Hi I noticed a crash issue when I passed the following values: celt_mode_create(96000, 258, &e); CELTMode->mdct.kfft[0] is not initialized after calling?clt_mdct_init() and when?celt_mode_destroy() is called it tries to dereference this value in kiss_fft_free(). -- Bjoern Here's the callstack: !kiss_fft_free(const kiss_fft_state * cfg=0x00000000) ?Line 650 + 0x3 bytes C!clt_mdct_clear(mdct_lookup * l=0x0111bc04) ?Line 103 + 0x10 bytes C!celt_mode_destroy(CELTMode * mode=0x0111bbd8) ?Line 432 + 0xc bytes C!celt_mode_create(int Fs=96000, int frame_size=258, int * error=0x0017fa88) ?Line 413 + 0x9 bytes C
Bjoern Rasmussen wrote:> Hi > I noticed a crash issue when I passed the following values: > celt_mode_create(96000, 258, &e); > CELTMode->mdct.kfft[0] is not initialized after calling clt_mdct_init() and when celt_mode_destroy() is called it tries to dereference this value in kiss_fft_free().CELT no longer supports frame sizes which can't be factored into 2's, 3's, and 5's (and always required at least one 2). 258 has a factor of 43. libcelt doesn't do very good error checking for this.
Hi, CELT only handles frames sizes that are multiples of 2, 3 and 5. That's why what you tried didn't work. That being said, this kind of error should definitely be handled more gracefully :-) Cheers, Jean-Marc Bjoern Rasmussen <bjoern_rasmussen at hotmail.com> a ?crit?:> > Hi > I noticed a crash issue when I passed the following values: > celt_mode_create(96000, 258, &e); > CELTMode->mdct.kfft[0] is not initialized after > calling?clt_mdct_init() and when?celt_mode_destroy() is called it > tries to dereference this value in kiss_fft_free(). > -- Bjoern > Here's the callstack: > !kiss_fft_free(const kiss_fft_state * cfg=0x00000000) ?Line 650 + > 0x3 bytes C!clt_mdct_clear(mdct_lookup * l=0x0111bc04) ?Line 103 + > 0x10 bytes C!celt_mode_destroy(CELTMode * mode=0x0111bbd8) ?Line 432 > + 0xc bytes C!celt_mode_create(int Fs=96000, int frame_size=258, int > * error=0x0017fa88) ?Line 413 + 0x9 bytes C > > > _______________________________________________ > celt-dev mailing list > celt-dev at xiph.org > http://lists.xiph.org/mailman/listinfo/celt-dev > >