aboutsummaryrefslogtreecommitdiffstats
path: root/doc/examples/transcode_aac.c
blob: 339d65c71cd3c130cbb46a2b60ab5dd06e0d7275 (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
/*
 * This file is part of FFmpeg.
 *
 * FFmpeg is free software; you can redistribute it and/or
 * modify it under the terms of the GNU Lesser General Public
 * License as published by the Free Software Foundation; either
 * version 2.1 of the License, or (at your option) any later version.
 *
 * FFmpeg is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * Lesser General Public License for more details.
 *
 * You should have received a copy of the GNU Lesser General Public
 * License along with FFmpeg; if not, write to the Free Software
 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
 */

/**
 * @file
 * simple audio converter
 *
 * @example transcode_aac.c
 * Convert an input audio file to AAC in an MP4 container using FFmpeg.
 * @author Andreas Unterweger (dustsigns@gmail.com)
 */

#include <stdio.h>

#include "libavformat/avformat.h"
#include "libavformat/avio.h"

#include "libavcodec/avcodec.h"

#include "libavutil/audio_fifo.h"
#include "libavutil/avassert.h"
#include "libavutil/avstring.h"
#include "libavutil/frame.h"
#include "libavutil/opt.h"

#include "libswresample/swresample.h"

/** The output bit rate in kbit/s */
#define OUTPUT_BIT_RATE 96000
/** The number of output channels */
#define OUTPUT_CHANNELS 2

/**
 * Convert an error code into a text message.
 * @param error Error code to be converted
 * @return Corresponding error text (not thread-safe)
 */
static const char *get_error_text(const int error)
{
    static char error_buffer[255];
    av_strerror(error, error_buffer, sizeof(error_buffer));
    return error_buffer;
}

/** Open an input file and the required decoder. */
static int open_input_file(const char *filename,
                           AVFormatContext **input_format_context,
                           AVCodecContext **input_codec_context)
{
    AVCodec *input_codec;
    int error;

    /** Open the input file to read from it. */
    if ((error = avformat_open_input(input_format_context, filename, NULL,
                                     NULL)) < 0) {
        fprintf(stderr, "Could not open input file '%s' (error '%s')\n",
                filename, get_error_text(error));
        *input_format_context = NULL;
        return error;
    }

    /** Get information on the input file (number of streams etc.). */
    if ((error = avformat_find_stream_info(*input_format_context, NULL)) < 0) {
        fprintf(stderr, "Could not open find stream info (error '%s')\n",
                get_error_text(error));
        avformat_close_input(input_format_context);
        return error;
    }

    /** Make sure that there is only one stream in the input file. */
    if ((*input_format_context)->nb_streams != 1) {
        fprintf(stderr, "Expected one audio input stream, but found %d\n",
                (*input_format_context)->nb_streams);
        avformat_close_input(input_format_context);
        return AVERROR_EXIT;
    }

    /** Find a decoder for the audio stream. */
    if (!(input_codec = avcodec_find_decoder((*input_format_context)->streams[0]->codec->codec_id))) {
        fprintf(stderr, "Could not find input codec\n");
        avformat_close_input(input_format_context);
        return AVERROR_EXIT;
    }

    /** Open the decoder for the audio stream to use it later. */
    if ((error = avcodec_open2((*input_format_context)->streams[0]->codec,
                               input_codec, NULL)) < 0) {
        fprintf(stderr, "Could not open input codec (error '%s')\n",
                get_error_text(error));
        avformat_close_input(input_format_context);
        return error;
    }

    /** Save the decoder context for easier access later. */
    *input_codec_context = (*input_format_context)->streams[0]->codec;

    return 0;
}

/**
 * Open an output file and the required encoder.
 * Also set some basic encoder parameters.
 * Some of these parameters are based on the input file's parameters.
 */
static int open_output_file(const char *filename,
                            AVCodecContext *input_codec_context,
                            AVFormatContext **output_format_context,
                            AVCodecContext **output_codec_context)
{
    AVIOContext *output_io_context = NULL;
    AVStream *stream               = NULL;
    AVCodec *output_codec          = NULL;
    int error;

