Chen Yi
8630dcad55
- 修复上次提交把 dfannals/cli.py 写成 0 字节的问题（它是唯一入口，导致管道不可运行） - 性别：解析 <caste>，人物表与写作素材带性别（Ral Fastenhatchets 实为女性） - 新增 dfannals/deslop.py：AI 味机械诊断（硬伤词/句式/标点，按千字密度报告） - 新增 dfannals/normalize.py：标点与结构清理（引号配对、重复段落与句子、模型自加的小节标记） - 新增 dfannals/expand.py 与 prompts/literary-expander.md：按年份场景分块大量扩写 - 专名防幻觉：每块附史料专名白名单，事后按段自动修复可疑专名 - episode 命令并进文笔层（骨架稿另存 .skeleton.md），新增 expand 命令做 A/B 对照 - 新增 notes/switched-threads.md 与 test_deslop / test_normalize 回归测试 - 提交前拦截「已跟踪文件为空」，防止上述事故复发
87 lines
2.8 KiB
Python
87 lines
2.8 KiB
Python
"""标点与结构清理的回归测试。"""
|
||
from __future__ import annotations
|
||
|
||
import sys
|
||
from pathlib import Path
|
||
|
||
sys.path.insert(0, str(Path(__file__).resolve().parents[1]))
|
||
|
||
from dfannals import normalize
|
||
|
||
|
||
def test_ascii_quotes_become_chinese() -> None:
|
||
res = normalize.normalize('他说："好。" 她说："不。"')
|
||
assert res.text == "他说：“好。” 她说：“不。”", res.text
|
||
assert any("英文引号" in n for n in res.notes)
|
||
|
||
|
||
def test_halfwidth_punct_between_cjk() -> None:
|
||
res = normalize.normalize("他说,好。她走,停。")
|
||
assert "，" in res.text and "," not in res.text, res.text
|
||
|
||
|
||
def test_english_punctuation_untouched() -> None:
|
||
src = "Mon Sagus, The Plane of Dawn"
|
||
assert normalize.normalize(src).text == src
|
||
|
||
|
||
def test_separator_lines_dropped() -> None:
|
||
res = normalize.normalize("甲段。\n\n---\n\n乙段。")
|
||
assert "---" not in res.text, res.text
|
||
assert any("分隔线" in n for n in res.notes)
|
||
|
||
|
||
def test_stray_section_markings_dropped_but_title_kept() -> None:
|
||
res = normalize.normalize("# 守门人\n\n甲段。\n\n## 一\n\n乙段。\n\n七\n\n丙段。")
|
||
assert res.text.startswith("# 守门人"), res.text
|
||
assert "## 一" not in res.text, res.text
|
||
assert "\n七\n" not in res.text, res.text
|
||
assert any("小节标记" in n for n in res.notes)
|
||
|
||
|
||
def test_duplicate_paragraph_merged() -> None:
|
||
res = normalize.normalize("同一段。\n同一段。\n不同段。")
|
||
assert res.text.count("同一段。") == 1, res.text
|
||
assert any("重复段落" in n for n in res.notes)
|
||
|
||
|
||
def test_duplicate_sentences_merged() -> None:
|
||
res = normalize.normalize("他走了。他走了。她留下。")
|
||
assert res.text.count("他走了。") == 1, res.text
|
||
assert any("重复句子" in n for n in res.notes)
|
||
|
||
|
||
def test_blank_lines_tidied() -> None:
|
||
res = normalize.normalize("甲。\n\n\n\n乙。")
|
||
assert "\n\n\n" not in res.text
|
||
assert res.text == "甲。\n\n乙。"
|
||
|
||
|
||
def test_clean_text_untouched() -> None:
|
||
src = "Ral把绳子绕了两圈，打了个结。她没说话。"
|
||
res = normalize.normalize(src)
|
||
assert res.text == src
|
||
assert not res.changed, res.notes
|
||
|
||
|
||
def _main() -> int:
|
||
tests = [v for k, v in sorted(globals().items()) if k.startswith("test_") and callable(v)]
|
||
failed = 0
|
||
for fn in tests:
|
||
try:
|
||
fn()
|
||
except AssertionError as exc:
|
||
failed += 1
|
||
print(f" ✗ {fn.__name__}: {exc}")
|
||
except Exception as exc: # noqa: BLE001
|
||
failed += 1
|
||
print(f" ✗ {fn.__name__}: {type(exc).__name__}: {exc}")
|
||
else:
|
||
print(f" ✓ {fn.__name__}")
|
||
print(f"\n{len(tests) - failed}/{len(tests)} 通过")
|
||
return 1 if failed else 0
|
||
|
||
|
||
if __name__ == "__main__":
|
||
sys.exit(_main())
|