|
| 1 | +# -*- coding: utf-8 -*- |
| 2 | +# |
| 3 | +# RERO ILS |
| 4 | +# Copyright (C) 2024 RERO |
| 5 | +# |
| 6 | +# This program is free software: you can redistribute it and/or modify |
| 7 | +# it under the terms of the GNU Affero General Public License as published by |
| 8 | +# the Free Software Foundation, version 3 of the License. |
| 9 | +# |
| 10 | +# This program is distributed in the hope that it will be useful, |
| 11 | +# but WITHOUT ANY WARRANTY; without even the implied warranty of |
| 12 | +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
| 13 | +# GNU Affero General Public License for more details. |
| 14 | +# |
| 15 | +# You should have received a copy of the GNU Affero General Public License |
| 16 | +# along with this program. If not, see <http://www.gnu.org/licenses/>. |
| 17 | + |
| 18 | +"""API for Memovs audiovisual archives records.""" |
| 19 | + |
| 20 | +from invenio_db import db |
| 21 | +from requests import codes as requests_codes |
| 22 | + |
| 23 | +from rero_ils.modules.documents.api import Document, DocumentsSearch |
| 24 | +from rero_ils.modules.holdings.api import Holding, HoldingsSearch, create_holding |
| 25 | +from rero_ils.modules.utils import JsonWriter, requests_retry_session |
| 26 | + |
| 27 | +from ..api import ApiHarvest |
| 28 | +from ..models import HarvestActionType |
| 29 | +from .dojson.json import memovs_json |
| 30 | + |
| 31 | + |
| 32 | +class ApiMemovs(ApiHarvest): |
| 33 | + """ApiMemovs class. |
| 34 | +
|
| 35 | + Class for harvesting audiovisual archives from Memovs API. |
| 36 | + """ |
| 37 | + |
| 38 | + def __init__(self, name, file_name=None, process=False, harvest_count=-1, verbose=False): |
| 39 | + """Class init.""" |
| 40 | + super().__init__( |
| 41 | + name=name, |
| 42 | + process=process, |
| 43 | + harvest_count=harvest_count, |
| 44 | + verbose=verbose, |
| 45 | + ) |
| 46 | + if file_name: |
| 47 | + self.file = JsonWriter(file_name) |
| 48 | + self._vendor = "MEMOVS" |
| 49 | + |
| 50 | + def get_request_url(self, start_date="1990-01-01", page=1): |
| 51 | + """Get request URL. |
| 52 | +
|
| 53 | + :param start_date: date from where records has to be harvested |
| 54 | + :param page: page from where records have to be harvested |
| 55 | + :returns: request url |
| 56 | + """ |
| 57 | + params = f"from={start_date}¤tPage={page}" |
| 58 | + return f"{self._url}?{params}" |
| 59 | + |
| 60 | + def delete_holdings(self, document_pid): |
| 61 | + """Delete holdings. |
| 62 | +
|
| 63 | + :param document_pid: document pid |
| 64 | + """ |
| 65 | + for hold_pid in list(Holding.get_holdings_pid_by_document_pid(document_pid)): |
| 66 | + if holding := Holding.get_record_by_pid(hold_pid): |
| 67 | + for electronic_location in holding.get("electronic_location", []): |
| 68 | + if electronic_location.get("source") == self._code: |
| 69 | + holding.delete(dbcommit=True, delindex=True) |
| 70 | + break |
| 71 | + |
| 72 | + def create_holdings(self, document_pid, link): |
| 73 | + """Create holdings. |
| 74 | +
|
| 75 | + :param document_pid: document pid |
| 76 | + :param link: link to memovs document |
| 77 | + """ |
| 78 | + holdings = [] |
| 79 | + for info in self._info.values(): |
| 80 | + item_type_pid = info["item_type_pid"] |
| 81 | + for location_pid, url in info["locations"].items(): |
| 82 | + if url: |
| 83 | + # Use organization-specific URL if available |
| 84 | + link_parts = link.split("/")[3:] |
| 85 | + link_parts.insert(0, url.rstrip("/")) |
| 86 | + link = "/".join(link_parts) |
| 87 | + # Check if the holding already exists |
| 88 | + query = ( |
| 89 | + HoldingsSearch() |
| 90 | + .filter("term", document__pid=document_pid) |
| 91 | + .filter("term", location__pid=location_pid) |
| 92 | + .filter("term", holdings_type="electronic") |
| 93 | + .filter("term", electronic_location__source=self._code) |
| 94 | + ) |
| 95 | + if query.count() == 0: |
| 96 | + holding = create_holding( |
