Fixes to Unicode support. Believe that most unicode issues are now fixed. Bug 37622 & Bug 22873 squashed.
git-svn-id: https://svn.apache.org/repos/asf/jakarta/poi/trunk@365609 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Jason Height
parent
b55089d607
commit
b57336834b
|
|
@ -457,10 +457,11 @@ public class Workbook implements Model
|
|||
* @param sheetnum the sheet number (0 based)
|
||||
* @param sheetname the name for the sheet
|
||||
*/
|
||||
|
||||
// for compatibility
|
||||
public void setSheetName(int sheetnum, String sheetname ) {
|
||||
setSheetName( sheetnum, sheetname, (byte)0 );
|
||||
checkSheets(sheetnum);
|
||||
BoundSheetRecord sheet = (BoundSheetRecord)boundsheets.get( sheetnum );
|
||||
sheet.setSheetname(sheetname);
|
||||
sheet.setSheetnameLength( (byte)sheetname.length() );
|
||||
}
|
||||
|
||||
/**
|
||||
|
|
@ -481,6 +482,14 @@ public class Workbook implements Model
|
|||
return false;
|
||||
}
|
||||
|
||||
/**
|
||||
* sets the name for a given sheet forcing the encoding. This is STILL A BAD IDEA.
|
||||
* Poi now automatically detects unicode
|
||||
*
|
||||
*@deprecated 3-Jan-06 Simply use setSheetNam e(int sheetnum, String sheetname)
|
||||
* @param sheetnum the sheet number (0 based)
|
||||
* @param sheetname the name for the sheet
|
||||
*/
|
||||
public void setSheetName(int sheetnum, String sheetname, short encoding ) {
|
||||
checkSheets(sheetnum);
|
||||
BoundSheetRecord sheet = (BoundSheetRecord)boundsheets.get( sheetnum );
|
||||
|
|
|
|||
|
|
@ -69,8 +69,8 @@ public class StringPtg
|
|||
if (value.length() >255) {
|
||||
throw new IllegalArgumentException("String literals in formulas cant be bigger than 255 characters ASCII");
|
||||
}
|
||||
this.field_2_options=0;
|
||||
this.fHighByte.setBoolean(field_2_options, false);
|
||||
this.field_2_options=0;
|
||||
field_2_options = (byte)this.fHighByte.setBoolean(field_2_options, StringUtil.hasMultibyte(value));
|
||||
this.field_3_string=value;
|
||||
this.field_1_length=value.length(); //for the moment, we support only ASCII strings in formulas we create
|
||||
}
|
||||
|
|
|
|||
|
|
@ -381,13 +381,13 @@ public class HSSFCell
|
|||
int sst = 0;
|
||||
|
||||
UnicodeString str = getRichStringCellValue().getUnicodeString();
|
||||
if (encoding == ENCODING_COMPRESSED_UNICODE)
|
||||
{
|
||||
str.setCompressedUnicode();
|
||||
} else if (encoding == ENCODING_UTF_16)
|
||||
{
|
||||
str.setUncompressedUnicode();
|
||||
}
|
||||
//jmh if (encoding == ENCODING_COMPRESSED_UNICODE)
|
||||
//jmh {
|
||||
// jmh str.setCompressedUnicode();
|
||||
// jmh } else if (encoding == ENCODING_UTF_16)
|
||||
// jmh {
|
||||
// jmh str.setUncompressedUnicode();
|
||||
// jmh }
|
||||
sst = book.addSSTString(str);
|
||||
lrec.setSSTIndex(sst);
|
||||
getRichStringCellValue().setUnicodeString(book.getSSTString(sst));
|
||||
|
|
@ -572,13 +572,13 @@ public class HSSFCell
|
|||
int index = 0;
|
||||
|
||||
UnicodeString str = value.getUnicodeString();
|
||||
if (encoding == ENCODING_COMPRESSED_UNICODE)
|
||||
{
|
||||
str.setCompressedUnicode();
|
||||
} else if (encoding == ENCODING_UTF_16)
|
||||
{
|
||||
str.setUncompressedUnicode();
|
||||
}
|
||||
// jmh if (encoding == ENCODING_COMPRESSED_UNICODE)
|
||||
// jmh {
|
||||
// jmh str.setCompressedUnicode();
|
||||
// jmh } else if (encoding == ENCODING_UTF_16)
|
||||
// jmh {
|
||||
// jmh str.setUncompressedUnicode();
|
||||
// jmh }
|
||||
index = book.addSSTString(str);
|
||||
(( LabelSSTRecord ) record).setSSTIndex(index);
|
||||
stringValue = value;
|
||||
|
|
@ -856,6 +856,8 @@ public class HSSFCell
|
|||
* @see #ENCODING_UTF_16
|
||||
*
|
||||
* @return -1, 1 or 0 for unchanged, compressed or uncompressed (used only with String type)
|
||||
*
|
||||
* @deprecated As of 3-Jan-06 POI now automatically handles Unicode without forcing the encoding.
