first

backend/alembic/README

@@ -0,0 +1 @@
+Generic single-database configuration.

backend/alembic/env.py

@@ -0,0 +1,91 @@
+from logging.config import fileConfig
+import sys
+from pathlib import Path
+
+from sqlalchemy import engine_from_config
+from sqlalchemy import pool
+
+from alembic import context
+
+# Add parent directory to Python path to import app modules
+sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
+
+# Import application settings and models
+from app.core.config import settings
+from app.core.database import Base
+
+# Import all models to ensure they're registered with Base.metadata
+from app.models import User, OCRBatch, OCRFile, OCRResult, ExportRule, TranslationConfig
+
+# this is the Alembic Config object, which provides
+# access to the values within the .ini file in use.
+config = context.config
+
+# Set sqlalchemy.url from settings
+config.set_main_option("sqlalchemy.url", settings.database_url)
+
+# Interpret the config file for Python logging.
+# This line sets up loggers basically.
+if config.config_file_name is not None:
+    fileConfig(config.config_file_name)
+
+# add your model's MetaData object here
+# for 'autogenerate' support
+target_metadata = Base.metadata
+
+# other values from the config, defined by the needs of env.py,
+# can be acquired:
+# my_important_option = config.get_main_option("my_important_option")
+# ... etc.
+
+
+def run_migrations_offline() -> None:
+    """Run migrations in 'offline' mode.
+
+    This configures the context with just a URL
+    and not an Engine, though an Engine is acceptable
+    here as well.  By skipping the Engine creation
+    we don't even need a DBAPI to be available.
+
+    Calls to context.execute() here emit the given string to the
+    script output.
+
+    """
+    url = config.get_main_option("sqlalchemy.url")
+    context.configure(
+        url=url,
+        target_metadata=target_metadata,
+        literal_binds=True,
+        dialect_opts={"paramstyle": "named"},
+    )
+
+    with context.begin_transaction():
+        context.run_migrations()
+
+
+def run_migrations_online() -> None:
+    """Run migrations in 'online' mode.
+
+    In this scenario we need to create an Engine
+    and associate a connection with the context.
+
+    """
+    connectable = engine_from_config(
+        config.get_section(config.config_ini_section, {}),
+        prefix="sqlalchemy.",
+        poolclass=pool.NullPool,
+    )
+
+    with connectable.connect() as connection:
+        context.configure(
+            connection=connection, target_metadata=target_metadata
+        )
+
+        with context.begin_transaction():
+            context.run_migrations()
+
+
+if context.is_offline_mode():
+    run_migrations_offline()
+else:
+    run_migrations_online()

backend/alembic/script.py.mako

@@ -0,0 +1,28 @@
+"""${message}
+
+Revision ID: ${up_revision}
+Revises: ${down_revision | comma,n}
+Create Date: ${create_date}
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+${imports if imports else ""}
+
+# revision identifiers, used by Alembic.
+revision: str = ${repr(up_revision)}
+down_revision: Union[str, None] = ${repr(down_revision)}
+branch_labels: Union[str, Sequence[str], None] = ${repr(branch_labels)}
+depends_on: Union[str, Sequence[str], None] = ${repr(depends_on)}
+
+
+def upgrade() -> None:
+    """Upgrade schema."""
+    ${upgrades if upgrades else "pass"}
+
+
+def downgrade() -> None:
+    """Downgrade schema."""
+    ${downgrades if downgrades else "pass"}

backend/alembic/versions/271dc036ea80_add_retry_count_to_files.py

@@ -0,0 +1,31 @@
+"""add_retry_count_to_files
+
+Revision ID: 271dc036ea80
+Revises: a7802b126240
+Create Date: 2025-11-12 01:48:34.258048
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision: str = '271dc036ea80'
+down_revision: Union[str, None] = 'a7802b126240'
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    """Add retry_count column to paddle_ocr_files table."""
+    op.add_column(
+        'paddle_ocr_files',
+        sa.Column('retry_count', sa.Integer(), nullable=False, server_default='0')
+    )
+
+
+def downgrade() -> None:
+    """Remove retry_count column from paddle_ocr_files table."""
+    op.drop_column('paddle_ocr_files', 'retry_count')

backend/alembic/versions/a7802b126240_initial_migration_with_paddle_ocr_prefix.py

