ext/java/nokogiri/XmlElementDecl.java
index bd4bc8cf25..a67b4a75ed 100644
--- a/ext/java/nokogiri/XmlElementDecl.java
+++ b/ext/java/nokogiri/XmlElementDecl.java
@@ -31,6 +31,7 @@ public class XmlElementDecl extends XmlNode
XmlElementDecl(Ruby runtime, RubyClass klazz)
{
super(runtime, klazz);
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
attrDecls = RubyArray.newArray(runtime);
contentModel = runtime.getNil();
}
@@ -49,6 +50,7 @@ public class XmlElementDecl extends XmlNode
setNode(Ruby runtime, Node node)
{
super.setNode(runtime, node);
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
attrDecls = RubyArray.newArray(runtime);
contentModel = runtime.getNil();
}
@@ -136,6 +138,7 @@ public class XmlElementDecl extends XmlNode
public void
appendAttrDecl(XmlAttributeDecl decl)
{
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
attrDecls.append(decl);
}
diff --git a/ext/java/nokogiri/XmlEntityReference.java b/ext/java/nokogiri/XmlEntityReference.java
index 77db5ddb2c..c32ae5ba59 100644
--- a/ext/java/nokogiri/XmlEntityReference.java
+++ b/ext/java/nokogiri/XmlEntityReference.java
@@ -1,6 +1,5 @@
package nokogiri;
-import static nokogiri.internals.NokogiriHelpers.getCachedNodeOrCreate;
import static nokogiri.internals.NokogiriHelpers.rubyStringToString;
import nokogiri.internals.SaveContextVisitor;
@@ -31,6 +30,8 @@ public class XmlEntityReference extends XmlNode
super(ruby, klazz);
}
+ // unused
+ @Deprecated
public
XmlEntityReference(Ruby ruby, RubyClass klass, Node node)
{
@@ -41,6 +42,7 @@ public class XmlEntityReference extends XmlNode
init(ThreadContext context, IRubyObject[] args)
{
if (args.length < 2) {
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
throw context.runtime.newArgumentError(args.length, 2);
}
diff --git a/ext/java/nokogiri/XmlNamespace.java b/ext/java/nokogiri/XmlNamespace.java
index b2804bb7bc..030cfac529 100644
--- a/ext/java/nokogiri/XmlNamespace.java
+++ b/ext/java/nokogiri/XmlNamespace.java
@@ -106,7 +106,8 @@ public class XmlNamespace extends RubyObject
Document document = owner.getOwnerDocument();
XmlDocument xmlDocument = (XmlDocument) getCachedNodeOrCreate(runtime, document);
- assert xmlDocument.getNamespaceCache().get(prefixStr, hrefStr) == null;
+ XmlNamespace cachedNamespace = xmlDocument.getNamespaceCache().get(prefixStr, hrefStr);
+ assert cachedNamespace == null;
// creating XmlNamespace instance
String attrName = "xmlns";
diff --git a/ext/java/nokogiri/XmlNode.java b/ext/java/nokogiri/XmlNode.java
index c74650cd6b..3386301688 100644
--- a/ext/java/nokogiri/XmlNode.java
+++ b/ext/java/nokogiri/XmlNode.java
@@ -1,10 +1,7 @@
package nokogiri;
-import static java.lang.Math.max;
import static nokogiri.internals.NokogiriHelpers.*;
-import java.io.ByteArrayInputStream;
-import java.io.InputStream;
import java.nio.ByteBuffer;
import java.nio.charset.Charset;
import java.util.*;
@@ -16,12 +13,10 @@
import org.jruby.RubyClass;
import org.jruby.RubyFixnum;
import org.jruby.RubyInteger;
-import org.jruby.RubyModule;
import org.jruby.RubyObject;
import org.jruby.RubyString;
import org.jruby.anno.JRubyClass;
import org.jruby.anno.JRubyMethod;
-import org.jruby.exceptions.RaiseException;
import org.jruby.runtime.Block;
import org.jruby.runtime.Helpers;
import org.jruby.runtime.ThreadContext;
@@ -89,6 +84,7 @@ public class XmlNode extends RubyObject
{
if (!(node instanceof XmlNode)) {
final Ruby runtime = context.runtime;
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
throw runtime.newTypeError(node == null ? runtime.getNil() : node, getNokogiriClass(runtime, "Nokogiri::XML::Node"));
}
return (XmlNode) node;
@@ -107,7 +103,7 @@ public class XmlNode extends RubyObject
/**
* Coalesce to adjacent TextNodes.
- * @param context
+ * @param context The current context
* @param prev Previous node to cur.
* @param cur Next node to prev.
*/
@@ -132,13 +128,14 @@ public class XmlNode extends RubyObject
* are text nodes, the content will be merged into
* anchorNode and the redundant nodes will be removed
* from the DOM.
- *
+ *
* To match libxml behavior (?) the final content of
* anchorNode and any removed nodes will be
* identical.
*
- * @param context
- * @param anchorNode
+ * @param context the current context
+ * @param anchorNode the anchor node
+ * @param scheme the scheme
*/
protected static void
coalesceTextNodes(ThreadContext context,
@@ -230,18 +227,18 @@ public class XmlNode extends RubyObject
* object as the only argument. If cls is
* Nokogiri::XML::Node, creates a new Nokogiri::XML::Element
* instead.
- *
+ *
* This static method seems to be inherited, strangely enough.
* E.g. creating a new XmlAttr from Ruby code calls this method if
* XmlAttr does not define its own 'new' method.
- *
+ *
* Since there is some Java bookkeeping that always needs to
* happen, we don't define the 'initialize' method in Java because
* we'd have to count on subclasses calling 'super'.
- *
+ *
* The main consequence of this is that every subclass needs to
* define its own 'new' method.
- *
+ *
* As a convenience, this method does the following:
*
*
@@ -269,10 +266,12 @@ public class XmlNode extends RubyObject
Ruby ruby = context.runtime;
RubyClass klazz = (RubyClass) cls;
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
if ("Nokogiri::XML::Node".equals(klazz.getName())) {
klazz = getNokogiriClass(ruby, "Nokogiri::XML::Element");
}
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
XmlNode xmlNode = (XmlNode) klazz.allocate();
xmlNode.init(context, args);
xmlNode.callInit(args, block);
@@ -289,7 +288,7 @@ public class XmlNode extends RubyObject
* interact means that subclasses cannot arbitrarily change the
* require arguments by defining an 'initialize' method. This is
* how the C libxml wrapper works also.
- *
+ *
* As written it performs initialization for a new Element with
* the given name within the document
* doc. So XmlElement need not override this. This
@@ -301,6 +300,7 @@ public class XmlNode extends RubyObject
init(ThreadContext context, IRubyObject[] args)
{
if (args.length < 2) {
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
throw context.runtime.newArgumentError(args.length, 2);
}
@@ -366,17 +366,19 @@ public class XmlNode extends RubyObject
public boolean
isElement()
{
- if (node instanceof Element) { return true; } // in case of subclassing
- else { return false; }
+ // in case of subclassing
+ return node instanceof Element;
}
+ // unused
+ @Deprecated
public boolean
isProcessingInstruction() { return false; }
/**
* Return the string value of the attribute key or
* nil.
- *
+ *
* Only applies where the underlying Node is an Element node, but
* implemented here in XmlNode because not all nodes with
* underlying Element nodes subclass XmlElement, such as the DTD
@@ -401,7 +403,7 @@ public class XmlNode extends RubyObject
if (node.getNodeType() != Node.ELEMENT_NODE) { return null; }
String value = ((Element)node).getAttribute(key);
- return value.length() == 0 ? null : value;
+ return value.isEmpty() ? null : value;
}
/**
@@ -438,25 +440,24 @@ public class XmlNode extends RubyObject
if (ns_inherit.isTrue()) {
set_namespace(context, ((XmlNode)parent(context)).namespace(context));
}
- return;
- }
-
- String currentPrefix = e.getParentNode().lookupPrefix(nsURI);
- String currentURI = e.getParentNode().lookupNamespaceURI(prefix);
- boolean isDefault = e.getParentNode().isDefaultNamespace(nsURI);
-
- // add xmlns attribute if this is a new root node or if the node's
- // namespace isn't a default namespace in the new document
- if (e.getParentNode().getNodeType() == Node.DOCUMENT_NODE) {
- // this is the root node, so we must set the namespaces attributes anyway
- e.setAttribute(prefix == null ? "xmlns" : "xmlns:" + prefix, nsURI);
- } else if (prefix == null) {
- // this is a default namespace but isn't the default where this node is being added
- if (!isDefault) { e.setAttribute("xmlns", nsURI); }
- } else if (!prefix.equals(currentPrefix) || nsURI.equals(currentURI)) {
- // this is a prefixed namespace
- // but doesn't have the same prefix or the prefix is set to a different URI
- e.setAttribute("xmlns:" + prefix, nsURI);
+ } else {
+ String currentPrefix = e.getParentNode().lookupPrefix(nsURI);
+ String currentURI = e.getParentNode().lookupNamespaceURI(prefix);
+ boolean isDefault = e.getParentNode().isDefaultNamespace(nsURI);
+
+ // add xmlns attribute if this is a new root node or if the node's
+ // namespace isn't a default namespace in the new document
+ if (e.getParentNode().getNodeType() == Node.DOCUMENT_NODE) {
+ // this is the root node, so we must set the namespaces attributes anyway
+ e.setAttribute(prefix == null ? "xmlns" : "xmlns:" + prefix, nsURI);
+ } else if (prefix == null) {
+ // this is a default namespace but isn't the default where this node is being added
+ if (!isDefault) { e.setAttribute("xmlns", nsURI); }
+ } else if (!prefix.equals(currentPrefix) || !nsURI.equals(currentURI)) {
+ // this is a prefixed namespace
+ // but doesn't have the same prefix or the prefix is set to a different URI
+ e.setAttribute("xmlns:" + prefix, nsURI);
+ }
}
if (e.hasAttributes()) {
@@ -482,7 +483,7 @@ public class XmlNode extends RubyObject
nsUri = null;
}
- if (!(nsUri == null || "".equals(nsUri) || "http://www.w3.org/XML/1998/namespace".equals(nsUri))) {
+ if (!(nsUri == null || nsUri.isEmpty() || "http://www.w3.org/XML/1998/namespace".equals(nsUri))) {
// Create a new namespace object and add it to the document namespace cache.
// TODO: why do we need the namespace cache ?
XmlNamespace.createFromAttr(context.runtime, attr);
@@ -491,6 +492,32 @@ public class XmlNode extends RubyObject
}
}
+ // if this namespace is a duplicate of what's already in the document, remove it.
+ // a "duplicate" here is if the prefix and the URI both match what resolves in the parent.
+ if (e.getParentNode().getNodeType() == Node.ELEMENT_NODE) {
+ RubyArray nsdefs = this.namespace_definitions(context);
+ for (int j = 0 ; j < nsdefs.getLength() ; j++) {
+ XmlNamespace ns = (XmlNamespace)nsdefs.get(j);
+
+ String selfPrefix = ns.getPrefix();
+ String selfURI = ns.getHref();
+ String parentPrefix = e.getParentNode().lookupPrefix(selfURI);
+ String parentURI = e.getParentNode().lookupNamespaceURI(selfPrefix);
+
+ boolean prefixMatch = ((selfPrefix == null && parentPrefix == null) ||
+ (selfPrefix != null && selfPrefix.equals(parentPrefix)));
+ boolean uriMatch = ((selfURI == null && parentURI == null) ||
+ (selfURI != null && selfURI.equals(parentURI)));
+
+ if (prefixMatch && uriMatch) {
+ String attrName = "xmlns";
+ if (selfPrefix != null && !selfPrefix.isEmpty()) { attrName = attrName + ':' + selfPrefix; }
+
+ e.removeAttribute(attrName);
+ }
+ }
+ }
+
if (this.node.hasChildNodes()) {
relink_namespace(context, getChildren());
}
@@ -499,9 +526,9 @@ public class XmlNode extends RubyObject
static void
relink_namespace(ThreadContext context, IRubyObject[] nodes)
{
- for (int i = 0; i < nodes.length; i++) {
- if (nodes[i] instanceof XmlNode) {
- ((XmlNode) nodes[i]).relink_namespace(context);
+ for (IRubyObject iRubyObject : nodes) {
+ if (iRubyObject instanceof XmlNode) {
+ ((XmlNode) iRubyObject).relink_namespace(context);
}
}
}
@@ -519,8 +546,7 @@ public class XmlNode extends RubyObject
acceptChildren(ThreadContext context, IRubyObject[] nodes, SaveContextVisitor visitor)
{
if (nodes.length > 0) {
- for (int i = 0; i < nodes.length; i++) {
- Object item = nodes[i];
+ for (Object item : nodes) {
if (item instanceof XmlNode) {
((XmlNode) item).accept(context, visitor);
} else if (item instanceof XmlNamespace) {
@@ -652,7 +678,7 @@ public class XmlNode extends RubyObject
Node attribute = attributes.item(j);
String localName = attribute.getLocalName();
if (localName == null) {
- continue;
+ localName = attribute.getNodeName();
}
if (localName.equals(name)) {
return getCachedNodeOrCreate(context.runtime, attribute);
@@ -669,12 +695,14 @@ public class XmlNode extends RubyObject
NamedNodeMap nodeMap = this.node.getAttributes();
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
if (nodeMap == null) { return runtime.newEmptyArray(); }
RubyArray attr = runtime.newArray(nodeMap.getLength());
final XmlDocument doc = document(context.runtime);
for (int i = 0; i < nodeMap.getLength(); i++) {
if ((doc instanceof Html4Document) || !NokogiriHelpers.isNamespace(nodeMap.item(i))) {
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
attr.append(getCachedNodeOrCreate(runtime, nodeMap.item(i)));
}
}
@@ -742,7 +770,7 @@ public class XmlNode extends RubyObject
first_element_child(ThreadContext context)
{
List elementNodes = getElements(node, true);
- if (elementNodes.size() == 0) { return context.nil; }
+ if (elementNodes.isEmpty()) { return context.nil; }
return getCachedNodeOrCreate(context.runtime, elementNodes.get(0));
}
@@ -751,7 +779,7 @@ public class XmlNode extends RubyObject
last_element_child(ThreadContext context)
{
List elementNodes = getElements(node, false);
- if (elementNodes.size() == 0) { return context.nil; }
+ if (elementNodes.isEmpty()) { return context.nil; }
return getCachedNodeOrCreate(context.runtime, elementNodes.get(elementNodes.size() - 1));
}
@@ -771,7 +799,7 @@ public class XmlNode extends RubyObject
if (children.getLength() == 0) {
return Collections.emptyList();
}
- ArrayList elements = new ArrayList();
+ ArrayList elements = new ArrayList<>();
for (int i = 0; i < children.getLength(); i++) {
Node child = children.item(i);
if (child.getNodeType() == Node.ELEMENT_NODE) {
@@ -833,7 +861,6 @@ public class XmlNode extends RubyObject
{
RubyClass klass;
XmlDomParserContext ctx;
- InputStream istream;
final Ruby runtime = context.runtime;
@@ -864,6 +891,7 @@ public class XmlNode extends RubyObject
RubyArray docErrors = getErrors(doc);
if (checkNewErrors(documentErrors, docErrors)) {
for (int i = 0; i < docErrors.getLength(); i++) {
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
documentErrors.append(docErrors.entry(i));
}
document.setInstanceVariable("@errors", documentErrors);
@@ -887,14 +915,15 @@ public class XmlNode extends RubyObject
getErrors(XmlDocument document)
{
IRubyObject obj = document.getInstanceVariable("@errors");
- if (obj instanceof RubyArray) { return (RubyArray) obj; }
+ if (obj instanceof RubyArray) { return (RubyArray) obj; }
return RubyArray.newEmptyArray(document.getRuntime());
}
private static boolean
checkNewErrors(RubyArray baseErrors, RubyArray newErrors)
{
- int length = ((RubyArray) newErrors.op_diff(baseErrors)).size();
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
+ int length = ((RubyArray) newErrors.op_diff(baseErrors)).size();
return length > 0;
}
@@ -980,6 +1009,7 @@ public class XmlNode extends RubyObject
public IRubyObject
initialize_copy_with_args(ThreadContext context, IRubyObject other, IRubyObject level, IRubyObject document)
{
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
boolean deep = level instanceof RubyInteger && RubyFixnum.fix2int(level) != 0;
this.node = asXmlNode(context, other).node.cloneNode(deep);
setDocument(context, (XmlDocument)document);
@@ -1049,8 +1079,7 @@ public class XmlNode extends RubyObject
XmlDocument xdoc =
(XmlDocument) getCachedNodeOrCreate(context.getRuntime(), document);
- IRubyObject xdtd = xdoc.getInternalSubset(context);
- return xdtd;
+ return xdoc.getInternalSubset(context);
}
@JRubyMethod
@@ -1072,9 +1101,8 @@ public class XmlNode extends RubyObject
XmlDocument xdoc =
(XmlDocument) getCachedNodeOrCreate(context.getRuntime(), document);
- IRubyObject xdtd = xdoc.createInternalSubset(context, name,
+ return xdoc.createInternalSubset(context, name,
external_id, system_id);
- return xdtd;
}
@JRubyMethod
@@ -1089,8 +1117,7 @@ public class XmlNode extends RubyObject
XmlDocument xdoc =
(XmlDocument) getCachedNodeOrCreate(context.getRuntime(), document);
- IRubyObject xdtd = xdoc.getExternalSubset(context);
- return xdtd;
+ return xdoc.getExternalSubset(context);
}
@JRubyMethod
@@ -1110,8 +1137,7 @@ public class XmlNode extends RubyObject
return context.getRuntime().getNil();
}
XmlDocument xdoc = (XmlDocument) getCachedNodeOrCreate(context.getRuntime(), document);
- IRubyObject xdtd = xdoc.createExternalSubset(context, name, external_id, system_id);
- return xdtd;
+ return xdoc.createExternalSubset(context, name, external_id, system_id);
}
/**
@@ -1175,28 +1201,23 @@ public class XmlNode extends RubyObject
public RubyArray
namespace_definitions(ThreadContext context)
{
- // don't use namespace_definitions cache anymore since
- // namespaces might be deleted. Reflecting the result of
- // namespace removals is complicated, so the cache might not be
- // updated.
+ // don't use namespace_definitions cache anymore since namespaces might be deleted. Reflecting
+ // the result of namespace removals is complicated, so the cache might not be updated.
final XmlDocument doc = document(context.runtime);
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
if (doc == null) { return context.runtime.newEmptyArray(); }
if (doc instanceof Html4Document) { return context.runtime.newEmptyArray(); }
- List namespaces = doc.getNamespaceCache().get(node);
- return RubyArray.newArray(context.runtime, namespaces);
-
- // // TODO: I think this implementation would be better but there are edge cases
- // // See https://github.com/sparklemotion/nokogiri/issues/2543
- // RubyArray nsdefs = RubyArray.newArray(context.getRuntime());
- // NamedNodeMap attrs = node.getAttributes();
- // for (int j = 0 ; j < attrs.getLength() ; j++) {
- // Attr attr = (Attr)attrs.item(j);
- // if ("http://www.w3.org/2000/xmlns/" == attr.getNamespaceURI()) {
- // nsdefs.append(XmlNamespace.createFromAttr(context.getRuntime(), attr));
- // }
- // }
- // return nsdefs;
+ RubyArray nsdefs = RubyArray.newArray(context.getRuntime());
+ NamedNodeMap attrs = node.getAttributes();
+ for (int j = 0 ; j < attrs.getLength() ; j++) {
+ Attr attr = (Attr)attrs.item(j);
+ if ("http://www.w3.org/2000/xmlns/".equals(attr.getNamespaceURI())) {
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
+ nsdefs.append(XmlNamespace.createFromAttr(context.getRuntime(), attr));
+ }
+ }
+ return nsdefs;
}
/**
@@ -1208,6 +1229,7 @@ public class XmlNode extends RubyObject
namespace_scopes(ThreadContext context)
{
final XmlDocument doc = document(context.runtime);
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
if (doc == null) { return context.runtime.newEmptyArray(); }
if (doc instanceof Html4Document) { return context.runtime.newEmptyArray(); }
@@ -1219,6 +1241,8 @@ public class XmlNode extends RubyObject
} else {
previousNode = findPreviousElement(node);
}
+
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
if (previousNode == null) { return context.runtime.newEmptyArray(); }
final RubyArray scoped_namespaces = context.runtime.newArray();
@@ -1228,6 +1252,7 @@ public class XmlNode extends RubyObject
List namespaces = nsCache.get(previous);
for (XmlNamespace namespace : namespaces) {
if (prefixes_in_scope.contains(namespace.getPrefix())) { continue; }
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
scoped_namespaces.append(namespace);
prefixes_in_scope.add(namespace.getPrefix());
}
@@ -1261,7 +1286,7 @@ public class XmlNode extends RubyObject
{
String javaContent = rubyStringToString(content);
node.setTextContent(javaContent);
- if (javaContent == null || javaContent.length() == 0) { return; }
+ if (javaContent == null || javaContent.isEmpty()) { return; }
if (node.getNodeType() == Node.TEXT_NODE || node.getNodeType() == Node.CDATA_SECTION_NODE) { return; }
if (node.getFirstChild() != null) {
node.getFirstChild().setUserData(NokogiriHelpers.ENCODED_STRING, true, null);
@@ -1321,6 +1346,7 @@ public class XmlNode extends RubyObject
IRubyObject encoding = args[1];
IRubyObject indentString = args[2];
IRubyObject options_rb = args[3];
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
int options = RubyFixnum.fix2int(options_rb);
String encString = rubyStringToString(encoding);
@@ -1361,8 +1387,7 @@ public class XmlNode extends RubyObject
isFragment()
{
if (node instanceof DocumentFragment) { return true; }
- if (node.getParentNode() != null && node.getParentNode() instanceof DocumentFragment) { return true; }
- return false;
+ return node.getParentNode() != null && node.getParentNode() instanceof DocumentFragment;
}
@JRubyMethod(name = {"next_sibling", "next"})
@@ -1588,6 +1613,7 @@ public class XmlNode extends RubyObject
return context.runtime.newFixnum(0);
}
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
return getNokogiriClass(context.runtime, "Nokogiri::XML::Node").getConstant(type);
}
@@ -1837,7 +1863,7 @@ protected enum AdoptScheme {
parentNode.replaceChild(otherNode, thisNode);
} catch (Exception e) {
String prefix = "could not replace child: ";
- throw context.runtime.newRuntimeError(prefix + e.toString());
+ throw context.runtime.newRuntimeError(prefix + e);
}
}
@@ -1894,7 +1920,7 @@ protected enum AdoptScheme {
process_xincludes(ThreadContext context, IRubyObject options)
{
XmlDocument xmlDocument = (XmlDocument)document(context);
- RubyArray errors = (RubyArray)xmlDocument.getInstanceVariable("@errors");
+ RubyArray errors = (RubyArray)xmlDocument.getInstanceVariable("@errors");
while (errors.getLength() > 0) {
XmlSyntaxError error = (XmlSyntaxError)errors.shift(context);
if (error.toString().contains("Include operation failed")) {
diff --git a/ext/java/nokogiri/XmlNodeSet.java b/ext/java/nokogiri/XmlNodeSet.java
index bdb5a06e0e..080ae6eda7 100644
--- a/ext/java/nokogiri/XmlNodeSet.java
+++ b/ext/java/nokogiri/XmlNodeSet.java
@@ -2,7 +2,6 @@
import static nokogiri.XmlNode.setDocumentAndDecorate;
import static nokogiri.internals.NokogiriHelpers.getNokogiriClass;
-import static nokogiri.internals.NokogiriHelpers.nodeListToRubyArray;
import java.util.Arrays;
@@ -151,11 +150,9 @@ public class XmlNodeSet extends RubyObject implements NodeList
int last = 0;
outer:
- for (int i = 0; i < curr.length; i++) {
- IRubyObject n = curr[i];
-
- for (int j = 0; j < other.length; j++) {
- if (other[j] == n) {
+ for (IRubyObject n : curr) {
+ for (IRubyObject iRubyObject : other) {
+ if (iRubyObject == n) {
result[last++] = n;
continue outer;
}
@@ -182,9 +179,7 @@ public class XmlNodeSet extends RubyObject implements NodeList
int last = 0;
- for (int i = 0; i < orig.length; i++) {
- IRubyObject n = orig[i];
-
+ for (IRubyObject n : orig) {
if (n == nodeOrNamespace) {
continue;
}
@@ -223,8 +218,8 @@ public class XmlNodeSet extends RubyObject implements NodeList
public IRubyObject
include_p(ThreadContext context, IRubyObject node_or_namespace)
{
- for (int i = 0; i < nodes.length; i++) {
- if (nodes[i] == node_or_namespace) {
+ for (IRubyObject node : nodes) {
+ if (node == node_or_namespace) {
return context.tru;
}
}
@@ -259,11 +254,9 @@ public class XmlNodeSet extends RubyObject implements NodeList
int last = 0;
outer:
- for (int i = 0; i < curr.length; i++) {
- IRubyObject n = curr[i];
-
- for (int j = 0; j < other.length; j++) {
- if (other[j] == n) {
+ for (IRubyObject n : curr) {
+ for (IRubyObject iRubyObject : other) {
+ if (iRubyObject == n) {
continue outer;
}
}
@@ -283,6 +276,8 @@ public class XmlNodeSet extends RubyObject implements NodeList
IRubyObject[] otherNodes = getNodes(context, nodeSet);
if (nodes.length == 0) {
+ // TODO: switch to interface method when it has been in 9.4 for a year.
