Coverage for diffoscope/comparators/sphinx.py: 91%

1# 

2# diffoscope: in-depth comparison of files, archives, and directories 

3# 

4# Copyright © 2021-2022 Chris Lamb <lamby@debian.org> 

5# 

6# diffoscope is free software: you can redistribute it and/or modify 

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

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

9# (at your option) any later version. 

10# 

11# diffoscope is distributed in the hope that it will be useful, 

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

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

14# GNU General Public License for more details. 

15# 

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

17# along with diffoscope. If not, see <https://www.gnu.org/licenses/>. 

18 

19import zlib 

20 

21from diffoscope.difference import Difference 

22 

23from .utils.file import File 

24 

25MAGIC = b"# Sphinx inventory version" 

26 

27 

28class SphinxInventoryFile(File): 

29 DESCRIPTION = "Sphinx inventory files" 

30 FILE_EXTENSION_SUFFIX = {".inv"} 

31 

32 def compare_details(self, other, source=None): 

33 return [ 

34 Difference.from_text( 

35 describe_inventory(self.path), 

36 describe_inventory(other.path), 

37 self.path, 

38 other.path, 

39 source="Sphinx inventory", 

40 ) 

41 ] 

42 

43 

44def describe_inventory(filename): 

45 head = b"" 

46 tail = b"" 

47 

48 with open(filename, "rb") as f: 

49 for line in f: 

50 if line.startswith(b"#"): 

51 # Save commented lines at top of file 

52 head += line 

53 else: 

54 # ... save the rest for decompression 

55 tail += line 

56 

57 result = head + b"\n" if head else b"" 

58 

59 try: 

60 result += zlib.decompress(tail) 

61 except zlib.error: 

62 # Even if the file is labelled "The remainder of this file is 

63 # compressed using zlib.", it might not actually be. In this case, 

64 # simply return the original content. 

65 result += tail 

66 

67 return result.decode("utf-8", "ignore")