add database migration tooling with alembic

alembic.ini

@@ -0,0 +1,148 @@
+# A generic, single database configuration.
+
+[alembic]
+# path to migration scripts.
+# this is typically a path given in POSIX (e.g. forward slashes)
+# format, relative to the token %(here)s which refers to the location of this
+# ini file
+script_location = %(here)s/alembic
+
+# 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
+# Or organize into date-based subdirectories (requires recursive_version_locations = true)
+# file_template = %%(year)d/%%(month).2d/%%(day).2d_%%(hour).2d%%(minute).2d_%%(second).2d_%%(rev)s_%%(slug)s
+
+# sys.path path, will be prepended to sys.path if present.
+# defaults to the current working directory.  for multiple paths, the path separator
+# is defined by "path_separator" below.
+prepend_sys_path = .
+
+
+# timezone to use when rendering the date within the migration file
+# as well as the filename.
+# If specified, requires the tzdata library which can be 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 <script_location>/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 "path_separator"
+# below.
+# version_locations = %(here)s/bar:%(here)s/bat:%(here)s/alembic/versions
+
+# path_separator; This indicates what character is used to split lists of file
+# paths, including version_locations and prepend_sys_path within configparser
+# files such as alembic.ini.
+# The default rendered in new alembic.ini files is "os", which uses os.pathsep
+# to provide os-dependent path splitting.
+#
+# Note that in order to support legacy alembic.ini files, this default does NOT
+# take place if path_separator is not present in alembic.ini.  If this
+# option is omitted entirely, fallback logic is as follows:
+#
+# 1. Parsing of the version_locations option falls back to using the legacy
+#    "version_path_separator" key, which if absent then falls back to the legacy
+#    behavior of splitting on spaces and/or commas.
+# 2. Parsing of the prepend_sys_path option falls back to the legacy
+#    behavior of splitting on spaces, commas, or colons.
+#
+# Valid values for path_separator are:
+#
+# path_separator = :
+# path_separator = ;
+# path_separator = space
+# path_separator = newline
+#
+# Use os.pathsep. Default configuration used for new projects.
+path_separator = os
+
+# 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
+
+# database URL.  This is consumed by the user-maintained env.py script only.
+# other means of configuring database URLs may be customized within the env.py
+# file.
+sqlalchemy.url = sqlite:///data/db/wce_grunderfassung.db
+
+[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 module runner, against the "ruff" module
+# hooks = ruff
+# ruff.type = module
+# ruff.module = ruff
+# ruff.options = check --fix REVISION_SCRIPT_FILENAME
+
+# Alternatively, use the exec runner to execute a binary found on your PATH
+# hooks = ruff
+# ruff.type = exec
+# ruff.executable = ruff
+# ruff.options = check --fix REVISION_SCRIPT_FILENAME
+
+# Logging configuration.  This is also consumed by the user-maintained
+# env.py script only.
+[loggers]
+keys = root,sqlalchemy,alembic
+
+[handlers]
+keys = console
+
+[formatters]
+keys = generic
+
+[logger_root]
+level = WARNING
+handlers = console
+qualname =
+
+[logger_sqlalchemy]
+level = WARNING
+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

alembic/README

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

alembic/env.py

@@ -0,0 +1,80 @@
+from logging.config import fileConfig
+from pathlib import Path
+
+import dotenv
+from alembic import context
+from sqlalchemy import engine_from_config, pool
+
+from wce_crm import constants, db
+
+# 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.
+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 = db.MD_MAIN
+
+# 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.
+config.set_main_option("sqlalchemy.url", f"sqlite:///{constants.Config.DB_PATH_MAIN}")
+
+
+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()

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, Sequence[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"}

