comparison matroskadec.c @ 3692:e8f67b6063c3 libavformat

misc spelling/grammar fixes

3691:b91cad3c97e8

/*
 * Matroska file demuxer
 * Copyright (c) 2003-2008 The ffmpeg Project
 *
 * 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

 * @file matroskadec.c
 * Matroska file demuxer
 * by Ronald Bultje <[e-mail]>
 * with a little help from Moritz Bunkus <[e-mail]>
 * totally reworked by Aurelien Jacobs <[e-mail]>
 * Specs available on the matroska project page: http://www.matroska.org/.
 */

#include "avformat.h"
/* For codec_get_id(). */
#include "riff.h"

} MatroskaLevel;

typedef struct {
    AVFormatContext *ctx;

    /* ebml stuff */
    int num_levels;
    MatroskaLevel levels[EBML_MAX_DEPTH];
    int level_up;

    uint64_t time_scale;

    EbmlList seekhead;

    /* byte position of the segment inside the stream */
    offset_t segment_start;

    /* The packet queue. */
    AVPacket **packets;
    int num_packets;

    int done;
    int has_cluster_id;

    { MATROSKA_ID_CLUSTER,        EBML_NEST, 0, 0, {.n=matroska_cluster} },
    { 0 }
};

/*
 * Return: whether we reached the end of a level in the hierarchy or not
 */
static int ebml_level_end(MatroskaDemuxContext *matroska)
{
    ByteIOContext *pb = matroska->ctx->pb;
    offset_t pos = url_ftell(pb);

 * Read: an "EBML number", which is defined as a variable-length
 * array of bytes. The first byte indicates the length by giving a
 * number of 0-bits followed by a one. The position of the first
 * "one" bit inside the first byte indicates the length of this
 * number.
 * Returns: num. of bytes read. < 0 on error.
 */
static int ebml_read_num(MatroskaDemuxContext *matroska, ByteIOContext *pb,
                         int max_size, uint64_t *number)
{
    int len_mask = 0x80, read = 1, n = 1;
    int64_t total = 0;

    /* the first byte tells us the length in bytes - get_byte() can normally
     * return 0, but since that's not a valid first ebmlID byte, we can
     * use it safely here to catch EOS. */
    if (!(total = get_byte(pb))) {
        /* we might encounter EOS here */
        if (!url_feof(pb)) {

    int n = 0;

    if (size < 1 || size > 8)
        return AVERROR_INVALIDDATA;

    /* big-endian ordening; build up number */
    *num = 0;
    while (n++ < size)
        *num = (*num << 8) | get_byte(pb);

    return 0;

 * 0 is success, < 0 is failure.
 */
static int ebml_read_ascii(ByteIOContext *pb, int size, char **str)
{
    av_free(*str);
    /* ebml strings are usually not 0-terminated, so we allocate one
     * byte more, read the string and NULL-terminate it ourselves. */
    if (!(*str = av_malloc(size + 1)))
        return AVERROR(ENOMEM);
    if (get_buffer(pb, (uint8_t *) *str, size) != size) {
        av_free(*str);

    return 0;
}

/*
 * Read signed/unsigned "EBML" numbers.
 * Return: number of bytes processed, < 0 on error.
 */
static int matroska_ebmlnum_uint(MatroskaDemuxContext *matroska,
                                 uint8_t *data, uint32_t size, uint64_t *num)
{
    ByteIOContext pb;

{
    uint64_t total = 0;
    int len_mask = 0x80, size = 1, n = 1;
    char probe_data[] = "matroska";

    /* ebml header? */
    if (AV_RB32(p->buf) != EBML_ID_HEADER)
        return 0;

    /* length of header */
    total = p->buf[4];

      return 0;
    total &= (len_mask - 1);
    while (n < size)
        total = (total << 8) | p->buf[4 + n++];

    /* does the probe data contain the whole header? */
    if (p->buf_size < 4 + size + total)
      return 0;