|
||||
*/
|
||||
public short getEncoding()
|
||||
{
|
||||
|
|
@ -870,6 +872,7 @@ public class HSSFCell
|
|||
* @see #ENCODING_UTF_16
|
||||
*
|
||||
* @param encoding either ENCODING_COMPRESSED_UNICODE (0) or ENCODING_UTF_16 (1)
|
||||
* @deprecated As of 3-Jan-06 POI now automatically handles Unicode without forcing the encoding.
|
||||
*/
|
||||
|
||||
public void setEncoding(short encoding)
|
||||
|
|
|
|||
|
|
@ -339,7 +339,15 @@ public class HSSFWorkbook
|
|||
return workbook.getWindowOne().getDisplayedTab();
|
||||
}
|
||||
|
||||
/**
|
||||
* @deprecated POI will now properly handle unicode strings without
|
||||
* forceing an encoding
|
||||
*/
|
||||
public final static byte ENCODING_COMPRESSED_UNICODE = 0;
|
||||
/**
|
||||
* @deprecated POI will now properly handle unicode strings without
|
||||
* forceing an encoding
|
||||
*/
|
||||
public final static byte ENCODING_UTF_16 = 1;
|
||||
|
||||
|
||||
|
|
@ -354,9 +362,23 @@ public class HSSFWorkbook
|
|||
if (workbook.doesContainsSheetName( name, sheet ))
|
||||
throw new IllegalArgumentException( "The workbook already contains a sheet with this name" );
|
||||
|
||||
workbook.setSheetName( sheet, name, ENCODING_COMPRESSED_UNICODE );
|
||||
if (sheet > (sheets.size() - 1))
|
||||
{
|
||||
throw new RuntimeException("Sheet out of bounds");
|
||||
}
|
||||
|
||||
workbook.setSheetName( sheet, name);
|
||||
}
|
||||
|
||||
|
||||
/**
|
||||
* set the sheet name forcing the encoding. Forcing the encoding IS A BAD IDEA!!!
|
||||
* @deprecated 3-Jan-2006 POI now automatically detects unicode and sets the encoding
|
||||
* appropriately. Simply use setSheetName(int sheet, String encoding)
|
||||
* @throws IllegalArgumentException if the name is greater than 31 chars
|
||||
* or contains /\?*[]
|
||||
* @param sheet number (0 based)
|
||||
*/
|
||||
public void setSheetName( int sheet, String name, short encoding )
|
||||
{
|
||||
if (workbook.doesContainsSheetName( name, sheet ))
|
||||
|
|
|
|||
|
|
@ -49,9 +49,8 @@ public class TestBoundSheetRecord
|
|||
public void testWideRecordLength()
|
||||
throws Exception
|
||||
{
|
||||
BoundSheetRecord record = new BoundSheetRecord();
|
||||
record.setCompressedUnicodeFlag((byte)0x01);
|
||||
record.setSheetname("Sheet1");
|
||||
BoundSheetRecord record = new BoundSheetRecord();
|
||||
record.setSheetname("Sheet\u20ac");
|
||||
record.setSheetnameLength((byte)6);
|
||||
|
||||
assertEquals(" 2 + 2 + 4 + 2 + 1 + 1 + len(str) * 2", 24, record.getRecordSize());
|
||||
|
|
|
|||
|
|
@ -46,15 +46,15 @@ public class TestHSSFWorkbook extends TestCase
|
|||
|
||||
try
|
||||
{
|
||||
b.setSheetName( 3, "name1", HSSFWorkbook.ENCODING_UTF_16 );
|
||||
b.setSheetName( 3, "name1"/*JMH, HSSFWorkbook.ENCODING_UTF_16*/ );
|
||||
fail();
|
||||
}
|
||||
catch ( IllegalArgumentException pass )
|
||||
{
|
||||
}
|
||||
|
||||
b.setSheetName( 3, "name2", HSSFWorkbook.ENCODING_UTF_16 );
|
||||
b.setSheetName( 3, "name2", HSSFWorkbook.ENCODING_UTF_16 );
|
||||
b.setSheetName( 3, "name2"/*JMH, HSSFWorkbook.ENCODING_UTF_16*/ );
|
||||
b.setSheetName( 3, "name2"/*JMH, HSSFWorkbook.ENCODING_UTF_16*/ );
|
||||
b.setSheetName( 3, "name2" );
|
||||
|
||||
HSSFWorkbook c = new HSSFWorkbook( );
