FFT of samples from portAudio stream - macos

Beginner here, (OSX 10.9.5, Xcode 6)
I have a portAudio stream that gives out noise. Now I'd like to get those random values generated in the callback and run them through an fftw plan. As far as I know, fftw needs to be executed in the main. So how can I show the numbers from the callback to the main? I have a feeling it has something to do with pointers but that's a very uneducated guess...
I'm having some difficulty with joining two different libraries. Little help would be greatly appreciated, thank you!
#include <stdio.h>
#include <math.h>
#include <stdlib.h>
#include "portaudio.h"
#include "fftw3.h"
#define NUM_SECONDS (1)
#define SAMPLE_RATE (44100)
typedef struct
{
float left_phase;
float right_phase;
}
paTestData;
static int patestCallback( const void *inputBuffer, void *outputBuffer,
unsigned long framesPerBuffer,
const PaStreamCallbackTimeInfo* timeInfo,
PaStreamCallbackFlags statusFlags,
void *userData )
{
/* Cast data passed through stream to our structure. */
paTestData *data = (paTestData*)userData;
float *out = (float*)outputBuffer;
unsigned int i;
(void) inputBuffer; /* Prevent unused variable warning. */
for( i=0; i<framesPerBuffer; i++ )
{
*out++ = data->left_phase; /* left */
*out++ = data->right_phase; /* right */
/* Generate random value that ranges between -1.0 and 1.0. */
data->left_phase = (((float)rand()/(float)(RAND_MAX)) * 2) - 1 ;
data->right_phase = (((float)rand()/(float)(RAND_MAX)) * 2) - 1 ;
printf("%f, %f\n", data->left_phase, data->right_phase);
}
return 0;
}
/*******************************************************************/
static paTestData data;
int main(void);
int main(void)
{
PaStream *stream;
PaError err;
printf("PortAudio Test: output noise.\n");
/* Initialize our data for use by callback. */
data.left_phase = data.right_phase = 0.0;
/* Initialize library before making any other calls. */
err = Pa_Initialize();
if( err != paNoError ) goto error;
/* Open an audio I/O stream. */
err = Pa_OpenDefaultStream( &stream,
0, /* no input channels */
2, /* stereo output */
paFloat32, /* 32 bit floating point output */
SAMPLE_RATE,
512, /* frames per buffer */
patestCallback,
&data );
if( err != paNoError ) goto error;
err = Pa_StartStream( stream );
if( err != paNoError ) goto error;
/* Sleep for several seconds. */
Pa_Sleep(NUM_SECONDS*1000);
err = Pa_StopStream( stream );
if( err != paNoError ) goto error;
err = Pa_CloseStream( stream );
if( err != paNoError ) goto error;
Pa_Terminate();
printf("Test finished.\n");
return err;
error:
Pa_Terminate();
fprintf( stderr, "An error occured while using the portaudio stream\n" );
fprintf( stderr, "Error number: %d\n", err );
fprintf( stderr, "Error message: %s\n", Pa_GetErrorText( err ) );
return err;
}

You could try running the stream in "blocking write" mode instead of using the callback. To use this mode, you pass NULL for the streamCallback parameter of Pa_OpenDefaultStream and then you continually call Pa_WriteStream in a loop. The call will block as necessary. Something like this pseudo code:
Pa_OpenStream(&stream, 0, 2, paFloat32, SAMPLE_RATE, 512, NULL, NULL);
Pa_StartStream(stream);
float interleavedSamples[2*512];
for (int i = 0 ; i < SAMPLE_RATE/512 ; i++) // approx 1 second
{
GenerateNoise(&interleavedSamples, 2, 512, &data);
RunFft(interleavedSamples, ...);
PaWriteStream(stream, interleavedSamples, 512);
}

Related

How to produce same mfcc result as librosa using aubio?

I am trying to calculate Mfcc feature in C++. And I found Aubio (https://github.com/aubio/aubio) but I cannot produce same result as Librosa of Python (this is important).
