实现 ClinDB 第一批清洗组件

tests/test_reference_spacing.py

@@ -0,0 +1,65 @@
+from __future__ import annotations
+
+import pytest
+
+from mdpolish import Pipeline, RunStatus
+from mdpolish.components import ReferenceSpacingComponent
+
+
+def transform(markdown: str):  # type: ignore[no-untyped-def]
+    return Pipeline([ReferenceSpacingComponent()]).transform(markdown)
+
+
+def test_normalizes_missing_and_extra_blank_lines_in_references_only() -> None:
+    markdown = "1. Method\n2. Method\n\n## REFERENCES\n\n1. First\n2. Second\n\n\n3. Third"
+    result = transform(markdown)
+
+    assert result.status is RunStatus.SUCCESS
+    assert result.output_markdown == "1. Method\n2. Method\n\n## REFERENCES\n\n1. First\n\n2. Second\n\n3. Third"
+    assert len(result.changes) == 2
+
+
+@pytest.mark.parametrize("heading", ["# References", "## REFERENCES", "### references", "#### ReFeReNcEs"])
+def test_accepts_exact_references_heading_with_ascii_case_folding(heading: str) -> None:
+    markdown = f"{heading}\n\n1. First\n2. Second"
+    assert transform(markdown).output_markdown == f"{heading}\n\n1. First\n\n2. Second"
+
+
+@pytest.mark.parametrize("line_ending", ["\n", "\r\n", "\r"])
+def test_preserves_line_ending_style(line_ending: str) -> None:
+    markdown = line_ending.join(("## References", "", "1. First", "2. Second"))
+    expected = line_ending.join(("## References", "", "1. First", "", "2. Second"))
+    assert transform(markdown).output_markdown == expected
+
+
+@pytest.mark.parametrize(
+    "markdown",
+    [
+        "## Reference\n\n1. First\n2. Second",
+        "## References\n\n1. First\n3. Third",
+        "## References\n\n2. Second\n3. Third",
+        "## References\n\n1. First\n### Subsection\n2. Second",
+        "## References\r\n\r\n1. First\r\n\n2. Second",
+    ],
+)
+def test_ambiguous_or_mixed_sections_are_preserved(markdown: str) -> None:
+    assert transform(markdown).output_markdown == markdown
+
+
+def test_same_or_higher_heading_ends_section() -> None:
+    markdown = "## References\n\n1. First\n2. Second\n\n## Appendix\n\n1. Keep\n2. Keep"
+    result = transform(markdown)
+    assert result.output_markdown == "## References\n\n1. First\n\n2. Second\n\n## Appendix\n\n1. Keep\n2. Keep"
+
+
+def test_multiline_reference_uses_its_last_text_line_as_boundary() -> None:
+    markdown = "## References\n\n1. First line\ncontinuation\n2. Second"
+    result = transform(markdown)
+    assert result.output_markdown == "## References\n\n1. First line\ncontinuation\n\n2. Second"
+
+
+def test_successful_output_is_idempotent() -> None:
+    pipeline = Pipeline([ReferenceSpacingComponent()])
+    first = pipeline.transform("## References\n\n1. First\n2. Second")
+    assert first.output_markdown is not None
+    assert pipeline.transform(first.output_markdown).changes == ()