1055 improve the ux of the export process for new users [WIP] (#1093)

.gitignore

@@ -145,3 +145,5 @@ cython_debug/
 
 # Development Docker Compose file
 docker-compose.dev.yaml
+karton-logs
+output

alembic.ini

@@ -0,0 +1,40 @@
+[alembic]
+script_location = migrations
+prepend_sys_path = .
+version_path_separator = os  # Use os.pathsep. Default configuration used for new projects.
+
+[post_write_hooks]
+
+[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

artemis/csrf.py

@@ -9,8 +9,11 @@
 from fastapi_csrf_protect.exceptions import CsrfProtectError
 from pydantic import BaseModel
 
+from artemis.db import DB
 from artemis.templating import templates
 
+db = DB()
+
 
 def generate_csrf_secret() -> str:
     csrf_secret_path = "/data/csrf_secret"
@@ -44,6 +47,7 @@ def get_csrf_config() -> CsrfSettings:
 def csrf_form_template_response(template_name: str, context: Dict[str, Any], csrf_protect: CsrfProtect) -> Response:
     csrf_token, signed_token = csrf_protect.generate_csrf_tokens()
     context["csrf_token"] = csrf_token
+    context["tag_names"] = db.get_tags()
     response = templates.TemplateResponse(template_name, context)
     csrf_protect.set_csrf_cookie(signed_token, response)
     return response

artemis/db.py

@@ -8,7 +8,7 @@
 import os
 import shutil
 from enum import Enum
-from typing import Any, Dict, Generator, List, Optional
+from typing import Any, Dict, Generator, List, Optional, Type
 
 from karton.core import Task
 from pydantic import BaseModel
@@ -138,6 +138,14 @@ class ReportGenerationTask(Base):  # type: ignore
     alerts = Column(JSON, nullable=True)
 
 
+class Tag(Base):  # type: ignore
+    __tablename__ = "tag"
+
+    id = Column(Integer, primary_key=True)
+    tag_name = Column(String, index=True, unique=True)
+    created_at = Column(DateTime, server_default=text("NOW()"))
+
+
 @dataclasses.dataclass
 class PaginatedResults:
     records_count_total: int
@@ -179,7 +187,6 @@ def __init__(self) -> None:
             Config.Data.POSTGRES_CONN_STR, json_serializer=functools.partial(json.dumps, cls=JSONEncoderAdditionalTypes)
         )
         self.session = sessionmaker(bind=self._engine)
-        Base.metadata.create_all(bind=self._engine, checkfirst=True)
 
     def list_analysis(self) -> List[Dict[str, Any]]:
         with self.session() as session:
@@ -525,3 +532,15 @@ def _strip_internal_db_info(self, d: Dict[str, Any]) -> Dict[str, Any]:
         if "headers_string" in d:
             del d["headers_string"]
         return d
+
+    def save_tag(self, tag_name: str | None) -> None:
+        if tag_name is not None:
+            statement = postgres_insert(Tag).values(tag_name=tag_name)
+            statement = statement.on_conflict_do_nothing(index_elements=[Tag.tag_name])
+            with self.session() as session:
+                session.execute(statement)
+                session.commit()
+
+    def get_tags(self) -> List[Type[Tag]] | Any:
+        with self.session() as session:
+            return session.query(Tag).all()

artemis/producer.py

@@ -26,4 +26,5 @@ def create_tasks(
         task.add_payload("disabled_modules", disabled_modules, persistent=True)
         db.create_analysis(task)
         db.save_scheduled_task(task)
+        db.save_tag(tag)
         producer.send_task(task)

docker-compose.yaml

@@ -55,7 +55,7 @@ services:
 
