版权声明：本文为博主原创文章，未经博主允许不得转载。 https://blog.csdn.net/u011913612/article/details/53482773
上一节我们写了一个简单的程序，它可以把一个视频文件解码成多张图片。我们只是简单的使用的ffmepg提供的api来实现这一过程的，但对api具体的实现过程却一无所知，因此，从这篇博客看是，就逐步分析这些api的内部实现原理。这一节，主要分析avformat_open_input函数的具体实现。
avformat_open_input函数如下：
/**
* Open an input stream and read the header. The codecs are not opened.
* The stream must be closed with avformat_close_input().
*
* @param ps Pointer to user-supplied AVFormatContext (allocated by avformat_alloc_context).
* May be a pointer to NULL, in which case an AVFormatContext is allocated by this
* function and written into ps.
* Note that a user-supplied AVFormatContext will be freed on failure.
* @param url URL of the stream to open.
* @param fmt If non-NULL, this parameter forces a specific input format.
* Otherwise the format is autodetected.
* @param options A dictionary filled with AVFormatContext and demuxer-private options.
* On return this parameter will be destroyed and replaced with a dict containing
* options that were not found. May be NULL.
*
* @return 0 on success, a negative AVERROR on failure.
*
* @note If you want to use custom IO, preallocate the format context and set its pb field.
*/
int avformat_open_input(AVFormatContext **ps, const char *filename,
AVInputFormat *fmt, AVDictionary **options)
{
AVFormatContext *s = *ps;
int i, ret = 0;
AVDictionary *tmp = NULL;
ID3v2ExtraMeta *id3v2_extra_meta = NULL;
if (!s && !(s = avformat_alloc_context()))
return AVERROR(ENOMEM);
if (!s->av_class) {
av_log(NULL, AV_LOG_ERROR, "Input context has not been properly allocated by avformat_alloc_context() and is not NULL either\n");
return AVERROR(EINVAL);
}
if (fmt)
s->iformat = fmt;
if (options)
av_dict_copy(&tmp, *options, 0);
if (s->pb) // must be before any goto fail
s->flags |= AVFMT_FLAG_CUSTOM_IO;
if ((ret = av_opt_set_dict(s, &tmp)) < 0)
goto fail;
if ((ret = init_input(s, filename, &tmp)) < 0)
goto fail;
s->probe_score = ret;
if (!s->protocol_whitelist && s->pb && s->pb->protocol_whitelist) {
s->protocol_whitelist = av_strdup(s->pb->protocol_whitelist);
if (!s->protocol_whitelist) {
ret = AVERROR(ENOMEM);
goto fail;
}
}
if (!s->protocol_blacklist && s->pb && s->pb->protocol_blacklist) {
s->protocol_blacklist = av_strdup(s->pb->protocol_blacklist);
if (!s->protocol_blacklist) {
ret = AVERROR(ENOMEM);
goto fail;
}
}
if (s->format_whitelist && av_match_list(s->iformat->name, s->format_whitelist, ',') <= 0) {
av_log(s, AV_LOG_ERROR, "Format not on whitelist \'%s\'\n", s->format_whitelist);
ret = AVERROR(EINVAL);
goto fail;
}
avio_skip(s->pb, s->skip_initial_bytes);
/* Check filename in case an image number is expected. */
if (s->iformat->flags & AVFMT_NEEDNUMBER) {
if (!av_filename_number_test(filename)) {
ret = AVERROR(EINVAL);
goto fail;
}
}
s->duration = s->start_time = AV_NOPTS_VALUE;
av_strlcpy(s->filename, filename ? filename : "", sizeof(s->filename));
/* Allocate private data. */
if (s->iformat->priv_data_size > 0) {
if (!(s->priv_data = av_mallocz(s->iformat->priv_data_size))) {
ret = AVERROR(ENOMEM);
goto fail;
}
if (s->iformat->priv_class) {
*(const AVClass **) s->priv_data = s->iformat->priv_class;
av_opt_set_defaults(s->priv_data);
if ((ret = av_opt_set_dict(s->priv_data, &tmp)) < 0)
goto fail;
}
}
/* e.g. AVFMT_NOFILE formats will not have a AVIOContext */
if (s->pb)
ff_id3v2_read(s, ID3v2_DEFAULT_MAGIC, &id3v2_extra_meta, 0);
if (!(s->flags&AVFMT_FLAG_PRIV_OPT) && s->iformat->read_header)
if ((ret = s->iformat->read_header(s)) < 0)//read header,reader mp4 box info
goto fail;
if (id3v2_extra_meta) {
if (!strcmp(s->iformat->name, "mp3") || !strcmp(s->iformat->name, "aac") ||
!strcmp(s->iformat->name, "tta")) {
if ((ret = ff_id3v2_parse_apic(s, &id3v2_extra_meta)) < 0)
goto fail;
} else
av_log(s, AV_LOG_DEBUG, "demuxer does not support additional id3 data, skipping\n");
}
ff_id3v2_free_extra_meta(&id3v2_extra_meta);
if ((ret = avformat_queue_attached_pictures(s)) < 0)
goto fail;
if (!(s->flags&AVFMT_FLAG_PRIV_OPT) && s->pb && !s->internal->data_offset)
s->internal->data_offset = avio_tell(s->pb);
s->internal->raw_packet_buffer_remaining_size = RAW_PACKET_BUFFER_SIZE;
for (i = 0; i < s->nb_streams; i++)
s->streams[i]->internal->orig_codec_id = s->streams[i]->codecpar->codec_id;
if (options) {
av_dict_free(options);
*options = tmp;
}
*ps = s;
return 0;
fail:
ff_id3v2_free_extra_meta(&id3v2_extra_meta);
av_dict_free(&tmp);
if (s->pb && !(s->flags & AVFMT_FLAG_CUSTOM_IO))
avio_closep(&s->pb);
avformat_free_context(s);
*ps = NULL;
return ret;
}
结合注释，我们可以知道这个函数的作用是：打开一个输入流并且读它的头部信息，编解码器不会被打开，这个方法调用结束后，一定要调用avformat_close_input()关闭流。
使用要这个函数要注意一点：如果fmt参数非空，也就是人为的指定了一个AVInputFormat的实例，那么这个函数就不会再检测输入文件的格式了，相反，如果fmt为空，那么这个函数就会自动探测输入文件的格式等信息。
从源码来看，这个函数主要做了四件事：
1.分配一个AVFormatContext的实例。
2.调用init_input函数初始化输入流的信息。这里会初始化AVInputFormat。
3.根据上一步初始化好的AVInputFormat的类型，调用它的read_header方法，读取文件头。
该函数不管做的事情有多么复杂，它主要还是围绕着初始化下面一些数据结构来的：
这三件事说起来简单，具体分析起来相当复杂，我们一件一件来看：
第一件事情
分配一个AVFormatContext结构体。使用的是avformat_alloc_context函数，这个函数定义如下：
AVFormatContext *avformat_alloc_context(void)
{
AVFormatContext *ic;
ic = av_malloc(sizeof(AVFormatContext));
if (!ic) return ic;
avformat_get_context_defaults(ic);
ic->internal = av_mallocz(sizeof(*ic->internal));
if (!ic->internal) {
avformat_free_context(ic);
return NULL;
}
ic->internal->offset = AV_NOPTS_VALUE;
ic->internal->raw_packet_buffer_remaining_size = RAW_PACKET_BUFFER_SIZE;
ic->internal->shortest_end = AV_NOPTS_VALUE;
return ic;
}这个函数中调用av_malloc函数分配一块内容以后，使用avformat_get_context_defaults方法来做一些默认的初始化。之后给internal成员分配内存并做初始化工作。
avformat_get_context_defaults函数如下，看看它做了哪些初始化工作。
static void avformat_get_context_defaults(AVFormatContext *s)
{
memset(s, 0, sizeof(AVFormatContext));
s->av_class = &av_format_context_class;
s->io_open = io_open_default;
s->io_close = io_close_default;
av_opt_set_defaults(s);
}这里做的初始化工作有：
1.av_class成员，指向一个av_format_context_class结构体，这个结构体如下：
static const AVClass av_format_context_class = {
