last_chunk.sh

#!/usr/bin/bash

N=10000

echo "raw file:"
ls -lh OUTCAR; wc -l OUTCAR
echo

> NEW_OUTCAR

for _ in $(seq $N); do
    cat OUTCAR >> NEW_OUTCAR
done

cat >> NEW_OUTCAR <<'EOF'

 magnetization (z)

# of ion       s       p       d       f      tot
--------------------------------------------------
    1        0.037   0.030   4.519   5.000   9.586
    2       -0.037  -0.030  -4.519  -5.000  -9.586
    3        0.000   0.000   0.000   0.000   0.000
    4        0.000   0.000   0.000   0.000   0.000
    5        0.000   0.000  -0.000  -0.000   0.000
    6        0.000   0.000  -0.000  -0.000   0.000
    7        0.000   0.000  -0.000  -0.000   0.000
    8        0.000   0.000  -0.000  -0.000   0.000
    9        0.000   0.000  -0.000  -0.000   0.000
   10        0.001   0.001  -0.000  -0.000   0.002
------------------------------------------------------
tot          0.001   0.002   0.000   0.000   0.003
EOF

echo "huge file:"
ls -lh NEW_OUTCAR; wc -l NEW_OUTCAR
echo

echo -n ">>> awk with getline ... "
/usr/bin/time -f %es awk '
    /magnetization \(z\)/ {
        data=""; getline; getline; getline;
        for (i=1; i<=10; i++) {
            getline
            data = data sprintf("%8.3f\n", $NF)
        }
    }
    END {printf data}
' NEW_OUTCAR > res.awk_with_getline
echo

echo -n ">>> awk without getline ... "
/usr/bin/time -f %es awk '
    {
        if ($0 ~ /magnetization \(z\)/) { f = 1; c = "" }
        if (f == 1) {
            if ($1 ~ /^[0-9]+$/) c = c sprintf("%8.3f\n", $NF)
            if ($1 ~ /tot/) f = 0
        }
    }
    END { printf c }
' NEW_OUTCAR > res.awk_no_getline
echo

echo -n ">>> perl ... "
/usr/bin/time -f %es perl -00ne '
    /magnetization \(z\)/ and $f=1 and next;
    $f==1 and ($c,$f)=$_,0;
    }{ map {/^\s*\d+\b/ and printf "%8.3f\n", (split " ")[-1]}
           split /\n/, $c
' NEW_OUTCAR > res.perl
echo

echo -n ">>> python ... "
/usr/bin/time -f %es python -c '
import sys
f, c = 0, []
with open(sys.argv[1]) as input_file:
    for line in input_file:
        if "magnetization (z)" in line:
            f = 1
            c = []
        elif f == 1 and line.strip():
            first_field = line.strip().split()[0]
            if first_field.isdigit():
                last_field = line.strip().split()[-1]
                c.append(format(float(last_field), "8.3f"))
            elif first_field == "tot":
                f = 0
print("\n".join(c))
' NEW_OUTCAR > res.python
echo

echo -n ">>> C ... "
cat > manip.c <<'EOF'
#include <stdio.h>
#include <stdlib.h>
#include <string.h>

int main(int argc, char *argv[]) {
    int f = 0;
    char c[1001] = {0};

    if (argc < 2) {
        printf("Please provide a filename as a command-line argument.\n");
        return 1;
    }

    FILE *file = fopen(argv[1], "r");
    if (file == NULL) {
        printf("Failed to open the file.\n");
        return 1;
    }

    char line[1001];
    while (fgets(line, sizeof(line), file) != NULL) {
        if (strstr(line, "magnetization (z)") != NULL) {
            f = 1;
            c[0] = '\0';
        } else if (strncmp(line, "tot", 3) == 0) {
            f = 0;
        } else if (f == 1) {
            char *token;
            char *lastToken = NULL;
            token = strtok(line, " ");
            while (token != NULL) {
                lastToken = token;
                token = strtok(NULL, " ");
            }
            char *endptr;
            double value = strtod(lastToken, &endptr);
            if (endptr != lastToken) {
                char temp[10];
                snprintf(temp, sizeof(temp), "%8.3f\n", value);
                strcat(c, temp);
            }
        }
    }

    fclose(file);

    printf("%s", c);

    return 0;
}
EOF
gcc -O2 -o manip manip.c
/usr/bin/time -f %es ./manip NEW_OUTCAR > res.c
echo

echo "answer check:"
sha256sum res.*