File type identifiers
File
File: dtsearch.h
Syntax
C++
enum TypeId {
it_WordList = 104,
it_ContentAsXml = 108,
it_Ami = 201,
it_Ansi = 202,
it_Ascii = 203,
it_Binary = 204,
it_CompoundDoc = 205,
it_DBF = 206,
it_FilteredBinary = 207,
it_HyperText = 208,
it_MS_Word = 209,
it_MS_Works = 210,
it_Multimate = 211,
it_RTF = 212,
it_WS_2000 = 213,
it_WS_5 = 214,
it_WinWrite = 215,
it_WordForDos = 215,
it_WordForWin = 216,
it_WordForWin6 = 217,
it_WordPerfect42 = 218,
it_WordPerfect5 = 219,
it_WordPerfect6 = 220,
it_WordStar = 221,
it_XyWrite = 222,
it_ZIP = 223,
it_Properties = 224,
it_Excel5 = 225,
it_HTML = 226,
it_PDF = 227,
it_WordForWin97 = 228,
it_Excel97 = 229,
it_PowerPoint = 230,
it_EncryptedHtml = 231,
it_DatabaseRecord = 232,
it_SegmentedText = 233,
it_XML = 234,
it_WordPerfectEmbedded = 235,
it_Unicode = 236,
it_EudoraMessage = 237,
it_Utf8 = 238,
it_OutlookExpressMessage = 240,
it_MimeMessage = 241,
it_SingleByteText = 242,
it_MBoxArchive = 243,
it_FilteredBinaryUnicode = 244,
it_ZIP_zlib = 245,
it_OutlookMsgFile = 246,
it_TreepadHjtFile = 247,
it_PfsProfessionalWrite = 248,
it_FilteredBinaryUnicodeStream = 249,
it_DocFile = 250,
it_Media = 251,
it_NonTextData = 252,
it_EML = 253,
it_MicrosoftWord = 254,
it_UnformattedHTML = 256,
it_DatabaseRecord2 = 257,
it_Excel2003Xml = 258,
it_Word2003Xml = 259,
it_OpenOfficeDocument = 260,
it_CSV = 261,
it_MicrosoftAccess = 262,
it_XBase = 263,
it_OutlookExpressMessageStore = 264,
it_IFilter = 265,
it_Gzip = 266,
it_Excel4 = 267,
it_Word12 = 268,
it_Excel12 = 269,
it_PowerPoint12 = 270,
it_TNEF = 271,
it_XPS = 272,
it_WMF = 273,
it_EMF = 274,
it_TAR = 275,
it_Excel2 = 277,
it_Excel3 = 278,
it_MBoxArchive2 = 279,
it_Lotus123 = 280,
it_MsWorksWps4 = 281,
it_MsWorksWps6 = 282,
it_QuattroPro = 283,
it_QuattroPro8 = 284,
it_OutlookMsgAsContainer = 285,
it_MimeContainer = 286,
it_PdfWithAttachments = 287,
it_MicrosoftAccess2 = 288,
it_FlashSWF = 289,
it_RAR = 290,
it_NoContent = 291,
it_Excel12xlsb = 292,
it_XfaForm = 293,
it_MifFile = 294,
it_WordForWindows2 = 295,
it_ASF = 296,
it_MP3 = 297,
it_QuickTime = 298,
it_MP4 = 299,
it_M4A = 300,
it_MPG = 301,
it_JPEG = 302,
it_TIFF = 303,
it_MDI = 304,
it_GIF = 305,
it_PNG = 306,
it_CAB = 308,
it_dtSearchIndex = 309,
it_HtmlHelp = 310,
it_TrueTypeFont = 311,
it_WAV = 312,
it_BMP = 313,
it_AVI = 314,
it_Visio = 315,
it_Ichitaro = 316,
it_SolidWorks = 317,
it_Unigraphics = 318,
it_DWG = 319,
it_DWF = 320,
it_DXF = 321,
it_VisioXml = 322,
it_WordForWindows1 = 323,
it_OutlookPst = 324,
it_MicrosoftOfficeThemeData = 325,
it_MIDI = 326,
it_OutlookExpressMessageStore2 = 327,
it_PowerPoint4 = 328,
it_PowerPoint95 = 329,
it_PowerPoint3 = 330,
it_Ichitaro5 = 331,
it_OleDataMso = 332,
it_CsvAsReport = 333,
it_CsvAsDocument = 334,
it_MicrosoftAccessAsDocument = 335,
it_XBaseAsDocument = 336,
it_OneNote2003 = 337,
it_OneNote2007 = 338,
it_OneNote2010 = 339,
it_JpegXR = 340,
it_WindowsExecutable = 341,
it_ElfExecutable = 342,