@@ -0,0 +1,154 @@
+"""Initial migration with paddle_ocr prefix
+
+Revision ID: a7802b126240
+Revises: 
+Create Date: 2025-11-12 00:46:58.519941
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.dialects import mysql
+
+# revision identifiers, used by Alembic.
+revision: str = 'a7802b126240'
+down_revision: Union[str, None] = None
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    """Upgrade schema."""
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.create_table('paddle_ocr_users',
+    sa.Column('id', sa.Integer(), nullable=False),
+    sa.Column('username', sa.String(length=50), nullable=False),
+    sa.Column('email', sa.String(length=100), nullable=False),
+    sa.Column('password_hash', sa.String(length=255), nullable=False),
+    sa.Column('full_name', sa.String(length=100), nullable=True),
+    sa.Column('is_active', sa.Boolean(), nullable=False),
+    sa.Column('is_admin', sa.Boolean(), nullable=False),
+    sa.Column('created_at', sa.DateTime(), nullable=False),
+    sa.Column('updated_at', sa.DateTime(), nullable=False),
+    sa.PrimaryKeyConstraint('id')
+    )
+    op.create_index(op.f('ix_paddle_ocr_users_email'), 'paddle_ocr_users', ['email'], unique=True)
+    op.create_index(op.f('ix_paddle_ocr_users_id'), 'paddle_ocr_users', ['id'], unique=False)
+    op.create_index(op.f('ix_paddle_ocr_users_username'), 'paddle_ocr_users', ['username'], unique=True)
+    op.create_table('paddle_ocr_batches',
+    sa.Column('id', sa.Integer(), nullable=False),
+    sa.Column('user_id', sa.Integer(), nullable=False),
+    sa.Column('batch_name', sa.String(length=255), nullable=True),
+    sa.Column('status', sa.Enum('PENDING', 'PROCESSING', 'COMPLETED', 'PARTIAL', 'FAILED', name='batchstatus'), nullable=False),
+    sa.Column('total_files', sa.Integer(), nullable=False),
+    sa.Column('completed_files', sa.Integer(), nullable=False),
+    sa.Column('failed_files', sa.Integer(), nullable=False),
+    sa.Column('created_at', sa.DateTime(), nullable=False),
+    sa.Column('started_at', sa.DateTime(), nullable=True),
+    sa.Column('completed_at', sa.DateTime(), nullable=True),
+    sa.ForeignKeyConstraint(['user_id'], ['paddle_ocr_users.id'], ondelete='CASCADE'),
+    sa.PrimaryKeyConstraint('id')
+    )
+    op.create_index(op.f('ix_paddle_ocr_batches_created_at'), 'paddle_ocr_batches', ['created_at'], unique=False)
+    op.create_index(op.f('ix_paddle_ocr_batches_id'), 'paddle_ocr_batches', ['id'], unique=False)
+    op.create_index(op.f('ix_paddle_ocr_batches_status'), 'paddle_ocr_batches', ['status'], unique=False)
+    op.create_index(op.f('ix_paddle_ocr_batches_user_id'), 'paddle_ocr_batches', ['user_id'], unique=False)
+    op.create_table('paddle_ocr_export_rules',
+    sa.Column('id', sa.Integer(), nullable=False),
+    sa.Column('user_id', sa.Integer(), nullable=False),
+    sa.Column('rule_name', sa.String(length=100), nullable=False),
+    sa.Column('description', sa.Text(), nullable=True),
+    sa.Column('config_json', sa.JSON(), nullable=False),
+    sa.Column('css_template', sa.Text(), nullable=True),
+    sa.Column('created_at', sa.DateTime(), nullable=False),
+    sa.Column('updated_at', sa.DateTime(), nullable=False),
+    sa.ForeignKeyConstraint(['user_id'], ['paddle_ocr_users.id'], ondelete='CASCADE'),
+    sa.PrimaryKeyConstraint('id')
+    )
+    op.create_index(op.f('ix_paddle_ocr_export_rules_id'), 'paddle_ocr_export_rules', ['id'], unique=False)
+    op.create_index(op.f('ix_paddle_ocr_export_rules_user_id'), 'paddle_ocr_export_rules', ['user_id'], unique=False)
+    op.create_table('paddle_ocr_translation_configs',
+    sa.Column('id', sa.Integer(), nullable=False),
+    sa.Column('user_id', sa.Integer(), nullable=False),
+    sa.Column('source_lang', sa.String(length=20), nullable=False),
+    sa.Column('target_lang', sa.String(length=20), nullable=False),
+    sa.Column('engine_type', sa.String(length=50), nullable=False),
+    sa.Column('engine_config', sa.JSON(), nullable=True),
+    sa.Column('created_at', sa.DateTime(), nullable=False),
+    sa.Column('updated_at', sa.DateTime(), nullable=False),
+    sa.ForeignKeyConstraint(['user_id'], ['paddle_ocr_users.id'], ondelete='CASCADE'),
+    sa.PrimaryKeyConstraint('id')
+    )
+    op.create_index(op.f('ix_paddle_ocr_translation_configs_id'), 'paddle_ocr_translation_configs', ['id'], unique=False)
+    op.create_index(op.f('ix_paddle_ocr_translation_configs_user_id'), 'paddle_ocr_translation_configs', ['user_id'], unique=False)
+    op.create_table('paddle_ocr_files',
