Coverage for /pythoncovmergedfiles/medio/medio/usr/local/lib/python3.8/site-packages/markdown_it/_punycode.py: 87%

30 statements  

« prev     ^ index     » next       coverage.py v7.2.7, created at 2023-06-07 06:15 +0000

1# Copyright 2014 Mathias Bynens <https://mathiasbynens.be/> 

2# Copyright 2021 Taneli Hukkinen 

3# 

4# Permission is hereby granted, free of charge, to any person obtaining 

5# a copy of this software and associated documentation files (the 

6# "Software"), to deal in the Software without restriction, including 

7# without limitation the rights to use, copy, modify, merge, publish, 

8# distribute, sublicense, and/or sell copies of the Software, and to 

9# permit persons to whom the Software is furnished to do so, subject to 

10# the following conditions: 

11# 

12# The above copyright notice and this permission notice shall be 

13# included in all copies or substantial portions of the Software. 

14# 

15# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, 

16# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF 

17# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND 

18# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE 

19# LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION 

20# OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION 

21# WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. 

22 

23import codecs 

24import re 

25from typing import Callable 

26 

27REGEX_SEPARATORS = re.compile(r"[\x2E\u3002\uFF0E\uFF61]") 

28REGEX_NON_ASCII = re.compile(r"[^\0-\x7E]") 

29 

30 

31def encode(uni: str) -> str: 

32 return codecs.encode(uni, encoding="punycode").decode() 

33 

34 

35def decode(ascii: str) -> str: 

36 return codecs.decode(ascii, encoding="punycode") # type: ignore 

37 

38 

39def map_domain(string: str, fn: Callable[[str], str]) -> str: 

40 parts = string.split("@") 

41 result = "" 

42 if len(parts) > 1: 

43 # In email addresses, only the domain name should be punycoded. Leave 

44 # the local part (i.e. everything up to `@`) intact. 

45 result = parts[0] + "@" 

46 string = parts[1] 

47 labels = REGEX_SEPARATORS.split(string) 

48 encoded = ".".join(fn(label) for label in labels) 

49 return result + encoded 

50 

51 

52def to_unicode(obj: str) -> str: 

53 def mapping(obj: str) -> str: 

54 if obj.startswith("xn--"): 

55 return decode(obj[4:].lower()) 

56 return obj 

57 

58 return map_domain(obj, mapping) 

59 

60 

61def to_ascii(obj: str) -> str: 

62 def mapping(obj: str) -> str: 

63 if REGEX_NON_ASCII.search(obj): 

64 return "xn--" + encode(obj) 

65 return obj 

66 

67 return map_domain(obj, mapping)