.class_name = "AVFormatContext",
.item_name = format_to_name,
.option = avformat_options,
.version = LIBAVUTIL_VERSION_INT,
.child_next = format_child_next,
.child_class_next = format_child_class_next,
.category = AV_CLASS_CATEGORY_MUXER,
.get_category = get_category,
};
这个结构体的option选项赋值为avformat_options，其值如下：
static const AVOption avformat_options[] = {
{"avioflags", NULL, OFFSET(avio_flags), AV_OPT_TYPE_FLAGS, {.i64 = DEFAULT }, INT_MIN, INT_MAX, D|E, "avioflags"},
{"direct", "reduce buffering", 0, AV_OPT_TYPE_CONST, {.i64 = AVIO_FLAG_DIRECT }, INT_MIN, INT_MAX, D|E, "avioflags"},
{"probesize", "set probing size", OFFSET(probesize), AV_OPT_TYPE_INT64, {.i64 = 5000000 }, 32, INT64_MAX, D},
{"formatprobesize", "number of bytes to probe file format", OFFSET(format_probesize), AV_OPT_TYPE_INT, {.i64 = PROBE_BUF_MAX}, 0, INT_MAX-1, D},
{"packetsize", "set packet size", OFFSET(packet_size), AV_OPT_TYPE_INT, {.i64 = DEFAULT }, 0, INT_MAX, E},内容非常多，这里只列出其中一些。
那么AVClass,AVOption有什么作用呢？
很多的Ffmpeg中的结构体都有AVClass成员，用来描述属主结构体。AVClass有一定会有一个AVOption成员，存放这个结构体需要的一些值，以键值对的形式存放，还有帮助信息等，这些字段都是可以修改的，而且ffmpeg提供了一系列专门用于操作AVOption的函数，这些函数定义在opt.h文件中：
int av_opt_set (void *obj, const char *name, const char *val, int search_flags);
const AVOption *av_opt_next(const void *obj, const AVOption *prev);
const AVOption *av_opt_find2(void *obj, const char *name, const char *unit,
...这些函数的作用从名字上可以猜个大概，这里就不展开了。
接下来的av_opt_set_defaults(s)函数主要就是设置这些字段的：
void av_opt_set_defaults(void *s)
{
av_opt_set_defaults2(s, 0, 0);
}
void av_opt_set_defaults2(void *s, int mask, int flags)
{
const AVOption *opt = NULL;
while ((opt = av_opt_next(s, opt))) {
void *dst = ((uint8_t*)s) + opt->offset;
if ((opt->flags & mask) != flags)
continue;
if (opt->flags & AV_OPT_FLAG_READONLY)
continue;
switch (opt->type) {
case AV_OPT_TYPE_CONST:
/* Nothing to be done here */
break;
case AV_OPT_TYPE_BOOL:
case AV_OPT_TYPE_FLAGS:
case AV_OPT_TYPE_INT:
case AV_OPT_TYPE_INT64:
case AV_OPT_TYPE_DURATION:
case AV_OPT_TYPE_CHANNEL_LAYOUT:
case AV_OPT_TYPE_PIXEL_FMT:
case AV_OPT_TYPE_SAMPLE_FMT:
write_number(s, opt, dst, 1, 1, opt->default_val.i64);
break;
case AV_OPT_TYPE_DOUBLE:
case AV_OPT_TYPE_FLOAT: {
double val;
val = opt->default_val.dbl;
write_number(s, opt, dst, val, 1, 1);
}
break;
case AV_OPT_TYPE_RATIONAL: {
AVRational val;
val = av_d2q(opt->default_val.dbl, INT_MAX);
write_number(s, opt, dst, 1, val.den, val.num);
}
break;
case AV_OPT_TYPE_COLOR:
set_string_color(s, opt, opt->default_val.str, dst);
break;
case AV_OPT_TYPE_STRING:
set_string(s, opt, opt->default_val.str, dst);
break;
case AV_OPT_TYPE_IMAGE_SIZE:
set_string_image_size(s, opt, opt->default_val.str, dst);
break;
case AV_OPT_TYPE_VIDEO_RATE:
set_string_video_rate(s, opt, opt->default_val.str, dst);
break;
case AV_OPT_TYPE_BINARY:
set_string_binary(s, opt, opt->default_val.str, dst);
break;
case AV_OPT_TYPE_DICT:
/* Cannot set defaults for these types */
break;
default:
av_log(s, AV_LOG_DEBUG, "AVOption type %d of option %s not implemented yet\n",
opt->type, opt->name);
}
}
}
这里会遍历AVOption的每一个项，根据每一项的类型，写入一个默认的值。
也就是说，创建AVFormatContext结构体的主要工作是初始化它的internal和AVClass以及AVClass中的AVOption成员。还有就是给它的io_open赋值为io_open_default函数，io_close 赋值为io_close_default函数。
第二件事情
第二件事其实就是init_input函数做的事，这个函数定义如下：
/* Open input file and probe the format if necessary. */
static int init_input(AVFormatContext *s, const char *filename,
AVDictionary **options)
{
int ret;
AVProbeData pd = { filename, NULL, 0 };
int score = AVPROBE_SCORE_RETRY;
if (s->pb) {
s->flags |= AVFMT_FLAG_CUSTOM_IO;
if (!s->iformat)
return av_probe_input_buffer2(s->pb, &s->iformat, filename,
s, 0, s->format_probesize);
else if (s->iformat->flags & AVFMT_NOFILE)
av_log(s, AV_LOG_WARNING, "Custom AVIOContext makes no sense and "
"will be ignored with AVFMT_NOFILE format.\n");
return 0;
}
if ((s->iformat && s->iformat->flags & AVFMT_NOFILE) ||
(!s->iformat && (s->iformat = av_probe_input_format2(&pd, 0, &score))))
return score;
if ((ret = s->io_open(s, &s->pb, filename, AVIO_FLAG_READ | s->avio_flags, options)) < 0)
return ret;
if (s->iformat)
return 0;
return av_probe_input_buffer2(s->pb, &s->iformat, filename,
s, 0, s->format_probesize);
}从注释上来看，其作用是打开输入文件并且探测它的格式。
因此，这个函数做药做了两件事：
1.打开输入文件
2.探测输入文件的格式
打开输入文件使用的s->io_open，io_open是一个函数指针，着我们在分析第一件事情的时候已经说过了，它的值是io_open_default，看下这个函数，这个函数定义在libavformat/options.c文件中：
static int io_open_default(AVFormatContext *s, AVIOContext **pb,
const char *url, int flags, AVDictionary **options)
{
#if FF_API_OLD_OPEN_CALLBACKS
FF_DISABLE_DEPRECATION_WARNINGS
if (s->open_cb)
return s->open_cb(s, pb, url, flags, &s->interrupt_callback, options);
FF_ENABLE_DEPRECATION_WARNINGS
#endif
return ffio_open_whitelist(pb, url, flags, &s->interrupt_callback, options, s->protocol_whitelist, s->protocol_blacklist);
}open_cb肯定为空的，我们没有设置过，因此这里会调用ffio_open_whitelist方法。
这个函数定义在Libavformat/aviobuf.c文件中：
int ffio_open_whitelist(AVIOContext **s, const char *filename, int flags,
const AVIOInterruptCB *int_cb, AVDictionary **options,
const char *whitelist, const char *blacklist
)
{
URLContext *h;
int err;
err = ffurl_open_whitelist(&h, filename, flags, int_cb, options, whitelist, blacklist, NULL);
if (err < 0)
return err;
err = ffio_fdopen(s, h);
if (err < 0) {
ffurl_close(h);
return err;
}
return 0;
}
这里首先调用ffurl_open_whitelist方法，这个方法定义在libavformat/avio.c中：
int ffurl_open_whitelist(URLContext **puc, const char *filename, int flags,
const AVIOInterruptCB *int_cb, AVDictionary **options,
const char *whitelist, const char* blacklist,
URLContext *parent)
{
AVDictionary *tmp_opts = NULL;
AVDictionaryEntry *e;
int ret = ffurl_alloc(puc, filename, flags, int_cb);
if (ret < 0)
return ret;
if (parent)
av_opt_copy(*puc, parent);
if (options &&
(ret = av_opt_set_dict(*puc, options)) < 0)
goto fail;
if (options && (*puc)->prot->priv_data_class &&
(ret = av_opt_set_dict((*puc)->priv_data, options)) < 0)
goto fail;
if (!options)
options = &tmp_opts;
av_assert0(!whitelist ||
