九 h264 RTP传输详解(1)
前几章对Server端的介绍中有个比较重要的问题没有仔细探究：如何打开文件并获得其SDP信息。我们就从这里入手吧。
当RTSPServer收到对某个媒体的DESCRIBE请求时，它会找到对应的ServerMediaSession,调用ServerMediaSession::generateSDPDescription()。generateSDPDescription()中会遍历调用ServerMediaSession中所有的调用ServerMediaSubsession，通过subsession->sdpLines()取得每个Subsession的sdp，合并成一个完整的SDP返回之。
我们几乎可以断定，文件的打开和分析应该是在每个Subsession的sdpLines()函数中完成的，看看这个函数：
- char const* OnDemandServerMediaSubsession::sdpLines()
- {
- if (fSDPLines == NULL) {
- // We need to construct a set of SDP lines that describe this
- // subsession (as a unicast stream). To do so, we first create
- // dummy (unused) source and "RTPSink" objects,
- // whose parameters we use for the SDP lines:
- unsigned estBitrate;
- FramedSource* inputSource = createNewStreamSource(0, estBitrate);
- if (inputSource == NULL)
- return NULL; // file not found
- struct in_addr dummyAddr;
- dummyAddr.s_addr = 0;
- Groupsock dummyGroupsock(envir(), dummyAddr, 0, 0);
- unsigned char rtpPayloadType = 96 + trackNumber() - 1; // if dynamic
- RTPSink* dummyRTPSink = createNewRTPSink(&dummyGroupsock,
- rtpPayloadType, inputSource);
- setSDPLinesFromRTPSink(dummyRTPSink, inputSource, estBitrate);
- Medium::close(dummyRTPSink);
- closeStreamSource(inputSource);
- }
- return fSDPLines;
- }
char const* OnDemandServerMediaSubsession::sdpLines()
{
if (fSDPLines == NULL) {
// We need to construct a set of SDP lines that describe this
// subsession (as a unicast stream). To do so, we first create
// dummy (unused) source and "RTPSink" objects,
// whose parameters we use for the SDP lines:
unsigned estBitrate;
FramedSource* inputSource = createNewStreamSource(0, estBitrate);
if (inputSource == NULL)
return NULL; // file not found
struct in_addr dummyAddr;
dummyAddr.s_addr = 0;
Groupsock dummyGroupsock(envir(), dummyAddr, 0, 0);
unsigned char rtpPayloadType = 96 + trackNumber() - 1; // if dynamic
RTPSink* dummyRTPSink = createNewRTPSink(&dummyGroupsock,
rtpPayloadType, inputSource);
setSDPLinesFromRTPSink(dummyRTPSink, inputSource, estBitrate);
Medium::close(dummyRTPSink);
closeStreamSource(inputSource);
}
return fSDPLines;
}- FramedSource* H264VideoFileServerMediaSubsession::createNewStreamSource(
- unsigned /*clientSessionId*/,
- unsigned& estBitrate)
- {
- estBitrate = 500; // kbps, estimate
- // Create the video source:
- ByteStreamFileSource* fileSource = ByteStreamFileSource::createNew(envir(),
- fFileName);
- if (fileSource == NULL)
- return NULL;
- fFileSize = fileSource->fileSize();
- // Create a framer for the Video Elementary Stream:
- return H264VideoStreamFramer::createNew(envir(), fileSource);
- }
- RTPSink* H264VideoFileServerMediaSubsession::createNewRTPSink(
- Groupsock* rtpGroupsock,
- unsigned char rtpPayloadTypeIfDynamic,
- FramedSource* /*inputSource*/)
- {
- return H264VideoRTPSink::createNew(envir(), rtpGroupsock,
- rtpPayloadTypeIfDynamic);
- }
FramedSource* H264VideoFileServerMediaSubsession::createNewStreamSource(
unsigned /*clientSessionId*/,
unsigned& estBitrate)
{
estBitrate = 500; // kbps, estimate
// Create the video source:
ByteStreamFileSource* fileSource = ByteStreamFileSource::createNew(envir(),
fFileName);
if (fileSource == NULL)
return NULL;
fFileSize = fileSource->fileSize();
// Create a framer for the Video Elementary Stream:
return H264VideoStreamFramer::createNew(envir(), fileSource);
}
RTPSink* H264VideoFileServerMediaSubsession::createNewRTPSink(
Groupsock* rtpGroupsock,
unsigned char rtpPayloadTypeIfDynamic,
FramedSource* /*inputSource*/)
{
return H264VideoRTPSink::createNew(envir(), rtpGroupsock,
rtpPayloadTypeIfDynamic);
}- void OnDemandServerMediaSubsession::setSDPLinesFromRTPSink(
- RTPSink* rtpSink,
- FramedSource* inputSource,
- unsigned estBitrate)
- {
- if (rtpSink == NULL)
- return;
- char const* mediaType = rtpSink->sdpMediaType();
