correct_meta.py

import xml.etree.ElementTree as ET
import argparse
import logging
import subprocess

from correct_xml import add_element, correct_charset

_log = logging.getLogger(__name__)


def edit_add_attrs(adds):
    for child in adds:
        if child.attrib["name"] == "cdm_trajectory_variables":
            adds.remove(child)
        if child.attrib["name"] == "subsetVariables":
            adds.remove(child)

    add_element(adds, "cdm_data_type", "TimeSeries")
    add_element(adds, "featureType", "TimeSeries")
    add_element(adds, "cdm_timeseries_variables", "datasetID")
    add_element(adds, "subsetVariables", "datasetID")


def update_doc(dataset_id):
    """
    Edit the xml generated by GenerateDatasetsXml.sh for ctd datasets
    """

    document_loc = f"/home/usrerddap/erddap/xml_edit/xml/{dataset_id}.xml"
    dataset_id = f"meta_{dataset_id}"
    tree = ET.parse(document_loc)
    root = tree.getroot()
    root.attrib["datasetID"] = dataset_id 
    correct_charset(root)
    for child in root:
        # fix for addAttributes
        if child.tag == "addAttributes":
            add_attrs = child
            #edit_add_attrs(add_attrs)
        if child.tag == "dataVariable":
            profile_index = False
            # Fix for the profile index
            for grand_child in child:
                if grand_child.tag == "sourceName" and grand_child.text == "deployment_start":
                    profile_index = True
                if profile_index:
                    if grand_child.tag == "destinationName":
                        grand_child.text = "deployment_start"
                        profile_index = False
    ET.indent(tree, '  ')
    out = f"/home/usrerddap/erddap/content/parts/{dataset_id}.xml"
    tree.write(out, encoding="utf-8", xml_declaration=True)
    _log.info(f"Recombining datasets.xml")
    subprocess.check_call(['/usr/bin/bash', "/home/usrerddap/erddap/xml_edit/make_datasets.sh"])


if __name__ == '__main__':
    parser = argparse.ArgumentParser(description='Correct xml for ctd dataset')
    parser.add_argument('dataset_id', type=str, help='dataset id')
    args = parser.parse_args()
    logf = f'/data/log/ctd.log'
    logging.basicConfig(filename=logf,
                        filemode='a',
                        format='%(asctime)s %(levelname)-8s %(message)s',
                        level=logging.INFO,
                        datefmt='%Y-%m-%d %H:%M:%S')
    _log.info(f"Start add dataset {args.dataset_id} to xml")
    update_doc(args.dataset_id)
    _log.info(f"Complete add dataset {args.dataset_id} to xml")