视音频数据处理入门：FLV封装格式解析

Posted 2020-09-27 wzjhoutai

=====================================================

视音频数据处理入门系列文章：

视音频数据处理入门：RGB、YUV像素数据处理

视音频数据处理入门：PCM音频採样数据处理

视音频数据处理入门：H.264视频码流解析

视音频数据处理入门：AAC音频码流解析

视音频数据处理入门：FLV封装格式解析

视音频数据处理入门：UDP-RTP协议解析

=====================================================

前两篇文章介绍了音频码流处理程序和视频码流处理程序。本文介绍将他们打包到一起后的数据——封装格式数据的处理程序。封装格式数据在视频播放器中的位置例如以下所看到的。

本文中的程序是一个FLV封装格式解析程序。该程序能够从FLV中分析得到它的基本单元Tag，而且能够简单解析Tag首部的字段。通过改动该程序能够实现不同的FLV格式数据处理功能。

原理

FLV封装格式是由一个FLV Header文件头和一个一个的Tag组成的。

Tag中包括了音频数据以及视频数据。FLV的结构例如以下图所看到的。

有关FLV的格式本文不再做记录。能够參考文章《视音频编解码学习工程：FLV封装格式分析器》。本文的程序实现了FLV中的FLV Header和Tag的解析。并能够分离出当中的音频流。

代码

整个程序位于simplest_flv_parser()函数中，例如以下所看到的。

/**
 * 最简单的视音频数据处理演示样例
 * Simplest MediaData Test
 *
 * 雷霄骅 Lei Xiaohua
 * [email protected]
 * 中国传媒大学/数字电视技术
 * Communication University of China / Digital TV Technology
 * http://blog.csdn.net/leixiaohua1020
 *
 * 本项目包括例如以下几种视音频測试演示样例：
 *  (1)像素数据处理程序。包括RGB和YUV像素格式处理的函数。
 *  (2)音频採样数据处理程序。包括PCM音频採样格式处理的函数。
 *  (3)H.264码流分析程序。能够分离并解析NALU。
 *  (4)AAC码流分析程序。能够分离并解析ADTS帧。
 *  (5)FLV封装格式分析程序。能够将FLV中的MP3音频码流分离出来。
 *  (6)UDP-RTP协议分析程序。能够将分析UDP/RTP/MPEG-TS数据包。
 *
 * This project contains following samples to handling multimedia data:
 *  (1) Video pixel data handling program. It contains several examples to handle RGB and YUV data.
 *  (2) Audio sample data handling program. It contains several examples to handle PCM data.
 *  (3) H.264 stream analysis program. It can parse H.264 bitstream and analysis NALU of stream.
 *  (4) AAC stream analysis program. It can parse AAC bitstream and analysis ADTS frame of stream.
 *  (5) FLV format analysis program. It can analysis FLV file and extract MP3 audio stream.
 *  (6) UDP-RTP protocol analysis program. It can analysis UDP/RTP/MPEG-TS Packet.
 *
 */
#include <stdio.h>
#include <stdlib.h>
#include <string.h>

//Important!
#pragma pack(1)


#define TAG_TYPE_SCRIPT 18
#define TAG_TYPE_AUDIO  8
#define TAG_TYPE_VIDEO  9

typedef unsigned char byte;
typedef unsigned int uint;

typedef struct {
	byte Signature[3];
	byte Version;
	byte Flags;
	uint DataOffset;
} FLV_HEADER;

typedef struct {
	byte TagType;
	byte DataSize[3];
	byte Timestamp[3];
	uint Reserved;
} TAG_HEADER;


//reverse_bytes - turn a BigEndian byte array into a LittleEndian integer
uint reverse_bytes(byte *p, char c) {
	int r = 0;
	int i;
	for (i=0; i<c; i++) 
		r |= ( *(p+i) << (((c-1)*8)-8*i));
	return r;
}

/**
 * Analysis FLV file
 * @param url    Location of input FLV file.
 */

int simplest_flv_parser(char *url){

	//whether output audio/video stream
	int output_a=1;
	int output_v=1;
	//-------------
	FILE *ifh=NULL,*vfh=NULL, *afh = NULL;

	//FILE *myout=fopen("output_log.txt","wb+");
	FILE *myout=stdout;

	FLV_HEADER flv;
	TAG_HEADER tagheader;
	uint previoustagsize, previoustagsize_z=0;
	uint ts=0, ts_new=0;

	ifh = fopen(url, "rb+");
	if ( ifh== NULL) {
		printf("Failed to open files!");
		return -1;
	}

