实现第一版内存清洗核心

落实不可变数据契约、组件基类、原子修改执行器与顺序流水线。补充稳定性复查、审计记录、测试和当前机制文档。
This commit is contained in:
2026-08-22 01:03:03 +08:00
parent 8ac4f1dd12
commit 3edeeaf30e
15 changed files with 2023 additions and 145 deletions
+293
View File
@@ -0,0 +1,293 @@
from __future__ import annotations
from collections.abc import Mapping
from typing import cast
import pytest
from mdpolish import (
Component,
DocumentSnapshot,
ErrorStage,
Pipeline,
ProposedChange,
RunStatus,
TextEdit,
TextSpan,
)
class ReplaceComponent(Component):
def __init__(
self,
needle: str,
replacement: str,
*,
component_id: str,
version: str = "1.0.0",
parameters: object = None,
applicability: str = "处理精确测试字符串,要求完整匹配,排除其他内容。",
) -> None:
self.needle = needle
self.replacement = replacement
self._component_id = component_id
self._version = version
self._parameters = {"needle": needle, "replacement": replacement} if parameters is None else parameters
self._applicability = applicability
@property
def component_id(self) -> str:
return self._component_id
@property
def version(self) -> str:
return self._version
@property
def parameters(self) -> Mapping[str, object]:
return cast(Mapping[str, object], self._parameters)
@property
def applicability(self) -> str:
return self._applicability
def _propose_changes(self, snapshot: DocumentSnapshot) -> tuple[ProposedChange, ...]:
position = snapshot.markdown.find(self.needle)
if position < 0:
return ()
edit = TextEdit(
snapshot_sha256=snapshot.sha256,
span=TextSpan(position, position + len(self.needle)),
expected_text=self.needle,
replacement=self.replacement,
)
return (
ProposedChange(
snapshot_sha256=snapshot.sha256,
reason=f"replace test token for {self.component_id}",
edits=(edit,),
),
)
class ExplodingComponent(ReplaceComponent):
def __init__(self, *, trigger: str | None = None, component_id: str = "test.exploding") -> None:
super().__init__("unused", "unused-replacement", component_id=component_id)
self.trigger = trigger
def _propose_changes(self, snapshot: DocumentSnapshot) -> tuple[ProposedChange, ...]:
if self.trigger is None or snapshot.markdown == self.trigger:
raise RuntimeError(f"SECRET source: {snapshot.markdown}")
return ()
class InvalidReturnComponent(ReplaceComponent):
def __init__(self) -> None:
super().__init__("a", "A", component_id="test.invalid-return")
def _propose_changes(self, snapshot: DocumentSnapshot) -> tuple[ProposedChange, ...]:
return cast(tuple[ProposedChange, ...], [])
class StaleProposalComponent(ReplaceComponent):
def __init__(self) -> None:
super().__init__("a", "A", component_id="test.stale")
def _propose_changes(self, snapshot: DocumentSnapshot) -> tuple[ProposedChange, ...]:
stale_snapshot = DocumentSnapshot(snapshot.markdown + "!")
edit = TextEdit(stale_snapshot.sha256, TextSpan(0, 1), stale_snapshot.markdown[0], "X")
return (ProposedChange(stale_snapshot.sha256, "stale test proposal", (edit,)),)
class OverlapComponent(ReplaceComponent):
def __init__(self) -> None:
super().__init__("a", "A", component_id="test.overlap")
def _propose_changes(self, snapshot: DocumentSnapshot) -> tuple[ProposedChange, ...]:
first = TextEdit(snapshot.sha256, TextSpan(0, 3), snapshot.markdown[0:3], "X")
second = TextEdit(snapshot.sha256, TextSpan(2, 4), snapshot.markdown[2:4], "Y")
return (ProposedChange(snapshot.sha256, "overlapping test proposal", (first, second)),)
def test_empty_pipeline_returns_unchanged_success_for_empty_unicode_text() -> None:
for markdown in ("", "中文\nCafe\u0301\n🙂"):
result = Pipeline([]).transform(markdown)
assert result.status is RunStatus.SUCCESS
assert result.output_markdown == markdown
assert result.partial_markdown is None
assert result.changes == ()
assert result.components == ()
def test_later_component_reads_snapshot_produced_by_earlier_component() -> None:
pipeline = Pipeline(
[
ReplaceComponent("", "", component_id="test.first"),
ReplaceComponent("", "", component_id="test.second"),
]
)
result = pipeline.transform("")
assert result.status is RunStatus.SUCCESS
assert result.output_markdown == ""
assert [change.component_id for change in result.changes] == ["test.first", "test.second"]
assert result.changes[1].before_sha256 == result.changes[0].after_sha256
def test_same_input_components_and_parameters_produce_same_ordered_result() -> None:
pipeline = Pipeline(
[
ReplaceComponent("a", "b", component_id="test.first"),
ReplaceComponent("b", "c", component_id="test.second"),
]
)
assert pipeline.transform("a") == pipeline.transform("a")
def test_successful_pipeline_is_idempotent_on_its_output() -> None:
pipeline = Pipeline([ReplaceComponent("old", "new", component_id="test.replace")])
first = pipeline.transform("old value")
