nucliadb 6.2.1.post3087__py3-none-any.whl → 6.2.1.post3109__py3-none-any.whl

migrations/0030_label_deduplication.py

@@ -0,0 +1,60 @@
+# Copyright (C) 2021 Bosutech XXI S.L.
+#
+# nucliadb is offered under the AGPL v3.0 and as commercial software.
+# For commercial licensing, contact us at info@nuclia.com.
+#
+# AGPL:
+# 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, either version 3 of the
+# License, or (at your option) any later version.
+#
+# 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/>.
+#
+
+"""Migration #30
+
+We want to support labels with the same title anymore. Run a deduplication for
+all labelsets
+
+"""
+
+import logging
+
+from nucliadb.common import datamanagers
+from nucliadb.migrator.context import ExecutionContext
+
+logger = logging.getLogger(__name__)
+
+
+async def migrate(context: ExecutionContext) -> None: ...
+
+
+async def migrate_kb(context: ExecutionContext, kbid: str) -> None:
+    async with datamanagers.with_rw_transaction() as txn:
+        kb_labels = await datamanagers.labels.get_labels(txn, kbid=kbid)
+        changed = False
+
+        for labelset in kb_labels.labelset.values():
+            current_labels = labelset.labels
+            labelset.ClearField("labels")
+            deduplicator = set()
+
+            for label in current_labels:
+                label_id = label.title.lower()
+                if label_id not in deduplicator:
+                    deduplicator.add(label_id)
+                    labelset.labels.append(label)
+
+            changed = changed or (len(labelset.labels) < len(current_labels))
+
+        if changed:
+            await datamanagers.labels.set_labels(txn, kbid=kbid, labels=kb_labels)
+
+        await txn.commit()

{nucliadb-6.2.1.post3087.dist-info → nucliadb-6.2.1.post3109.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: nucliadb
-Version: 6.2.1.post3087
+Version: 6.2.1.post3109
 Home-page: https://docs.nuclia.dev/docs/management/nucliadb/intro
 Author: NucliaDB Community
 Author-email: nucliadb@nuclia.com
@@ -22,10 +22,10 @@ Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3 :: Only
 Requires-Python: >=3.9, <4
 Description-Content-Type: text/markdown
-Requires-Dist: nucliadb-telemetry[all]>=6.2.1.post3087
-Requires-Dist: nucliadb-utils[cache,fastapi,storages]>=6.2.1.post3087
-Requires-Dist: nucliadb-protos>=6.2.1.post3087
-Requires-Dist: nucliadb-models>=6.2.1.post3087
+Requires-Dist: nucliadb-telemetry[all]>=6.2.1.post3109
+Requires-Dist: nucliadb-utils[cache,fastapi,storages]>=6.2.1.post3109
+Requires-Dist: nucliadb-protos>=6.2.1.post3109
+Requires-Dist: nucliadb-models>=6.2.1.post3109
 Requires-Dist: nucliadb-admin-assets>=1.0.0.post1224
 Requires-Dist: nuclia-models>=0.24.2
 Requires-Dist: uvicorn

{nucliadb-6.2.1.post3087.dist-info → nucliadb-6.2.1.post3109.dist-info}/RECORD

@@ -25,6 +25,7 @@ migrations/0026_fix_high_cardinality_content_types.py,sha256=BsbBkvZDzjRHQfoouZN
 migrations/0027_rollover_texts3.py,sha256=UQDaMOayVuqDisf82NDrPStoEVveHvdjkSmzbIcU9o4,2730
 migrations/0028_extracted_vectors_reference.py,sha256=49DHCIlBpjofU8cYVHTdWv0EBIlnPTWV2WCezf0rJUo,2392
 migrations/0029_backfill_field_status.py,sha256=QWF69n1da9lpRnbEpgbqPjSQ-Wfn6rMC7Enz6bBYGt4,5663
+migrations/0030_label_deduplication.py,sha256=y14TxtCMi3-TBMz_eZoyyPDHNlZb29taJujlDuHumsA,2008
 migrations/__init__.py,sha256=cp15ZcFnHvpcu_5-aK2A4uUyvuZVV_MJn4bIXMa20ks,835
 migrations/pg/0001_bootstrap.py,sha256=Fsqkeof50m7fKiJN05kmNEMwiKDlOrAgcAS5sLLkutA,1256
 migrations/pg/0002_catalog.py,sha256=Rsleecu351Ty19kYZgOpqX5G3MEAY8nMxCJrAeuS2Mw,1690
@@ -329,9 +330,9 @@ nucliadb/writer/tus/local.py,sha256=7jYa_w9b-N90jWgN2sQKkNcomqn6JMVBOVeDOVYJHto,
 nucliadb/writer/tus/s3.py,sha256=vF0NkFTXiXhXq3bCVXXVV-ED38ECVoUeeYViP8uMqcU,8357
 nucliadb/writer/tus/storage.py,sha256=ToqwjoYnjI4oIcwzkhha_MPxi-k4Jk3Lt55zRwaC1SM,2903
 nucliadb/writer/tus/utils.py,sha256=MSdVbRsRSZVdkaum69_0wku7X3p5wlZf4nr6E0GMKbw,2556
-nucliadb-6.2.1.post3087.dist-info/METADATA,sha256=ATRQKTKtuCTKpwOtBrUBXJ-c5bmuSKKDlLl3jtV5f5o,4603
-nucliadb-6.2.1.post3087.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-nucliadb-6.2.1.post3087.dist-info/entry_points.txt,sha256=XqGfgFDuY3zXQc8ewXM2TRVjTModIq851zOsgrmaXx4,1268
-nucliadb-6.2.1.post3087.dist-info/top_level.txt,sha256=hwYhTVnX7jkQ9gJCkVrbqEG1M4lT2F_iPQND1fCzF80,20
-nucliadb-6.2.1.post3087.dist-info/zip-safe,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
-nucliadb-6.2.1.post3087.dist-info/RECORD,,
+nucliadb-6.2.1.post3109.dist-info/METADATA,sha256=sg4gBArQO8k3c5LBxpQELtuJVSsTFCrmxv1UbeqohIw,4603
+nucliadb-6.2.1.post3109.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
+nucliadb-6.2.1.post3109.dist-info/entry_points.txt,sha256=XqGfgFDuY3zXQc8ewXM2TRVjTModIq851zOsgrmaXx4,1268
+nucliadb-6.2.1.post3109.dist-info/top_level.txt,sha256=hwYhTVnX7jkQ9gJCkVrbqEG1M4lT2F_iPQND1fCzF80,20
+nucliadb-6.2.1.post3109.dist-info/zip-safe,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
+nucliadb-6.2.1.post3109.dist-info/RECORD,,