Shell Programming and Scripting

touch {1..16}.txt

awk 'BEGIN{flag=0; file=1 }{
if($0~/<page>/) flag=1;
if($0~/<\/page>/) {
        buf=buf$0"\n";
        flag=0;
        printf buf>>file".txt"
        buf="";
        
        file++;
        file=(file<=16)?file:1;
};
if(flag==1){
        buf=buf$0;
}
}' your30G_BIG.xml

#define _FILE_OFFSET_BITS 64

#include <stdio.h>
#include <stdlib.h>
#include <string.h>

#define NCHUNKS 16
#define NBUF  512
#define WORD "<page>"


void usage(char *progname) {
    printf("Usage: %s FILENAME\n", progname);
}

long long find_pos(FILE *fd, long long pos) {
    
    char BUF[NBUF+1];
    BUF[NBUF+1] = '\0';  // BUG !!!
    
    fseeko(fd, pos, SEEK_SET);
    int count = -1;
    char *found = NULL;

    while (!found) {
        fread(BUF, NBUF, 1, fd);
        found = strstr(BUF, WORD);
        count++;
    }
    int offset = found - BUF;

    return pos + NBUF*count + offset;
}

int main(int argc, char** argv) {
    FILE *fd = fopen(argv[1], "r"); // fopen should be fopen64 really
    if (! fd) {
        fprintf(stderr, "Couldn't open %s\n", argv[1]);
        usage(argv[0]);
        exit(-1);
    }

    long long fs;
    if (fseeko(fd, 0, SEEK_END)) {
        fprintf(stderr, "Couldn't go to the end of the file\n");
        exit(-1);
    }

    fs = ftello(fd);

    int count = 0;
    while (count < NCHUNKS-1) {
        printf("%lld ", find_pos(fd, ++count * fs/NCHUNKS));
    }
    printf("\n");
    
    fclose(fd);
    return 0;
}

xxd -sNUM testfile | head -1

char BUF[NBUF+1];
BUF[NBUF+1] = '\0';

char BUF[4+1];
buf[0]=0; // first element
buf[1]=1; // second element
buf[2]=2; // third element
buf[3]=3; // fourth element
buf[4]=4; // fifth element
buf[5]=5; // SIXTH element!  buf[4+1] is beyond the end!

char BUF[NBUF+1];
    BUF[NBUF] = '\0';

    long long fs;
    if (fseeko(fd, 0, SEEK_END)) {
        fprintf(stderr, "Couldn't go to the end of the file\n");
        exit(-1);
    }

    fs = ftello(fd);