+ // The "useless" cast here on JRuby 10 is necessary on 9.4 for now.
return ((XmlNodeSet) nodeSet).dup(context);
}
@@ -296,11 +291,9 @@ public class XmlNodeSet extends RubyObject implements NodeList
int last = curr.length;
outer:
- for (int i = 0; i < other.length; i++) {
- IRubyObject n = other[i];
-
- for (int j = 0; j < curr.length; j++) {
- if (curr[j] == n) {
+ for (IRubyObject n : other) {
+ for (IRubyObject iRubyObject : curr) {
+ if (iRubyObject == n) {
continue outer;
}
}
@@ -329,6 +322,7 @@ public class XmlNodeSet extends RubyObject implements NodeList
rangeBeginLength(ThreadContext context, IRubyObject rangeMaybe, int len, int[] begLen)
{
RubyRange range = (RubyRange) rangeMaybe;
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
int min = range.begin(context).convertToInteger().getIntValue();
int max = range.end(context).convertToInteger().getIntValue();
@@ -358,6 +352,7 @@ public class XmlNodeSet extends RubyObject implements NodeList
slice(ThreadContext context, IRubyObject indexOrRange)
{
if (indexOrRange instanceof RubyFixnum) {
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
return slice(context, ((RubyFixnum) indexOrRange).getIntValue());
}
if (indexOrRange instanceof RubyRange) {
@@ -367,6 +362,7 @@ public class XmlNodeSet extends RubyObject implements NodeList
int max = begLen[1];
return subseq(context, min, max - min);
}
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
throw context.runtime.newTypeError("index must be an Integer or a Range");
}
@@ -388,6 +384,7 @@ public class XmlNodeSet extends RubyObject implements NodeList
public IRubyObject
slice(ThreadContext context, IRubyObject start, IRubyObject length)
{
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
int s = ((RubyFixnum) start).getIntValue();
int l = ((RubyFixnum) length).getIntValue();
@@ -422,6 +419,7 @@ public class XmlNodeSet extends RubyObject implements NodeList
public RubyArray
to_a(ThreadContext context)
{
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
return context.runtime.newArrayNoCopy(nodes);
}
diff --git a/ext/java/nokogiri/XmlProcessingInstruction.java b/ext/java/nokogiri/XmlProcessingInstruction.java
index fc41098b39..ab0a80ed02 100644
--- a/ext/java/nokogiri/XmlProcessingInstruction.java
+++ b/ext/java/nokogiri/XmlProcessingInstruction.java
@@ -65,6 +65,8 @@ public class XmlProcessingInstruction extends XmlNode
return self;
}
+ // unused
+ @Deprecated
@Override
public boolean
isProcessingInstruction() { return true; }
diff --git a/ext/java/nokogiri/XmlReader.java b/ext/java/nokogiri/XmlReader.java
index 74ef72d631..1531b7ffdd 100644
--- a/ext/java/nokogiri/XmlReader.java
+++ b/ext/java/nokogiri/XmlReader.java
@@ -93,7 +93,7 @@ public class XmlReader extends RubyObject
public void
init(Ruby runtime)
{
- nodeQueue = new LinkedList();
+ nodeQueue = new LinkedList<>();
nodeQueue.add(new ReaderNode.EmptyNode(runtime));
}
@@ -181,8 +181,8 @@ public class XmlReader extends RubyObject
ensureNodeClosed(context);
if (readerNode == null) { return context.getRuntime().getNil(); }
- if (!(readerNode instanceof ElementNode)) { context.getRuntime().getFalse(); }
- return RubyBoolean.newBoolean(context.getRuntime(), !readerNode.hasChildren);
+ if (!(readerNode instanceof ElementNode)) { return context.getRuntime().getFalse(); }
+ return RubyBoolean.newBoolean(context, !readerNode.hasChildren);
}
@JRubyMethod
@@ -210,6 +210,7 @@ public class XmlReader extends RubyObject
"Nokogiri::XML::Reader"));
reader.init(runtime);
reader.setInstanceVariable("@source", args[0]);
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
reader.setInstanceVariable("@errors", runtime.newArray());
IRubyObject url = context.nil;
if (args.length > 1) { url = args[1]; }
@@ -241,6 +242,7 @@ public class XmlReader extends RubyObject
"Nokogiri::XML::Reader"));
reader.init(runtime);
reader.setInstanceVariable("@source", args[0]);
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
reader.setInstanceVariable("@errors", runtime.newArray());
IRubyObject url = context.nil;
if (args.length > 1) { url = args[1]; }
@@ -280,7 +282,7 @@ public class XmlReader extends RubyObject
{
if (current.depth < 0) { return null; }
if (!current.hasChildren) { return null; }
- StringBuffer sb = new StringBuffer();
+ StringBuilder sb = new StringBuilder();
for (int i = current.startOffset + 1; i <= current.endOffset - 1; i++) {
sb.append(nodeQueue.get(i).getString());
}
@@ -396,8 +398,9 @@ public class XmlReader extends RubyObject
final ReaderNode currentNode = currentNode();
if (currentNode == null) { return runtime.getNil(); }
if (currentNode.isError()) {
- RubyArray errors = (RubyArray) getInstanceVariable("@errors");
+ RubyArray errors = (RubyArray) getInstanceVariable("@errors");
IRubyObject error = currentNode.toSyntaxError();
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
errors.append(error);
setInstanceVariable("@errors", errors);
@@ -492,9 +495,9 @@ private class DocumentHandler extends DefaultXMLDocumentHandler implements XMLEr
startDocument(XMLLocator locator, String encoding, NamespaceContext context, Augmentations augs)
{
depth = 0;
- langStack = new Stack();
- xmlBaseStack = new Stack();
- elementStack = new Stack();
+ langStack = new Stack<>();
+ xmlBaseStack = new Stack<>();
+ elementStack = new Stack<>();
}
@Override
@@ -552,7 +555,7 @@ private class DocumentHandler extends DefaultXMLDocumentHandler implements XMLEr
String qName = element.rawname;
String uri = element.uri;
String localName = element.localpart;
- ReaderNode readerNode = ReaderNode.createElementNode(ruby, uri, localName, qName, attrs, depth, langStack,
+ ElementNode readerNode = ReaderNode.createElementNode(ruby, uri, localName, qName, attrs, depth, langStack,
xmlBaseStack);
if (!elementStack.isEmpty()) {
ElementNode parent = elementStack.peek();
@@ -564,7 +567,7 @@ private class DocumentHandler extends DefaultXMLDocumentHandler implements XMLEr
depth++;
if (readerNode.lang != null) { langStack.push(readerNode.lang); }
if (readerNode.xmlBase != null) { xmlBaseStack.push(readerNode.xmlBase); }
- elementStack.push((ReaderNode.ElementNode)readerNode);
+ elementStack.push(readerNode);
} else {
readerNode.endOffset = readerNode.startOffset;
readerNode.hasChildren = false;
diff --git a/ext/java/nokogiri/XmlRelaxng.java b/ext/java/nokogiri/XmlRelaxng.java
index eee9113a65..ed8f5a0a18 100644
--- a/ext/java/nokogiri/XmlRelaxng.java
+++ b/ext/java/nokogiri/XmlRelaxng.java
@@ -1,15 +1,12 @@
package nokogiri;
-import static nokogiri.internals.NokogiriHelpers.getNokogiriClass;
-
import java.io.ByteArrayInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.StringWriter;
-import java.io.UnsupportedEncodingException;
+import java.nio.charset.StandardCharsets;
import javax.xml.transform.Source;
-import javax.xml.transform.TransformerConfigurationException;
import javax.xml.transform.TransformerException;
import javax.xml.transform.TransformerFactory;
import javax.xml.transform.dom.DOMSource;
@@ -63,6 +60,7 @@ public class XmlRelaxng extends XmlSchema
parseOptions = defaultParseOptions(context.getRuntime());
}
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
xmlRelaxng.setInstanceVariable("@errors", runtime.newEmptyArray());
xmlRelaxng.setInstanceVariable("@parse_options", parseOptions);
@@ -89,27 +87,16 @@ public class XmlRelaxng extends XmlSchema
StreamResult result = new StreamResult(xmlAsWriter);
try {
TransformerFactory.newInstance().newTransformer().transform(ds, result);
- } catch (TransformerConfigurationException ex) {
- throw context.getRuntime()
- .newRuntimeError("Could not parse document: " + ex.getMessage());
} catch (TransformerException ex) {
throw context.getRuntime()
.newRuntimeError("Could not parse document: " + ex.getMessage());
}
- try {
- is = new ByteArrayInputStream(xmlAsWriter.toString().getBytes("UTF-8"));
- } catch (UnsupportedEncodingException ex) {
- throw context.getRuntime()
- .newRuntimeError("Could not parse document: " + ex.getMessage());
- }
+ is = new ByteArrayInputStream(xmlAsWriter.toString().getBytes(StandardCharsets.UTF_8));
}
try {
return factory.compileSchema(is);
- } catch (VerifierConfigurationException ex) {
- throw context.getRuntime()
- .newRuntimeError("Could not parse document: " + ex.getMessage());
- } catch (SAXException ex) {
+ } catch (VerifierConfigurationException | SAXException ex) {
throw context.getRuntime()
.newRuntimeError("Could not parse document: " + ex.getMessage());
} catch (IOException ex) {
diff --git a/ext/java/nokogiri/XmlSaxParserContext.java b/ext/java/nokogiri/XmlSaxParserContext.java
index 4c20349ea3..00568b0f75 100644
--- a/ext/java/nokogiri/XmlSaxParserContext.java
+++ b/ext/java/nokogiri/XmlSaxParserContext.java
@@ -1,14 +1,12 @@
package nokogiri;
import nokogiri.internals.*;
-import static nokogiri.internals.NokogiriHelpers.rubyStringToString;
import org.apache.xerces.parsers.AbstractSAXParser;
import org.jruby.Ruby;
import org.jruby.RubyClass;
import org.jruby.RubyEncoding;
import org.jruby.RubyFixnum;
-import org.jruby.RubyString;
import org.jruby.anno.JRubyClass;
import org.jruby.anno.JRubyMethod;
import org.jruby.exceptions.RaiseException;
@@ -18,7 +16,6 @@
import org.xml.sax.SAXException;
import org.xml.sax.SAXParseException;
-import java.io.ByteArrayInputStream;
import java.io.IOException;
import java.io.InputStream;
@@ -104,7 +101,7 @@ public class XmlSaxParserContext extends ParserContext
if (!(encoding instanceof RubyEncoding)) {
throw context.runtime.newTypeError("encoding must be kind_of Encoding");
}
- java_encoding = ((RubyEncoding)encoding).toString();
+ java_encoding = encoding.toString();
}
XmlSaxParserContext ctx = newInstance(context.runtime, (RubyClass) klazz);
@@ -129,9 +126,10 @@ public class XmlSaxParserContext extends ParserContext
String java_encoding = null;
if (encoding != context.runtime.getNil()) {
if (!(encoding instanceof RubyEncoding)) {
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
throw context.runtime.newTypeError("encoding must be kind_of Encoding");
}
- java_encoding = ((RubyEncoding)encoding).toString();
+ java_encoding = encoding.toString();
}
XmlSaxParserContext ctx = newInstance(context.runtime, (RubyClass) klazz);
@@ -156,15 +154,17 @@ public class XmlSaxParserContext extends ParserContext
parse_io(ThreadContext context, IRubyObject klazz, IRubyObject data, IRubyObject encoding)
{
if (!invoke(context, data, "respond_to?", context.runtime.newSymbol("read")).isTrue()) {
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
throw context.runtime.newTypeError("argument expected to respond to :read");
}
String java_encoding = null;
if (encoding != context.runtime.getNil()) {
if (!(encoding instanceof RubyEncoding)) {
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
throw context.runtime.newTypeError("encoding must be kind_of Encoding");
}
- java_encoding = ((RubyEncoding)encoding).toString();
+ java_encoding = encoding.toString();
}
XmlSaxParserContext ctx = newInstance(context.runtime, (RubyClass) klazz);
@@ -236,9 +236,10 @@ public class XmlSaxParserContext extends ParserContext
protected static Options
defaultParseOptions(ThreadContext context)
{
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
return new ParserContext.Options(
RubyFixnum.fix2long(Helpers.invoke(context,
- ((RubyClass)context.getRuntime().getClassFromPath("Nokogiri::XML::ParseOptions"))
+ context.getRuntime().getClassFromPath("Nokogiri::XML::ParseOptions")
.getConstant("DEFAULT_XML"),
"to_i"))
);
@@ -272,7 +273,7 @@ public class XmlSaxParserContext extends ParserContext
parser.setProperty("http://xml.org/sax/properties/lexical-handler", handler);
parser.setProperty("http://xml.org/sax/properties/declaration-handler", handler);
} catch (Exception ex) {
- throw runtime.newRuntimeError("Problem while creating XML SAX Parser: " + ex.toString());
+ throw runtime.newRuntimeError("Problem while creating XML SAX Parser: " + ex);
}
try {
diff --git a/ext/java/nokogiri/XmlSaxPushParser.java b/ext/java/nokogiri/XmlSaxPushParser.java
index 26261a33e3..d6c69eb1ca 100644
--- a/ext/java/nokogiri/XmlSaxPushParser.java
+++ b/ext/java/nokogiri/XmlSaxPushParser.java
@@ -89,6 +89,7 @@ public class XmlSaxPushParser extends RubyObject
setOptions(ThreadContext context, IRubyObject opts)
{
invoke(context, parse_options(context), "options=", opts);
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
options = new ParserContext.Options(opts.convertToInteger().getLongValue());
return getOptions(context);
}
@@ -169,15 +170,12 @@ public class XmlSaxPushParser extends RubyObject
assert saxParser != null : "saxParser null";
parserTask = new ParserTask(context, saxParser, stream);
- futureTask = new FutureTask(parserTask);
- executor = Executors.newSingleThreadExecutor(new ThreadFactory() {
- @Override
- public Thread newThread(Runnable r) {
- Thread t = new Thread(r);
- t.setName("XmlSaxPushParser");
- t.setDaemon(true);
- return t;
- }
+ futureTask = new FutureTask<>(parserTask);
+ executor = Executors.newSingleThreadExecutor(r -> {
+ Thread t = new Thread(r);
+ t.setName("XmlSaxPushParser");
+ t.setDaemon(true);
+ return t;
});
executor.submit(futureTask);
}
@@ -190,8 +188,6 @@ public Thread newThread(Runnable r) {
try {
terminateImpl();
- } catch (InterruptedException e) {
- throw runtime.newRuntimeError(e.toString());
} catch (Exception e) {
throw runtime.newRuntimeError(e.toString());
}
diff --git a/ext/java/nokogiri/XmlSchema.java b/ext/java/nokogiri/XmlSchema.java
index 381953c64d..d1432471e2 100644
--- a/ext/java/nokogiri/XmlSchema.java
+++ b/ext/java/nokogiri/XmlSchema.java
@@ -6,21 +6,17 @@
import java.io.IOException;
import java.io.InputStream;
import java.io.Reader;
-import java.io.StringReader;
import javax.xml.XMLConstants;
import javax.xml.transform.Source;
import javax.xml.transform.dom.DOMSource;
-import javax.xml.transform.stream.StreamSource;
import javax.xml.validation.Schema;
import javax.xml.validation.SchemaFactory;
import javax.xml.validation.Validator;
-import nokogiri.internals.IgnoreSchemaErrorsErrorHandler;
import nokogiri.internals.SchemaErrorHandler;
import nokogiri.internals.XmlDomParserContext;
import nokogiri.internals.ParserContext;
-import nokogiri.internals.ParserContext.Options;
import org.jruby.Ruby;
import org.jruby.RubyArray;
@@ -29,7 +25,6 @@
import org.jruby.RubyObject;
import org.jruby.anno.JRubyClass;
import org.jruby.anno.JRubyMethod;
-import org.jruby.exceptions.RaiseException;
import org.jruby.runtime.ThreadContext;
import org.jruby.runtime.Visibility;
import org.jruby.runtime.builtin.IRubyObject;
@@ -106,14 +101,16 @@ public class XmlSchema extends RubyObject
if (parseOptions == null) {
parseOptions = defaultParseOptions(context.getRuntime());
}
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
long intParseOptions = RubyFixnum.fix2long(Helpers.invoke(context, parseOptions, "to_i"));
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
xmlSchema.setInstanceVariable("@errors", runtime.newEmptyArray());
xmlSchema.setInstanceVariable("@parse_options", parseOptions);
try {
SchemaErrorHandler errorHandler =
- new SchemaErrorHandler(context.getRuntime(), (RubyArray)xmlSchema.getInstanceVariable("@errors"));
+ new SchemaErrorHandler(context.getRuntime(), (RubyArray)xmlSchema.getInstanceVariable("@errors"));
Schema schema =
xmlSchema.getSchema(source,
context.getRuntime().getCurrentDirectory(),
@@ -130,7 +127,7 @@ public class XmlSchema extends RubyObject
protected static IRubyObject
defaultParseOptions(Ruby runtime)
{
- return ((RubyClass)runtime.getClassFromPath("Nokogiri::XML::ParseOptions")).getConstant("DEFAULT_SCHEMA");
+ return runtime.getClassFromPath("Nokogiri::XML::ParseOptions").getConstant("DEFAULT_SCHEMA");
}
/*
@@ -151,6 +148,7 @@ public class XmlSchema extends RubyObject
if (!(rbDocument instanceof XmlNode)) {
String msg = "expected parameter to be a Nokogiri::XML::Document, received " + rbDocument.getMetaClass();
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
throw context.runtime.newTypeError(msg);
}
if (!(rbDocument instanceof XmlDocument)) {
@@ -159,8 +157,9 @@ public class XmlSchema extends RubyObject
XmlDocument doc = ((XmlDocument)((XmlNode) rbDocument).document(context));
- RubyArray errors = (RubyArray) doc.getInstanceVariable("@errors");
+ RubyArray errors = (RubyArray) doc.getInstanceVariable("@errors");
if (!errors.isEmpty()) {
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
throw((XmlSyntaxError) errors.first()).toThrowable();
}
@@ -178,6 +177,7 @@ public class XmlSchema extends RubyObject
private static IRubyObject
getSchema(ThreadContext context, RubyClass klazz, Source source, IRubyObject parseOptions)
{
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
String moduleName = klazz.getName();
if ("Nokogiri::XML::Schema".equals(moduleName)) {
return XmlSchema.createSchemaInstance(context, klazz, source, parseOptions);
@@ -206,9 +206,11 @@ public class XmlSchema extends RubyObject
XmlDocument xmlDocument = ctx.parse(context, getNokogiriClass(runtime, "Nokogiri::XML::Document"), context.nil);
return validate_document_or_file(context, xmlDocument);
} catch (Exception ex) {
- RubyArray errors = (RubyArray)context.runtime.newEmptyArray();
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
+ RubyArray errors = context.runtime.newEmptyArray();
XmlSyntaxError xmlSyntaxError = XmlSyntaxError.createXMLSyntaxError(context.runtime);
xmlSyntaxError.setException(ex);
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
errors.append(xmlSyntaxError);
return errors;
}
@@ -217,7 +219,8 @@ public class XmlSchema extends RubyObject
IRubyObject
validate_document_or_file(ThreadContext context, XmlDocument xmlDocument)
{
- RubyArray errors = context.runtime.newEmptyArray();
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
+ RubyArray errors = context.runtime.newEmptyArray();
ErrorHandler errorHandler = new SchemaErrorHandler(context.runtime, errors);
setErrorHandler(errorHandler);
@@ -226,6 +229,7 @@ public class XmlSchema extends RubyObject
} catch (SAXException ex) {
XmlSyntaxError xmlSyntaxError = XmlSyntaxError.createXMLSyntaxError(context.runtime);
xmlSyntaxError.setException(ex);
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
errors.append(xmlSyntaxError);
} catch (IOException ex) {
throw context.runtime.newIOError(ex.getMessage());
@@ -291,7 +295,7 @@ private class SchemaResourceResolver implements LSResourceResolver
}
try {
this.errorHandler.warning(new SAXParseException(String.format("Attempt to load network entity '%s'", systemId), null));
- } catch (SAXException ex) {
+ } catch (SAXException ignored) {
}
} else {
String adjusted = adjustSystemIdIfNecessary(currentDir, scriptFileName, baseURI, systemId);
@@ -303,7 +307,7 @@ private class SchemaResourceResolver implements LSResourceResolver
}
}
- private class SchemaLSInput implements LSInput
+ private static class SchemaLSInput implements LSInput
{
protected String fPublicId;
protected String fSystemId;
diff --git a/ext/java/nokogiri/XmlSyntaxError.java b/ext/java/nokogiri/XmlSyntaxError.java
index 0fe1b649e4..d3265499b4 100644
--- a/ext/java/nokogiri/XmlSyntaxError.java
+++ b/ext/java/nokogiri/XmlSyntaxError.java
@@ -91,6 +91,8 @@ public class XmlSyntaxError extends RubyException
return xmlSyntaxError;
}
+ // unused
+ @Deprecated
public static XmlSyntaxError
createFatalError(Ruby runtime, SAXParseException e)
{
diff --git a/ext/java/nokogiri/XmlText.java b/ext/java/nokogiri/XmlText.java
index f51bc6b91c..12f984c67c 100644
--- a/ext/java/nokogiri/XmlText.java
+++ b/ext/java/nokogiri/XmlText.java
@@ -47,6 +47,7 @@ public class XmlText extends XmlNode
init(ThreadContext context, IRubyObject[] args)
{
if (args.length < 2) {
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
throw context.runtime.newArgumentError(args.length, 2);
}
@@ -55,6 +56,7 @@ public class XmlText extends XmlNode
if (!(rbDocument instanceof XmlNode)) {
String msg = "expected second parameter to be a Nokogiri::XML::Document, received " + rbDocument.getMetaClass();
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
throw context.runtime.newTypeError(msg);
}
if (!(rbDocument instanceof XmlDocument)) {
diff --git a/ext/java/nokogiri/XmlXpathContext.java b/ext/java/nokogiri/XmlXpathContext.java
index 5996956f68..83044d4919 100644
--- a/ext/java/nokogiri/XmlXpathContext.java
+++ b/ext/java/nokogiri/XmlXpathContext.java
@@ -17,7 +17,6 @@
import org.jruby.RubyObject;
import org.jruby.anno.JRubyClass;
import org.jruby.anno.JRubyMethod;
-import org.jruby.exceptions.RaiseException;
import org.jruby.runtime.ThreadContext;
import org.jruby.runtime.builtin.IRubyObject;
import org.jruby.util.SafePropertyAccessor;
@@ -121,7 +120,6 @@ public class XmlXpathContext extends RubyObject
while (xpathFunctionCalls.find()) {
namespacedQuery.append(query.subSequence(jchar, xpathFunctionCalls.start()));
- jchar = xpathFunctionCalls.start();
if (methodNames.contains(xpathFunctionCalls.group())) {
namespacedQuery.append(NokogiriNamespaceContext.NOKOGIRI_PREFIX);
@@ -198,7 +196,7 @@ public class XmlXpathContext extends RubyObject
return tryGetNodeSet(context, expr, fnResolver);
} catch (TransformerException | RuntimeException ex) {
throw XmlSyntaxError.createXMLXPathSyntaxError(context.runtime,
- (expr + ": " + ex.toString()),
+ (expr + ": " + ex),
ex).toThrowable();
}
}
diff --git a/ext/java/nokogiri/XsltStylesheet.java b/ext/java/nokogiri/XsltStylesheet.java
index 1870b60d35..c71b4750c2 100644
--- a/ext/java/nokogiri/XsltStylesheet.java
+++ b/ext/java/nokogiri/XsltStylesheet.java
@@ -83,8 +83,9 @@ public class XsltStylesheet extends RubyObject
if (parameters instanceof RubyHash) {
setHashParameters(transf, (RubyHash)parameters);
} else if (parameters instanceof RubyArray) {
- setArrayParameters(transf, context, (RubyArray)parameters);
+ setArrayParameters(transf, context, (RubyArray)parameters);
} else {
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
throw context.getRuntime().newTypeError("parameters should be given either Array or Hash");
}
}
@@ -170,8 +171,9 @@ public class XsltStylesheet extends RubyObject
ensureDocumentHasNoError(ThreadContext context, XmlDocument xmlDoc)
{
Ruby runtime = context.getRuntime();
- RubyArray errors_of_xmlDoc = (RubyArray) xmlDoc.getInstanceVariable("@errors");
+ RubyArray errors_of_xmlDoc = (RubyArray) xmlDoc.getInstanceVariable("@errors");
if (!errors_of_xmlDoc.isEmpty()) {
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
throw runtime.newRuntimeError(errors_of_xmlDoc.first().asString().asJavaString());
}
}
@@ -212,11 +214,7 @@ public class XsltStylesheet extends RubyObject
if (result.getNode().getFirstChild() == null) {
stringResult = retryXsltTransformation(context, args, domSource, elistener); // StreamResult
}
- } catch (TransformerConfigurationException ex) {
- throw runtime.newRuntimeError(ex.getMessage());
- } catch (TransformerException ex) {
- throw runtime.newRuntimeError(ex.getMessage());
- } catch (IOException ex) {
+ } catch (TransformerException | IOException ex) {
throw runtime.newRuntimeError(ex.getMessage());
}
@@ -230,7 +228,7 @@ public class XsltStylesheet extends RubyObject
}
if (stringResult == null) {
- return createDocumentFromDomResult(context, runtime, result);
+ return createDocumentFromDomResult(context, result);
} else {
return createDocumentFromString(context, runtime, stringResult);
}
@@ -291,7 +289,7 @@ public class XsltStylesheet extends RubyObject
}
private IRubyObject
- createDocumentFromDomResult(ThreadContext context, Ruby runtime, DOMResult domResult)
+ createDocumentFromDomResult(ThreadContext context, DOMResult domResult)
{
if ("html".equals(domResult.getNode().getFirstChild().getNodeName())) {
return new Html4Document(context.runtime, (Document) domResult.getNode());
@@ -329,15 +327,17 @@ public class XsltStylesheet extends RubyObject
args[2] = runtime.getNil(); // encoding
RubyClass parse_options = (RubyClass)runtime.getClassFromPath("Nokogiri::XML::ParseOptions");
if (htmlish) {
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
args[3] = parse_options.getConstant("DEFAULT_HTML");
RubyClass htmlDocumentClass = getNokogiriClass(runtime, "Nokogiri::HTML4::Document");
return Helpers.invoke(context, htmlDocumentClass, "parse", args);
} else {
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
args[3] = parse_options.getConstant("DEFAULT_XML");
RubyClass xmlDocumentClass = getNokogiriClass(runtime, "Nokogiri::XML::Document");
XmlDocument xmlDocument = (XmlDocument) Helpers.invoke(context, xmlDocumentClass, "parse", args);
if (((Document)xmlDocument.getNode()).getDocumentElement() == null) {
- RubyArray errors = (RubyArray) xmlDocument.getInstanceVariable("@errors");
+ RubyArray errors = (RubyArray) xmlDocument.getInstanceVariable("@errors");
Helpers.invoke(context, errors, "<<", args[0]);
}
return xmlDocument;
diff --git a/ext/java/nokogiri/internals/NokogiriHelpers.java b/ext/java/nokogiri/internals/NokogiriHelpers.java
index 97ffc50034..8dd28ee6d1 100644
--- a/ext/java/nokogiri/internals/NokogiriHelpers.java
+++ b/ext/java/nokogiri/internals/NokogiriHelpers.java
@@ -40,6 +40,8 @@
import nokogiri.XmlText;
import nokogiri.XmlXpathContext;
+import static java.nio.charset.StandardCharsets.UTF_8;
+
/**
* A class for various utility methods.
*
@@ -59,6 +61,8 @@ public class NokogiriHelpers
return (XmlNode) node.getUserData(CACHED_NODE);
}
+ // unused
+ @Deprecated
public static void
clearCachedNode(Node node)
{
@@ -221,7 +225,7 @@ public class NokogiriHelpers
public static IRubyObject
nonEmptyStringOrNil(Ruby runtime, String s)
{
- if (s == null || s.length() == 0) { return runtime.getNil(); }
+ if (s == null || s.isEmpty()) { return runtime.getNil(); }
return RubyString.newString(runtime, s);
}
@@ -287,7 +291,7 @@ public class NokogiriHelpers
Node cur, tmp, next;
- String buffer = "";
+ StringBuilder buffer = new StringBuilder();
cur = node;
@@ -295,10 +299,10 @@ public class NokogiriHelpers
String name = "";
String sep = "?";
int occur = 0;
- boolean generic = false;
+ boolean generic;
if (cur.getNodeType() == Node.DOCUMENT_NODE) {
- if (buffer.startsWith("/")) { break; }
+ if (buffer.toString().startsWith("/")) { break; }
sep = "/";
next = null;
@@ -471,18 +475,20 @@ public class NokogiriHelpers
}
if (occur == 0) {
- buffer = sep + name + buffer;
+ buffer.insert(0, sep + name);
} else {
- buffer = sep + name + "[" + occur + "]" + buffer;
+ buffer.insert(0, sep + name + "[" + occur + "]");
}
cur = next;
} while (cur != null);
- return buffer;
+ return buffer.toString();
}
+ // unused
+ @Deprecated
static boolean
compareTwoNodes(Node m, Node n)
{
@@ -494,7 +500,7 @@ public class NokogiriHelpers
nodesAreEqual(Object a, Object b)
{
return (((a == null) && (b == null)) ||
- ((a != null) && (b != null) && (b.equals(a))));
+ ((b != null) && (b.equals(a))));
}
private static boolean
@@ -505,7 +511,7 @@ public class NokogiriHelpers
private static final Pattern encoded_pattern = Pattern.compile("&|>|<|
");
private static final String[] encoded = {"&", ">", "<", "
"};
- private static final Pattern decoded_pattern = Pattern.compile("&|>|<|\r");
+ private static final Pattern decoded_pattern = Pattern.compile("[&><\r]");
private static final String[] decoded = {"&", ">", "<", "\r"};
private static StringBuffer
@@ -555,6 +561,8 @@ public class NokogiriHelpers
return (nodeName.startsWith("xmlns"));
}
+ // unused
+ @Deprecated
public static boolean
isNonDefaultNamespace(Node node)
{
@@ -591,6 +599,8 @@ public class NokogiriHelpers
return str.isEmpty() || isBlank((CharSequence) str);
}
+ // unused
+ @Deprecated
public static boolean
isNullOrEmpty(String str)
{
@@ -649,8 +659,9 @@ public class NokogiriHelpers
nodeArrayToRubyArray(Ruby ruby, Node[] nodes)
{
RubyArray n = RubyArray.newArray(ruby, nodes.length);
- for (int i = 0; i < nodes.length; i++) {
- n.append(NokogiriHelpers.getCachedNodeOrCreate(ruby, nodes[i]));
+ for (Node node : nodes) {
+ // TODO: switch to common undeprecated API when 9.4 adds 10 methods
+ n.append(NokogiriHelpers.getCachedNodeOrCreate(ruby, node));
}
return n;
}
@@ -690,7 +701,7 @@ public class NokogiriHelpers
private static String
resolveSystemId(String baseName, String systemId)
{
- if (baseName == null || baseName.length() < 1) { return null; }
+ if (baseName == null || baseName.isEmpty()) { return null; }
String parentName;
baseName = baseName.replace("%20", " ");
File base = new File(baseName);
@@ -703,15 +714,13 @@ public class NokogiriHelpers
return null;
}
- private static final Charset UTF8 = Charset.forName("UTF-8");
-
public static boolean
isUTF8(String encoding)
{
if (encoding == null) { return true; } // no need to convert encoding
if ("UTF-8".equals(encoding)) { return true; }
- return UTF8.aliases().contains(encoding);
+ return UTF_8.aliases().contains(encoding);
}
public static ByteBuffer
@@ -720,6 +729,8 @@ public class NokogiriHelpers
return output_charset.encode(CharBuffer.wrap(input_string)); // does replace implicitly on un-mappable characters
}
+ // unused
+ @Deprecated
public static CharSequence
convertEncodingByNKFIfNecessary(ThreadContext context, XmlDocument doc, CharSequence str)
{
@@ -766,15 +777,8 @@ public class NokogiriHelpers
RubyString r_str =
(RubyString)nkf_method.invoke(null, context, null, runtime.newString(opt), runtime.newString(str.toString()));
return NokogiriHelpers.rubyStringToString(r_str);
- } catch (SecurityException e) {
- return str;
- } catch (NoSuchMethodException e) {
- return str;
- } catch (IllegalArgumentException e) {
- return str;
- } catch (IllegalAccessException e) {
- return str;
- } catch (InvocationTargetException e) {
+ } catch (SecurityException | NoSuchMethodException | IllegalArgumentException | IllegalAccessException |
+ InvocationTargetException e) {
return str;
}
}
diff --git a/ext/java/nokogiri/internals/SaveContextVisitor.java b/ext/java/nokogiri/internals/SaveContextVisitor.java
index 462a9bd69b..aac04a8430 100644
--- a/ext/java/nokogiri/internals/SaveContextVisitor.java
+++ b/ext/java/nokogiri/internals/SaveContextVisitor.java
@@ -58,6 +58,7 @@ public class SaveContextVisitor
private final Deque c14nNamespaceStack;
private final Deque c14nAttrStack;
//private List c14nExclusiveInclusivePrefixes = null;
+ private final Stack> xmlnsNamespaceStack;
/*
* U can't touch this.
