Coverage for python/lsst/daf/butler/_column_type_info.py: 37%
61 statements
« prev ^ index » next coverage.py v7.5.0, created at 2024-04-26 02:47 -0700
« prev ^ index » next coverage.py v7.5.0, created at 2024-04-26 02:47 -0700
1# This file is part of daf_butler.
2#
3# Developed for the LSST Data Management System.
4# This product includes software developed by the LSST Project
5# (http://www.lsst.org).
6# See the COPYRIGHT file at the top-level directory of this distribution
7# for details of code ownership.
8#
9# This software is dual licensed under the GNU General Public License and also
10# under a 3-clause BSD license. Recipients may choose which of these licenses
11# to use; please see the files gpl-3.0.txt and/or bsd_license.txt,
12# respectively. If you choose the GPL option then the following text applies
13# (but note that there is still no warranty even if you opt for BSD instead):
14#
15# This program is free software: you can redistribute it and/or modify
16# it under the terms of the GNU General Public License as published by
17# the Free Software Foundation, either version 3 of the License, or
18# (at your option) any later version.
19#
20# This program is distributed in the hope that it will be useful,
21# but WITHOUT ANY WARRANTY; without even the implied warranty of
22# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
23# GNU General Public License for more details.
24#
25# You should have received a copy of the GNU General Public License
26# along with this program. If not, see <http://www.gnu.org/licenses/>.
28from __future__ import annotations
30__all__ = ("ColumnTypeInfo", "LogicalColumn")
32import dataclasses
33import datetime
34from collections.abc import Iterable
35from typing import cast
37import astropy.time
38import sqlalchemy
39from lsst.daf.relation import ColumnTag, sql
41from . import ddl
42from ._column_tags import DatasetColumnTag, DimensionKeyColumnTag, DimensionRecordColumnTag
43from .dimensions import Dimension, DimensionUniverse
44from .timespan_database_representation import TimespanDatabaseRepresentation
46LogicalColumn = sqlalchemy.sql.ColumnElement | TimespanDatabaseRepresentation
47"""A type alias for the types used to represent columns in SQL relations.
49This is the butler specialization of the `lsst.daf.relation.sql.LogicalColumn`
50concept.
51"""
54@dataclasses.dataclass(frozen=True, eq=False)
55class ColumnTypeInfo:
56 """A struct that aggregates information about column types that can differ
57 across data repositories due to `Registry` and dimension configuration.
58 """
60 timespan_cls: type[TimespanDatabaseRepresentation]
61 """An abstraction around the column type or types used for timespans by
62 this database engine.
63 """
65 universe: DimensionUniverse
66 """Object that manages the definitions of all dimension and dimension
67 elements.
68 """
70 dataset_id_spec: ddl.FieldSpec
71 """Field specification for the dataset primary key column.
72 """
74 run_key_spec: ddl.FieldSpec
75 """Field specification for the `~CollectionType.RUN` primary key column.
76 """
78 ingest_date_dtype: type[ddl.AstropyTimeNsecTai] | type[sqlalchemy.TIMESTAMP]
79 """Type of the ``ingest_date`` column, can be either
80 `~lsst.daf.butler.ddl.AstropyTimeNsecTai` or `sqlalchemy.TIMESTAMP`.
81 """
83 @property
84 def ingest_date_pytype(self) -> type:
85 """Python type corresponding to ``ingest_date`` column type.
87 Returns
88 -------
89 `type`
90 The Python type.
91 """
92 if self.ingest_date_dtype is ddl.AstropyTimeNsecTai:
93 return astropy.time.Time
94 elif self.ingest_date_dtype is sqlalchemy.TIMESTAMP:
95 return datetime.datetime
96 else:
97 raise TypeError(f"Unexpected type of ingest_date_dtype: {self.ingest_date_dtype}")
99 def make_relation_table_spec(
100 self,
101 columns: Iterable[ColumnTag],
102 unique_keys: Iterable[Iterable[ColumnTag]] = (),
103 ) -> ddl.TableSpec:
104 """Create a specification for a table with the given relation columns.
106 This is used primarily to create temporary tables for query results.
108 Parameters
109 ----------
110 columns : `~collections.abc.Iterable` [ `ColumnTag` ]
111 Iterable of column identifiers.
112 unique_keys : `~collections.abc.Iterable` \
113 [ `~collections.abc.Iterable` [ `ColumnTag` ] ]
114 Unique constraints to add the table, as a nested iterable of
115 (first) constraint and (second) the columns within that constraint.
117 Returns
118 -------
119 spec : `ddl.TableSpec`
120 Specification for a table.
121 """
122 result = ddl.TableSpec(fields=())
123 columns = list(columns)
124 if not columns:
125 result.fields.add(
126 ddl.FieldSpec(
127 sql.Engine.EMPTY_COLUMNS_NAME,
128 dtype=sql.Engine.EMPTY_COLUMNS_TYPE,
129 nullable=True,
130 )
131 )
132 for tag in columns:
133 match tag:
134 case DimensionKeyColumnTag(dimension=dimension_name):
135 result.fields.add(
136 dataclasses.replace(
137 cast(Dimension, self.universe[dimension_name]).primaryKey,
138 name=tag.qualified_name,
139 primaryKey=False,
140 nullable=False,
141 )
142 )
143 case DimensionRecordColumnTag(column="region"):
144 result.fields.add(ddl.FieldSpec.for_region(tag.qualified_name))
145 case DimensionRecordColumnTag(column="timespan") | DatasetColumnTag(column="timespan"):
146 result.fields.update(
147 self.timespan_cls.makeFieldSpecs(nullable=True, name=tag.qualified_name)
148 )
149 case DimensionRecordColumnTag(element=element_name, column=column):
150 element = self.universe[element_name]
151 result.fields.add(
152 dataclasses.replace(
153 element.RecordClass.fields.facts[column],
154 name=tag.qualified_name,
155 nullable=True,
156 primaryKey=False,
157 )
158 )
159 case DatasetColumnTag(column="dataset_id"):
160 result.fields.add(
161 dataclasses.replace(
162 self.dataset_id_spec, name=tag.qualified_name, primaryKey=False, nullable=False
163 )
164 )
165 case DatasetColumnTag(column="run"):
166 result.fields.add(
167 dataclasses.replace(
168 self.run_key_spec, name=tag.qualified_name, primaryKey=False, nullable=False
169 )
170 )
171 case DatasetColumnTag(column="ingest_date"):
172 result.fields.add(
173 ddl.FieldSpec(tag.qualified_name, dtype=self.ingest_date_dtype, nullable=False)
174 )
175 case _:
176 raise TypeError(f"Unexpected column tag {tag}.")
177 for unique_key in unique_keys:
178 result.unique.add(tuple(tag.qualified_name for tag in unique_key))
179 return result