added database migrations + soft delete

README.md

@@ -17,6 +17,12 @@ cd /src
 orchestration must be from the console(?)
 * turn off VPNs if connection to docker is not working
 
+## Database migrations
+check https://alembic.sqlalchemy.org/en/latest/tutorial.html#the-migration-environment
+
+* create migrations with `alembic revision -m "create account table"`
+* migrate to most recent with `alembic upgrade head`
+* downgrade with `alembic downgrade -1`
 
 ## Release
 Copy `.env` and `src/.env` to deployment, along with the contents of `secrets/` including `secrets/orchestration.yaml`.
@@ -26,4 +32,5 @@ Then `docker compose up -d`.
 #### updating packages/app/access
 If pipenv packages are updated: `pipenv lock --requirements -r  > requirements.txt` (manually comment line `-i https://pypi.org/simple`) and then `docker compose down` + `docker compose up --build -d` to build images with new packages.
 
-New users should be added to the `src/.env` file `ALLOWED_EMAILS` prop
+New users should be added to the `src/.env` file `ALLOWED_EMAILS` prop
+

docker-compose.yml

@@ -46,6 +46,7 @@ services:
     build: ./src
     restart: always
     command:  flower --app=worker.celery --port=5555 --broker=redis://:${REDIS_PASSWORD}@redis:6379/0 --basic_auth=${FLOWER_USERNAME}:${FLOWER_PASSWORD}
+    env_file: src/.env
     ports:
       - 5556:5555
     environment:

src/.example.env

@@ -3,4 +3,5 @@ GOOGLE_CHROME_APP_ID=0000000000000000000000000000000000.apps.googleusercontent.c
 ALLOWED_EMAILS=email1,email2
 ORCHESTRATION_CONFIG_DEFAULT=secrets/orchestration.yaml
 # optional
-# ORCHESTRATION_CONFIG_BELLINGCAT=secrets/orchestration-bcat.yaml
+# ORCHESTRATION_CONFIG_BELLINGCAT=secrets/orchestration-bcat.yaml
+DATABASE_PATH="sqlite:///./auto-archiver.db"

src/Pipfile

@@ -18,6 +18,7 @@ python-dotenv = "*"
 loguru = "*"
 sqlalchemy = "*"
 auto-archiver = "*"
+alembic = "*"
 
 [dev-packages]
 

src/Pipfile.lock

@@ -1,7 +1,7 @@
 {
     "_meta": {
         "hash": {
-            "sha256": "3cd66e4888849b1bdd4ab32b2cf89ccff2260648da860c9890cb9ff9012ce451"
+            "sha256": "8fe474e7b0a87b22d9b1f772066d0a26927e38ad081f25ef2afefe27f0b922dc"
         },
         "pipfile-spec": 6,
         "requires": {
@@ -32,6 +32,14 @@
             "index": "pypi",
             "version": "==0.18.0"
         },
+        "alembic": {
+            "hashes": [
+                "sha256:4d3bd32ecdbb7bbfb48a9fe9e6d6fd6a831a1b59d03e26e292210237373e7db5",
+                "sha256:6f1c2207369bf4f49f952057a33bb017fbe5c148c2a773b46906b806ea6e825f"
+            ],
+            "index": "pypi",
+            "version": "==1.9.4"
+        },
         "amqp": {
             "hashes": [
                 "sha256:70cdb10628468ff14e57ec2f751c7aa9e48e7e3651cfd62d431213c0c4e58f21",
@@ -805,6 +813,14 @@
             "markers": "python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3, 3.4'",
             "version": "==4.9.2"
         },
+        "mako": {
+            "hashes": [
+                "sha256:c97c79c018b9165ac9922ae4f32da095ffd3c4e6872b45eded42926deea46818",
+                "sha256:d60a3903dc3bb01a18ad6a89cdbe2e4eadc69c0bc8ef1e3773ba53d44c3f7a34"
+            ],
+            "markers": "python_version >= '3.7'",
+            "version": "==1.2.4"
+        },
         "markdown-it-py": {
             "hashes": [
                 "sha256:5a35f8d1870171d9acc47b99612dc146129b631baf04970128b568f190d0cc30",
@@ -1172,7 +1188,7 @@
                 "sha256:2397d518c17bfbc16a3d414b1cf6d3c231fd8d322f21c755ac2215c9ee675537",
                 "sha256:4e03a30b2570fa4f17fbc7293d850fb8276c66be106d55e460b9287de37e1dd2"
             ],
-            "markers": "python_version >= '3.6' and python_version < '4'",
+            "markers": "python_version >= '3.6' and python_version < '4.0'",
             "version": "==0.8.1"
         },
         "pytz": {
@@ -1375,7 +1391,7 @@
                 "sha256:90260d9058e514786967344d0ef75fa8727eed8a7d2e43ce9f4bcf1b536174f7",
                 "sha256:e38464a49c6c85d7f1351b0126661487a7e0a14a50f1675ec50eb34d4f20ef21"
             ],
-            "markers": "python_version >= '3.6' and python_version < '4'",
+            "markers": "python_version >= '3.6' and python_version < '4.0'",
             "version": "==4.9"
         },
         "s3transfer": {