    /* the header must contain the document type 'matroska'. For now,
     * we don't parse the whole header but simply check for the
     * availability of that array of characters inside the header.
     * Not fully fool-proof, but good enough. */
    for (n = 4+size; n <= 4+size+total-(sizeof(probe_data)-1); n++)
        if (!memcmp(p->buf+n, probe_data, sizeof(probe_data)-1))

        /* seek */
        if (url_fseek(matroska->ctx->pb, offset, SEEK_SET) != offset)
            continue;

        /* we don't want to lose our seekhead level, so we add
         * a dummy. This is a crude hack. */
        if (matroska->num_levels == EBML_MAX_DEPTH) {
            av_log(matroska->ctx, AV_LOG_INFO,
                   "Max EBML element depth (%d) reached, "
                   "cannot parse further.\n", EBML_MAX_DEPTH);

            laces = 1;
            lace_size = av_mallocz(sizeof(int));
            lace_size[0] = size;
            break;

        case 0x1: /* xiph lacing */
        case 0x2: /* fixed-size lacing */
        case 0x3: /* EBML lacing */
            assert(size>0); // size <=3 is checked before size-=3 above
            laces = (*data) + 1;
            data += 1;
            size -= 1;
            lace_size = av_mallocz(laces * sizeof(int));

            switch ((flags & 0x06) >> 1) {
                case 0x1: /* xiph lacing */ {
                    uint8_t temp;
                    uint32_t total = 0;
                    for (n = 0; res == 0 && n < laces - 1; n++) {
                        while (1) {
                            if (size == 0) {

    MatroskaCluster cluster = { 0 };
    EbmlList *blocks_list;
    MatroskaBlock *blocks;
    int i, res;
    if (matroska->has_cluster_id){
        /* For the first cluster we parse, it's ID was already read as
           part of matroska_read_header(), so don't read it again */
        res = ebml_parse_id(matroska, matroska_clusters,
                            MATROSKA_ID_CLUSTER, &cluster);
        matroska->has_cluster_id = 0;
    } else

3692:e8f67b6063c3

/*
 * Matroska file demuxer
 * Copyright (c) 2003-2008 The FFmpeg Project
 *
 * 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

 * @file matroskadec.c
 * Matroska file demuxer
 * by Ronald Bultje <[e-mail]>
 * with a little help from Moritz Bunkus <[e-mail]>
 * totally reworked by Aurelien Jacobs <[e-mail]>
 * Specs available on the Matroska project page: http://www.matroska.org/.
 */

#include "avformat.h"
/* For codec_get_id(). */
#include "riff.h"

} MatroskaLevel;

typedef struct {
    AVFormatContext *ctx;

    /* EBML stuff */
    int num_levels;
    MatroskaLevel levels[EBML_MAX_DEPTH];
    int level_up;

    uint64_t time_scale;

    EbmlList seekhead;

    /* byte position of the segment inside the stream */
    offset_t segment_start;

    /* the packet queue */
    AVPacket **packets;
    int num_packets;

    int done;
    int has_cluster_id;

    { MATROSKA_ID_CLUSTER,        EBML_NEST, 0, 0, {.n=matroska_cluster} },
    { 0 }
};

/*
 * Return: Whether we reached the end of a level in the hierarchy or not.
 */
static int ebml_level_end(MatroskaDemuxContext *matroska)
{
    ByteIOContext *pb = matroska->ctx->pb;
    offset_t pos = url_ftell(pb);

 * Read: an "EBML number", which is defined as a variable-length
 * array of bytes. The first byte indicates the length by giving a
 * number of 0-bits followed by a one. The position of the first
 * "one" bit inside the first byte indicates the length of this
 * number.
 * Returns: number of bytes read, < 0 on error
 */
static int ebml_read_num(MatroskaDemuxContext *matroska, ByteIOContext *pb,
                         int max_size, uint64_t *number)
{
    int len_mask = 0x80, read = 1, n = 1;
    int64_t total = 0;