alembic/versions/5f2af5179c47_added_new_column_and_renamed_table_for_.py

@@ -0,0 +1,91 @@
+"""added new column and renamed table for initial recording
+
+Revision ID: 5f2af5179c47
+Revises:
+Create Date: 2026-06-17 16:06:46.421562
+
+"""
+
+from typing import Sequence, Union
+
+import sqlalchemy as sa
+from alembic import op
+
+# revision identifiers, used by Alembic.
+revision: str = "5f2af5179c47"
+down_revision: Union[str, Sequence[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.rename_table("grunderfassung_unternehmen", "grunderfassung")
+    op.add_column(
+        "grunderfassung",
+        sa.Column("Metadaten_wiedereintrittsdatum", sa.Date, nullable=True, default=None),
+    )
+    # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    """Downgrade schema."""
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.create_table(
+        "grunderfassung_unternehmen",
+        sa.Column("erfassung_id", sa.INTEGER(), nullable=False),
+        sa.Column("Metadaten_erstellung", sa.DATETIME(), nullable=True),
+        sa.Column("Metadaten_aktualisierung", sa.DATETIME(), nullable=True),
+        sa.Column("Metadaten_nutzer", sa.VARCHAR(length=20), nullable=True),
+        sa.Column("Arbeitserfahrung", sa.TEXT(), nullable=True),
+        sa.Column("Grunderfassung_fallnummer", sa.TEXT(), nullable=True),
+        sa.Column("Grunderfassung_notiz", sa.TEXT(), nullable=True),
+        sa.Column("HoehereBildung", sa.TEXT(), nullable=True),
+        sa.Column("Kontaktperson__KP_adresse", sa.TEXT(), nullable=True),
+        sa.Column("Kontaktperson__KP_anrede_anschrift", sa.TEXT(), nullable=True),
+        sa.Column("Kontaktperson__KP_email", sa.TEXT(), nullable=True),
+        sa.Column("Kontaktperson__KP_festnetznummer", sa.TEXT(), nullable=True),
+        sa.Column("Kontaktperson__KP_funktion_beziehung", sa.TEXT(), nullable=True),
+        sa.Column("Kontaktperson__KP_mobilfunknummer", sa.TEXT(), nullable=True),
+        sa.Column("Kontaktperson__KP_name", sa.TEXT(), nullable=True),
+        sa.Column("Kontaktperson__KP_name_partner", sa.TEXT(), nullable=True),
+        sa.Column("Kontaktperson__KP_titel", sa.TEXT(), nullable=True),
+        sa.Column("Kontaktperson__KP_vorname", sa.TEXT(), nullable=True),
+        sa.Column("Partnersuche__kanal_aufmerksamkeit", sa.TEXT(), nullable=True),
+        sa.Column("Partnersuche__person_suche", sa.INTEGER(), nullable=True),
+        sa.Column("Partnersuche__un_suche", sa.INTEGER(), nullable=True),
+        sa.Column("Projektrelevanz__relevanz", sa.TEXT(), nullable=True),
+        sa.Column("Projektrelevanz__foerderperiode", sa.TEXT(), nullable=True),
+        sa.Column("Schulbildung", sa.TEXT(), nullable=True),
+        sa.Column("Sprachkenntnisse", sa.TEXT(), nullable=True),
+        sa.Column("Stammdaten__PLZ", sa.TEXT(), nullable=True),
+        sa.Column("Stammdaten__anrede_anschrift", sa.TEXT(), nullable=True),
+        sa.Column("Stammdaten__anzahl_kinder__alter", sa.TEXT(), nullable=True),
+        sa.Column("Stammdaten__anzahl_kinder__anzahl", sa.INTEGER(), nullable=True),
+        sa.Column("Stammdaten__aufenthaltsort", sa.TEXT(), nullable=True),
+        sa.Column("Stammdaten__bundesland", sa.TEXT(), nullable=True),
+        sa.Column("Stammdaten__land", sa.TEXT(), nullable=True),
+        sa.Column("Stammdaten__email", sa.TEXT(), nullable=True),
+        sa.Column("Stammdaten__familienstand", sa.TEXT(), nullable=True),
+        sa.Column("Stammdaten__festnetznummer", sa.TEXT(), nullable=True),
+        sa.Column("Stammdaten__geburtsdatum", sa.DATE(), nullable=True),
+        sa.Column("Stammdaten__hausnummer", sa.TEXT(), nullable=True),
+        sa.Column("Stammdaten__herkunftsland", sa.TEXT(), nullable=True),
+        sa.Column("Stammdaten__mobilfunknummer", sa.TEXT(), nullable=True),
+        sa.Column("Stammdaten__name", sa.TEXT(), nullable=True),
+        sa.Column("Stammdaten__ort", sa.TEXT(), nullable=True),
+        sa.Column("Stammdaten__rueckkehrer", sa.BOOLEAN(), nullable=True),
+        sa.Column("Stammdaten__staatsangehoerigkeit", sa.TEXT(), nullable=True),
+        sa.Column("Stammdaten__strasse", sa.TEXT(), nullable=True),
+        sa.Column("Stammdaten__titel", sa.TEXT(), nullable=True),
+        sa.Column("Stammdaten__vorname", sa.TEXT(), nullable=True),
+        sa.Column("WeitereInfos__WI_arbeitsstatus", sa.TEXT(), nullable=True),
+        sa.Column("WeitereInfos__WI_aufenthaltstitel", sa.TEXT(), nullable=True),
+        sa.Column("WeitereInfos__WI_deutsch_sprache", sa.TEXT(), nullable=True),
+        sa.Column("WeitereInfos__WI_gueltigkeit_aufenthaltstitel", sa.DATE(), nullable=True),
+        sa.Column("WeitereInfos__WI_meldung_institution", sa.TEXT(), nullable=True),
+        sa.PrimaryKeyConstraint("erfassung_id"),
+    )
+    op.drop_table("grunderfassung")
+    # ### end Alembic commands ###

