PR:18846

Obtained from:
Submitted by:	kamoshida.toshiaki@future.co.jp (Toshiaki Kamoshida)
Reviewed by:


git-svn-id: https://svn.apache.org/repos/asf/jakarta/poi/trunk@353304 13f79535-47bb-0310-9956-ffa450edef68

src/documentation/content/xdocs/dtd/changes-v11.dtd

@@ -62,7 +62,7 @@ COPYRIGHT:
 <!-- Common entities -->
 <!-- =============================================================== -->
 
-<!ENTITY % types "add|remove|update|fix">
+<!ENTITY % types "add|remove|update|fix|unknown">
 
 <!-- =============================================================== -->
 <!-- Document Type Definition -->

src/java/org/apache/poi/hssf/record/BoundSheetRecord.java

@@ -138,7 +138,7 @@ public class BoundSheetRecord
         int nameLength = LittleEndian.ubyteToInt( field_3_sheetname_length );
         if ( ( field_4_compressed_unicode_flag & 0x01 ) == 1 )
         {
-            field_5_sheetname = StringUtil.getFromUnicodeHigh( data, 8 + offset, nameLength );
+            field_5_sheetname = StringUtil.getFromUnicodeLE( data, 8 + offset, nameLength );
         }
         else
         {
@@ -300,7 +300,7 @@ public class BoundSheetRecord
         data[11 + offset] = getCompressedUnicodeFlag();
 
         if ( ( field_4_compressed_unicode_flag & 0x01 ) == 1 )
-            StringUtil.putUncompressedUnicode( getSheetname(), data, 12 + offset );
+            StringUtil.putUnicodeLE( getSheetname(), data, 12 + offset );
         else
             StringUtil.putCompressedUnicode( getSheetname(), data, 12 + offset );
 

src/java/org/apache/poi/hssf/record/FontRecord.java

@@ -169,7 +169,7 @@ public class FontRecord
             }
             else
             {   // is not compressed unicode
-                field_11_font_name = StringUtil.getFromUnicodeHigh(data, 16,
+                field_11_font_name = StringUtil.getFromUnicodeLE(data, 16,
                         field_10_font_name_len);
             }
         }
@@ -579,7 +579,7 @@ public class FontRecord
         data[ 18 + offset ] = getFontNameLength();
         data[ 19 + offset ] = ( byte ) 1;
         if (getFontName() != null) {
-           StringUtil.putUncompressedUnicode(getFontName(), data, 20 + offset);
+           StringUtil.putUnicodeLE(getFontName(), data, 20 + offset);
         }
         return getRecordSize();
     }

src/java/org/apache/poi/hssf/record/FormatRecord.java

@@ -128,7 +128,7 @@ public class FormatRecord
                                               
       if ( field_3_unicode_flag  ) {
           // unicode
-          field_4_formatstring = StringUtil.getFromUnicodeHigh( data, 5 + offset, field_3_unicode_len );
+          field_4_formatstring = StringUtil.getFromUnicodeLE( data, 5 + offset, field_3_unicode_len );
       }
       else {
           // not unicode
@@ -264,7 +264,7 @@ public class FormatRecord
 
       if ( field_3_unicode_flag ) {
           // unicode
-          StringUtil.putUncompressedUnicode( getFormatString(), data, 9 + offset );
+          StringUtil.putUnicodeLE( getFormatString(), data, 9 + offset );
       }
       else {
           // not unicode

src/java/org/apache/poi/hssf/record/LabelRecord.java

@@ -152,7 +152,7 @@ public class LabelRecord
         field_5_unicode_flag = data[ 8 + offset ];
         if (isUnCompressedUnicode())
         {
-            field_6_value = StringUtil.getFromUnicode(data, 8 + offset,
+            field_6_value = StringUtil.getFromUnicodeBE(data, 8 + offset,
                                                       field_4_string_len);
         }
         else

src/java/org/apache/poi/hssf/record/SeriesTextRecord.java

@@ -133,7 +133,7 @@ public class SeriesTextRecord
         field_1_id                     = LittleEndian.getShort(data, pos + 0x0 + offset);
         field_2_textLength             = data[ pos + 0x2 + offset ];
         field_3_undocumented           = data[ pos + 0x3 + offset ];
-        field_4_text                   = StringUtil.getFromUnicodeHigh(data, pos + 0x4 + offset, ((field_2_textLength *2)/2));
+        field_4_text                   = StringUtil.getFromUnicodeLE(data, pos + 0x4 + offset, ((field_2_textLength *2)/2));
 