!(e=av_dict_get(*options, "protocol_whitelist", NULL, 0)) ||
!strcmp(whitelist, e->value));
av_assert0(!blacklist ||
!(e=av_dict_get(*options, "protocol_blacklist", NULL, 0)) ||
!strcmp(blacklist, e->value));
if ((ret = av_dict_set(options, "protocol_whitelist", whitelist, 0)) < 0)
goto fail;
if ((ret = av_dict_set(options, "protocol_blacklist", blacklist, 0)) < 0)
goto fail;
if ((ret = av_opt_set_dict(*puc, options)) < 0)
goto fail;
ret = ffurl_connect(*puc, options);
if (!ret)
return 0;
fail:
ffurl_close(*puc);
*puc = NULL;
return ret;
}
这个函数首先会使用ffurl_alloc方法分配一个URLContext,这个函数也是定义在avio.c文件中：
int ffurl_alloc(URLContext **puc, const char *filename, int flags,
const AVIOInterruptCB *int_cb)
{
URLProtocol *p = NULL;
if (!first_protocol) {
av_log(NULL, AV_LOG_WARNING, "No URL Protocols are registered. "
"Missing call to av_register_all()?\n");
}
p = url_find_protocol(filename);
if (p)
return url_alloc_for_protocol(puc, p, filename, flags, int_cb);
*puc = NULL;
if (av_strstart(filename, "https:", NULL))
av_log(NULL, AV_LOG_WARNING, "https protocol not found, recompile FFmpeg with "
"openssl, gnutls,\n"
"or securetransport enabled.\n");
return AVERROR_PROTOCOL_NOT_FOUND;
}
这个函数会根据所给的文件名找到对应的协议。使用的是url_find_protocol函数，这个函数也是定义在avio.c文件：
static struct URLProtocol *url_find_protocol(const char *filename)
{
URLProtocol *up = NULL;
char proto_str[128], proto_nested[128], *ptr;
size_t proto_len = strspn(filename, URL_SCHEME_CHARS);
printf("proto_len=%ld\n",proto_len);
printf("name is %s\n",filename);
//hello.mp4
if (filename[proto_len] != ':' &&
(strncmp(filename, "subfile,", 8) || !strchr(filename + proto_len + 1, ':')) ||
is_dos_path(filename))
strcpy(proto_str, "file");
else
av_strlcpy(proto_str, filename,
FFMIN(proto_len + 1, sizeof(proto_str)));
//proto_str = file
printf("proto_str=%s\n",proto_str);
if ((ptr = strchr(proto_str, ',')))
*ptr = '\0';
av_strlcpy(proto_nested, proto_str, sizeof(proto_nested));
//proto_nested = proto_str = file
printf("proto_nested=%s\n",proto_nested);
if ((ptr = strchr(proto_nested, '+')))
*ptr = '\0';
while (up = ffurl_protocol_next(up)) {
printf("int while:::up->name %s\n",up->name);
if (!strcmp(proto_str, up->name))
break;
if (up->flags & URL_PROTOCOL_FLAG_NESTED_SCHEME &&
!strcmp(proto_nested, up->name))
break;
}
printf("up->name %s\n",up->name);
return up;
}
这里为了理解程序，我加了一些打印。如果我们传入的参数是一个xxx.mp4这样的本地文件，这个函数找到的协议是file协议，这个协议定义在libavformat/file.c文件中：
const URLProtocol ff_file_protocol = {
.name = "file",
.url_open = file_open,
.url_read = file_read,
.url_write = file_write,
.url_seek = file_seek,
.url_close = file_close,
.url_get_file_handle = file_get_handle,
.url_check = file_check,
.url_delete = file_delete,
.url_move = file_move,
.priv_data_size = sizeof(FileContext),
.priv_data_class = &file_class,
.url_open_dir = file_open_dir,
.url_read_dir = file_read_dir,
.url_close_dir = file_close_dir,
.default_whitelist = "file,crypto"
};可见，这个协议定义了文件的操作方法，以后，我们打开和读写视频文件都会用到这里对应的方法。现在我们有了一个URLProtocol结构体的实例，它里面定义了对文件的操作函数。找到协议以后，要使用url_alloc_for_protocol函数来创建URLContext 的实例，并且做一堆的初始化工作。这个函数也是定义在avio.c文件中：
static int url_alloc_for_protocol(URLContext **puc, const URLProtocol *up,
const char *filename, int flags,
const AVIOInterruptCB *int_cb)
{
URLContext *uc;
int err;
#if CONFIG_NETWORK
if (up->flags & URL_PROTOCOL_FLAG_NETWORK && !ff_network_init())
return AVERROR(EIO);
#endif
if ((flags & AVIO_FLAG_READ) && !up->url_read) {
av_log(NULL, AV_LOG_ERROR,
"Impossible to open the '%s' protocol for reading\n", up->name);
return AVERROR(EIO);
}
if ((flags & AVIO_FLAG_WRITE) && !up->url_write) {
av_log(NULL, AV_LOG_ERROR,
"Impossible to open the '%s' protocol for writing\n", up->name);
return AVERROR(EIO);
}
uc = av_mallocz(sizeof(URLContext) + strlen(filename) + 1);
if (!uc) {
err = AVERROR(ENOMEM);
goto fail;
}
uc->av_class = &ffurl_context_class;
uc->filename = (char *)&uc[1];
strcpy(uc->filename, filename);
uc->prot = up;
uc->flags = flags;
uc->is_streamed = 0; /* default = not streamed */
uc->max_packet_size = 0; /* default: stream file */
if (up->priv_data_size) {
uc->priv_data = av_mallocz(up->priv_data_size);
if (!uc->priv_data) {
err = AVERROR(ENOMEM);
goto fail;
}
if (up->priv_data_class) {
int proto_len= strlen(up->name);
char *start = strchr(uc->filename, ',');
*(const AVClass **)uc->priv_data = up->priv_data_class;
av_opt_set_defaults(uc->priv_data);
if(!strncmp(up->name, uc->filename, proto_len) && uc->filename + proto_len == start){
int ret= 0;
char *p= start;
char sep= *++p;
char *key, *val;
p++;
if (strcmp(up->name, "subfile"))
ret = AVERROR(EINVAL);
while(ret >= 0 && (key= strchr(p, sep)) && p<key && (val = strchr(key+1, sep))){
*val= *key= 0;
if (strcmp(p, "start") && strcmp(p, "end")) {
ret = AVERROR_OPTION_NOT_FOUND;
} else
ret= av_opt_set(uc->priv_data, p, key+1, 0);
if (ret == AVERROR_OPTION_NOT_FOUND)
av_log(uc, AV_LOG_ERROR, "Key '%s' not found.\n", p);
*val= *key= sep;
p= val+1;
}
if(ret<0 || p!=key){
av_log(uc, AV_LOG_ERROR, "Error parsing options string %s\n", start);
av_freep(&uc->priv_data);
av_freep(&uc);
err = AVERROR(EINVAL);
goto fail;
}
memmove(start, key+1, strlen(key));
}
}
}
if (int_cb)
uc->interrupt_callback = *int_cb;
*puc = uc;
return 0;
fail:
*puc = NULL;
if (uc)
av_freep(&uc->priv_data);
av_freep(&uc);
#if CONFIG_NETWORK
if (up->flags & URL_PROTOCOL_FLAG_NETWORK)
ff_network_close();
#endif
return err;
}
这里创建了一个URLContext的实例，并且做了很多的初始化：
uc->av_class = &ffurl_context_class;
uc->filename = (char *)&uc[1];
strcpy(uc->filename, filename);
uc->prot = up;
uc->flags = flags;
uc->is_streamed = 0; /* default = not streamed */
uc->max_packet_size = 0; /* default: stream file */结束以后，我们就有了URLContext的实例 了，当然也有URLProtocol的实例，的它保存在uc->prot里面。
回到ffurl_open_whitelist函数，接下来，该函数会调用ffurl_connect函数，这个函数是要建立连接的意思，我们的文件是本地文件，应该会打开它。这个函数依旧定义在avio.c中：
int ffurl_connect(URLContext *uc, AVDictionary **options)
{
int err;
AVDictionary *tmp_opts = NULL;
AVDictionaryEntry *e;
...