+    sa.Column('id', sa.Integer(), nullable=False),
+    sa.Column('batch_id', sa.Integer(), nullable=False),
+    sa.Column('filename', sa.String(length=255), nullable=False),
+    sa.Column('original_filename', sa.String(length=255), nullable=False),
+    sa.Column('file_path', sa.String(length=512), nullable=False),
+    sa.Column('file_size', sa.Integer(), nullable=False),
+    sa.Column('file_format', sa.String(length=20), nullable=False),
+    sa.Column('status', sa.Enum('PENDING', 'PROCESSING', 'COMPLETED', 'FAILED', name='filestatus'), nullable=False),
+    sa.Column('error_message', sa.Text(), nullable=True),
+    sa.Column('created_at', sa.DateTime(), nullable=False),
+    sa.Column('started_at', sa.DateTime(), nullable=True),
+    sa.Column('completed_at', sa.DateTime(), nullable=True),
+    sa.Column('processing_time', sa.Float(), nullable=True),
+    sa.ForeignKeyConstraint(['batch_id'], ['paddle_ocr_batches.id'], ondelete='CASCADE'),
+    sa.PrimaryKeyConstraint('id')
+    )
+    op.create_index(op.f('ix_paddle_ocr_files_batch_id'), 'paddle_ocr_files', ['batch_id'], unique=False)
+    op.create_index(op.f('ix_paddle_ocr_files_id'), 'paddle_ocr_files', ['id'], unique=False)
+    op.create_index(op.f('ix_paddle_ocr_files_status'), 'paddle_ocr_files', ['status'], unique=False)
+    op.create_table('paddle_ocr_results',
+    sa.Column('id', sa.Integer(), nullable=False),
+    sa.Column('file_id', sa.Integer(), nullable=False),
+    sa.Column('markdown_path', sa.String(length=512), nullable=True),
+    sa.Column('json_path', sa.String(length=512), nullable=True),
+    sa.Column('images_dir', sa.String(length=512), nullable=True),
+    sa.Column('detected_language', sa.String(length=20), nullable=True),
+    sa.Column('total_text_regions', sa.Integer(), nullable=False),
+    sa.Column('average_confidence', sa.Float(), nullable=True),
+    sa.Column('layout_data', sa.JSON(), nullable=True),
+    sa.Column('images_metadata', sa.JSON(), nullable=True),
+    sa.Column('created_at', sa.DateTime(), nullable=False),
+    sa.ForeignKeyConstraint(['file_id'], ['paddle_ocr_files.id'], ondelete='CASCADE'),
+    sa.PrimaryKeyConstraint('id')
+    )
+    op.create_index(op.f('ix_paddle_ocr_results_file_id'), 'paddle_ocr_results', ['file_id'], unique=True)
+    op.create_index(op.f('ix_paddle_ocr_results_id'), 'paddle_ocr_results', ['id'], unique=False)
+    # NOTE: Removed all drop_table/drop_index commands to preserve existing tables in shared database
+    # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    """Downgrade schema - removes all paddle_ocr_ tables."""
+    # ### commands auto generated by Alembic - please adjust! ###
+    # Drop paddle_ocr tables in reverse order
+    op.drop_index(op.f('ix_paddle_ocr_results_id'), table_name='paddle_ocr_results')
+    op.drop_index(op.f('ix_paddle_ocr_results_file_id'), table_name='paddle_ocr_results')
+    op.drop_table('paddle_ocr_results')
+    op.drop_index(op.f('ix_paddle_ocr_files_status'), table_name='paddle_ocr_files')
+    op.drop_index(op.f('ix_paddle_ocr_files_id'), table_name='paddle_ocr_files')
+    op.drop_index(op.f('ix_paddle_ocr_files_batch_id'), table_name='paddle_ocr_files')
+    op.drop_table('paddle_ocr_files')
+    op.drop_index(op.f('ix_paddle_ocr_translation_configs_user_id'), table_name='paddle_ocr_translation_configs')
+    op.drop_index(op.f('ix_paddle_ocr_translation_configs_id'), table_name='paddle_ocr_translation_configs')
+    op.drop_table('paddle_ocr_translation_configs')
+    op.drop_index(op.f('ix_paddle_ocr_export_rules_user_id'), table_name='paddle_ocr_export_rules')
+    op.drop_index(op.f('ix_paddle_ocr_export_rules_id'), table_name='paddle_ocr_export_rules')
+    op.drop_table('paddle_ocr_export_rules')
+    op.drop_index(op.f('ix_paddle_ocr_batches_user_id'), table_name='paddle_ocr_batches')
+    op.drop_index(op.f('ix_paddle_ocr_batches_status'), table_name='paddle_ocr_batches')
+    op.drop_index(op.f('ix_paddle_ocr_batches_id'), table_name='paddle_ocr_batches')
+    op.drop_index(op.f('ix_paddle_ocr_batches_created_at'), table_name='paddle_ocr_batches')
+    op.drop_table('paddle_ocr_batches')
+    op.drop_index(op.f('ix_paddle_ocr_users_username'), table_name='paddle_ocr_users')
+    op.drop_index(op.f('ix_paddle_ocr_users_id'), table_name='paddle_ocr_users')
+    op.drop_index(op.f('ix_paddle_ocr_users_email'), table_name='paddle_ocr_users')
+    op.drop_table('paddle_ocr_users')
+    # NOTE: We do NOT recreate other tables that existed before this migration
+    # ### end Alembic commands ###
+