/// <summary>
/// Processe the specified file
/// </summary>
/// <exception cref="TextFilterException">If the filter cannot be created or initialised for this instance</exception>
internal void ProcessInSTAThread()
{
// Exceptions in a thread are not automatically thrown in the main thread
try
{
// Intialize
IFilter iflt = null;
IUnknown iunk = null;
// Try to load the corresponding IFilter
int i = LoadIFilter(mFile, ref iunk, ref iflt);
if (i != (int)IFilterReturnCodes.S_OK)
{
throw new TextFilterException(
String.Format("IFilter instance not found for file {0}", mFile));
}
// More initializing
IFilterReturnCodes scode;
mDocumentText = new StringBuilder();
mDocumentProperties = new ListDictionary(
CaseInsensitiveComparer.Default);
// Try to initialize the IFilter
int attr = 0;
IFILTER_FLAGS flagsSet = 0;
scode = iflt.Init(mFlags, attr, IntPtr.Zero, ref flagsSet);
if (scode != IFilterReturnCodes.S_OK)
{
throw new TextFilterException(
String.Format("IFilter initialisation failed: {0}",
Enum.GetName(scode.GetType(), scode)));
}
// More initializing
int bufferSize = 65536;
StringBuilder buffer = new StringBuilder(bufferSize, bufferSize);
// Allocate memory for the propvariant
IntPtr propvariantPtr = Marshal.AllocCoTaskMem(10000);
// Get all chunks from the filter
STAT_CHUNK chunkStatus = new STAT_CHUNK();
while (scode == IFilterReturnCodes.S_OK)
{
// Get chunk
scode = iflt.GetChunk(ref chunkStatus);
if (scode == IFilterReturnCodes.S_OK)
{
// Text chunk
if (chunkStatus.flags == CHUNKSTATE.CHUNK_TEXT)
{
// Get text
bufferSize = 65536;
IFilterReturnCodes scodeText = iflt.GetText(
ref bufferSize, buffer);
// Append text if buffer size greater than zero
if (bufferSize > 0)
mDocumentText.Append(buffer.ToString(0, bufferSize));
}
else if (chunkStatus.flags == CHUNKSTATE.CHUNK_VALUE)
{
// Get property id
PROPID propId = (PROPID)((int)chunkStatus.attribute.psProperty.propid);
// Get the value
IFilterReturnCodes scodeGetValue = iflt.GetValue(ref propvariantPtr);
// Check return value
if (scodeGetValue == IFilterReturnCodes.S_OK || scodeGetValue == IFilterReturnCodes.FILTER_S_LAST_VALUES)
{
// Get the prop variant
PROPVARIANT propvariant = (PROPVARIANT)Marshal.PtrToStructure(propvariantPtr, typeof(PROPVARIANT));
// Get the property
if (propvariant.vt == (int)VariantTypes.VT_LPSTR || propvariant.vt == (int)VariantTypes.VT_LPWSTR)
{
// Get prop name
string propName = propId.ToString();
if (propName.Length > 4)
propName = propName.Substring(4).ToLower();
// Get property
mDocumentProperties[propName] =
Marshal.PtrToStringAuto(propvariant.data);
}
// Free referenced memory
Marshal.DestroyStructure(propvariantPtr, typeof(PROPVARIANT));
}
}
}
}
// Deallocate memory
Marshal.FreeCoTaskMem(propvariantPtr);
}
catch (Exception exception)
{
mErrorMessage = "TextFilter error: " + exception.Message;
}
}
public static string Extract(string path)
{
StringBuilder sb = new StringBuilder();
IFilter filter = null;
try
{
filter = loadIFilter(path);
if (filter == null)
return String.Empty;
uint i = 0;
STAT_CHUNK ps = new STAT_CHUNK();
IFILTER_INIT iflags =
IFILTER_INIT.CANON_HYPHENS |
IFILTER_INIT.CANON_PARAGRAPHS |
IFILTER_INIT.CANON_SPACES |
IFILTER_INIT.APPLY_CRAWL_ATTRIBUTES |
IFILTER_INIT.APPLY_INDEX_ATTRIBUTES |
IFILTER_INIT.APPLY_OTHER_ATTRIBUTES |
IFILTER_INIT.HARD_LINE_BREAKS |
IFILTER_INIT.SEARCH_LINKS |
IFILTER_INIT.FILTER_OWNED_VALUE_OK;
if (filter.Init(iflags, 0, null, ref i) != (int)IFilterReturnCodes.S_OK)
throw new Exception("Problem initializing an IFilter for:\n" + path + " \n\n");
while (filter.GetChunk(out ps) == (int)(IFilterReturnCodes.S_OK))
{
if (ps.flags == CHUNKSTATE.CHUNK_TEXT)
{
IFilterReturnCodes scode = 0;
while (scode == IFilterReturnCodes.S_OK || scode == IFilterReturnCodes.FILTER_S_LAST_TEXT)
{
uint pcwcBuffer = 65536;
System.Text.StringBuilder sbBuffer = new System.Text.StringBuilder((int)pcwcBuffer);
scode = (IFilterReturnCodes)filter.GetText(ref pcwcBuffer, sbBuffer);
if (pcwcBuffer > 0 && sbBuffer.Length > 0)
{
if (sbBuffer.Length < pcwcBuffer) // Should never happen, but it happens !
pcwcBuffer = (uint)sbBuffer.Length;
sb.Append(sbBuffer.ToString(0, (int)pcwcBuffer));
sb.Append(" "); // "\r\n"
}
}
}
}
}
finally
{
if (filter != null)
{
Marshal.ReleaseComObject(filter);
System.GC.Collect();
System.GC.WaitForPendingFinalizers();
}
}
return sb.ToString();
}