| 97 | + document_pid=document_pid, |
| 98 | + location_pid=location_pid, |
| 99 | + item_type_pid=item_type_pid, |
| 100 | + electronic_location={"source": self._code, "uri": link}, |
| 101 | + holdings_type="electronic", |
| 102 | + ) |
| 103 | + holdings.append(holding) |
| 104 | + db.session.commit() |
| 105 | + for holding in holdings: |
| 106 | + holding.reindex() |
| 107 | + |
| 108 | + def create_update_record(self, data): |
| 109 | + """Create, update or delete record. |
| 110 | +
|
| 111 | + :param data: data for record operation |
| 112 | + :returns: harvested id and status |
| 113 | + """ |
| 114 | + status = HarvestActionType.NOTSET |
| 115 | + record = None |
| 116 | + record_data = memovs_json.do(data) |
| 117 | + if record_data.pop("deleted", None): |
| 118 | + status = HarvestActionType.DELETED |
| 119 | + link = record_data.pop("link", None) |
| 120 | + |
| 121 | + # Get harvested ID |
| 122 | + harvested_id = record_data.pop("pid") |
| 123 | + # Check if document already exists |
| 124 | + query = DocumentsSearch().filter("term", identifiedBy__value__raw=harvested_id).source(includes=["pid"]) |
| 125 | + try: |
| 126 | + pid = next(query.scan()).pid |
| 127 | + except StopIteration: |
| 128 | + pid = None |
| 129 | + |
| 130 | + if pid: |
| 131 | + if doc := Document.get_record_by_pid(pid): |
| 132 | + if status == HarvestActionType.DELETED: |
| 133 | + self._count_del += 1 |
| 134 | + self.delete_holdings(document_pid=doc.pid) |
| 135 | + # Try to delete document |
| 136 | + doc.pop("harvested", None) |
| 137 | + if not doc.reasons_not_to_delete(): |
| 138 | + doc.delete(dbcommit=True, delindex=True) |
| 139 | + else: |
| 140 | + self._count_upd += 1 |
| 141 | + status = HarvestActionType.UPDATED |
| 142 | + record_data["pid"] = doc.pid |
| 143 | + record = doc.replace(data=record_data, dbcommit=True, reindex=True) |
| 144 | + if link: |
| 145 | + self.create_holdings(document_pid=record.pid, link=link) |
| 146 | + elif status == HarvestActionType.NOTSET: |
| 147 | + self._count_new += 1 |
| 148 | + status = HarvestActionType.CREATED |
| 149 | + record = Document.create(data=record_data, dbcommit=True, reindex=True) |
| 150 | + if link: |
| 151 | + self.create_holdings(document_pid=record.pid, link=link) |
| 152 | + return harvested_id, status |
| 153 | + |
| 154 | + def harvest_records(self, from_date): |
| 155 | + """Harvest Memovs records. |
| 156 | +
|
| 157 | + :param from_date: record changed after this date to get |
| 158 | + :returns: count and total items |
| 159 | + """ |
| 160 | + self._count = 0 |
| 161 | + url = self.get_request_url(start_date=from_date, page=1) |
| 162 | + request = requests_retry_session().get(url) |
| 163 | + |
| 164 | + if request.status_code != requests_codes.ok: |
| 165 | + self.verbose_print(f"Error fetching data: {request.status_code}") |
| 166 | + return self._count, 0 |
| 167 | + |
| 168 | + response_data = request.json() |
| 169 | + total_pages = response_data.get("totalPages", 0) |
| 170 | + total_items = response_data.get("totalDocuments", 0) |
| 171 | + current_page = response_data.get("currentPage", 1) |
| 172 | + |
| 173 | + while ( |
| 174 | + request.status_code == requests_codes.ok |
| 175 | + and current_page <= total_pages |
| 176 | + and (self.harvest_count < 0 or self._count < self.harvest_count) |
| 177 | + ): |
| 178 | + self.verbose_print(f"API page: {current_page}/{total_pages} url: {url}") |
| 179 | + self.process_records(response_data.get("documents", [])) |
| 180 | + |
| 181 | + # Get next page |
| 182 | + current_page += 1 |
| 183 | + if current_page <= total_pages: |
| 184 | + url = self.get_request_url(start_date=from_date, page=current_page) |
| 185 | + request = requests_retry_session().get(url) |
| 186 | + if request.status_code == requests_codes.ok: |
| 187 | + response_data = request.json() |
| 188 | + |
| 189 | + return self._count, total_items |
0 commit comments