public static string Extract(string path)
{
StringBuilder sb = new StringBuilder();
IFilter filter = null;
try
{
string sciezka = Directory.GetCurrentDirectory();
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 | // to chyba wsadza wszystkie spacje zamiast zpecialnych znakow
IFILTER_INIT.HARD_LINE_BREAKS |
IFILTER_INIT.APPLY_CRAWL_ATTRIBUTES |
IFILTER_INIT.APPLY_INDEX_ATTRIBUTES |
IFILTER_INIT.APPLY_OTHER_ATTRIBUTES |
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);
// Kamil
// scode = (IFilterReturnCodes)filter.GetChunk( (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());
}
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();
}
