Description #

Regular expression batch replacement processor

Key features #

• Dual-mode replacement mechanism:
  • Exact string match replacement
  • Regular expression pattern match replacement
• Batch processing capability:
  • Supports parallel processing of multiple pattern-replacement pairs
• Fault tolerance mechanism:
  • Skips abnormal patterns and records detailed logs

Operator parameters #

Input #

Output #

Array of replaced text content, with element type string

Parameters #

If a parameter does not have a default value, it is required

Examples #

The following code demonstrates how to use daft to run the operator to replace specific expressions.

from __future__ import annotations

import os

import daft
from daft import col
from daft.las.functions.text.regex_replacement import RegexReplacer
from daft.las.functions.udf import las_udf

if __name__ == "__main__":

    if os.getenv("DAFT_RUNNER", "native") == "ray":
        import logging

        import ray

        def configure_logging():
            logging.basicConfig(
                level=logging.INFO,
                format="%(asctime)s - %(name)s - %(levelname)s - %(message)s",
                datefmt="%Y-%m-%d %H:%M:%S.%s".format(),
            )
            logging.getLogger("tracing.span").setLevel(logging.WARNING)
            logging.getLogger("daft_io.stats").setLevel(logging.WARNING)
            logging.getLogger("DaftStatisticsManager").setLevel(logging.WARNING)
            logging.getLogger("DaftFlotillaScheduler").setLevel(logging.WARNING)
            logging.getLogger("DaftFlotillaDispatcher").setLevel(logging.WARNING)

        ray.init(dashboard_host="0.0.0.0", runtime_env={"worker_process_setup_hook": configure_logging})
        daft.set_runner_ray()
    daft.set_execution_config(actor_udf_ready_timeout=600)
    daft.set_execution_config(min_cpu_per_task=0)

    samples = {
        "text": [
            "<Query></Query><Title></Title><Url>http://news.cnr.cn/native/gd/20191212/t20191212_524895559.shtml</Url>",
            None,
        ]
    }

    patterns = [r"<.*?>", ""]
    replacements = ["/replace_tag", ""]
    ds = daft.from_pydict(samples)
    ds = ds.with_column(
        "replaced_text",
        las_udf(
            RegexReplacer,
            construct_args={"patterns": patterns, "replacements": replacements},
        )(col("text")),
    )
    ds.show()

    # ╭───────────────────────────────────────┬────────────────────────────────╮
    # │ text                                  ┆ replaced_text                  │
    # │ ---                                   ┆ ---                            │
    # │ Utf8                                  ┆ Utf8                           │
    # ╞═══════════════════════════════════════╪════════════════════════════════╡
    # │ <Query></Query><Title>提升党的领导力…    ┆ /replace_tag/replace_tag/repl… │
    # ├╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┤
    # │ None                                  ┆ None                           │
    # ╰───────────────────────────────────────┴────────────────────────────────╯