protected void fillFields(byte[] data, int offset) {
field_1_iStartAt = LittleEndian.getInt(data, 0x0 + offset);
field_2_nfc = data[0x4 + offset];
field_3_info = data[0x5 + offset];
field_4_rgbxchNums = LittleEndian.getByteArray(data, 0x6 + offset, 9);
field_5_ixchFollow = data[0xf + offset];
field_6_dxaIndentSav = LittleEndian.getInt(data, 0x10 + offset);
field_7_unused2 = LittleEndian.getInt(data, 0x14 + offset);
field_8_cbGrpprlChpx = LittleEndian.getUByte(data, 0x18 + offset);
field_9_cbGrpprlPapx = LittleEndian.getUByte(data, 0x19 + offset);
field_10_ilvlRestartLim = LittleEndian.getUByte(data, 0x1a + offset);
field_11_grfhic = new Grfhic(data, 0x1b + offset);
}
public int fillFields(byte[] data, int offset, EscherRecordFactory recordFactory) {
int bytesRemaining = readHeader(data, offset);
int pos = offset + 8;
int size = 0;
field_1_rectX1 = LittleEndian.getInt(data, pos + size);
size += 4;
field_2_rectY1 = LittleEndian.getInt(data, pos + size);
size += 4;
field_3_rectX2 = LittleEndian.getInt(data, pos + size);
size += 4;
field_4_rectY2 = LittleEndian.getInt(data, pos + size);
size += 4;
bytesRemaining -= size;
if (bytesRemaining != 0)
throw new RecordFormatException("Expected no remaining bytes but got " + bytesRemaining);
// remainingData = new byte[bytesRemaining];
// System.arraycopy( data, pos + size, remainingData, 0, bytesRemaining );
return 8 + size + bytesRemaining;
}
private static int findText(byte[] tableStream, int complexOffset, ArrayList<WordTextPiece> text)
throws IOException {
// actual text
int pos = complexOffset;
int multiple = 2;
// skips through the prms before we reach the piece table. These contain
// data
// for actual fast saved files
while (tableStream[pos] == 1) {
pos++;
int skip = LittleEndian.getShort(tableStream, pos);
pos += 2 + skip;
}
if (tableStream[pos] != 2) {
throw new IOException("corrupted Word file");
} else {
// parse out the text pieces
int pieceTableSize = LittleEndian.getInt(tableStream, ++pos);
pos += 4;
int pieces = (pieceTableSize - 4) / 12;
for (int x = 0; x < pieces; x++) {
int filePos = LittleEndian.getInt(tableStream, pos + ((pieces + 1) * 4) + (x * 8) + 2);
boolean unicode = false;
if ((filePos & 0x40000000) == 0) {
unicode = true;
} else {
unicode = false;
multiple = 1;
filePos &= ~(0x40000000); // gives me FC in doc stream
filePos /= 2;
}
int totLength =
LittleEndian.getInt(tableStream, pos + (x + 1) * 4)
- LittleEndian.getInt(tableStream, pos + (x * 4));
WordTextPiece piece = new WordTextPiece(filePos, totLength, unicode);
text.add(piece);
}
}
return multiple;
}
public int fillFields(byte[] data, int offset, EscherRecordFactory recordFactory) {
int bytesRemaining = readHeader(data, offset);
int pos = offset + 8;
int size = 0;
field_1_shapeIdMax = LittleEndian.getInt(data, pos + size);
size += 4;
LittleEndian.getInt(data, pos + size);
size += 4; // field_2_numIdClusters
field_3_numShapesSaved = LittleEndian.getInt(data, pos + size);
size += 4;
field_4_drawingsSaved = LittleEndian.getInt(data, pos + size);
size += 4;
field_5_fileIdClusters =
new FileIdCluster[(bytesRemaining - size) / 8]; // Can't rely on field_2_numIdClusters
for (int i = 0; i < field_5_fileIdClusters.length; i++) {
field_5_fileIdClusters[i] =
new FileIdCluster(
LittleEndian.getInt(data, pos + size), LittleEndian.getInt(data, pos + size + 4));