src/alembic.ini

@@ -0,0 +1,106 @@
+# A generic, single database configuration.
+
+[alembic]
+# path to migration scripts
+script_location = migrations
+
+# template used to generate migration file names; The default value is %%(rev)s_%%(slug)s
+# Uncomment the line below if you want the files to be prepended with date and time
+# see https://alembic.sqlalchemy.org/en/latest/tutorial.html#editing-the-ini-file
+# for all available tokens
+# file_template = %%(year)d_%%(month).2d_%%(day).2d_%%(hour).2d%%(minute).2d-%%(rev)s_%%(slug)s
+
+# sys.path path, will be prepended to sys.path if present.
+# defaults to the current working directory.
+prepend_sys_path = .
+
+# timezone to use when rendering the date within the migration file
+# as well as the filename.
+# If specified, requires the python-dateutil library that can be
+# installed by adding `alembic[tz]` to the pip requirements
+# string value is passed to dateutil.tz.gettz()
+# leave blank for localtime
+# timezone =
+
+# max length of characters to apply to the
+# "slug" field
+# truncate_slug_length = 40
+
+# set to 'true' to run the environment during
+# the 'revision' command, regardless of autogenerate
+# revision_environment = false
+
+# set to 'true' to allow .pyc and .pyo files without
+# a source .py file to be detected as revisions in the
+# versions/ directory
+# sourceless = false
+
+# version location specification; This defaults
+# to migrations/versions.  When using multiple version
+# directories, initial revisions must be specified with --version-path.
+# The path separator used here should be the separator specified by "version_path_separator" below.
+# version_locations = %(here)s/bar:%(here)s/bat:migrations/versions
+
+# version path separator; As mentioned above, this is the character used to split
+# version_locations. The default within new alembic.ini files is "os", which uses os.pathsep.
+# If this key is omitted entirely, it falls back to the legacy behavior of splitting on spaces and/or commas.
+# Valid values for version_path_separator are:
+#
+# version_path_separator = :
+# version_path_separator = ;
+# version_path_separator = space
+version_path_separator = os  # Use os.pathsep. Default configuration used for new projects.
+
+# the output encoding used when revision files
+# are written from script.py.mako
+# output_encoding = utf-8
+
+# passed from .env
+# sqlalchemy.url = driver://user:pass@localhost/dbname
+
+
+[post_write_hooks]
+# post_write_hooks defines scripts or Python functions that are run
+# on newly generated revision scripts.  See the documentation for further
+# detail and examples
+
+# format using "black" - use the console_scripts runner, against the "black" entrypoint
+# hooks = black
+# black.type = console_scripts
+# black.entrypoint = black
+# black.options = -l 79 REVISION_SCRIPT_FILENAME
+
+# Logging configuration
+[loggers]
+keys = root,sqlalchemy,alembic
+
+[handlers]
+keys = console
+
+[formatters]
+keys = generic
+
+[logger_root]
+level = WARN
+handlers = console
+qualname =
+
+[logger_sqlalchemy]
+level = WARN
+handlers =
+qualname = sqlalchemy.engine
+
+[logger_alembic]
+level = INFO
+handlers =
+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

src/db/crud.py

@@ -15,10 +15,6 @@ def search_tasks_by_url(db: Session, url:str, skip: int = 0, limit: int = 100):
 def search_tasks_by_email(db: Session, email:str, skip: int = 0, limit: int = 100):
     return base_query(db).filter(models.Task.author==email).offset(skip).limit(limit).all()
 