@@ -117,6 +118,7 @@ public class SaveContextVisitor
if ((asBuilder && indent == null) || (asBuilder && indent.length() == 0)) { indent = " "; } // default, two spaces
indentString = indent;
if (!asXml && !asHtml && !asXhtml && !asBuilder) { asXml = true; }
+ xmlnsNamespaceStack = asXml ? new Stack>() : null;
}
@Override
@@ -432,19 +434,24 @@ public class SaveContextVisitor
public boolean
enter(Element element)
{
+ pushXmlnsNamespaceStack();
+
if (canonical) {
c14nNodeList.add(element);
if (element == element.getOwnerDocument().getDocumentElement()) {
c14nNodeList.add(element.getOwnerDocument());
}
}
+
String current = indentation.peek();
buffer.append(current);
if (needIndent(element)) {
indentation.push(current + indentString);
}
+
String name = element.getTagName();
buffer.append('<').append(name);
+
Attr[] attrs = getAttrsAndNamespaces(element);
for (Attr attr : attrs) {
if (attr.getSpecified()) {
@@ -453,11 +460,13 @@ public class SaveContextVisitor
leave(attr);
}
}
+
if (element.hasChildNodes()) {
buffer.append('>');
if (needBreakInOpening(element)) { buffer.append('\n'); }
return true;
}
+
// no child
if (asHtml) {
buffer.append('>');
@@ -472,12 +481,38 @@ public class SaveContextVisitor
} else {
buffer.append("/>");
}
+
if (needBreakInOpening(element)) {
buffer.append('\n');
}
return true;
}
+ private Map
+ pushXmlnsNamespaceStack() {
+ if (!asXml || xmlnsNamespaceStack == null) { return null; }
+ Map newContext;
+ if (xmlnsNamespaceStack.isEmpty()) {
+ newContext = new HashMap();
+ } else {
+ Map parentContext = xmlnsNamespaceStack.peek();
+ newContext = new HashMap(parentContext);
+ }
+ return xmlnsNamespaceStack.push(newContext);
+ }
+
+ private Map
+ popXmlnsNamespaceStack() {
+ if (!asXml || xmlnsNamespaceStack == null || xmlnsNamespaceStack.isEmpty()) { return null; }
+ return xmlnsNamespaceStack.pop();
+ }
+
+ private Map
+ peekXmlnsNamespaceStack() {
+ if (!asXml || xmlnsNamespaceStack == null || xmlnsNamespaceStack.isEmpty()) { return null; }
+ return xmlnsNamespaceStack.peek();
+ }
+
private boolean
needIndent(Element element)
{
@@ -511,11 +546,15 @@ public class SaveContextVisitor
NamedNodeMap attrs = element.getAttributes();
if (!canonical) {
if (attrs == null || attrs.getLength() == 0) { return new Attr[0]; }
- Attr[] attrsAndNamespaces = new Attr[attrs.getLength()];
+ Map xmlnsContext = peekXmlnsNamespaceStack();
+ List filteredAttrsAndNamespaces = new ArrayList();
for (int i = 0; i < attrs.getLength(); i++) {
- attrsAndNamespaces[i] = (Attr) attrs.item(i);
+ Attr attr = (Attr) attrs.item(i);
+ if (!findOrAddRedundantNamespaceAttr(xmlnsContext, attr)) {
+ filteredAttrsAndNamespaces.add(attr);
+ }
}
- return attrsAndNamespaces;
+ return filteredAttrsAndNamespaces.toArray(new Attr[0]);
} else {
List namespaces = new ArrayList();
List attributes = new ArrayList();
@@ -544,7 +583,45 @@ public class SaveContextVisitor
c14nAttrStack.push(attributeArray);
return allAttrs;
}
+ }
+
+ /**
+ * Detects whether a given attribute is a redundant xmlns namespace
+ * already present within xmlnsContext.
+ *
+ * As a side-effect, if the attribute is a non-redundant namespace,
+ * it is added to the xmlnsContext, so that it will be considered redundant
+ * for subsequent checks.
+ *
+ * @param xmlnsContext The namespace context, which should be the top object
+ * of xmlnsNamespaceStack.
+ * @param attr The attribute to check.
+ * @return True if the object is redundant, false otherwise.
+ */
+ private boolean
+ findOrAddRedundantNamespaceAttr(Map xmlnsContext, Attr attr) {
+ if (xmlnsContext == null || !attr.getSpecified()) { return false; }
+
+ String xmlnsPrefix;
+ String attrName = attr.getNodeName();
+ if (attrName.equals("xmlns")) {
+ xmlnsPrefix = "";
+ } else if (attrName.startsWith("xmlns:")) {
+ xmlnsPrefix = attrName.substring(6);
+ } else {
+ // Not a namespace attribute
+ return false;
+ }
+ String xmlnsUri = attr.getNodeValue();
+ if (xmlnsContext.containsKey(xmlnsPrefix) && xmlnsUri.equals(xmlnsContext.get(xmlnsPrefix))) {
+ // Redundant namespace detected
+ return true;
+ } else {
+ // Add non-redundant namespace to the top of xmlnsNamespaceStack
+ xmlnsContext.put(xmlnsPrefix, xmlnsUri);
+ return false;
+ }
}
private void
@@ -653,6 +730,8 @@ public int compare(Attr attr0, Attr attr1) {
public void
leave(Element element)
{
+ popXmlnsNamespaceStack();
+
if (canonical) {
c14nNamespaceStack.poll();
c14nAttrStack.poll();
diff --git a/ext/nokogiri/extconf.rb b/ext/nokogiri/extconf.rb
index 70e2fe0cc9..2960367e6b 100644
--- a/ext/nokogiri/extconf.rb
+++ b/ext/nokogiri/extconf.rb
@@ -240,15 +240,7 @@ def zlib_source(version_string)
end
def gnome_source
- # As of 2022-02-20, some mirrors have expired SSL certificates. I'm able to retrieve from my home,
- # but whatever host is resolved on the github actions workers see an expired cert.
- #
- # See https://github.com/sparklemotion/nokogiri/runs/5266206403?check_suite_focus=true
- if ENV["NOKOGIRI_USE_CANONICAL_GNOME_SOURCE"]
- "https://download.gnome.org"
- else
- "https://muug.ca/mirror/gnome" # old reliable
- end
+ "https://download.gnome.org"
end
LOCAL_PACKAGE_RESPONSE = Object.new
@@ -469,7 +461,7 @@ def recipe.port_path
yield recipe
env = Hash.new do |hash, key|
- hash[key] = (ENV[key]).to_s
+ hash[key] = ENV[key].to_s
end
recipe.configure_options.flatten!
@@ -627,7 +619,7 @@ def do_clean
def needs_darwin_linker_hack
config_cross_build? &&
darwin? &&
- Gem::Requirement.new("~> 3.2").satisfied_by?(Gem::Version.new(RbConfig::CONFIG["ruby_version"].split("+").first))
+ RbConfig::MAKEFILE_CONFIG["EXTDLDFLAGS"].include?("-bundle_loader")
end
#
@@ -764,10 +756,6 @@ def needs_darwin_linker_hack
cross_build_p = config_cross_build?
message "Cross build is #{cross_build_p ? "enabled" : "disabled"}.\n"
- if needs_darwin_linker_hack
- append_ldflags("-Wl,-flat_namespace")
- end
-
require "yaml"
dependencies = YAML.load_file(File.join(PACKAGE_ROOT_DIR, "dependencies.yml"))
@@ -1133,6 +1121,7 @@ def compile
have_func("xmlCtxtSetOptions") # introduced in libxml2 2.13.0
have_func("xmlCtxtGetOptions") # introduced in libxml2 2.14.0
have_func("xmlSwitchEncodingName") # introduced in libxml2 2.13.0
+have_func("xmlAddIDSafe") # introduced in libxml2 2.13.0
have_func("rb_category_warning") # introduced in Ruby 3.0 but had trouble resolving this symbol in truffleruby
other_library_versions_string = OTHER_LIBRARY_VERSIONS.map { |k, v| [k, v].join(":") }.join(",")
diff --git a/ext/nokogiri/gumbo.c b/ext/nokogiri/gumbo.c
index fd938f3c0c..e3ed40a7ca 100644
--- a/ext/nokogiri/gumbo.c
+++ b/ext/nokogiri/gumbo.c
@@ -113,6 +113,71 @@ set_line(xmlNodePtr node, size_t line)
}
}
+// This function is essentially xmlNewNsProp, but we skip the full list traversal to append by
+// providing the last property in the linked list as a parameter.
+static xmlAttrPtr
+append_property(xmlNodePtr node, xmlNsPtr ns, const xmlChar *name, const xmlChar *value, xmlAttrPtr last_prop)
+{
+ xmlAttrPtr cur = (xmlAttrPtr) xmlMalloc(sizeof(xmlAttr));
+ if (cur == NULL) {
+ return NULL;
+ }
+ memset(cur, 0, sizeof(xmlAttr));
+ cur->type = XML_ATTRIBUTE_NODE;
+ cur->parent = node;
+ xmlDocPtr doc = node->doc;
+ cur->doc = doc;
+ cur->ns = ns;
+
+ if ((doc != NULL) && (doc->dict != NULL)) {
+ cur->name = (xmlChar *) xmlDictLookup(doc->dict, name, -1);
+ } else {
+ cur->name = xmlStrdup(name);
+ }
+ if (cur->name == NULL) {
+ goto error;
+ }
+
+ if (value != NULL) {
+ cur->children = xmlNewDocText(doc, value);
+ if (cur->children == NULL) {
+ goto error;
+ }
+ cur->last = NULL;
+ xmlNodePtr tmp = cur->children;
+ while (tmp != NULL) {
+ tmp->parent = (xmlNodePtr) cur;
+ if (tmp->next == NULL) {
+ cur->last = tmp;
+ }
+ tmp = tmp->next;
+ }
+
+ if (doc != NULL) {
+ int res = xmlIsID(doc, node, cur);
+ if (res < 0) {
+ goto error;
+ }
+ if ((res == 1) && (xmlAddIDSafe(cur, value) < 0)) {
+ goto error;
+ }
+ }
+ }
+
+ if (node->properties == NULL) {
+ node->properties = cur;
+ } else {
+ last_prop->next = cur;
+ cur->prev = last_prop;
+ }
+
+ return cur;
+
+error:
+ xmlFreeProp(cur);
+ return (NULL);
+}
+
// Construct an XML tree rooted at xml_output_node from the Gumbo tree rooted
// at gumbo_node.
static void
@@ -200,6 +265,7 @@ build_tree(
xmlAddChild(xml_node, xml_child);
// Add the attributes.
+ xmlAttrPtr last_prop = NULL;
const GumboVector *attrs = &gumbo_child->v.element.attributes;
for (size_t i = 0; i < attrs->length; i++) {
const GumboAttribute *attr = attrs->data[i];
@@ -220,7 +286,9 @@ build_tree(
default:
ns = NULL;
}
- xmlNewNsProp(xml_child, ns, (const xmlChar *)attr->name, (const xmlChar *)attr->value);
+
+ // We micromanage the attribute list for performance reasons.
+ last_prop = append_property(xml_child, ns, (const xmlChar *)attr->name, (const xmlChar *)attr->value, last_prop);
}
// Add children for this element.
diff --git a/ext/nokogiri/libxml2_polyfill.c b/ext/nokogiri/libxml2_polyfill.c
index 750b1b52a2..2b4296cf32 100644
--- a/ext/nokogiri/libxml2_polyfill.c
+++ b/ext/nokogiri/libxml2_polyfill.c
@@ -112,3 +112,15 @@ xmlSwitchEncodingName(xmlParserCtxtPtr ctxt, const char *encoding)
return (xmlSwitchToEncoding(ctxt, handler));
}
#endif
+
+#ifndef HAVE_XMLADDIDSAFE
+int
+xmlAddIDSafe(xmlAttrPtr attr, const xmlChar *value)
+{
+ xmlIDPtr id = xmlAddID(NULL, attr->doc, value, attr);
+ if (id) {
+ return 1;
+ }
+ return 0;
+}
+#endif
diff --git a/ext/nokogiri/nokogiri.h b/ext/nokogiri/nokogiri.h
index b75ebc47fa..99d38e1183 100644
--- a/ext/nokogiri/nokogiri.h
+++ b/ext/nokogiri/nokogiri.h
@@ -66,6 +66,9 @@ int xmlCtxtGetOptions(xmlParserCtxtPtr ctxt);
#ifndef HAVE_XMLSWITCHENCODINGNAME
int xmlSwitchEncodingName(xmlParserCtxtPtr ctxt, const char *encoding);
#endif
+#ifndef HAVE_XMLADDIDSAFE
+int xmlAddIDSafe(xmlAttrPtr attr, const xmlChar *value);
+#endif
#define XMLNS_PREFIX "xmlns"
#define XMLNS_PREFIX_LEN 6 /* including either colon or \0 */
diff --git a/ext/nokogiri/xml_sax_parser_context.c b/ext/nokogiri/xml_sax_parser_context.c
index 75fe2e4f01..0d2b65b599 100644
--- a/ext/nokogiri/xml_sax_parser_context.c
+++ b/ext/nokogiri/xml_sax_parser_context.c
@@ -102,7 +102,10 @@ noko_xml_sax_parser_context_s_native_io(VALUE rb_class, VALUE rb_io, VALUE rb_en
c_context->sax = NULL;
}
- return noko_xml_sax_parser_context_wrap(rb_class, c_context);
+ VALUE rb_context = noko_xml_sax_parser_context_wrap(rb_class, c_context);
+ rb_iv_set(rb_context, "@input", rb_io);
+
+ return rb_context;
}
/* :nodoc: */
@@ -154,7 +157,10 @@ noko_xml_sax_parser_context_s_native_memory(VALUE rb_class, VALUE rb_input, VALU
c_context->sax = NULL;
}
- return noko_xml_sax_parser_context_wrap(rb_class, c_context);
+ VALUE rb_context = noko_xml_sax_parser_context_wrap(rb_class, c_context);
+ rb_iv_set(rb_context, "@input", rb_input);
+
+ return rb_context;
}
/*
diff --git a/gumbo-parser/src/Makefile b/gumbo-parser/src/Makefile
index 6bd4a18fbe..db58c3137f 100644
--- a/gumbo-parser/src/Makefile
+++ b/gumbo-parser/src/Makefile
@@ -13,9 +13,11 @@ gumbo_objs := \
char_ref.o \
error.o \
foreign_attrs.o \
+ hashmap.o \
parser.o \
string_buffer.o \
string_piece.o \
+ string_set.o \
svg_attrs.o \
svg_tags.o \
tag.o \
diff --git a/gumbo-parser/src/hashmap.c b/gumbo-parser/src/hashmap.c
new file mode 100644
index 0000000000..d70b16277e
--- /dev/null
+++ b/gumbo-parser/src/hashmap.c
@@ -0,0 +1,1154 @@
+// Copyright 2020 Joshua J Baker. All rights reserved.
+// Use of this source code is governed by an MIT-style
+// license that can be found in the LICENSE file.
+
+#include
+#include
+#include
+#include
+#include
+#include "hashmap.h"
+
+#define GROW_AT 0.60 /* 60% */
+#define SHRINK_AT 0.10 /* 10% */
+
+#ifndef HASHMAP_LOAD_FACTOR
+#define HASHMAP_LOAD_FACTOR GROW_AT
+#endif
+
+static void *(*__malloc)(size_t) = NULL;
+static void *(*__realloc)(void *, size_t) = NULL;
+static void (*__free)(void *) = NULL;
+
+// hashmap_set_allocator allows for configuring a custom allocator for
+// all hashmap library operations. This function, if needed, should be called
+// only once at startup and a prior to calling hashmap_new().
+void hashmap_set_allocator(void *(*malloc)(size_t), void (*free)(void*)) {
+ __malloc = malloc;
+ __free = free;
+}
+
+struct bucket {
+ uint64_t hash:48;
+ uint64_t dib:16;
+};
+
+// hashmap is an open addressed hash map using robinhood hashing.
+struct hashmap {
+ void *(*malloc)(size_t);
+ void *(*realloc)(void *, size_t);
+ void (*free)(void *);
+ size_t elsize;
+ size_t cap;
+ uint64_t seed0;
+ uint64_t seed1;
+ uint64_t (*hash)(const void *item, uint64_t seed0, uint64_t seed1);
+ int (*compare)(const void *a, const void *b, void *udata);
+ void (*elfree)(void *item);
+ void *udata;
+ size_t bucketsz;
+ size_t nbuckets;
+ size_t count;
+ size_t mask;
+ size_t growat;
+ size_t shrinkat;
+ uint8_t loadfactor;
+ uint8_t growpower;
+ bool oom;
+ void *buckets;
+ void *spare;
+ void *edata;
+};
+
+void hashmap_set_grow_by_power(struct hashmap *map, size_t power) {
+ map->growpower = power < 1 ? 1 : power > 16 ? 16 : power;
+}
+
+static double clamp_load_factor(double factor, double default_factor) {
+ // Check for NaN and clamp between 50% and 90%
+ return factor != factor ? default_factor :
+ factor < 0.50 ? 0.50 :
+ factor > 0.95 ? 0.95 :
+ factor;
+}
+
+void hashmap_set_load_factor(struct hashmap *map, double factor) {
+ factor = clamp_load_factor(factor, map->loadfactor / 100.0);
+ map->loadfactor = factor * 100;
+ map->growat = map->nbuckets * (map->loadfactor / 100.0);
+}
+
+static struct bucket *bucket_at0(void *buckets, size_t bucketsz, size_t i) {
+ return (struct bucket*)(((char*)buckets)+(bucketsz*i));
+}
+
+static struct bucket *bucket_at(struct hashmap *map, size_t index) {
+ return bucket_at0(map->buckets, map->bucketsz, index);
+}
+
+static void *bucket_item(struct bucket *entry) {
+ return ((char*)entry)+sizeof(struct bucket);
+}
+
+static uint64_t clip_hash(uint64_t hash) {
+ return hash & 0xFFFFFFFFFFFF;
+}
+
+static uint64_t get_hash(struct hashmap *map, const void *key) {
+ return clip_hash(map->hash(key, map->seed0, map->seed1));
+}
+
+
+// hashmap_new_with_allocator returns a new hash map using a custom allocator.
+// See hashmap_new for more information information
+struct hashmap *hashmap_new_with_allocator(void *(*_malloc)(size_t),
+ void *(*_realloc)(void*, size_t), void (*_free)(void*),
+ size_t elsize, size_t cap, uint64_t seed0, uint64_t seed1,
+ uint64_t (*hash)(const void *item, uint64_t seed0, uint64_t seed1),
+ int (*compare)(const void *a, const void *b, void *udata),
+ void (*elfree)(void *item),
+ void *udata)
+{
+ _malloc = _malloc ? _malloc : __malloc ? __malloc : malloc;
+ _realloc = _realloc ? _realloc : __realloc ? __realloc : realloc;
+ _free = _free ? _free : __free ? __free : free;
+ size_t ncap = 16;
+ if (cap < ncap) {
+ cap = ncap;
+ } else {
+ while (ncap < cap) {
+ ncap *= 2;
+ }
+ cap = ncap;
+ }
+ size_t bucketsz = sizeof(struct bucket) + elsize;
+ while (bucketsz & (sizeof(uintptr_t)-1)) {
+ bucketsz++;
+ }
+ // hashmap + spare + edata
+ size_t size = sizeof(struct hashmap)+bucketsz*2;
+ struct hashmap *map = _malloc(size);
+ if (!map) {
+ return NULL;
+ }
+ memset(map, 0, sizeof(struct hashmap));
+ map->elsize = elsize;
+ map->bucketsz = bucketsz;
+ map->seed0 = seed0;
+ map->seed1 = seed1;
+ map->hash = hash;
+ map->compare = compare;
+ map->elfree = elfree;
+ map->udata = udata;
+ map->spare = ((char*)map)+sizeof(struct hashmap);
+ map->edata = (char*)map->spare+bucketsz;
+ map->cap = cap;
+ map->nbuckets = cap;
+ map->mask = map->nbuckets-1;
+ map->buckets = _malloc(map->bucketsz*map->nbuckets);
+ if (!map->buckets) {
+ _free(map);
+ return NULL;
+ }
+ memset(map->buckets, 0, map->bucketsz*map->nbuckets);
+ map->growpower = 1;
+ map->loadfactor = clamp_load_factor(HASHMAP_LOAD_FACTOR, GROW_AT) * 100;
+ map->growat = map->nbuckets * (map->loadfactor / 100.0);
+ map->shrinkat = map->nbuckets * SHRINK_AT;
+ map->malloc = _malloc;
+ map->realloc = _realloc;
+ map->free = _free;
+ return map;
+}
+
+// hashmap_new returns a new hash map.
+// Param `elsize` is the size of each element in the tree. Every element that
+// is inserted, deleted, or retrieved will be this size.
+// Param `cap` is the default lower capacity of the hashmap. Setting this to
+// zero will default to 16.
+// Params `seed0` and `seed1` are optional seed values that are passed to the
+// following `hash` function. These can be any value you wish but it's often
+// best to use randomly generated values.
+// Param `hash` is a function that generates a hash value for an item. It's
+// important that you provide a good hash function, otherwise it will perform
+// poorly or be vulnerable to Denial-of-service attacks. This implementation
+// comes with two helper functions `hashmap_sip()` and `hashmap_murmur()`.
+// Param `compare` is a function that compares items in the tree. See the
+// qsort stdlib function for an example of how this function works.
+// The hashmap must be freed with hashmap_free().
+// Param `elfree` is a function that frees a specific item. This should be NULL
+// unless you're storing some kind of reference data in the hash.
+struct hashmap *hashmap_new(size_t elsize, size_t cap, uint64_t seed0,
+ uint64_t seed1,
+ uint64_t (*hash)(const void *item, uint64_t seed0, uint64_t seed1),
+ int (*compare)(const void *a, const void *b, void *udata),
+ void (*elfree)(void *item),
+ void *udata)
+{
+ return hashmap_new_with_allocator(NULL, NULL, NULL, elsize, cap, seed0,
+ seed1, hash, compare, elfree, udata);
+}
+
+static void free_elements(struct hashmap *map) {
+ if (map->elfree) {
+ for (size_t i = 0; i < map->nbuckets; i++) {
+ struct bucket *bucket = bucket_at(map, i);
+ if (bucket->dib) map->elfree(bucket_item(bucket));
+ }
+ }
+}
+
+// hashmap_clear quickly clears the map.
+// Every item is called with the element-freeing function given in hashmap_new,
+// if present, to free any data referenced in the elements of the hashmap.
+// When the update_cap is provided, the map's capacity will be updated to match
+// the currently number of allocated buckets. This is an optimization to ensure
+// that this operation does not perform any allocations.
+void hashmap_clear(struct hashmap *map, bool update_cap) {
+ map->count = 0;
+ free_elements(map);
+ if (update_cap) {
+ map->cap = map->nbuckets;
+ } else if (map->nbuckets != map->cap) {
+ void *new_buckets = map->malloc(map->bucketsz*map->cap);
+ if (new_buckets) {
+ map->free(map->buckets);
+ map->buckets = new_buckets;
+ }
+ map->nbuckets = map->cap;
+ }
+ memset(map->buckets, 0, map->bucketsz*map->nbuckets);
+ map->mask = map->nbuckets-1;
+ map->growat = map->nbuckets * (map->loadfactor / 100.0) ;
+ map->shrinkat = map->nbuckets * SHRINK_AT;
+}
+
+static bool resize0(struct hashmap *map, size_t new_cap) {
+ struct hashmap *map2 = hashmap_new_with_allocator(map->malloc, map->realloc,
+ map->free, map->elsize, new_cap, map->seed0, map->seed1, map->hash,
+ map->compare, map->elfree, map->udata);
+ if (!map2) return false;
+ for (size_t i = 0; i < map->nbuckets; i++) {
+ struct bucket *entry = bucket_at(map, i);
+ if (!entry->dib) {
+ continue;
+ }
+ entry->dib = 1;
+ size_t j = entry->hash & map2->mask;
+ while(1) {
+ struct bucket *bucket = bucket_at(map2, j);
+ if (bucket->dib == 0) {
+ memcpy(bucket, entry, map->bucketsz);
+ break;
+ }
+ if (bucket->dib < entry->dib) {
+ memcpy(map2->spare, bucket, map->bucketsz);
+ memcpy(bucket, entry, map->bucketsz);
+ memcpy(entry, map2->spare, map->bucketsz);
+ }
+ j = (j + 1) & map2->mask;
+ entry->dib += 1;
+ }
+ }
+ map->free(map->buckets);
+ map->buckets = map2->buckets;
+ map->nbuckets = map2->nbuckets;
+ map->mask = map2->mask;
+ map->growat = map2->growat;
+ map->shrinkat = map2->shrinkat;
+ map->free(map2);
+ return true;
+}
+
+static bool resize(struct hashmap *map, size_t new_cap) {
+ return resize0(map, new_cap);
+}
+
+// hashmap_set_with_hash works like hashmap_set but you provide your
+// own hash. The 'hash' callback provided to the hashmap_new function
+// will not be called
+const void *hashmap_set_with_hash(struct hashmap *map, const void *item,
+ uint64_t hash)
+{
+ hash = clip_hash(hash);
+ map->oom = false;
+ if (map->count >= map->growat) {
+ if (!resize(map, map->nbuckets*(1<growpower))) {
+ map->oom = true;
+ return NULL;
+ }
+ }
+
+ struct bucket *entry = map->edata;
+ entry->hash = hash;
+ entry->dib = 1;
+ void *eitem = bucket_item(entry);
+ memcpy(eitem, item, map->elsize);
+
+ void *bitem;
+ size_t i = entry->hash & map->mask;
+ while(1) {
+ struct bucket *bucket = bucket_at(map, i);
+ if (bucket->dib == 0) {
+ memcpy(bucket, entry, map->bucketsz);
+ map->count++;
+ return NULL;
+ }
+ bitem = bucket_item(bucket);
+ if (entry->hash == bucket->hash && (!map->compare ||
+ map->compare(eitem, bitem, map->udata) == 0))
+ {
+ memcpy(map->spare, bitem, map->elsize);
+ memcpy(bitem, eitem, map->elsize);
+ return map->spare;
+ }
+ if (bucket->dib < entry->dib) {
+ memcpy(map->spare, bucket, map->bucketsz);
+ memcpy(bucket, entry, map->bucketsz);
+ memcpy(entry, map->spare, map->bucketsz);
+ eitem = bucket_item(entry);
+ }
+ i = (i + 1) & map->mask;
+ entry->dib += 1;
+ }
+}
+
+// hashmap_set inserts or replaces an item in the hash map. If an item is
+// replaced then it is returned otherwise NULL is returned. This operation
+// may allocate memory. If the system is unable to allocate additional
+// memory then NULL is returned and hashmap_oom() returns true.
