Source code for disdrodb.l0.readers.template_reader_raw_text_data

#!/usr/bin/env python3

# -----------------------------------------------------------------------------.
# Copyright (c) 2021-2023 DISDRODB developers
#
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program.  If not, see <http://www.gnu.org/licenses/>.
# -----------------------------------------------------------------------------.
"""DISDRODB reader template for raw text data."""
from disdrodb.l0.l0_reader import is_documented_by, reader_generic_docstring
from disdrodb.l0.l0a_processing import read_raw_text_file




@is_documented_by(reader_generic_docstring)
def reader(
    filepath,
    logger=None,
):
    """Reader."""
    ##------------------------------------------------------------------------.
    ###########################
    #### CUSTOMIZABLE CODE ####
    ###########################
    #### - Define raw data headers
    column_names = []  # [ADD THE COLUMN NAMES LIST HERE]

    ##------------------------------------------------------------------------.
    #### Define reader options
    # - For more info: https://pandas.pydata.org/docs/reference/api/pandas.read_csv.html
    reader_kwargs = {}

    # - Define reader engine
    #   - C engine is faster
    #   - Python engine is more feature-complete
    reader_kwargs["engine"] = "python"

    # - Define on-the-fly decompression of on-disk data
    #   - Available: gzip, bz2, zip
    reader_kwargs["compression"] = "infer"

    # - Strings to recognize as NA/NaN and replace with standard NA flags
    #   - Already included: '#N/A', '#N/A N/A', '#NA', '-1.#IND', '-1.#QNAN',
    #                       '-NaN', '-nan', '1.#IND', '1.#QNAN', '<NA>', 'N/A',
    #                       'NA', 'NULL', 'NaN', 'n/a', 'nan', 'null'
    reader_kwargs["na_values"] = ["na", "", "error", " NA"]

    # - Define behaviour when encountering bad lines
    reader_kwargs["on_bad_lines"] = "skip"

    # Skip first row as columns names
    reader_kwargs["header"] = None

    # - Avoid first column to become df index
    reader_kwargs["index_col"] = False

    # - Define delimiter [THIS MIGHT BE CUSTOMIZED]
    reader_kwargs["delimiter"] = ","

    # Skip a specific number of rows [THIS MIGHT BE CUSTOMIZED]
    reader_kwargs["skiprows"] = None

    ##------------------------------------------------------------------------.
    #### Read the data
    df = read_raw_text_file(
        filepath=filepath,
        column_names=column_names,
        reader_kwargs=reader_kwargs,
        logger=logger,
    )

    ##------------------------------------------------------------------------.
    #### Adapt the dataframe to adhere to DISDRODB L0 standards
    # [ADD YOUR CUSTOM CODE HERE]

    return df