Scratchpad for developing a Python method to mint DOIs via EZID, WIP

mint_method.py

''' a scratch pad for developing the DOI minting method we will use with Janeway '''

# import os
import re
from urllib.parse import quote
import urllib.request as urlreq
from xmltodict import unparse

SHOULDER = 'doi:10.15697/' #for the actual plugin, get the value from the settings.py
USERNAME = 'apitest' #for the actual plugin, get the value from the settings.py
PASSWORD = 'apitest' #for the actual plugin, get the value from the settings.py
ENDPOINT_URL = 'https://uc3-ezidx2-stg.cdlib.org'
#URL = 'https://ezid.cdlib.org' #for the actual plugin, get the value from the settings.py
# staging URL is: https://uc3-ezidx2-stg.cdlib.org in case you need it
TARGET_URL = 'https://escholarship.org/'

class EzidHTTPErrorProcessor(urlreq.HTTPErrorProcessor):
    ''' Error Processor, required to let 201 responses pass '''
    def http_response(self, request, response):
    # Bizarre that Python leaves this out.
        if response.code == 201:
            return response
        else:
            return urlreq.HTTPErrorProcessor.http_response(self, request, response)
    https_response = http_response

def send_create_request(data, shoulder, username, password, endpoint_url):
    ''' sends a create request to EZID '''
    method = "POST"
    path = '/shoulder/' + encode(shoulder)

    opener = urlreq.build_opener(EzidHTTPErrorProcessor())
    ezid_handler = urlreq.HTTPBasicAuthHandler()
    ezid_handler.add_password("EZID", endpoint_url, username, password)
    opener.add_handler(ezid_handler)


    request = urlreq.Request("%s/%s" % (endpoint_url, path))
    request.get_method = lambda: method
    request.add_header("Content-Type", "text/plain; charset=UTF-8")
    request.data = data.encode("UTF-8")

    try:
        connection = opener.open(request)
        response = connection.read()
        return response.decode("UTF-8")

    except urlreq.HTTPError as ezid_error:
        print("%d %s\n" % (ezid_error.code, ezid_error.msg))
        if ezid_error.fp is not None:
            response = ezid_error.fp.read()
            if not response.endswith("\n"):
                response += "\n"
            print(response)

def encode(txt):
    ''' encode a text string '''
    return quote(txt, ":/")

def mint_doi_via_ezid(shoulder, username, password, endpoint_url, target_url, group_title, contributors, title, posted_date, acceptance_date):
    ''' Sends a mint request for the specified shoulder, via the EZID url, for the specified target '''

    posted_content = {
        "posted_content": {
            "@xmlns": "http://www.crossref.org/schema/4.4.0",
            "@xmlns:xsi": "http://www.w3.org/2001/XMLSchema-instance",
            "@xmlns:jats": "http://www.ncbi.nlm.nih.gov/JATS1",
            "@xsi:schemaLocation": "http://www.crossref.org/schema/4.4.0 http://www.crossref.org/schema/deposit/crossref4.4.0.xsd",
            "group_title": group_title,
            "contributors": contributors,
            "titles": {
                "title": title
            },
            "posted_date": posted_date,
            "acceptance_date": acceptance_date,
            "doi_data": {"doi": "10.50505/preprint_sample_doi_2", "resource": "https://escholarship.org/"}
        }
    }

    metadata = unparse(posted_content).replace('\n', '').replace('\r', '')

    # uncomment this to validate the metadata payload
    # print('\n\n')
    # print('Using this metadata:')
    # print('\n\n')
    # print(unparse(posted_content, pretty=True))

    #uncomment this and the import pdb in the imports above to crank up the debugger
    #pdb.set_trace()

    # These notes will be useful when we move this method to Django, but right now they're useless
    # from django.conf import settings
    # settings.ezid_shoulder
    # settings.ezid_username
    # settings.ezid_password

    # print('\n\n')
    # print('using these values, shoulder: ' + shoulder + '; username: ' + username + '; password: ' + password)
    # print('\n\n')

    # send the mint request
    # print('Sending request to EZID API...\n\n')

    # build the payload
    payload = 'crossref: ' + metadata + '\n_crossref: yes\n_profile: crossref\n_target: ' + target_url + '\n_owner: ' + username

    # print('\n\npayload:\n\n')
    # print(payload)

    result = send_create_request(payload, shoulder, username, password, endpoint_url)
    return result

#### BEGIN MAIN METHOD
if __name__ == "__main__":
    GROUP_TITLE = 'Physical Sciences and Mathematics'
    TITLE = 'test title, will be deleted'
    POSTED_DATE = {"month": "10", "day": "2", "year": "2020"}
    ACCEPTANCE_DATE = POSTED_DATE
    CONTRIBUTORS = {
                "person_name": [
                    {"@sequence": "first", "@contributor_role": "author", "given_name": "Hardy", "surname": "Pottinger", "ORCID": "https://orcid.org/0000-0001-8549-9354"},
                    {"@sequence": "additional", "@contributor_role": "author", "given_name": "Marco", "surname": "Psuedonym"},
                    {"@sequence": "additional", "@contributor_role": "author", "given_name": "Jonathan", "surname": "Alias"},
                    {"@sequence": "additional", "@contributor_role": "author", "given_name": "Ricardo", "surname": "Nomdeplume"},
                    {"@sequence": "additional", "@contributor_role": "author", "given_name": "Melissa", "surname": "Unreal"},
                    {"@sequence": "additional", "@contributor_role": "author", "given_name": "Simon", "surname": "Faker"}]
                }

    my_result = mint_doi_via_ezid(SHOULDER, USERNAME, PASSWORD, ENDPOINT_URL, TARGET_URL, GROUP_TITLE, CONTRIBUTORS, TITLE, POSTED_DATE, ACCEPTANCE_DATE)
    # print(my_result)
    if my_result.startswith('success:'):
        new_doi = re.search("doi:[0-9A-Z./]+", my_result).group()
        print('DOI successfully created: ' + new_doi)
    #