err =
uc->prot->url_open2 ? uc->prot->url_open2(uc,
uc->filename,
uc->flags,
options) :
uc->prot->url_open(uc, uc->filename, uc->flags);
av_dict_set(options, "protocol_whitelist", NULL, 0);
av_dict_set(options, "protocol_blacklist", NULL, 0);
if (err)
return err;
uc->is_connected = 1;
/* We must be careful here as ffurl_seek() could be slow,
* for example for http */
if ((uc->flags & AVIO_FLAG_WRITE) || !strcmp(uc->prot->name, "file"))
if (!uc->is_streamed && ffurl_seek(uc, 0, SEEK_SET) < 0)
uc->is_streamed = 1;
return 0;
}果然，这里出现了url_open函数的调用，那么对应的就会调用file_open函数，这个函数定义在libavformat/file.c中：
static int file_open(URLContext *h, const char *filename, int flags)
{
FileContext *c = h->priv_data;
int access;
int fd;
struct stat st;
av_strstart(filename, "file:", &filename);
if (flags & AVIO_FLAG_WRITE && flags & AVIO_FLAG_READ) {
access = O_CREAT | O_RDWR;
if (c->trunc)
access |= O_TRUNC;
} else if (flags & AVIO_FLAG_WRITE) {
access = O_CREAT | O_WRONLY;
if (c->trunc)
access |= O_TRUNC;
} else {
access = O_RDONLY;
}
#ifdef O_BINARY
access |= O_BINARY;
#endif
fd = avpriv_open(filename, access, 0666);
if (fd == -1)
return AVERROR(errno);
c->fd = fd;
h->is_streamed = !fstat(fd, &st) && S_ISFIFO(st.st_mode);
return 0;
}这里参数检查以后，会调用avpriv_open函数，这个函数定义在libavutil/file_open.c中：
int avpriv_open(const char *filename, int flags, ...)
{
int fd;
unsigned int mode = 0;
va_list ap;
va_start(ap, flags);
if (flags & O_CREAT)
mode = va_arg(ap, unsigned int);
va_end(ap);
#ifdef O_CLOEXEC
flags |= O_CLOEXEC;
#endif
#ifdef O_NOINHERIT
flags |= O_NOINHERIT;
#endif
fd = open(filename, flags, mode);
#if HAVE_FCNTL
if (fd != -1) {
if (fcntl(fd, F_SETFD, FD_CLOEXEC) == -1)
av_log(NULL, AV_LOG_DEBUG, "Failed to set close on exec\n");
}
#endif
return fd;
}可以看到这里回归到了open这样的系统调用函数了，调用open打开文件后返回文件描述符，这个函数的任务就完成了。这个函数返回到file_open函数后，就把得到的文件描述符赋值给FileContext结构体的fd成员：
c->fd = fd;
之后函数继续返回，函数返回到avio.c中的ffio_open_whitelist函数，接下来调用ffio_fdopen函数，这个函数定义在libavformat下的aviobuf.c中：
int ffio_fdopen(AVIOContext **s, URLContext *h)
{
AVIOInternal *internal = NULL;
uint8_t *buffer = NULL;
int buffer_size, max_packet_size;
max_packet_size = h->max_packet_size;
if (max_packet_size) {
buffer_size = max_packet_size; /* no need to bufferize more than one packet */
} else {
buffer_size = IO_BUFFER_SIZE;
}
buffer = av_malloc(buffer_size);
if (!buffer)
return AVERROR(ENOMEM);
internal = av_mallocz(sizeof(*internal));
if (!internal)
goto fail;
internal->h = h;
*s = avio_alloc_context(buffer, buffer_size, h->flags & AVIO_FLAG_WRITE,
internal, io_read_packet, io_write_packet, io_seek);
if (!*s)
goto fail;
(*s)->protocol_whitelist = av_strdup(h->protocol_whitelist);
if (!(*s)->protocol_whitelist && h->protocol_whitelist) {
avio_closep(s);
goto fail;
}
(*s)->protocol_blacklist = av_strdup(h->protocol_blacklist);
if (!(*s)->protocol_blacklist && h->protocol_blacklist) {
avio_closep(s);
goto fail;
}
(*s)->direct = h->flags & AVIO_FLAG_DIRECT;
(*s)->seekable = h->is_streamed ? 0 : AVIO_SEEKABLE_NORMAL;
(*s)->max_packet_size = max_packet_size;
if(h->prot) {
(*s)->read_pause = io_read_pause;
(*s)->read_seek = io_read_seek;
}
(*s)->av_class = &ff_avio_class;
return 0;
fail:
av_freep(&internal);
av_freep(&buffer);
return AVERROR(ENOMEM);
}
这个函数还是做了很多的事情的：
1.分配一快buffer内存，其大小有这里定义：#define IO_BUFFER_SIZE 32768
buffer的大小本来取决于URLContext的max_packet_size，前面在url_alloc_for_protocol函数中初始化URLContext的时候将其初始化为0了，因此，这里分配的大小为32768。
2.分配一个AVIOContext结构体，这个结构体也很重要，分配完以后我们就有AVIOContext结构体的实例了，分配完成后做了一些初始化工作。
(*s)->direct = h->flags & AVIO_FLAG_DIRECT;
(*s)->seekable = h->is_streamed ? 0 : AVIO_SEEKABLE_NORMAL;
(*s)->max_packet_size = max_packet_size;
(*s)->av_class = &ff_avio_class;这要注意seekable 是AVIO_SEEKABLE_NORMAL，因为is_streamed 为0,这在url_alloc_for_protocol函数中初始化URLContext的时候将其初始化。
这两件事情做完后函数一路返回，又来到了init_input函数中，是不是都快忘记了，这里就是本文分析的avformat_open_input函数做的第二件事情了。
init_input函数接下来调用av_probe_input_buffer2函数，探测输入的buffer,用来确定文件的格式。这里会创建给长重要的AVInputFormat结构体的实例。这个函数定义在libavformat/format.c中：
int av_probe_input_buffer2(AVIOContext *pb, AVInputFormat **fmt,
const char *filename, void *logctx,
unsigned int offset, unsigned int max_probe_size)
{
AVProbeData pd = { filename ? filename : "" };
uint8_t *buf = NULL;
int ret = 0, probe_size, buf_offset = 0;
int score = 0;
int ret2;
if (!max_probe_size)
max_probe_size = PROBE_BUF_MAX;
else if (max_probe_size < PROBE_BUF_MIN) {
av_log(logctx, AV_LOG_ERROR,
"Specified probe size value %u cannot be < %u\n", max_probe_size, PROBE_BUF_MIN);
return AVERROR(EINVAL);
}
if (offset >= max_probe_size)
return AVERROR(EINVAL);
if (pb->av_class) {
uint8_t *mime_type_opt = NULL;
av_opt_get(pb, "mime_type", AV_OPT_SEARCH_CHILDREN, &mime_type_opt);
pd.mime_type = (const char *)mime_type_opt;
}
#if 0
if (!*fmt && pb->av_class && av_opt_get(pb, "mime_type", AV_OPT_SEARCH_CHILDREN, &mime_type) >= 0 && mime_type) {
if (!av_strcasecmp(mime_type, "audio/aacp")) {
*fmt = av_find_input_format("aac");
}
av_freep(&mime_type);
}
#endif
for (probe_size = PROBE_BUF_MIN; probe_size <= max_probe_size && !*fmt;
probe_size = FFMIN(probe_size << 1,
FFMAX(max_probe_size, probe_size + 1))) {
score = probe_size < max_probe_size ? AVPROBE_SCORE_RETRY : 0;
/* Read probe data. */
if ((ret = av_reallocp(&buf, probe_size + AVPROBE_PADDING_SIZE)) < 0)
goto fail;
if ((ret = avio_read(pb, buf + buf_offset,
probe_size - buf_offset)) < 0) {
/* Fail if error was not end of file, otherwise, lower score. */
if (ret != AVERROR_EOF)
goto fail;
score = 0;
ret = 0; /* error was end of file, nothing read */
}
buf_offset += ret;
if (buf_offset < offset)
continue;
pd.buf_size = buf_offset - offset;
