fix: waveform can generate NaN in json database (#481)

* refactor: fixes transcript duration type, NaN in waveform, and prepare for postgres migration

* fix: ensure we don't have NaN in waveform

* fix: missing assertionerror

Co-authored-by: pr-agent-monadical[bot] <198624643+pr-agent-monadical[bot]@users.noreply.github.com>

* fix: potential empty array

---------

Co-authored-by: pr-agent-monadical[bot] <198624643+pr-agent-monadical[bot]@users.noreply.github.com>

server/migrations/env.py

@@ -24,6 +24,10 @@ target_metadata = metadata
 # ... etc.
 
 
+# don't use asyncpg for the moment
+settings.DATABASE_URL = settings.DATABASE_URL.replace("+asyncpg", "")
+
+
 def run_migrations_offline() -> None:
     """Run migrations in 'offline' mode.
 

server/migrations/versions/2cf0b60a9d34_fix_transcript_duration_type.py

@@ -0,0 +1,40 @@
+"""fix transcript duration type
+
+Revision ID: 2cf0b60a9d34
+Revises: ccd68dc784ff
+Create Date: 2025-07-15 16:53:40.397394
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision: str = '2cf0b60a9d34'
+down_revision: Union[str, None] = 'ccd68dc784ff'
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    with op.batch_alter_table('transcript', schema=None) as batch_op:
+        batch_op.alter_column('duration',
+               existing_type=sa.INTEGER(),
+               type_=sa.Float(),
+               existing_nullable=True)
+
+    # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    with op.batch_alter_table('transcript', schema=None) as batch_op:
+        batch_op.alter_column('duration',
+               existing_type=sa.Float(),
+               type_=sa.INTEGER(),
+               existing_nullable=True)
+
+    # ### end Alembic commands ###

server/migrations/versions/88d292678ba2_fix_transcript_json_nan_values.py

@@ -0,0 +1,73 @@
+"""fix_transcript_json_nan_values
+
+Revision ID: 88d292678ba2
+Revises: 2cf0b60a9d34
+Create Date: 2025-07-15 19:30:19.876332
+
+"""
+
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision: str = "88d292678ba2"
+down_revision: Union[str, None] = "2cf0b60a9d34"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    import json
+    import re
+    from sqlalchemy import text
+
+    # Get database connection
+    conn = op.get_bind()
+
+    # Fetch all transcript records with events data
+    result = conn.execute(
+        text("SELECT id, events FROM transcript WHERE events IS NOT NULL")
+    )
+
+    def fix_nan(obj):
+        if isinstance(obj, dict):
+            for key, value in obj.items():
+                if isinstance(value, (dict, list)):
+                    fix_nan(value)
+                elif isinstance(value, float) and value != value:
+                    obj[key] = None
+        elif isinstance(obj, list):
+            for i in range(len(obj)):
+                if isinstance(obj[i], (dict, list)):
+                    fix_nan(obj[i])
+                elif isinstance(obj[i], float) and obj[i] != obj[i]:
+                    obj[i] = None
+
+    for transcript_id, events in result:
+        if not events:
+            continue
+        if "NaN" not in events:
+            continue
+
+        try:
+            jevents = json.loads(events)
+            fix_nan(jevents)
+            fixed_events = json.dumps(jevents)
+            assert "NaN" not in fixed_events
+        except (json.JSONDecodeError, AssertionError) as e:
+            print(f"Warning: Invalid JSON for transcript {transcript_id}, skipping: {e}")
+            continue
+
+        # Update the record with fixed JSON
+        conn.execute(
+            text("UPDATE transcript SET events = :events WHERE id = :id"),
+            {"events": fixed_events, "id": transcript_id},
+        )
+
+
+def downgrade() -> None:
+    # No downgrade needed - this is a data fix
+    pass

server/migrations/versions/a9c9c229ee36_transcript_composite_index.py

@@ -0,0 +1,39 @@
+"""transcript composite index
+
+Revision ID: a9c9c229ee36
+Revises: 88d292678ba2
+Create Date: 2025-07-15 20:09:40.253018
+
+"""
+
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.dialects import postgresql
+
+# revision identifiers, used by Alembic.
+revision: str = "a9c9c229ee36"
+down_revision: Union[str, None] = "88d292678ba2"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    with op.batch_alter_table("transcript", schema=None) as batch_op:
+        batch_op.create_index(
+            "idx_transcript_user_id_recording_id",
+            ["user_id", "recording_id"],
+            unique=False,
+        )
+
+    # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    with op.batch_alter_table("transcript", schema=None) as batch_op:
+        batch_op.drop_index("idx_transcript_user_id_recording_id")
+
+    # ### end Alembic commands ###