Merge branch 'master' into escaping-npe-fix

.gitignore

@@ -8,3 +8,4 @@ target/
 .settings/
 *Thrash*
 bin/
+.vscode/

CHANGES

@@ -19,12 +19,37 @@ Release 1.16.2 [PENDING]
     lastElementSibling, firstElementChild, and lastElementChild. They now inplace filter/skip in the child-node list, vs
     having to allocate and scan a complete Element filtered list.
 
+  * Improvement: optimized internal methods that previously called Element.children() to use filter/skip child-node list
+    accessors instead, reducing new Element List allocations.
+
+  * Improvement: tweaked the performance of parsing :pseudo selectors.
+
+  * Improvement: when using the `:empty` pseudo-selector, blank textnodes are now considered empty. Previously,
+    an element containing any whitespace was not considered empty.
+    <https://github.com/jhy/jsoup/issues/1976>
+
   * Bugfix: `form` elements and empty elements (such as `img`) did not have their attributes de-duplicated.
     <https://github.com/jhy/jsoup/pull/1950>
 
   * Bugfix: if Document.OutputSettings was cloned from a clone, an NPE would be thrown when used.
     <https://github.com/jhy/jsoup/pull/1964>
 
+  * Bugfix: in Jsoup.connect(url), URL paths containing a %2B were incorrectly recoded to a '+', or a '+' was recoded
+    to a ' '. Fixed by reverting to the previous behavior of not encoding supplied paths, other than normalizing to
+    ASCII.
+    <https://github.com/jhy/jsoup/issues/1952>
+
+  * Bugfix: in Jsoup.connect(url), the ConstrainableInputStream would clear Thread interrupts when reading the body.
+    This precluded callers from spawning a thread, running a number of requests for a length of time, then joining that
+    thread after interrupting it.
+    <https://github.com/jhy/jsoup/issues/1991>
+
+  * Bugfix: when tracking HTML source positions, the closing tags for H1...H6 elements were not tracked correctly.
+    <https://github.com/jhy/jsoup/issues/1987>
+
+  * Bugfix: in Jsoup.connect(), a DELETE method request did not support a request body.
+    <https://github.com/jhy/jsoup/issues/1972>
+
   * Change: removed previously deprecated methods Document#normalise, Element#forEach(org.jsoup.helper.Consumer<>),
     Node#forEach(org.jsoup.helper.Consumer<>), and the org.jsoup.helper.Consumer interface; the latter being a
     previously required compatibility shim prior to Android's de-sugaring support.

pom.xml

@@ -109,7 +109,7 @@
       <plugin>
         <groupId>org.apache.maven.plugins</groupId>
         <artifactId>maven-source-plugin</artifactId>
-        <version>3.2.1</version>
+        <version>3.3.0</version>
         <configuration>
           <excludes>
             <exclude>org/jsoup/examples/**</exclude>
@@ -147,7 +147,7 @@
       <plugin>
         <groupId>org.apache.felix</groupId>
         <artifactId>maven-bundle-plugin</artifactId>
-        <version>5.1.8</version>
+        <version>5.1.9</version>
         <executions>
           <execution>
             <id>bundle-manifest</id>
@@ -185,7 +185,7 @@
       </plugin>
       <plugin>
         <artifactId>maven-failsafe-plugin</artifactId>
-        <version>3.1.0</version>
+        <version>3.1.2</version>
         <executions>
           <execution>
             <goals>
@@ -307,7 +307,7 @@
         <plugins>
           <plugin>
             <artifactId>maven-failsafe-plugin</artifactId>
-            <version>3.1.0</version>
+            <version>3.1.2</version>
             <executions>
               <execution>
                 <goals>

src/main/java/org/jsoup/Connection.java

@@ -43,7 +43,7 @@ public interface Connection {
      * GET and POST http methods.
      */
     enum Method {
-        GET(false), POST(true), PUT(true), DELETE(false), PATCH(true), HEAD(false), OPTIONS(false), TRACE(false);
+        GET(false), POST(true), PUT(true), DELETE(true), PATCH(true), HEAD(false), OPTIONS(false), TRACE(false);
 
         private final boolean hasBody;
 

src/main/java/org/jsoup/helper/UrlBuilder.java

@@ -38,24 +38,20 @@ URL build() {
                 u.getUserInfo(),
                 IDN.toASCII(decodePart(u.getHost())), // puny-code
                 u.getPort(),
-                decodePart(u.getPath()),
-                null, null // query and fragment appended later so as not to encode
+                null, null, null // path, query and fragment appended later so as not to encode
             );
 