    /* The first byte tells us the length in bytes - get_byte() can normally
     * return 0, but since that's not a valid first ebmlID byte, we can
     * use it safely here to catch EOS. */
    if (!(total = get_byte(pb))) {
        /* we might encounter EOS here */
        if (!url_feof(pb)) {

    int n = 0;

    if (size < 1 || size > 8)
        return AVERROR_INVALIDDATA;

    /* big-endian ordering; build up number */
    *num = 0;
    while (n++ < size)
        *num = (*num << 8) | get_byte(pb);

    return 0;

 * 0 is success, < 0 is failure.
 */
static int ebml_read_ascii(ByteIOContext *pb, int size, char **str)
{
    av_free(*str);
    /* EBML strings are usually not 0-terminated, so we allocate one
     * byte more, read the string and NULL-terminate it ourselves. */
    if (!(*str = av_malloc(size + 1)))
        return AVERROR(ENOMEM);
    if (get_buffer(pb, (uint8_t *) *str, size) != size) {
        av_free(*str);

    return 0;
}

/*
 * Read signed/unsigned "EBML" numbers.
 * Return: number of bytes processed, < 0 on error
 */
static int matroska_ebmlnum_uint(MatroskaDemuxContext *matroska,
                                 uint8_t *data, uint32_t size, uint64_t *num)
{
    ByteIOContext pb;

{
    uint64_t total = 0;
    int len_mask = 0x80, size = 1, n = 1;
    char probe_data[] = "matroska";

    /* EBML header? */
    if (AV_RB32(p->buf) != EBML_ID_HEADER)
        return 0;

    /* length of header */
    total = p->buf[4];

      return 0;
    total &= (len_mask - 1);
    while (n < size)
        total = (total << 8) | p->buf[4 + n++];

    /* Does the probe data contain the whole header? */
    if (p->buf_size < 4 + size + total)
      return 0;

    /* The header must contain the document type 'matroska'. For now,
     * we don't parse the whole header but simply check for the
     * availability of that array of characters inside the header.
     * Not fully fool-proof, but good enough. */
    for (n = 4+size; n <= 4+size+total-(sizeof(probe_data)-1); n++)
        if (!memcmp(p->buf+n, probe_data, sizeof(probe_data)-1))

        /* seek */
        if (url_fseek(matroska->ctx->pb, offset, SEEK_SET) != offset)
            continue;

        /* We don't want to lose our seekhead level, so we add
         * a dummy. This is a crude hack. */
        if (matroska->num_levels == EBML_MAX_DEPTH) {
            av_log(matroska->ctx, AV_LOG_INFO,
                   "Max EBML element depth (%d) reached, "
                   "cannot parse further.\n", EBML_MAX_DEPTH);

            laces = 1;
            lace_size = av_mallocz(sizeof(int));
            lace_size[0] = size;
            break;

        case 0x1: /* Xiph lacing */
        case 0x2: /* fixed-size lacing */
        case 0x3: /* EBML lacing */
            assert(size>0); // size <=3 is checked before size-=3 above
            laces = (*data) + 1;
            data += 1;
            size -= 1;
            lace_size = av_mallocz(laces * sizeof(int));

            switch ((flags & 0x06) >> 1) {
                case 0x1: /* Xiph lacing */ {
                    uint8_t temp;
                    uint32_t total = 0;
                    for (n = 0; res == 0 && n < laces - 1; n++) {
                        while (1) {
                            if (size == 0) {

    MatroskaCluster cluster = { 0 };
    EbmlList *blocks_list;
    MatroskaBlock *blocks;
    int i, res;
    if (matroska->has_cluster_id){
        /* For the first cluster we parse, its ID was already read as
           part of matroska_read_header(), so don't read it again */
        res = ebml_parse_id(matroska, matroska_clusters,
                            MATROSKA_ID_CLUSTER, &cluster);
        matroska->has_cluster_id = 0;
    } else