    /** Open the output file to write to it. */
    if ((error = avio_open(&output_io_context, filename,
                           AVIO_FLAG_WRITE)) < 0) {
        fprintf(stderr, "Could not open output file '%s' (error '%s')\n",
                filename, get_error_text(error));
        return error;
    }

    /** Create a new format context for the output container format. */
    if (!(*output_format_context = avformat_alloc_context())) {
        fprintf(stderr, "Could not allocate output format context\n");
        return AVERROR(ENOMEM);
    }

    /** Associate the output file (pointer) with the container format context. */
    (*output_format_context)->pb = output_io_context;

    /** Guess the desired container format based on the file extension. */
    if (!((*output_format_context)->oformat = av_guess_format(NULL, filename,
                                                              NULL))) {
        fprintf(stderr, "Could not find output file format\n");
        goto cleanup;
    }

    av_strlcpy((*output_format_context)->filename, filename,
               sizeof((*output_format_context)->filename));

    /** Find the encoder to be used by its name. */
    if (!(output_codec = avcodec_find_encoder(AV_CODEC_ID_AAC))) {
        fprintf(stderr, "Could not find an AAC encoder.\n");
        goto cleanup;
    }

    /** Create a new audio stream in the output file container. */
    if (!(stream = avformat_new_stream(*output_format_context, output_codec))) {
        fprintf(stderr, "Could not create new stream\n");
        error = AVERROR(ENOMEM);
        goto cleanup;
    }

    /** Save the encoder context for easier access later. */
    *output_codec_context = stream->codec;

    /**
     * Set the basic encoder parameters.
     * The input file's sample rate is used to avoid a sample rate conversion.
     */
    (*output_codec_context)->channels       = OUTPUT_CHANNELS;
    (*output_codec_context)->channel_layout = av_get_default_channel_layout(OUTPUT_CHANNELS);
    (*output_codec_context)->sample_rate    = input_codec_context->sample_rate;
    (*output_codec_context)->sample_fmt     = output_codec->sample_fmts[0];
    (*output_codec_context)->bit_rate       = OUTPUT_BIT_RATE;

    /** Allow the use of the experimental AAC encoder */
    (*output_codec_context)->strict_std_compliance = FF_COMPLIANCE_EXPERIMENTAL;

    /** Set the sample rate for the container. */
    stream->time_base.den = input_codec_context->sample_rate;
    stream->time_base.num = 1;

    /**
     * Some container formats (like MP4) require global headers to be present
     * Mark the encoder so that it behaves accordingly.
     */
    if ((*output_format_context)->oformat->flags & AVFMT_GLOBALHEADER)
        (*output_codec_context)->flags |= CODEC_FLAG_GLOBAL_HEADER;

    /** Open the encoder for the audio stream to use it later. */
    if ((error = avcodec_open2(*output_codec_context, output_codec, NULL)) < 0) {
        fprintf(stderr, "Could not open output codec (error '%s')\n",
                get_error_text(error));
        goto cleanup;
    }

    return 0;

cleanup:
    avio_closep(&(*output_format_context)->pb);
    avformat_free_context(*output_format_context);
    *output_format_context = NULL;
    return error < 0 ? error : AVERROR_EXIT;
}

/** Initialize one data packet for reading or writing. */
static void init_packet(AVPacket *packet)
{
    av_init_packet(packet);
    /** Set the packet data and size so that it is recognized as being empty. */
    packet->data = NULL;
    packet->size = 0;
}

/** Initialize one audio frame for reading from the input file */
static int init_input_frame(AVFrame **frame)
{
    if (!(*frame = av_frame_alloc())) {
        fprintf(stderr, "Could not allocate input frame\n");
        return AVERROR(ENOMEM);
    }
    return 0;
}

/**
 * Initialize the audio resampler based on the input and output codec settings.
 * If the input and output sample formats differ, a conversion is required
 * libswresample takes care of this, but requires initialization.
 */
static int init_resampler(AVCodecContext *input_codec_context,
                          AVCodecContext *output_codec_context,
                          SwrContext **resample_context)
{
        int error;

