feat(harvester): add Memovs audiovisual archives API

Add new API harvester for Médiathèque Valais audiovisual archives
(archives.memovs.ch). This harvester enables automatic ingestion of
Film, Photo, and Audio metadata from the Memovs digital archives.

Implementation includes:
- ApiMemovs class with pagination and date filtering support
- JSON transformation layer mapping Memovs metadata to RERO-ILS
- Document type detection (Film, Audio, Photo, Other)
- Holdings creation with electronic locations
- Support for creators, contributors, subjects, and descriptions
- Integration with existing CLI and task infrastructure
- Fix duplicate logging in CLI by disabling logger propagation

Configuration added as VS-MEMO in apisources.yml with endpoint
https://archives.memovs.ch/docs/api/ and code 'memovs'.

Technical notes:
- Uses current_app.logger with lazy % formatting for performance
- Sets app.logger.propagate = False to prevent duplicate log messages
  in CLI commands

Co-authored-by: Peter Weber <[email protected]>

Author: rerowep

data/apisources.yml

@@ -26,3 +26,8 @@ NJ-CANTOOK:
     url: https://bm.ebibliomedia.ch
     classname: 'rero_ils.modules.api_harvester.cantook.api.ApiCantook'
     code: 'ebibliomedia'
+
+VS-MEMO:
+    url: https://archives.memovs.ch/docs/api/
+    classname: 'rero_ils.modules.api_harvester.memovs.api.ApiMemovs'
+    code: 'memovs'

data/organisations.json

@@ -19,7 +19,7 @@
     "default_currency": "GBP",
     "current_budget_pid": "2",
     "online_harvested_source": [
-      "mv-cantook"
+      "mv-cantook", "memovs"
     ],
     "collection_enabled_on_public_view": false
   },

rero_ils/config.py

@@ -525,6 +525,12 @@ def _(x):
         "kwargs": {"name": "NJ-CANTOOK"},
         "enabled": False,
     },
+    "celery.harvest-vs-memo": {
+        "task": "rero_ils.modules.api_harvester.tasks.harvest_records",
+        "schedule": schedules.crontab(minute=55, hour=5),  # Every day at 03:33 UTC,
+        "kwargs": {"name": "VS-MEMO"},
+        "enabled": False,
+    },
 }
 
 INDEXER_BULK_REQUEST_TIMEOUT = 60

rero_ils/modules/api_harvester/memovs/__init__.py

@@ -0,0 +1,18 @@
+# -*- coding: utf-8 -*-
+#
+# RERO ILS
+# Copyright (C) 2024 RERO
+#
+# This program 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, version 3 of the License.
+#
+# This program 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 Affero General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with this program. If not, see <http://www.gnu.org/licenses/>.
+
+"""Memovs API harvester module."""

