实现本地 Markdown 清洗评审器

tests/test_artifact_replay.py

@@ -0,0 +1,189 @@
+from __future__ import annotations
+
+from collections.abc import Callable
+from dataclasses import replace
+
+import pytest
+
+from mdpolish._artifact_replay import (
+    ReplayChange,
+    ReplayComponent,
+    ReplayError,
+    replay_change_chain,
+)
+from mdpolish.models import markdown_sha256
+
+
+def change(
+    *,
+    component_position: int,
+    before_text: str,
+    after_text: str,
+    start: int,
+    end: int,
+    before_sha256: str,
+    after_sha256: str,
+    proposal_index: int = 0,
+    edit_index: int = 0,
+) -> ReplayChange:
+    return ReplayChange(
+        component_id=f"test.{component_position}",
+        component_version="1.0.0",
+        component_position=component_position,
+        proposal_component_position=component_position,
+        proposal_snapshot_sha256=before_sha256,
+        proposal_index=proposal_index,
+        edit_index=edit_index,
+        start=start,
+        end=end,
+        before=before_text,
+        after=after_text,
+        before_sha256=before_sha256,
+        after_sha256=after_sha256,
+    )
+
+
+def test_replay_builds_zero_change_stages_and_utf16_editor_ranges() -> None:
+    original = "\ufeff😀 old\r\nCafe\u0301"
+    final = "\ufeff😀 new\r\nCafe\u0301"
+    input_hash = markdown_sha256(original)
+    final_hash = markdown_sha256(final)
+    recorded = change(
+        component_position=0,
+        before_text="old",
+        after_text="new",
+        start=3,
+        end=6,
+        before_sha256=input_hash,
+        after_sha256=final_hash,
+    )
+
+    replayed = replay_change_chain(
+        input_markdown=original,
+        input_sha256=input_hash,
+        components=(ReplayComponent("test.0", "1.0.0"), ReplayComponent("test.1", "1.0.0")),
+        changes=(recorded,),
+        current_sha256=final_hash,
+        current_markdown=final,
+        include_zero_change_stages=True,
+    )
+
+    assert replayed.current_markdown == final
+    assert len(replayed.stages) == 2
+    assert replayed.stages[1].before_markdown == final
+    assert replayed.stages[1].after_markdown == final
+    assert replayed.stages[1].changes == ()
+    assert (replayed.changes[0].line, replayed.changes[0].column) == (1, 4)
+    assert (replayed.changes[0].editor_start, replayed.changes[0].editor_end) == (4, 7)
+
+
+def test_replay_uses_full_descending_application_key_not_record_order() -> None:
+    original = "abcd"
+    final = "aXXcYY"
+    input_hash = markdown_sha256(original)
+    final_hash = markdown_sha256(final)
+    right = change(
+        component_position=0,
+        before_text="d",
+        after_text="YY",
+        start=3,
+        end=4,
+        before_sha256=input_hash,
+        after_sha256=final_hash,
+        proposal_index=1,
+    )
+    left = change(
+        component_position=0,
+        before_text="b",
+        after_text="XX",
+        start=1,
+        end=2,
+        before_sha256=input_hash,
+        after_sha256=final_hash,
+    )
+
+    replayed = replay_change_chain(
+        input_markdown=original,
+        input_sha256=input_hash,
+        components=(ReplayComponent("test.0", "1.0.0"),),
+        changes=(right, left),
+        current_sha256=final_hash,
+        current_markdown=final,
+        include_zero_change_stages=True,
+    )
+
+    assert replayed.current_markdown == final
+
+
+@pytest.mark.parametrize(
+    ("mutate", "message"),
+    [
+        (lambda item: replace(item, component_position=2), "component position"),
+        (lambda item: replace(item, proposal_component_position=1), "proposal reference"),
+        (lambda item: replace(item, before="bad"), "recorded snapshot"),
+        (lambda item: replace(item, after_sha256="0" * 64), "batch hash"),
+    ],
+)
+def test_replay_rejects_untrusted_change_chains(
+    mutate: Callable[[ReplayChange], ReplayChange], message: str
+) -> None:
+    original = "old"
+    final = "new"
+    input_hash = markdown_sha256(original)
+    final_hash = markdown_sha256(final)
+    valid = change(
+        component_position=0,
+        before_text="old",
+        after_text="new",
+        start=0,
+        end=3,
+        before_sha256=input_hash,
+        after_sha256=final_hash,
+    )
+    tampered = mutate(valid)
+
+    with pytest.raises(ReplayError, match=message):
+        replay_change_chain(
+            input_markdown=original,
+            input_sha256=input_hash,
+            components=(ReplayComponent("test.0", "1.0.0"),),
+            changes=(tampered,),
+            current_sha256=final_hash,
+            current_markdown=final,
+            include_zero_change_stages=True,
+        )
+
+
+def test_replay_rejects_conflicting_ranges() -> None:
+    original = "abc"
+    input_hash = markdown_sha256(original)
+    first = change(
+        component_position=0,
+        before_text="ab",
+        after_text="x",
+        start=0,
+        end=2,
+        before_sha256=input_hash,
+        after_sha256="0" * 64,
+    )
+    second = change(
+        component_position=0,
+        before_text="bc",
+        after_text="y",
+        start=1,
+        end=3,
+        before_sha256=input_hash,
+        after_sha256="0" * 64,
+        proposal_index=1,
+    )
+
+    with pytest.raises(ReplayError, match="conflicting"):
+        replay_change_chain(
+            input_markdown=original,
+            input_sha256=input_hash,
+            components=(ReplayComponent("test.0", "1.0.0"),),
+            changes=(first, second),
+            current_sha256=input_hash,
+            current_markdown=None,
+            include_zero_change_stages=False,
+        )