fix(documents): retain language extensions in ZIP exports (#6848)

routes/document/document_routes.py

@@ -812,10 +812,13 @@ def setup_document_routes(session_manager, upload_handler=None) -> APIRouter:
                     ext = _ext.get(doc.language or "text", ".txt")
                     base = (doc.title or "document").strip() or "document"
                     base = re.sub(r"[^\w\-. ]+", "", base)[:60].strip() or doc.id
-                    name = base if "." in base else base + ext
+                    has_ext = base.lower().endswith(ext)
+                    stem = base[:-len(ext)] if has_ext else base
+                    suffix = base[-len(ext):] if has_ext else ext
+                    name = stem + suffix
                     i = 1
                     while name in used:
-                        name = f"{base}-{i}" + ("" if "." in base else ext)
+                        name = f"{stem}-{i}{suffix}"
                         i += 1
                     used.add(name)
                     content = doc.current_content or ""

tests/test_document_export_zip_filenames.py

@@ -0,0 +1,96 @@
+"""ZIP exports keep language extensions and place collision suffixes before them."""
+import io
+import zipfile
+
+import pytest
+from fastapi import FastAPI, Request
+from fastapi.testclient import TestClient
+from sqlalchemy import create_engine
+from sqlalchemy.orm import sessionmaker
+
+from core.database import Base, Document
+from routes.document import document_routes
+
+
+@pytest.fixture
+def exports(tmp_path, monkeypatch):
+    engine = create_engine(f"sqlite:///{tmp_path / 'documents.db'}", connect_args={"check_same_thread": False})
+    Base.metadata.create_all(engine)
+    factory = sessionmaker(bind=engine)
+    monkeypatch.setattr(document_routes, "SessionLocal", factory)
+    monkeypatch.setenv("AUTH_ENABLED", "true")
+    app = FastAPI()
+
+    @app.middleware("http")
+    async def fixture_user(request: Request, call_next):
+        request.state.current_user = "alice"
+        return await call_next(request)
+
+    app.include_router(document_routes.setup_document_routes(None))
+
+    def add(doc_id, title, language, content="body\n", owner="alice"):
+        with factory() as db:
+            db.add(Document(id=doc_id, title=title, language=language,
+                            current_content=content, owner=owner, is_active=True))
+            db.commit()
+
+    with TestClient(app) as client:
+        yield client, add
+    engine.dispose()
+
+
+@pytest.mark.parametrize("title,language,filename", [
+    ("config.local", "python", "config.local.py"),
+    ("report.v2", "markdown", "report.v2.md"),
+    ("data.2024", "json", "data.2024.json"),
+    ("module.ts", "typescript", "module.ts"),
+    ("SCRIPT.PY", "python", "SCRIPT.PY"),
+    ("résumé.v2", "text", "résumé.v2.txt"),
+    ("unknown.v2", "unknown", "unknown.v2.txt"),
+    ("draft", None, "draft.txt"),
+    ("project/report.v2", "markdown", "projectreport.v2.md"),
+])
+def test_export_uses_the_language_extension_even_for_dotted_titles(exports, title, language, filename):
+    client, add = exports
+    body = "Original text: α\n"
+    add("doc", title, language, body)
+    response = client.post("/api/documents/export-zip", json={"ids": ["doc"]})
+    assert response.status_code == 200
+    assert response.headers["content-type"] == "application/zip"
+    with zipfile.ZipFile(io.BytesIO(response.content)) as archive:
+        assert archive.namelist() == [filename]
+        assert archive.read(filename).decode() == body
+
+
+@pytest.mark.parametrize("title", ["config.local", "config.local.py"])
+def test_duplicate_names_keep_the_extension_at_the_end(exports, title):
+    client, add = exports
+    for i in range(3):
+        add(str(i), title, "python", f"body {i}")
+    response = client.post("/api/documents/export-zip", json={"ids": ["0", "1", "2"]})
+    assert response.status_code == 200
+    with zipfile.ZipFile(io.BytesIO(response.content)) as archive:
+        assert set(archive.namelist()) == {"config.local.py", "config.local-1.py", "config.local-2.py"}
+        assert {archive.read(name).decode() for name in archive.namelist()} == {"body 0", "body 1", "body 2"}
+
+
+def test_added_extension_collides_safely_with_an_existing_extension(exports):
+    client, add = exports
+    add("a", "report.v2", "markdown", "first")
+    add("b", "report.v2.md", "markdown", "second")
+    response = client.post("/api/documents/export-zip", json={"ids": ["a", "b"]})
+    assert response.status_code == 200
+    with zipfile.ZipFile(io.BytesIO(response.content)) as archive:
+        assert set(archive.namelist()) == {"report.v2.md", "report.v2-1.md"}
+        assert {archive.read(name) for name in archive.namelist()} == {b"first", b"second"}
+
+
+def test_foreign_documents_are_still_excluded_and_email_body_is_preserved(exports):
+    client, add = exports
+    add("owned", "reply.v2", "email", "Subject: Hello\n---\nBody")
+    add("foreign", "private", "python", "secret", owner="bob")
+    response = client.post("/api/documents/export-zip", json={"ids": ["owned", "foreign"]})
+    assert response.status_code == 200
+    with zipfile.ZipFile(io.BytesIO(response.content)) as archive:
+        assert archive.namelist() == ["reply.v2.eml"]
+        assert archive.read("reply.v2.eml") == b"Subject: Hello\r\n\r\nBody"