UmbraTrans/tools/translation/tests/test_translation.py

# Copyright 2026 Umbra Tools (umbratools.com)
# SPDX-License-Identifier: Apache-2.0

"""Unit tests for the translation cleanup and QA helpers.

The pipeline calls an LLM, so these tests deliberately cover only the
deterministic parts: prompt-leak removal, quote normalisation, English
residue detection, JSON extraction and the mechanical QA checks.
"""

from __future__ import annotations

import sys
import unittest
from pathlib import Path

HERE = Path(__file__).resolve().parent
sys.path.insert(0, str(HERE.parent))

from llm import parse_json  # noqa: E402
from pipeline import latin_residue, sanitize  # noqa: E402
from qa import check_chapter  # noqa: E402


class SanitizeTests(unittest.TestCase):
    def test_strips_dialogue_label(self) -> None:
        self.assertEqual(sanitize("（对话；凯因达）“我在游艇上。”"), "“我在游艇上。”")

    def test_strips_narration_label(self) -> None:
        self.assertEqual(sanitize("（旁白）凯因达登上了游艇。"), "凯因达登上了游艇。")

    def test_strips_paragraph_id(self) -> None:
        self.assertEqual(sanitize("[ch-6-p0000] “你好。”"), "“你好。”")

    def test_title_and_brand(self) -> None:
        self.assertEqual(sanitize("《交易猎人》"), "《Deal Hunter》")
        self.assertEqual(sanitize("由乌姆布拉音频系统制作"), "由Umbra Audio制作")

    def test_missing_hour(self) -> None:
        self.assertEqual(sanitize("她在小时前登船。"), "她一小时前登船。")

    def test_straight_quotes_become_chinese(self) -> None:
        self.assertEqual(sanitize('"你好"，她说。'), "“你好”，她说。")

    def test_unmatched_closing_quote_removed(self) -> None:
        self.assertEqual(sanitize("凯因达登上了游艇。”"), "凯因达登上了游艇。")

    def test_unmatched_opening_quote_closed(self) -> None:
        self.assertEqual(sanitize("“你好"), "“你好”")

    def test_ellipsis_and_dash(self) -> None:
        self.assertEqual(sanitize("等等... 然后--"), "等等…… 然后——")


class ResidueTests(unittest.TestCase):
    def test_lowercase_english_is_flagged(self) -> None:
        common, proper = latin_residue("她被 escorted 到了舱室。")
        self.assertEqual(common, ["escorted"])
        self.assertEqual(proper, [])

    def test_allowed_names_are_ignored(self) -> None:
        common, proper = latin_residue("Deal Hunter 和 Hunter 在 Umbra Audio。")
        self.assertEqual(common, [])
        self.assertEqual(proper, [])

    def test_unknown_capitalised_name_is_reported(self) -> None:
        common, proper = latin_residue("这是 Foo 的船。")
        self.assertEqual(common, [])
        self.assertEqual(proper, ["Foo"])


class JsonTests(unittest.TestCase):
    def test_plain_json(self) -> None:
        self.assertEqual(parse_json('{"a": 1}'), {"a": 1})

    def test_fenced_json(self) -> None:
        self.assertEqual(parse_json('```json\n{"a": 1}\n```'), {"a": 1})

    def test_json_with_prose(self) -> None:
        self.assertEqual(parse_json('结果如下：\n{"a": 1}\n完毕。'), {"a": 1})


class QaTests(unittest.TestCase):
    def test_missing_paragraph_is_block(self) -> None:
        chapter = {
            "id": "ch-x",
            "index": 1,
            "title": "Test",
            "paragraphs": [
                {"id": "ch-x-p0000", "type": "narration", "text": "One."},
                {"id": "ch-x-p0001", "type": "narration", "text": "Two."},
            ],
        }
        data = {"paragraphs": {"ch-x-p0000": "第一段。"}}
        issues, metrics = check_chapter(chapter, data)
        kinds = {i["kind"] for i in issues}
        self.assertIn("missing", kinds)
        self.assertEqual(metrics["translated"], 1)

    def test_metadata_leak_and_residue(self) -> None:
        chapter = {
            "id": "ch-x",
            "index": 1,
            "title": "Test",
            "paragraphs": [
                {"id": "ch-x-p0000", "type": "narration", "text": "One."},
                {"id": "ch-x-p0001", "type": "narration", "text": "The Albert system is far."},
            ],
        }
        data = {
            "paragraphs": {
                "ch-x-p0000": "（旁白）第一段 escorted。",
                "ch-x-p0001": "阿尔伯特系统很远。",
            }
        }
        issues, _ = check_chapter(chapter, data)
        kinds = {i["kind"] for i in issues}
        self.assertIn("metadata_leak", kinds)
        self.assertIn("english_residue", kinds)
        self.assertIn("system_mistranslated", kinds)

    def test_ship_systems_are_not_star_systems(self) -> None:
        chapter = {
            "id": "ch-x",
            "index": 1,
            "title": "Test",
            "paragraphs": [
                {"id": "ch-x-p0000", "type": "narration", "text": "Keep away from the ship systems."},
            ],
        }
        data = {"paragraphs": {"ch-x-p0000": "远离飞船系统。"}}
        issues, _ = check_chapter(chapter, data)
        self.assertNotIn("system_mistranslated", {i["kind"] for i in issues})


if __name__ == "__main__":
    unittest.main()