+const void *hashmap_set(struct hashmap *map, const void *item) {
+ return hashmap_set_with_hash(map, item, get_hash(map, item));
+}
+
+// hashmap_get_with_hash works like hashmap_get but you provide your
+// own hash. The 'hash' callback provided to the hashmap_new function
+// will not be called
+const void *hashmap_get_with_hash(struct hashmap *map, const void *key,
+ uint64_t hash)
+{
+ hash = clip_hash(hash);
+ size_t i = hash & map->mask;
+ while(1) {
+ struct bucket *bucket = bucket_at(map, i);
+ if (!bucket->dib) return NULL;
+ if (bucket->hash == hash) {
+ void *bitem = bucket_item(bucket);
+ if (!map->compare || map->compare(key, bitem, map->udata) == 0) {
+ return bitem;
+ }
+ }
+ i = (i + 1) & map->mask;
+ }
+}
+
+// hashmap_get returns the item based on the provided key. If the item is not
+// found then NULL is returned.
+const void *hashmap_get(struct hashmap *map, const void *key) {
+ return hashmap_get_with_hash(map, key, get_hash(map, key));
+}
+
+// hashmap_probe returns the item in the bucket at position or NULL if an item
+// is not set for that bucket. The position is 'moduloed' by the number of
+// buckets in the hashmap.
+const void *hashmap_probe(struct hashmap *map, uint64_t position) {
+ size_t i = position & map->mask;
+ struct bucket *bucket = bucket_at(map, i);
+ if (!bucket->dib) {
+ return NULL;
+ }
+ return bucket_item(bucket);
+}
+
+// hashmap_delete_with_hash works like hashmap_delete but you provide your
+// own hash. The 'hash' callback provided to the hashmap_new function
+// will not be called
+const void *hashmap_delete_with_hash(struct hashmap *map, const void *key,
+ uint64_t hash)
+{
+ hash = clip_hash(hash);
+ map->oom = false;
+ size_t i = hash & map->mask;
+ while(1) {
+ struct bucket *bucket = bucket_at(map, i);
+ if (!bucket->dib) {
+ return NULL;
+ }
+ void *bitem = bucket_item(bucket);
+ if (bucket->hash == hash && (!map->compare ||
+ map->compare(key, bitem, map->udata) == 0))
+ {
+ memcpy(map->spare, bitem, map->elsize);
+ bucket->dib = 0;
+ while(1) {
+ struct bucket *prev = bucket;
+ i = (i + 1) & map->mask;
+ bucket = bucket_at(map, i);
+ if (bucket->dib <= 1) {
+ prev->dib = 0;
+ break;
+ }
+ memcpy(prev, bucket, map->bucketsz);
+ prev->dib--;
+ }
+ map->count--;
+ if (map->nbuckets > map->cap && map->count <= map->shrinkat) {
+ // Ignore the return value. It's ok for the resize operation to
+ // fail to allocate enough memory because a shrink operation
+ // does not change the integrity of the data.
+ resize(map, map->nbuckets/2);
+ }
+ return map->spare;
+ }
+ i = (i + 1) & map->mask;
+ }
+}
+
+// hashmap_delete removes an item from the hash map and returns it. If the
+// item is not found then NULL is returned.
+const void *hashmap_delete(struct hashmap *map, const void *key) {
+ return hashmap_delete_with_hash(map, key, get_hash(map, key));
+}
+
+// hashmap_count returns the number of items in the hash map.
+size_t hashmap_count(struct hashmap *map) {
+ return map->count;
+}
+
+// hashmap_free frees the hash map
+// Every item is called with the element-freeing function given in hashmap_new,
+// if present, to free any data referenced in the elements of the hashmap.
+void hashmap_free(struct hashmap *map) {
+ if (!map) return;
+ free_elements(map);
+ map->free(map->buckets);
+ map->free(map);
+}
+
+// hashmap_oom returns true if the last hashmap_set() call failed due to the
+// system being out of memory.
+bool hashmap_oom(struct hashmap *map) {
+ return map->oom;
+}
+
+// hashmap_scan iterates over all items in the hash map
+// Param `iter` can return false to stop iteration early.
+// Returns false if the iteration has been stopped early.
+bool hashmap_scan(struct hashmap *map,
+ bool (*iter)(const void *item, void *udata), void *udata)
+{
+ for (size_t i = 0; i < map->nbuckets; i++) {
+ struct bucket *bucket = bucket_at(map, i);
+ if (bucket->dib && !iter(bucket_item(bucket), udata)) {
+ return false;
+ }
+ }
+ return true;
+}
+
+// hashmap_iter iterates one key at a time yielding a reference to an
+// entry at each iteration. Useful to write simple loops and avoid writing
+// dedicated callbacks and udata structures, as in hashmap_scan.
+//
+// map is a hash map handle. i is a pointer to a size_t cursor that
+// should be initialized to 0 at the beginning of the loop. item is a void
+// pointer pointer that is populated with the retrieved item. Note that this
+// is NOT a copy of the item stored in the hash map and can be directly
+// modified.
+//
+// Note that if hashmap_delete() is called on the hashmap being iterated,
+// the buckets are rearranged and the iterator must be reset to 0, otherwise
+// unexpected results may be returned after deletion.
+//
+// This function has not been tested for thread safety.
+//
+// The function returns true if an item was retrieved; false if the end of the
+// iteration has been reached.
+bool hashmap_iter(struct hashmap *map, size_t *i, void **item) {
+ struct bucket *bucket;
+ do {
+ if (*i >= map->nbuckets) return false;
+ bucket = bucket_at(map, *i);
+ (*i)++;
+ } while (!bucket->dib);
+ *item = bucket_item(bucket);
+ return true;
+}
+
+
+//-----------------------------------------------------------------------------
+// SipHash reference C implementation
+//
+// Copyright (c) 2012-2016 Jean-Philippe Aumasson
+//
+// Copyright (c) 2012-2014 Daniel J. Bernstein
+//
+// To the extent possible under law, the author(s) have dedicated all copyright
+// and related and neighboring rights to this software to the public domain
+// worldwide. This software is distributed without any warranty.
+//
+// You should have received a copy of the CC0 Public Domain Dedication along
+// with this software. If not, see
+// .
+//
+// default: SipHash-2-4
+//-----------------------------------------------------------------------------
+static uint64_t SIP64(const uint8_t *in, const size_t inlen, uint64_t seed0,
+ uint64_t seed1)
+{
+#define U8TO64_LE(p) \
+ { (((uint64_t)((p)[0])) | ((uint64_t)((p)[1]) << 8) | \
+ ((uint64_t)((p)[2]) << 16) | ((uint64_t)((p)[3]) << 24) | \
+ ((uint64_t)((p)[4]) << 32) | ((uint64_t)((p)[5]) << 40) | \
+ ((uint64_t)((p)[6]) << 48) | ((uint64_t)((p)[7]) << 56)) }
+#define U64TO8_LE(p, v) \
+ { U32TO8_LE((p), (uint32_t)((v))); \
+ U32TO8_LE((p) + 4, (uint32_t)((v) >> 32)); }
+#define U32TO8_LE(p, v) \
+ { (p)[0] = (uint8_t)((v)); \
+ (p)[1] = (uint8_t)((v) >> 8); \
+ (p)[2] = (uint8_t)((v) >> 16); \
+ (p)[3] = (uint8_t)((v) >> 24); }
+#define ROTL(x, b) (uint64_t)(((x) << (b)) | ((x) >> (64 - (b))))
+#define SIPROUND \
+ { v0 += v1; v1 = ROTL(v1, 13); \
+ v1 ^= v0; v0 = ROTL(v0, 32); \
+ v2 += v3; v3 = ROTL(v3, 16); \
+ v3 ^= v2; \
+ v0 += v3; v3 = ROTL(v3, 21); \
+ v3 ^= v0; \
+ v2 += v1; v1 = ROTL(v1, 17); \
+ v1 ^= v2; v2 = ROTL(v2, 32); }
+ uint64_t k0 = U8TO64_LE((uint8_t*)&seed0);
+ uint64_t k1 = U8TO64_LE((uint8_t*)&seed1);
+ uint64_t v3 = UINT64_C(0x7465646279746573) ^ k1;
+ uint64_t v2 = UINT64_C(0x6c7967656e657261) ^ k0;
+ uint64_t v1 = UINT64_C(0x646f72616e646f6d) ^ k1;
+ uint64_t v0 = UINT64_C(0x736f6d6570736575) ^ k0;
+ const uint8_t *end = in + inlen - (inlen % sizeof(uint64_t));
+ for (; in != end; in += 8) {
+ uint64_t m = U8TO64_LE(in);
+ v3 ^= m;
+ SIPROUND; SIPROUND;
+ v0 ^= m;
+ }
+ const int left = inlen & 7;
+ uint64_t b = ((uint64_t)inlen) << 56;
+ switch (left) {
+ case 7: b |= ((uint64_t)in[6]) << 48; /* fall through */
+ case 6: b |= ((uint64_t)in[5]) << 40; /* fall through */
+ case 5: b |= ((uint64_t)in[4]) << 32; /* fall through */
+ case 4: b |= ((uint64_t)in[3]) << 24; /* fall through */
+ case 3: b |= ((uint64_t)in[2]) << 16; /* fall through */
+ case 2: b |= ((uint64_t)in[1]) << 8; /* fall through */
+ case 1: b |= ((uint64_t)in[0]); break;
+ case 0: break;
+ }
+ v3 ^= b;
+ SIPROUND; SIPROUND;
+ v0 ^= b;
+ v2 ^= 0xff;
+ SIPROUND; SIPROUND; SIPROUND; SIPROUND;
+ b = v0 ^ v1 ^ v2 ^ v3;
+ uint64_t out = 0;
+ U64TO8_LE((uint8_t*)&out, b);
+ return out;
+}
+
+//-----------------------------------------------------------------------------
+// MurmurHash3 was written by Austin Appleby, and is placed in the public
+// domain. The author hereby disclaims copyright to this source code.
+//
+// Murmur3_86_128
+//-----------------------------------------------------------------------------
+static uint64_t MM86128(const void *key, const int len, uint32_t seed) {
+#define ROTL32(x, r) ((x << r) | (x >> (32 - r)))
+#define FMIX32(h) h^=h>>16; h*=0x85ebca6b; h^=h>>13; h*=0xc2b2ae35; h^=h>>16;
+ const uint8_t * data = (const uint8_t*)key;
+ const int nblocks = len / 16;
+ uint32_t h1 = seed;
+ uint32_t h2 = seed;
+ uint32_t h3 = seed;
+ uint32_t h4 = seed;
+ uint32_t c1 = 0x239b961b;
+ uint32_t c2 = 0xab0e9789;
+ uint32_t c3 = 0x38b34ae5;
+ uint32_t c4 = 0xa1e38b93;
+ const uint32_t * blocks = (const uint32_t *)(data + nblocks*16);
+ for (int i = -nblocks; i; i++) {
+ uint32_t k1 = blocks[i*4+0];
+ uint32_t k2 = blocks[i*4+1];
+ uint32_t k3 = blocks[i*4+2];
+ uint32_t k4 = blocks[i*4+3];
+ k1 *= c1; k1 = ROTL32(k1,15); k1 *= c2; h1 ^= k1;
+ h1 = ROTL32(h1,19); h1 += h2; h1 = h1*5+0x561ccd1b;
+ k2 *= c2; k2 = ROTL32(k2,16); k2 *= c3; h2 ^= k2;
+ h2 = ROTL32(h2,17); h2 += h3; h2 = h2*5+0x0bcaa747;
+ k3 *= c3; k3 = ROTL32(k3,17); k3 *= c4; h3 ^= k3;
+ h3 = ROTL32(h3,15); h3 += h4; h3 = h3*5+0x96cd1c35;
+ k4 *= c4; k4 = ROTL32(k4,18); k4 *= c1; h4 ^= k4;
+ h4 = ROTL32(h4,13); h4 += h1; h4 = h4*5+0x32ac3b17;
+ }
+ const uint8_t * tail = (const uint8_t*)(data + nblocks*16);
+ uint32_t k1 = 0;
+ uint32_t k2 = 0;
+ uint32_t k3 = 0;
+ uint32_t k4 = 0;
+ switch(len & 15) {
+ case 15: k4 ^= tail[14] << 16; /* fall through */
+ case 14: k4 ^= tail[13] << 8; /* fall through */
+ case 13: k4 ^= tail[12] << 0;
+ k4 *= c4; k4 = ROTL32(k4,18); k4 *= c1; h4 ^= k4;
+ /* fall through */
+ case 12: k3 ^= tail[11] << 24; /* fall through */
+ case 11: k3 ^= tail[10] << 16; /* fall through */
+ case 10: k3 ^= tail[ 9] << 8; /* fall through */
+ case 9: k3 ^= tail[ 8] << 0;
+ k3 *= c3; k3 = ROTL32(k3,17); k3 *= c4; h3 ^= k3;
+ /* fall through */
+ case 8: k2 ^= tail[ 7] << 24; /* fall through */
+ case 7: k2 ^= tail[ 6] << 16; /* fall through */
+ case 6: k2 ^= tail[ 5] << 8; /* fall through */
+ case 5: k2 ^= tail[ 4] << 0;
+ k2 *= c2; k2 = ROTL32(k2,16); k2 *= c3; h2 ^= k2;
+ /* fall through */
+ case 4: k1 ^= tail[ 3] << 24; /* fall through */
+ case 3: k1 ^= tail[ 2] << 16; /* fall through */
+ case 2: k1 ^= tail[ 1] << 8; /* fall through */
+ case 1: k1 ^= tail[ 0] << 0;
+ k1 *= c1; k1 = ROTL32(k1,15); k1 *= c2; h1 ^= k1;
+ /* fall through */
+ };
+ h1 ^= len; h2 ^= len; h3 ^= len; h4 ^= len;
+ h1 += h2; h1 += h3; h1 += h4;
+ h2 += h1; h3 += h1; h4 += h1;
+ FMIX32(h1); FMIX32(h2); FMIX32(h3); FMIX32(h4);
+ h1 += h2; h1 += h3; h1 += h4;
+ h2 += h1; h3 += h1; h4 += h1;
+ return (((uint64_t)h2)<<32)|h1;
+}
+
+//-----------------------------------------------------------------------------
+// xxHash Library
+// Copyright (c) 2012-2021 Yann Collet
+// All rights reserved.
+//
+// BSD 2-Clause License (https://www.opensource.org/licenses/bsd-license.php)
+//
+// xxHash3
+//-----------------------------------------------------------------------------
+#define XXH_PRIME_1 11400714785074694791ULL
+#define XXH_PRIME_2 14029467366897019727ULL
+#define XXH_PRIME_3 1609587929392839161ULL
+#define XXH_PRIME_4 9650029242287828579ULL
+#define XXH_PRIME_5 2870177450012600261ULL
+
+static uint64_t XXH_read64(const void* memptr) {
+ uint64_t val;
+ memcpy(&val, memptr, sizeof(val));
+ return val;
+}
+
+static uint32_t XXH_read32(const void* memptr) {
+ uint32_t val;
+ memcpy(&val, memptr, sizeof(val));
+ return val;
+}
+
+static uint64_t XXH_rotl64(uint64_t x, int r) {
+ return (x << r) | (x >> (64 - r));
+}
+
+static uint64_t xxh3(const void* data, size_t len, uint64_t seed) {
+ const uint8_t* p = (const uint8_t*)data;
+ const uint8_t* const end = p + len;
+ uint64_t h64;
+
+ if (len >= 32) {
+ const uint8_t* const limit = end - 32;
+ uint64_t v1 = seed + XXH_PRIME_1 + XXH_PRIME_2;
+ uint64_t v2 = seed + XXH_PRIME_2;
+ uint64_t v3 = seed + 0;
+ uint64_t v4 = seed - XXH_PRIME_1;
+
+ do {
+ v1 += XXH_read64(p) * XXH_PRIME_2;
+ v1 = XXH_rotl64(v1, 31);
+ v1 *= XXH_PRIME_1;
+
+ v2 += XXH_read64(p + 8) * XXH_PRIME_2;
+ v2 = XXH_rotl64(v2, 31);
+ v2 *= XXH_PRIME_1;
+
+ v3 += XXH_read64(p + 16) * XXH_PRIME_2;
+ v3 = XXH_rotl64(v3, 31);
+ v3 *= XXH_PRIME_1;
+
+ v4 += XXH_read64(p + 24) * XXH_PRIME_2;
+ v4 = XXH_rotl64(v4, 31);
+ v4 *= XXH_PRIME_1;
+
+ p += 32;
+ } while (p <= limit);
+
+ h64 = XXH_rotl64(v1, 1) + XXH_rotl64(v2, 7) + XXH_rotl64(v3, 12) +
+ XXH_rotl64(v4, 18);
+
+ v1 *= XXH_PRIME_2;
+ v1 = XXH_rotl64(v1, 31);
+ v1 *= XXH_PRIME_1;
+ h64 ^= v1;
+ h64 = h64 * XXH_PRIME_1 + XXH_PRIME_4;
+
+ v2 *= XXH_PRIME_2;
+ v2 = XXH_rotl64(v2, 31);
+ v2 *= XXH_PRIME_1;
+ h64 ^= v2;
+ h64 = h64 * XXH_PRIME_1 + XXH_PRIME_4;
+
+ v3 *= XXH_PRIME_2;
+ v3 = XXH_rotl64(v3, 31);
+ v3 *= XXH_PRIME_1;
+ h64 ^= v3;
+ h64 = h64 * XXH_PRIME_1 + XXH_PRIME_4;
+
+ v4 *= XXH_PRIME_2;
+ v4 = XXH_rotl64(v4, 31);
+ v4 *= XXH_PRIME_1;
+ h64 ^= v4;
+ h64 = h64 * XXH_PRIME_1 + XXH_PRIME_4;
+ }
+ else {
+ h64 = seed + XXH_PRIME_5;
+ }
+
+ h64 += (uint64_t)len;
+
+ while (p + 8 <= end) {
+ uint64_t k1 = XXH_read64(p);
+ k1 *= XXH_PRIME_2;
+ k1 = XXH_rotl64(k1, 31);
+ k1 *= XXH_PRIME_1;
+ h64 ^= k1;
+ h64 = XXH_rotl64(h64, 27) * XXH_PRIME_1 + XXH_PRIME_4;
+ p += 8;
+ }
+
+ if (p + 4 <= end) {
+ h64 ^= (uint64_t)(XXH_read32(p)) * XXH_PRIME_1;
+ h64 = XXH_rotl64(h64, 23) * XXH_PRIME_2 + XXH_PRIME_3;
+ p += 4;
+ }
+
+ while (p < end) {
+ h64 ^= (*p) * XXH_PRIME_5;
+ h64 = XXH_rotl64(h64, 11) * XXH_PRIME_1;
+ p++;
+ }
+
+ h64 ^= h64 >> 33;
+ h64 *= XXH_PRIME_2;
+ h64 ^= h64 >> 29;
+ h64 *= XXH_PRIME_3;
+ h64 ^= h64 >> 32;
+
+ return h64;
+}
+
+// hashmap_sip returns a hash value for `data` using SipHash-2-4.
+uint64_t hashmap_sip(const void *data, size_t len, uint64_t seed0,
+ uint64_t seed1)
+{
+ return SIP64((uint8_t*)data, len, seed0, seed1);
+}
+
+// hashmap_murmur returns a hash value for `data` using Murmur3_86_128.
+uint64_t hashmap_murmur(const void *data, size_t len, uint64_t seed0,
+ uint64_t seed1)
+{
+ (void)seed1;
+ return MM86128(data, len, seed0);
+}
+
+uint64_t hashmap_xxhash3(const void *data, size_t len, uint64_t seed0,
+ uint64_t seed1)
+{
+ (void)seed1;
+ return xxh3(data, len ,seed0);
+}
+
+//==============================================================================
+// TESTS AND BENCHMARKS
+// $ cc -DHASHMAP_TEST hashmap.c && ./a.out # run tests
+// $ cc -DHASHMAP_TEST -O3 hashmap.c && BENCH=1 ./a.out # run benchmarks
+//==============================================================================
+#ifdef HASHMAP_TEST
+
+static size_t deepcount(struct hashmap *map) {
+ size_t count = 0;
+ for (size_t i = 0; i < map->nbuckets; i++) {
+ if (bucket_at(map, i)->dib) {
+ count++;
+ }
+ }
+ return count;
+}
+
+#ifdef __GNUC__
+#pragma GCC diagnostic ignored "-Wpedantic"
+#endif
+#ifdef __clang__
+#pragma GCC diagnostic ignored "-Wunknown-warning-option"
+#pragma GCC diagnostic ignored "-Wcompound-token-split-by-macro"
+#pragma GCC diagnostic ignored "-Wgnu-statement-expression-from-macro-expansion"
+#endif
+#ifdef __GNUC__
+#pragma GCC diagnostic ignored "-Wunused-parameter"
+#endif
+
+#include
+#include
+#include
+#include
+#include
+#include "hashmap.h"
+
+static bool rand_alloc_fail = false;
+static int rand_alloc_fail_odds = 3; // 1 in 3 chance malloc will fail.
+static uintptr_t total_allocs = 0;
+static uintptr_t total_mem = 0;
+
+static void *xmalloc(size_t size) {
+ if (rand_alloc_fail && rand()%rand_alloc_fail_odds == 0) {
+ return NULL;
+ }
+ void *mem = malloc(sizeof(uintptr_t)+size);
+ assert(mem);
+ *(uintptr_t*)mem = size;
+ total_allocs++;
+ total_mem += size;
+ return (char*)mem+sizeof(uintptr_t);
+}
+
+static void xfree(void *ptr) {
+ if (ptr) {
+ total_mem -= *(uintptr_t*)((char*)ptr-sizeof(uintptr_t));
+ free((char*)ptr-sizeof(uintptr_t));
+ total_allocs--;
+ }
+}
+
+static void shuffle(void *array, size_t numels, size_t elsize) {
+ char tmp[elsize];
+ char *arr = array;
+ for (size_t i = 0; i < numels - 1; i++) {
+ int j = i + rand() / (RAND_MAX / (numels - i) + 1);
+ memcpy(tmp, arr + j * elsize, elsize);
+ memcpy(arr + j * elsize, arr + i * elsize, elsize);
+ memcpy(arr + i * elsize, tmp, elsize);
+ }
+}
+
+static bool iter_ints(const void *item, void *udata) {
+ int *vals = *(int**)udata;
+ vals[*(int*)item] = 1;
+ return true;
+}
+
+static int compare_ints_udata(const void *a, const void *b, void *udata) {
+ return *(int*)a - *(int*)b;
+}
+
+static int compare_strs(const void *a, const void *b, void *udata) {
+ return strcmp(*(char**)a, *(char**)b);
+}
+
+static uint64_t hash_int(const void *item, uint64_t seed0, uint64_t seed1) {
+ return hashmap_xxhash3(item, sizeof(int), seed0, seed1);
+ // return hashmap_sip(item, sizeof(int), seed0, seed1);
+ // return hashmap_murmur(item, sizeof(int), seed0, seed1);
+}
+
+static uint64_t hash_str(const void *item, uint64_t seed0, uint64_t seed1) {
+ return hashmap_xxhash3(*(char**)item, strlen(*(char**)item), seed0, seed1);
+ // return hashmap_sip(*(char**)item, strlen(*(char**)item), seed0, seed1);
+ // return hashmap_murmur(*(char**)item, strlen(*(char**)item), seed0, seed1);
+}
+
+static void free_str(void *item) {
+ xfree(*(char**)item);
+}
+
+static void all(void) {
+ int seed = getenv("SEED")?atoi(getenv("SEED")):time(NULL);
+ int N = getenv("N")?atoi(getenv("N")):2000;
+ printf("seed=%d, count=%d, item_size=%zu\n", seed, N, sizeof(int));
+ srand(seed);
+
+ rand_alloc_fail = true;
+
+ // test sip and murmur hashes
+ assert(hashmap_sip("hello", 5, 1, 2) == 2957200328589801622);
+ assert(hashmap_murmur("hello", 5, 1, 2) == 1682575153221130884);
+ assert(hashmap_xxhash3("hello", 5, 1, 2) == 2584346877953614258);
+
+ int *vals;
+ while (!(vals = xmalloc(N * sizeof(int)))) {}
+ for (int i = 0; i < N; i++) {
+ vals[i] = i;
+ }
+
+ struct hashmap *map;
+
+ while (!(map = hashmap_new(sizeof(int), 0, seed, seed,
+ hash_int, compare_ints_udata, NULL, NULL))) {}
+ shuffle(vals, N, sizeof(int));
+ for (int i = 0; i < N; i++) {
+ // // printf("== %d ==\n", vals[i]);
+ assert(map->count == (size_t)i);
+ assert(map->count == hashmap_count(map));
+ assert(map->count == deepcount(map));
+ const int *v;
+ assert(!hashmap_get(map, &vals[i]));
+ assert(!hashmap_delete(map, &vals[i]));
+ while (true) {
+ assert(!hashmap_set(map, &vals[i]));
+ if (!hashmap_oom(map)) {
+ break;
+ }
+ }
+
+ for (int j = 0; j < i; j++) {
+ v = hashmap_get(map, &vals[j]);
+ assert(v && *v == vals[j]);
+ }
+ while (true) {
+ v = hashmap_set(map, &vals[i]);
+ if (!v) {
+ assert(hashmap_oom(map));
+ continue;
+ } else {
+ assert(!hashmap_oom(map));
+ assert(v && *v == vals[i]);
+ break;
+ }
+ }
+ v = hashmap_get(map, &vals[i]);
+ assert(v && *v == vals[i]);
+ v = hashmap_delete(map, &vals[i]);
+ assert(v && *v == vals[i]);
+ assert(!hashmap_get(map, &vals[i]));
+ assert(!hashmap_delete(map, &vals[i]));
+ assert(!hashmap_set(map, &vals[i]));
+ assert(map->count == (size_t)(i+1));
+ assert(map->count == hashmap_count(map));
+ assert(map->count == deepcount(map));
+ }
+
+ int *vals2;
+ while (!(vals2 = xmalloc(N * sizeof(int)))) {}
+ memset(vals2, 0, N * sizeof(int));
+ assert(hashmap_scan(map, iter_ints, &vals2));
+
+ // Test hashmap_iter. This does the same as hashmap_scan above.
