Release 0.15.0

.github/pull_request_template.md

@@ -3,5 +3,6 @@
 
 
 ## TODO:
+- [ ] ❗ If this PR includes a new database schema migration, following steps are completed: (README)[README.md]
 - [ ] Version of pepdbagent updated in `__version__.py` file
 - [ ] Changelog updated

.github/workflows/run-pytest.yml

@@ -15,6 +15,7 @@ jobs:
         python-version: ["3.10", "3.13"]
         os: [ubuntu-latest] # can't use macOS when using service containers or container jobs
     runs-on: ${{ matrix.os }}
+
     services:
         postgres:
           image: postgres

README.md

@@ -48,11 +48,62 @@ from bbconf import BedBaseAgent
 agent = BedBaseAgent(config="config.yaml")
 
 # Access submodules
-agent.bed        # BED file operations
-agent.bedset     # BED set operations
-agent.objects    # Generic object/file operations
+agent.bed  # BED file operations
+agent.bedset  # BED set operations
+agent.objects  # Generic object/file operations
 
 # Get platform statistics
 stats = agent.get_stats()
 print(stats.bedfiles_number, stats.bedsets_number)
 ```
+
+## Database migrations
+
+`bbconf` uses [Alembic](https://alembic.sqlalchemy.org/) to version the database
+schema. The migration scripts live in `bbconf/alembic`, and `alembic.ini` (repo
+root) is used for local CLI work. The first (baseline) revision is
+`8b0b706d0827`; it reproduces exactly the schema that `Base.metadata.create_all()`
+builds, including the `pg_trgm` extension and the trigram / partial / expression
+indexes.
+
+To update schema for desirable database, use different database url in `alembic.ini`, 
+otherwise run test database
+
+### Creating a new revision
+
+After changing the models in `bbconf/db_utils.py`:
+
+```bash
+alembic revision --autogenerate -m "Describe your change"
+```
+
+Review the generated file. Alembic cannot autogenerate a few constructs used by
+bbconf — the `pg_trgm` extension and expression-based indexes may need a manual
+`op.execute(...)` — so always check the diff before committing.
+
+### Applying migrations
+
+```bash
+alembic upgrade head      # upgrade to the latest revision
+alembic downgrade -1      # roll back one revision
+alembic current           # show the DB's current revision
+```
+
+### Running migrations automatically
+
+To upgrade the database to `head` automatically when `bbconf` starts, set
+`run_migrations: true` under the `database` section of the config file:
+
+```yaml
+database:
+  host: localhost
+  port: 5432
+  user: postgres
+  password: docker
+  database: bedbase
+  run_migrations: true
+```
+
+> **Note:** enable this only after the database has been stamped/upgraded to a
+> known revision. Turning it on against an un-stamped existing database will fail
+> on startup, because the baseline revision creates tables that already exist.

alembic.ini

@@ -0,0 +1,128 @@
+# A generic, single database configuration.
+#
+# This file is used only for local development / CLI work
+# (e.g. `alembic revision --autogenerate`, `alembic upgrade head`).
+# At runtime, bbconf builds the Alembic config programmatically in
+# `BaseEngine.run_db_migration()` and does NOT read this file.
+
+[alembic]
+# path to migration scripts
+# Use forward slashes (/) also on windows to provide an os agnostic path
+script_location = ./bbconf/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
+
+# 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 and tzdata 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 alembic/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:alembic/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 = newline
+#
+# Use os.pathsep. Default configuration used for new projects.
+version_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
+
+# Local development connection string. Override with `-x` or edit as needed.
+# Runtime migrations use the URL built from the bbconf config instead.
+
+### !!!! Change this code to desirable database!!!!
+sqlalchemy.url = postgresql+psycopg://postgres:docker@localhost:5432/bedbase
+
+
+[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 = check --fix REVISION_SCRIPT_FILENAME
+
+# Logging configuration
+[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

bbconf/alembic/README

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

bbconf/alembic/env.py

@@ -0,0 +1,77 @@
+from logging.config import fileConfig
+
+from alembic import context
+from sqlalchemy import engine_from_config, pool
+
+# 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.
+# Importing from bbconf.db_utils also registers the custom @compiles types
+# (BIGSERIAL, JSON->JSONB, ARRAY) and the pg_trgm extension DDL event, so the
+# metadata compiles to exactly the same DDL that create_all() produces.
+from bbconf.db_utils import Base
+
+target_metadata = Base.metadata
+
+# 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()

bbconf/alembic/script.py.mako

@@ -0,0 +1,28 @@
+"""${message}
+
+Revision ID: ${up_revision}
+Revises: ${down_revision | comma,n}
+Create Date: ${create_date}
+
+"""
+from typing import Sequence, Union
+
+import sqlalchemy as sa
+from alembic import op
+${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:
+    """Upgrade schema."""
+    ${upgrades if upgrades else "pass"}
+
+
+def downgrade() -> None:
+    """Downgrade schema."""
+    ${downgrades if downgrades else "pass"}

bbconf/alembic/versions/845d978eac7d_added_genomic_distribution_json_plots.py

@@ -0,0 +1,60 @@
+"""Added genomic distribution json plots
+
+Revision ID: 845d978eac7d
+Revises: 8b0b706d0827
+Create Date: 2026-08-16 18:02:03.058352
+
+"""
+
+from typing import Sequence, Union
+
+import sqlalchemy as sa
+from alembic import op
+from sqlalchemy.dialects import postgresql
+
+# revision identifiers, used by Alembic.
+revision: str = "845d978eac7d"
+down_revision: Union[str, None] = "8b0b706d0827"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    """Upgrade schema."""
+
+    op.drop_column("bed", "pephub")
+    op.add_column(
+        "bed_stats",
+        sa.Column(
+            "distributions",
+            postgresql.JSONB(astext_type=sa.Text()),
+            nullable=True,
+            comment="Full distribution arrays from gtars genomicdist (JSONB)",
+        ),
+    )
+    op.add_column(
+        "bedsets",
+        sa.Column(
+            "bedset_stats",
+            postgresql.JSONB(astext_type=sa.Text()),
+            nullable=True,
+            comment="Pre-aggregated distribution statistics from gtars (JSONB)",
+        ),
+    )
+
+
+def downgrade() -> None:
+    """Downgrade schema."""
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_column("bedsets", "bedset_stats")
+    op.drop_column("bed_stats", "distributions")
+    op.add_column(
+        "bed",
+        sa.Column(
+            "pephub",
+            sa.BOOLEAN(),
+            autoincrement=False,
+            nullable=False,
+            comment="Whether sample was added to pephub",
+        ),
+    )