Librosa code:
X, sample_rate = sf.read(file_name, dtype='float32')
mfccs = librosa.feature.mfcc(y=X, sr=sample_rate, n_mfcc=40)
Aubio code:
#include "utils.h"
#include "parse_args.h"
#include <stdlib.h>
aubio_pvoc_t *pv; // a phase vocoder
cvec_t *fftgrain; // outputs a spectrum
aubio_mfcc_t * mfcc; // which the mfcc will process
fvec_t * mfcc_out; // to get the output coefficients
uint_t n_filters = 128;
uint_t n_coefs = 40;
void process_block (fvec_t *ibuf, fvec_t *obuf)
{
fvec_zeros(obuf);
//compute mag spectrum
aubio_pvoc_do (pv, ibuf, fftgrain);
//compute mfccs
aubio_mfcc_do(mfcc, fftgrain, mfcc_out);
}
void process_print (void)
{
/* output times in selected format */
print_time (blocks * hop_size);
outmsg ("\t");
/* output extracted mfcc */
fvec_print (mfcc_out);
}
int main(int argc, char **argv) {
int ret = 0;
// change some default params
buffer_size = 2048;
hop_size = 512;
examples_common_init(argc,argv);
verbmsg ("using source: %s at %dHz\n", source_uri, samplerate);
verbmsg ("buffer_size: %d, ", buffer_size);
verbmsg ("hop_size: %d\n", hop_size);
pv = new_aubio_pvoc (buffer_size, hop_size);
fftgrain = new_cvec (buffer_size);
mfcc = new_aubio_mfcc(buffer_size, n_filters, n_coefs, samplerate);
mfcc_out = new_fvec(n_coefs);
if (pv == NULL || fftgrain == NULL || mfcc == NULL || mfcc_out == NULL) {
ret = 1;
goto beach;
}
examples_common_process(process_block, process_print);
printf("\nlen=%u\n", mfcc_out->length);
del_aubio_pvoc (pv);
del_cvec (fftgrain);
del_aubio_mfcc(mfcc);
del_fvec(mfcc_out);
beach:
examples_common_del();
return ret;
}
Please help to obtain same result of Librosa or suggest any C++ library do this well.
Thanks
This might be what you are looking for: C Speech Features
The library is a complete port of python_speech_features to C and according to the documentation, you should be able to use it in a C++ projects. The results will not be the same of Librosa, here is why but you should be able to work with them.

How to chunk shell script input by time, not by size?

In a bash script I am using a many-producer single-consumer pattern. Producers are background processes writing lines into a fifo (via GNU Parallel). The consumer reads all lines from the fifo, then sorts, filters, and prints the formatted result to stdout.
However, it could take a long time until the full result is available. Producers are usually fast on the first few results but then would slow down. Here I am more interested to see chunks of data every few seconds, each sorted and filtered individually.
mkfifo fifo
parallel ... >"$fifo" &
while chunk=$(read with timeout 5s and at most 10s <"$fifo"); do
process "$chunk"
done
The loop would run until all producers are done and all input is read. Each chunk is read until there has been no new data for 5s, or until 10s have passed since the chunk was started. A chunk may also be empty if there was no new data for 10s.
I tried to make it work like this:
output=$(mktemp)
while true; do
wasTimeout=0 interruptAt=$(( $(date '+%s') + 10 ))
while true; do
IFS= read -r -t5 <>"${fifo}"
rc="$?"
if [[ "${rc}" -gt 0 ]]; then
[[ "${rc}" -gt 128 ]] && wasTimeout=1
break
fi
echo "$REPLY" >>"${output}"
if [[ $(date '+%s') -ge "${interruptAt}" ]]; then
wasTimeout=1
break
fi
done
echo '---' >>"${output}"
[[ "${wasTimeout}" -eq 0 ]] && break
done
Tried some variations of this. In the form above it reads the first chunk but then loops forever. If I use <"${fifo}" (no read/write as above) it blocks after the first chunk. Maybe all of this could be simplified with buffer and/or stdbuf? But both of them define blocks by size, not by time.
This is not a trivial problem to resolve. As I hinted, a C program (or a program in some programming language other than the shell) is probably the best solution. Some of the complicating factors are:
Reading with timeouts.
If data arrives soon enough, the timeout changes.
Different systems have different sets of interval timing functions:
alarm() is likely available everywhere, but has only 1-second resolution which is liable to accumulated rounding errors. (Compile this version with make UFLAGS=-DUSE_ALARM; on macOS, use make UFLAGS=-DUSE_ALARM LDLIB2=.)
setitimer()
uses microsecond timing and the struct timeval type. (Compile this version with make UFLAGS=-DUSE_SETITIMER; on macOS, compile with make UFLAGS=-DUSE_SETITIMER LDLIB2=.)
timer_create() and
timer_settime() etc use the modern nanosecond type struct timespec. This is available on Linux; it is not available on macOS 10.14.5 Mojave or earlier. (Compile this version with make; it won't work on macOS.)
The program usage message is:
$ chunker79 -h
Usage: chunker79 [-hvV][-c chunk][-d delay][-f file]
-c chunk Maximum time to wait for data in a chunk (default 10)
-d delay Maximum delay after line read (default: 5)
-f file Read from file instead of standard input
-h Print this help message and exit
-v Verbose mode: print timing information to stderr
-V Print version information and exit
$
This code is available in my SOQ (Stack Overflow Questions) repository on GitHub as file chunker79.c in the src/so-5631-4784 sub-directory. You will need some of the support code from the src/libsoq directory too.
