Les deux services traduisent desormais les documents par lots numeros dans une seule requete, comme le provider OpenAI : vitesse multipliee et moins de limites de debit. Repli automatique texte par texte si la reponse du service est douteuse ou en erreur : aucune traduction perdue, le document n'echoue jamais a cause d'un lot. Tests: nouveau test_deepseek_provider.py + extension minimax.
313 lines
13 KiB
Python
313 lines
13 KiB
Python
"""
|
|
Tests for the DeepSeekTranslationProvider.
|
|
|
|
Covers:
|
|
- defaults (public endpoint ``api.deepseek.com/v1``, model ``deepseek-chat``)
|
|
- translation success, 401/429 handling, empty-text short-circuit
|
|
|
|
Batch mode (ported from the OpenAI provider):
|
|
- same language pair + metadata chunk → ONE numbered-JSON request for all texts
|
|
- unparseable/failed batch answer → per-item fallback, every text still translated
|
|
- mixed metadata or a single text → no batch (individual requests)
|
|
"""
|
|
|
|
import json
|
|
|
|
import pytest
|
|
from unittest.mock import patch, MagicMock
|
|
|
|
from services.providers.deepseek_provider import (
|
|
DeepSeekTranslationProvider,
|
|
DeepSeekProviderError,
|
|
DEEPSEEK_RATE_LIMITED,
|
|
DEEPSEEK_INVALID_KEY,
|
|
DEEPSEEK_TIMEOUT,
|
|
DEEPSEEK_SERVICE_ERROR,
|
|
)
|
|
from services.providers.schemas import TranslationRequest
|
|
|
|
|
|
class TestDeepSeekProviderConfig:
|
|
"""Defaults must point at the real public endpoint."""
|
|
|
|
def test_default_base_url_is_public_host(self):
|
|
provider = DeepSeekTranslationProvider(api_key="k", max_retries=0)
|
|
assert provider._base_url == "https://api.deepseek.com/v1"
|
|
|
|
def test_default_model_is_deepseek_chat(self):
|
|
provider = DeepSeekTranslationProvider(api_key="k", max_retries=0)
|
|
assert provider._model == "deepseek-chat"
|
|
|
|
def test_custom_base_url_respected(self):
|
|
provider = DeepSeekTranslationProvider(
|
|
api_key="k", base_url="https://proxy.example.com/v1", max_retries=0
|
|
)
|
|
assert provider._base_url == "https://proxy.example.com/v1"
|
|
|
|
def test_get_name(self):
|
|
provider = DeepSeekTranslationProvider(api_key="k", max_retries=0)
|
|
assert provider.get_name() == "deepseek"
|
|
|
|
def test_empty_api_key_raises(self):
|
|
with pytest.raises(ValueError, match="API key cannot be empty"):
|
|
DeepSeekTranslationProvider(api_key=" ")
|
|
|
|
|
|
class TestDeepSeekTranslateText:
|
|
@pytest.fixture
|
|
def provider(self):
|
|
return DeepSeekTranslationProvider(api_key="k", max_retries=0)
|
|
|
|
def _mock_post(self, payload, status_code=200):
|
|
mock_response = MagicMock()
|
|
mock_response.status_code = status_code
|
|
mock_response.json.return_value = payload
|
|
mock_response.text = ""
|
|
return mock_response
|
|
|
|
@patch("requests.post")
|
|
def test_success(self, mock_post, provider):
|
|
mock_post.return_value = self._mock_post(
|
|
{"choices": [{"message": {"content": "Bonjour"}}], "usage": {}}
|
|
)
|
|
resp = provider.translate_text(TranslationRequest(text="Hello", target_language="fr"))
|
|
assert resp.translated_text == "Bonjour"
|
|
assert resp.provider_name == "deepseek"
|
|
assert mock_post.call_args[0][0] == "https://api.deepseek.com/v1/chat/completions"
|
|
|
|
def test_empty_text_short_circuits(self, provider):
|
|
resp = provider.translate_text(TranslationRequest(text="", target_language="fr"))
|
|
assert resp.translated_text == ""
|
|
|
|
@patch("requests.post")
|
|
def test_invalid_key_returns_error(self, mock_post, provider):
|
|
mock_post.return_value = self._mock_post({"error": "bad key"}, status_code=401)
|
|
resp = provider.translate_text(TranslationRequest(text="Hello", target_language="fr"))
