Стадия перевода: мост к book_translator без модификации стороннего репозитория

scripts/test_translate.py

@@ -0,0 +1,82 @@
+#!/usr/bin/env python3
+"""Самопроверка моста без сети: python3 test_translate.py"""
+import json
+from pathlib import Path
+
+import translate as t
+
+
+def test_marks_roundtrip():
+    src = 'She thinks <i>this is bad</i> &amp; says &#x201c;no&#x201d;'
+    marked = t.to_marks(src)
+    assert "<i>" not in marked and "⟦i⟧" in marked
+    assert "&amp;" not in marked, "сущности должны раскрываться для переводчика"
+    body, ok = t.from_marks(marked)
+    assert ok
+    assert "<i>this is bad</i>" in body
+    assert "&amp;" in body, "спецсимволы должны экранироваться обратно"
+
+
+def test_broken_marks_drop_tags():
+    body, ok = t.from_marks("текст ⟦i⟧без закрытия")
+    assert not ok and "⟦" not in body and "<i>" not in body
+
+
+def test_language_detection():
+    assert t.detect_language("the quick brown fox " * 40)[0] == "en"
+    assert t.detect_language("быстрая бурая лиса " * 40)[0] == "ru"
+    assert t.detect_language("short")[0] == "unknown"
+
+
+def test_split_and_rebuild(tmp: Path):
+    src = tmp / "book.html"
+    src.write_text("\n".join([
+        "<html><body>",
+        "<h1>CHAPTER 1</h1>",
+        "<p>He said <i>hello</i> loudly.</p>",
+        '<p class="figure"><img src="images/img01.png"/></p>',
+        "<h1>CHAPTER 2</h1>",
+        "<p>Second chapter text.</p>",
+        "</body></html>",
+    ]), encoding="utf-8")
+
+    blocks = t.parse_blocks(src)
+    assert len(blocks) == 4, "картинка не должна попадать в перевод"
+    chapters = t.split_chapters(blocks)
+    assert [len(c) for c in chapters] == [2, 2]
+
+    extracted = tmp / "extracted"
+    t.write_input(chapters, extracted)
+    ch0 = json.loads((extracted / "chapter_000.json").read_text(encoding="utf-8"))
+    assert ch0["title"] == "CHAPTER 1"
+    assert ch0["paragraphs"][1] == "He said ⟦i⟧hello⟦/i⟧ loudly."
+
+    # подделываем ответ book_translator: тот же формат, тот же порядок
+    trans = tmp / "translations"
+    trans.mkdir()
+    for n, ch in enumerate(chapters):
+        paragraphs = [json.loads((extracted / ("chapter_%03d.json" % n))
+                                 .read_text(encoding="utf-8"))["paragraphs"][i]
+                      .replace("He said", "Он сказал").replace("hello", "привет")
+                      for i in range(len(ch))]
+        (trans / ("chapter_%03d_translated.json" % n)).write_text(
+            json.dumps({"number": n, "paragraphs": paragraphs}, ensure_ascii=False),
+            encoding="utf-8")
+
+    out = tmp / "book.ru.html"
+    assert t.rebuild(src, chapters, tmp, out)
+    result = out.read_text(encoding="utf-8")
+    assert "<p>Он сказал <i>привет</i> loudly.</p>" in result
+    assert '<img src="images/img01.png"/>' in result, "картинка должна уцелеть"
+    assert result.count("<h1>") == 2
+
+
+if __name__ == "__main__":
+    import tempfile
+
+    test_marks_roundtrip()
+    test_broken_marks_drop_tags()
+    test_language_detection()
+    with tempfile.TemporaryDirectory() as d:
+        test_split_and_rebuild(Path(d))
+    print("OK")