        /**
         * Create a resampler context for the conversion.
         * Set the conversion parameters.
         * Default channel layouts based on the number of channels
         * are assumed for simplicity (they are sometimes not detected
         * properly by the demuxer and/or decoder).
         */
        *resample_context = swr_alloc_set_opts(NULL,
                                              av_get_default_channel_layout(output_codec_context->channels),
                                              output_codec_context->sample_fmt,
                                              output_codec_context->sample_rate,
                                              av_get_default_channel_layout(input_codec_context->channels),
                                              input_codec_context->sample_fmt,
                                              input_codec_context->sample_rate,
                                              0, NULL);
        if (!*resample_context) {
            fprintf(stderr, "Could not allocate resample context\n");
            return AVERROR(ENOMEM);
        }
        /**
        * Perform a sanity check so that the number of converted samples is
        * not greater than the number of samples to be converted.
        * If the sample rates differ, this case has to be handled differently
        */
        av_assert0(output_codec_context->sample_rate == input_codec_context->sample_rate);

        /** Open the resampler with the specified parameters. */
        if ((error = swr_init(*resample_context)) < 0) {
            fprintf(stderr, "Could not open resample context\n");
            swr_free(resample_context);
            return error;
        }
    return 0;
}

/** Initialize a FIFO buffer for the audio samples to be encoded. */
static int init_fifo(AVAudioFifo **fifo, AVCodecContext *output_codec_context)
{
    /** Create the FIFO buffer based on the specified output sample format. */
    if (!(*fifo = av_audio_fifo_alloc(output_codec_context->sample_fmt,
                                      output_codec_context->channels, 1))) {
        fprintf(stderr, "Could not allocate FIFO\n");
        return AVERROR(ENOMEM);
    }
    return 0;
}

/** Write the header of the output file container. */
static int write_output_file_header(AVFormatContext *output_format_context)
{
    int error;
    if ((error = avformat_write_header(output_format_context, NULL)) < 0) {
        fprintf(stderr, "Could not write output file header (error '%s')\n",
                get_error_text(error));
        return error;
    }
    return 0;
}

/** Decode one audio frame from the input file. */
static int decode_audio_frame(AVFrame *frame,
                              AVFormatContext *input_format_context,
                              AVCodecContext *input_codec_context,
                              int *data_present, int *finished)
{
    /** Packet used for temporary storage. */
    AVPacket input_packet;
    int error;
    init_packet(&input_packet);

    /** Read one audio frame from the input file into a temporary packet. */
    if ((error = av_read_frame(input_format_context, &input_packet)) < 0) {
        /** If we are at the end of the file, flush the decoder below. */
        if (error == AVERROR_EOF)
            *finished = 1;
        else {
            fprintf(stderr, "Could not read frame (error '%s')\n",
                    get_error_text(error));
            return error;
        }
    }

    /**
     * Decode the audio frame stored in the temporary packet.
     * The input audio stream decoder is used to do this.
     * If we are at the end of the file, pass an empty packet to the decoder
     * to flush it.
     */
    if ((error = avcodec_decode_audio4(input_codec_context, frame,
                                       data_present, &input_packet)) < 0) {
        fprintf(stderr, "Could not decode frame (error '%s')\n",
                get_error_text(error));
        av_free_packet(&input_packet);
        return error;
    }

    /**
     * If the decoder has not been flushed completely, we are not finished,
     * so that this function has to be called again.
     */
    if (*finished && *data_present)
        *finished = 0;
    av_free_packet(&input_packet);
    return 0;
}

/**
 * Initialize a temporary storage for the specified number of audio samples.
 * The conversion requires temporary storage due to the different format.
 * The number of audio samples to be allocated is specified in frame_size.
 */
static int init_converted_samples(uint8_t ***converted_input_samples,
                                  AVCodecContext *output_codec_context,
                                  int frame_size)
{
    int error;

    /**
     * Allocate as many pointers as there are audio channels.
     * Each pointer will later point to the audio samples of the corresponding
     * channels (although it may be NULL for interleaved formats).
     */
    if (!(*converted_input_samples = calloc(output_codec_context->channels,
                                            sizeof(**converted_input_samples)))) {
        fprintf(stderr, "Could not allocate converted input sample pointers\n");
        return AVERROR(ENOMEM);
    }

