重构为函数式通用 Markdown 修改库

tests/test_regex.py

@@ -0,0 +1,108 @@
+from __future__ import annotations
+
+import re
+
+import pytest
+
+from mdpolish import Modifier, ModifierContractError, Pipeline, RunStatus, regex_replace
+
+
+def test_factory_returns_modifier_and_expands_capture_groups() -> None:
+    modifier = regex_replace(
+        modifier_id="example.swap-date",
+        version="1.0.0",
+        pattern=r"(\d{4})-(\d{2})-(\d{2})",
+        replacement=r"\3/\2/\1",
+        applicability="处理 ISO 形状的虚构日期；不验证真实日历日期。",
+    )
+
+    result = Pipeline([modifier]).transform("A 2026-08-26, B 2027-01-02")
+
+    assert isinstance(modifier, Modifier)
+    assert result.status is RunStatus.SUCCESS
+    assert result.output_markdown == "A 26/08/2026, B 02/01/2027"
+    assert len(result.changes) == 2
+    assert result.changes[0].before == "2026-08-26"
+    assert result.changes[0].after == "26/08/2026"
+
+
+def test_flags_and_factory_parameters_are_recorded() -> None:
+    modifier = regex_replace(
+        modifier_id="example.case",
+        version="2.0.0",
+        pattern="token",
+        replacement="value",
+        flags=re.IGNORECASE | re.MULTILINE,
+    )
+
+    result = Pipeline([modifier]).transform("TOKEN")
+
+    assert result.status is RunStatus.SUCCESS
+    assert result.modifiers[0].modifier_id == modifier.modifier_id
+    assert result.modifiers[0].parameters == modifier.parameters
+    assert dict(modifier.parameters) == {
+        "flags": int(re.IGNORECASE | re.MULTILINE),
+        "pattern": "token",
+        "replacement": "value",
+    }
+
+
+def test_zero_match_and_no_op_replacement_are_stable() -> None:
+    missing = Pipeline(
+        [regex_replace(modifier_id="example.missing", version="1.0.0", pattern="missing", replacement="new")]
+    ).transform("text")
+    no_op = Pipeline(
+        [regex_replace(modifier_id="example.no-op", version="1.0.0", pattern="text", replacement="text")]
+    ).transform("text")
+
+    assert missing.output_markdown == "text"
+    assert missing.changes == ()
+    assert no_op.status is RunStatus.SUCCESS
+    assert no_op.changes == ()
+
+
+@pytest.mark.parametrize("pattern", [r"", r"^", r"a*", r"(?=a)"])
+def test_zero_length_matches_are_rejected(pattern: str) -> None:
+    if pattern == r"(?=a)":
+        modifier = regex_replace(
+            modifier_id="example.zero",
+            version="1.0.0",
+            pattern=pattern,
+            replacement="x",
+        )
+        result = Pipeline([modifier]).transform("a")
+        assert result.status is RunStatus.FAILED
+        assert result.partial_markdown == "a"
+        assert result.changes == ()
+        return
+
+    with pytest.raises(ModifierContractError, match="zero-length"):
+        regex_replace(
+            modifier_id="example.zero",
+            version="1.0.0",
+            pattern=pattern,
+            replacement="x",
+        )
+
+
+def test_invalid_pattern_flags_and_input_types_are_rejected() -> None:
+    with pytest.raises(ModifierContractError, match="compile"):
+        regex_replace(modifier_id="example.invalid", version="1.0.0", pattern="(", replacement="x")
+    with pytest.raises(ModifierContractError, match="flags"):
+        regex_replace(
+            modifier_id="example.flags",
+            version="1.0.0",
+            pattern="x",
+            replacement="y",
+            flags=True,
+        )
+
+
+def test_successful_output_is_idempotent() -> None:
+    pipeline = Pipeline(
+        [regex_replace(modifier_id="example.space", version="1.0.0", pattern=r" {2,}", replacement=" ")]
+    )
+    first = pipeline.transform("a   b")
+    assert first.output_markdown == "a b"
+    assert first.output_markdown is not None
+    assert pipeline.transform(first.output_markdown).changes == ()