wave文件头解析

Waveform Audio File Format&＃xff08;WAVE&＃xff0c;又或者是因为扩展名而被大众所知的WAV&＃xff09;&＃xff0c;是微软与IBM公司所开发在个人电脑存储音频流的编码格式&＃xff0c;在Windows平台的应用软件受到广泛的支持&＃xff0c;地位上类似于麦金塔电脑里的AIFF。[2] 此格式属于资源交换文件格式(RIFF)的应用之一&＃xff0c;通常会将采用脉冲编码调制的音频资存储在区块中。也是其音乐发烧友中常用的指定规格之一。由于此音频格式未经过压缩&＃xff0c;所以在音质方面不会出现失真的情况&＃xff0c;但文件的体积因而在众多音频格式中较为大。

格式详解

1. WAV文件格式详解
2. WAV

代码

1. 定义上下文结构体

struct StWAVContext
{std::string name;std::ifstream fileHanler;std::vector> chunks; // 所有的chunk集合StAudioFormat format;char* pcmBuf; // pcm bufferuint32_t pcmSize; // pcm数据的大小
};


2. 获取当前chunk的ID、Size

void getNextChunk(StWAVContext *context, std::string &id, uint32_t *size)
{char chunk[5] &＃61; { 0 }; // ID字段 4bytesstd::ifstream &fp &＃61; context->fileHanler;// 获取IDfp.read(chunk, 4);id &＃61; std::string(chunk);// 获取Sizememset(chunk, 0, 5);fp.read(chunk, 4);memset(size, 0, sizeof(uint32_t));memcpy(size, chunk, sizeof(uint32_t));
}


3. 循环解析所有chunk&＃xff0c;其中对chunkID的处理基于自己的业务需求。

std::string chunkID;uint32_t chunkSize &＃61; 0;uint32_t curPos &＃61; 0;do{chunkID.clear();getNextChunk(context, chunkID, &chunkSize);context->chunks.push_back(std::make_pair(chunkID, chunkSize));debugf("Find chunk: ID[%s] Size[%ld]", chunkID.c_str(), chunkSize);curPos &＃61; context->fileHanler.tellg();if (chunkID.empty()){errorf("Parse nothing.");break;}if (chunkID &＃61;&＃61; "RIFF"){context->fileHanler.seekg(4, context->fileHanler.cur);}else if (chunkID &＃61;&＃61; "fmt "){parseFormatChunk(context, chunkSize);}else if (chunkID &＃61;&＃61; "data"){parseDataChunk(context, chunkSize);break;}else{context->fileHanler.seekg(chunkSize, context->fileHanler.cur);}} while (true);


4. 以chunkID &＃61;&＃61; "fmt "为例(注意&＃xff1a;fmt后还有一个空格&＃xff0c;这是因为chunkID占用了4个字节&＃xff0c;而fmt仅占用3个字节的原因)&＃xff0c;解析特定chunk如下&＃xff1a;

void parseFormatChunk(StWAVContext *context, uint32_t chunkSize)
{char str_chunk4B[5] &＃61; { 0 };char str_chunk2B[3] &＃61; { 0 };uint32_t digit_chunk4B &＃61; 0;uint16_t digit_chunk2B &＃61; 0;std::ifstream &fp &＃61; context->fileHanler;// 解析AudioFormatmemset(&str_chunk2B, 0, sizeof(str_chunk2B));fp.read(str_chunk2B, 2);digit_chunk2B &＃61; 0;memcpy(&digit_chunk2B, str_chunk2B, sizeof(digit_chunk2B));if (is_bigEndian()){digit_chunk2B &＃61; ntohs(digit_chunk2B);}context->format.type &＃61; digit_chunk2B;debugf("File[%s] type: %d.", context->name.c_str(), context->format.type);// 解析channelmemset(&str_chunk2B, 0, sizeof(str_chunk2B));fp.read(str_chunk2B, 2);digit_chunk2B &＃61; 0;memcpy(&digit_chunk2B, str_chunk2B, sizeof(digit_chunk2B));if (is_bigEndian()){digit_chunk2B &＃61; ntohs(digit_chunk2B);}context->format.channels &＃61; digit_chunk2B;debugf("File[%s] channels: %d.", context->name.c_str(), context->format.channels);// sample_ratememset(&str_chunk4B, 0, sizeof(str_chunk4B));fp.read(str_chunk4B, 4);digit_chunk4B &＃61; 0;memcpy(&digit_chunk4B, str_chunk4B, sizeof(digit_chunk4B));if (is_bigEndian()){digit_chunk4B &＃61; ntohl(digit_chunk4B);}context->format.sample_rate &＃61; digit_chunk4B;debugf("File[%s] sample_rate: %ld.", context->name.c_str(), context->format.sample_rate);// bytes per secondmemset(&str_chunk4B, 0, sizeof(str_chunk4B));fp.read(str_chunk4B, 4);digit_chunk4B &＃61; 0;memcpy(&digit_chunk4B, str_chunk4B, sizeof(digit_chunk4B));if (is_bigEndian()){digit_chunk4B &＃61; ntohl(digit_chunk4B);}context->format.bytes_per_second &＃61; digit_chunk4B;debugf("File[%s] bytes_per_second: %ld.", context->name.c_str(), context->format.bytes_per_second);// block align sizememset(&str_chunk2B, 0, sizeof(str_chunk2B));fp.read(str_chunk2B, 2);digit_chunk2B &＃61; 0;memcpy(&digit_chunk2B, str_chunk2B, sizeof(digit_chunk2B));if (is_bigEndian()){digit_chunk2B &＃61; ntohs(digit_chunk2B);}context->format.block_size &＃61; digit_chunk2B;debugf("File[%s] block_size: %ld.", context->name.c_str(), context->format.block_size);// bits per samplememset(&str_chunk2B, 0, sizeof(str_chunk2B));fp.read(str_chunk2B, 2);digit_chunk2B &＃61; 0;memcpy(&digit_chunk2B, str_chunk2B, sizeof(digit_chunk2B));if (is_bigEndian()){digit_chunk2B &＃61; ntohs(digit_chunk2B);}context->format.bits_per_sample &＃61; digit_chunk2B;debugf("File[%s] bits_per_sample: %ld.", context->name.c_str(), context->format.bits_per_sample);
}


字节序

在wave的每一个chunk中&＃xff0c;涉及到了大量的大小端字节序转换&＃xff0c;由此带来一个问题&＃xff0c;判断当前主机cpu的字节序&＃xff0c;代码如下&＃xff1a;

bool is_bigEndian()
{static union { char c; unsigned long mylong; } endian_test &＃61; { 0x01 };// bit_endian: 00 00 00 01// little_endian: 01 00 00 00return endian_test.c &＃61;&＃61; 0x00;
}