- unsigned char rtpPayloadType = rtpSink->rtpPayloadType();
- struct in_addr serverAddrForSDP;
- serverAddrForSDP.s_addr = fServerAddressForSDP;
- char* const ipAddressStr = strDup(our_inet_ntoa(serverAddrForSDP));
- char* rtpmapLine = rtpSink->rtpmapLine();
- char const* rangeLine = rangeSDPLine();
- char const* auxSDPLine = getAuxSDPLine(rtpSink, inputSource);
- if (auxSDPLine == NULL)
- auxSDPLine = "";
- char const* const sdpFmt = "m=%s %u RTP/AVP %d\r\n"
- "c=IN IP4 %s\r\n"
- "b=AS:%u\r\n"
- "%s"
- "%s"
- "%s"
- "a=control:%s\r\n";
- unsigned sdpFmtSize = strlen(sdpFmt) + strlen(mediaType) + 5 /* max short len */
- + 3 /* max char len */
- + strlen(ipAddressStr) + 20 /* max int len */
- + strlen(rtpmapLine) + strlen(rangeLine) + strlen(auxSDPLine)
- + strlen(trackId());
- char* sdpLines = new char[sdpFmtSize];
- sprintf(sdpLines, sdpFmt, mediaType, // m= <media>
- fPortNumForSDP, // m= <port>
- rtpPayloadType, // m= <fmt list>
- ipAddressStr, // c= address
- estBitrate, // b=AS:<bandwidth>
- rtpmapLine, // a=rtpmap:... (if present)
- rangeLine, // a=range:... (if present)
- auxSDPLine, // optional extra SDP line
- trackId()); // a=control:<track-id>
- delete[] (char*) rangeLine;
- delete[] rtpmapLine;
- delete[] ipAddressStr;
- fSDPLines = strDup(sdpLines);
- delete[] sdpLines;
- }
void OnDemandServerMediaSubsession::setSDPLinesFromRTPSink(
RTPSink* rtpSink,
FramedSource* inputSource,
unsigned estBitrate)
{
if (rtpSink == NULL)
return;
char const* mediaType = rtpSink->sdpMediaType();
unsigned char rtpPayloadType = rtpSink->rtpPayloadType();
struct in_addr serverAddrForSDP;
serverAddrForSDP.s_addr = fServerAddressForSDP;
char* const ipAddressStr = strDup(our_inet_ntoa(serverAddrForSDP));
char* rtpmapLine = rtpSink->rtpmapLine();
char const* rangeLine = rangeSDPLine();
char const* auxSDPLine = getAuxSDPLine(rtpSink, inputSource);
if (auxSDPLine == NULL)
auxSDPLine = "";
char const* const sdpFmt = "m=%s %u RTP/AVP %d\r\n"
"c=IN IP4 %s\r\n"
"b=AS:%u\r\n"
"%s"
"%s"
"%s"
"a=control:%s\r\n";
unsigned sdpFmtSize = strlen(sdpFmt) + strlen(mediaType) + 5 /* max short len */
+ 3 /* max char len */
+ strlen(ipAddressStr) + 20 /* max int len */
+ strlen(rtpmapLine) + strlen(rangeLine) + strlen(auxSDPLine)
+ strlen(trackId());
char* sdpLines = new char[sdpFmtSize];
sprintf(sdpLines, sdpFmt, mediaType, // m= <media>
fPortNumForSDP, // m= <port>
rtpPayloadType, // m= <fmt list>
ipAddressStr, // c= address
estBitrate, // b=AS:<bandwidth>
rtpmapLine, // a=rtpmap:... (if present)
rangeLine, // a=range:... (if present)
auxSDPLine, // optional extra SDP line
trackId()); // a=control:<track-id>
delete[] (char*) rangeLine;
delete[] rtpmapLine;
delete[] ipAddressStr;
fSDPLines = strDup(sdpLines);
delete[] sdpLines;
}- char const* OnDemandServerMediaSubsession::getAuxSDPLine(
- RTPSink* rtpSink,
- FramedSource* /*inputSource*/)
- {
- // Default implementation:
- return rtpSink == NULL ? NULL : rtpSink->auxSDPLine();
- }
char const* OnDemandServerMediaSubsession::getAuxSDPLine(
RTPSink* rtpSink,
FramedSource* /*inputSource*/)
{
// Default implementation:
return rtpSink == NULL ? NULL : rtpSink->auxSDPLine();
}- char const* H264VideoFileServerMediaSubsession::getAuxSDPLine(
- RTPSink* rtpSink,
- FramedSource* inputSource)
- {
- if (fAuxSDPLine != NULL)
- return fAuxSDPLine; // it's already been set up (for a previous client)
- if (fDummyRTPSink == NULL) { // we're not already setting it up for another, concurrent stream
- // Note: For H264 video files, the 'config' information ("profile-level-id" and "sprop-parameter-sets") isn't known
- // until we start reading the file. This means that "rtpSink"s "auxSDPLine()" will be NULL initially,
- // and we need to start reading data from our file until this changes.