|
|
assert resp.error_code == DEEPSEEK_INVALID_KEY
|
|
# Original text returned on failure.
|
|
assert resp.translated_text == "Hello"
|
|
|
|
@patch("time.sleep")
|
|
@patch("requests.post")
|
|
def test_rate_limit_then_success(self, mock_post, mock_sleep):
|
|
provider = DeepSeekTranslationProvider(api_key="k", max_retries=2, retry_delay=0.01)
|
|
mock_post.side_effect = [
|
|
self._mock_post({"error": "slow down"}, status_code=429),
|
|
self._mock_post({"choices": [{"message": {"content": "Hola"}}], "usage": {}}),
|
|
]
|
|
resp = provider.translate_text(TranslationRequest(text="Hello", target_language="es"))
|
|
assert resp.translated_text == "Hola"
|
|
assert mock_sleep.called # backoff happened
|
|
|
|
@patch("requests.post")
|
|
def test_service_error_when_empty_choices(self, mock_post, provider):
|
|
mock_post.return_value = self._mock_post({"choices": []})
|
|
resp = provider.translate_text(TranslationRequest(text="Hello", target_language="fr"))
|
|
assert resp.error_code == DEEPSEEK_SERVICE_ERROR
|
|
|
|
|
|
class TestDeepSeekBatchTranslation:
|
|
"""Batch mode: one numbered-JSON request per same pair/metadata chunk."""
|
|
|
|
@pytest.fixture
|
|
def provider(self):
|
|
return DeepSeekTranslationProvider(api_key="k", max_retries=0)
|
|
|
|
def _mock_post(self, payload, status_code=200):
|
|
mock_response = MagicMock()
|
|
mock_response.status_code = status_code
|
|
mock_response.json.return_value = payload
|
|
mock_response.text = ""
|
|
return mock_response
|
|
|
|
def _batch_response(self, translations):
|
|
"""Mock a 200 response whose content is a numbered JSON array."""
|
|
content = json.dumps(
|
|
[{"id": i, "translation": t} for i, t in enumerate(translations)]
|
|
)
|
|
return self._mock_post({"choices": [{"message": {"content": content}}], "usage": {}})
|
|
|
|
@patch("requests.post")
|
|
def test_batch_of_three_uses_single_request(self, mock_post, provider):
|
|
mock_post.return_value = self._batch_response(["Bonjour", "Au revoir", "Merci"])
|
|
requests = [
|
|
TranslationRequest(text="Hello", target_language="fr"),
|
|
TranslationRequest(text="Goodbye", target_language="fr"),
|
|
TranslationRequest(text="Thank you", target_language="fr"),
|
|
]
|
|
|
|
responses = provider.translate_batch(requests)
|
|
|
|
assert mock_post.call_count == 1
|
|
assert [r.translated_text for r in responses] == ["Bonjour", "Au revoir", "Merci"]
|
|
assert all(r.provider_name == "deepseek" for r in responses)
|
|
assert all(r.error is None for r in responses)
|
|
assert mock_post.call_args[0][0] == "https://api.deepseek.com/v1/chat/completions"
|
|
|
|
@patch("requests.post")
|
|
def test_batch_request_payload_is_numbered_json_with_instructions(self, mock_post, provider):
|
|
mock_post.return_value = self._batch_response(["Bonjour", "Au revoir"])
|
|
requests = [
|
|
TranslationRequest(
|
|
text="Hello",
|
|
target_language="fr",
|
|
source_language="en",
|
|
metadata={"custom_prompt": "use a formal tone"},
|
|
),
|
|
TranslationRequest(
|
|
text="Goodbye",
|
|
target_language="fr",
|
|
source_language="en",
|
|
metadata={"custom_prompt": "use a formal tone"},
|
|
),
|
|
]
|
|
|
|
provider.translate_batch(requests)
|
|
|
|
payload = mock_post.call_args[1]["json"]
|
|
system = payload["messages"][0]["content"]
|
|
user = payload["messages"][1]["content"]
