本文中的程序是一个H.264码流解析程序。该程序可以从H.264码流中分析得到它的基本单元NALU，并且可以简单解析NALU首部的字段。
原理
H.264原始码流（又称为“裸流”）是由一个一个的NALU组成的。他们的结构如下图所示。
image.png
其中每个NALU之间通过startcode（起始码）进行分隔，起始码分成两种：0x000001（3Byte）或者0x00000001（4Byte）。如果NALU对应的Slice为一帧的开始就用0x00000001，否则就用0x000001。
H.264码流解析的步骤就是首先从码流中搜索0x000001和0x00000001，分离出NALU；然后再分析NALU的各个字段。本文的程序即实现了上述的两个步骤。
『NALU』的格式如下图3（引用H264 PDF）所示：
image.png
很明显，『NALU』由头和身体两个部分组成：
-
头：一般存储标志信息，譬如NALU的类型。存储了和编解码信息相关的数据；
-
身体：存储了真正的数据。但实际上，这块也会相对比较复杂，过H264的一个目的是“网络友好性”，说白了就是能够很好地适配各种传输格式。所以根据实际采用数据传输流格式，也会对这部分数据格式再进行处理。
代码
#import "ViewController.h"
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
typedef enum {
NALU_TYPE_SLICE = 1,
NALU_TYPE_DPA = 2,
NALU_TYPE_DPB = 3,
NALU_TYPE_DPC = 4,
NALU_TYPE_IDR = 5,
NALU_TYPE_SEI = 6,
NALU_TYPE_SPS = 7,
NALU_TYPE_PPS = 8,
NALU_TYPE_AUD = 9,
NALU_TYPE_EOSEQ = 10,
NALU_TYPE_EOSTREAM = 11,
NALU_TYPE_FILL = 12,
} NaluType;
typedef enum {
NALU_PRIORITY_DISPOSABLE = 0,
NALU_PRIRITY_LOW = 1,
NALU_PRIORITY_HIGH = 2,
NALU_PRIORITY_HIGHEST = 3
} NaluPriority;
/**
NALU = NALU Header + NALU Body
1.NALU Header
首先，『NALU Header』只占1个字节，即8位，其组成如下：
| forbidden_zero_bit | nal_ref_idc | nal_unit_type |
`--------------------+-------------+---------------`
| 1 bit | 2 bit | 5 bit |
*/
typedef struct
{
int startcodeprefix_len; //! 4 for parameter sets and first slice in picture, 3 for everything else (suggested)
unsigned len; //! Length of the NAL unit (Excluding the start code, which does not belong to the NALU)
unsigned max_size; //! Nal Unit Buffer size 这个值是自己设置的，项目里设置是100000， 和nalu的结构没有关系
int forbidden_bit; //! should be always FALSE 占用1位
int nal_reference_idc; //! NALU_PRIORITY_xxxx 占用2位
int nal_unit_type; //! NALU_TYPE_xxxx 占用5位
char *buf; //! contains the first byte followed by the EBSP NALU的数据体部分数据
} NALU_t;
FILE *h264bitstream = NULL; //!< the bit stream file
int info2=0, info3=0;
static int FindStartCode2 (unsigned char *Buf){
if(Buf[0]!=0 || Buf[1]!=0 || Buf[2] !=1) return 0; //查找0x000001?
else return 1;
}
static int FindStartCode3 (unsigned char *Buf){
if(Buf[0]!=0 || Buf[1]!=0 || Buf[2] !=0 || Buf[3] !=1) return 0;//查找0x00000001?
