/* Program to put a column of a fixed-width database into a binary
 * column file.  Rather slow, only processes 6 million records a
 * second.  findcuit.c is the program that queries it.
 */
#include <stdio.h>
#include <stdlib.h>
#include <unistd.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <sys/mman.h>
#include <fcntl.h>
#include <string.h>

enum { recsize = 52, keysize = 11 };

int main(int argc, char **argv) {
  if (argc != 2) {
    fprintf(stderr, "Usage: %s utlfile/padr/SELE-SAL-CONSTA.p20out1.20230415.tmp\n",
            argv[0]);
    return 1;
  }

  int bufsize = strlen(argv[1]) + 10;
  char tmpfilenamebuf[bufsize], filenamebuf[bufsize];
  strcpy(filenamebuf, argv[1]);
  strcat(filenamebuf, ".cuit");
  strcpy(tmpfilenamebuf, filenamebuf);
  strcat(tmpfilenamebuf, ".tmp");

  int fd = open(argv[1], O_RDONLY);
  if (fd < 0) {
    perror(argv[1]);
    return 1;
  }

  FILE *out = fopen(tmpfilenamebuf, "w");
  if (!out) {
    perror(tmpfilenamebuf);
    return 1;
  }

  off_t size = lseek(fd, 0, SEEK_END);
  printf("%s is %ld bytes\n", argv[1], size);

  char *mem = mmap(NULL, size, PROT_READ, MAP_SHARED, fd, (off_t)0);
  if (mem == MAP_FAILED) {
    perror("mmap");
    return 1;
  }
  close(fd);
  
  for (int off = 0; off <= size - recsize; off += recsize) {
    char *end = mem + off + keysize;
    unsigned long cuit = strtol(mem + off, &end, 10);
    unsigned char cuitbuf[8];

    for (int i = 0; i < 8; i++) {
      cuitbuf[i] = cuit & 255;
      cuit >>= 8;
    }

    fwrite(cuitbuf, 8, 1, out);
  }

  fflush(out);
  printf("Wrote %ld bytes\n", ftell(out));
  fsync(fileno(out));
  fclose(out);
  if (rename(tmpfilenamebuf, filenamebuf) < 0) {
    perror("rename");
    return 1;
  }

  return 0;
}