    /**
     * Allocate memory for the samples of all channels in one consecutive
     * block for convenience.
     */
    if ((error = av_samples_alloc(*converted_input_samples, NULL,
                                  output_codec_context->channels,
                                  frame_size,
                                  output_codec_context->sample_fmt, 0)) < 0) {
        fprintf(stderr,
                "Could not allocate converted input samples (error '%s')\n",
                get_error_text(error));
        av_freep(&(*converted_input_samples)[0]);
        free(*converted_input_samples);
        return error;
    }
    return 0;
}

/**
 * Convert the input audio samples into the output sample format.
 * The conversion happens on a per-frame basis, the size of which is specified
 * by frame_size.
 */
static int convert_samples(const uint8_t **input_data,
                           uint8_t **converted_data, const int frame_size,
                           SwrContext *resample_context)
{
    int error;

    /** Convert the samples using the resampler. */
    if ((error = swr_convert(resample_context,
                             converted_data, frame_size,
                             input_data    , frame_size)) < 0) {
        fprintf(stderr, "Could not convert input samples (error '%s')\n",
                get_error_text(error));
        return error;
    }

    return 0;
}

/** Add converted input audio samples to the FIFO buffer for later processing. */
static int add_samples_to_fifo(AVAudioFifo *fifo,
                               uint8_t **converted_input_samples,
                               const int frame_size)
{
    int error;

    /**
     * Make the FIFO as large as it needs to be to hold both,
     * the old and the new samples.
     */
    if ((error = av_audio_fifo_realloc(fifo, av_audio_fifo_size(fifo) + frame_size)) < 0) {
        fprintf(stderr, "Could not reallocate FIFO\n");
        return error;
    }

    /** Store the new samples in the FIFO buffer. */
    if (av_audio_fifo_write(fifo, (void **)converted_input_samples,
                            frame_size) < frame_size) {
        fprintf(stderr, "Could not write data to FIFO\n");
        return AVERROR_EXIT;
    }
    return 0;
}

/**
 * Read one audio frame from the input file, decodes, converts and stores
 * it in the FIFO buffer.
 */
static int read_decode_convert_and_store(AVAudioFifo *fifo,
                                         AVFormatContext *input_format_context,
                                         AVCodecContext *input_codec_context,
                                         AVCodecContext *output_codec_context,
                                         SwrContext *resampler_context,
                                         int *finished)
{
    /** Temporary storage of the input samples of the frame read from the file. */
    AVFrame *input_frame = NULL;
    /** Temporary storage for the converted input samples. */
    uint8_t **converted_input_samples = NULL;
    int data_present;
    int ret = AVERROR_EXIT;

    /** Initialize temporary storage for one input frame. */
    if (init_input_frame(&input_frame))
        goto cleanup;
    /** Decode one frame worth of audio samples. */
    if (decode_audio_frame(input_frame, input_format_context,
                           input_codec_context, &data_present, finished))
        goto cleanup;
    /**
     * If we are at the end of the file and there are no more samples
     * in the decoder which are delayed, we are actually finished.
     * This must not be treated as an error.
     */
    if (*finished && !data_present) {
        ret = 0;
        goto cleanup;
    }
    /** If there is decoded data, convert and store it */
    if (data_present) {
        /** Initialize the temporary storage for the converted input samples. */
        if (init_converted_samples(&converted_input_samples, output_codec_context,
                                   input_frame->nb_samples))
            goto cleanup;

        /**
         * Convert the input samples to the desired output sample format.
         * This requires a temporary storage provided by converted_input_samples.
         */
        if (convert_samples((const uint8_t**)input_frame->extended_data, converted_input_samples,
                            input_frame->nb_samples, resampler_context))
            goto cleanup;

        /** Add the converted input samples to the FIFO buffer for later processing. */
        if (add_samples_to_fifo(fifo, converted_input_samples,
                                input_frame->nb_samples))
            goto cleanup;
        ret = 0;
    }
    ret = 0;

cleanup:
    if (converted_input_samples) {
        av_freep(&converted_input_samples[0]);
        free(converted_input_samples);
    }
    av_frame_free(&input_frame);

    return ret;
}

/**
 * Initialize one input frame for writing to the output file.
 * The frame will be exactly frame_size samples large.
 */
static int init_output_frame(AVFrame **frame,
                             AVCodecContext *output_codec_context,
                             int frame_size)
{
    int error;