     }
 
@@ -172,7 +172,7 @@ public class SeriesTextRecord
         LittleEndian.putShort(data, 4 + offset + pos, field_1_id);
         data[ 6 + offset + pos ] = field_2_textLength;
         data[ 7 + offset + pos ] = field_3_undocumented;
-        StringUtil.putUncompressedUnicodeHigh(field_4_text, data, 8 + offset + pos);
+        StringUtil.putUnicodeLE(field_4_text, data, 8 + offset + pos);
 
         return getRecordSize();
     }

src/java/org/apache/poi/hssf/record/StringRecord.java

@@ -130,7 +130,7 @@ public class StringRecord
         field_2_unicode_flag            = data[ 2 + offset ];
         if (isUnCompressedUnicode())
         {
-            field_3_string = StringUtil.getFromUnicode(data, 3 + offset, field_1_string_length );
+            field_3_string = StringUtil.getFromUnicodeBE(data, 3 + offset, field_1_string_length );
         }
         else
         {
@@ -182,7 +182,7 @@ public class StringRecord
         data[6 + offset] = field_2_unicode_flag;
         if (isUnCompressedUnicode())
         {
-            StringUtil.putUncompressedUnicode(field_3_string, data, 7 + offset);
+            StringUtil.putUnicodeLE(field_3_string, data, 7 + offset);
         }
         else
         {

src/java/org/apache/poi/hssf/record/StyleRecord.java

@@ -143,7 +143,7 @@ public class StyleRecord
             field_3_string_options = data[4+offset];
             
             if (fHighByte.isSet(field_3_string_options)) {
-                field_4_name= StringUtil.getFromUnicode(data,offset+5,field_2_name_length);
+                field_4_name= StringUtil.getFromUnicodeBE(data,offset+5,field_2_name_length);
             }else {
                 field_4_name=StringUtil.getFromCompressedUnicode(data,offset+5,field_2_name_length);
             }

src/java/org/apache/poi/hssf/record/UnicodeString.java

@@ -328,7 +328,7 @@ offset);
             }
             else
             {
-                StringUtil.putUncompressedUnicode(unicodeString, data,
+                StringUtil.putUnicodeLE(unicodeString, data,
                                                     0x3 + offset);
             }
         }
@@ -340,7 +340,7 @@ offset);
             }
             else
             {
-                StringUtil.putUncompressedUnicode(getString(), data,
+                StringUtil.putUnicodeLE(getString(), data,
                                                   0x3 + offset);
             }
         }

src/java/org/apache/poi/hssf/record/formula/StringPtg.java

@@ -89,7 +89,7 @@ public class StringPtg
         field_1_length = data[offset];
         field_2_options = data[offset+1];
         if (fHighByte.isSet(field_2_options)) {
-            field_3_string= StringUtil.getFromUnicode(data,offset+2,field_1_length);
+            field_3_string= StringUtil.getFromUnicodeBE(data,offset+2,field_1_length);
         }else {
             field_3_string=StringUtil.getFromCompressedUnicode(data,offset+2,field_1_length);
         }
@@ -130,7 +130,7 @@ public class StringPtg
         array[ offset + 1 ] = field_1_length;
         array[ offset + 2 ] = field_2_options;
         if (fHighByte.isSet(field_2_options)) {
-            StringUtil.putUncompressedUnicode(getValue(),array,offset+3);
+            StringUtil.putUnicodeLE(getValue(),array,offset+3);
         }else {
             StringUtil.putCompressedUnicode(getValue(),array,offset+3);
         }

src/java/org/apache/poi/util/StringUtil.java

@@ -2,7 +2,7 @@
  * ====================================================================
  * The Apache Software License, Version 1.1
  *
- *  Copyright (c) 2002 The Apache Software Foundation.  All rights
+ * Copyright (c) 2003 The Apache Software Foundation.  All rights
  * reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -55,38 +55,32 @@
 package org.apache.poi.util;
 
