from __future__ import annotations

import pytest

from yuxi.channels.sdk.chunking import ChunkConfig, chunk_message


class TestChunkConfig:
    def test_default_values(self):
        cfg = ChunkConfig()
        assert cfg.limit == 4096
        assert cfg.mode == "text"

    def test_custom_values(self):
        cfg = ChunkConfig(limit=2000, mode="markdown")
        assert cfg.limit == 2000
        assert cfg.mode == "markdown"


class TestChunkMessageTextMode:
    def test_short_text_no_chunk(self):
        result = chunk_message("hello world")
        assert len(result) == 1
        assert result[0] == "hello world"

    def test_exact_limit(self):
        text = "a" * 4096
        cfg = ChunkConfig(limit=4096)
        result = chunk_message(text, cfg)
        assert len(result) == 1
        assert len(result[0]) == 4096

    def test_empty_text(self):
        result = chunk_message("")
        assert len(result) == 1
        assert result[0] == ""

    def test_over_limit_splits_at_paragraph(self):
        para1 = "A" * 3000
        para2 = "B" * 3000
        text = f"{para1}\n\n{para2}"
        cfg = ChunkConfig(limit=4096)
        result = chunk_message(text, cfg)
        assert len(result) == 2

    def test_over_limit_splits_at_sentence(self):
        text = ("A" * 1000 + "\u3002") * 5
        cfg = ChunkConfig(limit=4096)
        result = chunk_message(text, cfg)
        assert len(result) == 2

    def test_chunk_size_less_than_limit(self):
        text = "B" * 5000
        cfg = ChunkConfig(limit=4096)
        for ch in chunk_message(text, cfg):
            assert len(ch) <= 4096, f"Chunk length {len(ch)} exceeds limit"

    def test_multiple_paragraphs_merge_when_possible(self):
        text = "short1\n\nshort2\n\nshort3"
        result = chunk_message(text)
        assert len(result) == 1

    def test_very_long_single_paragraph_splits(self):
        text = "word " * 5000
        cfg = ChunkConfig(limit=1000)
        result = chunk_message(text, cfg)
        assert len(result) > 1
        for ch in result:
            assert len(ch) <= 1000

    def test_no_double_newline_splits_by_size(self):
        text = "A" * 8000
        cfg = ChunkConfig(limit=4096)
        result = chunk_message(text, cfg)
        assert len(result) >= 2
        for ch in result:
            assert len(ch) <= 4096


class TestChunkMessageMarkdownMode:
    def test_short_markdown_no_chunk(self):
        text = "# Title\n\nSome content"
        cfg = ChunkConfig(mode="markdown", limit=4096)
        result = chunk_message(text, cfg)
        assert len(result) == 1

    def test_code_block_preserved(self):
        code_block = "```python\n" + "x = 1\n" * 200 + "```"
        text = f"Intro\n\n{code_block}\n\nOutro"
        cfg = ChunkConfig(mode="markdown", limit=500)
        result = chunk_message(text, cfg)
        assert len(result) >= 1

    def test_splits_between_sections(self):
        text = "# Section 1\n\n" + "A" * 3000 + "\n\n# Section 2\n\n" + "B" * 3000
        cfg = ChunkConfig(mode="markdown", limit=4096)
        result = chunk_message(text, cfg)
        assert len(result) >= 2

    def test_markdown_empty_text(self):
        result = chunk_message("", ChunkConfig(mode="markdown"))
        assert len(result) == 1
        assert result[0] == ""

    def test_fenced_code_block_toggle(self):
        text = "before\n```\ncode\n```\nafter"
        cfg = ChunkConfig(mode="markdown", limit=4096)
        result = chunk_message(text, cfg)
        assert len(result) == 1
        assert "```" in result[0]