private bool InitialiserMethodForExcelFile()
{
StructuredStorageInterface.IStorage iStorage;
IStream iStream = GetStream(out iStorage, "Workbook");
if (null == iStream)
{
iStream = GetStream(out iStorage, "Book");
if (null == iStream)
return false;
}
m_fileData.FileType = FileType.ExcelSheet;
using (new ComObjectGovernor(iStream))
using (new ComObjectGovernor(iStorage))
{
StreamWrapper stream = new StreamWrapper(iStream);
XLBOF xlbof = new XLBOF();
object bofObject = xlbof;
stream.GetHeaderStructure(ref bofObject);
xlbof = (XLBOF) bofObject;
if (xlbof.vers == 0x08)
{
switch (xlbof.vers2)
{
case 0x0500:
break;
case 0x0600:
break;
case 0x1333:
break;
default:
return false;
}
}
StructuredStorageInterface.IPropertyStorage ipropertyStorage = GetPropertyStorage(iStorage, StructuredStorageInterface.FMTID_SummaryInformation);
if (ipropertyStorage != null)
// Not all excel documents have summary information
// Content detail reports only have a Workbook section.
{
using (new ComObjectGovernor(ipropertyStorage))
using (new ComObjectGovernor(iStorage))
{
StructuredStorageInterface.IEnumSTATPROPSTG iEnumSTATPROPSTG;
ipropertyStorage.Enum(out iEnumSTATPROPSTG);
if (null != iEnumSTATPROPSTG)
{
StructuredStorageInterface.STATPROPSTG statprop;
while (1 == iEnumSTATPROPSTG.Next(1, out statprop))
{
if (statprop.PROPID == StructuredStorageInterface.PIDSI_DOC_SECURITY)
{
StructuredStorageInterface.PROPSPEC propspec = new StructuredStorageInterface.PROPSPEC
{
PROPID = StructuredStorageInterface.PIDSI_DOC_SECURITY,
ulKind = 1
};
try
{
StructuredStorageInterface.PROPVARIANT propval;
ipropertyStorage.ReadMultiple(1, ref propspec, out propval);
if (1 == propval.value)
{
m_fileData.ReadPasswordProtected = true;
}
}
catch (COMException)
{
// above check can throw in 64 bit, not sure what to do about it
}
}
}
}
}
}
// Check if file is also write protected...
// (A write protected workbook that is not read protected, will not have the PIDSI_DOC_SECURITY flag)
m_fileData.WritePasswordProtected = ExcelDocumentReader.IsWriteProtected(m_fileData.BinaryFileData);
m_impl = new FileImpl(m_fileData);
return true;
}
}
private bool InitialiserMethodForPPTFile()
{
StructuredStorageInterface.IStorage iStorage;
IStream encryptedStream;
encryptedStream = GetStream(out iStorage, "EncryptedSummary");
using (new ComObjectGovernor(encryptedStream))
using (new ComObjectGovernor(iStorage))
{
if (null != encryptedStream)
{
m_fileData.FileEncrypted = true;
m_fileData.FileType = FileType.PowerPoint;
m_fileData.ReadPasswordProtected = true;
m_impl = new FileImpl(m_fileData);
return true;
}
}
IStream iStream = GetStream(out iStorage, "PowerPoint Document");
using (new ComObjectGovernor(iStream))
using (new ComObjectGovernor(iStorage))
{
if (null == iStream)
return false;
m_fileData.FileType = FileType.PowerPoint;
if (PptStreamContainsEncryptedLabel(iStream))//encrypted .ppt created via PP2013 for some reason do not have "EncryptedSummary" stream
{
m_fileData.FileEncrypted = true;
m_fileData.ReadPasswordProtected = true;
}
m_impl = new FileImpl(m_fileData);
return true;
}
}
private bool InitialiseMethodForEncryptedXlsxFileOnDisk()