+ size_t iter = 0;
+ void *iter_val;
+ while (hashmap_iter (map, &iter, &iter_val)) {
+ assert (iter_ints(iter_val, &vals2));
+ }
+ for (int i = 0; i < N; i++) {
+ assert(vals2[i] == 1);
+ }
+ xfree(vals2);
+
+ shuffle(vals, N, sizeof(int));
+ for (int i = 0; i < N; i++) {
+ const int *v;
+ v = hashmap_delete(map, &vals[i]);
+ assert(v && *v == vals[i]);
+ assert(!hashmap_get(map, &vals[i]));
+ assert(map->count == (size_t)(N-i-1));
+ assert(map->count == hashmap_count(map));
+ assert(map->count == deepcount(map));
+ for (int j = N-1; j > i; j--) {
+ v = hashmap_get(map, &vals[j]);
+ assert(v && *v == vals[j]);
+ }
+ }
+
+ for (int i = 0; i < N; i++) {
+ while (true) {
+ assert(!hashmap_set(map, &vals[i]));
+ if (!hashmap_oom(map)) {
+ break;
+ }
+ }
+ }
+
+ assert(map->count != 0);
+ size_t prev_cap = map->cap;
+ hashmap_clear(map, true);
+ assert(prev_cap < map->cap);
+ assert(map->count == 0);
+
+
+ for (int i = 0; i < N; i++) {
+ while (true) {
+ assert(!hashmap_set(map, &vals[i]));
+ if (!hashmap_oom(map)) {
+ break;
+ }
+ }
+ }
+
+ prev_cap = map->cap;
+ hashmap_clear(map, false);
+ assert(prev_cap == map->cap);
+
+ hashmap_free(map);
+
+ xfree(vals);
+
+
+ while (!(map = hashmap_new(sizeof(char*), 0, seed, seed,
+ hash_str, compare_strs, free_str, NULL)));
+
+ for (int i = 0; i < N; i++) {
+ char *str;
+ while (!(str = xmalloc(16)));
+ snprintf(str, 16, "s%i", i);
+ while(!hashmap_set(map, &str));
+ }
+
+ hashmap_clear(map, false);
+ assert(hashmap_count(map) == 0);
+
+ for (int i = 0; i < N; i++) {
+ char *str;
+ while (!(str = xmalloc(16)));
+ snprintf(str, 16, "s%i", i);
+ while(!hashmap_set(map, &str));
+ }
+
+ hashmap_free(map);
+
+ if (total_allocs != 0) {
+ fprintf(stderr, "total_allocs: expected 0, got %lu\n", total_allocs);
+ exit(1);
+ }
+}
+
+#define bench(name, N, code) {{ \
+ if (strlen(name) > 0) { \
+ printf("%-14s ", name); \
+ } \
+ size_t tmem = total_mem; \
+ size_t tallocs = total_allocs; \
+ uint64_t bytes = 0; \
+ clock_t begin = clock(); \
+ for (int i = 0; i < N; i++) { \
+ (code); \
+ } \
+ clock_t end = clock(); \
+ double elapsed_secs = (double)(end - begin) / CLOCKS_PER_SEC; \
+ double bytes_sec = (double)bytes/elapsed_secs; \
+ printf("%d ops in %.3f secs, %.0f ns/op, %.0f op/sec", \
+ N, elapsed_secs, \
+ elapsed_secs/(double)N*1e9, \
+ (double)N/elapsed_secs \
+ ); \
+ if (bytes > 0) { \
+ printf(", %.1f GB/sec", bytes_sec/1024/1024/1024); \
+ } \
+ if (total_mem > tmem) { \
+ size_t used_mem = total_mem-tmem; \
+ printf(", %.2f bytes/op", (double)used_mem/N); \
+ } \
+ if (total_allocs > tallocs) { \
+ size_t used_allocs = total_allocs-tallocs; \
+ printf(", %.2f allocs/op", (double)used_allocs/N); \
+ } \
+ printf("\n"); \
+}}
+
+static void benchmarks(void) {
+ int seed = getenv("SEED")?atoi(getenv("SEED")):time(NULL);
+ int N = getenv("N")?atoi(getenv("N")):5000000;
+ printf("seed=%d, count=%d, item_size=%zu\n", seed, N, sizeof(int));
+ srand(seed);
+
+
+ int *vals = xmalloc(N * sizeof(int));
+ for (int i = 0; i < N; i++) {
+ vals[i] = i;
+ }
+
+ shuffle(vals, N, sizeof(int));
+
+ struct hashmap *map;
+ shuffle(vals, N, sizeof(int));
+
+ map = hashmap_new(sizeof(int), 0, seed, seed, hash_int, compare_ints_udata,
+ NULL, NULL);
+ bench("set", N, {
+ const int *v = hashmap_set(map, &vals[i]);
+ assert(!v);
+ })
+ shuffle(vals, N, sizeof(int));
+ bench("get", N, {
+ const int *v = hashmap_get(map, &vals[i]);
+ assert(v && *v == vals[i]);
+ })
+ shuffle(vals, N, sizeof(int));
+ bench("delete", N, {
+ const int *v = hashmap_delete(map, &vals[i]);
+ assert(v && *v == vals[i]);
+ })
+ hashmap_free(map);
+
+ map = hashmap_new(sizeof(int), N, seed, seed, hash_int, compare_ints_udata,
+ NULL, NULL);
+ bench("set (cap)", N, {
+ const int *v = hashmap_set(map, &vals[i]);
+ assert(!v);
+ })
+ shuffle(vals, N, sizeof(int));
+ bench("get (cap)", N, {
+ const int *v = hashmap_get(map, &vals[i]);
+ assert(v && *v == vals[i]);
+ })
+ shuffle(vals, N, sizeof(int));
+ bench("delete (cap)" , N, {
+ const int *v = hashmap_delete(map, &vals[i]);
+ assert(v && *v == vals[i]);
+ })
+
+ hashmap_free(map);
+
+
+ xfree(vals);
+
+ if (total_allocs != 0) {
+ fprintf(stderr, "total_allocs: expected 0, got %lu\n", total_allocs);
+ exit(1);
+ }
+}
+
+int main(void) {
+ hashmap_set_allocator(xmalloc, xfree);
+
+ if (getenv("BENCH")) {
+ printf("Running hashmap.c benchmarks...\n");
+ benchmarks();
+ } else {
+ printf("Running hashmap.c tests...\n");
+ all();
+ printf("PASSED\n");
+ }
+}
+
+
+#endif
+
+
+
diff --git a/gumbo-parser/src/hashmap.h b/gumbo-parser/src/hashmap.h
new file mode 100644
index 0000000000..e22990e045
--- /dev/null
+++ b/gumbo-parser/src/hashmap.h
@@ -0,0 +1,62 @@
+// Copyright 2020 Joshua J Baker. All rights reserved.
+// Use of this source code is governed by an MIT-style
+// license that can be found in the LICENSE file.
+
+#ifndef HASHMAP_H
+#define HASHMAP_H
+
+#include
+#include
+#include
+
+#if defined(__cplusplus)
+extern "C" {
+#endif // __cplusplus
+
+struct hashmap;
+
+struct hashmap *hashmap_new(size_t elsize, size_t cap, uint64_t seed0,
+ uint64_t seed1,
+ uint64_t (*hash)(const void *item, uint64_t seed0, uint64_t seed1),
+ int (*compare)(const void *a, const void *b, void *udata),
+ void (*elfree)(void *item),
+ void *udata);
+
+struct hashmap *hashmap_new_with_allocator(void *(*malloc)(size_t),
+ void *(*realloc)(void *, size_t), void (*free)(void*), size_t elsize,
+ size_t cap, uint64_t seed0, uint64_t seed1,
+ uint64_t (*hash)(const void *item, uint64_t seed0, uint64_t seed1),
+ int (*compare)(const void *a, const void *b, void *udata),
+ void (*elfree)(void *item),
+ void *udata);
+
+void hashmap_free(struct hashmap *map);
+void hashmap_clear(struct hashmap *map, bool update_cap);
+size_t hashmap_count(struct hashmap *map);
+bool hashmap_oom(struct hashmap *map);
+const void *hashmap_get(struct hashmap *map, const void *item);
+const void *hashmap_set(struct hashmap *map, const void *item);
+const void *hashmap_delete(struct hashmap *map, const void *item);
+const void *hashmap_probe(struct hashmap *map, uint64_t position);
+bool hashmap_scan(struct hashmap *map, bool (*iter)(const void *item, void *udata), void *udata);
+bool hashmap_iter(struct hashmap *map, size_t *i, void **item);
+
+uint64_t hashmap_sip(const void *data, size_t len, uint64_t seed0, uint64_t seed1);
+uint64_t hashmap_murmur(const void *data, size_t len, uint64_t seed0, uint64_t seed1);
+uint64_t hashmap_xxhash3(const void *data, size_t len, uint64_t seed0, uint64_t seed1);
+
+const void *hashmap_get_with_hash(struct hashmap *map, const void *key, uint64_t hash);
+const void *hashmap_delete_with_hash(struct hashmap *map, const void *key, uint64_t hash);
+const void *hashmap_set_with_hash(struct hashmap *map, const void *item, uint64_t hash);
+void hashmap_set_grow_by_power(struct hashmap *map, size_t power);
+void hashmap_set_load_factor(struct hashmap *map, double load_factor);
+
+
+// DEPRECATED: use `hashmap_new_with_allocator`
+void hashmap_set_allocator(void *(*malloc)(size_t), void (*free)(void*));
+
+#if defined(__cplusplus)
+}
+#endif // __cplusplus
+
+#endif // HASHMAP_H
diff --git a/gumbo-parser/src/nokogiri_gumbo.h b/gumbo-parser/src/nokogiri_gumbo.h
index 69555607ff..cdec31674b 100644
--- a/gumbo-parser/src/nokogiri_gumbo.h
+++ b/gumbo-parser/src/nokogiri_gumbo.h
@@ -318,21 +318,6 @@ const char* gumbo_normalized_tagname(GumboTag tag);
*/
void gumbo_tag_from_original_text(GumboStringPiece* text);
-/**
- * Fixes the case of SVG elements that are not all lowercase. This is
- * not done at parse time because there's no place to store a mutated
- * tag name. `tag_name` is an enum (which will be `TAG_UNKNOWN` for most
- * SVG tags without special handling), while `original_tag_name` is a
- * pointer into the original buffer. Instead, we provide this helper
- * function that clients can use to rename SVG tags as appropriate.
- * Returns the case-normalized SVG tagname if a replacement is found, or
- * `NULL` if no normalization is called for. The return value is static
- * data and owned by the library.
- *
- * @see https://html.spec.whatwg.org/multipage/parsing.html#parsing-main-inforeign
- */
-const char* gumbo_normalize_svg_tagname(const GumboStringPiece* tagname);
-
/**
* Converts a tag name string (which may be in upper or mixed case) to a
* tag enum.
diff --git a/gumbo-parser/src/parser.c b/gumbo-parser/src/parser.c
index 96e6f2bdbe..6498b4850c 100644
--- a/gumbo-parser/src/parser.c
+++ b/gumbo-parser/src/parser.c
@@ -1962,14 +1962,6 @@ static void merge_attributes (
#endif
}
-const char* gumbo_normalize_svg_tagname(const GumboStringPiece* tag) {
- const StringReplacement *replacement = gumbo_get_svg_tag_replacement (
- tag->data,
- tag->length
- );
- return replacement ? replacement->to : NULL;
-}
-
// https://html.spec.whatwg.org/multipage/parsing.html#adjust-foreign-attributes
// This destructively modifies any matching attributes on the token and sets the
// namespace appropriately.
diff --git a/gumbo-parser/src/string_set.c b/gumbo-parser/src/string_set.c
new file mode 100644
index 0000000000..e296a02c46
--- /dev/null
+++ b/gumbo-parser/src/string_set.c
@@ -0,0 +1,41 @@
+#include "string_set.h"
+
+#include
+#include "hashmap.h"
+
+#define SEED0 0xf00ba2
+#define SEED1 0xfa1afe1
+
+static int
+string_compare(const void *a, const void *b, void *udata) {
+ return strcmp((const char *)a, (const char *)b);
+}
+
+static uint64_t
+string_hash(const void *item, uint64_t seed0, uint64_t seed1) {
+ const char *str = (const char *)item;
+ return hashmap_xxhash3(str, strlen(str), seed0, seed1);
+}
+
+GumboStringSet *
+gumbo_string_set_new(size_t cap)
+{
+ return hashmap_new(sizeof(char *), cap, SEED0, SEED1, string_hash, string_compare, NULL, NULL);
+}
+
+void gumbo_string_set_free(GumboStringSet *set)
+{
+ hashmap_free(set);
+}
+
+void
+gumbo_string_set_insert(GumboStringSet *set, const char *str)
+{
+ hashmap_set(set, str);
+}
+
+int
+gumbo_string_set_contains(GumboStringSet *set, const char *str)
+{
+ return hashmap_get(set, str) == NULL ? 0 : 1;
+}
diff --git a/gumbo-parser/src/string_set.h b/gumbo-parser/src/string_set.h
new file mode 100644
index 0000000000..8fd544d17f
--- /dev/null
+++ b/gumbo-parser/src/string_set.h
@@ -0,0 +1,21 @@
+#ifndef STRING_SET_H
+#define STRING_SET_H
+
+#include
+
+#if defined(__cplusplus)
+extern "C" {
+#endif // __cplusplus
+
+typedef struct hashmap GumboStringSet;
+
+GumboStringSet* gumbo_string_set_new(size_t cap);
+void gumbo_string_set_free(GumboStringSet *set);
+void gumbo_string_set_insert(GumboStringSet *set, const char *str);
+int gumbo_string_set_contains(GumboStringSet *set, const char *str);
+
+#if defined(__cplusplus)
+}
+#endif // __cplusplus
+
+#endif // STRING_SET_H
diff --git a/gumbo-parser/src/tokenizer.c b/gumbo-parser/src/tokenizer.c
index bc34181351..e82dd873a4 100644
--- a/gumbo-parser/src/tokenizer.c
+++ b/gumbo-parser/src/tokenizer.c
@@ -58,6 +58,10 @@
#include "utf8.h"
#include "util.h"
#include "vector.h"
+#include "string_set.h"
+
+// Tuned this based on benchmark in https://github.com/sparklemotion/nokogiri/issues/2568
+#define GUMBO_ATTRIBUTES_LOOKUP_MIN_SIZE 16
// Compared against _temporary_buffer to determine if we're in
// double-escaped script mode.
@@ -99,6 +103,7 @@ typedef struct GumboInternalTagState {
// attributes are added as soon as their attribute name state is complete, and
// values are filled in by operating on _attributes.data[attributes.length-1].
GumboVector /* GumboAttribute */ _attributes;
+ GumboStringSet* _attributes_lookup;
// If true, the next attribute value to be finished should be dropped. This
// happens if a duplicate attribute name is encountered - we want to consume
@@ -440,11 +445,9 @@ static StateResult emit_doctype(GumboParser* parser, GumboToken* output) {
return EMIT_TOKEN;
}
-// Debug-only function that explicitly sets the attribute vector data to NULL so
-// it can be asserted on tag creation, verifying that there are no memory leaks.
static void mark_tag_state_as_empty(GumboTagState* tag_state) {
- UNUSED_IF_NDEBUG(tag_state);
tag_state->_name = NULL;
+ tag_state->_attributes_lookup = NULL;
#ifndef NDEBUG
tag_state->_attributes = kGumboEmptyVector;
#endif
@@ -461,6 +464,7 @@ static StateResult emit_current_tag(GumboParser* parser, GumboToken* output) {
output->v.start_tag.attributes = tag_state->_attributes;
output->v.start_tag.is_self_closing = tag_state->_is_self_closing;
tag_state->_last_start_tag = tag_state->_tag;
+ gumbo_string_set_free(tag_state->_attributes_lookup);
mark_tag_state_as_empty(tag_state);
gumbo_debug(
"Emitted start tag %s.\n", gumbo_normalized_tagname(tag_state->_tag));
@@ -480,6 +484,7 @@ static StateResult emit_current_tag(GumboParser* parser, GumboToken* output) {
gumbo_destroy_attribute(tag_state->_attributes.data[i]);
}
gumbo_free(tag_state->_attributes.data);
+ gumbo_string_set_free(tag_state->_attributes_lookup);
mark_tag_state_as_empty(tag_state);
gumbo_debug(
"Emitted end tag %s.\n", gumbo_normalized_tagname(tag_state->_tag));
@@ -508,6 +513,7 @@ static void abandon_current_tag(GumboParser* parser) {
}
gumbo_free(tag_state->_name);
gumbo_free(tag_state->_attributes.data);
+ gumbo_string_set_free(tag_state->_attributes_lookup);
mark_tag_state_as_empty(tag_state);
gumbo_string_buffer_destroy(&tag_state->_buffer);
gumbo_debug("Abandoning current tag.\n");
@@ -786,6 +792,8 @@ static void finish_attribute_name(GumboParser* parser) {
GumboTokenizerState* tokenizer = parser->_tokenizer_state;
GumboTagState* tag_state = &tokenizer->_tag_state;
GumboVector* /* GumboAttribute* */ attributes = &tag_state->_attributes;
+ GumboStringSet* attributes_lookup = tag_state->_attributes_lookup;
+ char* attr_name = NULL;
int max_attributes = parser->_options->max_attributes;
if (unlikely(max_attributes >= 0 && attributes->length >= (unsigned int) max_attributes)) {
@@ -796,32 +804,42 @@ static void finish_attribute_name(GumboParser* parser) {
return;
}
+ if (attributes->length >= GUMBO_ATTRIBUTES_LOOKUP_MIN_SIZE && tag_state->_attributes_lookup == NULL) {
+ // build the hash table of attributes
+ attributes_lookup = tag_state->_attributes_lookup = gumbo_string_set_new(GUMBO_ATTRIBUTES_LOOKUP_MIN_SIZE * 2);
+ for (unsigned int i = 0; i < attributes->length; ++i) {
+ GumboAttribute* attr = attributes->data[i];
+ gumbo_string_set_insert(attributes_lookup, attr->name);
+ }
+ }
+
// May've been set by a previous attribute without a value; reset it here.
tag_state->_drop_next_attr_value = false;
assert(tag_state->_attributes.data);
assert(tag_state->_attributes.capacity);
- for (unsigned int i = 0; i < attributes->length; ++i) {
- GumboAttribute* attr = attributes->data[i];
- if (
- strlen(attr->name) == tag_state->_buffer.length
- && 0 == memcmp (
- attr->name,
- tag_state->_buffer.data,
- tag_state->_buffer.length
- )
- ) {
- // Identical attribute; bail.
- add_duplicate_attr_error(parser);
- reinitialize_tag_buffer(parser);
- tag_state->_drop_next_attr_value = true;
- return;
+ if (!attributes_lookup) {
+ for (unsigned int i = 0; i < attributes->length; ++i) {
+ GumboAttribute* attr = attributes->data[i];
+ if (strlen(attr->name) == tag_state->_buffer.length
+ && 0 == memcmp(attr->name, tag_state->_buffer.data, tag_state->_buffer.length)) {
+ goto duplicate_attribute;
+ }
+ }
+ } else {
+ attr_name = gumbo_string_buffer_to_string(&tag_state->_buffer);
+ if (gumbo_string_set_contains(attributes_lookup, attr_name)) {
+ goto duplicate_attribute;
}
}
GumboAttribute* attr = gumbo_alloc(sizeof(GumboAttribute));
attr->attr_namespace = GUMBO_ATTR_NAMESPACE_NONE;
- copy_over_tag_buffer(parser, &attr->name);
+ if (attr_name) {
+ attr->name = attr_name;
+ } else {
+ copy_over_tag_buffer(parser, &attr->name);
+ }
copy_over_original_tag_text (
parser,
&attr->original_name,
@@ -836,7 +854,19 @@ static void finish_attribute_name(GumboParser* parser) {
&attr->name_end
);
gumbo_vector_add(attr, attributes);
+ if (attributes_lookup) {
+ gumbo_string_set_insert(attributes_lookup, attr->name);
+ }
+ reinitialize_tag_buffer(parser);
+ return;
+
+duplicate_attribute:
+ // Identical attribute; bail.
+ gumbo_free(attr_name);
+ add_duplicate_attr_error(parser);
reinitialize_tag_buffer(parser);
+ tag_state->_drop_next_attr_value = true;
+ return;
}
// Finishes an attribute value. This sets the value of the most recently added
diff --git a/gumbo-parser/test/tokenizer.cc b/gumbo-parser/test/tokenizer.cc
index 9cde694cf0..139dda10f2 100644
--- a/gumbo-parser/test/tokenizer.cc
+++ b/gumbo-parser/test/tokenizer.cc
@@ -4684,6 +4684,42 @@ TEST_F(GumboTokenizerTest, Data_MultipleAttributes) {
NextChar('z');
}
+TEST_F(GumboTokenizerTest, Data_DuplicateAttributes) {
+ SetInput("");
+ NextStartTag(GUMBO_TAG_SPAN, true);
+
+ Error(GUMBO_ERR_DUPLICATE_ATTRIBUTE);
+ ASSERT_EQ(3, token_.v.start_tag.attributes.length);
+
+ GumboAttribute *attr = static_cast(token_.v.start_tag.attributes.data[0]);
+ EXPECT_STREQ("foo", attr->name);
+ EXPECT_STREQ("123", attr->value);
+
+ attr = static_cast(token_.v.start_tag.attributes.data[1]);
+ EXPECT_STREQ("bar", attr->name);
+ EXPECT_STREQ("456", attr->value);
+
+ attr = static_cast(token_.v.start_tag.attributes.data[2]);
+ EXPECT_STREQ("baz", attr->name);
+ EXPECT_STREQ("abc", attr->value);
+}
+
+TEST_F(GumboTokenizerTest, Data_DuplicateAttributesWithHashtable) {
+ SetInput("");
+ NextStartTag(GUMBO_TAG_SPAN, true);
+
+ Error(GUMBO_ERR_DUPLICATE_ATTRIBUTE);
+ ASSERT_EQ(26, token_.v.start_tag.attributes.length);
+
+ GumboAttribute *attr = static_cast(token_.v.start_tag.attributes.data[0]);
+ EXPECT_STREQ("a", attr->name);
+ EXPECT_STREQ("1", attr->value);
+
+ attr = static_cast(token_.v.start_tag.attributes.data[25]);
+ EXPECT_STREQ("z", attr->name);
+ EXPECT_STREQ("1", attr->value);
+}
+
TEST_F(GumboTokenizerTest, Data_LT_Alpha_Slash_GT) {
SetInput("
z");
NextStartTag(GUMBO_TAG_BR);
diff --git a/lib/nokogiri/css/xpath_visitor.rb b/lib/nokogiri/css/xpath_visitor.rb
index dd228cf070..4032d814ed 100644
--- a/lib/nokogiri/css/xpath_visitor.rb
+++ b/lib/nokogiri/css/xpath_visitor.rb
@@ -283,7 +283,8 @@ def visit_element_name(node)
else
node.value.join(":")
end
- elsif @namespaces&.key?("xmlns") # apply the default namespace if it's declared
+ elsif node.value.first != "*" && @namespaces&.key?("xmlns")
+ # apply the default namespace (if one is present) to a non-wildcard selector
"xmlns:#{node.value.first}"
else
node.value.first
diff --git a/lib/nokogiri/extension.rb b/lib/nokogiri/extension.rb
index 47492bc786..f4ff04abd0 100644
--- a/lib/nokogiri/extension.rb
+++ b/lib/nokogiri/extension.rb
@@ -16,8 +16,8 @@
If that's the case, then please install Nokogiri via the `ruby` platform gem:
gem install nokogiri --platform=ruby
- or:
- bundle config set force_ruby_platform true
+ or, in your Gemfile:
+ gem "nokogiri", force_ruby_platform: true
Please visit https://nokogiri.org/tutorials/installing_nokogiri.html for more help.
diff --git a/lib/nokogiri/html4/element_description_defaults.rb b/lib/nokogiri/html4/element_description_defaults.rb
index 79a8b81064..948323b5f4 100644
--- a/lib/nokogiri/html4/element_description_defaults.rb
+++ b/lib/nokogiri/html4/element_description_defaults.rb
@@ -9,7 +9,6 @@ class ElementDescription
# defined there.
Desc = Struct.new(
- "HTMLElementDescription",
:name,
:startTag,
:endTag,
diff --git a/lib/nokogiri/html4/encoding_reader.rb b/lib/nokogiri/html4/encoding_reader.rb
index ce8069adcf..aec2676332 100644
--- a/lib/nokogiri/html4/encoding_reader.rb
+++ b/lib/nokogiri/html4/encoding_reader.rb
@@ -108,7 +108,7 @@ def read(len)
ret = @firstchunk.slice!(0, len)
if (len -= ret.length) > 0
- (rest = @io.read(len)) && ret << (rest)
+ (rest = @io.read(len)) && ret << rest
end
if ret.empty?
nil
diff --git a/lib/nokogiri/version/constant.rb b/lib/nokogiri/version/constant.rb
index 8a6fe62f17..11b5a4b83d 100644
--- a/lib/nokogiri/version/constant.rb
+++ b/lib/nokogiri/version/constant.rb
@@ -2,5 +2,5 @@
module Nokogiri
# The version of Nokogiri you are using
- VERSION = "1.18.0"
+ VERSION = "1.19.0.dev"
end
diff --git a/lib/nokogiri/xml/builder.rb b/lib/nokogiri/xml/builder.rb
index 617ef45e73..eb05f22135 100644
--- a/lib/nokogiri/xml/builder.rb
+++ b/lib/nokogiri/xml/builder.rb
@@ -200,7 +200,7 @@ module XML
# === Namespace inheritance
#
# In the Builder context, children will inherit their parent's namespace. This is the same
- # behavior as if the underlying {XML::Document} set +namespace_inheritance+ to +true+:
+ # behavior as if the underlying XML::Document set +namespace_inheritance+ to +true+:
#
# result = Nokogiri::XML::Builder.new do |xml|
# xml["soapenv"].Envelope("xmlns:soapenv" => "http://schemas.xmlsoap.org/soap/envelope/") do
@@ -229,7 +229,7 @@ module XML
# #
# #
#
- # For more information on namespace inheritance, please see {XML::Document#namespace_inheritance}
+ # For more information on namespace inheritance, please see XML::Document#namespace_inheritance
#
#
# == Document Types
@@ -314,7 +314,7 @@ def initialize(options = {}, root = nil, &block)
@context = nil
@arity = nil
- @ns = nil
+ @ns_prefix = nil
options = DEFAULT_DOCUMENT_OPTIONS.merge(options)
options.each do |k, v|
@@ -355,20 +355,8 @@ def comment(string)
###
# Build a tag that is associated with namespace +ns+. Raises an
# ArgumentError if +ns+ has not been defined higher in the tree.
- def [](ns)
- if @parent != @doc
- @ns = @parent.namespace_definitions.find { |x| x.prefix == ns.to_s }
- end
- return self if @ns
-
- @parent.ancestors.each do |a|
- next if a == doc
-
- @ns = a.namespace_definitions.find { |x| x.prefix == ns.to_s }
- return self if @ns
- end
-
- @ns = { pending: ns.to_s }
+ def [](ns_prefix)
+ @ns_prefix = ns_prefix.to_s
self
end
@@ -395,29 +383,33 @@ def method_missing(method, *args, &block) # :nodoc:
if @context&.respond_to?(method)
@context.send(method, *args, &block)
else
- node = @doc.create_element(method.to_s.sub(/[_!]$/, ""), *args) do |n|
- # Set up the namespace
- if @ns.is_a?(Nokogiri::XML::Namespace)
- n.namespace = @ns
- @ns = nil
- end
- end
-
- if @ns.is_a?(Hash)
- node.namespace = node.namespace_definitions.find { |x| x.prefix == @ns[:pending] }
- if node.namespace.nil?
- raise ArgumentError, "Namespace #{@ns[:pending]} has not been defined"
- end
-
- @ns = nil
- end
-
+ node = @doc.create_element(method.to_s.sub(/[_!]$/, ""), *args)
+ bind_ns(node)
insert(node, &block)
end
end
private
+ def bind_ns(node)
+ return if @ns_prefix.nil?
+
+ ancestors = [node, parent, parent.ancestors].flatten
+ ancestors.each do |ancestor|
+ break if ancestor.nil? || ancestor == @doc
+
+ if (ns = ancestor.namespace_definitions.find { |x| x.prefix == @ns_prefix })
+ @ns_prefix = nil
+ node.namespace = ns
+ break
+ end
+ end
+
+ return if @ns_prefix.nil?
+
+ raise ArgumentError, "Namespace prefix #{@ns_prefix.inspect} has not been defined"
+ end
+
###
# Insert +node+ as a child of the current Node
def insert(node, &block)
diff --git a/lib/nokogiri/xml/document.rb b/lib/nokogiri/xml/document.rb
index 6c9d4949a1..e4446f3d30 100644
--- a/lib/nokogiri/xml/document.rb
+++ b/lib/nokogiri/xml/document.rb
@@ -435,7 +435,7 @@ def fragment(tags = nil)
undef_method :namespace_definitions, :line, :add_namespace
def add_child(node_or_tags)
- raise "A document may not have multiple root nodes." if (root && root.name != "nokogiri_text_wrapper") && !(node_or_tags.comment? || node_or_tags.processing_instruction?)
+ raise "A document may not have multiple root nodes." if root && root.name != "nokogiri_text_wrapper" && !(node_or_tags.comment? || node_or_tags.processing_instruction?)
node_or_tags = coerce(node_or_tags)
if node_or_tags.is_a?(XML::NodeSet)
@@ -502,10 +502,10 @@ def deconstruct_keys(keys)
{ root: root }
end
- private
-
IMPLIED_XPATH_CONTEXTS = ["//"].freeze # :nodoc:
+ private
+
def inspect_attributes
[:name, :children]
end
diff --git a/lib/nokogiri/xml/node.rb b/lib/nokogiri/xml/node.rb
index 2c9d7f12d2..02e802d4df 100644
--- a/lib/nokogiri/xml/node.rb
+++ b/lib/nokogiri/xml/node.rb
@@ -5,9 +5,41 @@
module Nokogiri
module XML
- # Nokogiri::XML::Node is the primary API you'll use to interact with your Document.
+ # \Class XML::Node defines many methods and constants
+ # that are important for working with an \XML document.
#
- # == Attributes
+ # XML::Node itself includes modules that add still more methods and constants:
+ #
+ # - Nokogiri::XML::Searchable
+ # - Ruby core's {Enumerable}[https://docs.ruby-lang.org/en/master/Enumerable.html]
+ #
+ # == Node Hierarchy
+ #
+ # Each of the following classes is, directly or indirectly, a subclass of XML::Node,
+ # and so inherits all the methods and constants mentioned above:
+ #
+ # - Nokogiri::XML::Attr
+ # - Nokogiri::XML::AttributeDecl
+ # - Nokogiri::XML::CharacterData
+ # - Nokogiri::XML::Comment
+ # - Nokogiri::XML::Text
+ # - Nokogiri::XML::CDATA
+ # - Nokogiri::XML::DTD
+ # - Nokogiri::XML::Document
+ # - Nokogiri::XML::DocumentFragment
+ # - Nokogiri::XML::Element
+ # - Nokogiri::XML::ElementDecl
+ # - Nokogiri::XML::EntityDecl
+ # - Nokogiri::XML::EntityReference
+ # - Nokogiri::XML::ProcessingInstruction
+ #
+ # == About the Examples
+ #
+ # Examples on this page may assume that certain setup code has been executed.