 import java.io.UnsupportedEncodingException;
-
 import java.text.NumberFormat;
 import java.text.FieldPosition;
-
+import java.util.Arrays;
 /** 
  *  Title: String Utility Description: Collection of string handling utilities 
  *  
- * Now it is quite confusing: the method pairs, in which
- * one of them write data and other read written data are:
- * putUncompressedUnicodeHigh and getFromUnicode
- * putUncompressedUnicode     and getFromUnicodeHigh
  * 
  *@author     Andrew C. Oliver 
  *@author     Sergei Kozello (sergeikozello at mail.ru) 
+ *@author     Toshiaki Kamoshida (kamoshida.toshiaki at future dot co dot jp) 
  *@created    May 10, 2002 
  *@version    1.0 
  */
-
 public class StringUtil {
-    
 	private final static String ENCODING = "ISO-8859-1";
 	/**     
 	 *  Constructor for the StringUtil object     
 	 */
-    private StringUtil() { }
+	private StringUtil() {
-
+	}
 
 	/**     
 	 *  given a byte array of 16-bit unicode characters, compress to 8-bit and     
 	 *  return a string     
 	 *     
-     * { 0x16, 0x00 } -> 0x16
+	 * { 0x16, 0x00 } -0x16     
 	 *      
 	 *@param  string                              the byte array to be converted     
 	 *@param  offset                              the initial offset into the     
@@ -102,11 +96,11 @@ public class StringUtil {
 	 *      length)     
 	 *@len                                        the length of the final string     
 	 */
-
+	public static String getFromUnicodeLE(
-    public static String getFromUnicodeHigh(final byte[] string,
+		final byte[] string,
-            final int offset, final int len)
+		final int offset,
+		final int len)
 		throws ArrayIndexOutOfBoundsException, IllegalArgumentException {
-
 		if ((offset < 0) || (offset >= string.length)) {
 			throw new ArrayIndexOutOfBoundsException("Illegal offset");
 		}
@@ -114,39 +108,34 @@ public class StringUtil {
 			throw new IllegalArgumentException("Illegal length");
 		}
 
-        char[] chars = new char[ len ];
+		try {
-        for ( int i = 0; i < chars.length; i++ ) {
+			return new String(string, offset, len * 2, "UTF-16LE");
-            chars[i] = (char)( string[ offset + ( 2*i ) ] & 0xFF | 
+		} catch (UnsupportedEncodingException e) {
-                             ( string[ offset + ( 2*i+1 ) ] << 8 ) );
+			throw new InternalError(); /*unreachable*/
 		}
-
-        return new String( chars );
 	}
 
-    
 	/**     
 	 *  given a byte array of 16-bit unicode characters, compress to 8-bit and     
 	 *  return a string     
 	 *      
-     * { 0x16, 0x00 } -> 0x16
+	 * { 0x16, 0x00 } -0x16     
 	 *     
 	 *@param  string  the byte array to be converted     
 	 *@return         the converted string    
 	 */
-
+	public static String getFromUnicodeLE(final byte[] string) {
-    public static String getFromUnicodeHigh( final byte[] string ) {
+		return getFromUnicodeLE(string, 0, string.length / 2);
-        return getFromUnicodeHigh( string, 0, string.length / 2 );
 	}
 
-
 	/**     
 	 *  given a byte array of 16-bit unicode characters, compress to 8-bit and     
 	 *  return a string     
 	 *      
-     * { 0x00, 0x16 } -> 0x16
+	 * { 0x00, 0x16 } -0x16     
 	 *     
 	 *@param  string                              the byte array to be converted     
-     *@param  offset                              the initial offset into the
+	 **@param  offset                              the initial offset into the     
 	 *      byte array. it is assumed that string[ offset ] and string[ offset +     
 	 *      1 ] contain the first 16-bit unicode character     
 	 *@param  len     
@@ -159,9 +148,10 @@ public class StringUtil {
 	 *      length)     
 	 *@len                                        the length of the final string     
 	 */
-
+	public static String getFromUnicodeBE(
-    public static String getFromUnicode(final byte[] string,
+		final byte[] string,
-            final int offset, final int len)
+		final int offset,
+		final int len)
 		throws ArrayIndexOutOfBoundsException, IllegalArgumentException {
 		if ((offset < 0) || (offset >= string.length)) {
 			throw new ArrayIndexOutOfBoundsException("Illegal offset");
@@ -169,49 +159,41 @@ public class StringUtil {
 		if ((len < 0) || (((string.length - offset) / 2) < len)) {
 			throw new IllegalArgumentException("Illegal length");
 		}
-
+		try {
-        
+			return new String(string, offset, len * 2, "UTF-16BE");
-        char[] chars = new char[ len ];
+		} catch (UnsupportedEncodingException e) {
-        for ( int i = 0; i < chars.length; i++ ) {
+			throw new InternalError(); /*unreachable*/
-            chars[i] = (char)( ( string[ offset + ( 2*i ) ] << 8 ) +
-                              string[ offset + ( 2*i+1 ) ] );
 		}
-        
-        return new String( chars );
 	}
 
