"""Compare two CSV snapshots by one unique key. Python 3.9+, standard library."""
import argparse
import csv
import json
from pathlib import Path
import sys


def load_csv(path, key):
    records = {}
    with open(path, encoding="utf-8-sig", newline="") as handle:
        reader = csv.reader(handle, strict=True)
        header = next(reader, None)
        if not header or any(not name or name != name.strip() for name in header):
            raise ValueError(f"{path}: empty or padded column name")
        if len(set(header)) != len(header) or key not in header:
            raise ValueError(f"{path}: columns must be unique and include {key!r}")
        key_index = header.index(key)
        for number, row in enumerate(reader, 1):
            if len(row) != len(header):
                raise ValueError(f"{path}: record {number}: wrong field count")
            identity = row[key_index]
            if not identity or identity != identity.strip():
                raise ValueError(f"{path}: record {number}: empty or padded key")
            if identity in records:
                raise ValueError(f"{path}: record {number}: duplicate key {identity!r}")
            records[identity] = dict(zip(header, row))
    return header, records


def compare(old_path, new_path, key):
    old_header, old = load_csv(old_path, key)
    new_header, new = load_csv(new_path, key)
    if old_header != new_header:
        raise ValueError("headers differ: column names and order must match")
    added = sorted(new.keys() - old.keys())
    removed = sorted(old.keys() - new.keys())
    changed = []
    for identity in sorted(old.keys() & new.keys()):
        fields = {
            name: {"old": old[identity][name], "new": new[identity][name]}
            for name in old_header
            if old[identity][name] != new[identity][name]
        }
        if fields:
            changed.append({"id": identity, "fields": fields})
    return {"key": key, "added": added, "removed": removed, "changed": changed}


def main():
    parser = argparse.ArgumentParser(description=__doc__)
    parser.add_argument("old", type=Path)
    parser.add_argument("new", type=Path)
    parser.add_argument("--key", default="sample_id", help="unique key column")
    args = parser.parse_args()
    try:
        report = compare(args.old, args.new, args.key)
        json.dump(report, sys.stdout, ensure_ascii=True, indent=2)
        sys.stdout.write("\n")
        sys.stdout.flush()
    except (OSError, UnicodeError, ValueError, csv.Error) as exc:
        parser.exit(2, f"error: {exc}\n")
    return int(any(report[name] for name in ("added", "removed", "changed")))


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