ark: get rid of archetype

* Adds a Ark NAAN configuration into organisation.
* Disallows Ark NAAN configuration modification for non super user.
* Mints an ark identifier if the document organisation contains a NAAN.
* Removes legacy code.
* Closes #652.
* Adds the cli to create an ARK in existing documents.
* Removes unused file.
* Adds document Dublin Core export format.
* Moves ark in identifiedBy.
* Uses dumpers to enrich indexed documents.
* Adds dublin core as export format.
* Closes #669.
* Adds the full URI version of the ARK on the search result API.
* Sets the application configurations for the test to allow the use of
  multiple docker-compose files.
* Uses angular 14.
* Solves safety, need to move to Flask 2.
* Fixes json-ld context value.
* Adds multiple identifiers for dublin core.
* Uses ARK URI for `@id` and `identifier` field in json-ld.
* Fixes some tests.
* Makes all fields searchable for documents index.

Co-Authored-by: Johnny Mariéthoz <Johnny.Mariethoz@rero.ch>

data/organisations/data.json

@@ -3,6 +3,7 @@
       "code": "rero",
       "name": "RERO",
       "isShared": true,
+      "arkNAAN": "99999",
       "files": [
         {
           "key": "rero.jpg",

pyproject.toml

@@ -121,6 +121,7 @@ theme = "sonar.theme.views:blueprint"
 validation = "sonar.modules.validation.views:blueprint"
 users = "sonar.modules.users.views:blueprint"
 sitemap = "sonar.modules.sitemap.views:blueprint"
+ark = "sonar.modules.ark.views:blueprint"
 
 [tool.poetry.plugins."invenio_base.api_blueprints"]
 deposits = "sonar.modules.deposits.rest:api_blueprint"

scripts/setup

@@ -62,7 +62,7 @@ if $import; then
     message "Size of import sets is set to \"$size\"" "info"
 fi
 
-# Try to create database and tables if does not exists
+# Try to create database and tables if does not exist
 invenio db init create || true
 
 # Purge celery

scripts/test

@@ -50,7 +50,7 @@ fi
 # | celery                     | 5.1.2     | <5.2.0                   | 42498    |
 # | celery                     | 5.1.2     | <5.2.2                   | 43738    |
 # +==============================================================================+
-safety check -i 45183 -i 44501 -i 51668 -i 42194 -i 42852 -i 53325 -i 53326 -i 54456 -i 42498 -i 43738 -i 47833 -i 51457 -i 51358 -i 53812 -i 52495 -i 50792
+safety check -i 45183 -i 44501 -i 51668 -i 42194 -i 42852 -i 53325 -i 53326 -i 54456 -i 42498 -i 43738 -i 47833 -i 51457 -i 51358 -i 53812 -i 52495 -i 50792 -i 55261
 pydocstyle sonar tests docs
 isort --check-only --diff "${SCRIPT_PATH}/.."
 autoflake -c -r --remove-all-unused-imports --ignore-init-module-imports . &> /dev/null || {

sonar/config.py

@@ -366,6 +366,7 @@ def _(x):
     },
 }
 """Records UI for sonar."""
+REST_MIMETYPE_QUERY_ARG_NAME = 'format'
 
 RECORDS_REST_ENDPOINTS = {
     'doc':
@@ -382,10 +383,22 @@ def _(x):
         record_serializers={
             'application/json': ('sonar.modules.documents.serializers'
                                  ':json_v1_response'),
+            'text/xml': ('sonar.modules.documents.serializers'
+                                 ':dc_v1_response'),
+        },
+        record_serializers_aliases={
+            'json': 'application/json',
+            'dc': 'text/xml',
         },
         search_serializers={
             'application/json': ('sonar.modules.documents.serializers'
                                  ':json_v1_search'),
+            'text/xml': ('sonar.modules.documents.serializers'
+                                 ':dc_v1_search'),
+        },
+        search_serializers_aliases={
+            'json': 'application/json',
+            'dc': 'text/xml',
         },
         record_loaders={
             'application/json': ('sonar.modules.documents.loaders'
@@ -874,7 +887,7 @@ def _(x):
     'oai_dc': {
         'namespace': 'http://www.openarchives.org/OAI/2.0/oai_dc/',
         'schema': 'http://www.openarchives.org/OAI/2.0/oai_dc.xsd',
-        'serializer': 'sonar.modules.documents.serializers.dc.sonar_dublin_core',
+        'serializer': 'sonar.modules.documents.serializers.oai_dc.sonar_dublin_core',
     }
 }
 #: Number of records to return per page in OAI-PMH results.

