如何用 c 或 c++ 读取 FORTRAN 二进制文件？

Question

我有 FORTRAN 77 二进制文件（在 Sun Sparc 机器上创建，大端）。我想在我的小端机器上阅读它。我遇到过这个

http://paulbourke.net/dataformats/reading/

Paul 为 C 或 C++ 编写了这些宏，但我不明白它们的真正作用。

#define SWAP_2(x) ( (((x) & 0xff) << 8) | ((unsigned short)(x) >> 8) )
#define SWAP_4(x) ( ((x) << 24) | (((x) << 8) & 0x00ff0000) | \
         (((x) >> 8) & 0x0000ff00) | ((x) >> 24) )
#define FIX_SHORT(x) (*(unsigned short *)&(x) = SWAP_2(*(unsigned short *)&(x)))
#define FIX_LONG(x) (*(unsigned *)&(x) = SWAP_4(*(unsigned *)&(x)))
#define FIX_FLOAT(x) FIX_LONG(x)

我知道文件的每条记录都包含包含

x,y,z,t,d,i

i 是整数*2，所有其他变量都是实数*4。 前 512 字节 hexdump

0000000 0000 1800 0000 0000 0000 0000 0000 0000
0000010 0000 0000 0000 0000 ffff ffff 0000 1800
0000020 0000 1800 003f 0000 0000 0000 233c 0ad7
0000030 0000 0000 233c 0ad7 0000 0100 0000 1800
0000040 0000 1800 803f 0000 0000 0000 233c 0ad7
0000050 0000 0000 233c 0ad7 0000 0100 0000 1800
0000060 0000 1800 c03f 0000 0000 0000 233c 0ad7
0000070 0000 0000 233c 0ad7 0000 0100 0000 1800
0000080 0000 1800 0040 0000 0000 0000 233c 0ad7
0000090 0000 0000 233c 0ad7 0000 0100 0000 1800
00000a0 0000 1800 2040 0000 0000 0000 233c 0ad7
00000b0 0000 0000 233c 0ad7 0000 0100 0000 1800
00000c0 0000 1800 4040 0000 0000 0000 233c 0ad7
00000d0 0000 0000 233c 0ad7 0000 0100 0000 1800
00000e0 0000 1800 6040 0000 0000 0000 233c 0ad7
00000f0 0000 0000 233c 0ad7 0000 0100 0000 1800
0000100 0000 1800 8040 0000 0000 0000 233c 0ad7
0000110 0000 0000 233c 0ad7 0000 0100 0000 1800
0000120 0000 1800 9040 0000 0000 0000 233c 0ad7
0000130 0000 0000 233c 0ad7 0000 0100 0000 1800
0000140 0000 1800 a040 0000 0000 0000 233c 0ad7
0000150 0000 0000 233c 0ad7 0000 0100 0000 1800
0000160 0000 1800 b040 0000 0000 0000 233c 0ad7
0000170 0000 0000 233c 0ad7 0000 0100 0000 1800
0000180 0000 1800 c040 0000 0000 0000 233c 0ad7
0000190 0000 0000 233c 0ad7 0000 0100 0000 1800
00001a0 0000 1800 d040 0000 0000 0000 233c 0ad7
00001b0 0000 0000 233c 0ad7 0000 0100 0000 1800
00001c0 0000 1800 e040 0000 0000 0000 233c 0ad7
00001d0 0000 0000 233c 0ad7 0000 0100 0000 1800
00001e0 0000 1800 f040 0000 0000 0000 233c 0ad7
00001f0 0000 0000 233c 0ad7 0000 0100 0000 1800
0000200

我读取文件的代码

#include <endian.h>
#include <stdint.h>
#include <stdio.h>
#include <stdlib.h>

int main() 
{
    FILE *file;
    char *buffer;
    char *rec;
    long fileLen;

    file = fopen("rec.in", "rb");


    fseek(file, 0, SEEK_END);
    fileLen=ftell(file);
    fseek(file, 0, SEEK_SET);

    buffer=(char *)malloc(fileLen+1);

    fread(buffer, fileLen, 1, file);
    fclose(file);
    free(buffer);

char *curr = buffer;
char *end = buffer + fileLen;

constexpr int LINE_SIZE = sizeof(float)*5 + sizeof(uint16_t); //based upon your "x,y,z,t,d,i" description

while(curr < end) {
    uint32_t temp = be32toh(*reinterpret_cast<uint32_t*>(*curr));
    float x = *reinterpret_cast<float*>(&temp);

    temp = be32toh(*reinterpret_cast<uint32_t*>(*(curr+sizeof(float))));
    float y = *reinterpret_cast<float*>(&temp);

    temp = be32toh(*reinterpret_cast<uint32_t*>(*(curr+2*sizeof(float))));
    float z = *reinterpret_cast<float*>(&temp);

    temp = be32toh(*reinterpret_cast<uint32_t*>(*(curr+3*sizeof(float))));
    float t = *reinterpret_cast<float*>(&temp);

    temp = be32toh(*reinterpret_cast<uint32_t*>(*(curr+4*sizeof(float))));
    float d = *reinterpret_cast<float*>(&temp);

    uint16_t i = be16toh(*reinterpret_cast<uint16_t*>(*(curr+5*sizeof(float))));

    curr += LINE_SIZE;

}

}

我有两个错误 r.cc: 在函数'int main()'中：

r.cc:29:1: error: ‘constexpr’ was not declared in this scope
 constexpr int LINE_SIZE = sizeof(float)*5 + sizeof(uint16_t); //based upon your "x,y,z,t,d,i" description
 ^
r.cc:49:13: error: ‘LINE_SIZE’ was not declared in this scope
     curr += LINE_SIZE;

Answer 1

如果您在 linux 机器上读取文件，endian.h 标头（文档here）中为此目的提供了一些库函数。要将 16 位整数转换为主机顺序（在您的情况下为小端序）：

uint16_t hostInteger = be16toh(bigEndianIntegerFromFile);

对于浮点数，您可以做类似的事情，但需要重新解释：

float hostFloat = reinterpret_cast<float>(be32toh(reinterpret_cast<uint32_t>(bigEndianFloatFromFile)));

或者，如果您一开始将其读作unsigned int，则不需要内部的reinterpret_cast：

float hostFloat = reinterpret_cast<float>(be32toh(bigEndianUint32FromFile));

更新：给定您的代码，您可以通过在 fclose 和 free 调用之间插入来读取文件：

char *curr = buffer;
char *end = buffer + fileLen;

constexpr int LINE_SIZE = sizeof(float)*5 + sizeof(uint16_t); //based upon your "x,y,z,t,d,i" description

while(curr < end) {
    uint32_t temp = be32toh(*reinterpret_cast<uint32_t*>(*curr));
    float x = *reinterpret_cast<float*>(&temp);

    temp = be32toh(*reinterpret_cast<uint32_t*>(*(curr+sizeof(float))));
    float y = *reinterpret_cast<float*>(&temp);

    temp = be32toh(*reinterpret_cast<uint32_t*>(*(curr+2*sizeof(float))));
    float z = *reinterpret_cast<float*>(&temp);

    temp = be32toh(*reinterpret_cast<uint32_t*>(*(curr+3*sizeof(float))));
    float t = *reinterpret_cast<float*>(&temp);

    temp = be32toh(*reinterpret_cast<uint32_t*>(*(curr+4*sizeof(float))));
    float d = *reinterpret_cast<float*>(&temp);

    uint16_t i = be16toh(*reinterpret_cast<uint16_t*>(*(curr+5*sizeof(float))));

    curr += LINE_SIZE;

    ...
    //do something with these values
    ...
}