-            String normUrl = uri.toASCIIString();
-            if (q != null || u.getRef() != null) {
-                StringBuilder sb = StringUtil.borrowBuilder().append(normUrl);
-                if (q != null) {
-                    sb.append('?');
-                    appendToAscii(StringUtil.releaseBuilder(q), true, sb);
-                }
-                if (u.getRef() != null) {
-                    sb.append('#');
-                    appendToAscii(u.getRef(), false, sb);
-                }
-                normUrl = StringUtil.releaseBuilder(sb);
+            StringBuilder normUrl = StringUtil.borrowBuilder().append(uri.toASCIIString());
+            appendToAscii(u.getPath(), false, normUrl);
+            if (q != null) {
+                normUrl.append('?');
+                appendToAscii(StringUtil.releaseBuilder(q), true, normUrl);
             }
-            u =  new URL(normUrl);
+            if (u.getRef() != null) {
+                normUrl.append('#');
+                appendToAscii(u.getRef(), false, normUrl);
+            }
+            u = new URL(StringUtil.releaseBuilder(normUrl));
             return u;
         } catch (MalformedURLException | URISyntaxException | UnsupportedEncodingException e) {
             // we assert here so that any incomplete normalization issues can be caught in devel. but in practise,

src/main/java/org/jsoup/helper/W3CDom.java

@@ -211,7 +211,7 @@ public Document fromJsoup(org.jsoup.nodes.Element in) {
             }
             out.setXmlStandalone(true);
             // if in is Document, use the root element, not the wrapping document, as the context:
-            org.jsoup.nodes.Element context = (in instanceof org.jsoup.nodes.Document) ? in.child(0) : in;
+            org.jsoup.nodes.Element context = (in instanceof org.jsoup.nodes.Document) ? in.firstElementChild() : in;
             out.setUserData(ContextProperty, context, null);
             convert(inDoc != null ? inDoc : in, out);
             return out;
@@ -251,7 +251,7 @@ public void convert(org.jsoup.nodes.Element in, Document out) {
             }
             builder.syntax = inDoc.outputSettings().syntax();
         }
-        org.jsoup.nodes.Element rootEl = in instanceof org.jsoup.nodes.Document ? in.child(0) : in; // skip the #root node if a Document
+        org.jsoup.nodes.Element rootEl = in instanceof org.jsoup.nodes.Document ? in.firstElementChild() : in; // skip the #root node if a Document
         NodeTraversor.traverse(builder, rootEl);
     }
 

src/main/java/org/jsoup/internal/ConstrainableInputStream.java

@@ -49,8 +49,8 @@ public static ConstrainableInputStream wrap(InputStream in, int bufferSize, int
     public int read(byte[] b, int off, int len) throws IOException {
         if (interrupted || capped && remaining <= 0)
             return -1;
-        if (Thread.interrupted()) {
-            // interrupted latches, because parse() may call twice (and we still want the thread interupt to clear)
+        if (Thread.currentThread().isInterrupted()) {
+            // interrupted latches, because parse() may call twice
             interrupted = true;
             return -1;
         }

src/main/java/org/jsoup/nodes/Document.java

@@ -102,9 +102,11 @@ else if (!(node instanceof LeafNode)) // scans forward across comments, text, pr
      @return the root HTML element.
      */
     private Element htmlEl() {
-        for (Element el: childElementsList()) {
+        Element el = firstElementChild();
+        while (el != null) {
             if (el.normalName().equals("html"))
                 return el;
+            el = el.nextElementSibling();
         }
         return appendElement("html");
     }
@@ -118,10 +120,12 @@ private Element htmlEl() {
      @return {@code head} element.
      */
     public Element head() {
-        Element html = htmlEl();
-        for (Element el: html.childElementsList()) {
+        final Element html = htmlEl();
+        Element el = html.firstElementChild();
+        while (el != null) {
             if (el.normalName().equals("head"))
                 return el;
+            el = el.nextElementSibling();
         }
         return html.prependElement("head");
     }
@@ -136,10 +140,12 @@ public Element head() {
      had no contents, or the outermost {@code <frameset> element} for frameset documents.
      */
     public Element body() {
-        Element html = htmlEl();
-        for (Element el: html.childElementsList()) {
+        final Element html = htmlEl();
+        Element el = html.firstElementChild();
+        while (el != null) {
             if ("body".equals(el.normalName()) || "frameset".equals(el.normalName()))
                 return el;
+            el = el.nextElementSibling();
         }
         return html.appendElement("body");
     }