else return 1;
}
// 获取Annexb格式的NALU，注意Annex B和 AVCC格式的区别，可以自行百度
int GetAnnexbNALU (NALU_t *nalu){
int pos = 0;
int StartCodeFound, rewind;
unsigned char *Buf;
if ((Buf = (unsigned char*)calloc (nalu->max_size , sizeof(char))) == NULL)
printf ("GetAnnexbNALU: Could not allocate Buf memory\n");
nalu->startcodeprefix_len=3;
//成功读取的元素总数会以 size_t 对象返回，size_t 对象是一个整型数据类型。如果总数与 nmemb 参数不同，则可能发生了一个错误或者到达了文件末尾。
if (3 != fread (Buf, 1, 3, h264bitstream)){// 读取3个字节
free(Buf);
return 0;
}
info2 = FindStartCode2 (Buf);// 查找startCode 0x000001
if(info2 != 1) {// 没找到
if(1 != fread(Buf+3, 1, 1, h264bitstream)){// 读取一个字节
free(Buf);
return 0;
}
info3 = FindStartCode3 (Buf);// 查找startCode 0x00000001
if (info3 != 1){
free(Buf);
return -1;
}
else {// 找到了startCode 0x00000001
pos = 4;
nalu->startcodeprefix_len = 4;
}
}
else{//// 找到了startCode 0x000001
nalu->startcodeprefix_len = 3;
pos = 3;
}
StartCodeFound = 0;
info2 = 0;
info3 = 0;
while (!StartCodeFound){// 循环查找startCode
if (feof (h264bitstream)){
nalu->len = (pos-1)-nalu->startcodeprefix_len;
memcpy (nalu->buf, &Buf[nalu->startcodeprefix_len], nalu->len);
nalu->forbidden_bit = nalu->buf[0] & 0x80; //1 bit 0x80的二进制为10000000
nalu->nal_reference_idc = nalu->buf[0] & 0x60; // 2 bit , 0x60的二进制为1100000
nalu->nal_unit_type = (nalu->buf[0]) & 0x1f;// 5 bit 0x1f的十进制是31，31的二进制为11111
free(Buf);
return pos-1;
}
/**
int fgetc(FILE *stream)
从指定的流 stream 获取下一个字符（一个无符号字符），并把位置标识符往前移动。
*/
Buf[pos++] = fgetc (h264bitstream);// pos位置加1
// 查找startCode
info3 = FindStartCode3(&Buf[pos-4]);
if(info3 != 1)
info2 = FindStartCode2(&Buf[pos-3]);
StartCodeFound = (info2 == 1 || info3 == 1);
}
// Here, we have found another start code (and read length of startcode bytes more than we should
// have. Hence, go back in the file
rewind = (info3 == 1)? -4 : -3;
/**
int fseek(FILE *stream, long int offset, int whence)
设置流 stream 的文件位置为给定的偏移 offset，参数 offset 意味着从给定的 whence 位置查找的字节数。
*/
if (0 != fseek (h264bitstream, rewind, SEEK_CUR)){
free(Buf);
printf("GetAnnexbNALU: Cannot fseek in the bit stream file");
}
// Here the Start code, the complete NALU, and the next start code is in the Buf.
// The size of Buf is pos, pos+rewind are the number of bytes excluding the next
// start code, and (pos+rewind)-startcodeprefix_len is the size of the NALU excluding the start code
nalu->len = (pos+rewind)-nalu->startcodeprefix_len;
memcpy (nalu->buf, &Buf[nalu->startcodeprefix_len], nalu->len);//给nalu填充数据，填充的数据是不包含startCode(本身NALU的定义就是NALU header + NALU body，并不包含startCode）,但是包含NALU header 从Buf偏移startcode长度的字节数位置开始，填充长度为nalu->len,
nalu->forbidden_bit = nalu->buf[0] & 0x80; //1 bit 0x80的二进制为10000000
nalu->nal_reference_idc = nalu->buf[0] & 0x60; // 2 bit 0x60的二进制为1100000
nalu->nal_unit_type = (nalu->buf[0]) & 0x1f;// 5 bit 0x1f的十进制是31，31的二进制为11111
free(Buf);
return (pos+rewind);
}
//H.264码流解析的步骤就是首先从码流中搜索0x000001和0x00000001，分离出NALU；然后再分析NALU的各个字段。本文的程序即实现了上述的两个步骤。
/**
* Analysis H.264 Bitstream
* @param url Location of input H.264 bitstream file.