pd.buf = &buf[offset];
memset(pd.buf + pd.buf_size, 0, AVPROBE_PADDING_SIZE);
/* Guess file format. */
*fmt = av_probe_input_format2(&pd, 1, &score);
if (*fmt) {
/* This can only be true in the last iteration. */
if (score <= AVPROBE_SCORE_RETRY) {
av_log(logctx, AV_LOG_WARNING,
"Format %s detected only with low score of %d, "
"misdetection possible!\n", (*fmt)->name, score);
} else
av_log(logctx, AV_LOG_DEBUG,
"Format %s probed with size=%d and score=%d\n",
(*fmt)->name, probe_size, score);
#if 0
FILE *f = fopen("probestat.tmp", "ab");
fprintf(f, "probe_size:%d format:%s score:%d filename:%s\n", probe_size, (*fmt)->name, score, filename);
fclose(f);
#endif
}
}
if (!*fmt)
ret = AVERROR_INVALIDDATA;
fail:
/* Rewind. Reuse probe buffer to avoid seeking. */
ret2 = ffio_rewind_with_probe_data(pb, &buf, buf_offset);
if (ret >= 0)
ret = ret2;
av_freep(&pd.mime_type);
return ret < 0 ? ret : score;
}
这个函数做的事情就是探测文件的格式。它会不断的读文件，然后分析，知道确定了文件的格式位置。
这个函数的for循环每次读PROBE_BUF_MIN个字节的内容，其实就是2048了，然后调用av_probe_input_format2函数来猜测文件的格式：
这个函数也定义在format.c文件中：
AVInputFormat *av_probe_input_format2(AVProbeData *pd, int is_opened, int *score_max)
{
int score_ret;
AVInputFormat *fmt = av_probe_input_format3(pd, is_opened, &score_ret);
if (score_ret > *score_max) {
*score_max = score_ret;
return fmt;
} else
return NULL;
}这里调用av_probe_input_format3继续处理：
该函数还是在format.c中：
AVInputFormat *av_probe_input_format3(AVProbeData *pd, int is_opened,
int *score_ret)
{
AVProbeData lpd = *pd;
AVInputFormat *fmt1 = NULL, *fmt;
int score, nodat = 0, score_max = 0;
const static uint8_t zerobuffer[AVPROBE_PADDING_SIZE];
if (!lpd.buf)
lpd.buf = zerobuffer;
if (lpd.buf_size > 10 && ff_id3v2_match(lpd.buf, ID3v2_DEFAULT_MAGIC)) {
int id3len = ff_id3v2_tag_len(lpd.buf);
if (lpd.buf_size > id3len + 16) {
lpd.buf += id3len;
lpd.buf_size -= id3len;
} else if (id3len >= PROBE_BUF_MAX) {
nodat = 2;
} else
nodat = 1;
}
fmt = NULL;
while ((fmt1 = av_iformat_next(fmt1))) {
if (!is_opened == !(fmt1->flags & AVFMT_NOFILE) && strcmp(fmt1->name, "image2"))
continue;
score = 0;
if (fmt1->read_probe) {
score = fmt1->read_probe(&lpd);
if (score)
av_log(NULL, AV_LOG_TRACE, "Probing %s score:%d size:%d\n", fmt1->name, score, lpd.buf_size);
if (fmt1->extensions && av_match_ext(lpd.filename, fmt1->extensions)) {
if (nodat == 0) score = FFMAX(score, 1);
else if (nodat == 1) score = FFMAX(score, AVPROBE_SCORE_EXTENSION / 2 - 1);
else score = FFMAX(score, AVPROBE_SCORE_EXTENSION);
}
} else if (fmt1->extensions) {
if (av_match_ext(lpd.filename, fmt1->extensions))
score = AVPROBE_SCORE_EXTENSION;
}
if (av_match_name(lpd.mime_type, fmt1->mime_type))
score = FFMAX(score, AVPROBE_SCORE_MIME);
if (score > score_max) {
score_max = score;
fmt = fmt1;
} else if (score == score_max)
fmt = NULL;
}
if (nodat == 1)
score_max = FFMIN(AVPROBE_SCORE_EXTENSION / 2 - 1, score_max);
*score_ret = score_max;
av_log(NULL, AV_LOG_TRACE, "format----- %s score:%d size:%d\n", fmt->name, score, lpd.buf_size);
return fmt;
}
这个函数会根据文件名的后缀，遍历AVInputFormat的全局链表，比如我们输入的xxx.mp4，那么匹配成功的必然是ff_mov_demuxer了，这个AVInputFormat 实例定义如下：
mp4文件格式解复用器：
AVInputFormat ff_mov_demuxer = {
.name = "mov,mp4,m4a,3gp,3g2,mj2",
.long_name = NULL_IF_CONFIG_SMALL("QuickTime / MOV"),
.priv_class = &mov_class,
.priv_data_size = sizeof(MOVContext),
.extensions = "mov,mp4,m4a,3gp,3g2,mj2",
.read_probe = mov_probe,
.read_header = mov_read_header,
.read_packet = mov_read_packet,
.read_close = mov_read_close,
.read_seek = mov_read_seek,
.flags = AVFMT_NO_BYTE_SEEK,
};
找到对应的AVInputFormat 的实例后，我们的AVFormatContext中的iformat成员就有内容了。至此，我们已经知道了文件的格式了，接下来需要做第三件事情了。
我们简单回顾下。第二件事情做完后，我们的AVFormatContext中的一下成员就被初始化了：
const AVClass *av_class;
struct AVInputFormat *iformat;
void *priv_data;
AVIOContext *pb;第三件事情
第三件事情就是调用AVInputFormat的read_header方法来解析文件了。我们找到的AVInputFormat的是ff_mov_demuxer ，它的.read_header 初始化为 mov_read_header，这个函数定义在libavformat/mov.c文件中：
static int mov_read_header(AVFormatContext *s)
{
MOVContext *mov = s->priv_data;
AVIOContext *pb = s->pb;
int j, err;
MOVAtom atom = { AV_RL32("root") };//AV)RL32把字符串组合成int类型
int i;
if (mov->decryption_key_len != 0 && mov->decryption_key_len != AES_CTR_KEY_SIZE) {
av_log(s, AV_LOG_ERROR, "Invalid decryption key len %d expected %d\n",
mov->decryption_key_len, AES_CTR_KEY_SIZE);
return AVERROR(EINVAL);
}
mov->fc = s;
mov->trak_index = -1;
/* .mov and .mp4 aren't streamable anyway (only progressive download if moov is before mdat) */
if (pb->seekable)
atom.size = avio_size(pb);
else
atom.size = INT64_MAX;
/* check MOV header */
do {
if (mov->moov_retry)
avio_seek(pb, 0, SEEK_SET);
if ((err = mov_read_default(mov, pb, atom)) < 0) {
av_log(s, AV_LOG_ERROR, "error reading header\n");
mov_read_close(s);
return err;
}
} while (pb->seekable && !mov->found_moov && !mov->moov_retry++);
if (!mov->found_moov) {
av_log(s, AV_LOG_ERROR, "moov atom not found\n");
mov_read_close(s);
return AVERROR_INVALIDDATA;
}
av_log(mov->fc, AV_LOG_TRACE, "on_parse_exit_offset=%"PRId64"\n", avio_tell(pb));
if (pb->seekable) {
if (mov->nb_chapter_tracks > 0 && !mov->ignore_chapters)
mov_read_chapters(s);
for (i = 0; i < s->nb_streams; i++)
if (s->streams[i]->codecpar->codec_tag == AV_RL32("tmcd")) {
mov_read_timecode_track(s, s->streams[i]);
} else if (s->streams[i]->codecpar->codec_tag == AV_RL32("rtmd")) {
mov_read_rtmd_track(s, s->streams[i]);
}
}
/* copy timecode metadata from tmcd tracks to the related video streams */
for (i = 0; i < s->nb_streams; i++) {
AVStream *st = s->streams[i];
MOVStreamContext *sc = st->priv_data;
if (sc->timecode_track > 0) {
AVDictionaryEntry *tcr;
int tmcd_st_id = -1;
for (j = 0; j < s->nb_streams; j++)