{
StructuredStorageInterface.IStorage iStorage;
//make sure it isn't an encrypted docx/docm
IStream iStream = GetStream(out iStorage, "WordDocument");
using (new ComObjectGovernor(iStream))
using (new ComObjectGovernor(iStorage))
{
if (null != iStream)
return false;
}
using (new ComObjectGovernor(iStorage))
{
bool bIstream1 = false;
IStream iStream1 = GetStream(out iStorage, "EncryptionInfo");
using (new ComObjectGovernor(iStream1))
using (new ComObjectGovernor(iStorage))
{
bIstream1 = iStream1 == null ? false : true;
}
bool bIstream2 = false;
IStream iStream2 = GetStream(out iStorage, "EncryptedPackage");
using (new ComObjectGovernor(iStream1))
using (new ComObjectGovernor(iStorage))
{
bIstream2 = iStream2 == null ? false : true;
}
string filename = m_fileData.Filename.ToLower();
//encrypted pptx/pptm have these streams as well, but there is no
//distinguishing characteristics that I have been able to identify
//so can but check the extensions
if ((bIstream1 && bIstream2) &&
(filename.EndsWith("xlsx", StringComparison.InvariantCultureIgnoreCase)
|| filename.EndsWith("xlsm", StringComparison.InvariantCultureIgnoreCase)
|| filename.EndsWith("xls", StringComparison.InvariantCultureIgnoreCase)
))
{
m_fileData.FileType = FileType.ExcelSheetX;
m_fileData.ReadPasswordProtected = true;
m_fileData.WritePasswordProtected = true;
m_impl = new FileImpl(m_fileData);
return true;
}
}
return false;
}
private bool InitialiserMethodForWordFileOnDisk()
{
StructuredStorageInterface.IStorage iStorage;
IStream iStream = GetStream(out iStorage, "WordDocument");
if (null == iStream)
return false;
StreamWrapper stream;
FIB fib;
DOPHeader dopHeader;
using (new ComObjectGovernor(iStream))
using (new ComObjectGovernor(iStorage))
{
stream = new StreamWrapper(iStream);
fib = new FIB();
dopHeader = new DOPHeader();
stream.GetDOP(ref dopHeader);
object fibObject = fib as object;
stream.GetHeaderStructure(ref fibObject);
fib = (FIB)fibObject;
}
// \ /
// .\-/.
// /\ () () /\
// / \ /~-~\ / \
// y Y V
// ,-^-./ | \,-^-.
/// { | } \
// \ | /
// /\ A /\
// / \/ \/ \
// / \
//
// int numLols = 1 // increment every time you see this for the first time
if (fib.magicNumber != 0) //THIS ZERO-CHECK IS A HACK FOR PROTECT MOBILE - IT SHOULD BE REMOVED ASAP
{
//THIS is the proper code to check for Word file versioning. This should stay.
if (fib.magicNumber != 0xA5DC && fib.magicNumber != 0xA5EC)
return false;
}
//we will get this far with a docx/docm if it is encrypted but the FIB is empty then so we can drop out now
if (fib.bitData == 0 && fib.lid == 0 && fib.magicNumber == 0 && fib.version == 0 && fib.nProduct == 0)
{
return false;
}
m_fileData.FileType = FileType.WordDocument;
if ((fib.bitData & StreamWrapper.fEncrypted) == StreamWrapper.fEncrypted)
m_fileData.ReadPasswordProtected = true;
if ((fib.bitData & StreamWrapper.fWriteReservation) == StreamWrapper.fWriteReservation)
m_fileData.WritePasswordProtected = true;
// only try to find the document protection flags within the DOP if we know that the
// file is not encrypted. Otherwise the offsets are not valid.
