1from __future__ import annotations
2
3import os
4
5import daft
6from daft import col
7
8from daft.aihc.common.udf import aihc_udf
9from daft.aihc.functions.text.copyright_cleaner import CopyrightCleaner
10
11if __name__ == "__main__":
12    if os.getenv("DAFT_RUNNER", "native") == "ray":
13        import ray
14        ray.init(dashboard_host="0.0.0.0", ignore_reinit_error=True)
15        daft.set_runner_ray()
16    daft.set_execution_config(actor_udf_ready_timeout=6000, min_cpu_per_task=0)
17
18    samples = {
19        "text": [
20            "Some article content.\nCopyright © 2024 Example Corp. All Rights Reserved.",
21            "Normal text without copyright.",
22            "版权所有 © 2023 某公司\n文章内容在这里。",
23        ]
24    }
25    ds = daft.from_pydict(samples)
26    ds = ds.with_column(
27        "cleaned_text",
28        aihc_udf(
29            CopyrightCleaner,
30            num_cpus=1,
31            concurrency=4,
32            batch_size=1024,
33        )(col("text")),
34    )
35    ds.show()