Kris
69fe97a90d
1. 移除Telegram格式化测试中未使用的导入项 2. 修复Teams测试用例，添加monkeypatch参数并配置通配符开关 3. 更新钉钉适配器测试，替换弃用的流属性检查 4. 修正Twitch规范化测试，更新ROOMSTATE测试逻辑 5. 重构会话映射测试，完善数据库执行结果模拟 6. 格式化Slack块构建测试的长参数调用 7. 修复LINE适配器测试，更新能力断言和异步锁使用 8. 修正Slack会话解析测试，修复聊天类型判断错误 9. 更新能力测试，补充缺失的字段检查 10. 修复Matrix适配器测试，修正位置参数和配置校验逻辑 11. 为飞书分析模块测试添加跳过标记 12. 新增微信能力、限流、链接格式、会话路由等模块的单元测试 13. 修复Twitch适配器导入路径和测试断言 14. 新增Discord Webhook、Nextcloud Talk、Signal多账户等模块的单元测试 15. 修复Manager阶段测试的导入路径 16. 新增iMessage异常和命令处理的单元测试 17. 新增Nostr健康检查和相关模块的单元测试 18. 新增Signal守护进程和SSE重连相关测试
125 lines
4.5 KiB
Python
125 lines
4.5 KiB
Python
from __future__ import annotations
|
|
|
|
import pytest
|
|
|
|
from yuxi.channels.adapters.nextcloudtalk.chunking import chunk_text
|
|
|
|
|
|
class TestChunkText:
|
|
def test_short_text_returns_single_chunk(self):
|
|
result = chunk_text("Hello World", limit=4000)
|
|
assert result == ["Hello World"]
|
|
|
|
def test_exact_limit_text(self):
|
|
text = "A" * 4000
|
|
result = chunk_text(text, limit=4000)
|
|
assert len(result) == 1
|
|
assert result[0] == text
|
|
|
|
def test_empty_string(self):
|
|
result = chunk_text("", limit=1000)
|
|
assert result == [""]
|
|
|
|
def test_chunk_markdown_paragraphs(self):
|
|
paragraphs = []
|
|
for i in range(100):
|
|
paragraphs.append(f"Paragraph {i}: " + "x" * 80)
|
|
text = "\n\n".join(paragraphs)
|
|
result = chunk_text(text, limit=500, mode="markdown")
|
|
assert len(result) > 1
|
|
assert all(len(c) <= 500 for c in result)
|
|
reconstructed = "".join(result)
|
|
assert reconstructed == text or all(p in reconstructed for p in paragraphs[:3])
|
|
|
|
def test_chunk_markdown_lines(self):
|
|
lines = []
|
|
for i in range(200):
|
|
lines.append(f"Line {i}: " + "y" * 60)
|
|
text = "\n".join(lines)
|
|
result = chunk_text(text, limit=500, mode="markdown")
|
|
assert len(result) > 1
|
|
assert all(len(c) <= 500 for c in result)
|
|
|
|
def test_chunk_markdown_sentences(self):
|
|
sentences = []
|
|
for i in range(200):
|
|
sentences.append(f"This is sentence number {i} with some content. ")
|
|
text = "".join(sentences)
|
|
result = chunk_text(text, limit=500, mode="markdown")
|
|
assert len(result) > 1
|
|
assert all(len(c) <= 500 for c in result)
|
|
|
|
def test_chunk_markdown_no_breaks_falls_back_to_length(self):
|
|
text = "A" * 5000
|
|
result = chunk_text(text, limit=1000, mode="markdown")
|
|
assert len(result) > 1
|
|
assert all(len(c) <= 1001 for c in result)
|
|
|
|
def test_chunk_newline_mode(self):
|
|
lines = [f"Line {i:03d}: " + "x" * 200 for i in range(30)]
|
|
text = "\n".join(lines)
|
|
result = chunk_text(text, limit=500, mode="newline")
|
|
assert len(result) > 1
|
|
assert all(len(c) <= 500 for c in result)
|
|
|
|
def test_chunk_newline_single_line_equals_limit(self):
|
|
text = "A" * 500
|
|
result = chunk_text(text, limit=500, mode="newline")
|
|
assert len(result) == 1
|
|
assert result[0] == text
|
|
|
|
def test_chunk_newline_long_line(self):
|
|
text = "A" * 600
|
|
result = chunk_text(text, limit=500, mode="newline")
|
|
assert len(result) >= 1
|
|
|
|
def test_chunk_by_length(self):
|
|
text = "B" * 2500
|
|
result = chunk_text(text, limit=500, mode="length")
|
|
assert len(result) == 5
|
|
for chunk in result:
|
|
assert len(chunk) == 500
|
|
|
|
def test_chunk_by_length_uneven(self):
|
|
text = "C" * 1234
|
|
result = chunk_text(text, limit=500, mode="length")
|
|
assert len(result) == 3
|
|
assert len(result[0]) == 500
|
|
assert len(result[1]) == 500
|
|
assert len(result[2]) == 234
|
|
|
|
def test_chunk_unknown_mode_falls_back_to_length(self):
|
|
text = "D" * 1500
|
|
result = chunk_text(text, limit=500, mode="unknown_mode")
|
|
assert len(result) == 3
|
|
assert all(len(c) == 500 for c in result)
|
|
|
|
def test_chunk_with_limit_zero_uses_default(self):
|
|
text = "Short text"
|
|
result = chunk_text(text, limit=4000)
|
|
assert result == ["Short text"]
|
|
|
|
def test_chunk_markdown_borderline(self):
|
|
text = "A" * 500 + "\n\n" + "B" * 500
|
|
result = chunk_text(text, limit=550, mode="markdown")
|
|
assert len(result) >= 1
|
|
assert all(len(c) <= 550 for c in result)
|
|
|
|
def test_chunk_markdown_small_limit_forces_sentence_split(self):
|
|
text = "First. Second very long sentence with lots of words. Third. Fourth."
|
|
result = chunk_text(text, limit=20, mode="markdown")
|
|
assert len(result) >= 2
|
|
|
|
def test_chunk_newline_empty_lines(self):
|
|
text = "\n\n\nA\n\nB\n\n"
|
|
result = chunk_text(text, limit=500, mode="newline")
|
|
assert "A" in "".join(result)
|
|
assert "B" in "".join(result)
|
|
|
|
def test_chunk_preserves_all_content(self):
|
|
text = "Hello World\n\nThis is a test.\n\nMore content here."
|
|
result = chunk_text(text, limit=20, mode="markdown")
|
|
reconstructed = "".join(result)
|
|
assert "Hello World" in reconstructed
|
|
assert "This is a test" in reconstructed
|
|
assert "More content here" in reconstructed |