deployment/.env

@@ -2,3 +2,4 @@ DOPT_STOP_FOLDER_NAME=python
 DOPT_DB_CRM=data/wce_crm.db
 DOPT_DB_MAIN=data/wce_grunderfassung.db
 DOPT_PATH_LOGGING=data/logs
+DOPT_ALEMBIC_BASE=python/alembic

pdm.lock

@@ -5,7 +5,7 @@
 groups = ["default", "dev", "lint", "nb", "tests"]
 strategy = ["inherit_metadata"]
 lock_version = "4.5.0"
-content_hash = "sha256:25812ee6ba42033e1341c1799716828d8582092826c1d0889ea775a0f5c548a2"
+content_hash = "sha256:bde2f66706034b9c34c6794bf192b44db6e116a287938d88c90c751a2666bdf7"
 
 [[metadata.targets]]
 requires_python = ">=3.11,<3.14"
@@ -152,6 +152,23 @@ files = [
     {file = "aiosignal-1.4.0.tar.gz", hash = "sha256:f47eecd9468083c2029cc99945502cb7708b082c232f9aca65da147157b251c7"},
 ]
 
+[[package]]
+name = "alembic"
+version = "1.18.4"
+requires_python = ">=3.10"
+summary = "A database migration tool for SQLAlchemy."
+groups = ["default"]
+dependencies = [
+    "Mako",
+    "SQLAlchemy>=1.4.23",
+    "tomli; python_version < \"3.11\"",
+    "typing-extensions>=4.12",
+]
+files = [
+    {file = "alembic-1.18.4-py3-none-any.whl", hash = "sha256:a5ed4adcf6d8a4cb575f3d759f071b03cd6e5c7618eb796cb52497be25bfe19a"},
+    {file = "alembic-1.18.4.tar.gz", hash = "sha256:cb6e1fd84b6174ab8dbb2329f86d631ba9559dd78df550b57804d607672cedbc"},
+]
+
 [[package]]
 name = "annotated-doc"
 version = "0.0.4"
@@ -1845,7 +1862,7 @@ name = "mako"
 version = "1.3.11"
 requires_python = ">=3.8"
 summary = "A super-fast templating language that borrows the best ideas from the existing templating languages."
-groups = ["dev"]
+groups = ["default", "dev"]
 dependencies = [
     "MarkupSafe>=0.9.2",
 ]
@@ -1895,7 +1912,7 @@ name = "markupsafe"
 version = "3.0.3"
 requires_python = ">=3.9"
 summary = "Safely add untrusted strings to HTML/XML markup."
-groups = ["dev", "nb"]
+groups = ["default", "dev", "nb"]
 files = [
     {file = "markupsafe-3.0.3-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:1cc7ea17a6824959616c525620e387f6dd30fec8cb44f649e31712db02123dad"},
     {file = "markupsafe-3.0.3-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:4bd4cd07944443f5a265608cc6aab442e4f74dff8088b0dfc8238647b8f6ae9a"},

pyproject.toml

@@ -5,7 +5,7 @@ description = "GUI for CRM of NAFKA project with WCE"
 authors = [
     {name = "d-opt GmbH, resp. Florian Förster", email = "f.foerster@d-opt.com"},
 ]
-dependencies = ["pyside6>=6.11.0", "sqlalchemy[asyncio]>=2.0.50", "polars>=1.40.1", "dopt-basics>=0.2.6", "pydantic[email]>=2.13.4", "babel>=2.18.0", "python-dotenv>=1.2.2"]
+dependencies = ["pyside6>=6.11.0", "sqlalchemy[asyncio]>=2.0.50", "polars>=1.40.1", "dopt-basics>=0.2.6", "pydantic[email]>=2.13.4", "babel>=2.18.0", "python-dotenv>=1.2.2", "alembic>=1.18.4"]
 requires-python = "<3.14,>=3.11"
 readme = "README.md"
 license = {text = "LicenseRef-Proprietary"}

scripts/alembic_revision.ps1

@@ -0,0 +1,5 @@
+param(
+    [string]$Message
+)
+
+pdm run alembic revision --autogenerate -m $Message

src/wce_crm/README.md

@@ -5,3 +5,4 @@
 - DOPT_DB_CRM: path to CRM database, relative to base path
 - DOPT_DB_MAIN: path to main database, relative to base path
 - DOPT_PATH_LOGGING: path to logging folder, relative to base path
+- DOPT_ALEMBIC_BASE: path to all relevant alembic file

