Merge branch 'release/10.0' of https://code.fineres.com/scm/~hugh.c/base-third into release/10.0

fine-itext-old/src/main/java/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);
+		}
 	}
-
 }

fine-itext-old/src/main/java/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;
@@ -117,7 +118,7 @@ public final class SimpleXMLParser {
 	private final static int ATTRIBUTE_KEY = 12;
 	private final static int ATTRIBUTE_EQUAL = 13;
 	private final static int ATTRIBUTE_VALUE = 14;
-    
+ 
 	/** the state stack */
 	Stack stack;
 	/** The current character. */
@@ -161,7 +162,7 @@ public final class SimpleXMLParser {
 	String attributekey = null;
 	/** the attribute value. */
 	String attributevalue = null;
-    
+ 
 	/**
 	 * Creates a Simple XML parser object.
 	 * Call go(BufferedReader) immediately after creation.
@@ -207,7 +208,7 @@ public final class SimpleXMLParser {
 				}
 				return;
 			}
-            
+   
 			// dealing with  \n and \r
 			if (character == '\n' && eol) {
 				eol = false;
@@ -225,21 +226,18 @@ public final class SimpleXMLParser {
 			} else {
 				columns++;
 			}
-            
+   
 			switch(state) {
             // 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(), TEXT);
                 } 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