"""FICTIONAL DEMONSTRATION: AI-operated HireThomas Inc; not client work."""
import argparse
import csv
import sys
from collections import Counter
from pathlib import Path

FLAG = "is_duplicate"


def flag_csv(source, output):
    """Preserve parsed strings/order; mark ALL members of exact duplicate groups."""
    source, output = Path(source), Path(output)
    if source.resolve() == output.resolve():
        raise ValueError("source and output must be different paths")
    with source.open("r", encoding="utf-8", newline="") as handle:
        reader = csv.reader(handle, dialect="excel", strict=True)
        header = next(reader, None)
        if not header or any(name == "" for name in header):
            raise ValueError("a nonempty header with nonempty names is required")
        if len(set(header)) != len(header):
            raise ValueError("duplicate header names are not allowed")
        if FLAG in header:
            raise ValueError("header collision: is_duplicate already exists")
        rows = []
        for record, row in enumerate(reader, start=2):
            if len(row) != len(header):
                raise ValueError(
                    f"record {record}: expected {len(header)} fields, got {len(row)}"
                )
            rows.append(tuple(row))
    counts = Counter(rows)
    groups = sum(count > 1 for count in counts.values())
    repeated = sum(count - 1 for count in counts.values())
    flagged = sum(count for count in counts.values() if count > 1)
    # Validate everything before creating output; never overwrite existing files.
    with output.open("x", encoding="utf-8", newline="") as handle:
        writer = csv.writer(handle, dialect="excel", lineterminator="\n")
        writer.writerow(header + [FLAG])
        for row in rows:
            writer.writerow(row + (str(int(counts[row] > 1)),))
    return len(rows), groups, repeated, flagged


def main(argv=None):
    parser = argparse.ArgumentParser(description=__doc__)
    parser.add_argument("source", type=Path)
    parser.add_argument("output", type=Path)
    args = parser.parse_args(argv)
    try:
        rows, groups, repeated, flagged = flag_csv(args.source, args.output)
    except (OSError, UnicodeError, csv.Error, ValueError) as exc:
        print(f"error: {exc}", file=sys.stderr)
        return 2
    print(f"rows={rows} duplicate_groups={groups} repeated_rows={repeated} flagged_rows={flagged}")
    return 0


if __name__ == "__main__":
    sys.exit(main())