实现 ClinDB 第一批清洗组件

tests/test_repeated_running_header.py

@@ -0,0 +1,64 @@
+from __future__ import annotations
+
+import pytest
+
+from mdpolish import Pipeline, RunStatus
+from mdpolish.components import RepeatedRunningHeaderComponent
+
+HEADER = "## Repeated Paper Header"
+
+
+def transform(markdown: str):  # type: ignore[no-untyped-def]
+    return Pipeline([RepeatedRunningHeaderComponent()]).transform(markdown)
+
+
+@pytest.mark.parametrize("line_ending", ["\n", "\r\n", "\r"])
+def test_bridges_interrupted_sentence_and_deletes_other_occurrence(line_ending: str) -> None:
+    markdown = line_ending.join(
+        (
+            "Sentence continues in",
+            "",
+            HEADER,
+            "",
+            "the next line.",
+            "",
+            "18. Reference",
+            "",
+            HEADER,
+            "",
+            "19. Reference",
+        )
+    )
+    result = transform(markdown)
+
+    assert result.status is RunStatus.SUCCESS
+    assert result.output_markdown == line_ending.join(
+        ("Sentence continues in the next line.", "", "18. Reference", "", "19. Reference")
+    )
+    assert len(result.changes) == 2
+
+
+@pytest.mark.parametrize(
+    "markdown",
+    [
+        f"before\n\n{HEADER}\n\nafter",
+        f"Sentence ends.\n\n{HEADER}\n\nAfter\n\nAnother sentence.\n\n{HEADER}\n\nOther",
+        f"Sentence continues\n\n{HEADER}\n\nAfter\n\nText ends.\n\n{HEADER}\n\nOther",
+        f"Sentence continues\n\n{HEADER}\n\nafter\n{HEADER}\nnot blank",
+    ],
+)
+def test_missing_or_unsafe_group_evidence_preserves_document(markdown: str) -> None:
+    assert transform(markdown).output_markdown == markdown
+
+
+def test_header_matching_is_exact_and_not_keyword_based() -> None:
+    markdown = "continues\n\n## Any Header\n\nfrom here\n\n18. Ref\n\n## Any Header\n\n19. Ref"
+    result = transform(markdown)
+    assert result.output_markdown == "continues from here\n\n18. Ref\n\n19. Ref"
+
+
+def test_successful_output_is_idempotent() -> None:
+    pipeline = Pipeline([RepeatedRunningHeaderComponent()])
+    first = pipeline.transform(f"continues\n\n{HEADER}\n\nfrom here\n\ntext\n\n{HEADER}\n\nend")
+    assert first.output_markdown is not None
+    assert pipeline.transform(first.output_markdown).changes == ()