-
 	/**     
 	 *  given a byte array of 16-bit unicode characters, compress to 8-bit and     
 	 *  return a string     
 	 *      
-     * { 0x00, 0x16 } -> 0x16
+	 * { 0x00, 0x16 } -0x16     
 	 *     
 	 *@param  string  the byte array to be converted     
 	 *@return         the converted string     
 	 */
-
+	public static String getFromUnicodeBE(final byte[] string) {
-    public static String getFromUnicode(final byte[] string) {
+		return getFromUnicodeBE(string, 0, string.length / 2);
-        return getFromUnicode(string, 0, string.length / 2);
 	}
 
-
 	/**      
 	 * read compressed unicode(8bit)      
 	 *       
-      * @author Toshiaki Kamoshida(kamoshida.toshiaki at future dot co dot jp)
-      * 
 	 * @param string byte array to read      
 	 * @param offset offset to read byte array      
 	 * @param len    length to read byte array      
 	 * @return String generated String instance by reading byte array      
 	 */
-     public static String getFromCompressedUnicode(final byte[] string,
+	public static String getFromCompressedUnicode(
-            final int offset, final int len){
+		final byte[] string,
+		final int offset,
+		final int len) {
 		try {
 			return new String(string, offset, len, "ISO-8859-1");
-         }
+		} catch (UnsupportedEncodingException e) {
-         catch(UnsupportedEncodingException e){
 			throw new InternalError(); /* unreachable */
 		}
 	}
@@ -224,36 +206,15 @@ public class StringUtil {
 	 *@param  offset  an offset into the byte arrat at which the data is start     
 	 *      when written     
 	 */
-
+	public static void putCompressedUnicode(
-    public static void putCompressedUnicode(final String input,
+		final String input,
 		final byte[] output,
 		final int offset) {
-        int strlen = input.length();
+		try {
-
+			byte[] bytes = input.getBytes("ISO-8859-1");
-        for (int k = 0; k < strlen; k++) {
+			System.arraycopy(bytes, 0, output, offset, bytes.length);
-            output[offset + k] = (byte) input.charAt(k);
+		} catch (UnsupportedEncodingException e) {
-        }
+			throw new InternalError(); /*unreachable*/
-    }
-
-
-    /**
-     *  Write uncompressed unicode
-     *
-     *@param  input   the String containing the unicode data to be written
-     *@param  output  the byte array to hold the uncompressed unicode
-     *@param  offset  the offset to start writing into the byte array
-     */
-
-    public static void putUncompressedUnicode(final String input,
-            final byte[] output,
-            final int offset) {
-        int strlen = input.length();
-
-        for (int k = 0; k < strlen; k++) {
-            char c = input.charAt(k);
-
-            output[offset + (2 * k)] = (byte) c;
-            output[offset + (2 * k) + 1] = (byte) (c >> 8);
 		}
 	}
 
@@ -264,22 +225,36 @@ public class StringUtil {
 	 *@param  output  the byte array to hold the uncompressed unicode     
 	 *@param  offset  the offset to start writing into the byte array     
 	 */
-
+	public static void putUnicodeLE(
-    public static void putUncompressedUnicodeHigh(final String input,
+		final String input,
 		final byte[] output,
 		final int offset) {
-        int strlen = input.length();
+		try {
-
+			byte[] bytes = input.getBytes("UTF-16LE");
-        for (int k = 0; k < strlen; k++) {
+			System.arraycopy(bytes, 0, output, offset, bytes.length);
-            char c = input.charAt(k);
+		} catch (UnsupportedEncodingException e) {
-
+			throw new InternalError(); /*unreachable*/
-            output[offset + (2 * k)] = (byte) (c >> 8);
-            output[offset + (2 * k)] = (byte) c;
 		}
 	}
 
