Coverage for /pythoncovmergedfiles/medio/medio/usr/local/lib/python3.11/site-packages/markdown_it/common/normalize_url.py: 97%

Shortcuts on this page

r m x   toggle line displays

j k   next/prev highlighted chunk

0   (zero) top of page

1   (one) first highlighted chunk

29 statements  

1from __future__ import annotations 

2 

3from collections.abc import Callable 

4from contextlib import suppress 

5import re 

6from urllib.parse import quote, unquote, urlparse, urlunparse # noqa: F401 

7 

8import mdurl 

9 

10from .. import _punycode 

11 

12RECODE_HOSTNAME_FOR = ("http:", "https:", "mailto:") 

13 

14 

15def normalizeLink(url: str) -> str: 

16 """Normalize destination URLs in links 

17 

18 :: 

19 

20 [label]: destination 'title' 

21 ^^^^^^^^^^^ 

22 """ 

23 parsed = mdurl.parse(url, slashes_denote_host=True) 

24 

25 # Encode hostnames in urls like: 

26 # `http://host/`, `https://host/`, `mailto:user@host`, `//host/` 

27 # 

28 # We don't encode unknown schemas, because it's likely that we encode 

29 # something we shouldn't (e.g. `skype:name` treated as `skype:host`) 

30 # 

31 if parsed.hostname and ( 

32 not parsed.protocol or parsed.protocol in RECODE_HOSTNAME_FOR 

33 ): 

34 with suppress(Exception): 

35 parsed = parsed._replace(hostname=_punycode.to_ascii(parsed.hostname)) 

36 

37 if not parsed.hostname or ":" not in parsed.hostname: 

38 return mdurl.encode(mdurl.format(parsed)) 

39 

40 # Encode components before format() adds the IPv6 host brackets. 

41 return mdurl.format( 

42 parsed._replace( 

43 protocol=parsed.protocol and mdurl.encode(parsed.protocol), 

44 auth=parsed.auth and mdurl.encode(parsed.auth), 

45 hostname=mdurl.encode(parsed.hostname), 

46 pathname=parsed.pathname and mdurl.encode(parsed.pathname), 

47 search=parsed.search and mdurl.encode(parsed.search), 

48 hash=parsed.hash and mdurl.encode(parsed.hash), 

49 ) 

50 ) 

51 

52 

53def normalizeLinkText(url: str) -> str: 

54 """Normalize autolink content 

55 

56 :: 

57 

58 <destination> 

59 ~~~~~~~~~~~ 

60 """ 

61 parsed = mdurl.parse(url, slashes_denote_host=True) 

62 

63 # Encode hostnames in urls like: 

64 # `http://host/`, `https://host/`, `mailto:user@host`, `//host/` 

65 # 

66 # We don't encode unknown schemas, because it's likely that we encode 

67 # something we shouldn't (e.g. `skype:name` treated as `skype:host`) 

68 # 

69 if parsed.hostname and ( 

70 not parsed.protocol or parsed.protocol in RECODE_HOSTNAME_FOR 

71 ): 

72 with suppress(Exception): 

73 parsed = parsed._replace(hostname=_punycode.to_unicode(parsed.hostname)) 

74 

75 # add '%' to exclude list because of https://github.com/markdown-it/markdown-it/issues/720 

76 return mdurl.decode(mdurl.format(parsed), mdurl.DECODE_DEFAULT_CHARS + "%") 

77 

78 

79BAD_PROTO_RE = re.compile(r"^(vbscript|javascript|file|data):") 

80GOOD_DATA_RE = re.compile(r"^data:image\/(gif|png|jpeg|webp);") 

81 

82 

83def validateLink(url: str, validator: Callable[[str], bool] | None = None) -> bool: 

84 """Validate URL link is allowed in output. 

85 

86 This validator can prohibit more than really needed to prevent XSS. 

87 It's a tradeoff to keep code simple and to be secure by default. 

88 

89 Note: url should be normalized at this point, and existing entities decoded. 

90 """ 

91 if validator is not None: 

92 return validator(url) 

93 url = url.strip().lower() 

94 return bool(GOOD_DATA_RE.search(url)) if BAD_PROTO_RE.search(url) else True