Coverage for /pythoncovmergedfiles/medio/medio/usr/local/lib/python3.11/site-packages/markdown_it/rules_inline/html_inline.py: 96%

1# Process html tags 

2from ..common.html_re import HTML_TAG_RE 

3from ..common.utils import isLinkClose, isLinkOpen 

4from .state_inline import StateInline 

5 

6 

7def isLetter(ch: int) -> bool: 

8 lc = ch | 0x20 # to lower case 

9 # /* a */ and /* z */ 

10 return (lc >= 0x61) and (lc <= 0x7A) 

11 

12 

13def html_inline(state: StateInline, silent: bool) -> bool: 

14 pos = state.pos 

15 

16 if not state.md.options.get("html", None): 

17 return False 

18 

19 # Check start 

20 src = state.src 

21 maximum = state.posMax 

22 if src[pos] != "<" or pos + 2 >= maximum: 

23 return False 

24 

25 # Quick fail on second char 

26 ch = src[pos + 1] 

27 if ch not in ("!", "?", "/") and not isLetter(ord(ch)): # /* / */ 

28 return False 

29 

30 # Every alternative of the tag regex ends with a specific terminator, at a 

31 # known minimum offset from `pos`. If that terminator does not occur 

32 # anywhere at or after this offset, no match is possible; bail out before 

33 # running the regex, whose lazy sub-patterns would scan to the end of the 

34 # input. Without this, a run of unterminated openers is quadratic. 

35 if src.startswith("<!--", pos): 

36 # `<!-->` / `<!--->`, else `<!--` ... `-->` (`<!---->` is the shortest) 

37 if state.html_terminator_last(">") < pos + 4: 

38 return False 

39 if ( 

40 not src.startswith("<!-->", pos) 

41 and not src.startswith("<!--->", pos) 

42 and state.html_terminator_last("-->") < pos + 4 

43 ): 

44 return False 

45 elif src.startswith("<![CDATA[", pos): 

46 if state.html_terminator_last("]]>") < pos + 9: # `<![CDATA[]]>` 

47 return False 

48 elif ch == "?": 

49 if state.html_terminator_last("?>") < pos + 2: # `<??>` 

50 return False 

51 elif ch == "!": 

52 if state.html_terminator_last(">") < pos + 3: # `<!a>` 

53 return False 

54 elif state.html_terminator_last(">") < pos + 2: # `<a>`, `</a>` 

55 return False 

56 

57 match = HTML_TAG_RE.match(src, pos) 

58 if not match: 

59 return False 

60 

61 if not silent: 

62 token = state.push("html_inline", "", 0) 

63 token.content = src[pos : pos + len(match.group(0))] 

64 

65 if isLinkOpen(token.content): 

66 state.linkLevel += 1 

67 if isLinkClose(token.content): 

68 state.linkLevel -= 1 

69 

70 state.pos += len(match.group(0)) 

71 return True