实现 ClinDB 第一批清洗组件

tests/test_manuscript_line_number.py

@@ -0,0 +1,85 @@
+from __future__ import annotations
+
+import pytest
+
+from mdpolish import Pipeline, RunStatus
+from mdpolish.components import ManuscriptLineNumberComponent
+
+
+def _document(
+    *,
+    count: int = 20,
+    heading_numbers: frozenset[int] = frozenset({5, 15}),
+    numbers: tuple[int, ...] | None = None,
+    line_ending: str = "\n",
+) -> str:
+    values = numbers if numbers is not None else tuple(range(1, count + 1))
+    body = [
+        f"## {number} Section {number}" if number in heading_numbers else f"{number} body {number}"
+        for number in values
+    ]
+    return line_ending.join(("1 Affiliation", "2 Institute", "## Abstract", *body))
+
+
+def transform(markdown: str):  # type: ignore[no-untyped-def]
+    return Pipeline([ManuscriptLineNumberComponent()]).transform(markdown)
+
+
+def test_removes_long_monotonic_sequence_but_preserves_pre_abstract_affiliations() -> None:
+    result = transform(_document())
+
+    assert result.status is RunStatus.SUCCESS
+    assert result.output_markdown is not None
+    assert result.output_markdown.startswith("1 Affiliation\n2 Institute\n## Abstract\nbody 1")
+    assert "## Section 5" in result.output_markdown
+    assert len(result.changes) == 20
+
+
+@pytest.mark.parametrize("line_ending", ["\n", "\r\n", "\r"])
+def test_preserves_all_supported_line_endings(line_ending: str) -> None:
+    result = transform(_document(line_ending=line_ending))
+    assert result.output_markdown is not None
+    assert result.output_markdown.count(line_ending) == _document(line_ending=line_ending).count(line_ending)
+
+
+def test_allows_skipped_numbers_when_sequence_is_strictly_increasing() -> None:
+    numbers = tuple(range(10, 30))
+    result = transform(_document(numbers=numbers, heading_numbers=frozenset({14, 24})))
+
+    assert result.status is RunStatus.SUCCESS
+    assert len(result.changes) == 20
+
+
+@pytest.mark.parametrize(
+    "markdown",
+    [
+        _document(count=19, heading_numbers=frozenset({5, 15})),
+        _document(heading_numbers=frozenset({5})),
+        _document(numbers=(*tuple(range(1, 20)), 10), heading_numbers=frozenset({5, 15})),
+        _document().replace("## Abstract", "## ABSTRACT"),
+        _document() + "\n## Abstract",
+    ],
+)
+def test_incomplete_or_ambiguous_evidence_preserves_the_document(markdown: str) -> None:
+    result = transform(markdown)
+    assert result.output_markdown == markdown
+    assert result.changes == ()
+
+
+def test_lists_years_and_numbers_inside_body_are_not_candidates() -> None:
+    markdown = _document() + "\n1. list\n1) list\n2024 report\nThe panel included 35 experts"
+    result = transform(markdown)
+
+    assert result.output_markdown is not None
+    assert result.output_markdown.endswith("1. list\n1) list\n2024 report\nThe panel included 35 experts")
+    assert len(result.changes) == 20
+
+
+def test_successful_output_is_idempotent() -> None:
+    pipeline = Pipeline([ManuscriptLineNumberComponent()])
+    first = pipeline.transform(_document())
+    assert first.output_markdown is not None
+    second = pipeline.transform(first.output_markdown)
+
+    assert second.status is RunStatus.SUCCESS
+    assert second.changes == ()