Merge pull request #699 from alee/datacite_doi_registration

add support for DOI registration on published, peer reviewed models

Makefile

@@ -12,7 +12,7 @@ SECRETS_DIR=${BUILD_DIR}/secrets
 DB_PASSWORD_PATH=${SECRETS_DIR}/db_password
 PGPASS_PATH=${SECRETS_DIR}/.pgpass
 SECRET_KEY_PATH=${SECRETS_DIR}/django_secret_key
-EXT_SECRETS=hcaptcha_secret github_client_secret orcid_client_secret discourse_api_key discourse_sso_secret mail_api_key
+EXT_SECRETS=hcaptcha_secret github_client_secret orcid_client_secret discourse_api_key discourse_sso_secret mail_api_key datacite_api_password
 GENERATED_SECRETS=$(DB_PASSWORD_PATH) $(PGPASS_PATH) $(SECRET_KEY_PATH)
 
 ENVREPLACE := deploy/scripts/envreplace

base.yml

@@ -33,7 +33,7 @@ services:
       - ./deploy/elasticsearch.conf.d/log4j2.properties:/usr/share/elasticsearch/config/log4j2.properties
       - esdata:/usr/share/elasticsearch/data
   db:
-    image: postgis/postgis:15-3.4
+    image: postgis/postgis:16-3.4
     secrets:
       - db_password
     volumes:
@@ -60,6 +60,7 @@ services:
     build: django
     image: comses/server
     secrets:
+      - datacite_api_password
       - db_password
       - discourse_api_key
       - discourse_sso_secret
@@ -85,6 +86,8 @@ services:
       - ./.env
 
 secrets:
+  datacite_api_password:
+    file: ./build/secrets/datacite_api_password
   db_password:
     file: ./build/secrets/db_password
   discourse_api_key:

deploy/conf/.env.template

@@ -37,6 +37,10 @@ SENTRY_DSN=
 GITHUB_CLIENT_ID=
 ORCID_CLIENT_ID=
 
+# datacite api settings
+DATACITE_API_USERNAME=
+DATACITE_DRY_RUN="true" # allowed values: "true" or "false"
+
 # test
 TEST_USER_ID=10000000
 TEST_USERNAME=__test_user__

django/Dockerfile

@@ -39,7 +39,7 @@ RUN --mount=type=cache,target=/var/lib/apt,sharing=locked \
         unrar-free \
         unzip \
         && update-alternatives --install /usr/bin/python python /usr/bin/python3 1000 \
-        && apt-get upgrade -y -o Dpkg::Options::="--force-confold" \
+        && apt-get upgrade -q -y -o Dpkg::Options::="--force-confold" \
         && mkdir -p /etc/service/django \
         && touch /etc/service/django/run /etc/postgresql-backup-pre \
         && chmod a+x /etc/service/django/run /etc/postgresql-backup-pre \

django/core/pagination.py

@@ -31,11 +31,11 @@ def _to_search_terms(query_params):
     @staticmethod
     def _to_filter_display_terms(query_params):
         """
-        Convert query parameters into a list of displayable filter terms.
+        Convert query parameters into a list of displayable filter terms (replaces underscores withs spaces, etc)
         Args:
             query_params (QueryDict): The query parameters.
         Returns:
-            list: A list of display filter terms.
+            list: A list of displayable filter terms.
         """
         filters = []
         for key, values in query_params.lists():
@@ -47,16 +47,40 @@ def _to_filter_display_terms(query_params):
                 filters.extend(values)
             elif key in ["published_before", "published_after"]:
                 try:
-                    date = parser.isoparse(values[0]).date()
-                    filters.append(f"{key.replace('_', ' ')} {date.isoformat()}")
+                    publication_date = parser.isoparse(values[0]).date()
+                    filters.append(
+                        f"{key.replace('_', ' ')} {publication_date.isoformat()}"
+                    )
                 except ValueError:
+                    # FIXME: this default behavior duplicates what we want to do in the else clause below
                     filters.extend(v.replace("_", " ") for v in values)
             else:
                 filters.extend(v.replace("_", " ") for v in values)
         return filters
 
