UNIX for Beginners Questions & Answers

// convert to an executable with cc block.c -o block
#include <stdio.h>
#include <limits.h>
#include <stdlib.h>

int main(int argc, char *argv[]) {
        long int BLOCK=0;
        char *buf=NULL;

        if(argc < 2)
        {
                fprintf(stderr, "usage:  %s blocksize [inputfile]\n", argv[0]);
                exit(1);
        }

        if(argc >= 2) BLOCK=strtol(argv[1], NULL, 10);
        if(argc >= 3) {
                if(freopen(argv[2], "rb", stdin)==NULL)
                {
                        perror("Couldn't open");
                        return(1);
                }
        }

        if(BLOCK<=0)
        {
                fprintf(stderr, "Invalid block size %ld\n", BLOCK);
                return(1);
        }

        buf=malloc(BLOCK+1);
        if(buf == NULL)
        {
                perror("Couldn't allocate");
                return(1);
        }

//      fprintf(stderr, "block size %ld\n", BLOCK);

        buf[BLOCK]='\n';
        while(fread(buf,BLOCK,1,stdin))
                fwrite(buf,BLOCK+1,1,stdout);

        free(buf);
        return(0);
}

#!/bin/sh

BLOCKSIZE=3

# Add newlines using block utility
./block $BLOCKSIZE |
        # Remove characters, i.e. you'd put iconv here
        tr -d 'A-Z' |
        # Pad shrunken records with spaces
        dd ibs=$BLOCKSIZE cbs=$BLOCKSIZE conv=sync,block 2>/dev/null |
        # Remove newlines
        tr -d '\n'

$ cat fixed.txt
aAabBbcccdDdeeEfffggghhhiIijjjkkklLlmmmnnn

$ ./dump.sh < fixed.txt
aa bb cccdd ee fffggghhhii jjjkkkll mmmnnn   

$

LC_ALL=C sed 's/[\xC0-\xDF]./& /g; s/[\xE0-\xEF]../& /g' non-ascii.txt | iconv -futf8 -tASCII//TRANSLIT//IGNORE