/*
#(#)File: chunker79.c
#(#)Purpose: Chunk Reader for SO 5631-4784
#(#)Author: J Leffler
#(#)Copyright: (C) JLSS 2019
*/
/*TABSTOP=4*/
/*
** Problem specification from the Stack Overflow question
**
** In a bash script I am using a many-producer single-consumer pattern.
** Producers are background processes writing lines into a fifo (via GNU
** Parallel). The consumer reads all lines from the fifo, then sorts,
** filters, and prints the formatted result to stdout.
**
** However, it could take a long time until the full result is
** available. Producers are usually fast on the first few results but
** then would slow down. Here I am more interested to see chunks of
** data every few seconds, each sorted and filtered individually.
**
** mkfifo fifo
** parallel ... >"$fifo" &
** while chunk=$(read with timeout 5s and at most 10s <"$fifo"); do
** process "$chunk"
** done
**
** The loop would run until all producers are done and all input is
** read. Each chunk is read until there has been no new data for 5s, or
** until 10s have passed since the chunk was started. A chunk may also
** be empty if there was no new data for 10s.
*/
/*
** Analysis
**
** 1. If no data arrives at all for 10 seconds, then the program should
** terminate producing no output. This timeout is controlled by the
** value of time_chunk in the code.
** 2. If data arrives more or less consistently, then the collection
** should continue for 10s and then finish. This timeout is also
** controlled by the value of time_chunk in the code.
** 3. If a line of data arrives before 5 seconds have elapsed, and no
** more arrives for 5 seconds, then the collection should finish.
** (If the first line arrives after 5 seconds and no more arrives
** for more than 5 seconds, then the 10 second timeout cuts in.)
** This timeout is controlled by the value of time_delay in the code.
** 4. This means that we want two separate timers at work:
** - Chunk timer (started when the program starts).
** - Delay timer (started each time a line is read).
**
** It doesn't matter which timer goes off, but further timer signals
** should be ignored. External signals will confuse things; tough!
**
** -- Using alarm(2) is tricky because it provides only one time, not two.
** -- Using getitimer(2), setitimer(2) uses obsolescent POSIX functions,
** but these are available on macOS.
** -- Using timer_create(2), timer_destroy(2), timer_settime(2),
** timer_gettime(2) uses current POSIX function but is not available
** on macOS.
*/
#include "posixver.h"
#include "stderr.h"
#include "timespec_io.h"
#include <assert.h>
#include <signal.h>
#include <stdbool.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/uio.h>
#include <time.h>
#include <unistd.h>
#ifdef USE_SETITIMER
#include "timeval_math.h"
#include "timeval_io.h"
#include <sys/time.h>
#endif /* USE_SETITIMER */
static const char optstr[] = "hvVc:d:f:";
static const char usestr[] = "[-hvV][-c chunk][-d delay][-f file]";
static const char hlpstr[] =
" -c chunk Maximum time to wait for data in a chunk (default 10)\n"
" -d delay Maximum delay after line read (default: 5)\n"
" -f file Read from file instead of standard input\n"
" -h Print this help message and exit\n"
" -v Verbose mode: print timing information to stderr\n"
" -V Print version information and exit\n"
;
static struct timespec time_delay = { .tv_sec = 5, .tv_nsec = 0 };
static struct timespec time_chunk = { .tv_sec = 10, .tv_nsec = 0 };
static struct timespec time_start;
static bool verbose = false;
static void set_chunk_timeout(void);
static void set_delay_timeout(void);
static void cancel_timeout(void);
static void alarm_handler(int signum);
// Using signal() manages to set SA_RESTART on a Mac.
// This is allowed by standard C and POSIX, sadly.