|
|
# System prompt = base instructions + custom prompt + strict JSON rule.
|
|
assert "professional translator" in system
|
|
assert "ADDITIONAL CONTEXT AND INSTRUCTIONS" in system
|
|
assert "use a formal tone" in system
|
|
assert "BATCH MODE" in system
|
|
assert "ONLY a JSON array" in system
|
|
# User message = the numbered JSON list of the texts.
|
|
parsed = json.loads(user)
|
|
assert [item["text"] for item in parsed] == ["Hello", "Goodbye"]
|
|
assert [item["id"] for item in parsed] == [0, 1]
|
|
|
|
@patch("requests.post")
|
|
def test_invalid_batch_json_falls_back_to_individual(self, mock_post, provider):
|
|
broken_batch = self._mock_post(
|
|
{"choices": [{"message": {"content": "désolé, pas de JSON ici"}}], "usage": {}}
|
|
)
|
|
individuals = [
|
|
self._mock_post({"choices": [{"message": {"content": "Bonjour"}}], "usage": {}}),
|
|
self._mock_post({"choices": [{"message": {"content": "Au revoir"}}], "usage": {}}),
|
|
self._mock_post({"choices": [{"message": {"content": "Merci"}}], "usage": {}}),
|
|
]
|
|
mock_post.side_effect = [broken_batch] + individuals
|
|
requests = [
|
|
TranslationRequest(text="Hello", target_language="fr"),
|
|
TranslationRequest(text="Goodbye", target_language="fr"),
|
|
TranslationRequest(text="Thank you", target_language="fr"),
|
|
]
|
|
|
|
responses = provider.translate_batch(requests)
|
|
|
|
# 1 failed batch attempt + 3 individual calls.
|
|
assert mock_post.call_count == 4
|
|
assert [r.translated_text for r in responses] == ["Bonjour", "Au revoir", "Merci"]
|
|
assert all(r.error is None for r in responses)
|
|
|
|
@patch("requests.post")
|
|
def test_batch_api_error_falls_back_to_individual(self, mock_post, provider):
|
|
# The batch call itself fails (500) — per-item calls still translate everything.
|
|
failed_batch = self._mock_post({"error": "boom"}, status_code=500)
|
|
individuals = [
|
|
self._mock_post({"choices": [{"message": {"content": "Bonjour"}}], "usage": {}}),
|
|
self._mock_post({"choices": [{"message": {"content": "Au revoir"}}], "usage": {}}),
|
|
]
|
|
mock_post.side_effect = [failed_batch] + individuals
|
|
requests = [
|
|
TranslationRequest(text="Hello", target_language="fr"),
|
|
TranslationRequest(text="Goodbye", target_language="fr"),
|
|
]
|
|
|
|
responses = provider.translate_batch(requests)
|
|
|
|
assert mock_post.call_count == 3
|
|
assert [r.translated_text for r in responses] == ["Bonjour", "Au revoir"]
|
|
|
|
@patch("requests.post")
|
|
def test_wrong_batch_length_falls_back_to_individual(self, mock_post, provider):