    /** Create a new frame to store the audio samples. */
    if (!(*frame = av_frame_alloc())) {
        fprintf(stderr, "Could not allocate output frame\n");
        return AVERROR_EXIT;
    }

    /**
     * Set the frame's parameters, especially its size and format.
     * av_frame_get_buffer needs this to allocate memory for the
     * audio samples of the frame.
     * Default channel layouts based on the number of channels
     * are assumed for simplicity.
     */
    (*frame)->nb_samples     = frame_size;
    (*frame)->channel_layout = output_codec_context->channel_layout;
    (*frame)->format         = output_codec_context->sample_fmt;
    (*frame)->sample_rate    = output_codec_context->sample_rate;

    /**
     * Allocate the samples of the created frame. This call will make
     * sure that the audio frame can hold as many samples as specified.
     */
    if ((error = av_frame_get_buffer(*frame, 0)) < 0) {
        fprintf(stderr, "Could allocate output frame samples (error '%s')\n",
                get_error_text(error));
        av_frame_free(frame);
        return error;
    }

    return 0;
}

/** Global timestamp for the audio frames */
static int64_t pts = 0;

/** Encode one frame worth of audio to the output file. */
static int encode_audio_frame(AVFrame *frame,
                              AVFormatContext *output_format_context,
                              AVCodecContext *output_codec_context,
                              int *data_present)
{
    /** Packet used for temporary storage. */
    AVPacket output_packet;
    int error;
    init_packet(&output_packet);

    /** Set a timestamp based on the sample rate for the container. */
    if (frame) {
        frame->pts = pts;
        pts += frame->nb_samples;
    }

    /**
     * Encode the audio frame and store it in the temporary packet.
     * The output audio stream encoder is used to do this.
     */
    if ((error = avcodec_encode_audio2(output_codec_context, &output_packet,
                                       frame, data_present)) < 0) {
        fprintf(stderr, "Could not encode frame (error '%s')\n",
                get_error_text(error));
        av_free_packet(&output_packet);
        return error;
    }

    /** Write one audio frame from the temporary packet to the output file. */
    if (*data_present) {
        if ((error = av_write_frame(output_format_context, &output_packet)) < 0) {
            fprintf(stderr, "Could not write frame (error '%s')\n",
                    get_error_text(error));
            av_free_packet(&output_packet);
            return error;
        }

        av_free_packet(&output_packet);
    }

    return 0;
}

/**
 * Load one audio frame from the FIFO buffer, encode and write it to the
 * output file.
 */
static int load_encode_and_write(AVAudioFifo *fifo,
                                 AVFormatContext *output_format_context,
                                 AVCodecContext *output_codec_context)
{
    /** Temporary storage of the output samples of the frame written to the file. */
    AVFrame *output_frame;
    /**
     * Use the maximum number of possible samples per frame.
     * If there is less than the maximum possible frame size in the FIFO
     * buffer use this number. Otherwise, use the maximum possible frame size
     */
    const int frame_size = FFMIN(av_audio_fifo_size(fifo),
                                 output_codec_context->frame_size);
    int data_written;

    /** Initialize temporary storage for one output frame. */
    if (init_output_frame(&output_frame, output_codec_context, frame_size))
        return AVERROR_EXIT;

    /**
     * Read as many samples from the FIFO buffer as required to fill the frame.
     * The samples are stored in the frame temporarily.
     */
    if (av_audio_fifo_read(fifo, (void **)output_frame->data, frame_size) < frame_size) {
        fprintf(stderr, "Could not read data from FIFO\n");
        av_frame_free(&output_frame);
        return AVERROR_EXIT;
    }

    /** Encode one frame worth of audio samples. */
    if (encode_audio_frame(output_frame, output_format_context,
                           output_codec_context, &data_written)) {
        av_frame_free(&output_frame);
        return AVERROR_EXIT;
    }
    av_frame_free(&output_frame);
    return 0;
}

