import unittest

from pydantic import ValidationError

from schemas import KnowledgeRetrievalConfig
from services.knowledge import extract_text, split_text


class KnowledgeTextTest(unittest.TestCase):
    def test_extracts_utf8_text(self):
        self.assertEqual(extract_text("说明.txt", "你好，知识库".encode()), "你好，知识库")

    def test_split_text_keeps_overlap_and_all_content(self):
        text = "第一段。" * 250
        chunks = split_text(text, chunk_size=120, overlap=20)
        self.assertGreater(len(chunks), 1)
        self.assertTrue(all(chunk for chunk in chunks))
        self.assertLessEqual(max(map(len, chunks)), 120)

    def test_rejects_unsupported_binary_file(self):
        with self.assertRaisesRegex(ValueError, "暂仅支持"):
            extract_text("archive.zip", b"data")


class KnowledgeRetrievalConfigTest(unittest.TestCase):
    def test_accepts_unlimited_top_n_with_threshold(self):
        config = KnowledgeRetrievalConfig.model_validate(
            {"mode": "on_demand", "topN": -1, "scoreThreshold": 0.65}
        )

        self.assertEqual(config.top_n, -1)
        self.assertEqual(
            config.model_dump(by_alias=True),
            {"mode": "on_demand", "topN": -1, "scoreThreshold": 0.65},
        )

    def test_rejects_zero_top_n(self):
        with self.assertRaises(ValidationError):
            KnowledgeRetrievalConfig(top_n=0)


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