org.apache.poi.hssf.record.common.UnicodeString Maven / Gradle / Ivy
Go to download
Show more of this group Show more artifacts with this name
Show all versions of poi Show documentation
Show all versions of poi Show documentation
Apache POI - Java API To Access Microsoft Format Files
/* ====================================================================
Licensed to the Apache Software Foundation (ASF) under one or more
contributor license agreements. See the NOTICE file distributed with
this work for additional information regarding copyright ownership.
The ASF licenses this file to You under the Apache License, Version 2.0
(the "License"); you may not use this file except in compliance with
the License. You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
==================================================================== */
package org.apache.poi.hssf.record.common;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.Collections;
import java.util.Iterator;
import java.util.List;
import org.apache.poi.hssf.record.RecordInputStream;
import org.apache.poi.hssf.record.cont.ContinuableRecordInput;
import org.apache.poi.hssf.record.cont.ContinuableRecordOutput;
import org.apache.poi.util.BitField;
import org.apache.poi.util.BitFieldFactory;
import org.apache.poi.util.LittleEndianInput;
import org.apache.poi.util.LittleEndianOutput;
import org.apache.poi.util.POILogFactory;
import org.apache.poi.util.POILogger;
import org.apache.poi.util.StringUtil;
/**
* Title: Unicode String
* Description: Unicode String - just standard fields that are in several records.
* It is considered more desirable then repeating it in all of them.
* This is often called a XLUnicodeRichExtendedString in MS documentation.
* REFERENCE: PG 264 Microsoft Excel 97 Developer's Kit (ISBN: 1-57231-498-2)
* REFERENCE: PG 951 Excel Binary File Format (.xls) Structure Specification v20091214
*/
public class UnicodeString implements Comparable { // TODO - make this final when the compatibility version is removed
private static POILogger _logger = POILogFactory.getLogger(UnicodeString.class);
private short field_1_charCount;
private byte field_2_optionflags;
private String field_3_string;
private List field_4_format_runs;
private ExtRst field_5_ext_rst;
private static final BitField highByte = BitFieldFactory.getInstance(0x1);
// 0x2 is reserved
private static final BitField extBit = BitFieldFactory.getInstance(0x4);
private static final BitField richText = BitFieldFactory.getInstance(0x8);
public static class FormatRun implements Comparable {
final short _character;
short _fontIndex;
public FormatRun(short character, short fontIndex) {
this._character = character;
this._fontIndex = fontIndex;
}
public FormatRun(LittleEndianInput in) {
this(in.readShort(), in.readShort());
}
public short getCharacterPos() {
return _character;
}
public short getFontIndex() {
return _fontIndex;
}
public boolean equals(Object o) {
if (!(o instanceof FormatRun)) {
return false;
}
FormatRun other = ( FormatRun ) o;
return _character == other._character && _fontIndex == other._fontIndex;
}
public int compareTo(FormatRun r) {
if (_character == r._character && _fontIndex == r._fontIndex) {
return 0;
}
if (_character == r._character) {
return _fontIndex - r._fontIndex;
}
return _character - r._character;
}
@Override
public int hashCode() {
assert false : "hashCode not designed";
return 42; // any arbitrary constant will do
}
public String toString() {
return "character="+_character+",fontIndex="+_fontIndex;
}
public void serialize(LittleEndianOutput out) {
out.writeShort(_character);
out.writeShort(_fontIndex);
}
}
// See page 681
public static class ExtRst implements Comparable {
private short reserved;
// This is a Phs (see page 881)
private short formattingFontIndex;
private short formattingOptions;
// This is a RPHSSub (see page 894)
