Enhance XLS upload functionality and update requirements. Added Flask, Flask-SQLAlchemy, and Alembic to requirements. Modified database schema in upload_xls.py for improved data handling and added SQLAlchemy configuration in config.py.

This commit is contained in:
2025-06-09 15:34:18 +01:00
parent f478a52a2f
commit c00bb71d2a
14 changed files with 427 additions and 33 deletions
+56
View File
@@ -0,0 +1,56 @@
# Database Migration & Data Upload Guide
This project uses **Flask-Migrate** (powered by Alembic) for managing database schema changes and a custom Flask CLI command for uploading XLS data.
## Migration Workflow
Follow these steps to manage database schema and upload data:
1. **Set Flask App Environment Variable:**
Open your terminal in the project root (`digifi-Analytics/`) and set the `FLASK_APP` variable:
```bash
# For Windows
set FLASK_APP=run.py
# For macOS/Linux
export FLASK_APP=run.py
```
2. **Initialize Migration Repository (First-time setup only):**
This command sets up the `migrations/` directory structure. You've likely already run this, so you might get a "Directory already exists" message, which is fine.
```bash
flask --app run.py db init
```
3. **Generate a New Migration Script:**
After making changes to `salary_analytics/app/models.py` (e.g., adding a new table or column), use this command to create a migration file. This file will contain the `upgrade()` and `downgrade()` logic.
```bash
flask --app run.py db migrate -m "Descriptive message for your changes"
```
4. **Review the Generated Migration:**
Open the newly created `.py` file in `migrations/versions/` (e.g., `XXXXXXXXXXXX_your_message.py`) and review the `upgrade()` and `downgrade()` functions. Ensure they accurately reflect your intended schema changes.
5. **Apply Migrations to the Database:**
This command executes the pending migration scripts, updating your database schema. **Always apply migrations after generating them.**
```bash
flask --app run.py db upgrade
```
## Uploading XLS Data
Once your `analytics_raw_transactions` table is created via migration, you can upload your XLS files using the custom command:
```bash
flask --app run.py upload-xls <path_to_your_xls_file>
```
**Example:**
```bash
flask --app run.py upload-xls data/transactions.xls
```
+44
View File
@@ -0,0 +1,44 @@
[alembic]
script_location = migrations
sqlalchemy.url =
revision_environment = false
version_locations = %(script_location)s/versions
output_encoding = utf-8
[post_write_hooks]
hooks =
hook_default_ops =
[loggers]
keys = root,sqlalchemy,alembic
[handlers]
keys = console
[formatters]
keys = generic
[logger_root]
level = WARNING
handlers = console
qualname =
[logger_sqlalchemy]
level = WARNING
handlers = console
qualname = sqlalchemy
[logger_alembic]
level = DEBUG
handlers = console
qualname = alembic
[handler_console]
class = StreamHandler
args = (sys.stderr,)
level = NOTSET
formatter = generic
[formatter_generic]
format = %(levelname)-5.5s [%(name)s] %(message)s
datefmt = %H:%M:%S
+89
View File
@@ -0,0 +1,89 @@
from logging.config import fileConfig
from sqlalchemy import engine_from_config
from sqlalchemy import pool
from alembic import context
# this is the Alembic Config object, which provides
# access to values within the .ini file in use.
config = context.config
# 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
# from myapp import Base
# target_metadata = Base.metadata
from flask import current_app
from salary_analytics.app.extensions import db
config.set_main_option('sqlalchemy.url',
current_app.config.get('SQLALCHEMY_DATABASE_URI'))
target_metadata = db.metadata
# Function to filter objects for autogenerate
def include_object(object, name, type_, reflected, compare_to):
"""
Control which objects are included in the autogenerate process.
Only include objects that are part of the Flask app's declared models.
"""
if type_ == "table" and reflected and name not in target_metadata.tables:
return False # Exclude tables that are in DB but not in models
return True # Include everything else (e.g., our modeled tables, columns, etc.)
def run_migrations_offline():
"""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 database to begin with.
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"},
include_object=include_object
)
with context.begin_transaction():
context.run_migrations()
def run_migrations_online():
"""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,
include_object=include_object
)
with context.begin_transaction():
context.run_migrations()
if context.is_offline_mode():
run_migrations_offline()
else:
run_migrations_online()
+24
View File
@@ -0,0 +1,24 @@
"""${message}
Revision ID: ${up_revision}
Revises: ${down_revision | comma,n}
Create Date: ${create_date}
"""
from alembic import op
import sqlalchemy as sa
${imports if imports else ""}
# revision identifiers, used by Alembic.
revision = ${repr(up_revision)}
down_revision = ${repr(down_revision)}
branch_labels = ${repr(branch_labels)}
depends_on = ${repr(depends_on)}
def upgrade():
${upgrades if upgrades else "pass"}
def downgrade():
${downgrades if downgrades else "pass"}
@@ -0,0 +1,46 @@
"""Create analytics_raw_transactions table
Revision ID: c2b2cdbc8022
Revises:
Create Date: 2025-06-09 15:19:36.017861
"""
from alembic import op
import sqlalchemy as sa
# revision identifiers, used by Alembic.
revision = 'c2b2cdbc8022'
down_revision = None
branch_labels = None
depends_on = None
def upgrade():
# ### commands auto generated by Alembic - please adjust! ###
op.create_table('analytics_raw_transactions',
sa.Column('id', sa.Integer(), nullable=False),
sa.Column('cust_id', sa.String(length=10), nullable=True),
sa.Column('accountid', sa.String(length=10), nullable=True),
sa.Column('tran_id', sa.String(length=12), nullable=True),
sa.Column('entry_date', sa.TIMESTAMP(), nullable=True),
sa.Column('value_date', sa.TIMESTAMP(), nullable=True),
sa.Column('pstd_date', sa.TIMESTAMP(), nullable=True),
sa.Column('tran_date', sa.TIMESTAMP(), nullable=True),
sa.Column('tran_sub_ty', sa.String(length=4), nullable=True),
sa.Column('part_tran_ty', sa.String(length=4), nullable=True),
sa.Column('channel', sa.String(length=32), nullable=True),
sa.Column('tran_amt', sa.Numeric(precision=20, scale=2), nullable=True),
sa.Column('balance', sa.Numeric(precision=20, scale=2), nullable=True),
sa.Column('isreverse', sa.String(length=4), nullable=True),
sa.Column('reverse', sa.String(length=4), nullable=True),
sa.Column('tran_particular', sa.String(length=100), nullable=True),
sa.PrimaryKeyConstraint('id')
)
# ### end Alembic commands ###
def downgrade():
# ### commands auto generated by Alembic - please adjust! ###
op.drop_table('analytics_raw_transactions')
# ### end Alembic commands ###