if (!m_fileData.ReadPasswordProtected && !m_fileData.WritePasswordProtected)
{
//DOPHeader dopHeader = new DOPHeader();
//stream.GetDOP(ref dopHeader);
m_fileData.DocumentProtected = HasDocumentProtection(fib, dopHeader);
}
m_impl = new FileImpl(m_fileData);
return true;
//}
}
private bool InitialiseMethodForEncryptedDocXFileOnDisk()
{
StructuredStorageInterface.IStorage iStorage;
IStream iStream = GetStream(out iStorage, "WordDocument");
bool bIstream = false;
using (new ComObjectGovernor(iStream))
using (new ComObjectGovernor(iStorage))
{
bIstream = iStream == null ? false : true;
}
if (!bIstream && (iStorage == null))
return false;
// Office2007 SP2 does not have "WordDocument" stream
if (!bIstream && (iStorage != null))
{
bool bIstream1 = false;
IStream iStream1 = GetStream(out iStorage, "EncryptionInfo");
using (new ComObjectGovernor(iStream1))
using (new ComObjectGovernor(iStorage))
{
bIstream1 = iStream1 == null ? false : true;
}
bool bIstream2 = false;
IStream iStream2 = GetStream(out iStorage, "EncryptedPackage");
using (new ComObjectGovernor(iStream2))
using (new ComObjectGovernor(iStorage))
{
bIstream2 = iStream2 == null ? false : true;
}
string filename = m_fileData.Filename.ToLower();
if ((bIstream1 && bIstream2) &&
(filename.EndsWith("docx", StringComparison.InvariantCultureIgnoreCase)
|| filename.EndsWith("docm", StringComparison.InvariantCultureIgnoreCase)
|| filename.EndsWith("doc", StringComparison.InvariantCultureIgnoreCase)))
{
m_fileData.FileType = FileType.WordDocumentX;
m_fileData.ReadPasswordProtected = true;
m_fileData.WritePasswordProtected = true;
m_impl = new FileImpl(m_fileData);
return true;
}
else
return false;
}
iStream = GetStream(out iStorage, "WordDocument");
FIB fib = new FIB();
using (new ComObjectGovernor(iStream))
using (new ComObjectGovernor(iStorage))
{
StreamWrapper stream = new StreamWrapper(iStream);
object fibObject = fib as object;
stream.GetHeaderStructure(ref fibObject);
fib = (FIB) fibObject;
}
if (fib.bitData == 0 && fib.lid == 0 && fib.magicNumber == 0 && fib.version == 0 && fib.nProduct == 0)
{
bool bIstream1 = false;
IStream iStream1 = GetStream(out iStorage, "EncryptionInfo");
using (new ComObjectGovernor(iStream1))
using (new ComObjectGovernor(iStorage))
{
bIstream1 = iStream1 == null ? false : true;
}
bool bIstream2 = false;
IStream iStream2 = GetStream(out iStorage, "EncryptedPackage");
using (new ComObjectGovernor(iStream2))
using (new ComObjectGovernor(iStorage))
{
bIstream2 = iStream2 == null ? false : true;
}
if (bIstream1 && bIstream2)
{
m_fileData.FileType = FileType.WordDocumentX;
m_fileData.ReadPasswordProtected = true;
m_fileData.WritePasswordProtected = true;
m_impl = new FileImpl(m_fileData);
return true;
}
}
return false;
}
private bool InitialiserMethodForXlsXFile()
{
if (!IsZipFile())
{
return Workshare.Interop.Options.OptionApi.GetBool("UseDiskBasedFiles") ? InitialiseMethodForEncryptedXlsxFileOnDisk() :
InitialiseMethodForEncryptedXlsxFile();
}
using (Stream stream = m_fileData.BinaryFileData.AsStream())
using (ZipEntryFinder zipEntryFinder = new ZipEntryFinder(stream, false))
{
if (!zipEntryFinder.HasEntry("[content_types].xml"))
return false;
ZipEntry zipEntry = zipEntryFinder.GetEntry(@"xl\workbook.xml");
if (zipEntry == null)
return false;
//Method to look at the XML within the document and determine the correct file type.