private int numberOfRuns;
private String phoneticText;
// This is an array of PhRuns (see page 881)
private PhRun[] phRuns;
// Sometimes there's some cruft at the end
private byte[] extraData;
private void populateEmpty() {
reserved = 1;
phoneticText = "";
phRuns = new PhRun[0];
extraData = new byte[0];
}
protected ExtRst() {
populateEmpty();
}
protected ExtRst(LittleEndianInput in, int expectedLength) {
reserved = in.readShort();
// Old style detection (Reserved = 0xFF)
if(reserved == -1) {
populateEmpty();
return;
}
// Spot corrupt records
if(reserved != 1) {
_logger.log(POILogger.WARN, "Warning - ExtRst has wrong magic marker, expecting 1 but found " + reserved + " - ignoring");
// Grab all the remaining data, and ignore it
for(int i=0; i 0) {
length2 = 0;
}
if(length1 != length2) {
throw new IllegalStateException(
"The two length fields of the Phonetic Text don't agree! " +
length1 + " vs " + length2
);
}
phoneticText = StringUtil.readUnicodeLE(in, length1);
int runData = stringDataSize - 4 - 6 - (2*phoneticText.length());
int numRuns = (runData / 6);
phRuns = new PhRun[numRuns];
for(int i=0; i 0)) {
field_4_format_runs = new ArrayList(runCount);
for (int i=0;i 0)) {
field_5_ext_rst = new ExtRst(new ContinuableRecordInput(in), extensionLength);
if(field_5_ext_rst.getDataSize()+4 != extensionLength) {
_logger.log(POILogger.WARN, "ExtRst was supposed to be " + extensionLength + " bytes long, but seems to actually be " + (field_5_ext_rst.getDataSize() + 4));
}
}
}
/**
* get the number of characters in the string,
* as an un-wrapped int
*
* @return number of characters
*/
public int getCharCount() {
if(field_1_charCount < 0) {
return field_1_charCount + 65536;
}
return field_1_charCount;
}
/**
* get the number of characters in the string,
* wrapped as needed to fit within a short
*
* @return number of characters
*/
public short getCharCountShort() {
return field_1_charCount;
}
/**
* set the number of characters in the string
* @param cc - number of characters
*/
public void setCharCount(short cc)
{
field_1_charCount = cc;
}
/**
* get the option flags which among other things return if this is a 16-bit or
* 8 bit string
*
* @return optionflags bitmask
*
*/
public byte getOptionFlags()
{
return field_2_optionflags;
}
/**
* set the option flags which among other things return if this is a 16-bit or
* 8 bit string
*
* @param of optionflags bitmask
*
*/
public void setOptionFlags(byte of)
{
field_2_optionflags = of;
}
/**
* @return the actual string this contains as a java String object
*/
public String getString()
{
return field_3_string;
}
/**
* set the actual string this contains
* @param string the text
*/
public void setString(String string)
{
field_3_string = string;
setCharCount((short)field_3_string.length());
// scan for characters greater than 255 ... if any are
// present, we have to use 16-bit encoding. Otherwise, we
// can use 8-bit encoding
boolean useUTF16 = false;
int strlen = string.length();
for ( int j = 0; j < strlen; j++ )
{
if ( string.charAt( j ) > 255 )
{
useUTF16 = true;
break;
}
}
if (useUTF16)
//Set the uncompressed bit
field_2_optionflags = highByte.setByte(field_2_optionflags);
else field_2_optionflags = highByte.clearByte(field_2_optionflags);
}
public int getFormatRunCount() {
if (field_4_format_runs == null)
return 0;
return field_4_format_runs.size();
}
public FormatRun getFormatRun(int index) {
if (field_4_format_runs == null) {
return null;
}
if (index < 0 || index >= field_4_format_runs.size()) {
return null;
}
return field_4_format_runs.get(index);
}
private int findFormatRunAt(int characterPos) {
int size = field_4_format_runs.size();
for (int i=0;i characterPos)
return -1;
}
return -1;
}
/** Adds a font run to the formatted string.
*
* If a font run exists at the current charcter location, then it is
* replaced with the font run to be added.
