Merge pull request #24 from anonyein/origin

Origin

Author: anonyein

.github/dependabot.yml

@@ -11,6 +11,9 @@ updates:
         update-types: ["version-update:semver-major"]
       - dependency-name: "org.eclipse.jetty:jetty-servlet"
         update-types: ["version-update:semver-major"]
+      # Et tu, junit? Keep us on 5, as 6 has min JDK17 - https://docs.junit.org/6.0.0-RC3/release-notes/#release-notes-6.0.0-M1
+      - dependency-name: "org.junit.jupiter:junit-jupiter"
+        update-types: ["version-update:semver-major"]
 
   - package-ecosystem: github-actions
     directory: /

.github/workflows/codeql.yml

@@ -20,11 +20,11 @@ jobs:
           distribution: 'temurin'
           cache: 'maven'
       - name: CodeQL Initialization
-        uses: github/codeql-action/init@v3
+        uses: github/codeql-action/init@v4
         with:
           languages: java
           queries: +security-and-quality
       - name: Autobuild
-        uses: github/codeql-action/autobuild@v3
+        uses: github/codeql-action/autobuild@v4
       - name: CodeQL Analysis
-        uses: github/codeql-action/analyze@v3
+        uses: github/codeql-action/analyze@v4

CHANGES.md

@@ -25,6 +25,7 @@
 * Null characters in the HTML body were not consistently removed; and in foreign content were not correctly replaced. [#2395](https://github.com/jhy/jsoup/issues/2395)
 * An IndexOutOfBoundsException could be thrown when parsing a body fragment with crafted input. Now logged as a parse error. [#2397](https://github.com/jhy/jsoup/issues/2397), [#2406](https://github.com/jhy/jsoup/issues/2406)
 * When using StructuralEvaluators (e.g., a `parent child` selector) across many retained threads, their memoized results could also be retained, increasing memory use. These results are now cleared immediately after use, reducing overall memory consumption. [#2411](https://github.com/jhy/jsoup/issues/2411)
+* Custom tags marked as `Tag.Void` now parse and serialize like the built-in void elements: they no longer consume following content, and the XML serializer emits the expected self-closing form. [#2425](https://github.com/jhy/jsoup/issues/2425)
 
 ### Internal Changes
 * Deprecated internal helper `org.jsoup.internal.Functions` (for removal in v1.23.1). This was previously used to support older Android API levels without full `java.util.function` coverage; jsoup now requires core library desugaring so this indirection is no longer necessary. [#2412](https://github.com/jhy/jsoup/pull/2412)

pom.xml

@@ -66,7 +66,7 @@
       <plugin>
         <groupId>org.codehaus.mojo</groupId>
         <artifactId>animal-sniffer-maven-plugin</artifactId>
-        <version>1.24</version>
+        <version>1.26</version>
         <executions>
           <execution>
             <id>api-java8</id>
@@ -275,7 +275,7 @@
         <!-- API version compat check - https://siom79.github.io/japicmp/ -->
         <groupId>com.github.siom79.japicmp</groupId>
         <artifactId>japicmp-maven-plugin</artifactId>
-        <version>0.23.1</version>
+        <version>0.24.2</version>
         <configuration>
           <!-- hard code previous version; can't detect when running stateless on build server -->
           <oldVersion>
@@ -501,7 +501,7 @@
     <dependency>
       <groupId>org.junit.jupiter</groupId>
       <artifactId>junit-jupiter</artifactId>
-      <version>5.13.4</version>
+      <version>5.14.0</version>
       <scope>test</scope>
     </dependency>
 