maxDgId = Math.max(maxDgId, field_5_fileIdClusters[i].getDrawingGroupId());
size += 8;
}
bytesRemaining -= size;
if (bytesRemaining != 0)
throw new RecordFormatException(
"Expecting no remaining data but got " + bytesRemaining + " byte(s).");
return 8 + size + bytesRemaining;
}
public NativeHeader(byte data[], int offset) {
int type = (int) LittleEndian.getUInt(data, offset);
offset += 4;
if (type != 1) {
throw new HSLFException("Invalid EMF picture");
}
// ignore header size
offset += 4;
int left = LittleEndian.getInt(data, offset);
offset += 4;
int top = LittleEndian.getInt(data, offset);
offset += 4;
int right = LittleEndian.getInt(data, offset);
offset += 4;
int bottom = LittleEndian.getInt(data, offset);
offset += 4;
deviceBounds = new Rectangle(left, top, right - left, bottom - top);
// ignore frame bounds
offset += 16;
String signature = new String(data, offset, EMF_SIGNATURE.length(), LocaleUtil.CHARSET_1252);
if (!EMF_SIGNATURE.equals(signature)) {
throw new HSLFException("Invalid EMF picture");
}
}
public FIBFieldHandler(
byte mainStream[],
int startOffset,
byte tableStream[],
HashSet offsetList,
boolean areKnown) {
_unknownMap = new HashMap();
int numFields = LittleEndian.getShort(mainStream, startOffset);
int offset = startOffset + 2;
_fields = new int[numFields * 2];
for (int x = 0; x < numFields; x++) {
int fieldOffset = x * 8 + offset;
int dsOffset = LittleEndian.getInt(mainStream, fieldOffset);
fieldOffset += 4;
int dsSize = LittleEndian.getInt(mainStream, fieldOffset);
if (offsetList.contains(Integer.valueOf(x)) ^ areKnown && dsSize > 0)
if (dsOffset + dsSize > tableStream.length) {
log.log(
POILogger.WARN,
(new StringBuilder())
.append("Unhandled data structure points to outside the buffer. offset = ")
.append(dsOffset)
.append(", length = ")
.append(dsSize)
.append(", buffer length = ")
.append(tableStream.length)
.toString());
} else {
UnhandledDataStructure unhandled =
new UnhandledDataStructure(tableStream, dsOffset, dsSize);
_unknownMap.put(Integer.valueOf(x), unhandled);
}
_fields[x * 2] = dsOffset;
_fields[x * 2 + 1] = dsSize;
}
}
/** For the TextHeader Atom */
protected TextHeaderAtom(byte[] source, int start, int len) {
// Sanity Checking - we're always 12 bytes long
if (len < 12) {
len = 12;
if (source.length - start < 12) {
throw new RuntimeException(
"Not enough data to form a TextHeaderAtom (always 12 bytes long) - found "
+ (source.length - start));
}
}
// Get the header
_header = new byte[8];
System.arraycopy(source, start, _header, 0, 8);
// Grab the type
textType = LittleEndian.getInt(source, start + 8);
}
static Sttb read(int cDataLength, byte[] buffer, int startOffset) {
short ffff = LittleEndian.getShort(buffer, startOffset);
int offset = startOffset + 2;
if (ffff != (short) 0xffff) {
// Non-extended character Pascal strings
throw new UnsupportedOperationException(
"Non-extended character Pascal strings are not supported right now. "
+ "Please, contact POI developers for update.");
}
// strings are extended character strings
int cData =
cDataLength == 2
? LittleEndian.getUShort(buffer, offset)
: LittleEndian.getInt(buffer, offset);
offset += cDataLength;
Sttb sttb = new Sttb();
sttb.cDataLength = cDataLength;
sttb.cbExtra = LittleEndian.getUShort(buffer, offset);
offset += 2;
sttb.data = new String[cData];
sttb.extraData = new byte[cData][];
for (int i = 0; i < cData; i++) {
