From 2b0774489afbf24f55859cfb95b40dcea1511909 Mon Sep 17 00:00:00 2001
From: "Hugh.C" <hugh.c@fanruan.com>
Date: Fri, 15 May 2020 13:48:37 +0800
Subject: [PATCH] =?UTF-8?q?REPORT-31492=20word=E5=AF=BC=E5=87=BA=E4=B8=ADH?=
 =?UTF-8?q?tml=E6=97=A0=E6=B3=95=E8=A7=A3=E6=9E=90=E5=B0=8F=E4=BA=8E?=
 =?UTF-8?q?=E5=8F=B7?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 .../text/html/simpleparser/HTMLWorker.java    |  9 ++++--
 .../xml/simpleparser/SimpleXMLParser.java     | 29 +++++++++++++++----
 2 files changed, 30 insertions(+), 8 deletions(-)

diff --git a/fine-itext-old/src/com/fr/third/com/lowagie/text/html/simpleparser/HTMLWorker.java b/fine-itext-old/src/com/fr/third/com/lowagie/text/html/simpleparser/HTMLWorker.java
index f1ea48571..adb73e007 100644
--- a/fine-itext-old/src/com/fr/third/com/lowagie/text/html/simpleparser/HTMLWorker.java
+++ b/fine-itext-old/src/com/fr/third/com/lowagie/text/html/simpleparser/HTMLWorker.java
@@ -775,11 +775,14 @@ public class HTMLWorker implements SimpleXMLDocHandler, DocListener {
 			+ " h1 h2 h3 h4 h5 h6 img hr";
 
 	public static final HashMap tagsSupported = new HashMap();
+	public static final HashMap tagsPrefixSupported = new HashMap();
 
 	static {
 		StringTokenizer tok = new StringTokenizer(tagsSupportedString);
-		while (tok.hasMoreTokens())
-			tagsSupported.put(tok.nextToken(), null);
+		while (tok.hasMoreTokens()) {
+			String s = tok.nextToken();
+			tagsSupported.put(s, null);
+			tagsPrefixSupported.put(s.charAt(0), null);
+		}
 	}
-
 }
diff --git a/fine-itext-old/src/com/fr/third/com/lowagie/text/xml/simpleparser/SimpleXMLParser.java b/fine-itext-old/src/com/fr/third/com/lowagie/text/xml/simpleparser/SimpleXMLParser.java
index fe9c80e03..0d7209ece 100755
--- a/fine-itext-old/src/com/fr/third/com/lowagie/text/xml/simpleparser/SimpleXMLParser.java
+++ b/fine-itext-old/src/com/fr/third/com/lowagie/text/xml/simpleparser/SimpleXMLParser.java
@@ -75,6 +75,7 @@
  */
 package com.fr.third.com.lowagie.text.xml.simpleparser;
 
+import com.fr.third.com.lowagie.text.html.simpleparser.HTMLWorker;
 import java.io.BufferedReader;
 import java.io.ByteArrayOutputStream;
 import java.io.IOException;
@@ -230,16 +231,13 @@ public final class SimpleXMLParser {
             // we are in an unknown state before there's actual content
 			case UNKNOWN:
                 if(character == '<') {
-                    saveState(TEXT);
-                    state = TAG_ENCOUNTERED;
+                    beginnOfTag((char) reader.read(), UNKNOWN);
                 }
                 break;
             // we can encounter any content
 			case TEXT:
                 if(character == '<') {
-                    flush();
-                    saveState(state);
-                    state = TAG_ENCOUNTERED;
+                    beginnOfTag((char) reader.read(), UNKNOWN);
                 } else if(character == '&') {
                     saveState(state);
                     entity.setLength(0);
@@ -499,6 +497,27 @@ public final class SimpleXMLParser {
     private void saveState(int s) {
     	stack.push(new Integer(s));
     }
+
+    /**
+     * 处理标签的开头，若不在支持标签范围内，将<符号作为文本处理，例：<1111 (仿造浏览器的处理方式)
+     */
+    public void beginnOfTag(char c, int type) {
+        previousCharacter = c;
+        if (c == -1) {
+            return;
+        }
+        if (c == '/' || HTMLWorker.tagsPrefixSupported.containsKey(c)) {
+            if (type == TEXT) {
+                flush();
+            }
+            saveState(TEXT);
+            state = TAG_ENCOUNTERED;
+            return;
+        }
+        text.append((char) character);
+        nowhite = true;
+    }
+
     /**
      * Flushes the text that is currently in the buffer.
      * The text can be ignored, added to the document