Semantic search

2026-06-16 12:45:42 +02:00 · 2026-03-25 18:39:50 +01:00
parent f5fb537fed
commit cbeedc2d2f
14 changed files with 1336 additions and 56 deletions
@@ -0,0 +1,76 @@
+"""add full text search vector to messages and extracted_text to attachments
+
+Revision ID: 0008
+Revises: 0007
+Create Date: 2026-03-25
+"""
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.dialects import postgresql
+
+revision = '0008'
+down_revision = '0007'
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    # 1. Aggiunge colonna search_vector a messages
+    op.add_column(
+        'messages',
+        sa.Column('search_vector', postgresql.TSVECTOR(), nullable=True),
+    )
+
+    # 2. Aggiunge colonna extracted_text ad attachments (testo estratto da PDF/DOCX)
+    op.add_column(
+        'attachments',
+        sa.Column('extracted_text', sa.Text(), nullable=True),
+    )
+
+    # 3. Indice GIN per ricerca full-text veloce
+    op.execute(
+        "CREATE INDEX idx_messages_fts ON messages USING gin(search_vector) "
+        "WHERE search_vector IS NOT NULL"
+    )
+
+    # 4. Funzione trigger che aggiorna search_vector quando cambiano i campi testuali
+    op.execute("""
+        CREATE OR REPLACE FUNCTION messages_search_vector_update() RETURNS trigger AS $$
+        BEGIN
+            NEW.search_vector :=
+                setweight(to_tsvector('italian', coalesce(NEW.subject, '')), 'A') ||
+                setweight(to_tsvector('simple',  coalesce(NEW.from_address, '')), 'B') ||
+                setweight(to_tsvector('simple',
+                    coalesce(array_to_string(NEW.to_addresses, ' '), '')), 'B') ||
+                setweight(to_tsvector('italian', coalesce(NEW.body_text, '')), 'C');
+            RETURN NEW;
+        END;
+        $$ LANGUAGE plpgsql;
+    """)
+
+    # 5. Crea trigger (si attiva su INSERT e UPDATE dei campi rilevanti)
+    op.execute("""
+        CREATE TRIGGER trg_messages_search_vector
+        BEFORE INSERT OR UPDATE OF subject, from_address, to_addresses, body_text
+        ON messages
+        FOR EACH ROW EXECUTE FUNCTION messages_search_vector_update();
+    """)
+
+    # 6. Backfill: popola search_vector per i messaggi esistenti
+    op.execute("""
+        UPDATE messages SET search_vector =
+            setweight(to_tsvector('italian', coalesce(subject, '')), 'A') ||
+            setweight(to_tsvector('simple',  coalesce(from_address, '')), 'B') ||
+            setweight(to_tsvector('simple',
+                coalesce(array_to_string(to_addresses, ' '), '')), 'B') ||
+            setweight(to_tsvector('italian', coalesce(body_text, '')), 'C')
+        WHERE search_vector IS NULL
+    """)
+
+
+def downgrade() -> None:
+    op.execute("DROP TRIGGER IF EXISTS trg_messages_search_vector ON messages")
+    op.execute("DROP FUNCTION IF EXISTS messages_search_vector_update()")
+    op.execute("DROP INDEX IF EXISTS idx_messages_fts")
+    op.drop_column('attachments', 'extracted_text')
+    op.drop_column('messages', 'search_vector')