Coverage for /pythoncovmergedfiles/medio/medio/usr/local/lib/python3.11/site-packages/markdown_it/rules_block/state_block.py: 87%

1from __future__ import annotations 

2 

3from typing import TYPE_CHECKING, Literal 

4 

5from ..common.utils import isStrSpace 

6from ..ruler import StateBase 

7from ..token import Token 

8from ..utils import EnvType 

9 

10if TYPE_CHECKING: 

11 from markdown_it.main import MarkdownIt 

12 

13 

14class StateBlock(StateBase): 

15 def __init__( 

16 self, src: str, md: MarkdownIt, env: EnvType, tokens: list[Token] 

17 ) -> None: 

18 self.src = src 

19 

20 # link to parser instance 

21 self.md = md 

22 

23 self.env = env 

24 

25 # 

26 # Internal state variables 

27 # 

28 

29 self.tokens = tokens 

30 

31 self.bMarks: list[int] = [] # line begin offsets for fast jumps 

32 self.eMarks: list[int] = [] # line end offsets for fast jumps 

33 # offsets of the first non-space characters (tabs not expanded) 

34 self.tShift: list[int] = [] 

35 self.sCount: list[int] = [] # indents for each line (tabs expanded) 

36 

37 # An amount of virtual spaces (tabs expanded) between beginning 

38 # of each line (bMarks) and real beginning of that line. 

39 # 

40 # It exists only as a hack because blockquotes override bMarks 

41 # losing information in the process. 

42 # 

43 # It's used only when expanding tabs, you can think about it as 

44 # an initial tab length, e.g. bsCount=21 applied to string `\t123` 

45 # means first tab should be expanded to 4-21%4 === 3 spaces. 

46 # 

47 self.bsCount: list[int] = [] 

48 

49 # block parser variables 

50 self.blkIndent = 0 # required block content indent (for example, if we are 

51 # inside a list, it would be positioned after list marker) 

52 self.line = 0 # line index in src 

53 self.lineMax = 0 # lines count 

54 self.tight = False # loose/tight mode for lists 

55 self.ddIndent = -1 # indent of the current dd block (-1 if there isn't any) 

56 self.listIndent = -1 # indent of the current list block (-1 if there isn't any) 

57 

58 # can be 'blockquote', 'list', 'root', 'paragraph' or 'reference' 

59 # used in lists to determine if they interrupt a paragraph 

60 self.parentType = "root" 

61 

62 self.level = 0 

63 

64 # renderer 

65 self.result = "" 

66 

67 # Create caches 

68 # Generate markers. 

69 indent_found = False 

70 

71 start = pos = indent = offset = 0 

72 length = len(self.src) 

73 

74 for pos, character in enumerate(self.src): 

75 if not indent_found: 

76 if isStrSpace(character): 

77 indent += 1 

78 

79 if character == "\t": 

80 offset += 4 - offset % 4 

81 else: 

82 offset += 1 

83 continue 

84 else: 

85 indent_found = True 

86 

87 if character == "\n" or pos == length - 1: 

88 if character != "\n": 

89 pos += 1 

90 self.bMarks.append(start) 

91 self.eMarks.append(pos) 

92 self.tShift.append(indent) 

93 self.sCount.append(offset) 

94 self.bsCount.append(0) 

95 

96 indent_found = False 

97 indent = 0 

98 offset = 0 

99 start = pos + 1 

100 

101 # Push fake entry to simplify cache bounds checks 

102 self.bMarks.append(length) 

103 self.eMarks.append(length) 

104 self.tShift.append(0) 

105 self.sCount.append(0) 

106 self.bsCount.append(0) 

107 

108 self.lineMax = len(self.bMarks) - 1 # don't count last fake line 

109 

110 # pre-check if code blocks are enabled, to speed up is_code_block method 

111 self._code_enabled = "code" in self.md["block"].ruler.get_active_rules() 

112 

113 def __repr__(self) -> str: 

114 return ( 

115 f"{self.__class__.__name__}" 

116 f"(line={self.line},level={self.level},tokens={len(self.tokens)})" 

117 ) 

118 

119 def push(self, ttype: str, tag: str, nesting: Literal[-1, 0, 1]) -> Token: 

120 """Push new token to "stream".""" 