|
||||
|
|
|
|||
|
|
@ -0,0 +1,95 @@
|
|||
package org.apache.poi.hssf.usermodel;
|
||||
|
||||
import java.io.File;
|
||||
import java.io.FileOutputStream;
|
||||
import java.io.FileInputStream;
|
||||
|
||||
import org.apache.poi.util.TempFile;
|
||||
|
||||
import junit.framework.TestCase;
|
||||
|
||||
public class TestUnicodeWorkbook extends TestCase {
|
||||
|
||||
public TestUnicodeWorkbook(String s) {
|
||||
super(s);
|
||||
}
|
||||
|
||||
/** Tests that all of the unicode capable string fields can be set, written and then read back
|
||||
*
|
||||
*
|
||||
*/
|
||||
public void testUnicodeInAll() throws Exception {
|
||||
HSSFWorkbook wb = new HSSFWorkbook();
|
||||
//Create a unicode dataformat (contains euro symbol)
|
||||
HSSFDataFormat df = wb.createDataFormat();
|
||||
final String formatStr = "_([$\u20ac-2]\\\\\\ * #,##0.00_);_([$\u20ac-2]\\\\\\ * \\\\\\(#,##0.00\\\\\\);_([$\u20ac-2]\\\\\\ *\\\"\\-\\\\\"??_);_(@_)";
|
||||
short fmt = df.getFormat(formatStr);
|
||||
|
||||
//Create a unicode sheet name (euro symbol)
|
||||
HSSFSheet s = wb.createSheet("\u20ac");
|
||||
|
||||
//Set a unicode header (you guessed it the euro symbol)
|
||||
HSSFHeader h = s.getHeader();
|
||||
h.setCenter("\u20ac");
|
||||
h.setLeft("\u20ac");
|
||||
h.setRight("\u20ac");
|
||||
|
||||
//Set a unicode footer
|
||||
HSSFFooter f = s.getFooter();
|
||||
f.setCenter("\u20ac");
|
||||
f.setLeft("\u20ac");
|
||||
f.setRight("\u20ac");
|
||||
|
||||
HSSFRow r = s.createRow(0);
|
||||
HSSFCell c = r.createCell((short)1);
|
||||
c.setCellValue(12.34);
|
||||
c.getCellStyle().setDataFormat(fmt);
|
||||
|
||||
HSSFCell c2 = r.createCell((short)2);
|
||||
c.setCellValue(new HSSFRichTextString("\u20ac"));
|
||||
|
||||
HSSFCell c3 = r.createCell((short)3);
|
||||
String formulaString = "TEXT(12.34,\"\u20ac###,##\")";
|
||||
c3.setCellFormula(formulaString);
|
||||
|
||||
|
||||
File tempFile = TempFile.createTempFile("unicode", "test.xls");
|
||||
FileOutputStream stream = new FileOutputStream(tempFile);
|
||||
wb.write(stream);
|
||||
|
||||
wb = null;
|
||||
FileInputStream in = new FileInputStream(tempFile);
|
||||
wb = new HSSFWorkbook(in);
|
||||
|
||||
//Test the sheetname
|
||||
s = wb.getSheet("\u20ac");
|
||||
assertNotNull(s);
|
||||
|
||||
//Test the header
|
||||
h = s.getHeader();
|
||||
assertEquals(h.getCenter(), "\u20ac");
|
||||
assertEquals(h.getLeft(), "\u20ac");
|
||||
assertEquals(h.getRight(), "\u20ac");
|
||||
|
||||
//Test the footer
|
||||
f = s.getFooter();
|
||||
assertEquals(f.getCenter(), "\u20ac");
|
||||
assertEquals(f.getLeft(), "\u20ac");
|
||||
assertEquals(f.getRight(), "\u20ac");
|
||||
|
||||
//Test the dataformat
|
||||
r = s.getRow(0);
|
||||
c = r.getCell((short)1);
|
||||
df = wb.createDataFormat();
|
||||
assertEquals(formatStr, df.getFormat(c.getCellStyle().getDataFormat()));
|
||||
|
||||
//Test the cell string value
|
||||
c2 = r.getCell((short)2);
|
||||
assertEquals(c.getRichStringCellValue().getString(), "\u20ac");
|
||||
|
||||
//Test the cell formula
|
||||
c3 = r.getCell((short)3);
|
||||
assertEquals(c3.getCellFormula(), formulaString);
|
||||
}
|
||||
|
||||
}
|
||||
Loading…
Reference in New Issue