UmbraTrans/tools/translation/tests/test_render.py

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

"""Tests for the renderer.

The renderer writes the book the reader receives, so its typography is part
of the translation: the fonts, the language codes, the chapter-numbering
convention and the fixed editorial strings all have to be the target
language's. A Spanish edition typeset with Chinese fonts and Chinese chapter
headings is the same defect as a Chinese draft filed under a Spanish name,
one level down and much easier to miss.
"""

from __future__ import annotations

import json
import sys
import tempfile
import unittest
from pathlib import Path

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

from languages import resolve  # noqa: E402
from render import build_asciidoc, build_fodt, build_styles  # noqa: E402

CHINESE = resolve("zh-Hans")
SPANISH = resolve("es-ES")
ARABIC = resolve("ar-SA")


def _book(target: str = "zh-Hans", subtitle: str = "交易猎人") -> dict:
    return {
        "title": "Deal Hunter",
        "title_target": "Deal Hunter",
        "subtitle_target": subtitle,
        "target_language": target,
        "chapters": [
            {
                "id": "ch-6",
                "index": 6,
                "row": 6,
                "matter": "body",
                "title": "Salvage",
                "title_target": "Salvage",
                "paragraphs": [
                    {"id": "ch-6-p0000", "type": "narration", "text": "The chair has"},
                    {"id": "ch-6-p0001", "type": "dialogue", "text": "Hello."},
                ],
            },
        ],
    }


def _run_dir(root: Path, text: str) -> Path:
    chapter = root / "ch-6"
    chapter.mkdir(parents=True, exist_ok=True)
    (chapter / "translation.json").write_text(
        json.dumps({"paragraphs": {"ch-6-p0000": text, "ch-6-p0001": text}}),
        encoding="utf-8",
    )
    return root


class RenderTypographyTests(unittest.TestCase):
    """The renderer's typography is the target language's."""

    def test_the_asciidoc_language_is_the_target_language(self) -> None:
        with tempfile.TemporaryDirectory() as tmp:
            run = _run_dir(Path(tmp), "La silla estaba sucia.")
            asciidoc = build_asciidoc(_book("es-ES", "Cazador de Ofertas"), run, target=SPANISH)
        self.assertIn(":lang: es-ES", asciidoc)
        self.assertNotIn("zh-CN", asciidoc)

    def test_the_stylesheet_carries_the_target_language_codes(self) -> None:
        styles = build_styles(SPANISH)
        self.assertIn('fo:language="es"', styles)
        self.assertIn('fo:country="ES"', styles)
        self.assertIn('style:font-name="Noto Serif"', styles)
        self.assertNotIn('fo:language="zh"', styles)

    def test_an_rtl_target_gets_a_right_to_left_direction(self) -> None:
        self.assertIn('fo:direction="rtl"', build_styles(ARABIC))
        self.assertNotIn('fo:direction="rtl"', build_styles(SPANISH))

    def test_the_chapter_heading_follows_the_target_convention(self) -> None:
        with tempfile.TemporaryDirectory() as tmp:
            run = _run_dir(Path(tmp), "La silla estaba sucia.")
            spanish = build_asciidoc(_book("es-ES"), run, target=SPANISH)
            chinese = build_asciidoc(_book(), run, target=CHINESE)
        self.assertIn("== Capítulo 1  Salvage", spanish)
        self.assertIn("== 第一章　Salvage", chinese)

    def test_a_latin_target_does_not_mark_its_text_as_english(self) -> None:
        """The Latin-run span exists so Chinese line-breaking leaves names alone.

        For a Spanish paragraph the whole text is Latin, and marking it as
        English would tell the renderer that the paragraph is English.
        """
        with tempfile.TemporaryDirectory() as tmp:
            run = _run_dir(Path(tmp), "La silla estaba sucia.")
            spanish = build_fodt(_book("es-ES"), run, target=SPANISH)
            chinese = build_fodt(_book(), run, target=CHINESE)
        self.assertNotIn('text:style-name="Latin"', spanish)
        self.assertIn('text:style-name="Latin"', chinese)

    def test_the_fixed_strings_are_the_target_language_s(self) -> None:
        with tempfile.TemporaryDirectory() as tmp:
            run = _run_dir(Path(tmp), "La silla estaba sucia.")
            spanish = build_asciidoc(_book("es-ES"), run, target=SPANISH, sample=True)
            chinese = build_asciidoc(_book(), run, target=CHINESE, sample=True)
        self.assertIn("Muestra de revisión", spanish)
        self.assertIn("Traducido por Umbra Tools", spanish)
        self.assertNotIn("审阅样本", spanish)
        self.assertIn("审阅样本", chinese)

    def test_the_contents_heading_is_the_target_language_s(self) -> None:
        with tempfile.TemporaryDirectory() as tmp:
            run = _run_dir(Path(tmp), "La silla estaba sucia.")
            spanish = build_fodt(_book("es-ES"), run, target=SPANISH)
        self.assertIn(">Índice</text:index-title-template>", spanish)
        self.assertNotIn(">目录</text:index-title-template>", spanish)

    def test_the_running_header_carries_the_target_subtitle(self) -> None:
        with tempfile.TemporaryDirectory() as tmp:
            run = _run_dir(Path(tmp), "La silla estaba sucia.")
            spanish = build_fodt(_book("es-ES", "Cazador de Ofertas"), run, target=SPANISH)
        self.assertIn("Deal Hunter · Cazador de Ofertas", spanish)

    def test_the_old_book_format_still_renders(self) -> None:
        """A book file written before the subtitle field existed must still work.

        The old format stored the subtitle in the book-level ``title_zh``.
        """
        book = _book()
        del book["subtitle_target"]
        book["title_zh"] = "交易猎人"
        with tempfile.TemporaryDirectory() as tmp:
            run = _run_dir(Path(tmp), "中间的椅子旁。")
            asciidoc = build_asciidoc(book, run, target=CHINESE)
            fodt = build_fodt(book, run, target=CHINESE)
        self.assertIn("= Deal Hunter: 交易猎人", asciidoc)
        self.assertIn("交易猎人", fodt)

    def test_a_chapter_with_no_target_title_falls_back_to_the_english_one(self) -> None:
        """A missing translation is visible; borrowing another language's is not."""
        book = _book("es-ES")
        del book["chapters"][0]["title_target"]
        with tempfile.TemporaryDirectory() as tmp:
            run = _run_dir(Path(tmp), "La silla estaba sucia.")
            asciidoc = build_asciidoc(book, run, target=SPANISH)
        self.assertIn("Salvage", asciidoc)
        self.assertNotIn("打捞", asciidoc)


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