// signal(SIGALRM, alarm_handler);
#if defined(USE_ALARM)
static void set_chunk_timeout(void)
{
if (verbose)
err_remark("-->> %s()\n", __func__);
alarm(time_chunk.tv_sec);
struct sigaction sa;
sa.sa_handler = alarm_handler;
sigemptyset(&sa.sa_mask);
sa.sa_flags = 0;
sigaction(SIGALRM, &sa, NULL);
if (verbose)
err_remark("<<-- %s()\n", __func__);
}
static void set_delay_timeout(void)
{
if (verbose)
err_remark("-->> %s()\n", __func__);
unsigned time_left = alarm(0);
if (time_left > time_delay.tv_sec)
alarm(time_delay.tv_sec);
else
alarm(time_left);
if (verbose)
err_remark("<<-- %s()\n", __func__);
}
static void cancel_timeout(void)
{
if (verbose)
err_remark("-->> %s()\n", __func__);
alarm(0);
signal(SIGALRM, SIG_IGN);
if (verbose)
err_remark("<<-- %s()\n", __func__);
}
#elif defined(USE_SETITIMER)
static inline struct timeval cvt_timespec_to_timeval(struct timespec ts)
{
return (struct timeval){ .tv_sec = ts.tv_sec, .tv_usec = ts.tv_nsec / 1000 };
}
static void set_chunk_timeout(void)
{
if (verbose)
err_remark("-->> %s()\n", __func__);
struct itimerval tv_new = { { 0, 0 }, { 0, 0 } };
tv_new.it_value = cvt_timespec_to_timeval(time_chunk);
struct itimerval tv_old;
if (setitimer(ITIMER_REAL, &tv_new, &tv_old) != 0)
err_syserr("failed to set interval timer: ");
struct sigaction sa;
sa.sa_handler = alarm_handler;
sigemptyset(&sa.sa_mask);
sa.sa_flags = 0;
sigaction(SIGALRM, &sa, NULL);
if (verbose)
err_remark("<<-- %s()\n", __func__);
}
static void set_delay_timeout(void)
{
if (verbose)
err_remark("-->> %s()\n", __func__);
struct itimerval tv_until;
if (getitimer(ITIMER_REAL, &tv_until) != 0)
err_syserr("failed to set interval timer: ");
struct timeval tv_delay = cvt_timespec_to_timeval(time_delay);
if (verbose)
{
char buff1[32];
fmt_timeval(&tv_delay, 6, buff1, sizeof(buff1));
char buff2[32];
fmt_timeval(&tv_until.it_value, 6, buff2, sizeof(buff2));
err_remark("---- %s(): delay %s, left %s\n", __func__, buff1, buff2);
}
if (cmp_timeval(tv_until.it_value, tv_delay) <= 0)
{
if (verbose)
err_remark("---- %s(): no need for delay timer\n", __func__);
}
else
{
struct itimerval tv_new = { { 0, 0 }, { 0, 0 } };
tv_new.it_value = cvt_timespec_to_timeval(time_delay);
struct itimerval tv_old;
if (setitimer(ITIMER_REAL, &tv_new, &tv_old) != 0)
err_syserr("failed to set interval timer: ");
if (verbose)
err_remark("---- %s(): set delay timer\n", __func__);
}
if (verbose)
err_remark("<<-- %s()\n", __func__);
}
static void cancel_timeout(void)
{
if (verbose)
err_remark("-->> %s()\n", __func__);
struct itimerval tv_new =
{
.it_value = { .tv_sec = 0, .tv_usec = 0 },
.it_interval = { .tv_sec = 0, .tv_usec = 0 },
};
struct itimerval tv_old;
if (setitimer(ITIMER_REAL, &tv_new, &tv_old) != 0)
err_syserr("failed to set interval timer: ");
if (verbose)
err_remark("<<-- %s()\n", __func__);
}
#else /* USE_TIMER_GETTIME */
#include "timespec_math.h"
static timer_t t0 = { 0 };
static void set_chunk_timeout(void)
{
if (verbose)
err_remark("-->> %s()\n", __func__);
struct sigevent ev =
{
.sigev_notify = SIGEV_SIGNAL,
.sigev_signo = SIGALRM,
.sigev_value.sival_int = 0,
.sigev_notify_function = 0,
.sigev_notify_attributes = 0,
};
if (timer_create(CLOCK_REALTIME, &ev, &t0) < 0)
err_syserr("failed to create a timer: ");
struct itimerspec it =
{
.it_interval = { .tv_sec = 0, .tv_nsec = 0 },
.it_value = time_chunk,
};
struct itimerspec ot;
if (timer_settime(t0, 0, &it, &ot) != 0)
err_syserr("failed to activate timer: ");
struct sigaction sa;
sa.sa_handler = alarm_handler;
sigemptyset(&sa.sa_mask);
sa.sa_flags = 0;
sigaction(SIGALRM, &sa, NULL);
if (verbose)
err_remark("<<-- %s()\n", __func__);
}
static void set_delay_timeout(void)
{
if (verbose)
err_remark("-->> %s()\n", __func__);
struct itimerspec time_until;
