Coverage for /pythoncovmergedfiles/medio/medio/usr/local/lib/python3.8/site-packages/markdown_it/rules_core/replacements.py: 38%

1"""Simple typographic replacements 

2 

3* ``(c)``, ``(C)`` → © 

4* ``(tm)``, ``(TM)`` → ™ 

5* ``(r)``, ``(R)`` → ® 

6* ``+-`` → ± 

7* ``...`` → … 

8* ``?....`` → ?.. 

9* ``!....`` → !.. 

10* ``????????`` → ??? 

11* ``!!!!!`` → !!! 

12* ``,,,`` → , 

13* ``--`` → &ndash 

14* ``---`` → &mdash 

15""" 

16from __future__ import annotations 

17 

18import logging 

19import re 

20 

21from ..token import Token 

22from .state_core import StateCore 

23 

24LOGGER = logging.getLogger(__name__) 

25 

26# TODO: 

27# - fractionals 1/2, 1/4, 3/4 -> ½, ¼, ¾ 

28# - multiplication 2 x 4 -> 2 × 4 

29 

30RARE_RE = re.compile(r"\+-|\.\.|\?\?\?\?|!!!!|,,|--") 

31 

32# Workaround for phantomjs - need regex without /g flag, 

33# or root check will fail every second time 

34# SCOPED_ABBR_TEST_RE = r"\((c|tm|r)\)" 

35 

36SCOPED_ABBR_RE = re.compile(r"\((c|tm|r)\)", flags=re.IGNORECASE) 

37 

38PLUS_MINUS_RE = re.compile(r"\+-") 

39 

40ELLIPSIS_RE = re.compile(r"\.{2,}") 

41 

42ELLIPSIS_QUESTION_EXCLAMATION_RE = re.compile(r"([?!])…") 

43 

44QUESTION_EXCLAMATION_RE = re.compile(r"([?!]){4,}") 

45 

46COMMA_RE = re.compile(r",{2,}") 

47 

48EM_DASH_RE = re.compile(r"(^|[^-])---(?=[^-]|$)", flags=re.MULTILINE) 

49 

50EN_DASH_RE = re.compile(r"(^|\s)--(?=\s|$)", flags=re.MULTILINE) 

51 

52EN_DASH_INDENT_RE = re.compile(r"(^|[^-\s])--(?=[^-\s]|$)", flags=re.MULTILINE) 

53 

54 

55SCOPED_ABBR = {"c": "©", "r": "®", "tm": "™"} 

56 

57 

58def replaceFn(match: re.Match[str]) -> str: 

59 return SCOPED_ABBR[match.group(1).lower()] 

60 

61 

62def replace_scoped(inlineTokens: list[Token]) -> None: 

63 inside_autolink = 0 

64 

65 for token in inlineTokens: 

66 if token.type == "text" and not inside_autolink: 

67 token.content = SCOPED_ABBR_RE.sub(replaceFn, token.content) 

68 

69 if token.type == "link_open" and token.info == "auto": 

70 inside_autolink -= 1 

71 

72 if token.type == "link_close" and token.info == "auto": 

73 inside_autolink += 1 

74 

75 

76def replace_rare(inlineTokens: list[Token]) -> None: 

77 inside_autolink = 0 

78 

79 for token in inlineTokens: 

80 if ( 

81 token.type == "text" 

82 and (not inside_autolink) 

83 and RARE_RE.search(token.content) 

84 ): 

85 # +- -> ± 

86 token.content = PLUS_MINUS_RE.sub("±", token.content) 

87 

88 # .., ..., ....... -> … 

89 token.content = ELLIPSIS_RE.sub("…", token.content) 

90 

91 # but ?..... & !..... -> ?.. & !.. 

92 token.content = ELLIPSIS_QUESTION_EXCLAMATION_RE.sub("\\1..", token.content) 

93 token.content = QUESTION_EXCLAMATION_RE.sub("\\1\\1\\1", token.content) 

94 

95 # ,, ,,, ,,,, -> , 

96 token.content = COMMA_RE.sub(",", token.content) 

97 

98 # em-dash 

99 token.content = EM_DASH_RE.sub("\\1\u2014", token.content) 

100 

101 # en-dash 

102 token.content = EN_DASH_RE.sub("\\1\u2013", token.content) 

103 token.content = EN_DASH_INDENT_RE.sub("\\1\u2013", token.content) 

104 

105 if token.type == "link_open" and token.info == "auto": 

106 inside_autolink -= 1 

107 

108 if token.type == "link_close" and token.info == "auto": 

109 inside_autolink += 1 

110 

111 

112def replace(state: StateCore) -> None: 

113 if not state.md.options.typographer: 

114 return 

115 

116 for token in state.tokens: 

117 if token.type != "inline": 

118 continue 

119 if token.children is None: 

120 continue 

121 

122 if SCOPED_ABBR_RE.search(token.content): 

123 replace_scoped(token.children) 

124 

125 if RARE_RE.search(token.content): 

126 replace_rare(token.children)