dig-groupby-ip.bb

#!/usr/bin/env bash

cat ip_domain.tsv | bb -e '
  (->> (line-seq (java.io.BufferedReader. *in*))
       (map #(str/split % #"\t"))
       (group-by first)
       (map (fn [[ip rows]] (str ip "\t" (str/join ";" (map second rows)))))
       (run! println))
' > ip_domains.tsv

#!/usr/bin/env bash

bb -e '
  (->> (slurp "ip_domain.tsv")
       str/split-lines
       (map #(str/split % #"\t"))
       (group-by first)
       (map (fn [[ip rows]] (str ip "\t" (str/join ";" (map second rows)))))
       (str/join "\n")
       println)
' > ip_domains.tsv

#!/usr/bin/env python

import sys
from collections import defaultdict


def parse_line(line: str) -> tuple[str, str] | None:
    parts = line.rstrip("\n").split("\t")
    if len(parts) < 2 or not parts[0]:
        return None
    return parts[0], parts[1]


def group_by_ip(lines: list[str]) -> dict[str, list[str]]:
    groups = defaultdict(list)
    for line in lines:
        parsed = parse_line(line)
        if parsed:
            ip, domain = parsed
            groups[ip].append(domain)
    return groups


def format_output(groups: dict[str, list[str]]) -> list[str]:
    return [f"{ip}\t{';'.join(domains)}" for ip, domains in groups.items()]


def main():
    lines = sys.stdin
    groups = group_by_ip(lines)
    output = format_output(groups)
    print("\n".join(output))


if __name__ == "__main__":
    main()