it_ICalendar = 343,
it_MicrosoftPublisher = 344,
it_PhotoshopImage = 346,
it_Cals = 347,
it_iWork2009 = 348,
it_iWork2009Pages = 349,
it_iWork2009Numbers = 350,
it_iWork2009Keynote = 351,
it_Visio2013 = 352,
it_SASF = 353,
it_Unigraphics2 = 354,
it_OneNoteOnline = 355,
it_7z = 359
};
Members
Members |
Description |
---|---|
it_WordList = 104 |
List of words in UTF-8 format, with the word ordinal in front of each word |
it_ContentAsXml = 108 |
Output format for FileConverter that organizes document content, metadata, and attachments into a standard XML format |
it_Ami = 201 |
Ami Pro |
it_Ansi = 202 |
Ansi text file |
it_Ascii = 203 |
Ascii (DOS) text file |
it_Binary = 204 |
Binary file (unrecognized format) |
it_CompoundDoc = 205 |
OLE Compound Document (or "DocFile") |
it_DBF = 206 |
XBase database file |
it_FilteredBinary = 207 |
Filtered binary file |
it_HyperText = 208 |
Obsolete |
it_MS_Word = 209 |
Obsolete |
it_MS_Works = 210 |
Microsoft Works word processor |
it_Multimate = 211 |
Multimate (any version) |
it_RTF = 212 |
Microsoft Rich Text Format |
it_WS_2000 = 213 |
Wordstar 2000 |
it_WS_5 = 214 |
WordStar version 5 or 6 |
it_WinWrite = 215 |
Windows Write |
it_WordForDos = 215 |
Word for DOS (same as Windows Write, it_WinWrite) |
it_WordForWin = 216 |
Obsolete |
it_WordForWin6 = 217 |
Microsoft Word 6.0 |
it_WordPerfect42 = 218 |
WordPerfect 4.2 |
it_WordPerfect5 = 219 |
WordPerfect 5 |
it_WordPerfect6 = 220 |
WordPerfect 6 |
it_WordStar = 221 |
WordStar through version 4 |
it_XyWrite = 222 |
XyWrite |
it_ZIP = 223 |
ZIP archive |
it_Properties = 224 |
PropertySet stream in a Compound Document |
it_Excel5 = 225 |
Excel versions 5 and 7 |
it_HTML = 226 |
HTML |
it_PDF = 227 |
PDF |
it_WordForWin97 = 228 |
Word For Windows 97, 2000, XP, or 2003 |
it_Excel97 = 229 |
Excel 97, 2000, XP, or 2003 |
it_PowerPoint = 230 |
PowerPoint 97-2003 |
it_EncryptedHtml = 231 |
Obsolete |
it_DatabaseRecord = 232 |
Record in a database file (such as XBase or Access) |
it_SegmentedText = 233 |
Text segmented using File Segmentation Rules |
it_XML = 234 |
XML |
it_WordPerfectEmbedded = 235 |
WordPerfect document embedded in another file |
it_Unicode = 236 |
UCS-16 text |
it_EudoraMessage = 237 |
Message in a Eudora message store |
it_Utf8 = 238 |
UTF-8 text |
it_OutlookExpressMessage = 240 |
Message in an Outlook Express message store |
it_MimeMessage = 241 |
dtSearch 6.40 and earlier file parser for .eml files |
it_SingleByteText = 242 |
Single-byte text, encoding automatically detected |
it_MBoxArchive = 243 |
Email archive conforming to the MBOX standard (dtSearch versions 7.50 and earlier) |
it_FilteredBinaryUnicode = 244 |
Binary file filtered using Unicode Filtering |
it_ZIP_zlib = 245 |
ZIP file parsed using zlib |
it_OutlookMsgFile = 246 |
Microsoft Outlook .MSG file |
it_TreepadHjtFile = 247 |
TreePad file (HJT format in TreePad 6 and earlier) |
it_PfsProfessionalWrite = 248 |
PFS Professional Write file |
