实现 ClinDB 第一批清洗组件

tests/test_page_break_word_join.py

@@ -0,0 +1,83 @@
+from __future__ import annotations
+
+import pytest
+
+from mdpolish import Pipeline, RunStatus
+from mdpolish.component import ComponentContractError
+from mdpolish.components import PageBreakWordJoinComponent
+
+MAPPINGS = (
+    ("possi-", "bly", "possibly"),
+    ("SOFA-", "based", "SOFA-based"),
+    ("threshold.", "olds", "thresholds"),
+)
+
+
+def transform(markdown: str):  # type: ignore[no-untyped-def]
+    return Pipeline([PageBreakWordJoinComponent(MAPPINGS)]).transform(markdown)
+
+
+@pytest.mark.parametrize(
+    ("markdown", "expected"),
+    [
+        ("except possi-\nbly through care", "except possibly through care"),
+        ("except possi-\n\nbly through care", "except possibly through care"),
+        ("use SOFA-\nbased criteria", "use SOFA-based criteria"),
+        ("at threshold.\n\nolds of eight", "at thresholds of eight"),
+        ("except possi-\r\n\r\nbly now", "except possibly now"),
+        ("except possi-\r\rbly now", "except possibly now"),
+    ],
+)
+def test_applies_exact_mapping_across_approved_line_shapes(markdown: str, expected: str) -> None:
+    result = transform(markdown)
+    assert result.status is RunStatus.SUCCESS
+    assert result.output_markdown == expected
+    assert len(result.changes) == 1
+
+
+@pytest.mark.parametrize(
+    "markdown",
+    [
+        "except unknown-\nword here",
+        "except possi-\n\n\nbly here",
+        "except possi-\r\n\nbly here",
+        "except POSSI-\nbly here",
+        "except possi-\nblymore here",
+        "except xSOFA-\nbased here",
+    ],
+)
+def test_unknown_or_unsafe_boundaries_are_preserved(markdown: str) -> None:
+    assert transform(markdown).output_markdown == markdown
+
+
+def test_parameters_and_results_are_independent_of_mapping_order() -> None:
+    first = PageBreakWordJoinComponent(MAPPINGS)
+    second = PageBreakWordJoinComponent(reversed(MAPPINGS))
+    markdown = "possibly becomes possi-\nbly"
+
+    first_result = Pipeline([first]).transform(markdown)
+    second_result = Pipeline([second]).transform(markdown)
+
+    assert first_result.components == second_result.components
+    assert first_result.output_markdown == second_result.output_markdown
+
+
+@pytest.mark.parametrize(
+    "mappings",
+    [
+        (("", "right", "word"),),
+        (("left", "right", "two words"),),
+        (("left", "right", "word"), ("left", "right", "other")),
+        (("left", "right"),),
+    ],
+)
+def test_invalid_mappings_raise_contract_error(mappings: object) -> None:
+    with pytest.raises(ComponentContractError):
+        PageBreakWordJoinComponent(mappings)  # type: ignore[arg-type]
+
+
+def test_successful_output_is_idempotent() -> None:
+    pipeline = Pipeline([PageBreakWordJoinComponent(MAPPINGS)])
+    first = pipeline.transform("except possi-\n\nbly here")
+    assert first.output_markdown is not None
+    assert pipeline.transform(first.output_markdown).changes == ()