#!/usr/bin/env python3
"""Local-only CSV-to-JSON sample. Python 3.9+; standard library only.
Copyright 2026 Automaton. Licensed under the MIT License; see csv-sample-license.txt.
"""
import argparse
import csv
import io
import json
import sys

MAX_BYTES = 10_000_000

def convert(path):
    with open(path, "rb") as stream:
        raw = stream.read(MAX_BYTES + 1)
    if len(raw) > MAX_BYTES:
        raise ValueError("input exceeds 10 MB (10,000,000 bytes)")
    text = raw.decode("utf-8-sig")
    if "\x00" in text:
        raise ValueError("NUL characters are not supported")
    csv.field_size_limit(MAX_BYTES)
    reader = csv.reader(io.StringIO(text, newline=""), strict=True)
    headers = next(reader, None)
    if not headers or len(headers) > 20:
        raise ValueError("require a header with 1 to 20 columns")
    if any(not name.strip() for name in headers) or len(set(headers)) != len(headers):
        raise ValueError("headers must be nonblank and unique")
    rows = []
    for row in reader:
        if not row:  # Empty physical records are deliberately ignored.
            continue
        if len(row) != len(headers):
            raise ValueError(f"record ending on line {reader.line_num} has the wrong column count")
        rows.append(dict(zip(headers, row)))
    return rows

def main():
    parser = argparse.ArgumentParser(description="Convert a UTF-8 CSV to JSON; keep every value a string.")
    parser.add_argument("input", help="CSV file, at most 10 MB; output goes to stdout")
    args = parser.parse_args()
    try:
        output = json.dumps(convert(args.input), ensure_ascii=False, indent=2)
    except (OSError, UnicodeError, csv.Error, ValueError) as error:
        print(f"error: {error}", file=sys.stderr)
        return 1
    sys.stdout.buffer.write((output + "\n").encode("utf-8"))
    return 0

if __name__ == "__main__":
    raise SystemExit(main())