//If we don't find a file type, then we assume that the type is ExcelSheetX
FileType type = DetermineFileTypeForOfficeXMLFiles(zipEntryFinder, stream);
switch (type)
{
case FileType.Unknown:
type = FileType.ExcelSheetX;
break;
//Office 2003 compatibility packs don't support 2007 template types...so we don't either.
case FileType.ExcelSheetTemplateX:
case FileType.ExcelSheetMacroTemplateX:
if (OfficeApplicationVersion.IsWord2003())
{
type = FileType.Unknown;
}
break;
}
m_fileData.FileType = type;
GetXlsXWriteProtection(zipEntry, stream);
GetXlsXSheetsProtection(zipEntryFinder, stream);
m_impl = new FileImpl(m_fileData);
Logger.LogInfo(".xlsx;.xlsm;.xltx;.xltm file detected");
return true;
}
}
[InitialiserMethod(Order = 13, Extensions = ".txt")] //Text must run after everything else
private bool InitialiserMethodForTextFile()
{
if (0 == m_fileData.BinaryFileData.Length)
return false;
if (m_fileData.Encoding == System.Text.Encoding.Unicode ||
m_fileData.Encoding == System.Text.Encoding.BigEndianUnicode)
{
m_fileData.FileType = FileType.TextDocument;
m_impl = new FileImpl(m_fileData);
}
else
{
int ibyte = 0;
while (ibyte < Math.Min(m_fileData.BinaryFileData.Length, 2048))
{
byte currentByte = m_fileData.BinaryFileData[ibyte];
if ((currentByte > 0) && (currentByte < 9))
return false;
ibyte++;
}
m_fileData.FileType = FileType.TextDocument;
m_impl = new FileImpl(m_fileData);
}
return true;
}
private bool InitialiserMethodForXMLFile()
{
if (!Utils.LooksLikeXML(m_fileData.BinaryFileData))
return false;
byte[] byteArray = new byte[4];
using (Stream str = m_fileData.BinaryFileData.AsStream())
{
str.Read(byteArray, 0, 4);
Encoding encoding = Utils.FindEncoding(ref byteArray);
string stringData = m_fileData.BinaryFileData.AsString(10240, encoding);
string xmlPattern = @"(?i)<(.*)\?(.*)xml(.*)version";
// is xml
if (!System.Text.RegularExpressions.Regex.IsMatch(stringData, xmlPattern))
return false;
}
try
{
using (Stream stream = m_fileData.BinaryFileData.AsStream())
{
XmlDocument document = new XmlDocument();
document.XmlResolver = null;
document.Load(stream);
}
}
catch (XmlException)
{
// Not well formated.
return false;
}
m_fileData.FileType = FileType.XMLDocument;
m_impl = new FileImpl(m_fileData);
return true;
}
private bool InitialiserMethodForHTMLFile()
{
bool ishtml = Utils.IsDataHTML(m_fileData.BinaryFileData);
if (ishtml)
{
m_fileData.FileType = FileType.HTMLDocument;
}
m_impl = new FileImpl(m_fileData);
return ishtml;
}
private bool InitialiserMethodForRTFFile()
{
if (!IsRtfFile(m_fileData.BinaryFileData))
{
return false;
}
m_fileData.FileType = FileType.RTFDocument;
GetRtfDocumentProtection();
m_impl = new FileImpl(m_fileData);
return true;
}
private bool InitialiserMethodForPdfFile()
{
if (5 >= m_fileData.BinaryFileData.Length)
return false;
BinaryData binaryData = m_fileData.BinaryFileData;
if (((0x25 == binaryData[0]) && (0x50 == binaryData[1]) && (0x44 == binaryData[2]) && (0x46 == binaryData[3])) ||
IsPdfFileWithHtmlTags(binaryData))
{
m_fileData.FileType = FileType.PDFDocument;
try
{
using (FCS.Lite.PdfDocumentReader pdfReader = new FCS.Lite.PdfDocumentReader(m_fileData.Filename))
{
m_fileData.ReadPasswordProtected = pdfReader.IsEncrypted();
}
}
catch (System.Exception)
{
m_fileData.ReadPasswordProtected = true;
}
m_impl = new FileImpl(m_fileData);
return true;
}
return false;
}