- fDummyRTPSink = rtpSink;
- // Start reading the file:
- fDummyRTPSink->startPlaying(*inputSource, afterPlayingDummy, this);
- // Check whether the sink's 'auxSDPLine()' is ready:
- checkForAuxSDPLine(this);
- }
- envir().taskScheduler().doEventLoop(&fDoneFlag);
- return fAuxSDPLine;
- }
char const* H264VideoFileServerMediaSubsession::getAuxSDPLine(
RTPSink* rtpSink,
FramedSource* inputSource)
{
if (fAuxSDPLine != NULL)
return fAuxSDPLine; // it's already been set up (for a previous client)
if (fDummyRTPSink == NULL) { // we're not already setting it up for another, concurrent stream
// Note: For H264 video files, the 'config' information ("profile-level-id" and "sprop-parameter-sets") isn't known
// until we start reading the file. This means that "rtpSink"s "auxSDPLine()" will be NULL initially,
// and we need to start reading data from our file until this changes.
fDummyRTPSink = rtpSink;
// Start reading the file:
fDummyRTPSink->startPlaying(*inputSource, afterPlayingDummy, this);
// Check whether the sink's 'auxSDPLine()' is ready:
checkForAuxSDPLine(this);
}
envir().taskScheduler().doEventLoop(&fDoneFlag);
return fAuxSDPLine;
}- void H264VideoFileServerMediaSubsession::checkForAuxSDPLine1()
- {
- char const* dasl;
- if (fAuxSDPLine != NULL) {
- // Signal the event loop that we're done:
- setDoneFlag();
- } else if (fDummyRTPSink != NULL
- && (dasl = fDummyRTPSink->auxSDPLine()) != NULL) {
- fAuxSDPLine = strDup(dasl);
- fDummyRTPSink = NULL;
- // Signal the event loop that we're done:
- setDoneFlag();
- } else {
- // try again after a brief delay:
- int uSecsToDelay = 100000; // 100 ms
- nextTask() = envir().taskScheduler().scheduleDelayedTask(uSecsToDelay,
- (TaskFunc*) checkForAuxSDPLine, this);
- }
- }
void H264VideoFileServerMediaSubsession::checkForAuxSDPLine1()
{
char const* dasl;
if (fAuxSDPLine != NULL) {
// Signal the event loop that we're done:
setDoneFlag();
} else if (fDummyRTPSink != NULL
&& (dasl = fDummyRTPSink->auxSDPLine()) != NULL) {
fAuxSDPLine = strDup(dasl);
fDummyRTPSink = NULL;
// Signal the event loop that we're done:
setDoneFlag();
} else {
// try again after a brief delay:
int uSecsToDelay = 100000; // 100 ms
nextTask() = envir().taskScheduler().scheduleDelayedTask(uSecsToDelay,
(TaskFunc*) checkForAuxSDPLine, this);
}
}它检查是否已取得Aux sdp，如果取得了，设置结束标志，直接返回。如果没有，就检查是否sink中已取得了aux sdp，如果是，也设置结束标志，返回。如果还没有取得，则把这个检查函数做为delay task加入计划任务中。每100毫秒检查一次，每检查一次主要就是调用一次fDummyRTPSink->auxSDPLine()。大循环在检测到fDoneFlag改变时停止，此时已取得了aux sdp。但是如果直到文件结束也没有得到aux sdp，则afterPlayingDummy（）被执行，在其中停止掉这个大循环。然后在父Subsession类中关掉这些临时的source和sink。在直正播放时重新创建。
十 h264 RTP传输详解(2)
上一章并没有把打开文件分析文件的代码找到，因为发现它隐藏得比较深，而且H264的Source又有多个，形成了连环计。所以此章中就将文件处理与H264的Source们并在一起分析吧。
