Aidem-Media-DLL-Analysis/tests/test_diff.py

"""Unit tests for the diff engine + an integration test over the committed golden pair."""

from __future__ import annotations

from pathlib import Path

import pytest

from ams.diff import compute_diff, filter_by_owner
from ams.render import render_text
from ams.snapshot import Snapshot

SNAP_DIR = Path(__file__).resolve().parents[1] / "snapshots"


def _snap(**axes) -> Snapshot:
    base = {"binary": {"name": "x", "engine": "e", "compiler": "c"},
            "types": [], "methods": [], "events": [], "fields": [],
            "struct_layout": [], "method_inheritance": [], "field_inheritance": []}
    base.update(axes)
    return Snapshot(base)


# --- unit --------------------------------------------------------------------------------------
def test_types_added_removed_changed():
    old = _snap(types=[
        {"script_name": "ANIMO", "cpp_class": "CMC_Animo", "object_size": 108, "via_module_iface": False},
        {"script_name": "OLD", "cpp_class": "CMC_Old", "object_size": 10, "via_module_iface": False},
    ])
    new = _snap(types=[
        {"script_name": "ANIMO", "cpp_class": "CMC_Animo", "object_size": 128, "via_module_iface": False},
        {"script_name": "NEW", "cpp_class": "CMC_New", "object_size": 20, "via_module_iface": False},
    ])
    d = compute_diff(old, new)["types"]
    assert [t["script_name"] for t in d["added"]] == ["NEW"]
    assert [t["script_name"] for t in d["removed"]] == ["OLD"]
    assert len(d["changed"]) == 1
    assert d["changed"][0]["changes"]["object_size"] == [108, 128]


def test_dual_multiarray_kept_distinct():
    # same script_name, different via_module_iface -> two distinct, stable keys
    items = [
        {"script_name": "MULTIARRAY", "cpp_class": "CMC_MultiArray", "object_size": 88, "via_module_iface": False},
        {"script_name": "MULTIARRAY", "cpp_class": "CMC_MultiArray", "object_size": 88, "via_module_iface": True},
    ]
    d = compute_diff(_snap(types=items), _snap(types=items))["types"]
    assert d == {"added": [], "removed": [], "changed": []}


def test_method_id_change_and_move():
    old = _snap(methods=[
        {"owner": "CMC_Animo", "name": "SHOW", "id": 1},
        {"owner": "CMC_Animo", "name": "PING", "id": 9},
    ])
    new = _snap(methods=[
        {"owner": "CMC_Animo", "name": "SHOW", "id": 2},   # id changed
        {"owner": "CMC", "name": "PING", "id": 9},          # moved Animo -> base CMC
    ])
    d = compute_diff(old, new)
    assert d["methods"]["changed"][0]["changes"]["id"] == [1, 2]
    assert d["moved_methods"] == [{"name": "PING", "from_owners": ["CMC_Animo"], "to_owners": ["CMC"]}]


def test_field_type_change_and_owner_filter():
    old = _snap(fields=[{"owner": "CMC_Animo", "name": "FPS", "type": "int", "order": 0},
                        {"owner": "CMC_Sound", "name": "VOLUME", "type": "int", "order": 0}])
    new = _snap(fields=[{"owner": "CMC_Animo", "name": "FPS", "type": "double", "order": 0},
                        {"owner": "CMC_Sound", "name": "VOLUME", "type": "int", "order": 0}])
    d = filter_by_owner(compute_diff(old, new), "CMC_Animo")
    assert d["fields"]["changed"][0]["changes"]["type"] == ["int", "double"]
    assert d["fields"]["added"] == [] and d["fields"]["removed"] == []


def test_method_dispatch_body_change():
    old = _snap(
        methods=[{"owner": "CMC_Animo", "name": "SHOW", "id": 1}],
        method_dispatch=[{"owner": "CMC_Animo", "id": 1, "impl": None,
                          "impl_addr": "0x1", "calls": ["CMC_Animo::getAnimo", "vtbl+0xa0"]}],
    )
    new = _snap(
        methods=[{"owner": "CMC_Animo", "name": "SHOW", "id": 1}],
        method_dispatch=[{"owner": "CMC_Animo", "id": 1, "impl": None,
                          "impl_addr": "0x1", "calls": ["CMC_Animo::getAnimo", "vtbl+0xa4"]}],
    )
    d = compute_diff(old, new)["method_dispatch"]
    assert len(d["changed"]) == 1
    ch = d["changed"][0]
    assert ch["item"]["name"] == "SHOW"  # name joined from the methods axis on (owner, id)
    assert ch["changes"]["calls"] == [["CMC_Animo::getAnimo", "vtbl+0xa0"],
                                      ["CMC_Animo::getAnimo", "vtbl+0xa4"]]
    assert "METHOD BODIES" in render_text(compute_diff(old, new))


def test_render_no_diff():
    out = render_text(compute_diff(_snap(), _snap()))
    assert "(no differences)" in out


# --- integration over the committed golden pair ------------------------------------------------
@pytest.mark.skipif(not (SNAP_DIR / "PIKLIB8.dll.snapshot.json").exists(),
                    reason="golden snapshots not present")
def test_golden_pair_piklib_to_bloomoo():
    old = Snapshot.load(str(SNAP_DIR / "PIKLIB8.dll.snapshot.json"))   # VS6
    new = Snapshot.load(str(SNAP_DIR / "bloomoodll.dll.snapshot.json"))  # VS8
    d = compute_diff(old, new)

    added_types = {t["script_name"] for t in d["types"]["added"]}
    assert {"GRBUFFER", "INTERNET"} <= added_types
    assert d["types"]["removed"] == []

    size_changes = {c["item"]["script_name"]: c["changes"].get("object_size")
                    for c in d["types"]["changed"]}
    assert size_changes.get("MOUSE") == [104, 128]

    # BlooMoo added Animo methods; none removed for Animo
    animo = filter_by_owner(d, "CMC_Animo")
    assert "GETFPS" in {m["name"] for m in animo["methods"]["added"]}
    assert animo["fields"]["added"] == []  # Animo's script fields are identical across the pair

    # rendering must not raise and must mention the new types
    text = render_text(d)
    assert "GRBUFFER" in text and "MOUSE" in text

    # method bodies recovered cross-compiler: Animo SHOW (id 1) maps to the same vtable leaf
    # despite MSVC6 inlining it and MSVC8 keeping it as a separate show() function
    disp_old = {(r["owner"], r["id"]): r for r in old.method_dispatch}
    disp_new = {(r["owner"], r["id"]): r for r in new.method_dispatch}
    assert disp_old[("CMC_Animo", 1)]["calls"][-1] == "vtbl+0xa0"
    assert disp_new[("CMC_Animo", 1)]["calls"][-1] == "vtbl+0xa0"