tardecode/mmap.c

#include <sys/mman.h>
#include <math.h>
#include <stdlib.h>
#include <string.h>
#include <stdio.h>
#include <sys/types.h>
#include <fcntl.h>
#include <unistd.h>
#include <sys/stat.h>
#include <assert.h>

size_t getFilesize(const char* filename) {
    struct stat st;
    stat(filename, &st);
    return st.st_size;
}

int octToInt(char *current_char, unsigned int size) {
    unsigned int output = 0;
    while(size > 0){
        output = output * 8 + *current_char - '0';
        current_char++;
        size--;
    }
    return output;
}

char *findNextHeader(char *start, long int *actualSize) {
    char *header = start;
    char tmp[13];
    long int size;

    // printf("%d. %s\n", i, header);
    memset(tmp, 0, 13);
    strncpy(tmp, header + 124, 12); // size
    size = strtol(tmp, 0, 8);
    printf("\tbad: %s %ld\n", header, size);
    header += 512;

    long int next512 = ceil(size/512.0) * 512;
    header += next512; // look beyond this

    for (;; ++header) {
        if (header[0] != '.') continue;

        char *magic = header + 257; // ustar
        if (magic[0] == 'u' && magic[1] == 's' && magic[2] == 't') break;
    }

    printf("\tbingo! actual_size: %ld next_file:%s\n", (header - start + 512), header);
    if (actualSize) *actualSize = header - start + 512;

    return header;
}

void process(void *start, long length, int outFd) {
    char *header = (char *) start; // 512

    int i = 0;

    while (header < ((char *)start+length)) {
        char tmp[13];
        memset(tmp, 0, 13);
        strncpy(tmp, header + 124, 12); // size
        long int size = strtol(tmp, 0, 8);
        printf("%d. %s %ld\n", i++, header, size);

        if (size == 8589934591) { // oops, bad size
            printf("\tbad size detected. will find next header\n");
            long int actualSize = 0;
            header = findNextHeader(header, &actualSize);
            printf("\tdd skip=%ld count=%ld if=input.binary of=output.binary iflag=skip_bytes,count_bytes\n", (header - actualSize) - (char *)start, actualSize);
        } else {
            int next512 = ceil(size/512.0) * 512; // file data with padding size

            write(outFd, header, 512+next512);

            header += 512 + next512; // header size + the file data size
        }
    }

    printf("done\n");
}

int main(int argc, char** argv) {
    size_t filesize = getFilesize(argv[1]);
    //Open file
    int fd = open(argv[1], O_RDONLY, 0);
    assert(fd != -1);

    struct stat buf;
    fstat(fd, &buf);

    int fd2 = open(argv[2], O_CREAT | O_WRONLY, 0);
    assert(fd2 != -1);

    //Execute mmap
    void* mmappedData = mmap(NULL, filesize, PROT_READ, MAP_SHARED, fd, 0);
    assert(mmappedData != MAP_FAILED);

    process(mmappedData, buf.st_size, fd2);

    //Cleanup
    int rc = munmap(mmappedData, filesize);
    assert(rc == 0);

    close(fd);
    close(fd2);
}