src/main/java/org/jsoup/nodes/Node.java

@@ -456,8 +456,10 @@ public Node wrap(String html) {
     }
 
     private Element getDeepChild(Element el) {
-        while (el.childrenSize() > 0) {
-            el = el.childElementsList().get(0);
+        Element child = el.firstElementChild();
+        while (child != null) {
+            el = child;
+            child = child.firstElementChild();
         }
         return el;
     }

src/main/java/org/jsoup/parser/HtmlTreeBuilder.java

@@ -424,20 +424,12 @@ Element popStackToClose(String elName) {
     // elnames is sorted, comes from Constants
     void popStackToClose(String... elNames) {
         for (int pos = stack.size() -1; pos >= 0; pos--) {
-            Element next = stack.get(pos);
+            Element el = stack.get(pos);
             stack.remove(pos);
-            if (inSorted(next.normalName(), elNames))
-                break;
-        }
-    }
-
-    void popStackToBefore(String elName) {
-        for (int pos = stack.size() -1; pos >= 0; pos--) {
-            Element next = stack.get(pos);
-            if (next.normalName().equals(elName)) {
+            if (inSorted(el.normalName(), elNames)) {
+                if (currentToken instanceof Token.EndTag)
+                    onNodeClosed(el, currentToken);
                 break;
-            } else {
-                stack.remove(pos);
             }
         }
     }

src/main/java/org/jsoup/select/Evaluator.java

@@ -464,7 +464,7 @@ public static final class IsLastChild extends Evaluator {
 		@Override
 		public boolean matches(Element root, Element element) {
 			final Element p = element.parent();
-			return p != null && !(p instanceof Document) && element.elementSiblingIndex() == p.childrenSize()-1;
+			return p != null && !(p instanceof Document) && element == p.lastElementChild();
 		}
 
 		@Override
@@ -617,9 +617,11 @@ protected int calculatePosition(Element root, Element element) {
                 return 0;
 
             int pos = 0;
-            int size = parent.childrenSize();
-            for (int i = element.elementSiblingIndex(); i < size; i++) {
-                if (parent.child(i).normalName().equals(element.normalName())) pos++;
+            Element next = element;
+            while (next != null) {
+                if (next.normalName().equals(element.normalName()))
+                    pos++;
+                next = next.nextElementSibling();
             }
             return pos;
         }
@@ -637,7 +639,7 @@ public static final class IsFirstChild extends Evaluator {
     	@Override
     	public boolean matches(Element root, Element element) {
     		final Element p = element.parent();
-    		return p != null && !(p instanceof Document) && element.elementSiblingIndex() == 0;
+    		return p != null && !(p instanceof Document) && element == p.firstElementChild();
     	}
 
     	@Override
@@ -654,7 +656,7 @@ public String toString() {
     public static final class IsRoot extends Evaluator {
     	@Override
     	public boolean matches(Element root, Element element) {
-    		final Element r = root instanceof Document?root.child(0):root;
+    		final Element r = root instanceof Document ? root.firstElementChild() : root;
     		return element == r;
     	}
 
@@ -687,12 +689,13 @@ public boolean matches(Element root, Element element) {
 			if (p==null || p instanceof Document) return false;
 
 			int pos = 0;
-            int size = p.childrenSize();
-            for (int i = 0; i < size; i++) {
-                if (p.child(i).normalName().equals(element.normalName()))
+            Element next = p.firstElementChild();
+            while (next != null) {
+                if (next.normalName().equals(element.normalName()))
                     pos++;
                 if (pos > 1)
                     break;
+                next = next.nextElementSibling();
             }
         	return pos == 1;
 		}
@@ -707,7 +710,10 @@ public static final class IsEmpty extends Evaluator {
 		public boolean matches(Element root, Element element) {
         	List<Node> family = element.childNodes();
             for (Node n : family) {
-                if (!(n instanceof Comment || n instanceof XmlDeclaration || n instanceof DocumentType)) return false;
+                if (n instanceof TextNode)
+                    return ((TextNode)n).isBlank();
+                if (!(n instanceof Comment || n instanceof XmlDeclaration || n instanceof DocumentType))
+                    return false;
             }
         	return true;
 		}