sonar/config_sonar.py

@@ -565,19 +565,11 @@
 # ARK
 # ===
 
-# SONAR_APP_ARK_USER = 'test'
-"""Username for the NMA server."""
-# SONAR_APP_ARK_PASSWORD = 'test'
-"""Password for the NMA server."""
-# SONAR_APP_ARK_RESOLVER = 'https://n2t.net'
+SONAR_APP_ARK_RESOLVER = 'https://localhost:5000'
 """ARK resolver URL."""
-# SONAR_APP_ARK_NMA = 'https://www.arketype.ch'
-"""ARK Name Mapping Authority: a service provider server."""
-# SONAR_APP_ARK_NAAN = '99999'
-"""ARK prefix corresponding to an organisation."""
-# SONAR_APP_ARK_SCHEME = 'ark:'
+SONAR_APP_ARK_SCHEME = 'ark:'
 """ARK scheme."""
-# SONAR_APP_ARK_SHOULDER = 'ffk3'
+SONAR_APP_ARK_SHOULDER = 'ffk3'
 """ARK Shoulder, can be multiple for a given organisation."""
 
 SONAR_APP_SWISSCOVERY_SEARCH_URL = 'https://swisscovery.slsp.ch/view/sru/41SLSP_NETWORK'

sonar/ext.py

@@ -125,6 +125,14 @@ def init_config(self, app):
                 'SONAR_APP_SITEMAP_FOLDER_PATH',
                 os.path.join(app.instance_path, 'sitemap'))
 
+        # add keep alive support for angular application
+        # NOTE: this will not work for werkzeug> 2.1.2
+        # https://werkzeug.palletsprojects.com/en/2.2.x/changes/#version-2-1-2
+        if app.config.get('DEBUG'): # pragma: no cover
+            # debug code do not need to be cover by the tests
+            from werkzeug.serving import WSGIRequestHandler
+            WSGIRequestHandler.protocol_version = "HTTP/1.1"
+
     def init_views(self, app):
         """Initialize the main flask views."""
         app.url_map.converters['org_code'] = OrganisationCodeConverter

sonar/json_schemas/organisations_json_schema.py

@@ -35,7 +35,7 @@ def process(self):
         # Remove modes fields if user does not have superuser role.
         if not current_user_record.is_superuser:
             propertiesOrder = schema.get('propertiesOrder', []);
-            for field in ['isDedicated', 'isShared']:
+            for field in ['isDedicated', 'isShared', 'arkNAAN']:
                 if field in propertiesOrder:
                     schema['propertiesOrder'].remove(field)
 

sonar/modules/api.py

@@ -19,6 +19,7 @@
 
 import os.path
 import re
+from copy import deepcopy
 from io import BytesIO
 from uuid import uuid4
 
@@ -219,6 +220,15 @@ def get_record_by_bucket(bucket):
         except Exception:
             return None
 
+    def resolve(self):
+        """Resolve references data.
+
+        Mainly used by the `resolve=1` URL parameter.
+
+        :returns: a fresh copy of the resolved data.
+        """
+        return deepcopy(self.replace_refs())
+
     def reindex(self):
         """Reindex record."""
         indexer = self.get_indexer_class()
@@ -344,7 +354,7 @@ def has_subdivision(self, subdivision_pid):
         if not self.subdivisions:
             return False
 
-        for subdivision in self.subdivisions:            
+        for subdivision in self.subdivisions:
             if subdivision_pid == subdivision['pid']:
                 return True