Mozilla's Universal Charset Detector C/C++ API

Abstract

Determine the charset of the input data with Mozilla Universal Charset Detection

This project move to GitHUB. After 10 seconds, redirect to GitHUB project page.

Repository https://github.com/Joungkyun/libchardet

Download

This download page is deprecated. Move to https://github.com/Joungkyun/libchardet/releases

libchardet-1.0.6.tar.bz2
1.0.5.tar.bz2
libchardet-1.0.4.tar.bz2
libchardet-1.0.3.tar.bz2
libchardet-1.0.2.tar.bz2
libchardet-1.0.1.tar.bz2
libchardet-1.0.0.tar.bz2

If you want to download with wget, don't use default user-agent of wget! (Use -U option)

Samples

See also test directory of source code

       #include <chardet.h>

       int main (void) {
            DetectObj *obj;

            if ( (obj = detect_obj_init ()) == NULL ) {
                 fprintf (stderr, "Memory Allocation failed\n");
                 return CHARDET_MEM_ALLOCATED_FAIL;
            }

            switch (detect ("안녕하세요", &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;
            }

            printf ("encoding: %s, confidence: %f\n", obj->encoding, obj->confidence);
            detect_obj_free (&obj);

           return 0;
       }

       #include <chardet.h>

       int main (void) {
            Detect    * d;
            DetectObj * obj;

            if ( (d = detect_init ()) == NULL ) {
                 fprintf (stderr, "chardet handle initialize failed\n");
                 return CHARDET_MEM_ALLOCATED_FAIL;
            }

            // for loop
            //detect_reset (&d);

            if ( (obj = detect_obj_init ()) == NULL ) {
                 fprintf (stderr, "Memory Allocation failed\n");
                 return CHARDET_MEM_ALLOCATED_FAIL;
            }

            switch (detect_handledata (&d, "안녕하세요", &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;
            }

            printf ("encoding: %s, confidence: %f\n", obj->encoding, obj->confidence);
            detect_obj_free (&obj);
            detect_destroy (&d);

           return 0;
       }

        Copyright (c) 2015 JoungKyun.Kim <http://oops.org>
        All rights reserved.
        
		This program is under MPL 1.1 or LGPL 2.1

		Original Code is Perl Encode::Detect-1.01 by
			John Gardiner Myers <jgmyers@proofpoint.com>