-def base_query(db:Session):
-    # allow only some fields to be returned, for example author should remain hidden
-    return db.query(models.Task).options(load_only(models.Task.id, models.Task.created_at, models.Task.url, models.Task.result))
-
 def create_task(db: Session, task: schemas.TaskCreate):
     db_task = models.Task(id=task.id, url=task.url, author=task.author, result=task.result)
     db.add(db_task)
@@ -26,10 +22,22 @@ def create_task(db: Session, task: schemas.TaskCreate):
     db.refresh(db_task)
     return db_task
 
-# TODO: implement soft delete so that S3 content can be found ant not dangling
+# def delete_task(db: Session, task_id: str, email:str)->bool:
-def delete_task(db: Session, task_id: str, email:str)->bool:
+#     db_task = db.query(models.Task).filter(models.Task.id == task_id, models.Task.author==email).first()
-    db_task = db.query(models.Task).filter(models.Task.id == task_id, models.Task.author==email).first()
+#     if db_task:
+#         db.delete(db_task)
+#         db.commit()
+#     return db_task is not None
+
+def soft_delete_task(db: Session, task_id: str, email:str)->bool:
+    db_task = db.query(models.Task).filter(models.Task.id == task_id, models.Task.author==email, models.Task.deleted==False).first()
     if db_task:
-        db.delete(db_task)
+        db_task.deleted = True
         db.commit()
-    return db_task is not None
+    return db_task is not None
+
+def base_query(db:Session):
+    # allow only some fields to be returned, for example author should remain hidden
+    return db.query(models.Task)\
+        .options(load_only(models.Task.id, models.Task.created_at, models.Task.url, models.Task.result))\
+        .filter(models.Task.deleted == False)

src/db/database.py

@@ -1,9 +1,12 @@
 from sqlalchemy import create_engine
 from sqlalchemy.ext.declarative import declarative_base
 from sqlalchemy.orm import sessionmaker
+import os
 
-SQLALCHEMY_DATABASE_URL = "sqlite:///./auto-archiver.db"
+SQLALCHEMY_DATABASE_URL = os.environ.get("DATABASE_PATH")#"sqlite:///./auto-archiver.db"
 # SQLALCHEMY_DATABASE_URL = "postgresql://user:password@postgresserver/db"
+print("-"*50)
+print(SQLALCHEMY_DATABASE_URL)
 
 engine = create_engine(
     SQLALCHEMY_DATABASE_URL, connect_args={"check_same_thread": False}

src/db/models.py

@@ -1,4 +1,4 @@
-from sqlalchemy import Column, String, JSON, DateTime
+from sqlalchemy import Column, String, JSON, DateTime, Boolean
 from sqlalchemy.sql import func
 from .database import Base
 
@@ -12,5 +12,7 @@ class Task(Base):
     result = Column(JSON, default=None)
     created_at = Column(DateTime(timezone=True), server_default=func.now())
     # updated_at = Column(DateTime(timezone=True), onupdate=func.now())
+    deleted = Column(Boolean, default=False)
+
 
     # items = relationship("Item", back_populates="owner")

src/db/schemas.py

@@ -10,6 +10,7 @@ class TaskCreate(BaseModel):
 
 class Task(TaskCreate):
     created_at: datetime
+    deleted: bool
 
     class Config:
         orm_mode = True

src/main.py

@@ -26,7 +26,7 @@ assert len(GOOGLE_CHROME_APP_ID)>10, "GOOGLE_CHROME_APP_ID env variable not set"
 ALLOWED_EMAILS = set(os.environ.get("ALLOWED_EMAILS", "").split(","))
 assert len(GOOGLE_CHROME_APP_ID)>=1, "at least one ALLOWED_EMAILS is required from the env variable"
 ALLOWED_ORIGINS = os.environ.get("ALLOWED_ORIGINS", "chrome-extension://ondkcheoicfckabcnkdgbepofpjmjcmb,chrome-extension://ojcimmjndnlmmlgnjaeojoebaceokpdp").split(",")
-VERSION = "0.1.5"
+VERSION = "0.1.6"
 
 app = FastAPI() 
 app.add_middleware(
@@ -95,7 +95,7 @@ def get_status(task_id, access_token:str, db: Session = Depends(get_db)):
     logger.info(f"deleting task {task_id} request by {email}")
     return JSONResponse({
         "id": task_id,
-        "deleted": crud.delete_task(db, task_id, email)
+        "deleted": crud.soft_delete_task(db, task_id, email)
     })
 
