Microservice_Draft

dataverse.sql

1.

INSERT INTO `MCP`.`StandardTasksConfigs` (`pk`, 'execute', `arguments`, `requiresOutputLock`, `lastModified`) 
VALUES ('7c17bd71-9683-4598-8662-89ac7e0797b6', 'dataverse_v0.0' ,'\"%SIPDirectory%\"', '0', '2018-10-02 00:25:01.000000');

2.

INSERT INTO `MCP`.`TasksConfigs` (`pk`, `taskTypePKReference`, `description`, `lastModified`, `taskType`) 
VALUES ('1a6b8183-d988-47cb-af23-48cf5dd71cb9', '7c17bd71-9683-4598-8662-89ac7e0797b6', 'Convert Dataverse Structure', '2012-10-02 00:25:11.000000', '36b2e239-4a57-4aa5-8ebc-7a29139baca6');

3.

INSERT INTO `MCP`.`MicroServiceChainLinks` (`pk`, `microserviceGroup`, `reloadFileList`, `defaultExitMessage`, `lastModified`, `currentTask`, `defaultNextChainLink`) 
VALUES ('3e02f395-a030-47a5-b9fb-a32eb46144bc', 'Verify transfer compliance', '1', '4', '2018-10-02 00:25:06.000000', '1a6b8183-d988-47cb-af23-48cf5dd71cb9', '61c316a6-0a50-4f65-8767-1f44b1eeb6dd');


4.

INSERT INTO `MCP`.`MicroServiceChainLinksExitCodes` (`pk`, `exitCode`, `exitMessage`, `lastModified`, `microServiceChainLink`, `nextMicroServiceChainLink`) 
VALUES ('b4760b68-d9d9-4e63-ac50-85caa09eeaaf', '0', '2', '2018-05-08 13:34:24.947332', '3e02f395-a030-47a5-b9fb-a32eb46144bc', '7d0616b2-afed-41a6-819a-495032e86291');

5.

UPDATE `MCP`.`MicroServiceChainLinksExitCodes` SET `nextMicroServiceChainLink`='3e02f395-a030-47a5-b9fb-a32eb46144bc' 
WHERE `pk`='9cb81a5c-a7a1-43a8-8eb6-3e999923e03c';

duplicates.py

#!/usr/bin/env python2
# -*- coding: utf-8 -*-

# This file is part of Archivematica.
#
# Copyright 2010-2013 Artefactual Systems Inc. <http://artefactual.com>
#
# Archivematica is free software: you can redistribute it and/or modify
# it under the terms of the GNU Affero General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# Archivematica 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 Archivematica.  If not, see <http://www.gnu.org/licenses/>.

from __future__ import print_function
import argparse
import hashlib
import os
import sys

from custom_handlers import get_script_logger

logger = get_script_logger("archivematica.mcp.client.dataverse")


def md5sum(filename, blocksize=65536):
    hash = hashlib.md5()
    with open(filename, "rb") as f:
        for block in iter(lambda: f.read(blocksize), b""):
            hash.update(block)
        return hash.hexdigest()


def map_dataverse(sip_dir):

    flist = []
    for root, subdirs, files in os.walk(sip_dir):
        if files:
            for f in files:
                h = md5sum(os.path.join(root, f))
                logger.info(h)
                flist.append(h)
    if flist:
        print("{0} duplicates in the transfer "
              "directory.".format(len(flist) - len(set(flist))))
    print("This is stdout")
    logger.error("This is stderr")
    return 0


def main(sip_dir):
    return map_dataverse(sip_dir)


if __name__ == '__main__':
    parser = argparse.ArgumentParser()
    parser.add_argument('sip_dir',
                        type=str,
                        help='The Dataverse SIP folder to process.')
    args = parser.parse_args()
    if args.sip_dir == 'None':
        sys.exit(0)
    logger.info('dataverse called with args: %s', vars(args))
    sys.exit(main(**vars(args)))