int cchData = LittleEndian.getShort(buffer, offset);
offset += 2;
if (cchData < 0) continue;
sttb.data[i] = StringUtil.getFromUnicodeLE(buffer, offset, cchData);
offset += cchData * 2;
sttb.extraData[i] = LittleEndian.getByteArray(buffer, offset, sttb.cbExtra);
offset += sttb.cbExtra;
}
return sttb;
}
public void testWrite() {
HSSFWorkbook workbook = new HSSFWorkbook();
HSSFSheet sheet = workbook.createSheet();
CFRuleRecord rr = CFRuleRecord.create(sheet, ComparisonOperator.BETWEEN, "5", "10");
PatternFormatting patternFormatting = new PatternFormatting();
patternFormatting.setFillPattern(PatternFormatting.BRICKS);
rr.setPatternFormatting(patternFormatting);
byte[] data = rr.serialize();
assertEquals(26, data.length);
assertEquals(3, LittleEndian.getShort(data, 6));
assertEquals(3, LittleEndian.getShort(data, 8));
int flags = LittleEndian.getInt(data, 10);
assertEquals("unused flags should be 111", 0x00380000, flags & 0x00380000);
assertEquals(
"undocumented flags should be 0000", 0, flags & 0x03C00000); // Otherwise Excel gets unhappy
// check all remaining flag bits (some are not well understood yet)
assertEquals(0x203FFFFF, flags);
}
/**
* Reads the 8 byte header information and populates the <code>options</code> and <code>recordId
* </code> records.
*
* @param data the byte array to read from
* @param offset the offset to start reading from
* @return the number of bytes remaining in this record. This may include the children if this is
* a container.
*/
protected int readHeader(byte[] data, int offset) {
_options = LittleEndian.getShort(data, offset);
_recordId = LittleEndian.getShort(data, offset + 2);
int remainingBytes = LittleEndian.getInt(data, offset + 4);
return remainingBytes;
}
public String extractText(InputStream in) throws IOException {
ArrayList<WordTextPiece> text = new ArrayList<WordTextPiece>();
POIFSFileSystem fsys = new POIFSFileSystem(in);
DocumentEntry headerProps = (DocumentEntry) fsys.getRoot().getEntry("WordDocument");
DocumentInputStream din = fsys.createDocumentInputStream("WordDocument");
byte[] header = new byte[headerProps.getSize()];
din.read(header);
din.close();
// Prende le informazioni dall'header del documento
int info = LittleEndian.getShort(header, 0xa);
boolean useTable1 = (info & 0x200) != 0;
// boolean useTable1 = true;
// Prende informazioni dalla piece table
int complexOffset = LittleEndian.getInt(header, 0x1a2);
// int complexOffset = LittleEndian.getInt(header);
String tableName = null;
if (useTable1) {
tableName = "1Table";
} else {
tableName = "0Table";
}
DocumentEntry table = (DocumentEntry) fsys.getRoot().getEntry(tableName);
byte[] tableStream = new byte[table.getSize()];
din = fsys.createDocumentInputStream(tableName);
din.read(tableStream);
din.close();
din = null;
fsys = null;
table = null;
headerProps = null;
int multiple = findText(tableStream, complexOffset, text);
StringBuffer sb = new StringBuffer();
tableStream = null;
for (int x = 0; x < text.size(); x++) {
WordTextPiece nextPiece = (WordTextPiece) text.get(x);
int start = nextPiece.getStart();
int length = nextPiece.getLength();
boolean unicode = nextPiece.usesUnicode();
String toStr = null;
if (unicode) {
toStr = new String(header, start, length * multiple, "UTF-8");
} else {
toStr = new String(header, start, length, "big5");
}
sb.append(toStr).append(" ");
}
return sb.toString();
}
