实现本地清洗实验与产物保存

tests/test_reporting.py

@@ -0,0 +1,177 @@
+from __future__ import annotations
+
+import json
+from collections.abc import Mapping
+from dataclasses import replace
+
+import pytest
+
+from mdpolish import Component, DocumentSnapshot, Pipeline, ProposedChange, RunStatus, TextEdit, TextSpan
+from mdpolish.reporting import ReportingError, build_document_report, build_unified_diff
+
+
+class ReplaceComponent(Component):
+    def __init__(self, needle: str, replacement: str, component_id: str) -> None:
+        self.needle = needle
+        self.replacement = replacement
+        self._component_id = component_id
+
+    @property
+    def component_id(self) -> str:
+        return self._component_id
+
+    @property
+    def version(self) -> str:
+        return "1.0.0"
+
+    @property
+    def parameters(self) -> Mapping[str, object]:
+        return {"needle": self.needle, "replacement": self.replacement}
+
+    @property
+    def applicability(self) -> str:
+        return "处理精确测试标记，要求完整匹配，排除其他文本。"
+
+    def _propose_changes(self, snapshot: DocumentSnapshot) -> tuple[ProposedChange, ...]:
+        position = snapshot.markdown.find(self.needle)
+        if position < 0:
+            return ()
+        edit = TextEdit(
+            snapshot.sha256,
+            TextSpan(position, position + len(self.needle)),
+            self.needle,
+            self.replacement,
+        )
+        return (ProposedChange(snapshot.sha256, f"replace {self.needle}", (edit,)),)
+
+
+class ExplodingComponent(ReplaceComponent):
+    def __init__(self) -> None:
+        super().__init__("unused", "unused-replacement", "test.exploding")
+
+    def _propose_changes(self, snapshot: DocumentSnapshot) -> tuple[ProposedChange, ...]:
+        raise RuntimeError(f"private: {snapshot.markdown}")
+
+
+def test_success_report_replays_multiple_component_snapshots_and_derives_locations() -> None:
+    markdown = "x\r\ntarget\n"
+    pipeline = Pipeline(
+        [
+            ReplaceComponent("x", "XX", "test.expand"),
+            ReplaceComponent("target", "done", "test.target"),
+        ]
+    )
+    result = pipeline.transform(markdown)
+
+    report = build_document_report(
+        document_id="paper",
+        source_label="data/md/paper.md",
+        input_markdown=markdown,
+        result=result,
+    )
+    payload = json.loads(report.result_json)
+
+    assert result.status is RunStatus.SUCCESS
+    assert report.cleaned_markdown == b"XX\r\ndone\n"
+    assert payload["changes"][0]["location"] == {"line": 1, "column": 1}
+    assert payload["changes"][1]["location"] == {"line": 2, "column": 1}
+    assert payload["changes"][1]["before"] == "target"
+    assert payload["changes"][1]["after"] == "done"
+    assert payload["changes"][1]["before_sha256"] == result.changes[1].before_sha256
+    assert payload["changes"][1]["after_sha256"] == result.changes[1].after_sha256
+    assert report.diff is not None
+    assert b"--- a/paper.md\n+++ b/paper.md\n" in report.diff
+    assert b"data/md/paper.md" not in report.diff
+
+
+def test_zero_change_success_still_has_cleaned_markdown_and_empty_diff() -> None:
+    markdown = "中文\nCafe\u0301\n"
+    result = Pipeline([]).transform(markdown)
+
+    report = build_document_report(
+        document_id="unchanged",
+        source_label="论文.md",
+        input_markdown=markdown,
+        result=result,
+    )
+
+    assert report.cleaned_markdown == markdown.encode()
+    assert report.diff == b""
+    assert report.change_count == 0
+    assert report.result_json.endswith(b"\n")
+    assert "论文".encode() in report.result_json
+    assert b"\\u4e2d" not in report.result_json
+
+
+def test_diff_preserves_final_newline_changes_and_uses_report_newlines() -> None:
+    diff = build_unified_diff("paper", "same\r\n", "same")
+
+    assert b"--- a/paper.md\n+++ b/paper.md\n" in diff
+    assert b"-same\n+same\n\\ No newline at end of file\n" in diff
+    assert b"\r" not in diff
+
+
+def test_failed_report_keeps_change_audit_but_does_not_render_partial_markdown() -> None:
+    pipeline = Pipeline(
+        [
+            ReplaceComponent("a", "b", "test.first"),
+            ExplodingComponent(),
+        ]
+    )
+    result = pipeline.transform("a")
+
+    report = build_document_report(
+        document_id="failed",
+        source_label="failed.md",
+        input_markdown="a",
+        result=result,
+    )
+    payload = json.loads(report.result_json)
+
+    assert result.status is RunStatus.FAILED
+    assert report.cleaned_markdown is None
+    assert report.diff is None
+    assert payload["output"] == {"cleaned_path": None, "diff_path": None}
+    assert len(payload["changes"]) == 1
+    assert payload["errors"][0]["error_type"] == "RuntimeError"
+    assert "private" not in payload["errors"][0]["message"]
+    assert "partial_markdown" not in payload
+
+
+def test_unstable_report_serializes_residual_proposals_without_partial_markdown() -> None:
+    pipeline = Pipeline(
+        [
+            ReplaceComponent("bad", "good", "test.to-good"),
+            ReplaceComponent("good", "bad", "test.to-bad"),
+        ]
+    )
+    result = pipeline.transform("bad")
+
+    report = build_document_report(
+        document_id="unstable",
+        source_label="unstable.md",
+        input_markdown="bad",
+        result=result,
+    )
+    payload = json.loads(report.result_json)
+
+    assert result.status is RunStatus.UNSTABLE
+    assert report.cleaned_markdown is None
+    assert report.diff is None
+    assert payload["residual_proposals"][0]["proposal"]["reason"] == "replace bad"
+    assert payload["residual_proposals"][0]["proposal"]["edits"][0]["expected_text"] == "bad"
+    assert "partial_markdown" not in payload
+
+
+def test_report_rejects_a_tampered_change_hash_chain() -> None:
+    result = Pipeline([ReplaceComponent("a", "b", "test.replace")]).transform("a")
+    tampered_change = replace(result.changes[0], after_sha256="0" * 64)
+    tampered_result = replace(result, changes=(tampered_change,))
+
+    with pytest.raises(ReportingError, match="batch hash"):
+        build_document_report(
+            document_id="tampered",
+            source_label="tampered.md",
+            input_markdown="a",
+            result=tampered_result,
+        )