-    
+	/**     
-    
+	 *  Write uncompressed unicode     
+	 *     
+	 *@param  input   the String containing the unicode data to be written     
+	 *@param  output  the byte array to hold the uncompressed unicode     
+	 *@param  offset  the offset to start writing into the byte array     
+	 */
+	public static void putUnicodeBE(
+		final String input,
+		final byte[] output,
+		final int offset) {
+		try {
+			byte[] bytes = input.getBytes("UTF-16BE");
+			System.arraycopy(bytes, 0, output, offset, bytes.length);
+		} catch (UnsupportedEncodingException e) {
+			throw new InternalError(); /*unreachable*/
+		}
+	}
 
 	/**     
 	 *  Description of the Method     
@@ -291,21 +266,25 @@ public class StringUtil {
 	public static String format(String message, Object[] params) {
 		int currentParamNumber = 0;
 		StringBuffer formattedMessage = new StringBuffer();
-
 		for (int i = 0; i < message.length(); i++) {
 			if (message.charAt(i) == '%') {
 				if (currentParamNumber >= params.length) {
 					formattedMessage.append("?missing data?");
-                } else if ((params[currentParamNumber] instanceof Number)
+				} else if (
+					(params[currentParamNumber] instanceof Number)
 						&& (i + 1 < message.length())) {
-                    i += matchOptionalFormatting(
+					i
+						+= matchOptionalFormatting(
 							(Number) params[currentParamNumber++],
-                            message.substring(i + 1), formattedMessage);
+							message.substring(i + 1),
+							formattedMessage);
 				} else {
-                    formattedMessage.append(params[currentParamNumber++].toString());
+					formattedMessage.append(
+						params[currentParamNumber++].toString());
 				}
 			} else {
-                if ((message.charAt(i) == '\\') && (i + 1 < message.length())
+				if ((message.charAt(i) == '\\')
+					&& (i + 1 < message.length())
 					&& (message.charAt(i + 1) == '%')) {
 					formattedMessage.append('%');
 					i++;
@@ -317,7 +296,6 @@ public class StringUtil {
 		return formattedMessage.toString();
 	}
 
-
 	/**     
 	 *  Description of the Method     
 	 *     
@@ -326,26 +304,31 @@ public class StringUtil {
 	 *@param  outputTo    Description of the Parameter     
 	 *@return             Description of the Return Value     
 	 */
-    private static int matchOptionalFormatting(Number number,
+	private static int matchOptionalFormatting(
+		Number number,
 		String formatting,
 		StringBuffer outputTo) {
 		NumberFormat numberFormat = NumberFormat.getInstance();
-
 		if ((0 < formatting.length())
 			&& Character.isDigit(formatting.charAt(0))) {
-            numberFormat.setMinimumIntegerDigits(Integer.parseInt(formatting.charAt(0) + ""));
+			numberFormat.setMinimumIntegerDigits(
-            if ((2 < formatting.length()) && (formatting.charAt(1) == '.')
+				Integer.parseInt(formatting.charAt(0) + ""));
+			if ((2 < formatting.length())
+				&& (formatting.charAt(1) == '.')
 				&& Character.isDigit(formatting.charAt(2))) {
-                numberFormat.setMaximumFractionDigits(Integer.parseInt(formatting.charAt(2) + ""));
+				numberFormat.setMaximumFractionDigits(
+					Integer.parseInt(formatting.charAt(2) + ""));
 				numberFormat.format(number, outputTo, new FieldPosition(0));
 				return 3;
 			}
 			numberFormat.format(number, outputTo, new FieldPosition(0));
 			return 1;
-        } else if ((0 < formatting.length()) && (formatting.charAt(0) == '.')) {
+		} else if (
+			(0 < formatting.length()) && (formatting.charAt(0) == '.')) {
 			if ((1 < formatting.length())
 				&& Character.isDigit(formatting.charAt(1))) {
-                numberFormat.setMaximumFractionDigits(Integer.parseInt(formatting.charAt(1) + ""));
+				numberFormat.setMaximumFractionDigits(
+					Integer.parseInt(formatting.charAt(1) + ""));
 				numberFormat.format(number, outputTo, new FieldPosition(0));
 				return 2;
 			}