*/
public void addFormatRun(FormatRun r) {
if (field_4_format_runs == null) {
field_4_format_runs = new ArrayList();
}
int index = findFormatRunAt(r._character);
if (index != -1)
field_4_format_runs.remove(index);
field_4_format_runs.add(r);
//Need to sort the font runs to ensure that the font runs appear in
//character order
Collections.sort(field_4_format_runs);
//Make sure that we now say that we are a rich string
field_2_optionflags = richText.setByte(field_2_optionflags);
}
public Iterator formatIterator() {
if (field_4_format_runs != null) {
return field_4_format_runs.iterator();
}
return null;
}
public void removeFormatRun(FormatRun r) {
field_4_format_runs.remove(r);
if (field_4_format_runs.size() == 0) {
field_4_format_runs = null;
field_2_optionflags = richText.clearByte(field_2_optionflags);
}
}
public void clearFormatting() {
field_4_format_runs = null;
field_2_optionflags = richText.clearByte(field_2_optionflags);
}
public ExtRst getExtendedRst() {
return this.field_5_ext_rst;
}
void setExtendedRst(ExtRst ext_rst) {
if (ext_rst != null) {
field_2_optionflags = extBit.setByte(field_2_optionflags);
} else {
field_2_optionflags = extBit.clearByte(field_2_optionflags);
}
this.field_5_ext_rst = ext_rst;
}
/**
* Swaps all use in the string of one font index
* for use of a different font index.
* Normally only called when fonts have been
* removed / re-ordered
*/
public void swapFontUse(short oldFontIndex, short newFontIndex) {
for (FormatRun run : field_4_format_runs) {
if(run._fontIndex == oldFontIndex) {
run._fontIndex = newFontIndex;
}
}
}
/**
* unlike the real records we return the same as "getString()" rather than debug info
* @see #getDebugInfo()
* @return String value of the record
*/
public String toString()
{
return getString();
}
/**
* return a character representation of the fields of this record
*
*
* @return String of output for biffviewer etc.
*
*/
public String getDebugInfo()
{
StringBuffer buffer = new StringBuffer();
buffer.append("[UNICODESTRING]\n");
buffer.append(" .charcount = ")
.append(Integer.toHexString(getCharCount())).append("\n");
buffer.append(" .optionflags = ")
.append(Integer.toHexString(getOptionFlags())).append("\n");
buffer.append(" .string = ").append(getString()).append("\n");
if (field_4_format_runs != null) {
for (int i = 0; i < field_4_format_runs.size();i++) {
FormatRun r = field_4_format_runs.get(i);
buffer.append(" .format_run"+i+" = ").append(r.toString()).append("\n");
}
}
if (field_5_ext_rst != null) {
buffer.append(" .field_5_ext_rst = ").append("\n");
buffer.append( field_5_ext_rst.toString() ).append("\n");
}
buffer.append("[/UNICODESTRING]\n");
return buffer.toString();
}
/**
* Serialises out the String. There are special rules
* about where we can and can't split onto
* Continue records.
*/
public void serialize(ContinuableRecordOutput out) {
int numberOfRichTextRuns = 0;
int extendedDataSize = 0;
if (isRichText() && field_4_format_runs != null) {
numberOfRichTextRuns = field_4_format_runs.size();
}
if (isExtendedText() && field_5_ext_rst != null) {
extendedDataSize = 4 + field_5_ext_rst.getDataSize();
}
// Serialise the bulk of the String
// The writeString handles tricky continue stuff for us
out.writeString(field_3_string, numberOfRichTextRuns, extendedDataSize);
if (numberOfRichTextRuns > 0) {
//This will ensure that a run does not split a continue
for (int i=0;i 0) {
field_5_ext_rst.serialize(out);
}
}
public int compareTo(UnicodeString str) {
int result = getString().compareTo(str.getString());
//As per the equals method lets do this in stages
if (result != 0)
return result;
//OK string appears to be equal but now lets compare formatting runs
if ((field_4_format_runs == null) && (str.field_4_format_runs == null))
//Strings are equal, and there are no formatting runs.
return 0;
if ((field_4_format_runs == null) && (str.field_4_format_runs != null))
//Strings are equal, but one or the other has formatting runs
return 1;
if ((field_4_format_runs != null) && (str.field_4_format_runs == null))
//Strings are equal, but one or the other has formatting runs
return -1;
//Strings are equal, so now compare formatting runs.
int size = field_4_format_runs.size();
if (size != str.field_4_format_runs.size())
return size - str.field_4_format_runs.size();
for (int i=0;i();
for (FormatRun r : field_4_format_runs) {
str.field_4_format_runs.add(new FormatRun(r._character, r._fontIndex));
}
}
if (field_5_ext_rst != null) {
str.field_5_ext_rst = field_5_ext_rst.clone();
}
return str;
}
}