/** Write the trailer of the output file container. */
static int write_output_file_trailer(AVFormatContext *output_format_context)
{
    int error;
    if ((error = av_write_trailer(output_format_context)) < 0) {
        fprintf(stderr, "Could not write output file trailer (error '%s')\n",
                get_error_text(error));
        return error;
    }
    return 0;
}

/** Convert an audio file to an AAC file in an MP4 container. */
int main(int argc, char **argv)
{
    AVFormatContext *input_format_context = NULL, *output_format_context = NULL;
    AVCodecContext *input_codec_context = NULL, *output_codec_context = NULL;
    SwrContext *resample_context = NULL;
    AVAudioFifo *fifo = NULL;
    int ret = AVERROR_EXIT;

    if (argc < 3) {
        fprintf(stderr, "Usage: %s <input file> <output file>\n", argv[0]);
        exit(1);
    }

    /** Register all codecs and formats so that they can be used. */
    av_register_all();
    /** Open the input file for reading. */
    if (open_input_file(argv[1], &input_format_context,
                        &input_codec_context))
        goto cleanup;
    /** Open the output file for writing. */
    if (open_output_file(argv[2], input_codec_context,
                         &output_format_context, &output_codec_context))
        goto cleanup;
    /** Initialize the resampler to be able to convert audio sample formats. */
    if (init_resampler(input_codec_context, output_codec_context,
                       &resample_context))
        goto cleanup;
    /** Initialize the FIFO buffer to store audio samples to be encoded. */
    if (init_fifo(&fifo, output_codec_context))
        goto cleanup;
    /** Write the header of the output file container. */
    if (write_output_file_header(output_format_context))
        goto cleanup;

    /**
     * Loop as long as we have input samples to read or output samples
     * to write; abort as soon as we have neither.
     */
    while (1) {
        /** Use the encoder's desired frame size for processing. */
        const int output_frame_size = output_codec_context->frame_size;
        int finished                = 0;

        /**
         * Make sure that there is one frame worth of samples in the FIFO
         * buffer so that the encoder can do its work.
         * Since the decoder's and the encoder's frame size may differ, we
         * need to FIFO buffer to store as many frames worth of input samples
         * that they make up at least one frame worth of output samples.
         */
        while (av_audio_fifo_size(fifo) < output_frame_size) {
            /**
             * Decode one frame worth of audio samples, convert it to the
             * output sample format and put it into the FIFO buffer.
             */
            if (read_decode_convert_and_store(fifo, input_format_context,
                                              input_codec_context,
                                              output_codec_context,
                                              resample_context, &finished))
                goto cleanup;

            /**
             * If we are at the end of the input file, we continue
             * encoding the remaining audio samples to the output file.
             */
            if (finished)
                break;
        }

        /**
         * If we have enough samples for the encoder, we encode them.
         * At the end of the file, we pass the remaining samples to
         * the encoder.
         */
        while (av_audio_fifo_size(fifo) >= output_frame_size ||
               (finished && av_audio_fifo_size(fifo) > 0))
            /**
             * Take one frame worth of audio samples from the FIFO buffer,
             * encode it and write it to the output file.
             */
            if (load_encode_and_write(fifo, output_format_context,
                                      output_codec_context))
                goto cleanup;

        /**
         * If we are at the end of the input file and have encoded
         * all remaining samples, we can exit this loop and finish.
         */
        if (finished) {
            int data_written;
            /** Flush the encoder as it may have delayed frames. */
            do {
                if (encode_audio_frame(NULL, output_format_context,
                                       output_codec_context, &data_written))
                    goto cleanup;
            } while (data_written);
            break;
        }
    }

    /** Write the trailer of the output file container. */
    if (write_output_file_trailer(output_format_context))
        goto cleanup;
    ret = 0;

cleanup:
    if (fifo)
        av_audio_fifo_free(fifo);
    swr_free(&resample_context);
    if (output_codec_context)
        avcodec_close(output_codec_context);
    if (output_format_context) {
        avio_closep(&output_format_context->pb);
        avformat_free_context(output_format_context);
    }
    if (input_codec_context)
        avcodec_close(input_codec_context);
    if (input_format_context)
        avformat_close_input(&input_format_context);

    return ret;
}