if (s->streams[j]->id == sc->timecode_track)
tmcd_st_id = j;
if (tmcd_st_id < 0 || tmcd_st_id == i)
continue;
tcr = av_dict_get(s->streams[tmcd_st_id]->metadata, "timecode", NULL, 0);
if (tcr)
av_dict_set(&st->metadata, "timecode", tcr->value, 0);
}
}
export_orphan_timecode(s);
for (i = 0; i < s->nb_streams; i++) {
AVStream *st = s->streams[i];
MOVStreamContext *sc = st->priv_data;
fix_timescale(mov, sc);
if(st->codecpar->codec_type == AVMEDIA_TYPE_AUDIO && st->codecpar->codec_id == AV_CODEC_ID_AAC) {
st->skip_samples = sc->start_pad;
}
if (st->codecpar->codec_type == AVMEDIA_TYPE_VIDEO && sc->nb_frames_for_fps > 0 && sc->duration_for_fps > 0)
av_reduce(&st->avg_frame_rate.num, &st->avg_frame_rate.den,
sc->time_scale*(int64_t)sc->nb_frames_for_fps, sc->duration_for_fps, INT_MAX);
if (st->codecpar->codec_type == AVMEDIA_TYPE_SUBTITLE) {
if (st->codecpar->width <= 0 || st->codecpar->height <= 0) {
st->codecpar->width = sc->width;
st->codecpar->height = sc->height;
}
if (st->codecpar->codec_id == AV_CODEC_ID_DVD_SUBTITLE) {
if ((err = mov_rewrite_dvd_sub_extradata(st)) < 0)
return err;
}
}
if (mov->handbrake_version &&
mov->handbrake_version <= 1000000*0 + 1000*10 + 2 && // 0.10.2
st->codecpar->codec_id == AV_CODEC_ID_MP3
) {
av_log(s, AV_LOG_VERBOSE, "Forcing full parsing for mp3 stream\n");
st->need_parsing = AVSTREAM_PARSE_FULL;
}
}
if (mov->trex_data) {
for (i = 0; i < s->nb_streams; i++) {
AVStream *st = s->streams[i];
MOVStreamContext *sc = st->priv_data;
if (st->duration > 0)
st->codecpar->bit_rate = sc->data_size * 8 * sc->time_scale / st->duration;
}
}
if (mov->use_mfra_for > 0) {
for (i = 0; i < s->nb_streams; i++) {
AVStream *st = s->streams[i];
MOVStreamContext *sc = st->priv_data;
if (sc->duration_for_fps > 0) {
st->codecpar->bit_rate = sc->data_size * 8 * sc->time_scale /
sc->duration_for_fps;
}
}
}
for (i = 0; i < mov->bitrates_count && i < s->nb_streams; i++) {
if (mov->bitrates[i]) {
s->streams[i]->codecpar->bit_rate = mov->bitrates[i];
}
}
ff_rfps_calculate(s);
for (i = 0; i < s->nb_streams; i++) {
AVStream *st = s->streams[i];
MOVStreamContext *sc = st->priv_data;
switch (st->codecpar->codec_type) {
case AVMEDIA_TYPE_AUDIO:
err = ff_replaygain_export(st, s->metadata);
if (err < 0) {
mov_read_close(s);
return err;
}
break;
case AVMEDIA_TYPE_VIDEO:
if (sc->display_matrix) {
AVPacketSideData *sd, *tmp;
tmp = av_realloc_array(st->side_data,
st->nb_side_data + 1, sizeof(*tmp));
if (!tmp)
return AVERROR(ENOMEM);
st->side_data = tmp;
st->nb_side_data++;
sd = &st->side_data[st->nb_side_data - 1];
sd->type = AV_PKT_DATA_DISPLAYMATRIX;
sd->size = sizeof(int32_t) * 9;
sd->data = (uint8_t*)sc->display_matrix;
sc->display_matrix = NULL;
}
break;
}
}
ff_configure_buffers_for_index(s, AV_TIME_BASE);
return 0;
}
要看懂这个函数的话，的先对mp4文件的格式有所了解（我这里以mp4文件为例）。这里就不展开分析Mp4文件的格式了，请大家自行了解。
mp4文件由一系列的box组成，如下图：
从图中可以看出来这些box是有层级关系的。每一个box它的头部的8个字节是固定的，前四个字节是这个box的大小，后四个字节是这个box的类型，也就是途中的fytp,moov之类的。这个信息在ffmpeg中使用MOVAtom来标示：
typedef struct MOVAtom {
uint32_t type;
int64_t size; /* total size (excluding the size and type fields) */
} MOVAtom;
这个函数的一开始，就够早了一个叫做root的MOVAtom ，并从它开始，遍历这些box,怎么遍历的呢？调用mov_read_default方法，这个方法中，又会递归的调用mov_read_default方法来解析它的子box，一次来推，最终解析所有的box。
接下来我们看看mov_read_default方法;
static int mov_read_default(MOVContext *c, AVIOContext *pb, MOVAtom atom)
{
int64_t total_size = 0;
MOVAtom a;
int i;
char mmmss[5];
if (c->atom_depth > 10) {
av_log(c->fc, AV_LOG_ERROR, "Atoms too deeply nested\n");
return AVERROR_INVALIDDATA;
}
c->atom_depth ++;
printf("mov_read_default\n");
printf("c->atom_depth=%d\n",c->atom_depth);
if (atom.size < 0)
atom.size = INT64_MAX;
printf("total_size=%ld\n",total_size);
printf("atom.size=%ld\n",atom.size);
printf("avio_feof(pb)=%d\n",avio_feof(pb));
while (total_size + 8 <= atom.size && !avio_feof(pb)) {
int (*parse)(MOVContext*, AVIOContext*, MOVAtom) = NULL;
a.size = atom.size;
a.type=0;
if (atom.size >= 8) {
a.size = avio_rb32(pb);
a.type = avio_rl32(pb);
if (a.type == MKTAG('f','r','e','e') &&
a.size >= 8 &&
c->moov_retry) {
uint8_t buf[8];
uint32_t *type = (uint32_t *)buf + 1;
if (avio_read(pb, buf, 8) != 8)
return AVERROR_INVALIDDATA;
avio_seek(pb, -8, SEEK_CUR);
if (*type == MKTAG('m','v','h','d') ||
*type == MKTAG('c','m','o','v')) {
av_log(c->fc, AV_LOG_ERROR, "Detected moov in a free atom.\n");
a.type = MKTAG('m','o','o','v');
}
}
if (atom.type != MKTAG('r','o','o','t') &&
atom.type != MKTAG('m','o','o','v'))
{
if (a.type == MKTAG('t','r','a','k') || a.type == MKTAG('m','d','a','t'))
{
av_log(c->fc, AV_LOG_ERROR, "Broken file, trak/mdat not at top-level\n");
avio_skip(pb, -8);
c->atom_depth --;
return 0;
}
}
total_size += 8;
if (a.size == 1 && total_size + 8 <= atom.size) { /* 64 bit extended size */
a.size = avio_rb64(pb) - 8;
total_size += 8;
}
}
av_log(c->fc, AV_LOG_TRACE, "type: %08x '%.4s' parent:'%.4s' sz: %"PRId64" %"PRId64" %"PRId64"\n",
a.type, (char*)&a.type, (char*)&atom.type, a.size, total_size, atom.size);
if (a.size == 0) {
a.size = atom.size - total_size + 8;
}
a.size -= 8;
if (a.size < 0)
break;
a.size = FFMIN(a.size, atom.size - total_size);
for (i = 0; mov_default_parse_table[i].type; i++)
if (mov_default_parse_table[i].type == a.type) {
parse = mov_default_parse_table[i].parse;
break;
}
// container is user data
if (!parse && (atom.type == MKTAG('u','d','t','a') ||
atom.type == MKTAG('i','l','s','t')))
parse = mov_read_udta_string;
if (!parse) { /* skip leaf atoms data */
avio_skip(pb, a.size);
} else {
int64_t start_pos = avio_tell(pb);
int64_t left;
int err = parse(c, pb, a);
if (err < 0) {
c->atom_depth --;
return err;
}