it_FilteredBinaryUnicodeStream = 249 |
Binary file filtered using Unicode Filtering, not split into segments |
it_DocFile = 250 |
Compound document (new parser) |
it_Media = 251 |
Music or video file |
it_NonTextData = 252 |
Data file with no text to index |
it_EML = 253 |
Mime stream handled as a single document |
it_MicrosoftWord = 254 |
Microsoft Word 95 - 2003 (dtSearch versions 6.5 and later) |
it_UnformattedHTML = 256 |
Output format only, for generating a synopsis that is HTML-encoded but that does not include formatting such as font settings, paragraph breaks, etc. |
it_DatabaseRecord2 = 257 |
Database record (rendered as HTML) |
it_Excel2003Xml = 258 |
Microsoft Excel 2003 XML format |
it_Word2003Xml = 259 |
Microsoft Word 2003 XML format |
it_OpenOfficeDocument = 260 |
OpenOffice versions 1, 2, and 3 documents, spreadsheets, and presentations (*.sxc, *.sxd, *.sxi, *.sxw, *.sxg, *.stc, *.sti, *.stw, *.stm, *.odt, *.ott, *.odg, *.otg, *.odp, *.otp, *.ods, *.ots, *.odf) (includes OASIS Open Document Format for Office Applications) |
it_CSV = 261 |
Comma-separated values file |
it_MicrosoftAccess = 262 |
Microsoft Access database |
it_XBase = 263 |
XBase database |
it_OutlookExpressMessageStore = 264 |
Outlook Express dbx archive (versions 7.67 and earlier) |
it_IFilter = 265 |
File type processed using installed IFilter |
it_Gzip = 266 |
Archive compressed with gzip |
it_Excel4 = 267 |
Excel version 4 |
it_Word12 = 268 |
Word 2007 |
it_Excel12 = 269 |
Excel 2007 |
it_PowerPoint12 = 270 |
PowerPoint 2007 |
it_TNEF = 271 |
Transport-neutral encapsulation format |
it_XPS = 272 |
XML Paper Specification (Metro) |
it_WMF = 273 |
Windows Metafile Format (Win16) |
it_EMF = 274 |
Windows Metafile Format (Win32) |
it_TAR = 275 |
TAR archive |
it_Excel2 = 277 |
Excel Version 2 |
it_Excel3 = 278 |
Excel version 3 |
it_MBoxArchive2 = 279 |
Email archive conforming to the MBOX standard (dtSearch versions 7.51 and later) |
it_Lotus123 = 280 |
Lotus 123 spreadsheet |
it_MsWorksWps4 = 281 |
Microsoft Works WPS versions 4 and 5 |
it_MsWorksWps6 = 282 |
Microsoft Works WPS versions 6, 7, 8, and 9 |
it_QuattroPro = 283 |
Quattro Pro 9 and newer |
it_QuattroPro8 = 284 |
Quattro Pro 8 and older |
it_OutlookMsgAsContainer = 285 |
Outlook .MSG file processed as a container |
it_MimeContainer = 286 |
MIME-encoded message, processed as a container |
it_PdfWithAttachments = 287 |
PDF file with attachments |
it_MicrosoftAccess2 = 288 |
Microsoft Access (parsed directly, not via ODBC or the Jet Engine) |
it_FlashSWF = 289 |
Flash SWF |
it_RAR = 290 |
RAR archive |
it_NoContent = 291 |
File indexed with all content ignored (see dtsoIndexBinaryNoContent) |
it_Excel12xlsb = 292 |
Excel 2007 XLSB format |
it_XfaForm = 293 |
XFA form |
it_MifFile = 294 |
Framemaker MIF file |
it_WordForWindows2 = 295 |
Word for Windows 2 |
it_ASF = 296 |
ASF file |
it_MP3 = 297 |
MP3 file |
it_QuickTime = 298 |
QuickTime file |
it_MP4 = 299 |
MP4 file |