*/
int simplest_h264_parser(char *url){
NALU_t *n;
int buffersize=100000;
//FILE *myout=fopen("output_log.txt","wb+");
FILE *myout=stdout;
h264bitstream=fopen(url, "rb+");
if (h264bitstream==NULL){
printf("Open file error\n");
return 0;
}
n = (NALU_t*)calloc (1, sizeof (NALU_t));
if (n == NULL){
printf("Alloc NALU Error\n");
return 0;
}
n->max_size=buffersize;
n->buf = (char*)calloc (buffersize, sizeof (char));
if (n->buf == NULL){
free (n);
printf ("AllocNALU: n->buf");
return 0;
}
int data_offset=0;
int nal_num=0;
printf("-----+-------- NALU Table ------+---------+\n");
printf(" NUM | POS | IDC | TYPE | LEN |\n");
printf("-----+---------+--------+-------+---------+\n");
while(!feof(h264bitstream))
{
int data_lenth;
data_lenth=GetAnnexbNALU(n);// 读取NALU
char type_str[20]={0};
switch(n->nal_unit_type){
case NALU_TYPE_SLICE:sprintf(type_str,"SLICE");break;
case NALU_TYPE_DPA:sprintf(type_str,"DPA");break;
case NALU_TYPE_DPB:sprintf(type_str,"DPB");break;
case NALU_TYPE_DPC:sprintf(type_str,"DPC");break;
case NALU_TYPE_IDR:sprintf(type_str,"IDR");break;
case NALU_TYPE_SEI:sprintf(type_str,"SEI");break;
case NALU_TYPE_SPS:sprintf(type_str,"SPS");break;
case NALU_TYPE_PPS:sprintf(type_str,"PPS");break;
case NALU_TYPE_AUD:sprintf(type_str,"AUD");break;
case NALU_TYPE_EOSEQ:sprintf(type_str,"EOSEQ");break;
case NALU_TYPE_EOSTREAM:sprintf(type_str,"EOSTREAM");break;
case NALU_TYPE_FILL:sprintf(type_str,"FILL");break;
}
char idc_str[20]={0};
switch(n->nal_reference_idc>>5){ //nal_reference_idc 占2位，指示当前NALU的优先级，或者说重要性，数值越大表明越重要。所以取值范围为0～3
case NALU_PRIORITY_DISPOSABLE:sprintf(idc_str,"DISPOS");break;
case NALU_PRIRITY_LOW:sprintf(idc_str,"LOW");break;
case NALU_PRIORITY_HIGH:sprintf(idc_str,"HIGH");break;
case NALU_PRIORITY_HIGHEST:sprintf(idc_str,"HIGHEST");break;
}
fprintf(myout,"%5d| %8d| %7s| %6s| %8d|\n",nal_num,data_offset,idc_str,type_str,n->len);
data_offset=data_offset+data_lenth;
nal_num++;
}
//Free
if (n){
if (n->buf){
free(n->buf);
n->buf=NULL;
}
free (n);
}
return 0;
}
@interface ViewController ()
@end
@implementation ViewController
- (void)viewDidLoad {
[super viewDidLoad];
NSString *fileName = [[NSBundle mainBundle] pathForResource:@"sintel" ofType:@"h264"];
const char *filePath = [fileName cStringUsingEncoding:NSUTF8StringEncoding];
simplest_h264_parser(filePath);
}
@end
结果
本程序的输入为一个H.264原始码流（裸流）的文件路径，输出为该码流的NALU统计数据，如下图所示。
image.png
参考
视音频数据处理入门：H.264视频码流解析
https://blog.csdn.net/leixiaohua1020/article/details/50534369
网友评论