src/wce_crm/constants.py

@@ -24,3 +24,4 @@ class Config:
     )
     PATH_LOGGING: Path = BASE_PATH / os.getenv("DOPT_PATH_LOGGING", "data/d-opt.log")
     LOG_FILENAME: str = "dopt.log"
+    ALEMBIC_PATH: Path = BASE_PATH / os.getenv("DOPT_ALEMBIC_BASE", "python/alembic")

src/wce_crm/db.py

@@ -13,6 +13,7 @@ from wce_crm import constants
 from wce_crm import types as t
 
 
+# // declarations
 class SafeDateTime(TypeDecorator):
     """Cleans non-standard ISO strings before parsing."""
 
@@ -57,8 +58,8 @@ class UTCDateTime(TypeDecorator):
         return value
 
 
-md_crm = sql.MetaData()
+MD_CRM = sql.MetaData()
-md_main = sql.MetaData()
+MD_MAIN = sql.MetaData()
 ENGINE = sql.create_engine(f"sqlite:///{constants.Config.DB_PATH_MAIN}")
 
 # ---------- OLD "Kontaktliste" ----------
@@ -141,7 +142,7 @@ ENGINE = sql.create_engine(f"sqlite:///{constants.Config.DB_PATH_MAIN}")
 
 ext_crm_master: sql.Table = Table(
     "Master",
-    md_crm,
+    MD_CRM,
     Column("ma_id", sql.Integer, nullable=False, unique=True),
     Column("wce_id", sql.ForeignKey("Nutzer.wce_id")),
     Column("ma_unternehmensname", sql.Text, nullable=True),
@@ -218,7 +219,7 @@ DF_CRM_MASTER = get_ext_crm_master(constants.Config.DB_PATH_CRM)
 
 ext_crm_nutzer: sql.Table = Table(
     "Nutzer",
-    md_crm,
+    MD_CRM,
     Column("wce_id", sql.Integer, nullable=False, unique=True),
     Column("wce_name", sql.Text, nullable=True),
     Column("wce_vorname", sql.Text, nullable=True),
@@ -246,7 +247,7 @@ ext_crm_nutzer_schema: t.PolarsSchema = {
 
 ext_crm_contact_person: sql.Table = Table(
     "Ansprechpartner",
-    md_crm,
+    MD_CRM,
     Column("an_id", sql.Integer, nullable=False, unique=True),
     Column("ma_id", sql.ForeignKey("Master.ma_id")),
     Column("wce_id", sql.ForeignKey("Nutzer.wce_id")),
@@ -325,7 +326,7 @@ DF_CONTACT_PERSON = get_ext_crm_contact_person(constants.Config.DB_PATH_CRM)
 
 grunderfassung: sql.Table = Table(
     "grunderfassung",
-    md_main,
+    MD_MAIN,
     Column(
         "erfassung_id",
         sql.Integer,
@@ -398,4 +399,4 @@ grunderfassung: sql.Table = Table(
     Column("WeitereInfos__WI_meldung_institution", sql.Text, nullable=True),
 )
 
-md_main.create_all(ENGINE)
+MD_MAIN.create_all(ENGINE)

src/wce_crm/db_migration.py

@@ -0,0 +1,36 @@
+from alembic import command
+from alembic.config import Config
+
+from wce_crm import constants
+from wce_crm.logging import logger_base as logger
+
+
+def check_and_run_migrations() -> None:
+    logger.info("[DB migration - Alembic] Start...")
+    alembic_base_folder = constants.Config.ALEMBIC_PATH
+    alembic_ini_file = alembic_base_folder / "alembic.ini"
+    alembic_working_dir = alembic_base_folder / "alembic"
+
+    assert alembic_ini_file.exists(), "Alembic INI file not found"
+    assert alembic_working_dir.exists(), "Alembic working dir not found"
+    assert alembic_working_dir.is_dir(), "Alembic working dir is not a directory"
+
+    logger.info("[DB migration - Alembic] Initialise config...")
+    alembic_cfg = Config(alembic_ini_file)
+    alembic_cfg.set_main_option("script_location", str(alembic_working_dir))
+
+    logger.info("[DB migration - Alembic] Run...")
+    try:
+        command.upgrade(alembic_cfg, "head")
+        logger.info("[DB migration - Alembic] Database up-to-date.")
+    except Exception as err:
+        logger.info(
+            "[DB migration - Alembic] An error occurred during the migration:\n%s",
+            err,
+            stack_info=True,
+        )
+
+
+if __name__ == "__main__":
+    # start migration process before app start
+    check_and_run_migrations()