从哪里开始呢？从source开始吧!为什么要从它开始呢？我就想从这里开始，行了吧？
- FramedSource* H264VideoFileServerMediaSubsession::createNewStreamSource(
- unsigned /*clientSessionId*/,
- unsigned& estBitrate)
- {
- estBitrate = 500; // kbps, estimate
- // Create the video source:
- ByteStreamFileSource* fileSource = ByteStreamFileSource::createNew(envir(),
- fFileName);
- if (fileSource == NULL)
- return NULL;
- fFileSize = fileSource->fileSize();
- // Create a framer for the Video Elementary Stream:
- return H264VideoStreamFramer::createNew(envir(), fileSource);
- }
FramedSource* H264VideoFileServerMediaSubsession::createNewStreamSource(
unsigned /*clientSessionId*/,
unsigned& estBitrate)
{
estBitrate = 500; // kbps, estimate
// Create the video source:
ByteStreamFileSource* fileSource = ByteStreamFileSource::createNew(envir(),
fFileName);
if (fileSource == NULL)
return NULL;
fFileSize = fileSource->fileSize();
// Create a framer for the Video Elementary Stream:
return H264VideoStreamFramer::createNew(envir(), fileSource);
}先创建一个ByteStreamFileSource，显然这是一个从文件按字节读取数据的source，没什么可细说的。但是，打开文件，读写文件操作的确就在其中。最终来处理h264文件，分析其格式，解析出帧或nal的应是这个source: H264VideoStreamFramer。打开文件的地方找到了，但分析文件的代码才是更有价值的。那我们只能来看H264VideoStreamFramer。
H264VideoStreamFramer继承自MPEGVideoStreamFramer，MPEGVideoStreamFramer继承自FramedFilter,FramedFilter继承自FramedSource。
啊，中间又冒出个Filter。看到它，是不是联想到了DirectShow的filter？或者说Photoshop中的filter？它们的意义应该都差不多吧？即插入到source和render(sink)之间的处理媒体数据的东东？如果这样理解，还是更接近于photoshop中的概念。唉，说实话，我估计自己说的也不全对，反正就这样认识吧，谬不了一千里。既然我们这样认识了，那么我们就有理由相信可能会出现多个filter们一个连一个,然后高唱：手牵着脚脚牵着手一起向前走...
H264VideoStreamFramer继承自MPEGVideoStreamFramer，MPEGVideoStreamFramer比较简单，它只是把一些工作交给了MPEGVideoStreamParser（又出来个parser，这可是个新东西哦，先不要管它吧），重点来看一下。
构造函数：
- H264VideoStreamFramer::H264VideoStreamFramer(UsageEnvironment& env,
- FramedSource* inputSource,
- Boolean createParser,
- Boolean includeStartCodeInOutput)
- : MPEGVideoStreamFramer(env, inputSource),
- fIncludeStartCodeInOutput(includeStartCodeInOutput),
- fLastSeenSPS(NULL),
- fLastSeenSPSSize(0),
- fLastSeenPPS(NULL),
- fLastSeenPPSSize(0)
- {
- fParser = createParser ?
- new H264VideoStreamParser(this, inputSource,
- includeStartCodeInOutput) : NULL;
- fNextPresentationTime = fPresentationTimeBase;
- fFrameRate = 25.0; // We assume a frame rate of 25 fps,
- //unless we learn otherwise (from parsing a Sequence Parameter Set NAL unit)
- }
H264VideoStreamFramer::H264VideoStreamFramer(UsageEnvironment& env,
FramedSource* inputSource,
Boolean createParser,
Boolean includeStartCodeInOutput)
: MPEGVideoStreamFramer(env, inputSource),
fIncludeStartCodeInOutput(includeStartCodeInOutput),
fLastSeenSPS(NULL),
fLastSeenSPSSize(0),
fLastSeenPPS(NULL),
fLastSeenPPSSize(0)
{
fParser = createParser ?
