template is a special tag

Also updated isSpecial to current spec Fixes #2258
jhy · Jan 14, 2025 · 72fb596 · 72fb596
1 parent a62c7f3
commit 72fb596
Show file tree

Hide file tree

Showing 4 changed files with 52 additions and 12 deletions.
diff --git a/CHANGES.md b/CHANGES.md
@@ -46,6 +46,7 @@
   exceeded. [2250](https://github.com/jhy/jsoup/pull/2250)
 * For backwards compatibility, allow `null` InputStream inputs to `Jsoup.parse(InputStream stream, ...)`, by returning
   an empty `Document`. [2252](https://github.com/jhy/jsoup/issues/2252)
+* A `template` tag containing an `li` within an open `li` would be parsed incorrectly, as it was not recognized as a "special" tag (which have additional processing rules). Also, added the SVG and MathML namespace tags to the list of special tags.
 
 ## 1.18.3 (2024-Dec-02)
 

diff --git a/src/main/java/org/jsoup/parser/HtmlTreeBuilder.java b/src/main/java/org/jsoup/parser/HtmlTreeBuilder.java
@@ -35,14 +35,15 @@ public class HtmlTreeBuilder extends TreeBuilder {
     static final String[] TagSearchSelectScope = new String[]{"optgroup", "option"};
     static final String[] TagSearchEndTags = new String[]{"dd", "dt", "li", "optgroup", "option", "p", "rb", "rp", "rt", "rtc"};
     static final String[] TagThoroughSearchEndTags = new String[]{"caption", "colgroup", "dd", "dt", "li", "optgroup", "option", "p", "rb", "rp", "rt", "rtc", "tbody", "td", "tfoot", "th", "thead", "tr"};
-    static final String[] TagSearchSpecial = new String[]{"address", "applet", "area", "article", "aside", "base", "basefont", "bgsound",
-        "blockquote", "body", "br", "button", "caption", "center", "col", "colgroup", "command", "dd",
-        "details", "dir", "div", "dl", "dt", "embed", "fieldset", "figcaption", "figure", "footer", "form",
-        "frame", "frameset", "h1", "h2", "h3", "h4", "h5", "h6", "head", "header", "hgroup", "hr", "html",
-        "iframe", "img", "input", "isindex", "li", "link", "listing", "marquee", "menu", "meta", "nav",
-        "noembed", "noframes", "noscript", "object", "ol", "p", "param", "plaintext", "pre", "script",
-        "section", "select", "style", "summary", "table", "tbody", "td", "textarea", "tfoot", "th", "thead",
-        "title", "tr", "ul", "wbr", "xmp"};
+    static final String[] TagSearchSpecial = new String[]{
+        "address", "applet", "area", "article", "aside", "base", "basefont", "bgsound", "blockquote", "body", "br",
+        "button", "caption", "center", "col", "colgroup", "dd", "details", "dir", "div", "dl", "dt", "embed",
+        "fieldset", "figcaption", "figure", "footer", "form", "frame", "frameset", "h1", "h2", "h3", "h4", "h5", "h6",
+        "head", "header", "hgroup", "hr", "html", "iframe", "img", "input", "keygen", "li", "link", "listing", "main",
+        "marquee", "menu", "meta", "nav", "noembed", "noframes", "noscript", "object", "ol", "p", "param", "plaintext",
+        "pre", "script", "search", "section", "select", "source", "style", "summary", "table", "tbody", "td",
+        "template", "textarea", "tfoot", "th", "thead", "title", "tr", "track", "ul", "wbr", "xmp"};
+    static String[] TagSearchSpecialMath = {"annotation-xml", "mi", "mn", "mo", "ms", "mtext"}; // differs to MathML text integration point; adds annotation-xml
     static final String[] TagMathMlTextIntegration = new String[]{"mi", "mn", "mo", "ms", "mtext"};
     static final String[] TagSvgHtmlIntegration = new String[]{"desc", "foreignObject", "title"};
 
