Coverage for python / lsst / daf / butler / registry / expand_data_ids.py: 23%

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/>. 

27 

28from __future__ import annotations 

29 

30from collections import defaultdict 

31from collections.abc import Iterable 

32 

33from ..dimensions import ( 

34 DataCoordinate, 

35 DimensionDataAttacher, 

36 DimensionGroup, 

37 DimensionUniverse, 

38) 

39from ..dimensions.record_cache import DimensionRecordCache 

40from ..queries import QueryFactoryFunction 

41 

42 

43def expand_data_ids( 

44 data_ids: Iterable[DataCoordinate], 

45 universe: DimensionUniverse, 

46 query_func: QueryFactoryFunction, 

47 cache: DimensionRecordCache | None, 

48) -> list[DataCoordinate]: 

49 """Expand the given data IDs to look up implied dimension values and attach 

50 dimension records. 

51 

52 Parameters 

53 ---------- 

54 data_ids : `~collections.abc.Iterable` [ `DataCoordinate` ] 

55 Data coordinates to be expanded. 

56 universe : `DimensionUniverse` 

57 Dimension universe associated with the given ``data_ids`` values. 

58 query_func : QueryFactoryFunction 

59 Function used to set up a Butler query context for looking up required 

60 information from the database. 

61 cache : `DimensionRecordCache` | None 

62 Cache containing already-known dimension records. May be `None` if a 

63 cache is not available. 

64 

65 Returns 

66 ------- 

67 expanded : `list` [ `DataCoordinate` ] 

68 List of `DataCoordinate` instances in the same order as the input 

69 values. It is guaranteed that each `DataCoordinate` has 

70 ``hasRecords()=True`` and ``hasFull()=True``. 

71 """ 

72 output = list(data_ids) 

73 

74 grouped_by_dimensions: defaultdict[DimensionGroup, list[int]] = defaultdict(list) 

75 for i, data_id in enumerate(data_ids): 

76 if not data_id.hasRecords(): 

77 grouped_by_dimensions[data_id.dimensions].append(i) 

78 

79 if not grouped_by_dimensions: 

80 # All given DataCoordinate values are already expanded. 

81 return output 

82 

83 attacher = DimensionDataAttacher( 

84 cache=cache, 

85 dimensions=DimensionGroup.union(*grouped_by_dimensions.keys(), universe=universe), 

86 ) 

87 for dimensions, indexes in grouped_by_dimensions.items(): 

88 with query_func() as query: 

89 expanded = attacher.attach(dimensions, (output[index] for index in indexes), query) 

90 for index, data_id in zip(indexes, expanded): 

91 output[index] = data_id 

92 

93 return output