Coverage for python/lsst/daf/butler/registry/nameShrinker.py: 40%

21 statements  

« prev     ^ index     » next       coverage.py v6.4.4, created at 2022-09-15 09:40 +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 program is free software: you can redistribute it and/or modify 

10# it under the terms of the GNU General Public License as published by 

11# the Free Software Foundation, either version 3 of the License, or 

12# (at your option) any later version. 

13# 

14# This program is distributed in the hope that it will be useful, 

15# but WITHOUT ANY WARRANTY; without even the implied warranty of 

16# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 

17# GNU General Public License for more details. 

18# 

19# You should have received a copy of the GNU General Public License 

20# along with this program. If not, see <http://www.gnu.org/licenses/>. 

21from __future__ import annotations 

22 

23__all__ = ["NameShrinker"] 

24 

25import hashlib 

26from typing import Dict 

27 

28 

29class NameShrinker: 

30 """A utility class for `Database` implementations that need a nontrivial 

31 implementation of `Database.shrinkDatabaseEntityName` and 

32 `Database.expandDatabaseEntityName`. 

33 

34 Parameters 

35 ---------- 

36 maxLength : `int` 

37 The maximum number of characters in a database entity name. 

38 hashSize : `int`, optional 

39 The size of the hash (in bytes) to use for the tail of the shortened 

40 name. The hash is written in hexadecimal and prefixed with a "_", so 

41 the number of characters the hash occupies is ``hashSize*2 + 1``, and 

42 hence the number of characters preserved from the beginning of the 

43 original name is ``maxLength - hashSize*2 - 1``. 

44 """ 

45 

46 def __init__(self, maxLength: int, hashSize: int = 4): 

47 self.maxLength = maxLength 

48 self.hashSize = hashSize 

49 self._names: Dict[str, str] = {} 

50 

51 def shrink(self, original: str) -> str: 

52 """Shrink a name and remember the mapping between the original name and 

53 its shrunk form. 

54 """ 

55 if len(original) <= self.maxLength: 

56 return original 

57 message = hashlib.blake2b(digest_size=self.hashSize) 

58 message.update(original.encode("ascii")) 

59 trunc = self.maxLength - 2 * self.hashSize - 1 

60 shrunk = f"{original[:trunc]}_{message.digest().hex()}" 

61 assert len(shrunk) == self.maxLength 

62 self._names[shrunk] = original 

63 return shrunk 

64 

65 def expand(self, shrunk: str) -> str: 

66 """Return the original name that was passed to a previous call to 

67 `shrink`. 

68 

69 If the given name was not passed to `shrink` or was not modified by 

70 it, it is returned unmodified. 

71 """ 

72 return self._names.get(shrunk, shrunk)