+ #
+ # :include: doc/examples/bookstore_setup.rb
+ #
+ # # == Attributes
#
# A Nokogiri::XML::Node may be treated similarly to a hash with regard to attributes. For
# example:
@@ -171,16 +203,109 @@ def decorate!
# :section: Manipulating Document Structure
- ###
- # Add +node_or_tags+ as a child of this Node.
+ # :call-seq:
+ # add_child(object) -> Node or NodeSet
#
- # +node_or_tags+ can be a Nokogiri::XML::Node, a ::DocumentFragment, a ::NodeSet, or a String
- # containing markup.
+ # Appends specified Nodes to the children of +self+;
+ # each appended Node has +self+ as its #parent value,
+ # and self.document as its #document value.
#
- # Returns the reparented node (if +node_or_tags+ is a Node), or NodeSet (if +node_or_tags+ is
- # a DocumentFragment, NodeSet, or String).
+ # [Arguments]
+ #
+ # - +object+ (Node, NodeSet, DocumentFragment, String):
+ # Specifies the Node objects to be appended;
+ # the Nodes may be in the same Document or DocumentFragment as +self+,
+ # or in a different one.
+ #
+ # [Returns]
+ #
+ # - The given +object+, if +object+ is a Node or a NodeSet
+ # - A new NodeSet, if +object+ is a DocumentFragment or String.
+ #
+ # When +object+ is a Node,
+ # moves it to become the last child of +self+;
+ # returns +object+:
+ #
+ # src_xml = ''
+ # src_doc = Nokogiri::XML::Document.parse(src_xml)
+ # src_parent_node = src_doc.at_xpath('//src_parent')
+ # dst_xml = ''
+ # dst_doc = Nokogiri::XML::Document.parse(dst_xml)
+ # dst_parent_node = dst_doc.root
+ # node_to_move = src_doc.at_xpath('//src_child')
+ # # Before.
+ # src_parent_node.children.map {|child| child.name } # => ["src_child"]
+ # dst_parent_node.children.map {|child| child.name } # => ["dst_parent"]
+ # node_to_move.parent.name # => "src_parent"
+ # # Move the node.
+ # dst_parent_node.add_child(node_to_move)
+ # # After.
+ # src_parent_node.children.map {|child| child.name } # => []
+ # dst_parent_node.children.map {|child| child.name } # => ["dst_parent", "src_child"]
+ # node_to_move.parent.name # => "dst_root"
+ #
+ # When +object+ is a NodeSet,
+ # appends each of its nodes to the children of +self+;
+ # returns +object+:
+ #
+ # src_xml = ''
+ # src_doc = Nokogiri::XML::Document.parse(src_xml)
+ # nodeset_to_move = src_doc.root.children
+ # nodeset_to_move.class # => Nokogiri::XML::NodeSet
+ # dst_doc = Nokogiri::XML::Document.parse('')
+ # dst_node = dst_doc.root
+ # # Before.
+ # nodeset_to_move.map {|node| node.name } # => ["foo", "bar"]
+ # nodeset_to_move.map {|node| node.parent.name } # => ["src_root", "src_root"]
+ # dst_node.children.map {|child| child.name } # => ["baz"]
+ # # Move the nodeset.
+ # dst_node.add_child(nodeset_to_move)
+ # # After.
+ # nodeset_to_move.map {|node| node.name } # => ["foo", "bar"]
+ # nodeset_to_move.map {|node| node.parent.name } # => ["dst_root", "dst_root"]
+ # dst_node.children.map {|child| child.name } # => ["baz", "foo", "bar"]
+ #
+ # When +object+ is a DocumentFragment,
+ # creates a NodeSet object from the DocumentFragment;
+ # appends each of its nodes to the children of +self+;
+ # returns the NodeSet:
+ #
+ # src_xml = ''
+ # src_frag = Nokogiri::XML::DocumentFragment.parse(src_xml)
+ # dst_xml = ''
+ # dst_doc = Nokogiri::XML::Document.parse(dst_xml)
+ # dst_node = dst_doc.root
+ # # Before.
+ # src_frag.children.map {|child| child.name } # => ["foo", "bar"]
+ # src_frag.children.map {|child| child.parent.name } # => ["#document-fragment", "#document-fragment"]
+ # dst_node.children.map {|child| child.name } # => ["baz"]
+ # # Move the fragment.
+ # dst_node.add_child(src_frag)
+ # # After.
+ # src_frag.children.map {|child| child.name } # => []
+ # dst_node.children.map {|child| child.name } # => ["baz", "foo", "bar"]
+ # dst_node.children.map {|child| child.parent.name } # => ["dst_root", "dst_root", "dst_root"]
+ #
+ # When +object+ is a String,
+ # creates a NodeSet object from the string;
+ # appends each of its nodes to the children of +self+;
+ # returns the NodeSet:
+ #
+ # src_xml = ''
+ # dst_xml = ''
+ # dst_doc = Nokogiri::XML::Document.parse(dst_xml)
+ # dst_node = dst_doc.root
+ # # Before.
+ # dst_node.children.map {|child| child.name } # => ["baz"]
+ # dst_node.children.map {|child| child.parent.name } # => ["dst_root"]
+ # # Add the NodeSet created from src_xml.
+ # dst_node.add_child(src_xml)
+ # # After.
+ # dst_node.children.map {|child| child.name } # => ["baz", "foo", "bar"]
+ # dst_node.children.map {|child| child.parent.name } # => ["dst_root", "dst_root", "dst_root"]
+ #
+ # Related: #<<, #after, #before, #children=, #prepend_child.
#
- # Also see related method +<<+.
def add_child(node_or_tags)
node_or_tags = coerce(node_or_tags)
if node_or_tags.is_a?(XML::NodeSet)
@@ -1313,7 +1438,7 @@ def ancestors(selector = nil)
end
####
- # Yields self and all children to +block+ recursively.
+ # Yields all children to +block+ recursively, then yields self.
def traverse(&block)
children.each { |j| j.traverse(&block) }
yield(self)
@@ -1584,6 +1709,8 @@ def coerce(data)
EOERR
end
+ IMPLIED_XPATH_CONTEXTS = [".//"].freeze # :nodoc:
+
private
def keywordify(keywords)
@@ -1634,8 +1761,6 @@ def inspect_attributes
[:name, :namespace, :attribute_nodes, :children]
end
- IMPLIED_XPATH_CONTEXTS = [".//"].freeze
-
def add_child_node_and_reparent_attrs(node)
add_child_node(node)
node.attribute_nodes.find_all { |a| a.name.include?(":") }.each do |attr_node|
diff --git a/lib/nokogiri/xml/parse_options.rb b/lib/nokogiri/xml/parse_options.rb
index ddb7c79891..bdf069e429 100644
--- a/lib/nokogiri/xml/parse_options.rb
+++ b/lib/nokogiri/xml/parse_options.rb
@@ -1,87 +1,265 @@
# coding: utf-8
# frozen_string_literal: true
+# :markup: markdown
+
module Nokogiri
module XML
- # Options that control the parsing behavior for XML::Document, XML::DocumentFragment,
- # HTML4::Document, HTML4::DocumentFragment, XSLT::Stylesheet, and XML::Schema.
+ # \Class to contain options for parsing \XML or \HTML4 (but not \HTML5).
+ #
+ # 💡 Note that \HTML5 parsing has a separate, orthogonal set of options due to the API of the
+ # \HTML5 library used. See Nokogiri::HTML5.
+ #
+ # ## About the Examples
+ #
+ # Examples on this page assume that the following code has been executed:
+ #
+ # ```
+ # require 'nokogiri' # Make Nokogiri available.
+ # include Nokogiri # Allow omitting leading 'Nokogiri::'.
+ # xml_s = "\n" # String containing XML.
+ # File.write('t.xml', xml_s) # File containing XML.
+ # html_s = "\n" # String containing HTML.
+ # File.write('t.html', html_s) # File containing HTML.
+ # ```
+ #
+ # Examples executed via `IRB` (interactive Ruby) display \ParseOptions instances
+ # using method #inspect.
+ #
+ # ## Parsing Methods
+ #
+ # Each of the parsing methods performs parsing for an \XML or \HTML4 source:
+ #
+ # - Each requires a leading argument that specifies the source of the text to be parsed;
+ # except as noted, the argument's value may be either:
#
- # These options directly expose libxml2's parse options, which are all boolean in the sense that
- # an option is "on" or "off".
+ # - A string.
+ # - An open IO stream (must respond to methods `read` and `close`).
#
- # 💡 Note that HTML5 parsing has a separate, orthogonal set of options due to the nature of the
- # HTML5 specification. See Nokogiri::HTML5.
+ # Examples:
#
- # ⚠ Not all parse options are supported on JRuby. Nokogiri will attempt to invoke the equivalent
+ # ```
+ # XML::parse(xml_s)
+ # HTML4.parse(html_s)
+ # XML::parse(File.open('t.xml'))
+ # HTML4.parse(File.open('t.html'))
+ # ```
+ #
+ # - Each accepts a trailing optional argument `options`
+ # (or keyword argument `options`)
+ # that specifies parsing options;
+ # the argument's value may be either:
+ #
+ # - An integer: see [Bitmap Constants](rdoc-ref:ParseOptions@Bitmap+Constants).
+ # - An instance of \ParseOptions: see ParseOptions.new.
+ #
+ # Examples:
+ #
+ # ```
+ # XML::parse(xml_s, options: XML::ParseOptions::STRICT)
+ # HTML4::parse(html_s, options: XML::ParseOptions::BIG_LINES)
+ # XML::parse(xml_s, options: XML::ParseOptions.new.strict)
+ # HTML4::parse(html_s, options: XML::ParseOptions.new.big_lines)
+ # ```
+ #
+ # - Each (except as noted) accepts a block that allows parsing options to be specified;
+ # see [Options-Setting Blocks](rdoc-ref:ParseOptions@Options-Setting+Blocks).
+ #
+ # Certain other parsing methods use different options;
+ # see \HTML5.
+ #
+ # ⚠ Not all parse options are supported on JRuby.
+ # \Nokogiri attempts to invoke the equivalent
# behavior in Xerces/NekoHTML on JRuby when it's possible.
#
- # == Setting and unsetting parse options
+ # ## Bitmap Constants
#
- # You can build your own combinations of parse options by using any of the following methods:
+ # Each of the [parsing methods](rdoc-ref:ParseOptions@Parsing+Methods)
+ # discussed here accept an integer argument `options` that specifies parsing options.
#
- # [ParseOptions method chaining]
+ # That integer value may be constructed using the bitmap constants defined in \ParseOptions.
#
- # Every option has an equivalent method in lowercase. You can chain these methods together to
- # set various combinations.
+ # Except for `STRICT` (see note below),
+ # each of the bitmap constants has a non-zero value
+ # that represents a bit in an integer value;
+ # to illustrate, here are a few of the constants, displayed in binary format (base 2):
#
- # # Set the HUGE & PEDANTIC options
- # po = Nokogiri::XML::ParseOptions.new.huge.pedantic
- # doc = Nokogiri::XML::Document.parse(xml, nil, nil, po)
+ # ```
+ # ParseOptions::RECOVER.to_s(2) # => "1"
+ # ParseOptions::NOENT.to_s(2) # => "10"
+ # ParseOptions::DTDLOAD.to_s(2) # => "100"
+ # ParseOptions::DTDATTR.to_s(2) # => "1000"
+ # ParseOptions::DTDVALID.to_s(2) # => "10000"
+ # ```
#
- # Every option has an equivalent no{option} method in lowercase. You can call these
- # methods on an instance of ParseOptions to unset the option.
+ # Any of these constants may be used alone to specify a single option:
#
- # # Set the HUGE & PEDANTIC options
- # po = Nokogiri::XML::ParseOptions.new.huge.pedantic
+ # ```
+ # ParseOptions.new(ParseOptions::DTDLOAD)
+ # # => #
+ # ParseOptions.new(ParseOptions::DTDATTR)
+ # # => #
+ # ```
#
- # # later we want to modify the options
- # po.nohuge # Unset the HUGE option
- # po.nopedantic # Unset the PEDANTIC option
+ # Multiple constants may be ORed together to specify multiple options:
#
- # 💡 Note that some options begin with "no" leading to the logical but perhaps unintuitive
- # double negative:
+ # ```
+ # options = ParseOptions::BIG_LINES | ParseOptions::COMPACT | ParseOptions::NOCDATA
+ # ParseOptions.new(options)
+ # # => #
+ # ```
#
- # po.nocdata # Set the NOCDATA parse option
- # po.nonocdata # Unset the NOCDATA parse option
+ # **Note**:
+ # The value of constant `STRICT` is zero;
+ # it may be used alone to turn all options **off**:
#
- # 💡 Note that negation is not available for STRICT, which is itself a negation of all other
- # features.
+ # ```
+ # XML.parse('') {|options| puts options.inspect }
+ # #
+ # XML.parse('', nil, nil, ParseOptions::STRICT) {|options| puts options.inspect }
+ # #
+ # ```
#
+ # The single-option bitmask constants are:
+ # BIG_LINES,
+ # COMPACT,
+ # DTDATTR,
+ # DTDLOAD,
+ # DTDVALID,
+ # HUGE,
+ # NOBASEFIX,
+ # NOBLANKS,
+ # NOCDATA,
+ # NOENT,
+ # NOERROR,
+ # NONET,
+ # NOWARNING,
+ # NOXINCNODE,
+ # NSCLEAN,
+ # OLD10,
+ # PEDANTIC,
+ # RECOVER,
+ # STRICT,
+ # XINCLUDE.
#
- # [Using Ruby Blocks]
+ # There are also several "shorthand" constants that can set multiple options:
+ # DEFAULT_HTML,
+ # DEFAULT_SCHEMA,
+ # DEFAULT_XML,
+ # DEFAULT_XSLT.
#
- # Most parsing methods will accept a block for configuration of parse options, and we
- # recommend chaining the setter methods:
+ # Examples:
#
- # doc = Nokogiri::XML::Document.parse(xml) { |config| config.huge.pedantic }
+ # ```
+ # ParseOptions.new(ParseOptions::DEFAULT_HTML)
+ # # => #
+ # ParseOptions.new(ParseOptions::DEFAULT_SCHEMA)
+ # # => #
+ # ParseOptions.new(ParseOptions::DEFAULT_XML)
+ # # => #
+ # ParseOptions.new(ParseOptions::DEFAULT_XSLT)
+ # # => # #
+ # ```
#
+ # \Nokogiri itself uses these shorthand constants for its parsing,
+ # and they are generally most suitable for \Nokogiri users' code.
#
- # [ParseOptions constants]
+ # ## Options-Setting Blocks
+ #
+ # Many of the [parsing methods](rdoc-ref:ParseOptions@Parsing+Methods)
+ # discussed here accept an options-setting block.
+ #
+ # The block is called with a new instance of \ParseOptions
+ # created with the defaults for the specific method:
+ #
+ # ```
+ # XML::parse(xml_s) {|options| puts options.inspect }
+ # #
+ # HTML4::parse(html_s) {|options| puts options.inspect }
+ # #
+ # ```
+ #
+ # When the block returns, the parsing is performed using those `options`.
+ #
+ # The block may modify those options, which affects parsing:
+ #
+ # ```
+ # bad_xml = '' # End tag missing.
+ # XML::parse(bad_xml) # No error because option RECOVER is on.
+ # XML::parse(bad_xml) {|options| options.strict } # Raises SyntaxError because option STRICT is on.
+ # ```
+ #
+ # ## Convenience Methods
+ #
+ # A \ParseOptions object has three sets of convenience methods,
+ # each based on the name of one of the constants:
+ #
+ # - **Setters**: each is the downcase of an option name, and turns **on** an option:
+ #
+ # ```
+ # options = ParseOptions.new
+ # # => #
+ # options.big_lines
+ # # => #
+ # options.compact
+ # # => #
+ # ```
+ #
+ # - **Unsetters**: each begins with `no`, and turns **off** an option.
+ #
+ # Note that there is no unsetter `nostrict`,
+ # but the setter `recover` serves the same purpose:
+ #
+ # ```
+ # options.nobig_lines
+ # # => #
+ # options.nocompact
+ # # => #
+ # options.recover # Functionally equivalent to nostrict.
+ # # => #
+ # options.noent # Set NOENT.
+ # # => #
+ # options.nonoent # Unset NOENT.
+ # # => #
+ # ```
+ #
+ # 💡 Note that some options begin with `no`, leading to the logical but perhaps unintuitive
+ # double negative:
+ #
+ # ```
+ # po.nocdata # Set the NOCDATA parse option
+ # po.nonocdata # Unset the NOCDATA parse option
+ # ```
#
- # You can also use the constants declared under Nokogiri::XML::ParseOptions to set various
- # combinations. They are bits in a bitmask, and so can be combined with bitwise operators:
+ # - **Queries**: each ends with `?`, and returns whether an option is **on** or **off**:
#
- # po = Nokogiri::XML::ParseOptions.new(Nokogiri::XML::ParseOptions::HUGE | Nokogiri::XML::ParseOptions::PEDANTIC)
- # doc = Nokogiri::XML::Document.parse(xml, nil, nil, po)
+ # ```
+ # options.recover? # => true
+ # options.strict? # => false
+ # ```
+ #
+ # Each setter and unsetter method returns `self`,
+ # so the methods may be chained:
+ #
+ # ```
+ # options.compact.big_lines
+ # # => #
+ # ```
#
class ParseOptions
- # Strict parsing
+ # Strict parsing; do not recover from errors in input.
STRICT = 0
- # Recover from errors. On by default for XML::Document, XML::DocumentFragment,
- # HTML4::Document, HTML4::DocumentFragment, XSLT::Stylesheet, and XML::Schema.
+ # Recover from errors in input; no strict parsing.
RECOVER = 1 << 0
# Substitute entities. Off by default.
- #
- # ⚠ This option enables entity substitution, contrary to what the name implies.
- #
- # ⚠ It is UNSAFE to set this option when parsing untrusted documents.
+ # ⚠ This option enables entity substitution, contrary to what the name implies.
+ # ⚠ It is UNSAFE to set this option when parsing untrusted documents.
NOENT = 1 << 1
# Load external subsets. On by default for XSLT::Stylesheet.
- #
- # ⚠ It is UNSAFE to set this option when parsing untrusted documents.
+ # ⚠ It is UNSAFE to set this option when parsing untrusted documents.
DTDLOAD = 1 << 2
# Default DTD attributes. On by default for XSLT::Stylesheet.
@@ -90,10 +268,10 @@ class ParseOptions
# Validate with the DTD. Off by default.
DTDVALID = 1 << 4
- # Suppress error reports. On by default for HTML4::Document and HTML4::DocumentFragment
+ # Suppress error reports. On by default for HTML4::Document and HTML4::DocumentFragment.
NOERROR = 1 << 5
- # Suppress warning reports. On by default for HTML4::Document and HTML4::DocumentFragment
+ # Suppress warning reports. On by default for HTML4::Document and HTML4::DocumentFragment.
NOWARNING = 1 << 6
# Enable pedantic error reporting. Off by default.
@@ -103,19 +281,19 @@ class ParseOptions
NOBLANKS = 1 << 8
# Use the SAX1 interface internally. Off by default.
- SAX1 = 1 << 9
+ SAX1 = 1 << 9 # :nodoc:
# Implement XInclude substitution. Off by default.
XINCLUDE = 1 << 10
- # Forbid network access. On by default for XML::Document, XML::DocumentFragment,
+ # Forbid network access.
+ # On by default for XML::Document, XML::DocumentFragment,
# HTML4::Document, HTML4::DocumentFragment, XSLT::Stylesheet, and XML::Schema.
- #
- # ⚠ It is UNSAFE to unset this option when parsing untrusted documents.
+ # ⚠ It is UNSAFE to unset this option when parsing untrusted documents.
NONET = 1 << 11
# Do not reuse the context dictionary. Off by default.
- NODICT = 1 << 12
+ NODICT = 1 << 12 # :nodoc:
# Remove redundant namespaces declarations. Off by default.
NSCLEAN = 1 << 13
@@ -127,41 +305,85 @@ class ParseOptions
NOXINCNODE = 1 << 15
# Compact small text nodes. Off by default.
- #
- # ⚠ No modification of the DOM tree is allowed after parsing. libxml2 may crash if you try to
- # modify the tree.
+ # ⚠ No modification of the DOM tree is allowed after parsing.
COMPACT = 1 << 16
- # Parse using XML-1.0 before update 5. Off by default
+ # Parse using XML-1.0 before update 5. Off by default.
OLD10 = 1 << 17
- # Do not fixup XInclude xml:base uris. Off by default
+ # Do not fixup XInclude xml:base URIs. Off by default.
NOBASEFIX = 1 << 18
# Relax any hardcoded limit from the parser. Off by default.
- #
- # ⚠ It is UNSAFE to set this option when parsing untrusted documents.
+ # ⚠ It is UNSAFE to set this option when parsing untrusted documents.
HUGE = 1 << 19
- # Support line numbers up to long int (default is a short int). On
- # by default for for XML::Document, XML::DocumentFragment, HTML4::Document,
+ # Support line numbers up to `long int` (default is a `short int`).
+ # On by default for for XML::Document, XML::DocumentFragment, HTML4::Document,
# HTML4::DocumentFragment, XSLT::Stylesheet, and XML::Schema.
BIG_LINES = 1 << 22
- # The options mask used by default for parsing XML::Document and XML::DocumentFragment
+ # Shorthand options mask useful for parsing XML:
+ # sets RECOVER, NONET, BIG_LINES.
DEFAULT_XML = RECOVER | NONET | BIG_LINES
- # The options mask used by default used for parsing XSLT::Stylesheet
+ # Shorthand options mask useful for parsing XSLT stylesheets:
+ # sets RECOVER, NONET, NOENT, DTDLOAD, DTDATTR, NOCDATA, BIG_LINES.
DEFAULT_XSLT = RECOVER | NONET | NOENT | DTDLOAD | DTDATTR | NOCDATA | BIG_LINES
- # The options mask used by default used for parsing HTML4::Document and HTML4::DocumentFragment
+ # Shorthand options mask useful for parsing HTML4:
+ # sets RECOVER, NOERROR, NOWARNING, NONET, BIG_LINES.
DEFAULT_HTML = RECOVER | NOERROR | NOWARNING | NONET | BIG_LINES
- # The options mask used by default used for parsing XML::Schema
+ # Shorthand options mask useful for parsing \XML schemas:
+ # sets NONET, BIG_LINES.
DEFAULT_SCHEMA = NONET | BIG_LINES
+ # Returns or sets and returns the integer value of `self`:
+ #
+ # ```
+ # options = ParseOptions.new(ParseOptions::DEFAULT_HTML)
+ # # => # 4196449
+ # options.options = ParseOptions::STRICT
+ # options.options # => 0
+ # ```
+ #
attr_accessor :options
+ # :markup: markdown
+ #
+ # :call-seq:
+ # ParseOptions.new(options = ParseOptions::STRICT)
+ #
+ # Returns a new \ParseOptions object with options as specified by integer argument `options`.
+ # The value of `options` may be constructed
+ # using [Bitmap Constants](rdoc-ref:ParseOptions@Bitmap+Constants).
+ #
+ # With the simple constant `ParseOptions::STRICT` (the default), all options are **off**
+ # (`strict` means `norecover`):
+ #
+ # ```
+ # ParseOptions.new
+ # # => #
+ # ```
+ #
+ # With a different simple constant, one option may be set:
+ #
+ # ```
+ # ParseOptions.new(ParseOptions::RECOVER)
+ # # => #
+ # ParseOptions.new(ParseOptions::COMPACT)
+ # # => #
+ # ```
+ #
+ # With multiple ORed constants, multiple options may be set:
+ #
+ # ```
+ # options = ParseOptions::COMPACT | ParseOptions::RECOVER | ParseOptions::BIG_LINES
+ # ParseOptions.new(options)
+ # # => #
+ # ```
def initialize(options = STRICT)
@options = options
end
@@ -186,21 +408,88 @@ def #{constant.downcase}?
RUBY
end
+ # :call-seq:
+ # strict
+ #
+ # Turns **off** option `recover`:
+ #
+ # ```
+ # options = ParseOptions.new.recover.compact.big_lines
+ # # => #
+ # options.strict
+ # # => #
+ # ```
def strict
@options &= ~RECOVER
self
end
+ # :call-seq:
+ # strict?
+ #
+ # Returns whether option `strict` is **on**:
+ #
+ # ```
+ # options = ParseOptions.new.recover.compact.big_lines
+ # # => #
+ # options.strict? # => false
+ # options.strict
+ # # => #
+ # options.strict? # => true
+ # ```
def strict?
@options & RECOVER == STRICT
end
+ # :call-seq:
+ # self == object
+ #
+ # Returns true if the same options are set in `self` and `object`.
+ #
+ # ```
+ # options = ParseOptions.new
+ # # => #
+ # options == options.dup # => true
+ # options == options.dup.recover # => false
+ # ```
+ #
def ==(other)
other.to_i == to_i
end
alias_method :to_i, :options
+ # :call-seq:
+ # inspect
+ #
+ # Returns a string representation of +self+ that includes
+ # the numeric value of `@options`:
+ #
+ # ```
+ # options = ParseOptions.new
+ # options.inspect
+ # # => "#"
+ #
+ # ```
+ #
+ # In general, the returned string also includes the (downcased) names of the options
+ # that are **on** (but omits the names of those that are **off**):
+ #
+ # ```
+ # options.recover.big_lines
+ # options.inspect
+ # # => "#"
+ # ```
+ #
+ # The exception is that always either `recover` (i.e, *not strict*)
+ # or the pseudo-option `strict` is reported:
+ #
+ # ```
+ # options.norecover
+ # options.inspect
+ # # => "#"
+ # ```
+ #
def inspect
options = []
self.class.constants.each do |k|
diff --git a/lib/nokogiri/xml/searchable.rb b/lib/nokogiri/xml/searchable.rb
index 2985fa63d1..646813644b 100644
--- a/lib/nokogiri/xml/searchable.rb
+++ b/lib/nokogiri/xml/searchable.rb
@@ -50,6 +50,11 @@ module Searchable
# }.new
# node.search('.//title[nokogiri:regex(., "\w+")]', 'div.employee:regex("[0-9]+")', handler)
#
+ # ⚠ NOTE that the #search method may not always correctly detect whether the input is a CSS
+ # selector or an XPath expression; and the heuristic used may change in the future. The authors
+ # strongly recommend using Searchable#css when you know you're searching with a CSS selector,
+ # or Searchable#xpath when you know you're searching with an XPath expression.
