实现 ClinDB 第一批清洗组件

tests/test_word_review_comment.py

@@ -0,0 +1,69 @@
+from __future__ import annotations
+
+import pytest
+
+from mdpolish import Pipeline, RunStatus
+from mdpolish.components import WordReviewCommentComponent
+
+
+def transform(markdown: str):  # type: ignore[no-untyped-def]
+    return Pipeline([WordReviewCommentComponent()]).transform(markdown)
+
+
+def test_deletes_single_line_comment_and_one_following_blank() -> None:
+    markdown = "before\nCommented [AB1]: review this\n\nafter"
+    result = transform(markdown)
+
+    assert result.status is RunStatus.SUCCESS
+    assert result.output_markdown == "before\nafter"
+    assert len(result.changes) == 1
+    assert result.changes[0].reason == "删除严格单行 Word 审阅批注及其后一个空行"
+
+
+def test_adjacent_comment_blocks_are_deleted_without_overlap() -> None:
+    markdown = "before\nCommented [A1]: first\n\nCommented [B2R1]: second\n\nafter"
+    result = transform(markdown)
+
+    assert result.output_markdown == "before\nafter"
+    assert len(result.changes) == 2
+    assert result.changes[0].span.end == result.changes[1].span.start
+
+
+@pytest.mark.parametrize("line_ending", ["\n", "\r\n", "\r"])
+def test_preserves_line_ending_style(line_ending: str) -> None:
+    markdown = line_ending.join(("before", "Commented [A1]: note", "", "after"))
+    assert transform(markdown).output_markdown == line_ending.join(("before", "after"))
+
+
+@pytest.mark.parametrize(
+    "comment",
+    [
+        "prefix Commented [A1]: note",
+        " Commented [A1]: note",
+        "Commented []: note",
+        "Commented [A-1]: note",
+        "Commented [A1]:",
+        "Commented [A1]:   ",
+    ],
+)
+def test_similar_lines_are_preserved(comment: str) -> None:
+    markdown = f"before\n{comment}\n\nafter"
+    assert transform(markdown).output_markdown == markdown
+
+
+def test_requires_a_following_blank_line_and_does_not_delete_extra_blanks() -> None:
+    without_blank = "Commented [A1]: note\nafter"
+    with_two_blanks = "before\nCommented [A1]: note\n\n\nafter"
+
+    assert transform(without_blank).output_markdown == without_blank
+    assert transform(with_two_blanks).output_markdown == "before\n\nafter"
+
+
+def test_successful_output_is_idempotent() -> None:
+    pipeline = Pipeline([WordReviewCommentComponent()])
+    first = pipeline.transform("Commented [A1]: note\n\nafter")
+    assert first.output_markdown is not None
+    second = pipeline.transform(first.output_markdown)
+
+    assert second.status is RunStatus.SUCCESS
+    assert second.changes == ()