if (timer_gettime(t0, &time_until) != 0)
err_syserr("failed to set per-process timer: ");
char buff1[32];
fmt_timespec(&time_delay, 6, buff1, sizeof(buff1));
char buff2[32];
fmt_timespec(&time_until.it_value, 6, buff2, sizeof(buff2));
err_remark("---- %s(): delay %s, left %s\n", __func__, buff1, buff2);
if (cmp_timespec(time_until.it_value, time_delay) <= 0)
{
if (verbose)
err_remark("---- %s(): no need for delay timer\n", __func__);
}
else
{
struct itimerspec time_new =
{
.it_interval = { .tv_sec = 0, .tv_nsec = 0 },
.it_value = time_delay,
};
struct itimerspec time_old;
if (timer_settime(t0, 0, &time_new, &time_old) != 0)
err_syserr("failed to set per-process timer: ");
if (verbose)
err_remark("---- %s(): set delay timer\n", __func__);
}
if (verbose)
err_remark("<<-- %s()\n", __func__);
}
static void cancel_timeout(void)
{
if (timer_delete(t0) != 0)
err_syserr("failed to delete timer: ");
}
#endif /* Timing mode */
/* Writing to stderr via err_remark() is not officially supported */
static void alarm_handler(int signum)
{
assert(signum == SIGALRM);
if (verbose)
err_remark("---- %s(): signal %d\n", __func__, signum);
}
static void read_chunks(FILE *fp)
{
size_t num_data = 0;
size_t max_data = 0;
struct iovec *data = 0;
size_t buflen = 0;
char *buffer = 0;
ssize_t length;
size_t chunk_len = 0;
clock_gettime(CLOCK_REALTIME, &time_start);
set_chunk_timeout();
while ((length = getline(&buffer, &buflen, fp)) != -1)
{
if (num_data >= max_data)
{
size_t new_size = (num_data * 2) + 2;
void *newspace = realloc(data, new_size * sizeof(data[0]));
if (newspace == 0)
err_syserr("failed to allocate %zu bytes data: ", new_size * sizeof(data[0]));
data = newspace;
max_data = new_size;
}
data[num_data].iov_base = buffer;
data[num_data].iov_len = length;
num_data++;
if (verbose)
err_remark("Received line %zu\n", num_data);
chunk_len += length;
buffer = 0;
buflen = 0;
set_delay_timeout();
}
cancel_timeout();
if (chunk_len > 0)
{
if ((length = writev(STDOUT_FILENO, data, num_data)) < 0)
err_syserr("failed to write %zu bytes to standard output: ", chunk_len);
else if ((size_t)length != chunk_len)
err_error("failed to write %zu bytes to standard output "
"(short write of %zu bytes)\n", chunk_len, (size_t)length);
}
if (verbose)
err_remark("---- %s(): data written (%zu bytes)\n", __func__, length);
for (size_t i = 0; i < num_data; i++)
free(data[i].iov_base);
free(data);
free(buffer);
}
int main(int argc, char **argv)
{
const char *name = "(standard input)";
FILE *fp = stdin;
err_setarg0(argv[0]);
err_setlogopts(ERR_MICRO);
int opt;
while ((opt = getopt(argc, argv, optstr)) != -1)
{
switch (opt)
{
case 'c':
if (scn_timespec(optarg, &time_chunk) != 0)
err_error("Failed to convert '%s' into a time value\n", optarg);
break;
case 'd':
if (scn_timespec(optarg, &time_delay) != 0)
err_error("Failed to convert '%s' into a time value\n", optarg);
break;
case 'f':
if ((fp = fopen(optarg, "r")) == 0)
err_syserr("Failed to open file '%s' for reading: ", optarg);
name = optarg;
break;
case 'h':
err_help(usestr, hlpstr);
/*NOTREACHED*/
case 'v':
verbose = true;
break;
case 'V':
err_version("CHUNKER79", &"#(#)$Revision$ ($Date$)"[4]);
/*NOTREACHED*/
default:
err_usage(usestr);
/*NOTREACHED*/
}
}
if (optind != argc)
err_usage(usestr);
if (verbose)
{
err_remark("chunk: %3lld.%09ld\n", (long long)time_chunk.tv_sec, time_chunk.tv_nsec);
err_remark("delay: %3lld.%09ld\n", (long long)time_delay.tv_sec, time_delay.tv_nsec);
err_remark("file: %s\n", name);
}
read_chunks(fp);
return 0;
}
My SOQ repository also has a script gen-data.sh which makes use of some custom programs to generate a data stream such as this (the seed value is written to standard error, not standard output):
$ gen-data.sh
# Seed: 1313715286
2019-06-03 23:04:16.653: Zunmieoprri Rdviqymcho 5878 2017-03-29 03:59:15 Udransnadioiaeamprirteo