it_M4A = 300 |
M4A file |
it_MPG = 301 |
MPEG file |
it_JPEG = 302 |
JPEG file |
it_TIFF = 303 |
TIFF file |
it_MDI = 304 |
MDI image file |
it_GIF = 305 |
GIF image file |
it_PNG = 306 |
PNG image file |
it_CAB = 308 |
CAB archive |
it_dtSearchIndex = 309 |
dtSearch index file |
it_HtmlHelp = 310 |
HTML Help CHM file |
it_TrueTypeFont = 311 |
TrueType TTF file |
it_WAV = 312 |
WAV sound file |
it_BMP = 313 |
BMP image file |
it_AVI = 314 |
AVI file |
it_Visio = 315 |
Visio file |
it_Ichitaro = 316 |
Ichitaro word processor file (versions 8 through 2011) |
it_SolidWorks = 317 |
SolidWorks file |
it_Unigraphics = 318 |
Unigraphics file (docfile format) |
it_DWG = 319 |
DWG CAD file |
it_DWF = 320 |
DWF CAD file |
it_DXF = 321 |
DXF CAD file |
it_VisioXml = 322 |
Visio XML file |
it_WordForWindows1 = 323 |
Word for Windows 1 |
it_OutlookPst = 324 |
Outlook PST message store |
it_MicrosoftOfficeThemeData = 325 |
Microsoft Office .thmx file with theme data |
it_MIDI = 326 |
MIDI file |
it_OutlookExpressMessageStore2 = 327 |
Outlook Express dbx archive |
it_PowerPoint4 = 328 |
PowerPoint 4 |
it_PowerPoint95 = 329 |
PowerPoint 95 |
it_PowerPoint3 = 330 |
PowerPoint 3 |
it_Ichitaro5 = 331 |
Ichitaro versions 5, 6, 7 |
it_OleDataMso = 332 |
oledata.mso file |
it_CsvAsReport = 333 |
CSV file parsed as report (like a spreadsheet) instead of a database |
it_CsvAsDocument = 334 |
CSV file parsed as a single file listing all records |
it_MicrosoftAccessAsDocument = 335 |
Access database parsed as a single file listing all records |
it_XBaseAsDocument = 336 |
XBase file parsed as a single file listing all records |
it_OneNote2003 = 337 |
not supported |
it_OneNote2007 = 338 |
OneNote 2007 |
it_OneNote2010 = 339 |
OneNote 2010, 2013, and 2016 |
it_JpegXR = 340 |
Windows Media Photo/HDPhoto/*.wdp |
it_WindowsExecutable = 341 |
Windows .exe or .dll |
it_ElfExecutable = 342 |
ELF format executable |
it_ICalendar = 343 |
ICalendar (*.ics) file |
it_MicrosoftPublisher = 344 |
Microsoft Publisher file |
it_PhotoshopImage = 346 |
Photoshop Image (*.psd) |
it_Cals = 347 |
CALS metadata format described in MIL-STD-1840C |
it_iWork2009 = 348 |
IWork 2009 |
it_iWork2009Pages = 349 |
IWork 2009 Pages document |
it_iWork2009Numbers = 350 |
IWork 2009 Numbers spreadsheet |
it_iWork2009Keynote = 351 |
IWork 2009 Keynote presentation |
it_Visio2013 = 352 |
Visio 2013 document |
it_SASF = 353 |
SASF call center audio file |
it_Unigraphics2 = 354 |
Unigraphics file (#UGC format) |
it_OneNoteOnline = 355 |
OneNote variant generated by Microsoft online services |
it_7z = 359 |
7-zip archive (not supported) |
Group
Remarks
Because some older file parsers are still supported for backward compatibility, in a few cases there may be more than one TypeId for a file format. Not all file formats listed are supported for content extraction or indexing. For a current list of supported file types, see: http://support.dtsearch.com/faq/dts0103.htm