|
|
# A JSON answer with a missing item is NOT trusted → fallback.
|
|
short_batch = self._batch_response(["Bonjour", "Au revoir"])
|
|
individuals = [
|
|
self._mock_post({"choices": [{"message": {"content": "Bonjour"}}], "usage": {}}),
|
|
self._mock_post({"choices": [{"message": {"content": "Au revoir"}}], "usage": {}}),
|
|
self._mock_post({"choices": [{"message": {"content": "Merci"}}], "usage": {}}),
|
|
]
|
|
mock_post.side_effect = [short_batch] + individuals
|
|
requests = [
|
|
TranslationRequest(text="Hello", target_language="fr"),
|
|
TranslationRequest(text="Goodbye", target_language="fr"),
|
|
TranslationRequest(text="Thank you", target_language="fr"),
|
|
]
|
|
|
|
responses = provider.translate_batch(requests)
|
|
|
|
assert mock_post.call_count == 4
|
|
assert [r.translated_text for r in responses] == ["Bonjour", "Au revoir", "Merci"]
|
|
|
|
@patch("requests.post")
|
|
def test_mixed_metadata_skips_batch(self, mock_post, provider):
|
|
mock_post.side_effect = [
|
|
self._mock_post({"choices": [{"message": {"content": "Bonjour"}}], "usage": {}}),
|
|
self._mock_post({"choices": [{"message": {"content": "Au revoir"}}], "usage": {}}),
|
|
]
|
|
requests = [
|
|
TranslationRequest(
|
|
text="Hello", target_language="fr", metadata={"custom_prompt": "formal"}
|
|
),
|
|
TranslationRequest(
|
|
text="Goodbye", target_language="fr", metadata={"custom_prompt": "casual"}
|
|
),
|
|
]
|
|
|
|
responses = provider.translate_batch(requests)
|
|
|
|
# Two individual calls, no numbered-JSON batch attempt.
|
|
assert mock_post.call_count == 2
|
|
assert [r.translated_text for r in responses] == ["Bonjour", "Au revoir"]
|
|
for call in mock_post.call_args_list:
|
|
assert call[1]["json"]["messages"][1]["content"] in ("Hello", "Goodbye")
|
|
|
|
@patch("requests.post")
|
|
def test_mixed_language_pair_skips_batch(self, mock_post, provider):
|
|
mock_post.side_effect = [
|
|
self._mock_post({"choices": [{"message": {"content": "Bonjour"}}], "usage": {}}),
|
|
self._mock_post({"choices": [{"message": {"content": "Hola"}}], "usage": {}}),
|
|
]
|
|
requests = [
|
|
TranslationRequest(text="Hello", target_language="fr"),
|
|
TranslationRequest(text="Hello", target_language="es"),
|
|
]
|
|
|
|
responses = provider.translate_batch(requests)
|
|
|
|
assert mock_post.call_count == 2
|
|
assert [r.translated_text for r in responses] == ["Bonjour", "Hola"]
|
|
|
|
@patch("requests.post")
|
|
def test_single_request_is_individual(self, mock_post, provider):
|
|
mock_post.return_value = self._mock_post(
|
|
{"choices": [{"message": {"content": "Bonjour"}}], "usage": {}}
|
|
)
|
|
requests = [TranslationRequest(text="Hello", target_language="fr")]
|
|
|
|
responses = provider.translate_batch(requests)
|
|
|
|
assert mock_post.call_count == 1
|
|
assert responses[0].translated_text == "Bonjour"
|
|
# The user message is the raw text, not a numbered JSON list.
|
|
user_message = mock_post.call_args[1]["json"]["messages"][1]["content"]
|
|
assert user_message == "Hello"
|
|
|
|
def test_empty_batch_returns_empty(self, provider):
|
|
assert provider.translate_batch([]) == []
|
|
|
|
|
|
class TestDeepSeekProviderError:
|
|
def test_error_carries_code_and_message(self):
|
|
err = DeepSeekProviderError(DEEPSEEK_TIMEOUT, "timed out", details={"wait": 1})
|
|
assert err.code == DEEPSEEK_TIMEOUT
|
|
assert err.message == "timed out"
|
|
assert err.details == {"wait": 1}
|
|
|
|
def test_rate_limited_code_exists(self):
|
|
# Sanity: the retryable codes used by the provider are importable.
|
|
assert DEEPSEEK_RATE_LIMITED == "DEEPSEEK_RATE_LIMITED"
|