	//FLV file header
	fread((char *)&flv,1,sizeof(FLV_HEADER),ifh);

	fprintf(myout,"============== FLV Header ==============\n");
	fprintf(myout,"Signature:  0x %c %c %c\n",flv.Signature[0],flv.Signature[1],flv.Signature[2]);
	fprintf(myout,"Version:    0x %X\n",flv.Version);
	fprintf(myout,"Flags  :    0x %X\n",flv.Flags);
	fprintf(myout,"HeaderSize: 0x %X\n",reverse_bytes((byte *)&flv.DataOffset, sizeof(flv.DataOffset)));
	fprintf(myout,"========================================\n");

	//move the file pointer to the end of the header
	fseek(ifh, reverse_bytes((byte *)&flv.DataOffset, sizeof(flv.DataOffset)), SEEK_SET);

	//process each tag
	do {

		previoustagsize = _getw(ifh);

		fread((void *)&tagheader,sizeof(TAG_HEADER),1,ifh);

		//int temp_datasize1=reverse_bytes((byte *)&tagheader.DataSize, sizeof(tagheader.DataSize));
		int tagheader_datasize=tagheader.DataSize[0]*65536+tagheader.DataSize[1]*256+tagheader.DataSize[2];
		int tagheader_timestamp=tagheader.Timestamp[0]*65536+tagheader.Timestamp[1]*256+tagheader.Timestamp[2];

		char tagtype_str[10];
		switch(tagheader.TagType){
		case TAG_TYPE_AUDIO:sprintf(tagtype_str,"AUDIO");break;
		case TAG_TYPE_VIDEO:sprintf(tagtype_str,"VIDEO");break;
		case TAG_TYPE_SCRIPT:sprintf(tagtype_str,"SCRIPT");break;
		default:sprintf(tagtype_str,"UNKNOWN");break;
		}
		fprintf(myout,"[%6s] %6d %6d |",tagtype_str,tagheader_datasize,tagheader_timestamp);

		//if we are not past the end of file, process the tag
		if (feof(ifh)) {
			break;
		}

		//process tag by type
		switch (tagheader.TagType) {

		case TAG_TYPE_AUDIO:{ 
			char audiotag_str[100]={0};
			strcat(audiotag_str,"| ");
			char tagdata_first_byte;
			tagdata_first_byte=fgetc(ifh);
			int x=tagdata_first_byte&0xF0;
			x=x>>4;
			switch (x)
			{
			case 0:strcat(audiotag_str,"Linear PCM, platform endian");break;
			case 1:strcat(audiotag_str,"ADPCM");break;
			case 2:strcat(audiotag_str,"MP3");break;
			case 3:strcat(audiotag_str,"Linear PCM, little endian");break;
			case 4:strcat(audiotag_str,"Nellymoser 16-kHz mono");break;
			case 5:strcat(audiotag_str,"Nellymoser 8-kHz mono");break;
			case 6:strcat(audiotag_str,"Nellymoser");break;
			case 7:strcat(audiotag_str,"G.711 A-law logarithmic PCM");break;
			case 8:strcat(audiotag_str,"G.711 mu-law logarithmic PCM");break;
			case 9:strcat(audiotag_str,"reserved");break;
			case 10:strcat(audiotag_str,"AAC");break;
			case 11:strcat(audiotag_str,"Speex");break;
			case 14:strcat(audiotag_str,"MP3 8-Khz");break;
			case 15:strcat(audiotag_str,"Device-specific sound");break;
			default:strcat(audiotag_str,"UNKNOWN");break;
			}
			strcat(audiotag_str,"| ");
			x=tagdata_first_byte&0x0C;
			x=x>>2;
			switch (x)
			{
			case 0:strcat(audiotag_str,"5.5-kHz");break;
			case 1:strcat(audiotag_str,"1-kHz");break;
			case 2:strcat(audiotag_str,"22-kHz");break;
			case 3:strcat(audiotag_str,"44-kHz");break;
			default:strcat(audiotag_str,"UNKNOWN");break;
			}
			strcat(audiotag_str,"| ");
			x=tagdata_first_byte&0x02;
			x=x>>1;
			switch (x)
			{
			case 0:strcat(audiotag_str,"8Bit");break;
			case 1:strcat(audiotag_str,"16Bit");break;
			default:strcat(audiotag_str,"UNKNOWN");break;
			}
			strcat(audiotag_str,"| ");
			x=tagdata_first_byte&0x01;
			switch (x)
			{
			case 0:strcat(audiotag_str,"Mono");break;
			case 1:strcat(audiotag_str,"Stereo");break;
			default:strcat(audiotag_str,"UNKNOWN");break;
			}
			fprintf(myout,"%s",audiotag_str);

			//if the output file hasn‘t been opened, open it.
			if(output_a!=0&&afh == NULL){
				afh = fopen("output.mp3", "wb");
			}

			//TagData - First Byte Data
			int data_size=reverse_bytes((byte *)&tagheader.DataSize, sizeof(tagheader.DataSize))-1;
			if(output_a!=0){
				//TagData+1
				for (int i=0; i<data_size; i++)
					fputc(fgetc(ifh),afh);

