1from __future__ import annotations
2
3import os
4import daft
5from daft import col
6
7from daft.aihc.common.udf import aihc_udf
8from daft.aihc.functions.text.url_ratio_calculator import UrlRatioCalculator
9
10if __name__ == "__main__":
11    if os.getenv("DAFT_RUNNER", "native") == "ray":
12        import ray
13        ray.init(dashboard_host="0.0.0.0", ignore_reinit_error=True)
14        daft.set_runner_ray()
15    daft.set_execution_config(actor_udf_ready_timeout=6000, min_cpu_per_task=0)
16
17    samples = {
18        "text": [
19            "今天天气很好",
20            "请访问 https://baidu.com 获取更多信息",
21            "官网 http://example.com 和镜像站 https://mirror.example.org 均可访问",
22            "这段文字中没有任何链接",
23            "联系我们：https://contact.us 或发邮件至 support@test.com",
24            "http://a.com https://b.com https://c.com 三个链接",
25            "",
26        ]
27    }
28
29    ds = daft.from_pydict(samples)
30    ds = ds.with_column(
31        "url_ratio",
32        aihc_udf(
33            UrlRatioCalculator,
34            construct_args={},
35        )(col("text")),
36    )
37    ds.show()