     @classmethod
-    def limit_page_range(cls, page=1, count=max_result_window, size=page_size):
+    def limit_page_range(cls, page=1, count=None, size=None):
+        """
+        Limits the page range based on the maximum result window and page size.
+
+        This method ensures that the page number and result count do not exceed
+        the configured maximum result window for Elasticsearch. It also clamps
+        the page number to a valid range.
+
+        Args:
+            page (int): The current page number. Defaults to 1.
+            count (int): The total number of results. Defaults to max_result_window.
+            size (int): The number of results per page. Defaults to page_size.
+
+        Returns:
+            tuple: A tuple containing:
+                - limited_count (int): The total number of results to be shown in the current page, clamped to max_result_window.
+                - limited_page_number (int): The clamped page number within the valid range.
+        """
+        if count is None:
+            count = cls.max_result_window
+        if size is None:
+            size = cls.page_size
         try:
             es_settings = getattr(settings, "WAGTAILSEARCH_BACKENDS", {})
             max_result_window = es_settings["default"]["INDEX_SETTINGS"]["settings"][
@@ -73,13 +97,19 @@ def limit_page_range(cls, page=1, count=max_result_window, size=page_size):
         # limit the result count to max_result_window
         limited_count = min(count, max_result_window)
 
-        # Clamp page to range [1, max_page_number]
+        # Clamp page to range [1, max_page]
         try:
-            max_page_number = -(-limited_count // size)
-            limited_page_number = min(max(1, int(page)), max_page_number)
+            max_page = (limited_count + size - 1) // size
+            requested_page = max(1, int(page))
+            limited_page_number = min(requested_page, max_page)
         except ValueError:
             limited_page_number = 1
 
+        logger.debug(
+            "Clamping count to %s and requested page to %s",
+            limited_count,
+            limited_page_number,
+        )
         return limited_count, limited_page_number
 
     def get_paginated_response(self, data):

django/core/settings/defaults.py

@@ -10,6 +10,8 @@
 """
 
 import os
+import warnings
+from elasticsearch.exceptions import ElasticsearchWarning
 from enum import Enum
 from pathlib import Path
 
@@ -62,6 +64,10 @@ def is_test(self):
 # base directory is one level above the project directory
 BASE_DIR = os.path.dirname(PROJECT_DIR)
 
+# default to datacite sandbox and test mode
+DATACITE_PREFIX = "10.82853"
+DATACITE_TEST_MODE = True
+
 DEBUG = True
 
 DJANGO_VITE_DEV_MODE = True
@@ -212,6 +218,9 @@ def is_test(self):
 
 ROOT_URLCONF = "core.urls"
 
+# tune down elasticsearch complaints
+warnings.simplefilter("ignore", category=ElasticsearchWarning)
+
 # configure elasticsearch 7 wagtail backend
 WAGTAILSEARCH_BACKENDS = {
     "default": {
@@ -502,6 +511,10 @@ def is_test(self):
 TEST_USER_ID = os.getenv("TEST_USER_ID", 1000000)
 TEST_USERNAME = os.getenv("TEST_USERNAME", "__test_user__")
 
+DATACITE_API_USERNAME = os.getenv("DATACITE_API_USERNAME", "comses")
+DATACITE_DRY_RUN = os.getenv("DATACITE_DRY_RUN", "true")
+DATACITE_API_PASSWORD = read_secret("datacite_api_password")
+
 SOCIALACCOUNT_PROVIDERS = {
     # https://developer.github.com/apps/building-integrations/setting-up-and-registering-oauth-apps/about-scopes-for-oauth-apps/
     "github": {

django/core/settings/production.py

@@ -4,6 +4,10 @@
 # remove staging specific apps like fixture_magic
 INSTALLED_APPS.remove("fixture_magic")
 
+# datacite configuration
+DATACITE_PREFIX = "10.25937"
+DATACITE_TEST_MODE = False
+
 DEBUG = False
 DJANGO_VITE_DEV_MODE = False
 DEPLOY_ENVIRONMENT = Environment.PRODUCTION

django/core/settings/staging.py

@@ -7,6 +7,10 @@
 DJANGO_VITE_DEV_MODE = False
 DEPLOY_ENVIRONMENT = Environment.STAGING
 
