New table for wrokflow_tag and topic join

agr_literature_service/api/models/__init__.py

@@ -23,6 +23,7 @@
 from agr_literature_service.api.models.user_model import UserModel
 from agr_literature_service.api.models.obsolete_model import ObsoleteReferenceModel
 from agr_literature_service.api.models.workflow_tag_model import WorkflowTagModel
+from agr_literature_service.api.models.workflow_tag_topic_model import WorkflowTagTopicModel
 from agr_literature_service.api.models.workflow_transition_model import WorkflowTransitionModel
 from agr_literature_service.api.models.topic_entity_tag_model import TopicEntityTagModel, TopicEntityTagSourceModel
 from agr_literature_service.api.models.reference_mod_md5sum_model import ReferenceModMd5sumModel

agr_literature_service/api/models/workflow_tag_topic_model.py

@@ -0,0 +1,29 @@
+from typing import Dict
+from agr_literature_service.api.database.base import Base
+from agr_literature_service.api.database.versioning import enable_versioning
+from agr_literature_service.api.models.audited_model import AuditedModel
+from sqlalchemy import (Column, ForeignKey, Integer, String)
+from sqlalchemy.orm import relationship
+
+class WorkflowTagTopicModel(AuditedModel, Base):
+    __tablename__ = "workflow_tag_topic"
+
+    workflow_tag_topic_id = Column(
+        Integer,
+        primary_key=True,
+        autoincrement=True
+    )
+
+    workflow_tag = Column(
+        String(),
+        index=True,
+        unique=True,
+        nullable=False
+    )
+
+    # Obtained from A-Team ontology node term-id
+    topic = Column(
+        String(),
+        unique=False,
+        nullable=False
+    )

agr_literature_service/lit_processing/oneoff_scripts/make_subset_db/make_subset.py

@@ -316,31 +316,31 @@ def add_sequence_data(db_subset_session):
         if max_val:
             print(f"setting max value to {max_val + 1} for {x[2]}")
             com = f"ALTER SEQUENCE {x[2]} RESTART WITH {max_val+1}"
-            db_subset_session.execute(com)
+            db_subset_session.execute(text(com))
         else:
             print(f"setting max value to 0 for {x[2]} as none found")
             com = f"ALTER SEQUENCE {x[2]} RESTART WITH 1"
-            db_subset_session.execute(com)
+            db_subset_session.execute(text(com))
 
 
 def add_alembic(db_orig_session, db_subset_session):
     # Add alembic_version
-    alembic_rows = db_orig_session.execute("SELECT version_num from alembic_version")
+    alembic_rows = db_orig_session.execute(text("SELECT version_num from alembic_version"))
     version = ''
     for alembic_row in alembic_rows:
         version = alembic_row[0]
     if not version:
         print("ERROR: Could not find version_num for alembic_version table")
     else:
-        db_subset_session.execute(f"INSERT into alembic_version (version_num) VALUES ('{version}');")
+        db_subset_session.execute(text(f"INSERT into alembic_version (version_num) VALUES ('{version}');"))
     db_subset_session.commit()
     db_subset_session.close()
 
 
 def trigger_settings(db_session, state="DISABLE"):
     global trigger_list
     for table in trigger_list:
-        db_session.execute(f'ALTER TABLE {table} {state} TRIGGER all;')
+        db_session.execute(text(f'ALTER TABLE {table} {state} TRIGGER all;'))
     db_session.commit()
 
 
@@ -423,7 +423,7 @@ def start():
     okay = True
     tables = ['reference', 'citation']  # add other tables?
     for table_name in tables:
-        count_rows = db_subset_session.execute(f"SELECT count(1) from {table_name}")
+        count_rows = db_subset_session.execute(text(f"SELECT count(1) from {table_name}"))
         count = 0
         for count_row in count_rows:
             count = count_row[0]
@@ -442,7 +442,7 @@ def start():
     add_sequence_data(db_subset_session)
 
     # for what ever reason need this:
-    db_subset_session.execute("REFRESH MATERIALIZED VIEW _view")
+    db_subset_session.execute(text("REFRESH MATERIALIZED VIEW _view"))
     db_subset_session.commit()
     if subset_dump:
         dump_subset()

alembic/versions/20250307_bf8c336530f9_workflow_tag_topic_addition.py

@@ -0,0 +1,45 @@
+"""workflow_tag_topic addition
+
+Revision ID: bf8c336530f9
+Revises: a286f0a59a44
+Create Date: 2025-03-07 17:00:28.761932
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = 'bf8c336530f9'
+down_revision = 'a286f0a59a44'
+branch_labels = None
+depends_on = None
+
+
+def upgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.create_table('workflow_tag_topic',
+    sa.Column('workflow_tag_topic_id', sa.Integer(), autoincrement=True, nullable=False),
+    sa.Column('workflow_tag', sa.String(), nullable=False),
+    sa.Column('topic', sa.String(), nullable=False),
+    sa.Column('date_created', sa.DateTime(), nullable=False),
+    sa.Column('date_updated', sa.DateTime(), nullable=True),
+    sa.Column('created_by', sa.String(), nullable=True),
+    sa.Column('updated_by', sa.String(), nullable=True),
+    sa.ForeignKeyConstraint(['created_by'], ['users.id'], ),
+    sa.ForeignKeyConstraint(['updated_by'], ['users.id'], ),
+    sa.PrimaryKeyConstraint('workflow_tag_topic_id')
+    )
+    op.create_index(op.f('ix_workflow_tag_topic_date_created'), 'workflow_tag_topic', ['date_created'], unique=False)
+    op.create_index(op.f('ix_workflow_tag_topic_date_updated'), 'workflow_tag_topic', ['date_updated'], unique=False)
+    op.create_index(op.f('ix_workflow_tag_topic_workflow_tag'), 'workflow_tag_topic', ['workflow_tag'], unique=True)
+    # ### end Alembic commands ###
+
+
+def downgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_index(op.f('ix_workflow_tag_topic_workflow_tag'), table_name='workflow_tag_topic')
+    op.drop_index(op.f('ix_workflow_tag_topic_date_updated'), table_name='workflow_tag_topic')
+    op.drop_index(op.f('ix_workflow_tag_topic_date_created'), table_name='workflow_tag_topic')
+    op.drop_table('workflow_tag_topic')
+    # ### end Alembic commands ###