			}else{
				for (int i=0; i<data_size; i++)
					fgetc(ifh);
			}
			break;
		}
		case TAG_TYPE_VIDEO:{
			char videotag_str[100]={0};
			strcat(videotag_str,"| ");
			char tagdata_first_byte;
			tagdata_first_byte=fgetc(ifh);
			int x=tagdata_first_byte&0xF0;
			x=x>>4;
			switch (x)
			{
			case 1:strcat(videotag_str,"key frame  ");break;
			case 2:strcat(videotag_str,"inter frame");break;
			case 3:strcat(videotag_str,"disposable inter frame");break;
			case 4:strcat(videotag_str,"generated keyframe");break;
			case 5:strcat(videotag_str,"video info/command frame");break;
			default:strcat(videotag_str,"UNKNOWN");break;
			}
			strcat(videotag_str,"| ");
			x=tagdata_first_byte&0x0F;
			switch (x)
			{
			case 1:strcat(videotag_str,"JPEG (currently unused)");break;
			case 2:strcat(videotag_str,"Sorenson H.263");break;
			case 3:strcat(videotag_str,"Screen video");break;
			case 4:strcat(videotag_str,"On2 VP6");break;
			case 5:strcat(videotag_str,"On2 VP6 with alpha channel");break;
			case 6:strcat(videotag_str,"Screen video version 2");break;
			case 7:strcat(videotag_str,"AVC");break;
			default:strcat(videotag_str,"UNKNOWN");break;
			}
			fprintf(myout,"%s",videotag_str);

			fseek(ifh, -1, SEEK_CUR);
			//if the output file hasn‘t been opened, open it.
			if (vfh == NULL&&output_v!=0) {
				//write the flv header (reuse the original file‘s hdr) and first previoustagsize
					vfh = fopen("output.flv", "wb");
					fwrite((char *)&flv,1, sizeof(flv),vfh);
					fwrite((char *)&previoustagsize_z,1,sizeof(previoustagsize_z),vfh);
			}
#if 0
			//Change Timestamp
			//Get Timestamp
			ts = reverse_bytes((byte *)&tagheader.Timestamp, sizeof(tagheader.Timestamp));
			ts=ts*2;
			//Writeback Timestamp
			ts_new = reverse_bytes((byte *)&ts, sizeof(ts));
			memcpy(&tagheader.Timestamp, ((char *)&ts_new) + 1, sizeof(tagheader.Timestamp));
#endif


			//TagData + Previous Tag Size
			int data_size=reverse_bytes((byte *)&tagheader.DataSize, sizeof(tagheader.DataSize))+4;
			if(output_v!=0){
				//TagHeader
				fwrite((char *)&tagheader,1, sizeof(tagheader),vfh);
				//TagData
				for (int i=0; i<data_size; i++)
					fputc(fgetc(ifh),vfh);
			}else{
				for (int i=0; i<data_size; i++)
					fgetc(ifh);
			}
			//rewind 4 bytes, because we need to read the previoustagsize again for the loop‘s sake
			fseek(ifh, -4, SEEK_CUR);

			break;
			}
		default:

			//skip the data of this tag
			fseek(ifh, reverse_bytes((byte *)&tagheader.DataSize, sizeof(tagheader.DataSize)), SEEK_CUR);
		}

		fprintf(myout,"\n");

	} while (!feof(ifh));


	_fcloseall();

	return 0;
}

上文中的函数调用方法例如以下所看到的。

simplest_flv_parser("cuc_ieschool.flv");

结果

本程序的输入为一个FLV的文件路径，输出为FLV的统计数据，例如以下图所看到的。

此外本程序还能够分离FLV中的视频码流和音频码流。须要注意的是本程序并不能分离一些特定类型的音频（比如AAC）和视频，这一工作有待以后有时间再完毕。

下载

Simplest mediadata test

项目主页

SourceForge：https://sourceforge.net/projects/simplest-mediadata-test/

Github：https://github.com/leixiaohua1020/simplest_mediadata_test

开源中国：http://git.oschina.net/leixiaohua1020/simplest_mediadata_test


CSDN下载地址：http://download.csdn.net/detail/leixiaohua1020/9422409


本项目包括例如以下几种视音频数据解析演示样例：
 (1)像素数据处理程序。

包括RGB和YUV像素格式处理的函数。

 (2)音频採样数据处理程序。包括PCM音频採样格式处理的函数。

 (3)H.264码流分析程序。

能够分离并解析NALU。
 (4)AAC码流分析程序。能够分离并解析ADTS帧。
 (5)FLV封装格式分析程序。能够将FLV中的MP3音频码流分离出来。
 (6)UDP-RTP协议分析程序。能够将分析UDP/RTP/MPEG-TS数据包。






雷霄骅 (Lei Xiaohua)
[email protected]
http://blog.csdn.net/leixiaohua1020