+ #
# See Searchable#xpath and Searchable#css for further usage help.
def search(*args)
paths, handler, ns, binds = extract_params(args)
diff --git a/misc/native.yml b/misc/native.yml
new file mode 100644
index 0000000000..b8f29dbcbe
--- /dev/null
+++ b/misc/native.yml
@@ -0,0 +1,16 @@
+# configuration file for precompiled native gem packaging
+platforms:
+ - aarch64-linux-gnu
+ - aarch64-linux-musl
+ - arm64-darwin
+ - arm-linux-gnu
+ - arm-linux-musl
+ - x64-mingw-ucrt
+ - x86_64-darwin
+ - x86_64-linux-gnu
+ - x86_64-linux-musl
+rubies:
+ - "3.4"
+ - "3.3"
+ - "3.2"
+ - "3.1"
diff --git a/nokogiri.gemspec b/nokogiri.gemspec
index e5c8b0effa..054305a1d3 100644
--- a/nokogiri.gemspec
+++ b/nokogiri.gemspec
@@ -59,6 +59,7 @@ Gem::Specification.new do |spec|
"README.md",
"bin/nokogiri",
"dependencies.yml",
+ "doc/keyword_arguments.md",
"ext/java/nokogiri/Html4Document.java",
"ext/java/nokogiri/Html4ElementDescription.java",
"ext/java/nokogiri/Html4EntityLookup.java",
@@ -198,15 +199,19 @@ Gem::Specification.new do |spec|
"gumbo-parser/src/error.h",
"gumbo-parser/src/foreign_attrs.c",
"gumbo-parser/src/foreign_attrs.gperf",
- "gumbo-parser/src/nokogiri_gumbo.h",
+ "gumbo-parser/src/hashmap.c",
+ "gumbo-parser/src/hashmap.h",
"gumbo-parser/src/insertion_mode.h",
"gumbo-parser/src/macros.h",
+ "gumbo-parser/src/nokogiri_gumbo.h",
"gumbo-parser/src/parser.c",
"gumbo-parser/src/parser.h",
"gumbo-parser/src/replacement.h",
"gumbo-parser/src/string_buffer.c",
"gumbo-parser/src/string_buffer.h",
"gumbo-parser/src/string_piece.c",
+ "gumbo-parser/src/string_set.c",
+ "gumbo-parser/src/string_set.h",
"gumbo-parser/src/svg_attrs.c",
"gumbo-parser/src/svg_attrs.gperf",
"gumbo-parser/src/svg_tags.c",
@@ -328,10 +333,6 @@ Gem::Specification.new do |spec|
spec.rdoc_options = ["--main", "README.md"]
if java_p
- # loosen after jruby fixes https://github.com/jruby/jruby/issues/7262
- # also see https://github.com/mkristian/jar-dependencies/commit/006fb254
- spec.add_development_dependency("jar-dependencies", "= 0.4.1")
-
spec.require_paths << "lib/nokogiri/jruby" # where we install the jars, see the :vendor_jars rake task
spec.requirements << "jar isorelax, isorelax, 20030108" # https://search.maven.org/artifact/isorelax/isorelax
spec.requirements << "jar org.nokogiri, nekodtd, 0.1.11.noko2"
diff --git a/oci-images/nokogiri-test/alpine.dockerfile b/oci-images/nokogiri-test/alpine.dockerfile
index 42c3f3cf30..2d33ec18df 100644
--- a/oci-images/nokogiri-test/alpine.dockerfile
+++ b/oci-images/nokogiri-test/alpine.dockerfile
@@ -7,6 +7,9 @@ RUN apk add bash build-base git
# valgrind
RUN apk add valgrind
+# psych
+RUN apk add yaml-dev
+
# libxml-et-al
RUN apk add libxml2-dev libxslt-dev pkgconfig
diff --git a/oci-images/nokogiri-test/alpine.erb b/oci-images/nokogiri-test/alpine.erb
index 7a8082c611..12e0605b0b 100644
--- a/oci-images/nokogiri-test/alpine.erb
+++ b/oci-images/nokogiri-test/alpine.erb
@@ -7,6 +7,9 @@ RUN apk add bash build-base git
# valgrind
RUN apk add valgrind
+# psych
+RUN apk add yaml-dev
+
# libxml-et-al
RUN apk add libxml2-dev libxslt-dev pkgconfig
diff --git a/rakelib/check-manifest.rake b/rakelib/check-manifest.rake
index 33f49937da..6bc89567c6 100644
--- a/rakelib/check-manifest.rake
+++ b/rakelib/check-manifest.rake
@@ -38,7 +38,6 @@ task :check_manifest, [:verbose] do |_, args|
[0-9]*
}
ignore_files = %w[
- .cross_rubies
.editorconfig
.gitignore
.gitmodules
diff --git a/rakelib/extensions.rake b/rakelib/extensions.rake
index 232291c354..5790211580 100644
--- a/rakelib/extensions.rake
+++ b/rakelib/extensions.rake
@@ -2,6 +2,8 @@
require "rbconfig"
require "shellwords"
+require "rake_compiler_dock"
+require "yaml"
CrossRuby = Struct.new(:version, :platform) do
LINUX_PLATFORM_REGEX = /linux/
@@ -166,16 +168,14 @@ CrossRuby = Struct.new(:version, :platform) do
end
end
-CROSS_RUBIES = File.read(".cross_rubies").split("\n").filter_map do |line|
- case line
- when /\A([^#]+):([^#]+)/
- CrossRuby.new(Regexp.last_match(1), Regexp.last_match(2))
+native_config = YAML.load_file("misc/native.yml")
+CROSS_RUBIES = native_config["platforms"].flat_map do |platform|
+ native_config["rubies"].map do |minor|
+ version = RakeCompilerDock.cross_rubies[minor]
+ CrossRuby.new(version, platform)
end
end
-
-ENV["RUBY_CC_VERSION"] = CROSS_RUBIES.map(&:ver).uniq.join(":")
-
-require "rake_compiler_dock"
+RakeCompilerDock.set_ruby_cc_version(*native_config["rubies"])
def java?
RUBY_PLATFORM.include?("java")
@@ -375,7 +375,6 @@ if java?
end
else
require "rake/extensiontask"
- require "yaml"
dependencies = YAML.load_file("dependencies.yml")
diff --git a/rakelib/rdoc.rake b/rakelib/rdoc.rake
index 289bb755de..61938a096e 100644
--- a/rakelib/rdoc.rake
+++ b/rakelib/rdoc.rake
@@ -1,26 +1,30 @@
# frozen_string_literal: true
-require "rdoc/task"
+begin
+ require "rdoc/task"
-def rdoc_nokogiri_common_options(rdoc)
- rdoc.rdoc_files
- .include("README.md", "lib/**/*.rb", "ext/**/*.c")
- .exclude("ext/nokogiri/test_global_handlers.c")
- rdoc.options << "--embed-mixins"
- rdoc.options << "--main=README.md"
-end
+ def rdoc_nokogiri_common_options(rdoc)
+ rdoc.rdoc_files
+ .include("*.md", "lib/**/*.rb", "ext/**/*.c", "doc/**/*md")
+ .exclude("CHANGELOG.md", "ROADMAP.md", "ext/nokogiri/test_global_handlers.c")
+ rdoc.options << "--embed-mixins"
+ rdoc.options << "--main=README.md"
+ end
-RDoc::Task.new(rdoc: "rdoc", clobber_rdoc: "rdoc:clean", rerdoc: "rdoc:force") do |rdoc|
- rdoc.rdoc_dir = ENV["RDOC_DIR"] || "html"
- rdoc.options << "--show-hash"
- rdoc.options << "--template-stylesheets=misc/rdoc-tweaks.css"
- rdoc_nokogiri_common_options(rdoc)
-end
+ RDoc::Task.new(rdoc: "rdoc", clobber_rdoc: "rdoc:clean", rerdoc: "rdoc:force") do |rdoc|
+ rdoc.rdoc_dir = ENV["RDOC_DIR"] || "html"
+ rdoc.options << "--show-hash"
+ rdoc.options << "--template-stylesheets=misc/rdoc-tweaks.css"
+ rdoc_nokogiri_common_options(rdoc)
+ end
-RDoc::Task.new(rdoc: "ri", clobber_rdoc: "ri:clean", rerdoc: "ri:force") do |rdoc|
- rdoc.rdoc_dir = ENV["RI_DIR"] || "ri"
- rdoc.generator = "ri"
- rdoc_nokogiri_common_options(rdoc)
-end
+ RDoc::Task.new(rdoc: "ri", clobber_rdoc: "ri:clean", rerdoc: "ri:force") do |rdoc|
+ rdoc.rdoc_dir = ENV["RI_DIR"] || "ri"
+ rdoc.generator = "ri"
+ rdoc_nokogiri_common_options(rdoc)
+ end
-task clean: "rdoc:clean" # rubocop:disable Rake/Desc
+ task clean: "rdoc:clean" # rubocop:disable Rake/Desc
+rescue LoadError => e
+ warn("WARNING: rdoc is not available in this environment: #{e}")
+end
diff --git a/scripts/test-gem-file-contents b/scripts/test-gem-file-contents
index ba167fdbb1..45099dd143 100755
--- a/scripts/test-gem-file-contents
+++ b/scripts/test-gem-file-contents
@@ -16,8 +16,10 @@ require "bundler/inline"
gemfile do
source "https://rubygems.org"
gem "minitest"
+ gem "rake-compiler-dock", ">= 1.9.1"
end
+require "rake_compiler_dock"
require "yaml"
def usage_and_exit(message = nil)
@@ -68,22 +70,10 @@ require "minitest/autorun"
puts "Testing '#{gemfile}' (#{gemspec.platform})"
describe File.basename(gemfile) do
- let(:cross_rubies_path) { File.join(File.dirname(__FILE__), "..", ".cross_rubies") }
+ let(:native_config) { YAML.load_file(File.join(__dir__, "..", "misc", "native.yml")) }
- let(:platform_supported_ruby_versions) do
- File.read(cross_rubies_path).split("\n").filter_map do |line|
- ver, plat = line.split(":")
- next if plat != gemspec.platform.to_s
-
- ver.split(".").take(2).join(".") # ugh
- end.uniq.sort
- end
-
- let(:all_supported_ruby_versions) do
- File.read(cross_rubies_path).split("\n").map do |line|
- ver, _ = line.split(":")
- ver.split(".").take(2).join(".") # ugh
- end.uniq.sort
+ let(:supported_ruby_versions) do
+ native_config["rubies"]
end
describe "setup" do
@@ -93,7 +83,7 @@ describe File.basename(gemfile) do
end
it "gemspec is a Gem::Specification" do
- assert_equal(Gem::Specification, gemspec.class)
+ assert_instance_of(Gem::Specification, gemspec)
end
end
@@ -194,7 +184,7 @@ describe File.basename(gemfile) do
end
it "contains expected shared library files " do
- platform_supported_ruby_versions.each do |version|
+ supported_ruby_versions.each do |version|
actual = gemfile_contents.find do |p|
File.fnmatch?("lib/nokogiri/#{version}/nokogiri.{so,bundle}", p, File::FNM_EXTGLOB)
end
@@ -210,15 +200,16 @@ describe File.basename(gemfile) do
File.fnmatch?("lib/nokogiri/**/*.{so,bundle}", p, File::FNM_EXTGLOB)
end
assert_equal(
- platform_supported_ruby_versions.length,
+ supported_ruby_versions.length,
actual.length,
"did not expect extra shared library files",
)
end
it "sets required_ruby_version appropriately" do
- unsupported_versions = all_supported_ruby_versions - platform_supported_ruby_versions
- platform_supported_ruby_versions.each do |v|
+ all_supported_ruby_versions = RakeCompilerDock.cross_rubies.keys
+ unsupported_versions = all_supported_ruby_versions - supported_ruby_versions
+ supported_ruby_versions.each do |v|
assert(
gemspec.required_ruby_version.satisfied_by?(Gem::Version.new(v)),
"required_ruby_version='#{gemspec.required_ruby_version}' should support ruby #{v}",
diff --git a/scripts/test-gem-install b/scripts/test-gem-install
index 8528dc0475..6d3394d2f6 100755
--- a/scripts/test-gem-install
+++ b/scripts/test-gem-install
@@ -28,6 +28,7 @@ popd
# 2.3.21 because https://github.com/rubygems/rubygems/issues/5914
# 2.3.22 because https://github.com/rubygems/rubygems/issues/5940
gem install bundler -v "~> 2.2, != 2.3.21, != 2.3.22"
+bundle config set --local without rdoc
bundle install --local || bundle install
rm -rf lib ext # ensure we don't use the local files
diff --git a/scripts/test-gem-installation b/scripts/test-gem-installation
index 81f640a6a0..a3005e73f6 100755
--- a/scripts/test-gem-installation
+++ b/scripts/test-gem-installation
@@ -74,11 +74,11 @@ describe gemspec.full_name do
describe "native platform" do
it "declares packaged, precompiled libraries" do
- assert(Nokogiri::VersionInfo.instance.libxml2_using_packaged?)
+ assert_predicate(Nokogiri::VersionInfo.instance, :libxml2_using_packaged?)
assert(Nokogiri::VERSION_INFO["libxml"].key?("source"))
assert_equal("packaged", Nokogiri::VERSION_INFO["libxml"]["source"])
- assert(Nokogiri::VersionInfo.instance.libxml2_precompiled?)
+ assert_predicate(Nokogiri::VersionInfo.instance, :libxml2_precompiled?)
assert(Nokogiri::VERSION_INFO["libxml"].key?("precompiled"))
assert(Nokogiri::VERSION_INFO["libxml"]["precompiled"])
end
diff --git a/test/css/test_xpath_visitor.rb b/test/css/test_xpath_visitor.rb
index 7d87f523bc..c852d5e840 100644
--- a/test/css/test_xpath_visitor.rb
+++ b/test/css/test_xpath_visitor.rb
@@ -143,53 +143,68 @@ def visit_pseudo_class_aaron(node)
)
end
- it "# id" do
- assert_xpath("//*[@id='foo']", "#foo")
- assert_xpath("//*[@id='escape:needed,']", "#escape\\:needed\\,")
- assert_xpath("//*[@id='escape:needed,']", '#escape\3Aneeded\,')
- assert_xpath("//*[@id='escape:needed,']", '#escape\3A needed\2C')
- assert_xpath("//*[@id='escape:needed']", '#escape\00003Aneeded')
- end
-
- describe "attribute" do
- it "basic mechanics" do
- assert_xpath("//h1[@a='Tender Lovemaking']", "h1[a='Tender Lovemaking']")
- assert_xpath("//h1[@a]", "h1[a]")
- assert_xpath(%q{//h1[@a='gnewline\n']}, "h1[a='\\gnew\\\nline\\\\n']")
- assert_xpath("//h1[@a='test']", %q{h1[a=\te\st]})
- end
-
- it "parses leading @ (extended-syntax)" do
- assert_xpath("//a[@id='Boing']", "a[@id='Boing']")
- assert_xpath("//a[@id='Boing']", "a[@id = 'Boing']")
- assert_xpath("//a[@id='Boing']//div", "a[@id='Boing'] div")
+ describe "namespaces" do
+ let(:ns) do
+ {
+ "xmlns" => "http://default.example.com/",
+ "hoge" => "http://hoge.example.com/",
+ }
end
- it "namespacing" do
+ it "basic mechanics" do
assert_xpath("//a[@flavorjones:href]", "a[flavorjones|href]")
assert_xpath("//a[@href]", "a[|href]")
assert_xpath("//*[@flavorjones:href]", "*[flavorjones|href]")
+ end
- ns = {
- "xmlns" => "http://default.example.com/",
- "hoge" => "http://hoge.example.com/",
- }
-
- # An intentionally-empty namespace means "don't use the default xmlns"
- assert_equal(["//a"], Nokogiri::CSS.xpath_for("|a", ns: ns, cache: false))
-
- # The default namespace is not applied to attributes (just elements)
+ it "default namespace is applied to elements but not attributes" do
assert_equal(
["//xmlns:a[@class='bar']"],
Nokogiri::CSS.xpath_for("a[class='bar']", ns: ns, cache: false),
)
+ end
- # We can explicitly apply a namespace to an attribue
+ it "default namespace is not applied to wildcard selectors" do
+ assert_equal(
+ ["//xmlns:a//*"],
+ Nokogiri::CSS.xpath_for("a *", ns: ns, cache: false),
+ )
+ end
+
+ it "intentionally-empty namespace omits the default xmlns" do
+ # An intentionally-empty namespace
+ assert_equal(["//a"], Nokogiri::CSS.xpath_for("|a", ns: ns, cache: false))
+ end
+
+ it "explicit namespaces are applied to attributes" do
assert_equal(
["//xmlns:a[@hoge:class='bar']"],
Nokogiri::CSS.xpath_for("a[hoge|class='bar']", ns: ns, cache: false),
)
end
+ end
+
+ describe "attribute" do
+ it "basic mechanics" do
+ assert_xpath("//h1[@a='Tender Lovemaking']", "h1[a='Tender Lovemaking']")
+ assert_xpath("//h1[@a]", "h1[a]")
+ assert_xpath(%q{//h1[@a='gnewline\n']}, "h1[a='\\gnew\\\nline\\\\n']")
+ assert_xpath("//h1[@a='test']", %q{h1[a=\te\st]})
+ end
+
+ it "#id escaping" do
+ assert_xpath("//*[@id='foo']", "#foo")
+ assert_xpath("//*[@id='escape:needed,']", "#escape\\:needed\\,")
+ assert_xpath("//*[@id='escape:needed,']", '#escape\3Aneeded\,')
+ assert_xpath("//*[@id='escape:needed,']", '#escape\3A needed\2C')
+ assert_xpath("//*[@id='escape:needed']", '#escape\00003Aneeded')
+ end
+
+ it "parses leading @ (extended-syntax)" do
+ assert_xpath("//a[@id='Boing']", "a[@id='Boing']")
+ assert_xpath("//a[@id='Boing']", "a[@id = 'Boing']")
+ assert_xpath("//a[@id='Boing']//div", "a[@id='Boing'] div")
+ end
it "rhs with quotes" do
assert_xpath(%q{//h1[@a="'"]}, %q{h1[a="'"]})
diff --git a/test/helper.rb b/test/helper.rb
index 24f3023d80..a74e0920c7 100644
--- a/test/helper.rb
+++ b/test/helper.rb
@@ -266,19 +266,19 @@ def util_decorate(document, decorator_module)
document.decorate!
end
- def pending(msg)
+ def pending(msg, extra_uplevel = 0)
begin
yield
rescue Minitest::Assertion
- skip("pending #{msg} [#{caller(2..2).first}]")
+ skip("pending #{msg} [#{caller(2 + extra_uplevel, 1).first}]")
end
- flunk("pending test unexpectedly passed: #{msg} [#{caller(1..1).first}]")
+ flunk("pending test unexpectedly passed: #{msg} [#{caller(1 + extra_uplevel, 1).first}]")
end
def pending_if(msg, pend_eh, &block)
return yield unless pend_eh
- pending(msg, &block)
+ pending(msg, 1, &block)
end
# returns the page size in bytes
diff --git a/test/html4/sax/test_push_parser.rb b/test/html4/sax/test_push_parser.rb
index 6eb83c8339..cd37bad1d3 100644
--- a/test/html4/sax/test_push_parser.rb
+++ b/test/html4/sax/test_push_parser.rb
@@ -7,7 +7,7 @@
let(:parser) { Nokogiri::HTML4::SAX::PushParser.new(Nokogiri::SAX::TestCase::Doc.new) }
it :test_end_document_called do
- parser << (<<~HTML)
+ parser << <<~HTML
Paragraph 1
@@ -19,7 +19,7 @@
end
it :test_start_element do
- parser << (<<~HTML)
+ parser << <<~HTML
HTML
@@ -29,7 +29,7 @@
parser.document.start_elements,
)
- parser << (<<~HTML)
+ parser << <<~HTML
Paragraph 1
@@ -39,11 +39,11 @@
end
it :test_chevron_partial_html do
- parser << (<<~HTML)
+ parser << <<~HTML
HTML
- parser << (<<-HTML)
+ parser << <<~HTML
Paragraph 1
@@ -53,7 +53,7 @@
end
it :test_chevron do
- parser << (<<~HTML)
+ parser << <<~HTML
Paragraph 1
diff --git a/test/html4/test_comments.rb b/test/html4/test_comments.rb
index 5fc4d55d0e..7717e67c53 100644
--- a/test/html4/test_comments.rb
+++ b/test/html4/test_comments.rb
@@ -250,7 +250,7 @@ class TestComment < Nokogiri::TestCase
{
name: "div", children: [
{ name: "comment", content: "[if foo]" },
- { name: "div", attributes: [{name: "id", value: "do-i-exist"}] },
+ { name: "div", attributes: [{ name: "id", value: "do-i-exist" }] },
{ name: "comment", content: "[endif]" },
]
}
diff --git a/test/html4/test_document_fragment.rb b/test/html4/test_document_fragment.rb
index 57ad1193b3..c9a8c8774e 100644
--- a/test/html4/test_document_fragment.rb
+++ b/test/html4/test_document_fragment.rb
@@ -193,9 +193,9 @@ def test_malformed_fragment_is_corrected
assert_pattern do
fragment => [
{ name: "div", attributes: [
- { name: "<", value: ""},
- { name: "div", value: ""},
- ]}
+ { name: "<", value: "" },
+ { name: "div", value: "" },
+ ] }
]
end
else
diff --git a/test/html4/test_node.rb b/test/html4/test_node.rb
index 45ee8feb19..be00518e64 100644
--- a/test/html4/test_node.rb
+++ b/test/html4/test_node.rb
@@ -23,7 +23,15 @@ def test_to_a
def test_attr
node = @html.at("div.baz")
- assert_equal(node["class"], node.attr("class"))
+ assert_equal("baz", node["class"])
+ assert_equal("baz", node.attr("class"))
+ end
+
+ def test_attribute
+ # https://github.com/sparklemotion/nokogiri/issues/3487
+ node = @html.at("div.baz")
+ refute_nil(node.attribute("class"))
+ assert_equal("baz", node.attribute("class").value)
end
def test_get_attribute
diff --git a/test/html5/test_attributes.rb b/test/html5/test_attributes.rb
index 0dbfb6f13e..9cef22c7ed 100644
--- a/test/html5/test_attributes.rb
+++ b/test/html5/test_attributes.rb
@@ -15,4 +15,16 @@ def test_serialize_attribute
assert_equal('id="foo"', id_attr.to_html)
assert_equal('class="bar baz"', class_attr.to_html)
end
+
+ def test_duplicate_attributes
+ html = +""
+ span = Nokogiri::HTML5::DocumentFragment.parse(html, max_attributes: 1000).at_css("span")
+
+ assert_equal(676, span.attributes.length, "duplicate attribute should be silently ignored")
+ assert_equal("1", span["bb"], "bb attribute should hold the value of the first occurrence")
+ end
end if Nokogiri.uses_gumbo?
diff --git a/test/namespaces/test_namespace_definitions.rb b/test/namespaces/test_namespace_definitions.rb
index 7df6ea8608..77bf887f1e 100644
--- a/test/namespaces/test_namespace_definitions.rb
+++ b/test/namespaces/test_namespace_definitions.rb
@@ -26,12 +26,10 @@
end
child2 = doc.create_element("b", "xmlns:foo" => "http://nokogiri.org/ns/foo")
- pending_if("https://github.com/sparklemotion/nokogiri/issues/2543", Nokogiri.jruby?) do
- assert_equal(1, child2.namespace_definitions.length)
- child2.namespace_definitions.first.tap do |ns|
- assert_equal("foo", ns.prefix)
- assert_equal("http://nokogiri.org/ns/foo", ns.href)
- end
+ assert_equal(1, child2.namespace_definitions.length)
+ child2.namespace_definitions.first.tap do |ns|
+ assert_equal("foo", ns.prefix)
+ assert_equal("http://nokogiri.org/ns/foo", ns.href)
end
end
end
diff --git a/test/namespaces/test_serializing_namespaces.rb b/test/namespaces/test_serializing_namespaces.rb
new file mode 100644
index 0000000000..1a1a4f5515
--- /dev/null
+++ b/test/namespaces/test_serializing_namespaces.rb
@@ -0,0 +1,251 @@
+# frozen_string_literal: true
+
+require "helper"
+
+# This test uses Nokogiri::XML::Builder for code terseness.
+# The test is primarily intended to test serialization behavior,
+# not tree construction.
+describe "serializing namespaces" do
+ it "does not repeat xmlns definitions in child elements" do
+ # https://github.com/sparklemotion/nokogiri/issues/3455
+ doc = Nokogiri::XML::Builder.new do |xml|
+ xml["ds"].Signature("xmlns:ds" => "http://www.w3.org/2000/09/xmldsig#") do
+ xml["ds"].SignatureValue("foobar") do
+ end
+ end
+ end.doc.to_xml(save_with: Nokogiri::XML::Node::SaveOptions::AS_XML)
+
+ assert_includes(doc, '')
+ assert_includes(doc, "foobar")
+ end
+
+ it "does not repeat xmlns definitions even when explicitly defined" do
+ doc = Nokogiri::XML::Builder.new do |xml|
+ xml["ds"].Signature("xmlns:ds" => "http://www.w3.org/2000/09/xmldsig#") do
+ xml["ds"].SignatureValue("foobar", "xmlns:ds" => "http://www.w3.org/2000/09/xmldsig#") do
+ end
+ end
+ end.doc.to_xml(save_with: Nokogiri::XML::Node::SaveOptions::AS_XML)
+
+ assert_includes(doc, '')
+ assert_includes(doc, "foobar")
+ end
+
+ it "redeclares xmlns definitions when shadowed" do
+ doc = Nokogiri::XML::Builder.new do |xml|
+ xml["dnd"].adventure("xmlns:dnd" => "http://www.w3.org/dungeons#") do
+ xml["dnd"].party("xmlns:dnd" => "http://www.w3.org/dragons#") do
+ xml["dnd"].members("xmlns:dnd" => "http://www.w3.org/dragons#") do
+ xml["dnd"].character("xmlns:dnd" => "http://www.w3.org/dungeons#") do
+ xml["dnd"].name("Nigel", "xmlns:dnd" => "http://www.w3.org/dungeons#")
+ end
+ end
+ end
+ end
+ end.doc.to_xml(save_with: Nokogiri::XML::Node::SaveOptions::AS_XML)
+
+ assert_includes(doc, '')
+ assert_includes(doc, '')
+ assert_includes(doc, "")
+ assert_includes(doc, '')
+ assert_includes(doc, "Nigel")
+ end
+
+ describe "default namespaces" do
+ it "properly handles default namespaces" do
+ doc = Nokogiri::XML::Builder.new do |xml|
+ xml.root(xmlns: "http://default-namespace.org/") do
+ xml.child("with default namespace")
+ xml["specific"].child("with specific namespace", "xmlns:specific" => "http://specific-namespace.org/")
+ end
+ end.doc.to_xml(save_with: Nokogiri::XML::Node::SaveOptions::AS_XML)
+
+ assert_includes(doc, '')
+ assert_includes(doc, "with default namespace")
+ assert_includes(doc,
+ 'with specific namespace')
+ end
+
+ it "handles nested default namespaces" do
+ doc = Nokogiri::XML::Builder.new do |xml|
+ xml.root(xmlns: "http://outer-namespace.org/") do
+ xml.outer("in outer namespace")
+ xml.inner(xmlns: "http://inner-namespace.org/") do
+ xml.element("in inner namespace")
+ end
+ xml.another("back in outer namespace")
+ end
+ end.doc.to_xml(save_with: Nokogiri::XML::Node::SaveOptions::AS_XML)
+
+ assert_includes(doc, '')
+ assert_includes(doc, "in outer namespace")
+ assert_includes(doc, '')
+ pending_if("https://github.com/sparklemotion/nokogiri/issues/3457", Nokogiri.jruby?) do
+ # Here JRuby is incorrectly adding the xmlns namespace declaration, i.e.:
+ # 'in inner namespace'
+ assert_includes(doc, "in inner namespace")
+ end
+ assert_includes(doc, "back in outer namespace")
+ end
+ end
+
+ describe "multiple namespaces on elements" do
+ it "handles multiple namespaces declared on a single element" do
+ doc = Nokogiri::XML::Builder.new do |xml|
+ xml.root do
+ xml.element(
+ "xmlns:ns1" => "http://namespace1.org/",
+ "xmlns:ns2" => "http://namespace2.org/",
+ "xmlns:ns3" => "http://namespace3.org/",
+ ) do
+ xml["ns1"].first("using first namespace")
+ xml["ns2"].second("using second namespace")
+ xml["ns3"].third("using third namespace")
+ end
+ end
+ end.doc.to_xml(save_with: Nokogiri::XML::Node::SaveOptions::AS_XML)
+
+ assert_includes(doc, '')
+ assert_includes(doc, "using first namespace")
+ assert_includes(doc, "using second namespace")
+ assert_includes(doc, "using third namespace")
+ end
+
+ it "handles multiple namespaces declared on middle elements" do
+ doc = Nokogiri::XML::Builder.new do |xml|
+ xml.root("xmlns:top" => "http://top-namespace.org/") do
+ xml["top"].level1 do
+ xml.middle(
+ "xmlns:mid1" => "http://middle1-namespace.org/",
+ "xmlns:mid2" => "http://middle2-namespace.org/",
+ ) do
+ xml["mid1"].item("using middle1 namespace")
+ xml["mid2"].item("using middle2 namespace")
+ xml["top"].item("still using top namespace")
+
+ xml.bottom("xmlns:bot" => "http://bottom-namespace.org/") do
+ xml["bot"].item("using bottom namespace")
+ xml["mid1"].item("still using middle1 namespace")
+ end
+ end
+ end
+ end
+ end.doc.to_xml(save_with: Nokogiri::XML::Node::SaveOptions::AS_XML)
+
+ assert_includes(doc, '')
+ assert_includes(doc, "")
+ assert_includes(doc, '')
+ assert_includes(doc, "using middle1 namespace")
+ assert_includes(doc, "using middle2 namespace")
+ assert_includes(doc, "still using top namespace")
+ assert_includes(doc, '')
+ assert_includes(doc, "using bottom namespace")
+ assert_includes(doc, "still using middle1 namespace")
+ end
+ end
+
+ describe "namespace scope and visibility" do
+ it "handles namespace prefixes reused with different URIs" do
+ doc = Nokogiri::XML::Builder.new do |xml|
+ xml.root do
+ xml.outer("xmlns:ns" => "http://outer-uri.org/") do
+ xml["ns"].element("outer namespace")
+
+ xml.inner("xmlns:ns" => "http://inner-uri.org/") do
+ xml["ns"].element("inner namespace")
+ end
+
+ xml["ns"].another("back to outer namespace")
+ end
+ end
+ end.doc.to_xml(save_with: Nokogiri::XML::Node::SaveOptions::AS_XML)
+
+ assert_includes(doc, '')
+ assert_includes(doc, "outer namespace")
+ assert_includes(doc, '')
+ assert_includes(doc, "inner namespace")
+ assert_includes(doc, "back to outer namespace")
+ end
+
+ it "handles mixing default and prefixed namespaces" do
+ doc = Nokogiri::XML::Builder.new do |xml|
+ xml.root(:xmlns => "http://default.org/", "xmlns:ns" => "http://prefixed.org/") do
+ xml.default_element("in default namespace")
+ xml["ns"].prefixed_element("in prefixed namespace")
+
+ xml.mixed(xmlns: "http://new-default.org/") do
+ xml.new_default("in new default namespace")
+ xml["ns"].still_prefixed("still using original prefixed namespace")
+ end
+ end
+ end.doc.to_xml(save_with: Nokogiri::XML::Node::SaveOptions::AS_XML)
+
+ assert_includes(doc, '')
+ assert_includes(doc, "in default namespace")
+ assert_includes(doc, "in prefixed namespace")
+ assert_includes(doc, '')
+ pending_if("https://github.com/sparklemotion/nokogiri/issues/3457", Nokogiri.jruby?) do
+ # Here JRuby is incorrectly adding the xmlns namespace declaration, i.e.:
+ # 'in new default namespace'
+ assert_includes(doc, "in new default namespace")
+ end
+ assert_includes(doc, "still using original prefixed namespace")
+ end
+ end
+
+ describe "namespace inheritance" do
+ it "inherits namespaces from ancestors without redeclaring them" do
+ doc = Nokogiri::XML::Builder.new do |xml|
+ xml.root("xmlns:a" => "http://a.org/", "xmlns:b" => "http://b.org/") do
+ xml["a"].first do
+ xml["a"].second do
+ xml["b"].inner("using b namespace inside a")
+ end
+ end
+ xml["b"].third do
+ xml["a"].inner("using a namespace inside b")
+ end
+ end
+ end.doc.to_xml(save_with: Nokogiri::XML::Node::SaveOptions::AS_XML)
+
+ assert_includes(doc, '')
+ assert_includes(doc, "")
+ assert_includes(doc, "")
+ assert_includes(doc, "using b namespace inside a")
+ assert_includes(doc, "")
+ assert_includes(doc, "using a namespace inside b")
+
+ # Ensure namespaces aren't redundantly declared
+ assert_equal(1, doc.scan('xmlns:a="http://a.org/"').count)
+ assert_equal(1, doc.scan('xmlns:b="http://b.org/"').count)
+ end
+
+ it "works with namespace declarations at different levels of the hierarchy" do
+ doc = Nokogiri::XML::Builder.new do |xml|
+ xml.root("xmlns:top" => "http://top.org/") do
+ xml["top"].level1 do
+ xml["top"].level2("xmlns:mid" => "http://mid.org/") do
+ xml["mid"].item1
+ xml["top"].item2
+
+ xml["mid"].container("xmlns:deep" => "http://deep.org/") do
+ xml["deep"].deepest
+ xml["mid"].stillMid
+ xml["top"].stillTop
+ end
+ end
+ end
+ end
+ end.doc.to_xml(save_with: Nokogiri::XML::Node::SaveOptions::AS_XML)
+
+ assert_includes(doc, '')
+ assert_includes(doc, '')
+ assert_includes(doc, "")
+ assert_includes(doc, "")
+ assert_includes(doc, '')
+ assert_includes(doc, "")
+ assert_includes(doc, "")
+ assert_includes(doc, "")
+ end
+ end
+end
diff --git a/test/test_memory_usage.rb b/test/test_memory_usage.rb
index a23bb675e0..1b2044b448 100644
--- a/test/test_memory_usage.rb
+++ b/test/test_memory_usage.rb
@@ -313,5 +313,29 @@ def start_element(name, attrs = [])
