Server IP : 85.214.239.14 / Your IP : 3.142.172.250 Web Server : Apache/2.4.62 (Debian) System : Linux h2886529.stratoserver.net 4.9.0 #1 SMP Tue Jan 9 19:45:01 MSK 2024 x86_64 User : www-data ( 33) PHP Version : 7.4.18 Disable Function : pcntl_alarm,pcntl_fork,pcntl_waitpid,pcntl_wait,pcntl_wifexited,pcntl_wifstopped,pcntl_wifsignaled,pcntl_wifcontinued,pcntl_wexitstatus,pcntl_wtermsig,pcntl_wstopsig,pcntl_signal,pcntl_signal_get_handler,pcntl_signal_dispatch,pcntl_get_last_error,pcntl_strerror,pcntl_sigprocmask,pcntl_sigwaitinfo,pcntl_sigtimedwait,pcntl_exec,pcntl_getpriority,pcntl_setpriority,pcntl_async_signals,pcntl_unshare, MySQL : OFF | cURL : OFF | WGET : ON | Perl : ON | Python : ON | Sudo : ON | Pkexec : OFF Directory : /lib/python3/dist-packages/markdown_it/ |
Upload File : |
"""Tokenizes paragraph content. """ from __future__ import annotations from . import rules_inline from .ruler import RuleFunc, Ruler from .rules_inline.state_inline import StateInline from .token import Token # Parser rules _rules: list[tuple[str, RuleFunc]] = [ ("text", rules_inline.text), ("newline", rules_inline.newline), ("escape", rules_inline.escape), ("backticks", rules_inline.backtick), ("strikethrough", rules_inline.strikethrough.tokenize), ("emphasis", rules_inline.emphasis.tokenize), ("link", rules_inline.link), ("image", rules_inline.image), ("autolink", rules_inline.autolink), ("html_inline", rules_inline.html_inline), ("entity", rules_inline.entity), ] _rules2: list[tuple[str, RuleFunc]] = [ ("balance_pairs", rules_inline.link_pairs), ("strikethrough", rules_inline.strikethrough.postProcess), ("emphasis", rules_inline.emphasis.postProcess), ("text_collapse", rules_inline.text_collapse), ] class ParserInline: def __init__(self): self.ruler = Ruler() for name, rule in _rules: self.ruler.push(name, rule) # Second ruler used for post-processing (e.g. in emphasis-like rules) self.ruler2 = Ruler() for name, rule2 in _rules2: self.ruler2.push(name, rule2) def skipToken(self, state: StateInline) -> None: """Skip single token by running all rules in validation mode; returns `True` if any rule reported success """ ok = False pos = state.pos rules = self.ruler.getRules("") maxNesting = state.md.options["maxNesting"] cache = state.cache if pos in cache: state.pos = cache[pos] return if state.level < maxNesting: for rule in rules: # Increment state.level and decrement it later to limit recursion. # It's harmless to do here, because no tokens are created. # But ideally, we'd need a separate private state variable for this purpose. state.level += 1 ok = rule(state, True) state.level -= 1 if ok: break else: # Too much nesting, just skip until the end of the paragraph. # # NOTE: this will cause links to behave incorrectly in the following case, # when an amount of `[` is exactly equal to `maxNesting + 1`: # # [[[[[[[[[[[[[[[[[[[[[foo]() # # TODO: remove this workaround when CM standard will allow nested links # (we can replace it by preventing links from being parsed in # validation mode) # state.pos = state.posMax if not ok: state.pos += 1 cache[pos] = state.pos def tokenize(self, state: StateInline) -> None: """Generate tokens for input range.""" ok = False rules = self.ruler.getRules("") end = state.posMax maxNesting = state.md.options["maxNesting"] while state.pos < end: # Try all possible rules. # On success, rule should: # # - update `state.pos` # - update `state.tokens` # - return true if state.level < maxNesting: for rule in rules: ok = rule(state, False) if ok: break if ok: if state.pos >= end: break continue state.pending += state.src[state.pos] state.pos += 1 if state.pending: state.pushPending() def parse(self, src: str, md, env, tokens: list[Token]) -> list[Token]: """Process input string and push inline tokens into `tokens`""" state = StateInline(src, md, env, tokens) self.tokenize(state) rules2 = self.ruler2.getRules("") for rule in rules2: rule(state) return state.tokens