Merge pull request #6 from hotosm/alembic-setup

Alembic migrations setup

docker-compose.yml

@@ -62,6 +62,23 @@ services:
     networks:
       - dtm-network
 
+  migrations:
+    build:
+      context: .
+      dockerfile: src/backend/Dockerfile
+    container_name: dtm_migrations
+    volumes:
+      - ./src/backend:/project/src/backend
+    depends_on:
+      - web
+      - db
+    env_file:
+      - .env
+    networks:
+      - dtm-network
+    entrypoint: ["pdm", "run", "alembic", "upgrade", "head"]
+    restart: "no"
+
 networks:
   dtm-network:
     name: dtm-network

src/backend/Dockerfile

@@ -63,6 +63,9 @@ WORKDIR /project/src/backend/
 # Set environment PATH
 ENV PATH="/project/.venv/bin:$PATH"
 
+# Install PDM in runtime stage
+RUN pip install -U pdm
+
 # Copy the source files to the final image
 COPY src /project/src
 

src/backend/alembic.ini

@@ -0,0 +1,121 @@
+# A generic, single database configuration.
+
+[alembic]
+# path to migration scripts
+script_location = app/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>=3.9 or backports.zoneinfo library.
+# Any required deps can installed by adding `alembic[tz]` to the pip requirements
+# string value is passed to ZoneInfo()
+# 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 app/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:app/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.
+
+# set to 'true' to search source files recursively
+# in each "version_locations" directory
+# new in Alembic version 1.10
+# recursive_version_locations = false
+
+# the output encoding used when revision files
+# are written from script.py.mako
+# output_encoding = utf-8
+
+sqlalchemy.url =
+
+
+[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
+
+# lint with attempts to fix using "ruff" - use the exec runner, execute a binary
+# hooks = ruff
+# ruff.type = exec
+# ruff.executable = %(here)s/.venv/bin/ruff
+# ruff.options = --fix REVISION_SCRIPT_FILENAME
+
+# Custom param that enables us to specify tables to ignore when determining migrations
+[alembic:exclude]
+tables = spatial_ref_sys
+
+
+# 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/backend/app/config.py

@@ -50,10 +50,10 @@ def assemble_cors_origins(
     API_PREFIX: str = "/"
     SECRET_KEY: str = secrets.token_urlsafe(32)
 
-    POSTGRES_HOST: Optional[str] = "dtm-db"
+    POSTGRES_HOST: Optional[str] = "db"
     POSTGRES_USER: Optional[str] = "dtm"
     POSTGRES_PASSWORD: Optional[str] = "dtm"
-    POSTGRES_DB: Optional[str] = "dtm"
+    POSTGRES_DB: Optional[str] = "datm-db"
 
     DTM_DB_URL: Optional[PostgresDsn] = None
 

src/backend/app/main.py

@@ -73,8 +73,6 @@ def get_application() -> FastAPI:
     # Set custom logger
     _app.logger = get_logger()
 
-    print("cors = ", settings.EXTRA_CORS_ORIGINS)
-
     _app.add_middleware(
         CORSMiddleware,
         allow_origins=settings.EXTRA_CORS_ORIGINS,

src/backend/app/migrations/README

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

src/backend/app/migrations/alembic_headers.py

@@ -0,0 +1,30 @@
+"""Helpers for alembic migrate and downgrade."""
+
+from alembic import op
+from sqlalchemy import engine_from_config
+from sqlalchemy.engine import reflection
+
+
+def table_does_not_exist(table, schema=None):
+    """Handle tables that do not exist."""
+    config = op.get_context().config
+    engine = engine_from_config(
+        config.get_section(config.config_ini_section), prefix="sqlalchemy."
+    )
+    insp = reflection.Inspector.from_engine(engine)
+    return insp.has_table(table, schema) is False
+
+
+def table_has_column(table, column):
+    """Handle tables when column already exists."""
+    config = op.get_context().config
+    engine = engine_from_config(
+        config.get_section(config.config_ini_section), prefix="sqlalchemy."
+    )
+    insp = reflection.Inspector.from_engine(engine)
+    has_column = False
+    for col in insp.get_columns(table):
+        if column not in col["name"]:
+            continue
+        has_column = True
+    return has_column

src/backend/app/migrations/env.py

@@ -0,0 +1,111 @@
+from logging import getLogger
+
+from logging.config import fileConfig
+
+from sqlalchemy import engine_from_config
+from sqlalchemy import pool
+from app.db.db_models import Base
+from geoalchemy2 import alembic_helpers
+from alembic import context
+from app.config import settings
+
+# 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.
+
+config = context.config
+config.set_main_option("sqlalchemy.url", settings.DTM_DB_URL.unicode_string())
+
+
+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 mymodel
+# target_metadata = mymodel.Base.metadata
+target_metadata = Base.metadata
+exclude_tables = config.get_section("alembic:exclude").get("tables", "").split(",")
+
+log = getLogger(__name__)
+
+# 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 include_object(object, name, type_, reflected, compare_to):
+    """Ignore our excluded tables in the autogen sweep."""
+    if type_ == "table" and name in exclude_tables:
+        return False
+    else:
+        return alembic_helpers.include_object(
+            object, name, type_, reflected, compare_to
+        )
+
+
+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.
+
+    """
+    log.info("Running offline migrations")
+
+    url = config.get_main_option("sqlalchemy.url")
+    context.configure(
+        url=url,
+        include_object=include_object,
+        target_metadata=target_metadata,
+        literal_binds=True,
+        dialect_opts={"paramstyle": "named"},
+    )
+
+    with context.begin_transaction():
+        context.run_migrations()
+
+    log.info("Complete offline 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.
+
+    """
+    log.info("Running online migrations")
+
+    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,
+            include_object=include_object,
+            target_metadata=target_metadata,
+        )
+
+        with context.begin_transaction():
+            context.run_migrations()
+
+    log.info("Complete online migrations")
+
+
+if context.is_offline_mode():
+    run_migrations_offline()
+else:
+    run_migrations_online()

src/backend/app/migrations/script.py.mako

@@ -0,0 +1,26 @@
+"""${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:
+    ${upgrades if upgrades else "pass"}
+
+
+def downgrade() -> None:
+    ${downgrades if downgrades else "pass"}