2019-06-03 23:04:18.525: Rndflseoevhgs Etlaevieripeoetrnwkn 9500 2015-12-18 10:49:15 Ebyrcoebeezatiagpleieoefyc
2019-06-03 23:04:20.526: Nrzsuiakrooab Nbvliinfqidbujoops 1974 2020-05-13 08:05:14 Lgithearril
2019-06-03 23:04:21.777: Eeagop Aieneose 6533 2016-11-06 22:51:58 Aoejlwebbssroncmeovtuuueigraa
2019-06-03 23:04:23.876: Izirdoeektau Atesltiybysaclee 4557 2020-09-13 02:24:46 Igrooiaauiwtna
2019-06-03 23:04:26.145: Yhioit Eamrexuabagsaraiw 9703 2014-09-13 07:44:12 Dyiiienglolqopnrbneerltnmsdn
^C
$
When fed into chunker79 with default options, I get output like:
$ gen-data.sh | chunker79
# Seed: 722907235
2019-06-03 23:06:20.570: Aluaezkgiebeewal Oyvahee 1022 2015-08-12 07:45:54 Weuababeeduklleym
2019-06-03 23:06:24.100: Gmujvoyevihvoilc Negeiiuvleem 8196 2015-08-29 21:15:15 Nztkrvsadeoeagjgoyotvertavedi
$
If you analyze the time intervals (look at the first two fields in the output lines), that output meets the specification. A still more detailed analysis is shown by:
$ timecmd -mr -- gen-data.sh | timecmd -mr -- chunker79
2019-06-03 23:09:14.246 [PID 57159] gen-data.sh
2019-06-03 23:09:14.246 [PID 57160] chunker79
# Seed: -1077610201
2019-06-03 23:09:14.269: Woreio Rdtpimvoscttbyhxim 7893 2017-03-12 12:46:57 Uywaietirkekes
2019-06-03 23:09:16.939: Uigaba Nzoxdeuisofai 3630 2017-11-16 09:28:59 Jnsncgoesycsevdscugoathusaoq
2019-06-03 23:09:17.845: Sscreua Aloaoonnsuur 5163 2016-08-13 19:47:15 Injhsiifqovbnyeooiimitaaoir
2019-06-03 23:09:19.272 [PID 57160; status 0x0000] - 5.026s - chunker79
2019-06-03 23:09:22.084 [PID 57159; status 0x8D00] - 7.838s - gen-data.sh
$
There is a noticeable pause in this setup between when the output from chunker79 appears and when gen-data.sh completes. That's due to Bash waiting on all processes in the pipeline to complete, and gen-data.sh doesn't complete until the next time it writes to the pipe after the message that finishes chunker79. This is an artefact of this test setup; it wouldn't be a factor in the shell script outlined in the question.
I would consider writing a safe multi-threaded program with queues.
I know Java better, but there might be more modern suitable languages like Go and Kotlin.
Something like this:
#!/usr/bin/perl
$timeout = 3;
while(<STDIN>) {
# Make sure there is some input
push #out,$_;
eval {
local $SIG{ALRM} = sub { die };
alarm $timeout;
while(<STDIN>) {
alarm $timeout;
push #out,$_;
}
alarm 0;
};
system "echo","process",#out;
}
GNU Parallel 20200122 introduced --blocktimeout (--bt):
find ~ | parallel -j3 --bt 2s --pipe wc
This works like normal GNU Parallel except if it takes > 2 seconds to fill a block. In that case the block read so far is simply passed to wc (unless it is empty).
It has a slightly odd startup behaviour: You have to wait 3*2s (jobslots*timeout) before the output stabilizes, and you get an output at least every 2s.

show location of biggest memory leak on Windows

My program has big leaks. I am using the debug heap by putting this in my stdafx.h:
#define _CRTDBG_MAP_ALLOC
#include <stdlib.h>
#include <crtdbg.h>
Then I'm capturing all the leaks in a text file by putting this code just before exit:
HANDLE hLogFile;
hLogFile = CreateFile( "T:\\MyProject\\heap.txt", GENERIC_WRITE,
FILE_SHARE_WRITE, NULL, CREATE_ALWAYS,
FILE_ATTRIBUTE_NORMAL, NULL);
_CrtSetReportMode(_CRT_WARN, _CRTDBG_MODE_FILE);
_CrtSetReportFile(_CRT_WARN, hLogFile);
_CrtDumpMemoryLeaks();
exit( EXIT_SUCCESS );
However even then the data is leak by leak, which is far too low-level information.
Stepping into _CrtDumpMemoryLeaks(), the code is actually easy to follow. I wrote my own function that summarizes the data, reporting bytes leaked for each line of code and sorting by leak size.