if (c->found_moov && c->found_mdat &&
((!pb->seekable || c->fc->flags & AVFMT_FLAG_IGNIDX) ||
start_pos + a.size == avio_size(pb))) {
if (!pb->seekable || c->fc->flags & AVFMT_FLAG_IGNIDX)
c->next_root_atom = start_pos + a.size;
c->atom_depth --;
return 0;
}
left = a.size - avio_tell(pb) + start_pos;
if (left > 0) /* skip garbage at atom end */
avio_skip(pb, left);
else if (left < 0) {
av_log(c->fc, AV_LOG_WARNING,
"overread end of atom '%.4s' by %"PRId64" bytes\n",
(char*)&a.type, -left);
avio_seek(pb, left, SEEK_CUR);
}
}
total_size += a.size;
mmmss[4]='\0';
printf("-------------while----------");
printf("total_size=%ld\n",total_size);
printf("a.size=%ld\n",a.size);
AV_WL32(mmmss,a.type);
printf("a.type=%s\n",mmmss);
}
为了更好的理解，我加了写打印。这个函数中，没找到一个box，读出它的类型以后，就会调用对应的parse方法。配型与parse方法通过一下数组来对应：
static const MOVParseTableEntry mov_default_parse_table[] = {
{ MKTAG('A','C','L','R'), mov_read_aclr },
{ MKTAG('A','P','R','G'), mov_read_avid },
{ MKTAG('A','A','L','P'), mov_read_avid },
{ MKTAG('A','R','E','S'), mov_read_ares },
{ MKTAG('a','v','s','s'), mov_read_avss },
{ MKTAG('c','h','p','l'), mov_read_chpl },
{ MKTAG('c','o','6','4'), mov_read_stco },
{ MKTAG('c','o','l','r'), mov_read_colr },
{ MKTAG('c','t','t','s'), mov_read_ctts }, /* composition time to sample */
{ MKTAG('d','i','n','f'), mov_read_default },
{ MKTAG('D','p','x','E'), mov_read_dpxe },
{ MKTAG('d','r','e','f'), mov_read_dref },
{ MKTAG('e','d','t','s'), mov_read_default },
{ MKTAG('e','l','s','t'), mov_read_elst },
{ MKTAG('e','n','d','a'), mov_read_enda },
{ MKTAG('f','i','e','l'), mov_read_fiel },
{ MKTAG('f','t','y','p'), mov_read_ftyp },
{ MKTAG('g','l','b','l'), mov_read_glbl },
{ MKTAG('h','d','l','r'), mov_read_hdlr },
{ MKTAG('i','l','s','t'), mov_read_ilst },
{ MKTAG('j','p','2','h'), mov_read_jp2h },
{ MKTAG('m','d','a','t'), mov_read_mdat },
{ MKTAG('m','d','h','d'), mov_read_mdhd },
{ MKTAG('m','d','i','a'), mov_read_default },
{ MKTAG('m','e','t','a'), mov_read_meta },
{ MKTAG('m','i','n','f'), mov_read_default },
{ MKTAG('m','o','o','f'), mov_read_moof },
{ MKTAG('m','o','o','v'), mov_read_moov },
{ MKTAG('m','v','e','x'), mov_read_default },
{ MKTAG('m','v','h','d'), mov_read_mvhd },
{ MKTAG('S','M','I',' '), mov_read_svq3 },
{ MKTAG('a','l','a','c'), mov_read_alac }, /* alac specific atom */
{ MKTAG('a','v','c','C'), mov_read_glbl },
{ MKTAG('p','a','s','p'), mov_read_pasp },
{ MKTAG('s','t','b','l'), mov_read_default },
{ MKTAG('s','t','c','o'), mov_read_stco },
{ MKTAG('s','t','p','s'), mov_read_stps },
{ MKTAG('s','t','r','f'), mov_read_strf },
{ MKTAG('s','t','s','c'), mov_read_stsc },
{ MKTAG('s','t','s','d'), mov_read_stsd }, /* sample description */
{ MKTAG('s','t','s','s'), mov_read_stss }, /* sync sample */
{ MKTAG('s','t','s','z'), mov_read_stsz }, /* sample size */
{ MKTAG('s','t','t','s'), mov_read_stts },
{ MKTAG('s','t','z','2'), mov_read_stsz }, /* compact sample size */
{ MKTAG('t','k','h','d'), mov_read_tkhd }, /* track header */
{ MKTAG('t','f','d','t'), mov_read_tfdt },
{ MKTAG('t','f','h','d'), mov_read_tfhd }, /* track fragment header */
{ MKTAG('t','r','a','k'), mov_read_trak },
{ MKTAG('t','r','a','f'), mov_read_default },
{ MKTAG('t','r','e','f'), mov_read_default },
{ MKTAG('t','m','c','d'), mov_read_tmcd },
{ MKTAG('c','h','a','p'), mov_read_chap },
{ MKTAG('t','r','e','x'), mov_read_trex },
{ MKTAG('t','r','u','n'), mov_read_trun },
{ MKTAG('u','d','t','a'), mov_read_default },
{ MKTAG('w','a','v','e'), mov_read_wave },
{ MKTAG('e','s','d','s'), mov_read_esds },
{ MKTAG('d','a','c','3'), mov_read_dac3 }, /* AC-3 info */
{ MKTAG('d','e','c','3'), mov_read_dec3 }, /* EAC-3 info */
{ MKTAG('w','i','d','e'), mov_read_wide }, /* place holder */
{ MKTAG('w','f','e','x'), mov_read_wfex },
{ MKTAG('c','m','o','v'), mov_read_cmov },
{ MKTAG('c','h','a','n'), mov_read_chan }, /* channel layout */
{ MKTAG('d','v','c','1'), mov_read_dvc1 },
{ MKTAG('s','b','g','p'), mov_read_sbgp },
{ MKTAG('h','v','c','C'), mov_read_glbl },
{ MKTAG('u','u','i','d'), mov_read_uuid },
{ MKTAG('C','i','n', 0x8e), mov_read_targa_y216 },
{ MKTAG('f','r','e','e'), mov_read_free },
{ MKTAG('-','-','-','-'), mov_read_custom },
{ 0, NULL }
};以trak为例，其解析方法如下：
static int mov_read_trak(MOVContext *c, AVIOContext *pb, MOVAtom atom)
{
AVStream *st;
MOVStreamContext *sc;
int ret;
st = avformat_new_stream(c->fc, NULL);
if (!st) return AVERROR(ENOMEM);
st->id = c->fc->nb_streams;
sc = av_mallocz(sizeof(MOVStreamContext));
if (!sc) return AVERROR(ENOMEM);
st->priv_data = sc;
st->codec->codec_type = AVMEDIA_TYPE_DATA;
sc->ffindex = st->index;
if ((ret = mov_read_default(c, pb, atom)) < 0)
return ret;
/* sanity checks */
if (sc->chunk_count && (!sc->stts_count || !sc->stsc_count ||
(!sc->sample_size && !sc->sample_count))) {
av_log(c->fc, AV_LOG_ERROR, "stream %d, missing mandatory atoms, broken header\n",
st->index);
return 0;
}
fix_timescale(c, sc);
avpriv_set_pts_info(st, 64, 1, sc->time_scale);
mov_build_index(c, st);
if (sc->dref_id-1 < sc->drefs_count && sc->drefs[sc->dref_id-1].path) {
MOVDref *dref = &sc->drefs[sc->dref_id - 1];
if (c->enable_drefs) {
if (mov_open_dref(c, &sc->pb, c->fc->filename, dref,
&c->fc->interrupt_callback) < 0)
av_log(c->fc, AV_LOG_ERROR,
"stream %d, error opening alias: path='%s', dir='%s', "
"filename='%s', volume='%s', nlvl_from=%d, nlvl_to=%d\n",
st->index, dref->path, dref->dir, dref->filename,
dref->volume, dref->nlvl_from, dref->nlvl_to);
} else {
av_log(c->fc, AV_LOG_WARNING,
"Skipped opening external track: "
"stream %d, alias: path='%s', dir='%s', "
"filename='%s', volume='%s', nlvl_from=%d, nlvl_to=%d."
