Description #

Maximum English word length calculator – calculates the maximum length of English words in text
Key features

• English word recognition: Uses regular expressions to identify English words in text
• Maximum length calculation: Calculates the maximum length among all English words
• Batch processing: Supports calculating the maximum English word length for batch text

Application scenarios #

• Text quality inspection
• Data preprocessing and filtering

Technical features #

• Recognizes only English words: Uses the regular expression [A-Za-z]+ to match English words
• Intelligent processing: Automatically ignores non-English words and only calculates the length of English words

Operator parameters #

Input #

Output #

Maximum word length column, element type is integer

Examples #

The following code demonstrates how to use daft to run the operator to calculate the maximum length of English words in text.

from __future__ import annotations

import os

import daft
from daft import col
from daft.las.functions.text.maximum_word_length_calculator import MaximumWordLengthCalculator
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": [
            "Hello world 你好世界",
            "Python编程 is fun",
            "这是一个中文句子",
            "The quick brown fox jumps over the lazy dog",
            "supercalifragilisticexpialidocious is a very long word",
            None,
        ]
    }

    ds = daft.from_pydict(samples)
    ds = ds.with_column(
        "max_word_length",
        las_udf(
            MaximumWordLengthCalculator,
            construct_args={},
        )(col("text")),
    )

    ds.show()
    # ╭────────────────────────────────┬─────────────────╮
    # │ text                           ┆ max_word_length │
    # │ ---                            ┆ ---             │
    # │ String                         ┆ Int64           │
    # ╞════════════════════════════════╪═════════════════╡
    # │ Hello world 你好世界           ┆ 5               │
    # ├╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┤
    # │ Python编程 is fun              ┆ 6               │
    # ├╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┤
    # │ 这是一个中文句子               ┆ 0               │
    # ├╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┤
    # │ The quick brown fox jumps ove… ┆ 5               │
    # ├╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┤
    # │ supercalifragilisticexpialido… ┆ 34              │
    # ├╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┤
    # │ None                           ┆ None            │
    # ╰────────────────────────────────┴─────────────────╯