new H264VideoStreamParser(this, inputSource,
includeStartCodeInOutput) : NULL;
fNextPresentationTime = fPresentationTimeBase;
fFrameRate = 25.0; // We assume a frame rate of 25 fps,
//unless we learn otherwise (from parsing a Sequence Parameter Set NAL unit)
}由于createParser肯定为真，所以主要内容是创建了H264VideoStreamParser对象（先不管这个parser）。
其它的函数就没什么可看的了，都集中在所保存的PPS与SPS上。看来分析工作移到了H264VideoStreamParser，Parser嘛，就是分析器。分析器的基类是StreamParser。StreamParser做了不少的工作，那我们就先搞明白StreamParser做了哪些工作吧，并且可能为继承者提供什么样的调用框架呢？.....我看完了，呵呵。直接说分析结果吧：
StreamParser的主要工作是实现了对数据以位为单位进行访问。因为在处理媒体格式时，按位分析是很常见的情况。这两个函数skipBits(unsigned numBits)和unsigned getBits(unsigned numBits)很明显是基于位的操作。unsigned char* fBank[2]这个变量中的两个缓冲区被轮换使用。这个类中保存了一个Source，理所当然地它应该保存ByteStreamFileSource的实例，而不是FramedFilter的。那些getBytes()或getBits()最终会导致读文件的操作。从文件读取一次数据后，StreamParser::afterGettingBytes1（）被调用，StreamParser::afterGettingBytes1（）中做一点简单的工作后便调用fClientContinueFunc这个回调函数。fClientContinueFunc可能指向Frame的函数体也可能是指向RtpSink的函数体－－因为Framer完全可以把RtpSink的函数体传给Parser。至于到底指向哪个，只能在进一步分析之后才得知。
下面再来分析StreamParser的儿子:MPEGVideoStreamParser。
- MPEGVideoStreamParser::MPEGVideoStreamParser(
- MPEGVideoStreamFramer* usingSource,
- FramedSource* inputSource)
- : StreamParser(inputSource,
- FramedSource::handleClosure,
- usingSource,
- &MPEGVideoStreamFramer::continueReadProcessing,
- usingSource),
- fUsingSource(usingSource)
- {
- }
MPEGVideoStreamParser::MPEGVideoStreamParser(
MPEGVideoStreamFramer* usingSource,
FramedSource* inputSource)
: StreamParser(inputSource,
FramedSource::handleClosure,
usingSource,
&MPEGVideoStreamFramer::continueReadProcessing,
usingSource),
fUsingSource(usingSource)
{
}MPEGVideoStreamParser的构造函数中有很多有意思的东西。
首先参数usingSource是什么意思？表示正在使用这个Parser的Source? inputSource 很明确，就是能获取数据的source，也就是 ByteStreamFileSource。而且很明显的，StreamParser中保存的source是ByteStreamFileSource。从传入给StreamParser的回调函数以及它们的参数可以看出，这些回调函数全是指向的StreamParser的子类的函数（为啥不用虚函数的方式？哦，回调函数全是静态函数，不能成为虚函数）。这说明在每读一次数据后，MPEGVideoStreamFramer::continueReadProcessing()被调用，在其中对帧进行界定和分析，完成后再调用RTPSink的相应函数，RTPSink中对帧进行打包和发送（还记得吗，不记得了请回头看以前的章节）。
MPEGVideoStreamParser的fTo是RTPSink传入的缓冲指针，其saveByte(),save4Bytes()是把数据从StreamParser的缓冲把数据复制到fTo中，是给继承类使用的。saveToNextCode()是复制数据直到遇到一个同步字节串（比如h264中分隔nal的那一陀东东，当然此处的跟h264还不一样），也是给继承类使用的。纯虚函数parse()很明显是留继承类去写帧分析代码的地方。registerReadInterest()被调用者用来告诉MPEGVideoStreamParser其接收帧的缓冲地址与容量。
现在应该来分析一下MPEGVideoStreamFramer，以明确MPEGVideoStreamFramer与MPEGVideoStreamParser是怎样配合的。
MPEGVideoStreamFramer中用到Parser的重要的函数只有两个，一是：
- void MPEGVideoStreamFramer::doGetNextFrame()
- {
- fParser->registerReadInterest(fTo, fMaxSize);
- continueReadProcessing();
- }
void MPEGVideoStreamFramer::doGetNextFrame()
{
fParser->registerReadInterest(fTo, fMaxSize);
continueReadProcessing();
}很简单，只是告诉了Parser保存帧的缓冲和缓冲的大小，然后执行continueReadProcessing()，那么来看一下continueReadProcessing()：
- void MPEGVideoStreamFramer::continueReadProcessing()
- {
- unsigned acquiredFrameSize = fParser->parse();
- if (acquiredFrameSize > 0) {
- // We were able to acquire a frame from the input.