@@ -818,10 +819,18 @@ void closeElement(String name) {
     }
 
     static boolean isSpecial(Element el) {
-        // todo: mathml's mi, mo, mn
-        // todo: svg's foreigObject, desc, title
+        String namespace = el.tag().namespace();
         String name = el.normalName();
-        return inSorted(name, TagSearchSpecial);
+        switch (namespace) {
+            case NamespaceHtml:
+                return inSorted(name, TagSearchSpecial);
+            case Parser.NamespaceMathml:
+                return inSorted(name, TagSearchSpecialMath);
+            case Parser.NamespaceSvg:
+                return inSorted(name, TagSvgHtmlIntegration);
+            default:
+                return false;
+        }
     }
 
     Element lastFormattingElement() {

diff --git a/src/test/java/org/jsoup/parser/HtmlParserTest.java b/src/test/java/org/jsoup/parser/HtmlParserTest.java
@@ -1656,6 +1656,14 @@ private boolean didAddElements(String input) {
             TextUtil.stripNewlines(doc.head().html()));
     }
 
+    @Test void templateInLi() {
+        // https://github.com/jhy/jsoup/issues/2258
+        String html = "<ul><li>L1</li><li>L2 <template><li>T1</li><li>T2</template></li><li>L3</ul>";
+        Document doc = Jsoup.parse(html);
+        assertEquals("<ul><li>L1</li><li>L2 <template><li>T1</li><li>T2</li></template></li><li>L3</li></ul>",
+            TextUtil.stripNewlines(doc.body().html()));
+    }
+
     @Test void errorsBeforeHtml() {
         Parser parser = Parser.htmlParser();
         parser.setTrackErrors(10);

diff --git a/src/test/java/org/jsoup/parser/HtmlTreeBuilderTest.java b/src/test/java/org/jsoup/parser/HtmlTreeBuilderTest.java
@@ -1,21 +1,23 @@
 package org.jsoup.parser;
 
 
+import org.jsoup.nodes.Element;
 import org.jspecify.annotations.NullMarked;
 import org.junit.jupiter.api.Test;
 import java.io.Reader;
 import java.lang.annotation.Annotation;
 import java.lang.reflect.Method;
 import java.util.List;
 
+import static org.jsoup.parser.Parser.NamespaceHtml;
 import static org.junit.jupiter.api.Assertions.*;
 
 public class HtmlTreeBuilderTest {
     @Test
     public void ensureSearchArraysAreSorted() {
         List<Object[]> constants = HtmlTreeBuilderStateTest.findConstantArrays(HtmlTreeBuilder.class);
         HtmlTreeBuilderStateTest.ensureSorted(constants);
-        assertEquals(10, constants.size());
+        assertEquals(11, constants.size());
     }
 
     @Test
@@ -37,6 +39,26 @@ public void nonnull() {
 
         // would need to rework this if/when that annotation moves from the method to the class / package.
         assertTrue(seen);
+    }
+
+    @Test void isSpecial() {
+        ParseSettings settings = ParseSettings.htmlDefault;
+        Element htmlEl = new Element(Tag.valueOf("div", NamespaceHtml, settings), "");
+        assertTrue(HtmlTreeBuilder.isSpecial(htmlEl));
+
+        Element notHtml = new Element(Tag.valueOf("not-html", NamespaceHtml, settings), "");
+        assertFalse(HtmlTreeBuilder.isSpecial(notHtml));
+
+        Element mathEl = new Element(Tag.valueOf("mi", Parser.NamespaceMathml, settings), "");
+        assertTrue(HtmlTreeBuilder.isSpecial(mathEl));
+
+        Element notMathEl = new Element(Tag.valueOf("not-math", Parser.NamespaceMathml, settings), "");
+        assertFalse(HtmlTreeBuilder.isSpecial(notMathEl));
+
+        Element svgEl = new Element(Tag.valueOf("title", Parser.NamespaceSvg, settings), "");
+        assertTrue(HtmlTreeBuilder.isSpecial(svgEl));
 
+        Element notSvgEl = new Element(Tag.valueOf("not-svg", Parser.NamespaceSvg, settings), "");
+        assertFalse(HtmlTreeBuilder.isSpecial(notSvgEl));
     }
 }