rero_ils/modules/api_harvester/memovs/api.py

@@ -0,0 +1,189 @@
+# -*- coding: utf-8 -*-
+#
+# RERO ILS
+# Copyright (C) 2024 RERO
+#
+# This program 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, version 3 of the License.
+#
+# This program 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 Affero General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with this program. If not, see <http://www.gnu.org/licenses/>.
+
+"""API for Memovs audiovisual archives records."""
+
+from invenio_db import db
+from requests import codes as requests_codes
+
+from rero_ils.modules.documents.api import Document, DocumentsSearch
+from rero_ils.modules.holdings.api import Holding, HoldingsSearch, create_holding
+from rero_ils.modules.utils import JsonWriter, requests_retry_session
+
+from ..api import ApiHarvest
+from ..models import HarvestActionType
+from .dojson.json import memovs_json
+
+
+class ApiMemovs(ApiHarvest):
+    """ApiMemovs class.
+
+    Class for harvesting audiovisual archives from Memovs API.
+    """
+
+    def __init__(self, name, file_name=None, process=False, harvest_count=-1, verbose=False):
+        """Class init."""
+        super().__init__(
+            name=name,
+            process=process,
+            harvest_count=harvest_count,
+            verbose=verbose,
+        )
+        if file_name:
+            self.file = JsonWriter(file_name)
+        self._vendor = "MEMOVS"
+
+    def get_request_url(self, start_date="1990-01-01", page=1):
+        """Get request URL.
+
+        :param start_date: date from where records has to be harvested
+        :param page: page from where records have to be harvested
+        :returns: request url
+        """
+        params = f"from={start_date}&currentPage={page}"
+        return f"{self._url}?{params}"
+
+    def delete_holdings(self, document_pid):
+        """Delete holdings.
+
+        :param document_pid: document pid
+        """
+        for hold_pid in list(Holding.get_holdings_pid_by_document_pid(document_pid)):
+            if holding := Holding.get_record_by_pid(hold_pid):
+                for electronic_location in holding.get("electronic_location", []):
+                    if electronic_location.get("source") == self._code:
+                        holding.delete(dbcommit=True, delindex=True)
+                        break
+
+    def create_holdings(self, document_pid, link):
+        """Create holdings.
+
+        :param document_pid: document pid
+        :param link: link to memovs document
+        """
+        holdings = []
+        for info in self._info.values():
+            item_type_pid = info["item_type_pid"]
+            for location_pid, url in info["locations"].items():
+                if url:
+                    # Use organization-specific URL if available
+                    link_parts = link.split("/")[3:]
+                    link_parts.insert(0, url.rstrip("/"))
+                    link = "/".join(link_parts)
+                # Check if the holding already exists
+                query = (
+                    HoldingsSearch()
+                    .filter("term", document__pid=document_pid)
+                    .filter("term", location__pid=location_pid)
+                    .filter("term", holdings_type="electronic")
+                    .filter("term", electronic_location__source=self._code)
+                )
+                if query.count() == 0:
+                    holding = create_holding(
+                        document_pid=document_pid,
+                        location_pid=location_pid,
+                        item_type_pid=item_type_pid,
+                        electronic_location={"source": self._code, "uri": link},
+                        holdings_type="electronic",
+                    )
+                    holdings.append(holding)
+        db.session.commit()
+        for holding in holdings:
+            holding.reindex()
+
+    def create_update_record(self, data):
+        """Create, update or delete record.
+
+        :param data: data for record operation
+        :returns: harvested id and status
+        """
+        status = HarvestActionType.NOTSET
+        record = None
+        record_data = memovs_json.do(data)
+        if record_data.pop("deleted", None):
+            status = HarvestActionType.DELETED
+        link = record_data.pop("link", None)
+
+        # Get harvested ID
+        harvested_id = record_data.pop("pid")
+        # Check if document already exists
+        query = DocumentsSearch().filter("term", identifiedBy__value__raw=harvested_id).source(includes=["pid"])
+        try:
+            pid = next(query.scan()).pid
+        except StopIteration:
+            pid = None
+
+        if pid:
+            if doc := Document.get_record_by_pid(pid):
+                if status == HarvestActionType.DELETED:
+                    self._count_del += 1
+                    self.delete_holdings(document_pid=doc.pid)
+                    # Try to delete document
+                    doc.pop("harvested", None)
+                    if not doc.reasons_not_to_delete():
+                        doc.delete(dbcommit=True, delindex=True)
+                else:
+                    self._count_upd += 1
+                    status = HarvestActionType.UPDATED
+                    record_data["pid"] = doc.pid
+                    record = doc.replace(data=record_data, dbcommit=True, reindex=True)
+                    if link:
+                        self.create_holdings(document_pid=record.pid, link=link)
+        elif status == HarvestActionType.NOTSET:
+            self._count_new += 1
+            status = HarvestActionType.CREATED
+            record = Document.create(data=record_data, dbcommit=True, reindex=True)
+            if link:
+                self.create_holdings(document_pid=record.pid, link=link)
+        return harvested_id, status
+
+    def harvest_records(self, from_date):
+        """Harvest Memovs records.
+
+        :param from_date: record changed after this date to get
+        :returns: count and total items
+        """
+        self._count = 0
+        url = self.get_request_url(start_date=from_date, page=1)
+        request = requests_retry_session().get(url)
+
+        if request.status_code != requests_codes.ok:
+            self.verbose_print(f"Error fetching data: {request.status_code}")
+            return self._count, 0
+
+        response_data = request.json()
+        total_pages = response_data.get("totalPages", 0)
+        total_items = response_data.get("totalDocuments", 0)
+        current_page = response_data.get("currentPage", 1)
+
+        while (
+            request.status_code == requests_codes.ok
+            and current_page <= total_pages
+            and (self.harvest_count < 0 or self._count < self.harvest_count)
+        ):
+            self.verbose_print(f"API page: {current_page}/{total_pages} url: {url}")
+            self.process_records(response_data.get("documents", []))
+
+            # Get next page
+            current_page += 1
+            if current_page <= total_pages:
+                url = self.get_request_url(start_date=from_date, page=current_page)
+                request = requests_retry_session().get(url)
+                if request.status_code == requests_codes.ok:
+                    response_data = request.json()
+
+        return self._count, total_items

rero_ils/modules/api_harvester/memovs/dojson/__init__.py

@@ -0,0 +1,18 @@
+# -*- coding: utf-8 -*-
+#
+# RERO ILS
+# Copyright (C) 2024 RERO
+#
+# This program 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, version 3 of the License.
+#
+# This program 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 Affero General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with this program. If not, see <http://www.gnu.org/licenses/>.
+
+"""Memovs dojson module."""

rero_ils/modules/api_harvester/memovs/dojson/json/__init__.py

@@ -0,0 +1,22 @@
+# -*- coding: utf-8 -*-
+#
+# RERO ILS
+# Copyright (C) 2024 RERO
+#
+# This program 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, version 3 of the License.
+#
+# This program 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 Affero General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with this program. If not, see <http://www.gnu.org/licenses/>.
+
+"""Memovs json transformation."""
+
+from .model import Transformation
+
+memovs_json = Transformation()