detect_handledata3
Detecting character set and measuring accuracy of charset
Snopsys
#include <chardet.h>
short chardet_handledata (Detect ** handle, const char * inbuf, DetectObj ** outbuf);
short chardet_handledata_r (Detect ** handle, const char * inbuf, size_t inlen, DetectObj ** outbuf);
Overview
Storing charset and accuracy of inbuf to outbuf
The detect_handledata API is deprecated becase this api is not binary safe. Use or replace to detect_handledata_r api.
Arguments:
handle-
Detecthandle resource that allocated bydetect_initapi.
inbuf-
input string for detecting
inlen-
length of input string for detecting
outbuf-
Stroing inforamtion of
inbuf.The structure ofoutbufis follows.typedef struct DetectObject { char * encoding; float confidence; } DetectObj;The
outbufvariable is must initialized bydetect_obj_initAPI before calling this detect api.
Return values
Returns following condition as case by case.
|
Detecting success |
|---|---|
|
Detection failure |
|
Don't initializing |
|
Occuring out of memory at internal API |
Examples
#include <chardet.h>
int main (void) {
Detect * d;
DetectObj * obj;
int i, arrayNum;
char *str[] = {
"this is ascii",
"이건 euc-kr 입니다."
};
arrayNum = sizeof (str) / sizeof (str[0]);
if ( (d = detect_init ()) == NULL ) {
fprintf (stderr, "chardet handle initialize failed\n");
return CHARDET_MEM_ALLOCATED_FAIL;
}
for ( i=0; i<arrayNum; i++ ) {
detect_reset (&d);
if ( (obj = detect_obj_init ()) == NULL ) {
fprintf (stderr, "Memory Allocation failed\n");
return CHARDET_MEM_ALLOCATED_FAIL;
}
//switch (detect_handledata (&d, str[i], &obj))
switch (detect_handledata (&d, str[i], strlen(str[i]), &obj))
{
case CHARDET_OUT_OF_MEMORY :
fprintf (stderr, "On handle processing, occured out of memory\n");
detect_obj_free (&obj);
return CHARDET_OUT_OF_MEMORY;
case CHARDET_NULL_OBJECT :
fprintf (stderr,
"2st argument of chardet() is must memory allocation "
"with detect_obj_init API\n");
return CHARDET_NULL_OBJECT;
}
# check support obj->bom with CHARDET_BOM_CHECK constant
printf ("encoding: %s, confidence: %f, exists bom: %d\n", obj->encoding, obj->confidence, obj->bom);
detect_obj_free (&obj);
}
detect_destroy (&d);
return 0;
}
Releases
6 releases since Debian 9 (Stretch); the text changed 2 times.