However it requires a static variable inside dbgheap.c in order to work. I've tried to make a version of dbgheap.c that doesn't have these as static symbols and tried to make a mini-DLL out of it (but it complains about a missing symbol I can't find anywhere in the MSFT code, _heap_regions). Instead what I've settled on is putting this code right before the code above calling _CrtDumpMemoryLeaks():
// Put a breakpoint here; step INTO the malloc, then in variable watch
// window evaluate: _CrtDumpMemoryLeakSummary( _pFirstBlock );
void* pvAccess = malloc(1);
And in turn this is the code for the _CrtDumpMemoryLeakSummary function:
#define _CRTBLD
#include "C:\Program Files\Microsoft Visual Studio 9.0\VC\crt\src\dbgint.h"
typedef struct {
const char* pszFileName;
int iLine;
int iTotal;
} Location_T;
#define MAX_SUMMARY 5000
static Location_T aloc[ MAX_SUMMARY ];
static int CompareFn( const void* pv1, const void* pv2 ) {
Location_T* ploc1 = (Location_T*) pv1;
Location_T* ploc2 = (Location_T*) pv2;
if ( ploc1->iTotal > ploc2->iTotal )
return -1;
if ( ploc1->iTotal < ploc2->iTotal )
return 1;
return 0;
}
void _CrtDumpMemoryLeakSummary( _CrtMemBlockHeader* pHead )
{
int iLocUsed = 0, iUnbucketed = 0, i;
for ( /*pHead = _pFirstBlock */;
pHead != NULL && /* pHead != _pLastBlock && */ iLocUsed < MAX_SUMMARY;
pHead = pHead->pBlockHeaderNext ) {
const char* pszFileName = pHead->szFileName ? pHead->szFileName : "<UNKNOWN>";
// Linear search is theoretically horribly slow but saves trouble of
// avoiding heap use while measuring heap use.
int i;
for ( i = 0; i < iLocUsed; i++ ) {
// To speed search, compare line number (fast) before strcmp() (slow).
// If szFileName were guaranteed to be __LINE__ then we could take advantage
// of __LINE__ always having the same address for any given file, and just
// compare pointers rather than using strcmp(). However, szFileName could
// be something else.
if ( pHead->nLine == aloc[i].iLine &&
strcmp( pszFileName, aloc[i].pszFileName ) == 0 ) {
aloc[i].iTotal += pHead->nDataSize;
break;
}
}
if ( i == iLocUsed ) {
aloc[i].pszFileName = pszFileName;
aloc[i].iLine = pHead->nLine;
aloc[i].iTotal = pHead->nDataSize;
iLocUsed++;
}
}
if ( iLocUsed == MAX_SUMMARY )
_RPT0( _CRT_WARN, "\n\n\nARNING: RAN OUT OF BUCKETS! DATA INCOMPLETE!!!\n\n\n" );
qsort( aloc, iLocUsed, sizeof( Location_T ), CompareFn );
_RPT0(_CRT_WARN, "SUMMARY OF LEAKS\n" );
_RPT0(_CRT_WARN, "\n" );
_RPT0(_CRT_WARN, "bytes leaked code location\n" );
_RPT0(_CRT_WARN, "------------ -------------\n" );
for ( i = 0; i < iLocUsed; i++ )
_RPT3(_CRT_WARN, "%12d %s:%d\n", aloc[i].iTotal, aloc[i].pszFileName, aloc[i].iLine );
}
It produces output like this:
SUMMARY OF LEAKS
bytes leaked code location
------------ -------------
912997 <UNKNOWN>:0
377800 ..\MyProject\foo.h:205
358400 ..\MyProject\A.cpp:959
333672 ..\MyProject\B.cpp:359
8192 f:\dd\vctools\crt_bld\self_x86\crt\src\_getbuf.c:58
6144 ..\MyProject\Interpreter.cpp:196
4608 ..\MyProject\Interpreter.cpp:254
3634 f:\dd\vctools\crt_bld\self_x86\crt\src\stdenvp.c:126
2960 ..\MyProject\C.cpp:947
2089 ..\MyProject\D.cpp:1031
2048 f:\dd\vctools\crt_bld\self_x86\crt\src\ioinit.c:136
2048 f:\dd\vctools\crt_bld\self_x86\crt\src\_file.c:133

FSInit() - "CE_BAD_PARTITION"

I am using a PIC18F26K80 and an XC8 compiler. I am trying to initialise an SD card and create a file. I have simply formatted the SD card on Windows to have a "FAT32" file system and an "Allocation unit size" of 512 bytes. The capacity of the SD card is 2GB. I am using the MDD library from the MLA Legacy version. My main is the following:
FSFILE * file;
char sendBuffer[22] = "This is test string 1";
//**************************************************
// main function
//**************************************************
int main()
{
initIO();
LATBbits.LATB0 = 0;
// Initialise SPI and SD-card
while ( !MDD_MediaDetect() );
// Initialize the device
while ( !FSInit() );
// Initialize
#ifdef ALLOW_WRITES
// Create a new file
file = FSfopenpgm ( "FILE.TXT", "w" );
if ( file == NULL )
while(1);
// Write 21 1-byte objects from sendBuffer into the file
if ( FSfwrite ( (void *) sendBuffer, 1, 21, file ) != 21 )
while(1);
// Close the file
if ( FSfclose ( file ) )
while(1);
#endif
LATBbits.LATB0 = 1; //LED
while(1) {}
return (0);
}
The program gets stuck inside the function "FSInit()" and the error I get from the function is "CE_BAD_PARTITION", which means "The boot record is bad".