assert first.status is RunStatus.SUCCESS
assert first.output_markdown is not None
second = pipeline.transform(first.output_markdown)
assert second.status is RunStatus.SUCCESS
assert second.output_markdown == "new value"
assert second.changes == ()
def test_single_component_runs_through_pipeline_without_shortcut() -> None:
component = ReplaceComponent("a", "A", component_id="test.single")
result = Pipeline([component]).transform("a")
assert result.status is RunStatus.SUCCESS
assert result.output_markdown == "A"
assert len(result.changes) == 1
def test_transform_error_stops_later_components_and_keeps_only_partial_text() -> None:
pipeline = Pipeline(
[
ReplaceComponent("a", "b", component_id="test.first"),
ExplodingComponent(),
ReplaceComponent("b", "c", component_id="test.never-runs"),
]
)
result = pipeline.transform("a")
assert result.status is RunStatus.FAILED
assert result.output_markdown is None
assert result.partial_markdown == "b"
assert [change.component_id for change in result.changes] == ["test.first"]
assert len(result.errors) == 1
assert result.errors[0].stage is ErrorStage.TRANSFORM
assert result.residual_proposals == ()
def test_unexpected_component_error_does_not_leak_source_or_exception_message() -> None:
result = Pipeline([ExplodingComponent()]).transform("private markdown")
assert result.status is RunStatus.FAILED
assert result.errors[0].error_type == "RuntimeError"
assert "SECRET" not in result.errors[0].message
assert "private markdown" not in result.errors[0].message
def test_invalid_proposal_return_is_a_transform_contract_failure() -> None:
result = Pipeline([InvalidReturnComponent()]).transform("abc")
assert result.status is RunStatus.FAILED
assert result.partial_markdown == "abc"
assert result.errors[0].error_type == "ComponentContractError"
assert result.errors[0].stage is ErrorStage.TRANSFORM
@pytest.mark.parametrize("component", [StaleProposalComponent(), OverlapComponent()])
def test_invalid_edit_batch_fails_atomically(component: Component) -> None:
result = Pipeline([component]).transform("abcd")
assert result.status is RunStatus.FAILED
assert result.partial_markdown == "abcd"
assert result.changes == ()
assert result.errors[0].error_type == "EditValidationError"
def test_duplicate_component_ids_fail_during_preflight_before_modification() -> None:
pipeline = Pipeline(
[
ReplaceComponent("a", "b", component_id="test.duplicate"),
ReplaceComponent("b", "c", component_id="test.duplicate"),
]
)
result = pipeline.transform("a")
assert result.status is RunStatus.FAILED
assert result.partial_markdown == "a"
assert result.changes == ()
assert result.errors[0].error_type == "PipelineContractError"
@pytest.mark.parametrize(
"component",
[
ReplaceComponent("a", "b", component_id="test.bad-version", version="1.0"),
ReplaceComponent("a", "b", component_id="test.bad-parameters", parameters={"bad": {1}}),
ReplaceComponent("a", "b", component_id="test.bad-applicability", applicability=""),
],
)
def test_invalid_component_metadata_fails_before_modification(component: Component) -> None:
result = Pipeline([component]).transform("a")
assert result.status is RunStatus.FAILED
assert result.partial_markdown == "a"
assert result.changes == ()
assert result.errors[0].stage is ErrorStage.TRANSFORM
def test_cross_component_chain_is_reported_unstable_without_a_second_round() -> None:
pipeline = Pipeline(
[
ReplaceComponent("bad", "good", component_id="test.to-good"),
ReplaceComponent("good", "bad", component_id="test.to-bad"),
]
)
result = pipeline.transform("bad")
assert result.status is RunStatus.UNSTABLE
assert result.output_markdown is None
assert result.partial_markdown == "bad"
assert len(result.changes) == 2
assert len(result.residual_proposals) == 1
assert result.residual_proposals[0].component_id == "test.to-good"
assert result.errors == ()
def test_final_review_continues_after_error_and_keeps_valid_residual_proposal() -> None:
pipeline = Pipeline(
[
ExplodingComponent(trigger="done", component_id="test.review-error"),
ReplaceComponent("done", "clean", component_id="test.residual"),
ReplaceComponent("start", "done", component_id="test.producer"),
]
)
result = pipeline.transform("start")
assert result.status is RunStatus.FAILED
assert result.output_markdown is None
assert result.partial_markdown == "done"
assert len(result.errors) == 1
assert result.errors[0].stage is ErrorStage.FINAL_REVIEW
assert result.errors[0].component_id == "test.review-error"
assert len(result.residual_proposals) == 1
assert result.residual_proposals[0].component_id == "test.residual"
assert result.residual_proposals[0].proposal_ref.snapshot_sha256 == result.current_sha256