 
@@ -103,11 +103,14 @@ def get_status(task_id, access_token:str, db: Session = Depends(get_db)):
 def home():
     return JSONResponse({"status": "good", "version": VERSION})
 
+
+import alembic.config
 @app.on_event("startup")
 async def on_startup():
 #     # Not needed if you setup a migration system like Alembic
 #     await create_db_and_tables()https://github.com/bellingcat/auto-archiver/tree/dockerize
     models.Base.metadata.create_all(bind=engine)
+    alembic.config.main(argv=['--raiseerr', 'upgrade', 'head'])
 
 #### helper methods
 def authenticate_user(access_token):

src/migrations/README

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

src/migrations/env.py

@@ -0,0 +1,81 @@
+from logging.config import fileConfig
+import os
+from sqlalchemy import engine_from_config
+from sqlalchemy import pool
+
+from alembic import context
+from dotenv import load_dotenv
+
+load_dotenv()
+
+# this is the Alembic Config object, which provides
+# access to the values within the .ini file in use.
+config = context.config
+config.set_main_option('sqlalchemy.url', os.environ.get("DATABASE_PATH"))
+# 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, disable_existing_loggers=False) # disable_existing_loggers prevents loguru disabling
+
+# add your model's MetaData object here
+# for 'autogenerate' support
+# from myapp import mymodel
+# target_metadata = mymodel.Base.metadata
+target_metadata = None
+
+# 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()

src/migrations/script.py.mako

@@ -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() -> None:
+    ${upgrades if upgrades else "pass"}
+
+
+def downgrade() -> None:
+    ${downgrades if downgrades else "pass"}

src/migrations/versions/ae468b023078_created_tasks_deleted_column.py

@@ -0,0 +1,27 @@
+"""created tasks.deleted column
+
+Revision ID: ae468b023078
+Revises: 
+Create Date: 2023-02-27 12:40:24.146786
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = 'ae468b023078'
+down_revision = None
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        'tasks',
+        sa.Column('deleted', sa.Boolean, default=False, nullable=False, server_default=sa.sql.expression.false()),
+    )
+
+
+def downgrade() -> None:
+    op.drop_column('tasks', 'deleted')

src/requirements.txt

@@ -8,6 +8,7 @@
 # -i https://pypi.org/simple
 aiofiles==0.6.0
 aiosqlite==0.18.0
+alembic==1.9.4
 amqp==2.6.1; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3, 3.4'
 anyio==3.6.2; python_full_version >= '3.6.2'
 argparse==1.4.0
@@ -58,6 +59,7 @@ jmespath==1.0.1; python_version >= '3.7'
 kombu==4.6.11; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3, 3.4'
 loguru==0.6.0
 lxml==4.9.2; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3, 3.4'
+mako==1.2.4; python_version >= '3.7'
 markdown-it-py==2.2.0; python_version >= '3.7'
 markupsafe==2.1.2; python_version >= '3.7'
 marshmallow-enum==1.5.1
@@ -86,7 +88,7 @@ pytest==6.2.4
 python-dateutil==2.8.2; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3'
 python-dotenv==1.0.0
 python-slugify==8.0.1; python_version >= '3.7'
-python-twitter-v2==0.8.1; python_version >= '3.6' and python_version < '4'
+python-twitter-v2==0.8.1; python_version >= '3.6' and python_version < '4.0'
 pytz-deprecation-shim==0.1.0.post0; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3, 3.4, 3.5'
 pytz==2022.7.1
 pyyaml==6.0; python_version >= '3.6'
@@ -96,7 +98,7 @@ requests-oauthlib==1.3.1; python_version >= '2.7' and python_version not in '3.0
 requests-toolbelt==0.10.1; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3'
 requests==2.28.2
 rich==13.3.1; python_version >= '3.7'
-rsa==4.9; python_version >= '3.6' and python_version < '4'
+rsa==4.9; python_version >= '3.6' and python_version < '4.0'
 s3transfer==0.6.0; python_version >= '3.7'
 selenium==4.8.2; python_version >= '3.7'
 six==1.16.0; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3'