Issue #378: Add alembic support for database migrations

.circleci/config.yml

@@ -69,6 +69,21 @@ jobs:
             echo 'export PATH=$PWD:$PATH' >> $BASH_ENV
             source $BASH_ENV
             fastANI -h
+      - run:
+           name: install sqlite3
+           command: |
+             version=version-3.37.0
+             wget https://github.com/sqlite/sqlite/archive/refs/tags/${version}.tar.gz
+             tar xzf ${version}.tar.gz    ;#  Unpack the source tree into "sqlite"
+             mkdir bld                ;#  Build will occur in a sibling directory
+             cd bld                   ;#  Change to the build directory
+             ../sqlite-${version}/configure      ;#  Run the configure script
+             make                     ;#  Run the makefile.
+             make sqlite3.c           ;#  Build the "amalgamation" source file
+             make test                ;#  Run some tests (requires Tcl)
+             echo 'export PATH=~/repo/bld:$PATH' >> $BASH_ENV
+             source $BASH_ENV
+             echo $PATH
 
 
       - run:

.gitignore

@@ -1,5 +1,7 @@
 # Scratch directory for local testing
 scratch/
+alembic/version.txt
+*/*add_third_column.py
 
 # Mac-related dreck
 .DS_Store
@@ -72,4 +74,4 @@ venv-*
 
 # Extra documentation output
 classes_pyani.pdf
-packages_pyani.pdf
+packages_pyani.pdf

Makefile

@@ -7,6 +7,7 @@
 setup_conda:
 	@conda install --file requirements-dev.txt --yes
 	@conda install --file requirements.txt --yes
+	@conda config --add channels blaze
 	@conda install --file requirements-thirdparty.txt --yes
 	@conda install --file requirements-fastani.txt --yes
 	@conda install --file requirements-pyqt-conda.txt --yes

alembic.ini

@@ -0,0 +1,99 @@
+# A generic, single database configuration.
+
+[alembic]
+# path to migration scripts
+script_location = %(here)s/alembic
+
+# template used to generate migration files
+# file_template = %%(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 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"
+# 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. Valid values are:
+#
+# version_path_separator = :
+# version_path_separator = ;
+# version_path_separator = space
+version_path_separator = os  # default: use os.pathsep
+
+# the output encoding used when revision files
+# are written from script.py.mako
+# output_encoding = utf-8
+
+sqlalchemy.url = sqlite:///.pyani/pyanidb
+
+[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

alembic/env.py

@@ -0,0 +1,104 @@
+from logging.config import fileConfig
+
+from sqlalchemy import engine_from_config
+from sqlalchemy import pool
+
+from alembic import context
+
+import os
+
+# this is the Alembic Config object, which provides
+# access to the values within the .ini file in use.
+config = context.config
+
+dbpath = os.environ.get("PYANI_DATABASE")
+script_dir = os.environ.get("ALEMBIC_MIGRATIONS_DIR")
+url = f"sqlite:///{dbpath}"
+config.set_main_option("sqlalchemy.url", url)
+config.set_main_option("script_location", "alembic")
+
+
+# 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 = 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():
+    """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=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(
+        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():
+    # Track the current version of the database in a local file
+    # this value is used in the --dry-run option
+    version_file = os.path.join(
+        os.path.dirname(config.config_file_name), "alembic/version.txt"
+    )
+    if os.path.exists(version_file):
+        current_version = open(version_file).read().strip()
+    else:
+        current_version = None
+    context.configure(dialect_name="sqlite", starting_rev=current_version)
+
+    # Perform the dry run
+    run_migrations_offline()
+
+    # Write 'new' version to file
+    end_version = context.get_revision_argument()
+    if end_version and end_version != current_version:
+        open(version_file, "w").write(end_version)
+    elif end_version is None:
+        open(version_file, "w").write("base")
+else:
+    run_migrations_online()

