Description #

Document format conversion processor that supports conversion between multiple office document formats

Key features #

• Supports conversion from doc/docx to multiple formats
• Uses LibreOffice for high-quality conversion
• Supports local and cloud storage paths
• Provides conversion timeout control
• Automatically handles file upload and download

Format support #

• Input formats: Microsoft Word (.doc, .docx)
• Output formats: PDF (.pdf), ODT (.odt), HTML (.html), plain text (.txt), DOCX (.docx)
• It is recommended to use the docx format for optimal conversion results

Operator parameters #

Input #

Output #

Output file path; only TOS paths are supported

Parameters #

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

Examples #

The following code demonstrates how to use Daft (for distributed processing) to perform docx to pdf conversion.

# Copyright (c) Beijing Volcano Engine Technology Ltd.

from __future__ import annotations

import os

import daft
from daft import col
from daft.las.functions.doc import DocConvert
from daft.las.functions.udf import las_udf

if __name__ == "__main__":

    # After conversion, the modified document will be saved to the specified TOS path. Therefore, you need to set environment variables to ensure write permissions to TOS, including: ACCESS_KEY, SECRET_KEY, TOS_ENDPOINT, TOS_REGION, TOS_TEST_DIR
    TOS_DIR = os.getenv("TOS_TEST_DIR", "tos_bucket")
    output_dir = f"tos://{TOS_DIR}/doc/doc_convert"

    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)

    tos_dir_url = os.getenv("TOS_DIR_URL", "las-cn-beijing-public-online.tos-cn-beijing.volces.com")
    samples = {
        "docx": [
            f"https://{tos_dir_url}/public/shared_doc_dataset/sample.docx"
        ],
    }
    df = daft.from_pydict(samples)

    constructor_kwargs = {"target_format": "pdf", "output_dir": output_dir}

    # Distributed processing using Daft
    df = df.with_column(
        "pdf",
        las_udf(DocConvert, construct_args=constructor_kwargs, concurrency=1)(col("docx")),
    )

    df.show()
    # ╭──────────────────────────────────────────────┬──────────────────────────────────────────────╮
    # │ docx                                         ┆ pdf                                          │
    # │ ---                                          ┆ ---                                          │
    # │ Utf8                                         ┆ Utf8                                         │
    # ╞══════════════════════════════════════════════╪══════════════════════════════════════════════╡
    # │  https://las-cn-beijing-publi-…     ┆ tos://tos_bucket/doc/doc_convert/sample.pdf  │
    # ╰──────────────────────────────────────────────┴──────────────────────────────────────────────╯