The "initIO()" function is the following:
//==============================================================================
// void initIO( void );
//==============================================================================
// Sets the pins on the PIC to input or output and determines the speed of the
// internal oscilaltor
// input: none
// return: none
//==============================================================================
void initIO()
{
OSCCON = 0x75; // Clock speed = 32MHz (4x8Mhz)
TRISA = 0;
TRISB = 0;
TRISC = 0;
TRISBbits.TRISB0 = 0; //LED
TRISCbits.TRISC3 = 0; // set SCL pin as output
TRISCbits.TRISC4 = 1; // set RC4 pin as input
TRISCbits.TRISC5 = 0;
TRISAbits.TRISA5 = 0;
}

zlib deflate getting Z_DATA_ERROR

I'm trying to deflate and inflate a text file using zlib-1.2.7 with VC++2010.
I used pipe.c as basis and rewrote the main() in order to set the input/output files.
I'm able to deflate any text file but i can't inflate large files without getting a Z_DATA_ERROR (-3).
the inf() and def() are not changed from pipe.c.
Here is my main() :
int main (){
FILE *a, *b, *c;
int ret;
//ZIP
a = fopen("a_data.txt", "r");
b = fopen("b_compressedData.zip", "w");
if(a != NULL && b != NULL){
ret = def(a, b, Z_DEFAULT_COMPRESSION);
printf("%d\n", ret);
if (ret != Z_OK) zerr(ret);
fclose(a);
fclose(b);
}
//UNZIP
b = fopen("b_compressedData.zip", "r");
c = fopen("c_uncompressedData.txt", "w");
if(c != NULL && b != NULL){
ret = inf(b, c);
printf("%d\n", ret);
if (ret != Z_OK) zerr(ret);
fclose(b);
fclose(c);
}
return 0;
}
Here is the inf() function :
int inf(FILE *source, FILE *dest)
{
int ret;
unsigned have;
z_stream strm;
unsigned char in[CHUNK];
unsigned char out[CHUNK];
/* allocate inflate state */
strm.zalloc = Z_NULL;
strm.zfree = Z_NULL;
strm.opaque = Z_NULL;
strm.avail_in = 0;
strm.next_in = Z_NULL;
ret = inflateInit(&strm);
if (ret != Z_OK)
return ret;
/* decompress until deflate stream ends or end of file */
do {
strm.avail_in = fread(in, 1, CHUNK, source);
if (ferror(source)) {
(void)inflateEnd(&strm);
return Z_ERRNO;
}
if (strm.avail_in == 0)
break;
strm.next_in = in;
/* run inflate() on input until output buffer not full */
do {
strm.avail_out = CHUNK;
strm.next_out = out;
ret = inflate(&strm, Z_NO_FLUSH);
assert(ret != Z_STREAM_ERROR); /* state not clobbered */
switch (ret) {
case Z_NEED_DICT:
ret = Z_DATA_ERROR; /* and fall through */
case Z_DATA_ERROR:
case Z_MEM_ERROR:
(void)inflateEnd(&strm);
return ret;
}
have = CHUNK - strm.avail_out;
if (fwrite(out, 1, have, dest) != have || ferror(dest)) {
(void)inflateEnd(&strm);
return Z_ERRNO;
}
} while (strm.avail_out == 0);
/* done when inflate() says it's done */
} while (ret != Z_STREAM_END);
/* clean up and return */
(void)inflateEnd(&strm);
return ret == Z_STREAM_END ? Z_OK : Z_DATA_ERROR;
}
You need to add a "b" in the modes for fopen(), where the b is for binary. E.g. "rb" and "wb". Otherwise on Windows you get end-of-line conversions which mess up binary data.
By the way, you should not call the compressed file .zip since it isn't. zlib writes zlib-formatted data, or if requested gzip-formatted data. zlib does not write zip-formatted data on its own. There is third-party code for writing zip files, such as in the contrib directory of the zlib source distribution, or in libzip.
I use .zz as the suffix for zlib-formatted data. .gz is the suffix for gzip-formatted data.

Resources