+# datacite sandbox configuration inherited from defaults should suffice
+# DATACITE_PREFIX = "10.82853"
+# DATACITE_TEST_MODE = True
+
 # configure sentry
 sentry_sdk.init(
     dsn=SENTRY_DSN,

django/core/settings/test.py

@@ -1,6 +1,7 @@
+from os import path
+
 from .defaults import *
 
-from os import path
 
 DEPLOY_ENVIRONMENT = Environment.TEST
 

django/core/tests/base.py

@@ -4,10 +4,10 @@
 import shlex
 import shutil
 import subprocess
-from datetime import date, timedelta
 
+from datetime import date, timedelta
 from django.conf import settings
-from django.contrib.auth.models import User
+from django.contrib.auth import get_user_model
 from django.test import TestCase
 from django.utils import timezone
 
@@ -17,6 +17,8 @@
 
 logger = logging.getLogger(__name__)
 
+User = get_user_model()
+
 
 class ContentModelFactory(ABC):
     def __init__(self, submitter):
@@ -57,6 +59,9 @@ def create(self, **overrides):
         content.save()
         return content
 
+    def get_or_create(self, **kwargs):
+        return self.model.objects.get_or_create(**kwargs)
+
     def create_unsaved(self, **overrides):
         kwargs = self.get_default_data()
         kwargs.update(overrides)
@@ -95,65 +100,62 @@ def get_default_data(self):
         }
 
 
-def make_user(
-    username="test_user",
-    password="default.testing.password",
-    email="comses.test@mailinator.com",
+def create_test_user(
+    username="test_user", email="comses.test@mailinator.com", **kwargs
 ):
-    factory = UserFactory()
-    return factory.create(username=username, password=password, email=email), factory
+    factory = UserFactory(username=username, email=email, **kwargs)
+    return factory.create(), factory
 
 
 class UserFactory:
     def __init__(self, **defaults):
-        if not defaults.get("password"):
-            defaults["password"] = "test"
-        self.id = 0
-        self.password = defaults.get("password")
-        self.defaults = {}
-        username = defaults.get("username")
-        if username:
-            self.defaults.update({"username": username})
-        email = defaults.get("email")
-        if email:
-            self.defaults.update({"email": email})
+        self.next_user_id = 0
+        self.password = defaults.pop("password", "testing-password")
+        self.defaults = defaults.copy()
 
     def extract_password(self, overrides):
-        if overrides.get("password"):
+        if "password" in overrides:
             return overrides.pop("password")
         else:
             return self.password
 
-    def get_default_data(self):
+    def get_default_data(self, **kwargs):
         defaults = self.defaults.copy()
-        defaults["username"] = defaults.get("username", "submitter{}".format(self.id))
-        self.id += 1
+        # always generate a unique username for the next user
+        username = defaults["username"] = defaults.get(
+            "username", f"submitter{self.next_user_id}"
+        )
+        defaults.setdefault("email", f"{username}@example.com")
+        defaults.setdefault("username", username)
+        self.next_user_id += 1
+        defaults.update(kwargs)
         return defaults
 
-    def create(self, **overrides):
-        user = self.create_unsaved(**overrides)
+    def create(self, **kwargs):
+        return self.get_or_create(**kwargs)
+
+    def get_or_create(self, **kwargs):
+        password = self.extract_password(kwargs)
+        user_data_with_defaults = self.get_default_data(**kwargs)
+        """
+        if "email" not in kwargs:
+            kwargs.update(email=default_data.get('email'))
+        if "username" not in kwargs:
+            kwargs.update(username=default_data.get("username"))
+        """
+        user, created = User.objects.get_or_create(**user_data_with_defaults)
+        user.set_password(password)
         user.save()
         return user
 
-    def create_unsaved(self, **overrides):
-        password = self.extract_password(overrides)
-        kwargs = self.get_default_data()
-        kwargs.update(overrides)
-        if not kwargs.get("email"):
-            kwargs["email"] = "{}@gmail.com".format(kwargs["username"])
-        user = User(**kwargs)
-        if password:
-            user.set_password(password)
-        return user
-
 
 class BaseModelTestCase(TestCase):
     def setUp(self):
         self.user = self.create_user()
 
-    def create_user(self, username="test_user", password="test", **kwargs):
-        kwargs.setdefault("email", "testuser@mailinator.com")
-        return User.objects.create_user(username=username, password=password, **kwargs)
+    def create_user(self, **kwargs):
+        user, factory = create_test_user(**kwargs)
+        return user
 
 
 def initialize_test_shared_folders():