alembic/version.txt

@@ -0,0 +1 @@
+65538af5a5e1

alembic/versions/92f7f6b1626e_add_fastani_columns.py

@@ -0,0 +1,123 @@
+"""add fastani columns
+
+Revision ID: 92f7f6b1626e
+Revises:
+Create Date: 2022-02-07 22:57:35.779356
+
+"""
+from alembic import op
+import sqlalchemy as sa
+import sys
+
+from sqlalchemy import (
+    Column,
+    # Table,
+    # MetaData,
+    # ForeignKey,
+    Integer,
+    # String,
+    Float,
+    # Boolean,
+    UniqueConstraint,
+)
+
+# revision identifiers, used by Alembic.
+revision = "92f7f6b1626e"
+down_revision = None
+branch_labels = None
+depends_on = None
+
+
+def upgrade():
+    # op.add_column("comparisons", sa.Column("kmersize", sa.Integer))
+    # op.add_column("comparisons", sa.Column("minmatch", sa.Float))
+    """
+    comparisons = Table(
+        "comparisons",
+        meta,
+        Column("comparisons_id", Integer, primary_key=True),
+        Column("query_id", Integer, ForeignKey("genomes.genome_id"), nullable=False),
+        Column("subject_id", Integer, ForeignKey("genomes.genome_id"), nullable=False),
+        Column("aln_length", Integer),
+        Column("sim_errs", Integer),
+        Column("identity", Float),
+        Column("cov_query", Float),
+        Column("cov_subject", Float),
+        Column("program", String),
+        Column("version", String),
+        Column("fragsize", Integer),
+        Column("maxmatch", Boolean),
+        UniqueConstraint(
+            "query_id",
+            "subject_id",
+            "program",
+            "version",
+            "fragsize",
+            "maxmatch",
+            name="base_reqs",
+        ),
+    )
+    """
+    with op.batch_alter_table("comparisons") as batch_op:
+        # batch_op.add_column(sa.Column("kmersize", sa.Integer, default=None))
+        # batch_op.add_column(sa.Column("minmatch", sa.Float, default=None))
+        batch_op.drop_constraint("base_reqs")
+        batch_op.add_column(sa.Column("kmersize", sa.Integer, default=None))
+        batch_op.add_column(sa.Column("minmatch", sa.Float, default=None))
+        batch_op.create_unique_constraint(
+            "fastani_reqs",
+            [
+                "query_id",
+                "subject_id",
+                "program",
+                "version",
+                "fragsize",
+                "maxmatch",
+                "kmersize",
+                "minmatch",
+            ],
+        )
+
+
+def downgrade():
+    # op.drop_constraint("comparisons", 'kmersize')
+    # op.drop_column("comparisons", "kmersize")
+    """
+    comparisons = Table(
+        "comparisons",
+        meta,
+        Column("comparisons_id", Integer, primary_key=True),
+        Column("query_id", Integer, ForeignKey("genomes.genome_id"), nullable=False),
+        Column("subject_id", Integer, ForeignKey("genomes.genome_id"), nullable=False),
+        Column("aln_length", Integer),
+        Column("sim_errs", Integer),
+        Column("identity", Float),
+        Column("cov_query", Float),
+        Column("cov_subject", Float),
+        Column("program", String),
+        Column("version", String),
+        Column("fragsize", Integer),
+        Column("maxmatch", Boolean),
+        Column("kmersize", Integer),
+        Column("minmatch", Float),
+        UniqueConstraint(
+            "query_id",
+            "subject_id",
+            "program",
+            "version",
+            "fragsize",
+            "maxmatch",
+            "kmersize",
+            "minmatch",
+            name="fastani_reqs",
+        ),
+    )
+    """
+    with op.batch_alter_table("comparisons") as batch_op:
+        batch_op.drop_column("kmersize")
+        batch_op.drop_column("minmatch")
+        batch_op.drop_constraint("fastani_reqs")
+        batch_op.create_unique_constraint(
+            "base_reqs",
+            ["query_id", "subject_id", "program", "version", "fragsize", "maxmatch"],
+        )