Coverage for python/lsst/daf/butler/registry/_dataset_type_cache.py: 36%

41 statements  

« prev     ^ index     » next       coverage.py v7.4.4, created at 2024-04-18 09:55 +0000

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 

30__all__ = ("DatasetTypeCache",) 

31 

32from collections.abc import Iterable, Iterator 

33from typing import Generic, TypeVar 

34 

35from .._dataset_type import DatasetType 

36 

37_T = TypeVar("_T") 

38 

39 

40class DatasetTypeCache(Generic[_T]): 

41 """Cache for dataset types. 

42 

43 Notes 

44 ----- 

45 This class caches mapping of dataset type name to a corresponding 

46 `DatasetType` instance. Registry manager also needs to cache corresponding 

47 "storage" instance, so this class allows storing additional opaque object 

48 along with the dataset type. 

49 

50 In come contexts (e.g. ``resolve_wildcard``) a full list of dataset types 

51 is needed. To signify that cache content can be used in such contexts, 

52 cache defines special ``full`` flag that needs to be set by client. 

53 """ 

54 

55 def __init__(self) -> None: 

56 self._cache: dict[str, tuple[DatasetType, _T | None]] = {} 

57 self._full = False 

58 

59 @property 

60 def full(self) -> bool: 

61 """`True` if cache holds all known dataset types (`bool`).""" 

62 return self._full 

63 

64 def add(self, dataset_type: DatasetType, extra: _T | None = None) -> None: 

65 """Add one record to the cache. 

66 

67 Parameters 

68 ---------- 

69 dataset_type : `DatasetType` 

70 Dataset type, replaces any existing dataset type with the same 

71 name. 

72 extra : `Any`, optional 

73 Additional opaque object stored with this dataset type. 

74 """ 

75 self._cache[dataset_type.name] = (dataset_type, extra) 

76 

77 def set(self, data: Iterable[DatasetType | tuple[DatasetType, _T | None]], *, full: bool = False) -> None: 

78 """Replace cache contents with the new set of dataset types. 

79 

80 Parameters 

81 ---------- 

82 data : `~collections.abc.Iterable` 

83 Sequence of `DatasetType` instances or tuples of `DatasetType` and 

84 an extra opaque object. 

85 full : `bool` 

86 If `True` then ``data`` contains all known dataset types. 

87 """ 

88 self.clear() 

89 for item in data: 

90 if isinstance(item, DatasetType): 

91 item = (item, None) 

92 self._cache[item[0].name] = item 

93 self._full = full 

94 

95 def clear(self) -> None: 

96 """Remove everything from the cache.""" 

97 self._cache = {} 

98 self._full = False 

99 

100 def discard(self, name: str) -> None: 

101 """Remove named dataset type from the cache. 

102 

103 Parameters 

104 ---------- 

105 name : `str` 

106 Name of the dataset type to remove. 

107 """ 

108 self._cache.pop(name, None) 

109 

110 def get(self, name: str) -> tuple[DatasetType | None, _T | None]: 

111 """Return cached info given dataset type name. 

112 

113 Parameters 

114 ---------- 

115 name : `str` 

116 Dataset type name. 

117 

118 Returns 

119 ------- 

120 dataset_type : `DatasetType` or `None` 

121 Cached dataset type, `None` is returned if the name is not in the 

122 cache. 

123 extra : `Any` or `None` 

124 Cached opaque data, `None` is returned if the name is not in the 

125 cache or no extra info was stored for this dataset type. 

126 """ 

127 item = self._cache.get(name) 

128 if item is None: 

129 return (None, None) 

130 return item 

131 

132 def get_dataset_type(self, name: str) -> DatasetType | None: 

133 """Return dataset type given its name. 

134 

135 Parameters 

136 ---------- 

137 name : `str` 

138 Dataset type name. 

139 

140 Returns 

141 ------- 

142 dataset_type : `DatasetType` or `None` 

143 Cached dataset type, `None` is returned if the name is not in the 

144 cache. 

145 """ 

146 item = self._cache.get(name) 

147 if item is None: 

148 return None 

149 return item[0] 

150 

151 def items(self) -> Iterator[tuple[DatasetType, _T | None]]: 

152 """Return iterator for the set of items in the cache, can only be 

153 used if `full` is true. 

154 

155 Raises 

156 ------ 

157 RuntimeError 

158 Raised if ``self.full`` is `False`. 

159 """ 

160 if not self._full: 

161 raise RuntimeError("cannot call items() if cache is not full") 

162 return iter(self._cache.values())