- // It has already been copied to the reader's space.
- fFrameSize = acquiredFrameSize;
- fNumTruncatedBytes = fParser->numTruncatedBytes();
- // "fPresentationTime" should have already been computed.
- // Compute "fDurationInMicroseconds" now:
- fDurationInMicroseconds =
- (fFrameRate == 0.0 || ((int) fPictureCount) < 0) ?
- 0 : (unsigned) ((fPictureCount * 1000000) / fFrameRate);
- fPictureCount = 0;
- // Call our own 'after getting' function. Because we're not a 'leaf'
- // source, we can call this directly, without risking infinite recursion.
- afterGetting(this);
- } else {
- // We were unable to parse a complete frame from the input, because:
- // - we had to read more data from the source stream, or
- // - the source stream has ended.
- }
- }
void MPEGVideoStreamFramer::continueReadProcessing()
{
unsigned acquiredFrameSize = fParser->parse();
if (acquiredFrameSize > 0) {
// We were able to acquire a frame from the input.
// It has already been copied to the reader's space.
fFrameSize = acquiredFrameSize;
fNumTruncatedBytes = fParser->numTruncatedBytes();
// "fPresentationTime" should have already been computed.
// Compute "fDurationInMicroseconds" now:
fDurationInMicroseconds =
(fFrameRate == 0.0 || ((int) fPictureCount) < 0) ?
0 : (unsigned) ((fPictureCount * 1000000) / fFrameRate);
fPictureCount = 0;
// Call our own 'after getting' function. Because we're not a 'leaf'
// source, we can call this directly, without risking infinite recursion.
afterGetting(this);
} else {
// We were unable to parse a complete frame from the input, because:
// - we had to read more data from the source stream, or
// - the source stream has ended.
}
}先利用Parser进行分析（应该是解析出一帧吧？），分析完成后，帧数据已到了MPEGVideoStreamFramer的缓冲fTo中。计算出帧的持续时间后，调用FrameSource的afterGetting()，最终会调用RTPSink的函数。
看到这里，可以总结一下，其实看来看去，Parser直正被外部使用的函数几乎只有一个：parse()。
下面可以看H264VideoStreamParser了。其实也很简单，多了一些用于分析h264格式的函数，当然是非公开的，只供自己使用的。在哪里使用呢？当然是在parser()中使用。至于H264VideoStreamFramer前面已经说过了，没什么太多的东西，所以就不看了。总结起来也就是这样：RTPSink向H264VideoStreamFramer要下一帧（其实h264中肯定不是一帧了，而是一个NAL Unit），H264VideoStreamFramer告诉H264VideoStreamParser输出缓冲和容内的字节数，然后调用H264VideoStreamParser的parser()函数，parser()中调用ByteStreamFileSource从文件中读取数据，直到parser()获得完整的一帧，parser()返回，H264VideoStreamFramer进行一些自己的处理后把这一帧返回给了RTPSink（当然是以回调函数的方式返回）。
还有一个东西，H264FUAFragmenter，被H264VideoRTPSink所使用，继承自FramedFilter。它最初在RTPSink开始播放后创建，如下：
- Boolean H264VideoRTPSink::continuePlaying()
- {
- // First, check whether we have a 'fragmenter' class set up yet.
- // If not, create it now:
- if (fOurFragmenter == NULL) {
- fOurFragmenter = new H264FUAFragmenter(envir(), fSource,
- OutPacketBuffer::maxSize,
- ourMaxPacketSize() - 12/*RTP hdr size*/);
- fSource = fOurFragmenter;
- }
- // Then call the parent class's implementation:
- return MultiFramedRTPSink::continuePlaying();
- }
Boolean H264VideoRTPSink::continuePlaying()
{
// First, check whether we have a 'fragmenter' class set up yet.
// If not, create it now:
if (fOurFragmenter == NULL) {
fOurFragmenter = new H264FUAFragmenter(envir(), fSource,
OutPacketBuffer::maxSize,
ourMaxPacketSize() - 12/*RTP hdr size*/);
fSource = fOurFragmenter;
}
// Then call the parent class's implementation:
return MultiFramedRTPSink::continuePlaying();
}并且它取代了H264VideoStreamFramer成为直接与RTPSink发生关系的source.如此一来，RTPSink要获取帧时，都是从它获取的．看它最主要的一个函数吧：
- void H264FUAFragmenter::doGetNextFrame()
- {
- if (fNumValidDataBytes == 1) {
- // We have no NAL unit data currently in the buffer. Read a new one:
- fInputSource->getNextFrame(&fInputBuffer[1], fInputBufferSize - 1,
- afterGettingFrame, this, FramedSource::handleClosure, this);
- } else {
- // We have NAL unit data in the buffer. There are three cases to consider:
- // 1. There is a new NAL unit in the buffer, and it's small enough to deliver
- // to the RTP sink (as is).