"Set enable_drefs to allow this.\n",
st->index, dref->path, dref->dir, dref->filename,
dref->volume, dref->nlvl_from, dref->nlvl_to);
}
} else {
sc->pb = c->fc->pb;
sc->pb_is_copied = 1;
}
if (st->codec->codec_type == AVMEDIA_TYPE_VIDEO) {
if (!st->sample_aspect_ratio.num && st->codec->width && st->codec->height &&
sc->height && sc->width &&
(st->codec->width != sc->width || st->codec->height != sc->height)) {
st->sample_aspect_ratio = av_d2q(((double)st->codec->height * sc->width) /
((double)st->codec->width * sc->height), INT_MAX);
}
#if FF_API_R_FRAME_RATE
if (sc->stts_count == 1 || (sc->stts_count == 2 && sc->stts_data[1].count == 1))
av_reduce(&st->r_frame_rate.num, &st->r_frame_rate.den,
sc->time_scale, sc->stts_data[0].duration, INT_MAX);
#endif
}
// done for ai5q, ai52, ai55, ai1q, ai12 and ai15.
if (!st->codec->extradata_size && st->codec->codec_id == AV_CODEC_ID_H264 &&
TAG_IS_AVCI(st->codec->codec_tag)) {
ret = ff_generate_avci_extradata(st);
if (ret < 0)
return ret;
}
switch (st->codec->codec_id) {
#if CONFIG_H261_DECODER
case AV_CODEC_ID_H261:
#endif
#if CONFIG_H263_DECODER
case AV_CODEC_ID_H263:
#endif
#if CONFIG_MPEG4_DECODER
case AV_CODEC_ID_MPEG4:
#endif
st->codec->width = 0; /* let decoder init width/height */
st->codec->height= 0;
break;
}
/* Do not need those anymore. */
av_freep(&sc->chunk_offsets);
av_freep(&sc->stsc_data);
av_freep(&sc->sample_sizes);
av_freep(&sc->keyframes);
av_freep(&sc->stts_data);
av_freep(&sc->stps_data);
av_freep(&sc->elst_data);
av_freep(&sc->rap_group);
return 0;
}一开始，创建一个新流：
AVStream *avformat_new_stream(AVFormatContext *s, const AVCodec *c)
{
AVStream *st;
int i;
AVStream **streams;
if (s->nb_streams >= INT_MAX/sizeof(*streams))
return NULL;
streams = av_realloc_array(s->streams, s->nb_streams + 1, sizeof(*streams));
if (!streams)
return NULL;
s->streams = streams;
st = av_mallocz(sizeof(AVStream));
if (!st)
return NULL;
if (!(st->info = av_mallocz(sizeof(*st->info)))) {
av_free(st);
return NULL;
}
st->info->last_dts = AV_NOPTS_VALUE;
#if FF_API_LAVF_AVCTX
FF_DISABLE_DEPRECATION_WARNINGS
st->codec = avcodec_alloc_context3(c);
if (!st->codec) {
av_free(st->info);
av_free(st);
return NULL;
}
FF_ENABLE_DEPRECATION_WARNINGS
#endif
st->internal = av_mallocz(sizeof(*st->internal));
if (!st->internal)
goto fail;
st->codecpar = avcodec_parameters_alloc();
if (!st->codecpar)
goto fail;
st->internal->avctx = avcodec_alloc_context3(NULL);
if (!st->internal->avctx)
goto fail;
if (s->iformat) {
#if FF_API_LAVF_AVCTX
FF_DISABLE_DEPRECATION_WARNINGS
/* no default bitrate if decoding */
st->codec->bit_rate = 0;
FF_ENABLE_DEPRECATION_WARNINGS
#endif
/* default pts setting is MPEG-like */
avpriv_set_pts_info(st, 33, 1, 90000);
/* we set the current DTS to 0 so that formats without any timestamps
* but durations get some timestamps, formats with some unknown
* timestamps have their first few packets buffered and the
* timestamps corrected before they are returned to the user */
st->cur_dts = RELATIVE_TS_BASE;
} else {
st->cur_dts = AV_NOPTS_VALUE;
}
st->index = s->nb_streams;
st->start_time = AV_NOPTS_VALUE;
st->duration = AV_NOPTS_VALUE;
st->first_dts = AV_NOPTS_VALUE;
st->probe_packets = MAX_PROBE_PACKETS;
st->pts_wrap_reference = AV_NOPTS_VALUE;
st->pts_wrap_behavior = AV_PTS_WRAP_IGNORE;
st->last_IP_pts = AV_NOPTS_VALUE;
st->last_dts_for_order_check = AV_NOPTS_VALUE;
for (i = 0; i < MAX_REORDER_DELAY + 1; i++)
st->pts_buffer[i] = AV_NOPTS_VALUE;
st->sample_aspect_ratio = (AVRational) { 0, 1 };
#if FF_API_R_FRAME_RATE
st->info->last_dts = AV_NOPTS_VALUE;
#endif
st->info->fps_first_dts = AV_NOPTS_VALUE;
st->info->fps_last_dts = AV_NOPTS_VALUE;
st->inject_global_side_data = s->internal->inject_global_side_data;
st->internal->need_context_update = 1;
s->streams[s->nb_streams++] = st;
return st;
fail:
free_stream(&st);
return NULL;
}
- 最后将创建好的新流添加到AVFormatContext中的streams成员，添加到最后一项，并且让nb_streams成员自增。
2.递归解析下一级的box
通过这种解析，可以看到我们获取到了流的信息。
trak包含了很多的子box，这些box描述了trak的功能。比如我们要获取这个流是视频流呢还是音频流呢？亦或者是不是字幕流呢就要通过解析hdlr这个子box来获取：
if ((ret = mov_read_default(c, pb, atom)) < 0)
return ret;区分音频流还是视频流：
static int mov_read_hdlr(MOVContext *c, AVIOContext *pb, MOVAtom atom)
{
AVStream *st;
uint32_t type;
uint32_t av_unused ctype;
int64_t title_size;
char *title_str;
int ret;
if (c->fc->nb_streams < 1) // meta before first trak
return 0;
st = c->fc->streams[c->fc->nb_streams-1];
avio_r8(pb); /* version */
avio_rb24(pb); /* flags */
/* component type */
ctype = avio_rl32(pb);
type = avio_rl32(pb); /* component subtype */
av_log(c->fc, AV_LOG_TRACE, "ctype= %.4s (0x%08x)\n", (char*)&ctype, ctype);
av_log(c->fc, AV_LOG_TRACE, "stype= %.4s\n", (char*)&type);
if (type == MKTAG('v','i','d','e'))
st->codec->codec_type = AVMEDIA_TYPE_VIDEO;
else if (type == MKTAG('s','o','u','n'))
st->codec->codec_type = AVMEDIA_TYPE_AUDIO;
else if (type == MKTAG('m','1','a',' '))
st->codec->codec_id = AV_CODEC_ID_MP2;
else if ((type == MKTAG('s','u','b','p')) || (type == MKTAG('c','l','c','p')))
st->codec->codec_type = AVMEDIA_TYPE_SUBTITLE;
avio_rb32(pb); /* component manufacture */
avio_rb32(pb); /* component flags */
avio_rb32(pb); /* component flags mask */
title_size = atom.size - 24;
if (title_size > 0) {
title_str = av_malloc(title_size + 1); /* Add null terminator */
if (!title_str)
return AVERROR(ENOMEM);
ret = ffio_read_size(pb, title_str, title_size);
if (ret < 0) {
av_freep(&title_str);
return ret;
}
title_str[title_size] = 0;
if (title_str[0]) {
int off = (!c->isom && title_str[0] == title_size - 1);
av_dict_set(&st->metadata, "handler_name", title_str + off, 0);
}
av_freep(&title_str);
}
return 0;
}
其核心代码：
if (type == MKTAG('v','i','d','e'))
st->codec->codec_type = AVMEDIA_TYPE_VIDEO;
else if (type == MKTAG('s','o','u','n'))
st->codec->codec_type = AVMEDIA_TYPE_AUDIO;
else if (type == MKTAG('m','1','a',' '))
st->codec->codec_id = AV_CODEC_ID_MP2;
else if ((type == MKTAG('s','u','b','p')) || (type == MKTAG('c','l','c','p')))
st->codec->codec_type = AVMEDIA_TYPE_SUBTITLE;如果hdlr的第16-20个字节的内容为vide,那么就是视频流，如果是soun,那么就是音频流，如说是subp或者clcp，那么就是字幕流。
我们不可能把所有box的解析都分析一遍，这里对box的解析就到这里，其他的请感兴趣的reader自行分析了。