"""
The contract format, for the Python implementations.

A port of `src/contract.ts`, kept in one place so the three Python
implementations cannot drift apart about how a number is written down. See
`calc/CONTRACT.md` for what the format is and why it is shaped this way.
"""

from __future__ import annotations

import hashlib
import math
import re

HEADER = "metric\tkey\tvalue"

#: How a value that does not exist is written — an empty cohort, an undefined rate.
NA = "NA"

#: Decimal places used for every real in the contract.
PRECISION = 12

#: Printable ASCII, excluding space so that a key never looks like two columns.
_SORTABLE = re.compile(r"^[\x21-\x7e]+$")


def fmt_int(n):
    if isinstance(n, bool) or not isinstance(n, int):
        raise ValueError("contract: %r is not an integer" % (n,))
    return str(n)


def fmt_real(x):
    if x is None:
        return NA
    if not math.isfinite(x):
        raise ValueError("contract: %r is not finite" % (x,))
    # -0.0 and 0.0 are the same number; only their printed forms differ.
    return "%.*f" % (PRECISION, 0.0 if x == 0 else x)


def fmt_text(s):
    if "\t" in s or "\n" in s or "\r" in s:
        raise ValueError("contract: value contains a tab or newline: %r" % (s,))
    return s


def serialize(rows):
    """Sort (metric, key) in byte order and write the file. Rows are 3-tuples."""
    seen = set()
    for metric, key, value in rows:
        if not _SORTABLE.match(metric):
            raise ValueError("contract: metric is not printable ASCII: %r" % (metric,))
        if not _SORTABLE.match(key):
            raise ValueError("contract: key is not printable ASCII: %r" % (key,))
        fmt_text(value)
        if (metric, key) in seen:
            raise ValueError("contract: duplicate row for %s/%s" % (metric, key))
        seen.add((metric, key))
    lines = ["%s\t%s\t%s" % row for row in sorted(rows, key=lambda row: row[0] + "\t" + row[1])]
    return HEADER + "\n" + "\n".join(lines) + "\n"


def sha256(s):
    return hashlib.sha256(s.encode("utf-8")).hexdigest()