# Expected error. This comment makes rubocop happy.
end
end
+
+ it "XML::SAX::ParserContext.io holds a reference to IO input" do
+ content = File.read(XML_ATOM_FILE)
+
+ memwatch(__method__) do
+ pc = Nokogiri::XML::SAX::ParserContext.io(StringIO.new(content), "ISO-8859-1")
+ parser = Nokogiri::XML::SAX::Parser.new(Nokogiri::SAX::TestCase::Doc.new)
+ GC.stress
+ pc.parse_with(parser)
+
+ assert_equal(472, parser.document.data.length)
+ end
+ end
+
+ it "XML::SAX::ParserContext.memory holds a reference to string input" do
+ memwatch(__method__) do
+ pc = Nokogiri::XML::SAX::ParserContext.memory(File.read(XML_ATOM_FILE), "ISO-8859-1")
+ parser = Nokogiri::XML::SAX::Parser.new(Nokogiri::SAX::TestCase::Doc.new)
+ GC.stress
+ pc.parse_with(parser)
+
+ assert_equal(472, parser.document.data.length)
+ end
+ end
end if ENV["NOKOGIRI_MEMORY_SUITE"] && Nokogiri.uses_libxml?
end
diff --git a/test/test_pattern_matching.rb b/test/test_pattern_matching.rb
index fb2d6c2c15..2a1a6ffc1f 100644
--- a/test/test_pattern_matching.rb
+++ b/test/test_pattern_matching.rb
@@ -258,14 +258,14 @@
it "finds node contents" do
assert_pattern do
- doc => { root: { children: [*, { children: [*, {name: "grandchild1", content: }, *] }, *] } }
+ doc => { root: { children: [*, { children: [*, { name: "grandchild1", content: }, *] }, *] } }
assert_equal("hello & goodbye", content)
end
end
it "finds node contents by attribute" do
assert_pattern do
- doc => { root: { children: [*, { children: [*, {attributes: [*, {name: "size", value: "small"}, *], content: }, *] }, *] } }
+ doc => { root: { children: [*, { children: [*, { attributes: [*, { name: "size", value: "small" }, *], content: }, *] }, *] } }
assert_equal("hello & goodbye", content)
end
end
@@ -274,13 +274,13 @@
describe "Fragment" do
it "finds nodes" do
assert_pattern do
- frag => [{name: "child1"}, {name: "child2"}, {name: "child3"}, {content: "\n"}]
+ frag => [{ name: "child1" }, { name: "child2" }, { name: "child3" }, { content: "\n" }]
end
end
it "finds attributes" do
assert_pattern do
- frag => [*, {name: "child2", attributes: }, *]
+ frag => [*, { name: "child2", attributes: }, *]
assert_equal("foo", attributes.first.name)
end
end
@@ -289,7 +289,7 @@
describe "Node" do
it "finds nodes" do
assert_pattern do
- doc.root => { elements: [{name: "child1"}, {name: "child2"}, {name: "child3"}] }
+ doc.root => { elements: [{ name: "child1" }, { name: "child2" }, { name: "child3" }] }
end
end
end
diff --git a/test/xml/node/test_attribute_methods.rb b/test/xml/node/test_attribute_methods.rb
index 4d5b78cac7..fba50e7b58 100644
--- a/test/xml/node/test_attribute_methods.rb
+++ b/test/xml/node/test_attribute_methods.rb
@@ -193,134 +193,159 @@ def test_remove_class
end
describe "setup" do
- it { _(node.get_attribute("noob")).must_be_nil }
+ it { assert_nil(node.get_attribute("noob")) }
end
describe "#kwattr_values" do
it "returns an array of space-delimited values" do
- _(node.kwattr_values("blargh")).must_equal(["foo", "bar", "baz", "bar", "foo", "quux", "foo", "manx"])
+ assert_equal(["foo", "bar", "baz", "bar", "foo", "quux", "foo", "manx"], node.kwattr_values("blargh"))
end
describe "when no attribute exists" do
it "returns an empty array" do
- _(node.kwattr_values("noob")).must_equal([])
+ assert_empty(node.kwattr_values("noob"))
end
end
describe "when an empty attribute exists" do
it "returns an empty array" do
node.set_attribute("noob", "")
- _(node.kwattr_values("noob")).must_equal([])
+ assert_empty(node.kwattr_values("noob"))
node.set_attribute("noob", " ")
- _(node.kwattr_values("noob")).must_equal([])
+ assert_empty(node.kwattr_values("noob"))
end
end
end
describe "kwattr_add" do
it "returns the node for chaining" do
- _(node.kwattr_add("noob", "asdf")).must_be_same_as(node)
+ assert_same(node, node.kwattr_add("noob", "asdf"))
end
it "creates a new attribute when necessary" do
- _(node.kwattr_add("noob", "asdf").get_attribute("noob")).wont_be_nil
+ refute_nil(node.kwattr_add("noob", "asdf").get_attribute("noob"))
end
it "adds a new bare keyword string" do
- _(node.kwattr_add("blargh", "jimmy").kwattr_values("blargh"))
- .must_equal(["foo", "bar", "baz", "bar", "foo", "quux", "foo", "manx", "jimmy"])
+ assert_equal(
+ ["foo", "bar", "baz", "bar", "foo", "quux", "foo", "manx", "jimmy"],
+ node.kwattr_add("blargh", "jimmy").kwattr_values("blargh"),
+ )
end
it "does not add a repeated bare keyword string" do
- _(node.kwattr_add("blargh", "foo").kwattr_values("blargh"))
- .must_equal(["foo", "bar", "baz", "bar", "foo", "quux", "foo", "manx"])
+ assert_equal(
+ ["foo", "bar", "baz", "bar", "foo", "quux", "foo", "manx"],
+ node.kwattr_add("blargh", "foo").kwattr_values("blargh"),
+ )
end
describe "given a string of keywords" do
it "adds new keywords and ignores existing keywords" do
- _(node.kwattr_add("blargh", "foo jimmy\tjohnny").kwattr_values("blargh"))
- .must_equal(["foo", "bar", "baz", "bar", "foo", "quux", "foo", "manx", "jimmy", "johnny"])
+ assert_equal(
+ ["foo", "bar", "baz", "bar", "foo", "quux", "foo", "manx", "jimmy", "johnny"],
+ node.kwattr_add("blargh", "foo jimmy\tjohnny").kwattr_values("blargh"),
+ )
end
end
describe "given an array of keywords" do
it "adds new keywords and ignores existing keywords" do
- _(node.kwattr_add("blargh", ["foo", "jimmy"]).kwattr_values("blargh"))
- .must_equal(["foo", "bar", "baz", "bar", "foo", "quux", "foo", "manx", "jimmy"])
+ assert_equal(
+ ["foo", "bar", "baz", "bar", "foo", "quux", "foo", "manx", "jimmy"],
+ node.kwattr_add("blargh", ["foo", "jimmy"]).kwattr_values("blargh"),
+ )
end
end
end
describe "kwattr_append" do
it "returns the node for chaining" do
- _(node.kwattr_append("noob", "asdf")).must_be_same_as(node)
+ assert_same(node, node.kwattr_append("noob", "asdf"))
end
it "creates a new attribute when necessary" do
- _(node.kwattr_append("noob", "asdf").get_attribute("noob")).wont_be_nil
+ refute_nil(node.kwattr_append("noob", "asdf").get_attribute("noob"))
end
it "adds a new bare keyword string" do
- _(node.kwattr_append("blargh", "jimmy").kwattr_values("blargh"))
- .must_equal(["foo", "bar", "baz", "bar", "foo", "quux", "foo", "manx", "jimmy"])
+ assert_equal(
+ ["foo", "bar", "baz", "bar", "foo", "quux", "foo", "manx", "jimmy"],
+ node.kwattr_append("blargh", "jimmy").kwattr_values("blargh"),
+ )
end
it "adds a repeated bare keyword string" do
- _(node.kwattr_append("blargh", "foo").kwattr_values("blargh"))
- .must_equal(["foo", "bar", "baz", "bar", "foo", "quux", "foo", "manx", "foo"])
+ assert_equal(
+ ["foo", "bar", "baz", "bar", "foo", "quux", "foo", "manx", "foo"],
+ node.kwattr_append("blargh", "foo").kwattr_values("blargh"),
+ )
end
describe "given a string of keywords" do
it "adds new keywords and existing keywords" do
- _(node.kwattr_append("blargh", "foo jimmy\tjohnny").kwattr_values("blargh"))
- .must_equal(["foo", "bar", "baz", "bar", "foo", "quux", "foo", "manx", "foo", "jimmy", "johnny"])
+ assert_equal(
+ ["foo", "bar", "baz", "bar", "foo", "quux", "foo", "manx", "foo", "jimmy", "johnny"],
+ node.kwattr_append("blargh", "foo jimmy\tjohnny").kwattr_values("blargh"),
+ )
end
end
describe "given an array of keywords" do
it "adds new keywords and existing keywords" do
- _(node.kwattr_append("blargh", ["foo", "jimmy"]).kwattr_values("blargh"))
- .must_equal(["foo", "bar", "baz", "bar", "foo", "quux", "foo", "manx", "foo", "jimmy"])
+ assert_equal(
+ ["foo", "bar", "baz", "bar", "foo", "quux", "foo", "manx", "foo", "jimmy"],
+ node.kwattr_append("blargh", ["foo", "jimmy"]).kwattr_values("blargh"),
+ )
end
end
end
describe "kwattr_remove" do
it "returns the node for chaining" do
- _(node.kwattr_remove("noob", "asdf")).must_be_same_as(node)
+ assert_same(node, node.kwattr_remove("noob", "asdf"))
end
it "gracefully handles a non-existent attribute" do
- _(node.kwattr_remove("noob", "asdf").get_attribute("noob")).must_be_nil
+ assert_nil(node.kwattr_remove("noob", "asdf").get_attribute("noob"))
end
it "removes an existing bare keyword string" do
- _(node.kwattr_remove("blargh", "foo").kwattr_values("blargh"))
- .must_equal(["bar", "baz", "bar", "quux", "manx"])
+ assert_equal(
+ ["bar", "baz", "bar", "quux", "manx"],
+ node.kwattr_remove("blargh", "foo").kwattr_values("blargh"),
+ )
end
it "gracefully ignores a non-existent bare keyword string" do
- _(node.kwattr_remove("blargh", "jimmy").kwattr_values("blargh"))
- .must_equal(["foo", "bar", "baz", "bar", "foo", "quux", "foo", "manx"])
+ assert_equal(
+ ["foo", "bar", "baz", "bar", "foo", "quux", "foo", "manx"],
+ node.kwattr_remove("blargh", "jimmy").kwattr_values("blargh"),
+ )
end
describe "given a string of keywords" do
it "removes existing keywords and ignores other keywords" do
- _(node.kwattr_remove("blargh", "foo jimmy\tjohnny").kwattr_values("blargh"))
- .must_equal(["bar", "baz", "bar", "quux", "manx"])
+ assert_equal(
+ ["bar", "baz", "bar", "quux", "manx"],
+ node.kwattr_remove("blargh", "foo jimmy\tjohnny").kwattr_values("blargh"),
+ )
end
end
describe "given an array of keywords" do
it "adds new keywords and existing keywords" do
- _(node.kwattr_remove("blargh", ["foo", "jimmy"]).kwattr_values("blargh"))
- .must_equal(["bar", "baz", "bar", "quux", "manx"])
+ assert_equal(
+ ["bar", "baz", "bar", "quux", "manx"],
+ node.kwattr_remove("blargh", ["foo", "jimmy"]).kwattr_values("blargh"),
+ )
end
end
it "removes the attribute when no values are left" do
- _(node.kwattr_remove("blargh", ["foo", "bar", "baz", "bar", "foo", "quux", "foo", "manx"]).get_attribute("blargh")).must_be_nil
+ node.kwattr_remove("blargh", ["foo", "bar", "baz", "bar", "foo", "quux", "foo", "manx"])
+ assert_nil(node.get_attribute("blargh"))
end
end
end
diff --git a/test/xml/node/test_save_options.rb b/test/xml/node/test_save_options.rb
index 69aeb949c7..b718205a68 100644
--- a/test/xml/node/test_save_options.rb
+++ b/test/xml/node/test_save_options.rb
@@ -19,9 +19,9 @@ def test_predicate_#{constant.downcase}
def test_default_xml_save_options
if Nokogiri.jruby?
- assert_equal(0, (SaveOptions::DEFAULT_XML & SaveOptions::FORMAT))
+ assert_equal(0, SaveOptions::DEFAULT_XML & SaveOptions::FORMAT)
else
- assert_equal(SaveOptions::FORMAT, (SaveOptions::DEFAULT_XML & SaveOptions::FORMAT))
+ assert_equal(SaveOptions::FORMAT, SaveOptions::DEFAULT_XML & SaveOptions::FORMAT)
end
end
end
diff --git a/test/xml/sax/test_push_parser.rb b/test/xml/sax/test_push_parser.rb
index a0dea3b99e..0ea93cfd76 100644
--- a/test/xml/sax/test_push_parser.rb
+++ b/test/xml/sax/test_push_parser.rb
@@ -88,7 +88,7 @@ def error(msg)
end
it :test_end_document_called do
- parser << (<<~XML)
+ parser << <<~XML
Paragraph 1
@@ -100,14 +100,14 @@ def error(msg)
end
it :test_start_element do
- parser << (<<~XML)
+ parser << <<~XML
XML
assert_equal [["p", [["id", "asdfasdf"]]]],
parser.document.start_elements
- parser << (<<~XML)
+ parser << <<~XML
Paragraph 1
@@ -117,14 +117,14 @@ def error(msg)
end
it :test_start_element_with_namespaces do
- parser << (<<~XML)
+ parser << <<~XML
XML
assert_equal [["p", [["xmlns:foo", "http://foo.example.com/"]]]],
parser.document.start_elements
- parser << (<<~XML)
+ parser << <<~XML
Paragraph 1
@@ -134,7 +134,7 @@ def error(msg)
end
it :test_start_element_ns do
- parser << (<<~XML)
+ parser << <<~XML
XML
@@ -152,7 +152,7 @@ def error(msg)
end
it :test_end_element_ns do
- parser << (<<~XML)
+ parser << <<~XML
XML
@@ -162,11 +162,11 @@ def error(msg)
end
it :test_chevron_partial_xml do
- parser << (<<~XML)
+ parser << <<~XML
XML
- parser << (<<~XML)
+ parser << <<~XML
Paragraph 1
@@ -176,7 +176,7 @@ def error(msg)
end
it :test_chevron do
- parser << (<<~XML)
+ parser << <<~XML
Paragraph 1
@@ -192,7 +192,7 @@ def error(msg)
it :test_recover do
parser.options |= Nokogiri::XML::ParseOptions::RECOVER
- parser << (<<~XML)
+ parser << <<~XML
Foo
@@ -248,7 +248,7 @@ def error(msg)
it :test_untouched_entities do
skip_unless_libxml2("entities are always replaced in pure Java version")
- parser << (<<~XML)
+ parser << <<~XML
Paragraph 1 & 2
@@ -261,7 +261,7 @@ def error(msg)
it :test_replaced_entities do
parser.replace_entities = true
- parser << (<<~XML)
+ parser << <<~XML
Paragraph 1 & 2
diff --git a/test/xml/test_builder.rb b/test/xml/test_builder.rb
index 65dffe1ce3..f29bf44aba 100644
--- a/test/xml/test_builder.rb
+++ b/test/xml/test_builder.rb
@@ -78,6 +78,30 @@ def test_builder_namespace_part_deux
assert_equal({ "xmlns:a" => "x", "xmlns:c" => "z" }, namespaces_defined_on(b))
end
+ def test_builder_namespaces_part_three
+ doc = Nokogiri::XML::Builder.new do |xml|
+ xml["dnd"].adventure("xmlns:dnd" => "http://www.w3.org/dungeons#") do
+ xml["dnd"].party("xmlns:dnd" => "http://www.w3.org/dragons#") do
+ xml["dnd"].character("xmlns:dnd" => "http://www.w3.org/dungeons#") do
+ xml["dnd"].name("Nigel", "xmlns:dnd" => "http://www.w3.org/dungeons#")
+ end
+ end
+ end
+ end.doc
+
+ adventure_node = doc.at_xpath("//*[local-name()='adventure']")
+ assert_equal("http://www.w3.org/dungeons#", adventure_node.namespace.href)
+
+ party_node = doc.at_xpath("//*[local-name()='party']")
+ assert_equal("http://www.w3.org/dragons#", party_node.namespace.href)
+
+ character_node = doc.at_xpath("//*[local-name()='character']")
+ assert_equal("http://www.w3.org/dungeons#", character_node.namespace.href)
+
+ name_node = doc.at_xpath("//*[local-name()='name']")
+ assert_equal("http://www.w3.org/dungeons#", name_node.namespace.href)
+ end
+
def test_builder_with_unlink
b = Nokogiri::XML::Builder.new do |xml|
xml.foo do
diff --git a/test/xml/test_document_encoding.rb b/test/xml/test_document_encoding.rb
index aecad95c5b..0127d1a0a0 100644
--- a/test/xml/test_document_encoding.rb
+++ b/test/xml/test_document_encoding.rb
@@ -124,9 +124,12 @@ class TestDocumentEncoding < Nokogiri::TestCase
# no final newline on jruby. descriptive, not prescriptive.
expected_length = Nokogiri.jruby? ? xml.bytesize - 1 : xml.bytesize
-
- assert_equal(Encoding::UTF_8, output.encoding)
assert_equal(expected_length, output.bytesize)
+
+ # Note: I dropped the assertion on the encoding of the string return from io.read
+ # because this behavior has changed back and forth in rubyzip versions 2.4.1 and
+ # 3.0.0.dev, and it's not relevant to the original bug report which was about an
+ # exception during writing.
end
end
end
diff --git a/test/xml/test_node.rb b/test/xml/test_node.rb
index 641b0dce5b..138ee7decb 100644
--- a/test/xml/test_node.rb
+++ b/test/xml/test_node.rb
@@ -109,7 +109,7 @@ def test_node_context_parsing_of_malformed_html_fragment
assert_empty(doc.errors)
assert_pattern do
nodeset => [
- { name: "div", attributes: [{name: "<", value: ""}, { name: "div", value: ""}] },
+ { name: "div", attributes: [{ name: "<", value: "" }, { name: "div", value: "" }] },
]
end
else
@@ -131,7 +131,7 @@ def test_node_context_parsing_of_malformed_html_fragment_with_recover_is_correct
assert_empty(doc.errors)
assert_pattern do
nodeset => [
- { name: "div", attributes: [{name: "<", value: ""}, { name: "div", value: ""}] },
+ { name: "div", attributes: [{ name: "<", value: "" }, { name: "div", value: "" }] },
]
end
else
@@ -461,7 +461,7 @@ def test_description
def test_spaceship
nodes = xml.xpath("//employee")
- assert_equal(-1, (nodes.first <=> nodes.last))
+ assert_equal(-1, nodes.first <=> nodes.last)
list = [nodes.first, nodes.last].sort
assert_equal(nodes.first, list.first)
assert_equal(nodes.last, list.last)
diff --git a/test/xml/test_node_reparenting.rb b/test/xml/test_node_reparenting.rb
index 71270513d3..9e833d2af1 100644
--- a/test/xml/test_node_reparenting.rb
+++ b/test/xml/test_node_reparenting.rb
@@ -88,13 +88,13 @@ class TestNodeReparenting < Nokogiri::TestCase
it "unlinks the Node from its previous position" do
@doc.at_xpath(params[:target]).send(method, @other_node)
result = @other_doc.at_xpath("/root/a2")
- _(result).must_be_nil
+ assert_nil(result)
end
it "inserts the Node in the proper position" do
@doc.at_xpath(params[:target]).send(method, @other_node)
result = @doc.at_xpath("/root/a1/a2")
- _(result).wont_be_nil
+ refute_nil(result)
end
it "returns the expected value" do
@@ -103,9 +103,9 @@ class TestNodeReparenting < Nokogiri::TestCase
if !params.key?(:returns_self)
assert(method.to_s.end_with?("="))
elsif params[:returns_self]
- _(result).must_equal(sendee)
+ assert_equal(sendee, result)
else
- _(result).must_equal(@other_node)
+ assert_equal(@other_node, result)
end
end
end
@@ -115,7 +115,7 @@ class TestNodeReparenting < Nokogiri::TestCase
it "inserts the fragment roots in the proper position" do
@doc.at_xpath(params[:target]).send(method, @fragment_string)
result = @doc.xpath("/root/a1/node()").collect(&:name)
- _(result).must_equal(params[:children_tags])
+ assert_equal(params[:children_tags], result)
end
it "returns the expected value" do
@@ -124,10 +124,10 @@ class TestNodeReparenting < Nokogiri::TestCase
if !params.key?(:returns_self)
assert(method.to_s.end_with?("="))
elsif params[:returns_self]
- _(result).must_equal(sendee)
+ assert_equal(sendee, result)
else
- _(result).must_be_kind_of(Nokogiri::XML::NodeSet)
- _(result.to_html).must_equal(@fragment_string)
+ assert_kind_of(Nokogiri::XML::NodeSet, result)
+ assert_equal(@fragment_string, result.to_html)
end
end
end
@@ -135,7 +135,7 @@ class TestNodeReparenting < Nokogiri::TestCase
it "inserts the fragment roots in the proper position" do
@doc.at_xpath(params[:target]).send(method, @fragment)
result = @doc.xpath("/root/a1/node()").collect(&:name)
- _(result).must_equal(params[:children_tags])
+ assert_equal(params[:children_tags], result)
end
end
describe "passed a document" do
@@ -152,7 +152,7 @@ class TestNodeReparenting < Nokogiri::TestCase
it "inserts each member of the NodeSet in the proper order" do
@doc.at_xpath(params[:target]).send(method, @node_set)
result = @doc.xpath("/root/a1/node()").collect(&:name)
- _(result).must_equal(params[:children_tags])
+ assert_equal(params[:children_tags], result)
end
end
end
@@ -163,7 +163,7 @@ class TestNodeReparenting < Nokogiri::TestCase
it "merges the Text node with adjacent Text nodes" do
@doc.at_xpath("/root/a1").add_child(Nokogiri::XML::Text.new("hello", @doc))
result = @doc.at_xpath("/root/a1/text()").content
- _(result).must_equal("First nodehello")
+ assert_equal("First nodehello", result)
end
end
@@ -171,7 +171,7 @@ class TestNodeReparenting < Nokogiri::TestCase
it "merges the Text node with adjacent Text nodes" do
@doc.at_xpath("/root/a3/bx").replace(Nokogiri::XML::Text.new("hello", @doc))
result = @doc.at_xpath("/root/a3/text()").content
- _(result).must_equal("Third hellonode")
+ assert_equal("Third hellonode", result)
end
end
end
diff --git a/test/xml/test_node_set.rb b/test/xml/test_node_set.rb
index 2e2e6c7cde..5655c9e953 100644
--- a/test/xml/test_node_set.rb
+++ b/test/xml/test_node_set.rb
@@ -129,6 +129,23 @@ class TestNodeSet < Nokogiri::TestCase
end
end
+ it "#attr on XML gets attribute from first node" do
+ doc = Nokogiri::XML("")
+ children = doc.css("child")
+
+ refute_nil(children.attr("name"))
+ assert_equal(children.first.attribute("name"), children.attr("name"))
+ end
+
+ it "#attr on HTML gets attribute from first node" do
+ # https://github.com/sparklemotion/nokogiri/issues/3487
+ doc = Nokogiri::HTML("")
+ children = doc.css("child")
+
+ refute_nil(children.attr("name"))
+ assert_equal(children.first.attribute("name"), children.attr("name"))
+ end
+
it "#attribute with no args gets attribute from first node" do
list.first["foo"] = "bar"
assert_equal(list.first.attribute("foo"), list.attribute("foo"))
diff --git a/test/xml/test_xpath.rb b/test/xml/test_xpath.rb
index 7948cac051..f80dba124b 100644
--- a/test/xml/test_xpath.rb
+++ b/test/xml/test_xpath.rb
@@ -5,13 +5,6 @@
module Nokogiri
module XML
class TestXPath < Nokogiri::TestCase
- #
- # Note that many of these tests vary for jruby because custom xpath functions in JRuby require
- # a namespace, and libxml2 (and the original implementation of Nokogiri) do not.
- #
- # Ideally we should change this to always require a namespace.
- # See https://github.com/sparklemotion/nokogiri/issues/2147
- #
def setup
super