src/testcases/org/apache/poi/util/TestStringUtil.java

@@ -92,7 +92,7 @@ public class TestStringUtil
         }
 
         assertEquals( "abcdefghijklmnop",
-                StringUtil.getFromUnicode( test_data ) );
+                StringUtil.getFromUnicodeBE( test_data ) );
     }
 
     /**
@@ -112,7 +112,7 @@ public class TestStringUtil
         };
 
         assertEquals( "\u0422\u0435\u0441\u0442 test",
-                StringUtil.getFromUnicode( test_data ) );
+                StringUtil.getFromUnicodeBE( test_data ) );
     }
 
     /**
@@ -133,7 +133,7 @@ public class TestStringUtil
 
 
         assertEquals( "\u0422\u0435\u0441\u0442 test",
-                StringUtil.getFromUnicodeHigh( test_data ) );
+                StringUtil.getFromUnicodeLE( test_data ) );
     }
 
     /**
@@ -149,12 +149,12 @@ public class TestStringUtil
             test_data[index++] = (byte) ( 'a' + k );
         }
         assertEquals( "abcdefghijklmno",
-                StringUtil.getFromUnicode( test_data, 0, 15 ) );
+                StringUtil.getFromUnicodeBE( test_data, 0, 15 ) );
         assertEquals( "bcdefghijklmnop",
-                StringUtil.getFromUnicode( test_data, 2, 15 ) );
+                StringUtil.getFromUnicodeBE( test_data, 2, 15 ) );
         try
         {
-            StringUtil.getFromUnicode( test_data, -1, 16 );
+            StringUtil.getFromUnicodeBE( test_data, -1, 16 );
             fail( "Should have caught ArrayIndexOutOfBoundsException" );
         }
         catch ( ArrayIndexOutOfBoundsException ignored )
@@ -164,7 +164,7 @@ public class TestStringUtil
 
         try
         {
-            StringUtil.getFromUnicode( test_data, 32, 16 );
+            StringUtil.getFromUnicodeBE( test_data, 32, 16 );
             fail( "Should have caught ArrayIndexOutOfBoundsException" );
         }
         catch ( ArrayIndexOutOfBoundsException ignored )
@@ -174,7 +174,7 @@ public class TestStringUtil
 
         try
         {
-            StringUtil.getFromUnicode( test_data, 1, 16 );
+            StringUtil.getFromUnicodeBE( test_data, 1, 16 );
             fail( "Should have caught IllegalArgumentException" );
         }
         catch ( IllegalArgumentException ignored )
@@ -184,7 +184,7 @@ public class TestStringUtil
 
         try
         {
-            StringUtil.getFromUnicode( test_data, 1, -1 );
+            StringUtil.getFromUnicodeBE( test_data, 1, -1 );
             fail( "Should have caught IllegalArgumentException" );
         }
         catch ( IllegalArgumentException ignored )
@@ -248,13 +248,13 @@ public class TestStringUtil
                     (byte) 'd', (byte) 0
                 };
 
-        StringUtil.putUncompressedUnicode( input, output, 0 );
+        StringUtil.putUnicodeLE( input, output, 0 );
         for ( int j = 0; j < expected_output.length; j++ )
         {
             assertEquals( "testing offset " + j, expected_output[j],
                     output[j] );
         }
-        StringUtil.putUncompressedUnicode( input, output,
+        StringUtil.putUnicodeLE( input, output,
                 100 - expected_output.length );
         for ( int j = 0; j < expected_output.length; j++ )
         {
@@ -263,7 +263,7 @@ public class TestStringUtil
         }
         try
         {
-            StringUtil.putUncompressedUnicode( input, output,
+            StringUtil.putUnicodeLE( input, output,
                     101 - expected_output.length );
             fail( "Should have caught ArrayIndexOutOfBoundsException" );
         }