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
1"""Block-level tokenizer."""
2from __future__ import annotations
4import logging
5from typing import TYPE_CHECKING, Callable
7from . import rules_block
8from .ruler import Ruler
9from .rules_block.state_block import StateBlock
10from .token import Token
11from .utils import EnvType
13if TYPE_CHECKING:
14 from markdown_it import MarkdownIt
16LOGGER = logging.getLogger(__name__)
19RuleFuncBlockType = Callable[[StateBlock, int, int, bool], bool]
20"""(state: StateBlock, startLine: int, endLine: int, silent: bool) -> matched: bool)
22`silent` disables token generation, useful for lookahead.
23"""
25_rules: list[tuple[str, RuleFuncBlockType, list[str]]] = [
26 # First 2 params - rule name & source. Secondary array - list of rules,
27 # which can be terminated by this one.
28 ("table", rules_block.table, ["paragraph", "reference"]),
29 ("code", rules_block.code, []),
30 ("fence", rules_block.fence, ["paragraph", "reference", "blockquote", "list"]),
31 (
32 "blockquote",
33 rules_block.blockquote,
34 ["paragraph", "reference", "blockquote", "list"],
35 ),
36 ("hr", rules_block.hr, ["paragraph", "reference", "blockquote", "list"]),
37 ("list", rules_block.list_block, ["paragraph", "reference", "blockquote"]),
38 ("reference", rules_block.reference, []),
39 ("html_block", rules_block.html_block, ["paragraph", "reference", "blockquote"]),
40 ("heading", rules_block.heading, ["paragraph", "reference", "blockquote"]),
41 ("lheading", rules_block.lheading, []),
42 ("paragraph", rules_block.paragraph, []),
43]
46class ParserBlock:
47 """
48 ParserBlock#ruler -> Ruler
50 [[Ruler]] instance. Keep configuration of block rules.
51 """
53 def __init__(self) -> None:
54 self.ruler = Ruler[RuleFuncBlockType]()
55 for name, rule, alt in _rules:
56 self.ruler.push(name, rule, {"alt": alt})
58 def tokenize(self, state: StateBlock, startLine: int, endLine: int) -> None:
59 """Generate tokens for input range."""
60 rules = self.ruler.getRules("")
61 line = startLine
62 maxNesting = state.md.options.maxNesting
63 hasEmptyLines = False
65 while line < endLine:
66 state.line = line = state.skipEmptyLines(line)
67 if line >= endLine:
68 break
69 if state.sCount[line] < state.blkIndent:
70 # Termination condition for nested calls.
71 # Nested calls currently used for blockquotes & lists
72 break
73 if state.level >= maxNesting:
74 # If nesting level exceeded - skip tail to the end.
75 # That's not ordinary situation and we should not care about content.
76 state.line = endLine
77 break
79 # Try all possible rules.
80 # On success, rule should:
81 # - update `state.line`
82 # - update `state.tokens`
83 # - return True
84 for rule in rules:
85 if rule(state, line, endLine, False):
86 break
88 # set state.tight if we had an empty line before current tag
89 # i.e. latest empty line should not count
90 state.tight = not hasEmptyLines
92 line = state.line
94 # paragraph might "eat" one newline after it in nested lists
95 if (line - 1) < endLine and state.isEmpty(line - 1):
96 hasEmptyLines = True
98 if line < endLine and state.isEmpty(line):
99 hasEmptyLines = True
100 line += 1
101 state.line = line
103 def parse(
104 self, src: str, md: MarkdownIt, env: EnvType, outTokens: list[Token]
105 ) -> list[Token] | None:
106 """Process input string and push block tokens into `outTokens`."""
107 if not src:
108 return None
109 state = StateBlock(src, md, env, outTokens)
110 self.tokenize(state, state.line, state.lineMax)
111 return state.tokens