Merge pull request #408 from LCOGT/revert-407-revert-same-block-cals

Revert "Reverting changes on how calibrations are chosen that were included for floyds"

Author: jchate6

CHANGES.md

@@ -1,8 +1,3 @@
-1.22.0 (2025-03-17)
--------------------
-- Reverted the addition of prefer-same-block-cals, check-public-cals, and prefer-same-proposal-cals
-  banzai imaging does not use them so refactoring to inject them only in floyds
-
 1.21.0 (2025-02-12)
 -------------------
 - Added the ability to change the proposal of a frame before saving

alembic/alembic.ini

@@ -0,0 +1,117 @@
+# A generic, single database configuration.
+
+[alembic]
+# path to migration scripts
+# Use forward slashes (/) also on windows to provide an os agnostic path
+script_location = 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 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 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: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 = 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
+
+
+[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
+
+# 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

alembic/db_migration.py

@@ -0,0 +1,161 @@
+# I have archived this file here even though it is not in alembic format beacuse
+# this is one of the early database migrations we did when we changed banzai to track
+# instruments and cameras rather than just telescopes. Future migrations of this type
+# will use alembic.
+
+import argparse
+
+from sqlalchemy import create_engine
+from sqlalchemy import Column, Integer, String, Date, ForeignKey, Boolean, CHAR
+from sqlalchemy.ext.declarative import declarative_base
+
+from banzai import dbs, logs
+
+logger = logs.get_logger()
+
+Base = declarative_base()
+
+
+# The five base classes below are taken from Banzai version < 0.16.0
+class CalibrationImage(Base):
+    __tablename__ = 'calimages'
+    id = Column(Integer, primary_key=True, autoincrement=True)
+    type = Column(String(30), index=True)
+    filename = Column(String(50), unique=True)
+    filepath = Column(String(100))
+    dayobs = Column(Date, index=True)
+    ccdsum = Column(String(20))
+    filter_name = Column(String(32))
+    telescope_id = Column(Integer, ForeignKey("telescopes.id"), index=True)
+
+
+class Telescope(Base):
+    __tablename__ = 'telescopes'
+    id = Column(Integer, primary_key=True, autoincrement=True)
+    site = Column(String(10), ForeignKey('sites.id'), index=True)
+    instrument = Column(String(20), index=True)
+    camera_type = Column(String(20))
+    schedulable = Column(Boolean, default=False)
+
+
+class Site(Base):
+    __tablename__ = 'sites'
+    id = Column(String(3), primary_key=True)
+    timezone = Column(Integer)
+
+
+class BadPixelMask(Base):
+    __tablename__ = 'bpms'
+    id = Column(Integer, primary_key=True, autoincrement=True)
+    telescope_id = Column(Integer, ForeignKey("telescopes.id"), index=True)
+    filename = Column(String(50))
+    filepath = Column(String(100))
+    ccdsum = Column(String(20))
+    creation_date = Column(Date)
+
+
+class PreviewImage(Base):
+    __tablename__ = 'previewimages'
+    id = Column(Integer, primary_key=True, autoincrement=True)
+    filename = Column(String(50), index=True)
+    checksum = Column(CHAR(32), index=True, default='0'*32)
+    success = Column(Boolean, default=False)
+    tries = Column(Integer, default=0)
+
+
+def create_new_db(db_address):
+    engine = create_engine(db_address)
+    dbs.Base.metadata.create_all(engine)
+
+
+def base_to_dict(base):
+    return [{key: value for key, value in row.__dict__.items() if not key.startswith('_')} for row in base]
+
+
+def change_key_name(row_list, old_key, new_key):
+    for row in row_list:
+        row[new_key] = row.pop(old_key)
+
+
+def add_rows(db_session, base, row_list, max_chunk_size=100000):
+    for i in range(0, len(row_list), max_chunk_size):
+        logger.debug("Inserting rows {a} to {b}".format(a=i+1, b=min(i+max_chunk_size, len(row_list))))
+        db_session.bulk_insert_mappings(base, row_list[i:i + max_chunk_size])
+        db_session.commit()
+
+
+def migrate_db():
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument('old_db_address',
+                        help='Old database address to be migrated: Should be in SQLAlchemy form')
+    parser.add_argument('new_db_address',
+                        help='New database address: Should be in SQLAlchemy form')
+    parser.add_argument("--log-level", default='debug', choices=['debug', 'info', 'warning',
