For those interested, here's the final IDL for the typelib for CHSDET. What impressed me (after re-discovering Matt Curland's EditTLB tool) was that I can put structures into a typelib, and VB handles them as if I'd declared them in the source code.
I've written to the author of ChsDet and perhaps this will end up as part of the standard distro.
// Generated .IDL file (by the OLE/COM Object Viewer)
//
// typelib filename: chsdet.tlb
[
uuid(316A83D7-8BF4-490E-BDDE-75EBC332C355),
version(1.0),
helpstring("Charset Detector - as the name says - is a stand alone executable module for automatic charset detection of a given text.\r\n\t\r\nIt can be useful for internationalisation support in multilingual applications such as web-script editors or Unicode editors.\r\n\t\r\nGiven input buffer will be analysed to guess used encoding. The result can be used as control parameter for charset conversation procedure.\r\n\t\r\nCharset Detector can be compiled (and hopefully used) for MS Windows (as dll - dynamic link library) or Linux.\r\n\t\r\nBased on Mozilla's i18n component - http://www.mozilla.org/projects/intl/. \r\n\r\nCharset Detector is open source project and distributed under Lesser GPL.\r\nSee the GNU Lesser General Public License for more details - http://www.opensource.org/licenses/lgpl-license.php\r\n\r\nNikolaj Yakowlew \xFFFFFFA9 2006-2008 \r\nTypeLib by Bruce M. Axtens, 2008.")
]
library CHSDET
{
// TLib : // Forward declare all types defined in this typelib
[
dllname("CHSDET.dll"),
version(1.0),
helpstring("Functions in CHSDET.DLL")
]
module CHSDETFunctions {
[entry(0x60000000), helpstring("Returns rAbout record (qv)")]
void _stdcall GetAbout([in, out] rAbout* AboutRec);
[entry(0x60000001), helpstring("Reset detector. Prepares for new analysis.")]
void _stdcall Reset();
[entry(0x60000002), helpstring("Analyse given buffer of specified length.
Return value is of eHandleDataErrors, either
NS_ERROR_OUT_OF_MEMORY (Unable to create internal objects) or NS_OK.
Function can be called more that one time to continue guessing. Charset Detector remembers last state until Reset called.")]
void _stdcall HandleData(
[in] BSTR aBuf,
[in] short aLen,
[out, retval] short* retVal);
[entry(0x60000003), helpstring("Returns either TRUE (Charset Detector is sure about text encoding.) or FALSE.
NB: If input buffer is smaller then 1K, Charset Detector returns FALSE.")]
void _stdcall IsDone([out, retval] short* retVal);
[entry(0x60000004), helpstring("Signal data end. If Charset Detector hasn't sure result (IsDone = FALSE) the best guessed encoding will be set as result.")]
void _stdcall DataEnd();
[entry(0x60000005), helpstring("Returns guessed charset as rCharsetInfo record")]
void _stdcall GetDetectedCharset([out, retval] rCharsetInfo* retVal);
[entry(0x60000006), helpstring("Returns all supported charsets in form "0x0A Name - CodePage"")]
void _stdcall GetKnownCharsets(
[in, out] long* sList,
[out, retval] long* retVal);
[entry(0x60000007), helpstring("Return eBOMKind value matching byte order mark (if any) of input data.")]
void _stdcall GetDetectedBOM([out, retval] eBOMKind* retVal);
[entry(0x60000008), helpstring("Remove CodePage from consideration as a possible match")]
void _stdcall DisableCharsetCP([in] long CodePage);
};
typedef [uuid(91694067-30AB-44A9-A210-F5602935475F)]
struct tagrAbout {
long lMajor;
long lMinor;
long lRelease;
long sAbout;
} rAbout;
typedef [uuid(3C8B7420-D40B-458B-8DE8-9B3D28607396)]
enum {
BOM_Not_Found = 0,
BOM_UCS4_BE = 1,
BOM_UCS4_LE = 2,
BOM_UCS4_2143 = 3,
BOM_UCS4_3412 = 4,
BOM_UTF16_BE = 5,
BOM_UTF16_LE = 6,
BOM_UTF8 = 7
} eBOMKind;
typedef [uuid(9B231DEF-93FB-440D-B06B-D760AECE09D0)]
struct tagrCharsetInfo {
long Name;
short CodePage;
long Language;
} rCharsetInfo;
typedef enum {
NS_OK = 0,
NS_ERROR_OUT_OF_MEMORY = -2147024882
} eHandleDataErrors;
};