public void TestAsciiParts()
{
HWPFDocument doc = HWPFTestDataSamples.OpenSampleFile("ThreeColHeadFoot.doc");
TextPieceTable tbl = doc.TextTable;
// All ascii, so stored in one big lump
Assert.AreEqual(1, tbl.TextPieces.Count);
TextPiece tp = (TextPiece)tbl.TextPieces[0];
Assert.AreEqual(0, tp.Start);
Assert.AreEqual(339, tp.End);
Assert.AreEqual(339, tp.CharacterLength);
Assert.AreEqual(339, tp.BytesLength);
Assert.IsTrue(tp.GetStringBuilder().ToString().StartsWith("This is a sample word document"));
// Save and re-load
HWPFDocument docB = SaveAndReload(doc);
tbl = docB.TextTable;
Assert.AreEqual(1, tbl.TextPieces.Count);
tp = (TextPiece)tbl.TextPieces[0];
Assert.AreEqual(0, tp.Start);
Assert.AreEqual(339, tp.End);
Assert.AreEqual(339, tp.CharacterLength);
Assert.AreEqual(339, tp.BytesLength);
Assert.IsTrue(tp.GetStringBuilder().ToString().StartsWith("This is a sample word document"));
}
public override bool Equals(Object o)
{
if (LimitsAreEqual(o))
{
TextPiece tp = (TextPiece)o;
return(GetStringBuilder().ToString().Equals(tp.GetStringBuilder().ToString()) &&
tp._usesUnicode == _usesUnicode && _pd.Equals(tp._pd));
}
return(false);
}
public HWPFOldDocument(DirectoryNode directory)
: base(directory)
{
// Where are things?
int sedTableOffset = LittleEndian.GetInt(_mainStream, 0x88);
int sedTableSize = LittleEndian.GetInt(_mainStream, 0x8c);
int chpTableOffset = LittleEndian.GetInt(_mainStream, 0xb8);
int chpTableSize = LittleEndian.GetInt(_mainStream, 0xbc);
int papTableOffset = LittleEndian.GetInt(_mainStream, 0xc0);
int papTableSize = LittleEndian.GetInt(_mainStream, 0xc4);
//int shfTableOffset = LittleEndian.GetInt(_mainStream, 0x60);
//int shfTableSize = LittleEndian.GetInt(_mainStream, 0x64);
int complexTableOffset = LittleEndian.GetInt(_mainStream, 0x160);
// We need to get hold of the text that Makes up the
// document, which might be regular or fast-saved
StringBuilder text = new StringBuilder();
if (_fib.IsFComplex())
{
ComplexFileTable cft = new ComplexFileTable(
_mainStream, _mainStream,
complexTableOffset, _fib.GetFcMin()
);
tpt = cft.GetTextPieceTable();
foreach (TextPiece tp in tpt.TextPieces)
{
text.Append(tp.GetStringBuilder());
}
}
else
{
// TODO Discover if these older documents can ever hold Unicode Strings?
// (We think not, because they seem to lack a Piece table)
// TODO Build the Piece Descriptor properly
// (We have to fake it, as they don't seem to have a proper Piece table)
PieceDescriptor pd = new PieceDescriptor(new byte[] { 0, 0, 0, 0, 0, 127, 0, 0 }, 0);
pd.FilePosition = _fib.GetFcMin();
// Generate a single Text Piece Table, with a single Text Piece
// which covers all the (8 bit only) text in the file
tpt = new TextPieceTable();
byte[] textData = new byte[_fib.GetFcMac() - _fib.GetFcMin()];
Array.Copy(_mainStream, _fib.GetFcMin(), textData, 0, textData.Length);
TextPiece tp = new TextPiece(
0, textData.Length, textData, pd
);
tpt.Add(tp);
text.Append(tp.GetStringBuilder());
}
_text = tpt.Text;
// Now we can fetch the character and paragraph properties
_cbt = new OldCHPBinTable(
_mainStream, chpTableOffset, chpTableSize,
_fib.GetFcMin(), tpt
);
_pbt = new OldPAPBinTable(
_mainStream, chpTableOffset, papTableSize,
_fib.GetFcMin(), tpt
);
_st = new OldSectionTable(
_mainStream, chpTableOffset, sedTableSize,
_fib.GetFcMin(), tpt
);
}