+                                                                 'critical', 'fatal', 'error'])
+    args = parser.parse_args()
+
+    logs.set_log_level(args.log_level)
+    logger.info("Creating new DB {new_db_address} from old DB {old_db_address}".format(
+        new_db_address=args.new_db_address, old_db_address=args.old_db_address))
+    create_new_db(args.new_db_address)
+
+    with dbs.get_session(db_address=args.old_db_address) as old_db_session, dbs.get_session(db_address=args.new_db_address) as new_db_session:
+
+        # First copy sites table
+        logger.info("Querying and organizing the old Site table")
+        sites = base_to_dict(old_db_session.query(Site).all())
+        logger.info("Adding {n} rows from the old Site table to the new Site table".format(n=len(sites)))
+        add_rows(new_db_session, dbs.Site, sites)
+
+        # Move Telescope to Instrument with a couple of variable renames
+        logger.info("Querying and organizing the old Telescope table")
+        telescopes = base_to_dict(old_db_session.query(Telescope).all())
+        change_key_name(telescopes, 'instrument', 'camera')
+        change_key_name(telescopes, 'camera_type', 'type')
+        logger.info("Adding {n} rows from the old Telescope table to the new Instrument table".format(
+            n=len(telescopes)))
+        add_rows(new_db_session, dbs.Instrument, telescopes)
+
+        # Move old BPMs to CalibrationImage
+        logger.info("Querying and organizing the old BadPixelMask table")
+        bpms = base_to_dict(old_db_session.query(BadPixelMask).all())
+        for row in bpms:
+            row['type'] = 'BPM'
+            row['is_master'] = True
+            row['attributes'] = {'ccdsum': row.pop('ccdsum')}
+            del row['id']
+        change_key_name(bpms, 'creation_date', 'dateobs')
+        change_key_name(bpms, 'telescope_id', 'instrument_id')
+        # BPMs have some duplicates, remove them
+        already_seen = []
+        bpms_pruned = []
+        for row in bpms:
+            if row['filename'] not in already_seen:
+                bpms_pruned.append(row)
+                already_seen.append(row['filename'])
+        logger.info("Adding {n} rows from the old BadPixelMask table to the new CalibrationImage table".format(
+            n=len(bpms_pruned)))
+        add_rows(new_db_session, dbs.CalibrationImage, bpms_pruned)
+
+        # Convert old CalibrationImage to new type
+        logger.info("Querying and organizing the old CalibrationsImage table")
+        calibrations = base_to_dict(old_db_session.query(CalibrationImage).all())
+        for row in calibrations:
+            row['is_master'] = True
+            row['attributes'] = {'filter': row.pop('filter_name'), 'ccdsum': row.pop('ccdsum')}
+            del row['id']
+        change_key_name(calibrations, 'dayobs', 'dateobs')
+        change_key_name(calibrations, 'telescope_id', 'instrument_id')
+        logger.info("Adding {n} rows from the old CalibrationImage table to the new CalibrationImage table".format(
+            n=len(calibrations)))
+        add_rows(new_db_session, dbs.CalibrationImage, calibrations)
+
+        # Copy the PreviewImage table to ProcssedImage (attributes are all the same)
+        logger.info("Querying and organizing the old PreviewImage table")
+        preview_images = base_to_dict(old_db_session.query(PreviewImage).all())
+        logger.info("Adding {n} rows from the old PreviewImage table to the new ProcessedImage table".format(
+            n=len(preview_images)))
+        add_rows(new_db_session, dbs.ProcessedImage, preview_images)
+
+        logger.info("Finished")

alembic/migrations/env.py

@@ -0,0 +1,47 @@
+from logging.config import fileConfig
+
+import os
+from sqlalchemy import pool, create_engine
+from alembic import context
+
+# 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 = 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() -> None:
+    """Run migrations in 'online' mode.
+
+    In this scenario we need to create an Engine
+    and associate a connection with the context.
+
+    """
+    connection_url = os.getenv("DB_ADDRESS", "sqlite:///test.db")
+    connectable = create_engine(connection_url, poolclass=pool.NullPool)
+
+    with connectable.connect() as connection:
+        context.configure(
+            connection=connection, target_metadata=target_metadata
+        )
+
+        with context.begin_transaction():
+            context.run_migrations()
+
+
+run_migrations()

alembic/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"}