- // 2. There is a new NAL unit in the buffer, but it's too large to deliver to
- // the RTP sink in its entirety. Deliver the first fragment of this data,
- // as a FU-A packet, with one extra preceding header byte.
- // 3. There is a NAL unit in the buffer, and we've already delivered some
- // fragment(s) of this. Deliver the next fragment of this data,
- // as a FU-A packet, with two extra preceding header bytes.
- if (fMaxSize < fMaxOutputPacketSize) { // shouldn't happen
- envir() << "H264FUAFragmenter::doGetNextFrame(): fMaxSize ("
- << fMaxSize << ") is smaller than expected\n";
- } else {
- fMaxSize = fMaxOutputPacketSize;
- }
- fLastFragmentCompletedNALUnit = True; // by default
- if (fCurDataOffset == 1) { // case 1 or 2
- if (fNumValidDataBytes - 1 <= fMaxSize) { // case 1
- memmove(fTo, &fInputBuffer[1], fNumValidDataBytes - 1);
- fFrameSize = fNumValidDataBytes - 1;
- fCurDataOffset = fNumValidDataBytes;
- } else { // case 2
- // We need to send the NAL unit data as FU-A packets. Deliver the first
- // packet now. Note that we add FU indicator and FU header bytes to the front
- // of the packet (reusing the existing NAL header byte for the FU header).
- fInputBuffer[0] = (fInputBuffer[1] & 0xE0) | 28; // FU indicator
- fInputBuffer[1] = 0x80 | (fInputBuffer[1] & 0x1F); // FU header (with S bit)
- memmove(fTo, fInputBuffer, fMaxSize);
- fFrameSize = fMaxSize;
- fCurDataOffset += fMaxSize - 1;
- fLastFragmentCompletedNALUnit = False;
- }
- } else { // case 3
- // We are sending this NAL unit data as FU-A packets. We've already sent the
- // first packet (fragment). Now, send the next fragment. Note that we add
- // FU indicator and FU header bytes to the front. (We reuse these bytes that
- // we already sent for the first fragment, but clear the S bit, and add the E
- // bit if this is the last fragment.)
- fInputBuffer[fCurDataOffset - 2] = fInputBuffer[0]; // FU indicator
- fInputBuffer[fCurDataOffset - 1] = fInputBuffer[1] & ~0x80; // FU header (no S bit)
- unsigned numBytesToSend = 2 + fNumValidDataBytes - fCurDataOffset;
- if (numBytesToSend > fMaxSize) {
- // We can't send all of the remaining data this time:
- numBytesToSend = fMaxSize;
- fLastFragmentCompletedNALUnit = False;
- } else {
- // This is the last fragment:
- fInputBuffer[fCurDataOffset - 1] |= 0x40; // set the E bit in the FU header
- fNumTruncatedBytes = fSaveNumTruncatedBytes;
- }
- memmove(fTo, &fInputBuffer[fCurDataOffset - 2], numBytesToSend);
- fFrameSize = numBytesToSend;
- fCurDataOffset += numBytesToSend - 2;
- }
- if (fCurDataOffset >= fNumValidDataBytes) {
- // We're done with this data. Reset the pointers for receiving new data:
- fNumValidDataBytes = fCurDataOffset = 1;
- }
- // Complete delivery to the client:
- FramedSource::afterGetting(this);
- }
- }
void H264FUAFragmenter::doGetNextFrame()
{
if (fNumValidDataBytes == 1) {
// We have no NAL unit data currently in the buffer. Read a new one:
fInputSource->getNextFrame(&fInputBuffer[1], fInputBufferSize - 1,
afterGettingFrame, this, FramedSource::handleClosure, this);
} else {
// We have NAL unit data in the buffer. There are three cases to consider:
// 1. There is a new NAL unit in the buffer, and it's small enough to deliver
// to the RTP sink (as is).
// 2. There is a new NAL unit in the buffer, but it's too large to deliver to
// the RTP sink in its entirety. Deliver the first fragment of this data,
// as a FU-A packet, with one extra preceding header byte.