121 token = Token(ttype, tag, nesting) 

122 token.block = True 

123 if nesting < 0: 

124 self.level -= 1 # closing tag 

125 token.level = self.level 

126 if nesting > 0: 

127 self.level += 1 # opening tag 

128 self.tokens.append(token) 

129 return token 

130 

131 def isEmpty(self, line: int) -> bool: 

132 """.""" 

133 return (self.bMarks[line] + self.tShift[line]) >= self.eMarks[line] 

134 

135 def skipEmptyLines(self, from_pos: int) -> int: 

136 """.""" 

137 while from_pos < self.lineMax: 

138 try: 

139 if (self.bMarks[from_pos] + self.tShift[from_pos]) < self.eMarks[ 

140 from_pos 

141 ]: 

142 break 

143 except IndexError: 

144 pass 

145 from_pos += 1 

146 return from_pos 

147 

148 def skipSpaces(self, pos: int) -> int: 

149 """Skip spaces from given position.""" 

150 while True: 

151 try: 

152 current = self.src[pos] 

153 except IndexError: 

154 break 

155 if not isStrSpace(current): 

156 break 

157 pos += 1 

158 return pos 

159 

160 def skipSpacesBack(self, pos: int, minimum: int) -> int: 

161 """Skip spaces from given position in reverse.""" 

162 if pos <= minimum: 

163 return pos 

164 while pos > minimum: 

165 pos -= 1 

166 if not isStrSpace(self.src[pos]): 

167 return pos + 1 

168 return pos 

169 

170 def skipChars(self, pos: int, code: int) -> int: 

171 """Skip character code from given position.""" 

172 while True: 

173 try: 

174 current = self.srcCharCode[pos] 

175 except IndexError: 

176 break 

177 if current != code: 

178 break 

179 pos += 1 

180 return pos 

181 

182 def skipCharsStr(self, pos: int, ch: str) -> int: 

183 """Skip character string from given position.""" 

184 while True: 

185 try: 

186 current = self.src[pos] 

187 except IndexError: 

188 break 

189 if current != ch: 

190 break 

191 pos += 1 

192 return pos 

193 

194 def skipCharsBack(self, pos: int, code: int, minimum: int) -> int: 

195 """Skip character code reverse from given position - 1.""" 

196 if pos <= minimum: 

197 return pos 

198 while pos > minimum: 

199 pos -= 1 

200 if code != self.srcCharCode[pos]: 

201 return pos + 1 

202 return pos 

203 

204 def skipCharsStrBack(self, pos: int, ch: str, minimum: int) -> int: 

205 """Skip character string reverse from given position - 1.""" 

206 if pos <= minimum: 

207 return pos 

208 while pos > minimum: 

209 pos -= 1 

210 if ch != self.src[pos]: 

211 return pos + 1 

212 return pos 

213 

214 def getLines(self, begin: int, end: int, indent: int, keepLastLF: bool) -> str: 

215 """Cut lines range from source.""" 

216 line = begin 

217 if begin >= end: 

218 return "" 

219 

220 queue = [""] * (end - begin) 

221 

222 i = 1 

223 while line < end: 

224 lineIndent = 0 

225 lineStart = first = self.bMarks[line] 

226 last = ( 

227 self.eMarks[line] + 1 

228 if line + 1 < end or keepLastLF 

229 else self.eMarks[line] 

230 ) 

231 

232 while (first < last) and (lineIndent < indent): 

233 ch = self.src[first] 

234 if isStrSpace(ch): 

235 if ch == "\t": 

236 lineIndent += 4 - (lineIndent + self.bsCount[line]) % 4 

237 else: 

238 lineIndent += 1 

239 elif first - lineStart < self.tShift[line]: 

240 lineIndent += 1 

241 else: 

242 break 

243 first += 1 

244 

245 if lineIndent > indent: 

246 # partially expanding tabs in code blocks, e.g '\t\tfoobar' 

247 # with indent=2 becomes ' \tfoobar' 

248 queue[i - 1] = (" " * (lineIndent - indent)) + self.src[first:last] 

249 else: 

250 queue[i - 1] = self.src[first:last] 

251 

252 line += 1 

253 i += 1 

254 

255 return "".join(queue) 

256 

257 def is_code_block(self, line: int) -> bool: 

258 """Check if line is a code block, 

259 i.e. the code block rule is enabled and text is indented by more than 3 spaces. 

260 """ 

261 return self._code_enabled and (self.sCount[line] - self.blkIndent) >= 4