   autoreporter:
     <<: *artemis-build-or-image
-    command: "bash -c '/wait-for-it.sh postgres:5432 -- python3 -m artemis.reporting.task_handler'"
+    command: "bash -c '/wait-for-it.sh postgres:5432 -- alembic upgrade head && python3 -m artemis.reporting.task_handler'"
     env_file: .env
     restart: always
     volumes:
@@ -81,7 +81,7 @@ services:
     env_file: .env
     volumes:
       - ./archived-task-results/:/opt/archived-task-results/
-    command: "bash -c '/wait-for-it.sh postgres:5432 -- python3 -m artemis.autoarchiver.autoarchiver'"
+    command: "bash -c '/wait-for-it.sh postgres:5432 -- alembic upgrade head && python3 -m artemis.autoarchiver.autoarchiver'"
     restart: always
 
   web:

docker/Dockerfile

@@ -24,7 +24,9 @@ RUN apk add --no-cache --virtual .build-deps go gcc git libc-dev make libffi-dev
 WORKDIR /opt
 
 COPY "artemis/" "artemis/"
+COPY "alembic.ini" "alembic.ini"
+COPY "migrations/" "migrations/"
 COPY "static/" "static/"
 COPY "templates/" "templates/"
 
-CMD ["uvicorn", "artemis.main:app", "--host", "0.0.0.0", "--port", "5000"]
+CMD ["bash", "-c", "alembic upgrade head && uvicorn artemis.main:app --host 0.0.0.0 --port 5000"]

migrations/README

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

migrations/env.py

@@ -0,0 +1,80 @@
+#  type: ignore
+from logging.config import fileConfig
+
+from alembic import context
+from sqlalchemy import engine_from_config, pool
+
+from artemis.config import Config
+from artemis.db import Base
+
+# this is the Alembic Config object, which provides
+# access to the values within the .ini file in use.
+config = context.config
+
+# Interpret the config file for Python logging.
+# This line sets up loggers basically.
+fileConfig(config.config_file_name)
+
+# add your model's MetaData object here
+# for 'autogenerate' support
+# from myapp import mymodel
+# target_metadata = mymodel.Base.metadata
+
+target_metadata = 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.
+
+DATABASE_URL = Config.Data.POSTGRES_CONN_STR
+
+
+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 DBAPI to be available.
+
+    Calls to context.execute() here emit the given string to the
+    script output.
+
+    """
+    context.configure(
+        url=DATABASE_URL,
+        target_metadata=target_metadata,
+        literal_binds=True,
+        dialect_opts={"paramstyle": "named"},
+    )
+
+    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(
+        {"sqlalchemy.url": DATABASE_URL},
+        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()

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():
+    ${upgrades if upgrades else "pass"}
+
+
+def downgrade():
+    ${downgrades if downgrades else "pass"}

migrations/versions/40355237ae7c_tag_migration.py

@@ -0,0 +1,41 @@
+# type: ignore
+"""Tag migration
+
+Revision ID: 40355237ae7c
+Revises: 99b5570a348e
+Create Date: 2024-06-20 13:47:53.630547
+
+"""
+import sqlalchemy as sa
+from alembic import op
+
+from artemis.config import Config
+
+# revision identifiers, used by Alembic.
+revision = "40355237ae7c"
+down_revision = "99b5570a348e"
+branch_labels = None
+depends_on = None
+DATABASE_URL = Config.Data.POSTGRES_CONN_STR
+engine = sa.create_engine(DATABASE_URL)
+
+
+def upgrade():
+    op.create_table(
+        "tag",
+        sa.Column("id", sa.Integer(), nullable=False),
+        sa.Column("tag_name", sa.String(), nullable=True),
+        sa.Column("created_at", sa.DateTime(), server_default=sa.text("NOW()"), nullable=True),
+        sa.PrimaryKeyConstraint("id"),
+    )
+    op.create_index(op.f("ix_tag_tag_name"), "tag", ["tag_name"], unique=True)
+
+    print("""Data is now being migrated. We recommend being patient as it may take some time...""")
+    op.execute("INSERT INTO tag (tag_name) SELECT tag FROM analysis UNION SELECT tag FROM task_result;")
+
+
+def downgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_index(op.f("ix_tag_tag_name"), table_name="tag")
+    op.drop_table("tag")
+    # ### end Alembic commands ###