Short-circuit tag scans for custom tags

Author: jhy

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

@@ -632,7 +632,9 @@ private boolean inBodyStartTag(Token t, HtmlTreeBuilder tb) {
                     break;
                 default:
                     // todo - bring scan groups in if desired
-                    if (inSorted(name, Constants.InBodyStartEmptyFormatters)) {
+                    if (!Tag.isKnownTag(name)) { // no special rules for custom tags
+                        tb.insert(startTag);
+                    } else if (inSorted(name, Constants.InBodyStartEmptyFormatters)) {
                         tb.reconstructFormattingElements();
                         tb.insertEmpty(startTag);
                         tb.framesetOk(false);
@@ -658,8 +660,7 @@ private boolean inBodyStartTag(Token t, HtmlTreeBuilder tb) {
                         tb.error(this);
                         return false;
                     } else {
-                        if (Tag.isKnownTag(name)) // don't reconstruct for custom elements
-                            tb.reconstructFormattingElements();
+                        tb.reconstructFormattingElements();
                         tb.insert(startTag);
                     }
             }

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

@@ -237,15 +237,16 @@ protected Tag clone() {
             "ul", "ol", "pre", "div", "blockquote", "hr", "address", "figure", "figcaption", "form", "fieldset", "ins",
             "del", "dl", "dt", "dd", "li", "table", "caption", "thead", "tfoot", "tbody", "colgroup", "col", "tr", "th",
             "td", "video", "audio", "canvas", "details", "menu", "plaintext", "template", "article", "main",
-            "svg", "math", "center", "template"
+            "svg", "math", "center", "template",
+            "dir", "applet", "marquee", "listing" // deprecated but still known / special handling
     };
     private static final String[] inlineTags = {
             "object", "base", "font", "tt", "i", "b", "u", "big", "small", "em", "strong", "dfn", "code", "samp", "kbd",
             "var", "cite", "abbr", "time", "acronym", "mark", "ruby", "rt", "rp", "a", "img", "br", "wbr", "map", "q",
             "sub", "sup", "bdo", "iframe", "embed", "span", "input", "select", "textarea", "label", "button", "optgroup",
             "option", "legend", "datalist", "keygen", "output", "progress", "meter", "area", "param", "source", "track",
             "summary", "command", "device", "area", "basefont", "bgsound", "menuitem", "param", "source", "track",
-            "data", "bdi", "s"
+            "data", "bdi", "s", "strike", "nobr"
     };
     private static final String[] emptyTags = {
             "meta", "link", "base", "frame", "img", "br", "wbr", "embed", "hr", "input", "keygen", "col", "command",

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

@@ -1,6 +1,7 @@
 package org.jsoup.parser;
 
 import org.jsoup.Jsoup;
+import org.jsoup.internal.StringUtil;
 import org.jsoup.parser.HtmlTreeBuilderState.Constants;
 import org.junit.jupiter.api.Test;
 
@@ -10,8 +11,8 @@
 import java.util.Arrays;
 import java.util.List;
 
-import static org.junit.jupiter.api.Assertions.assertArrayEquals;
-import static org.junit.jupiter.api.Assertions.assertEquals;
+import static org.jsoup.parser.HtmlTreeBuilderState.Constants.InBodyStartInputAttribs;
+import static org.junit.jupiter.api.Assertions.*;
 
 public class HtmlTreeBuilderStateTest {
     static List<Object[]> findConstantArrays(Class aClass) {
@@ -47,6 +48,18 @@ public void ensureArraysAreSorted() {
         assertEquals(40, constants.size());
     }
 
+    @Test public void ensureTagSearchesAreKnownTags() {
+        List<Object[]> constants = findConstantArrays(Constants.class);
+        for (Object[] constant : constants) {
+            String[] tagNames = (String[]) constant;
+            for (String tagName : tagNames) {
+                if (StringUtil.inSorted(tagName, InBodyStartInputAttribs))
+                    continue; // odd one out in the constant
+                assertTrue(Tag.isKnownTag(tagName), String.format("Unknown tag name: %s", tagName));
+            }
+        }
+    }
+
 
     @Test
     public void nestedAnchorElements01() {