Description #

MD5 hash value calculator – compute the MD5 digest of text

Key features #

• Generate the corresponding MD5 hash value for each text data entry
• Output a fixed-length (32-character lowercase hexadecimal) digest
• Supports batch processing

Application scenarios #

• Generate a unique identifier for text
• Duplicate detection and data deduplication
• Data consistency verification

Operator parameters #

Input #

Output #

MD5 hash value column, with element type string

Examples #

The following code demonstrates how to use Daft to run the operator and compute the MD5 hash value of text.

from __future__ import annotations

import os

import daft
from daft import col
from daft.las.functions.text.md5_calculator import Md5Calculator
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": [
            '',
            "",
            '',
        ]
    }

    ds = daft.from_pydict(samples)
    ds = ds.with_column(
        "md5_hash",
        las_udf(Md5Calculator)(col("text")),
    )

    ds.show()
    # ╭─────────────────────────────────────────────────────────┬────────────────────────────────╮
    # │ text                                                    ┆ md5_hash                       │
    # │ ---                                                     ┆ ---                            │
    # │ String                                                  ┆ String                         │
    # ╞═════════════════════════════════════════════════════════╪════════════════════════════════╡
    # │ 2023年，中国乘用车市场零售总量恢复至疫情前的水平，显示…          ┆ 5430020e506a5700f52a1817ff6ca… │
    # ├╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┤
    # │ 与此同时，经过多年的快速发展和普及，2023年我国新车金融…          ┆ ea93a7088974310f970f85e3b4d52… │
    # ├╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┤
    # │ 2023年，中国乘用车市场零售总量恢复至疫情前的水平，显示…          ┆ 5430020e506a5700f52a1817ff6ca… │
    # ╰─────────────────────────────────────────────────────────┴────────────────────────────────╯