second commit

This commit is contained in:
2024-12-27 22:31:23 +09:00
parent 2353324570
commit 10a0f110ca
8819 changed files with 1307198 additions and 28 deletions

View File

@ -0,0 +1,6 @@
"""Functions for parsing Links
"""
__all__ = ("parseLinkLabel", "parseLinkDestination", "parseLinkTitle")
from .parse_link_destination import parseLinkDestination
from .parse_link_label import parseLinkLabel
from .parse_link_title import parseLinkTitle

View File

@ -0,0 +1,86 @@
"""
Parse link destination
"""
from ..common.utils import charCodeAt, unescapeAll
class _Result:
__slots__ = ("ok", "pos", "lines", "str")
def __init__(self) -> None:
self.ok = False
self.pos = 0
self.lines = 0
self.str = ""
def parseLinkDestination(string: str, pos: int, maximum: int) -> _Result:
lines = 0
start = pos
result = _Result()
if charCodeAt(string, pos) == 0x3C: # /* < */
pos += 1
while pos < maximum:
code = charCodeAt(string, pos)
if code == 0x0A: # /* \n */)
return result
if code == 0x3C: # / * < * /
return result
if code == 0x3E: # /* > */) {
result.pos = pos + 1
result.str = unescapeAll(string[start + 1 : pos])
result.ok = True
return result
if code == 0x5C and pos + 1 < maximum: # \
pos += 2
continue
pos += 1
# no closing '>'
return result
# this should be ... } else { ... branch
level = 0
while pos < maximum:
code = charCodeAt(string, pos)
if code is None or code == 0x20:
break
# ascii control characters
if code < 0x20 or code == 0x7F:
break
if code == 0x5C and pos + 1 < maximum:
if charCodeAt(string, pos + 1) == 0x20:
break
pos += 2
continue
if code == 0x28: # /* ( */)
level += 1
if level > 32:
return result
if code == 0x29: # /* ) */)
if level == 0:
break
level -= 1
pos += 1
if start == pos:
return result
if level != 0:
return result
result.str = unescapeAll(string[start:pos])
result.lines = lines
result.pos = pos
result.ok = True
return result

View File

@ -0,0 +1,43 @@
"""
Parse link label
this function assumes that first character ("[") already matches
returns the end of the label
"""
from markdown_it.rules_inline import StateInline
def parseLinkLabel(state: StateInline, start: int, disableNested: bool = False) -> int:
labelEnd = -1
oldPos = state.pos
found = False
state.pos = start + 1
level = 1
while state.pos < state.posMax:
marker = state.src[state.pos]
if marker == "]":
level -= 1
if level == 0:
found = True
break
prevPos = state.pos
state.md.inline.skipToken(state)
if marker == "[":
if prevPos == state.pos - 1:
# increase level if we find text `[`,
# which is not a part of any token
level += 1
elif disableNested:
state.pos = oldPos
return -1
if found:
labelEnd = state.pos
# restore old state
state.pos = oldPos
return labelEnd

View File

@ -0,0 +1,60 @@
"""Parse link title
"""
from ..common.utils import charCodeAt, unescapeAll
class _Result:
__slots__ = ("ok", "pos", "lines", "str")
def __init__(self) -> None:
self.ok = False
self.pos = 0
self.lines = 0
self.str = ""
def __str__(self) -> str:
return self.str
def parseLinkTitle(string: str, pos: int, maximum: int) -> _Result:
lines = 0
start = pos
result = _Result()
if pos >= maximum:
return result
marker = charCodeAt(string, pos)
# /* " */ /* ' */ /* ( */
if marker != 0x22 and marker != 0x27 and marker != 0x28:
return result
pos += 1
# if opening marker is "(", switch it to closing marker ")"
if marker == 0x28:
marker = 0x29
while pos < maximum:
code = charCodeAt(string, pos)
if code == marker:
title = string[start + 1 : pos]
title = unescapeAll(title)
result.pos = pos + 1
result.lines = lines
result.str = title
result.ok = True
return result
elif code == 0x28 and marker == 0x29: # /* ( */ /* ) */
return result
elif code == 0x0A:
lines += 1
elif code == 0x5C and pos + 1 < maximum: # /* \ */
pos += 1
if charCodeAt(string, pos) == 0x0A:
lines += 1
pos += 1
return result