cyclone/backend/tests/test_ack_id_helpers.py

"""Tests for the dedup-ed ack ID helpers (SP27 Task 1).

Locks the contract for the helpers that ``scheduler.py`` + ``api.py``
will both import from one place in ``cyclone.handlers._ack_id``.
"""
from __future__ import annotations

import hashlib
from pathlib import Path

from cyclone.handlers._ack_id import (
    ack_count_summary,
    ack_synthetic_source_batch_id,
    two77ca_synthetic_source_batch_id,
)
from cyclone.parsers.parse_999 import parse_999_text


ACCEPTED = Path(__file__).parent / "fixtures" / "minimal_999.txt"
REJECTED = Path(__file__).parent / "fixtures" / "minimal_999_rejected.txt"


def _parse(path: Path):
    return parse_999_text(path.read_text(), input_file=path.name)


def test_ack_count_summary_all_accepted():
    result = _parse(ACCEPTED)
    recv, acc, rej, code = ack_count_summary(result)
    assert recv == 1
    assert acc == 1
    assert rej == 0
    assert code == "A"


def test_ack_count_summary_all_rejected():
    result = _parse(REJECTED)
    recv, acc, rej, code = ack_count_summary(result)
    assert recv == 1
    assert acc == 0
    assert rej == 1
    assert code == "R"


def test_ack_count_summary_partial_uses_p_code():
    # Synthesize a 2-set 999 inline with one AK5=A and one AK5=R.
    # ISA is exactly 106 chars (positions 0-105); the parser slices
    # positionally then splits the body on ``~``.
    # SE count = ST + AK1 + AK2_1 + AK5_1 + AK2_2 + AK5_2 + AK9 + SE = 8.
    partial_999 = (
        "ISA*00*          *00*          *ZZ*SUBMITTERID    *ZZ*RECEIVERID     "
        "*240101*1200*^*00501*000000001*0*P*:~"
        "GS*FA*SUBMITTERID*RECEIVERID*20240101*1200*1*X*005010X231A1~"
        "ST*999*0001*005010X231A1~"
        "AK1*HC*0001*1*2~"
        "AK2*837*1~"
        "AK5*A~"
        "AK2*837*2~"
        "AK5*R~"
        "AK9*P*2*1*1~"
        "SE*8*0001~"
        "GE*1*1~"
        "IEA*1*000000001~"
    )
    result = parse_999_text(partial_999, input_file="partial.999")
    recv, acc, rej, code = ack_count_summary(result)
    assert recv == 2
    assert acc == 1
    assert rej == 1
    assert code == "P"


def test_ack_synthetic_with_pcn_and_filename_is_deterministic_and_prefix():
    bsid1 = ack_synthetic_source_batch_id(
        "000000001", pcn="PCN-12345", source_filename="tp_999.x12",
    )
    bsid2 = ack_synthetic_source_batch_id(
        "000000001", pcn="PCN-12345", source_filename="tp_999.x12",
    )
    assert bsid1 == bsid2, "same inputs must produce same id"
    assert bsid1.startswith("999-PCN-12345-")
    # Hash is 8 hex chars
    suffix = bsid1.split("-")[-1]
    assert len(suffix) == 8 and all(
        c in "0123456789abcdef" for c in suffix
    ), suffix


def test_ack_synthetic_with_pcn_strips_whitespace():
    bsid = ack_synthetic_source_batch_id(
        "000000001", pcn="  PCN  ", source_filename="f.x12",
    )
    assert bsid.startswith("999-PCN-")


def test_ack_synthetic_without_pcn_uses_icn():
    bsid = ack_synthetic_source_batch_id(
        "777777777", pcn=None, source_filename="f.x12",
    )
    assert bsid.startswith("999-777777777-")
    # <= 32 chars total (VARCHAR(32) constraint)
    assert len(bsid) <= 32


def test_ack_synthetic_default_icn_when_empty():
    bsid = ack_synthetic_source_batch_id("", pcn=None, source_filename=None)
    # No PCN, no filename → falls through to default ICN ``000000001``
    # (no hash suffix without a filename).
    assert bsid == "999-000000001"


def test_two77ca_synthetic_uses_icn():
    assert two77ca_synthetic_source_batch_id("000012345") == "277CA-000012345"


def test_two77ca_synthetic_empty_falls_back_to_default():
    assert two77ca_synthetic_source_batch_id("") == "277CA-000000001"
    assert two77ca_synthetic_source_batch_id(None) == "277CA-000000001"


def test_ack_count_summary_empty_set_responses_returns_zeros():
    """A 999 envelope without any AK2/IK5 sets is malformed per the spec,
    but the helper must still return a sane (0, 0, 0, 'A') tuple — the
    scheduler adds it to result.errors and the caller decides."""
    class _StubResult:
        set_responses = []
    recv, acc, rej, code = ack_count_summary(_StubResult())
    assert recv == 0
    assert acc == 0
    assert rej == 0
    # rejected == 0 → "A" (no rejection signal in this degenerate case)
    assert code == "A"


def test_ack_synthetic_uses_real_sha1_truncation():
    """The hash should match hashlib.sha1(filename).hexdigest()[:8] so
    a future migration to a different hash is intentional, not drift."""
    expected = hashlib.sha1(b"my-file.x12").hexdigest()[:8]
    bsid = ack_synthetic_source_batch_id(
        "000000001", pcn=None, source_filename="my-file.x12",
    )
    assert bsid.endswith(f"-{expected}")