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

@@ -332,7 +332,9 @@ Element insertElementFor(final Token.StartTag startTag) {
         if (startTag.isSelfClosing()) {
             Tag tag = el.tag();
             tag.setSeenSelfClose(); // can infer output if in xml syntax
-            if (tag.isKnownTag() && (tag.isEmpty() || tag.isSelfClosing())) {
+            if (tag.isEmpty()) {
+                // treated as empty below; nothing further
+            } else if (tag.isKnownTag() && tag.isSelfClosing()) {
                 // ok, allow it. effectively a pop, but fiddles with the state. handles empty style, title etc which would otherwise leave us in data state
                 tokeniser.transition(TokeniserState.Data); // handles <script />, otherwise needs breakout steps from script data
                 tokeniser.emit(emptyEnd.reset().name(el.tagName()));  // ensure we get out of whatever state we are in. emitted for yielded processing
@@ -342,6 +344,10 @@ Element insertElementFor(final Token.StartTag startTag) {
             }
         }
 
+        if (el.tag().isEmpty()) {
+            pop(); // custom void tags behave like built-in voids (no children, not left on the stack); known empty go via insertEmpty
+        }
+
         return el;
     }
 

src/test/java/org/jsoup/integration/TestServer.java

@@ -177,6 +177,7 @@ private static void addHttpsConnector(File keystoreFile, Server server) {
             server,
             new SslConnectionFactory(sslContextFactory, HttpVersion.HTTP_1_1.asString()),
             new HttpConnectionFactory(httpsConfig));
+        sslConnector.setHost(Localhost);
         server.addConnector(sslConnector);
     }
 

src/test/java/org/jsoup/parser/HtmlParserTest.java

@@ -2106,6 +2106,45 @@ static void assertErrorsDoNotContain(String msg, ParseErrorList errors) {
         assertEquals("<div /><custom /><custom>Foo</custom>", TextUtil.stripNewlines(doc.body().html()));
     }
 
+    @Test void customVoidTagsBehaveLikeHtmlVoids() {
+        Parser parser = Parser.htmlParser().setTrackErrors(10).tagSet(TagSet.Html());
+        TagSet tags = parser.tagSet();
+        tags.valueOf("voidtag", Parser.NamespaceHtml).set(Tag.Void);
+
+        String html = "<p><voidtag>Hello World</p>";
+        Document doc = Jsoup.parse(html, parser);
+        assertEquals(0, parser.getErrors().size());
+
+        doc.outputSettings().syntax(Document.OutputSettings.Syntax.html);
+        String emittedHtml = TextUtil.stripNewlines(doc.body().html());
+        assertEquals("<p><voidtag>Hello World</p>", emittedHtml);
+        assertEquals("Hello World", doc.body().text());
+
+        doc.outputSettings().syntax(Document.OutputSettings.Syntax.xml);
+        assertEquals("<p><voidtag />Hello World</p>", TextUtil.stripNewlines(doc.body().html()));
+    }
+
+    @Test void customSelfClosingVoidTagsRoundTrip() {
+        Parser parser = Parser.htmlParser().setTrackErrors(10).tagSet(TagSet.Html());
+        TagSet tags = parser.tagSet();
+        tags.valueOf("selfclosingvoidtag", Parser.NamespaceHtml).set(Tag.Void).set(Tag.SelfClose);
+
+        String html = "<p><selfclosingvoidtag />Hello World</p>";
+        Document doc = Jsoup.parse(html, parser);
+        assertEquals(0, parser.getErrors().size());
+
+        doc.outputSettings().syntax(Document.OutputSettings.Syntax.html);
+        String emittedHtml = TextUtil.stripNewlines(doc.body().html());
+        assertEquals("<p><selfclosingvoidtag>Hello World</p>", emittedHtml);
+
+        Document reparsed = Jsoup.parse(emittedHtml, parser);
+        reparsed.outputSettings().syntax(Document.OutputSettings.Syntax.html);
+        assertEquals(emittedHtml, TextUtil.stripNewlines(reparsed.body().html()));
+
+        doc.outputSettings().syntax(Document.OutputSettings.Syntax.xml);
+        assertEquals("<p><selfclosingvoidtag />Hello World</p>", TextUtil.stripNewlines(doc.body().html()));
+    }
+
     @Test void svgScriptParsedAsScriptData() {
         // https://github.com/jhy/jsoup/issues/2320
         String html = "<svg><script>a < b</script></svg>";