// 3. There is a NAL unit in the buffer, and we've already delivered some
// fragment(s) of this. Deliver the next fragment of this data,
// as a FU-A packet, with two extra preceding header bytes.
if (fMaxSize < fMaxOutputPacketSize) { // shouldn't happen
envir() << "H264FUAFragmenter::doGetNextFrame(): fMaxSize ("
<< fMaxSize << ") is smaller than expected\n";
} else {
fMaxSize = fMaxOutputPacketSize;
}
fLastFragmentCompletedNALUnit = True; // by default
if (fCurDataOffset == 1) { // case 1 or 2
if (fNumValidDataBytes - 1 <= fMaxSize) { // case 1
memmove(fTo, &fInputBuffer[1], fNumValidDataBytes - 1);
fFrameSize = fNumValidDataBytes - 1;
fCurDataOffset = fNumValidDataBytes;
} else { // case 2
// We need to send the NAL unit data as FU-A packets. Deliver the first
// packet now. Note that we add FU indicator and FU header bytes to the front
// of the packet (reusing the existing NAL header byte for the FU header).
fInputBuffer[0] = (fInputBuffer[1] & 0xE0) | 28; // FU indicator
fInputBuffer[1] = 0x80 | (fInputBuffer[1] & 0x1F); // FU header (with S bit)
memmove(fTo, fInputBuffer, fMaxSize);
fFrameSize = fMaxSize;
fCurDataOffset += fMaxSize - 1;
fLastFragmentCompletedNALUnit = False;
}
} else { // case 3
// We are sending this NAL unit data as FU-A packets. We've already sent the
// first packet (fragment). Now, send the next fragment. Note that we add
// FU indicator and FU header bytes to the front. (We reuse these bytes that
// we already sent for the first fragment, but clear the S bit, and add the E
// bit if this is the last fragment.)
fInputBuffer[fCurDataOffset - 2] = fInputBuffer[0]; // FU indicator
fInputBuffer[fCurDataOffset - 1] = fInputBuffer[1] & ~0x80; // FU header (no S bit)
unsigned numBytesToSend = 2 + fNumValidDataBytes - fCurDataOffset;
if (numBytesToSend > fMaxSize) {
// We can't send all of the remaining data this time:
numBytesToSend = fMaxSize;
fLastFragmentCompletedNALUnit = False;
} else {
// This is the last fragment:
fInputBuffer[fCurDataOffset - 1] |= 0x40; // set the E bit in the FU header
fNumTruncatedBytes = fSaveNumTruncatedBytes;
}
memmove(fTo, &fInputBuffer[fCurDataOffset - 2], numBytesToSend);
fFrameSize = numBytesToSend;
fCurDataOffset += numBytesToSend - 2;
}
if (fCurDataOffset >= fNumValidDataBytes) {
// We're done with this data. Reset the pointers for receiving new data:
fNumValidDataBytes = fCurDataOffset = 1;
}
// Complete delivery to the client:
FramedSource::afterGetting(this);
}
}如果输入缓冲中没有数据，调用fInputSource->getNextFrame()，fInputSource是H264VideoStreamFramer，H264VideoStreamFramer的getNextFrame()会调用H264VideoStreamParser的parser()，parser()又调用ByteStreamFileSource获取数据，然后分析，parser()完成后会调用：
- void H264FUAFragmenter::afterGettingFrame1(
- unsigned frameSize,
- unsigned numTruncatedBytes,
- struct timeval presentationTime,
- unsigned durationInMicroseconds)
- {
- fNumValidDataBytes += frameSize;
- fSaveNumTruncatedBytes = numTruncatedBytes;
- fPresentationTime = presentationTime;
- fDurationInMicroseconds = durationInMicroseconds;
- // Deliver data to the client:
- doGetNextFrame();
- }
void H264FUAFragmenter::afterGettingFrame1(
unsigned frameSize,
unsigned numTruncatedBytes,
struct timeval presentationTime,
unsigned durationInMicroseconds)
{
fNumValidDataBytes += frameSize;
fSaveNumTruncatedBytes = numTruncatedBytes;
fPresentationTime = presentationTime;
fDurationInMicroseconds = durationInMicroseconds;
// Deliver data to the client:
doGetNextFrame();
}然后又调用回H264FUAFragmenter::doGetNextFrame()，此时输入缓冲中有数据了，H264FUAFragmenter就进行分析处理．H264FUAFragmenter又对数据做了什么呢？
607
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
