__author__ = "Ka-Ping Yee <ping@lfw.org>"
__credits__ = "GvR, ESR, Tim Peters, Thomas Wouters, Fred Drake, Skip Montanaro"
-import regex as re
+import re
from codecs import BOM_UTF8, lookup
from blib2to3.pgen2.token import *
Comment = r"#[^\r\n]*"
Ignore = Whitespace + any(r"\\\r?\n" + Whitespace) + maybe(Comment)
Name = ( # this is invalid but it's fine because Name comes after Number in all groups
- r"\w+"
+ r"[^\s#\(\)\[\]\{\}+\-*/!@$%^&=|;:'\",\.<>/?`~\\]+"
)
Binnumber = r"0[bB]_?[01]+(?:_[01]+)*"
'"""': double3prog,
**{f"{prefix}'''": single3prog for prefix in _strprefixes},
**{f'{prefix}"""': double3prog for prefix in _strprefixes},
- **{prefix: None for prefix in _strprefixes},
}
triple_quoted: Final = (
cookie_re = re.compile(r"^[ \t\f]*#.*?coding[:=][ \t]*([-\w.]+)", re.ASCII)
-blank_re = re.compile(br"^[ \t\f]*(?:[#\r\n]|$)", re.ASCII)
+blank_re = re.compile(rb"^[ \t\f]*(?:[#\r\n]|$)", re.ASCII)
def _get_normal_name(orig_enc: str) -> str:
logical line; continuation lines are included.
"""
lnum = parenlev = continued = 0
- numchars: Final = "0123456789"
+ numchars: Final[str] = "0123456789"
contstr, needcont = "", 0
contline: Optional[str] = None
indents = [0]
):
if token[-1] == "\n": # continued string
strstart = (lnum, start)
- endprog = (
- endprogs[initial]
- or endprogs[token[1]]
- or endprogs[token[2]]
+ maybe_endprog = (
+ endprogs.get(initial)
+ or endprogs.get(token[1])
+ or endprogs.get(token[2])
)
+ assert maybe_endprog is not None, f"endprog not found for {token}"
+ endprog = maybe_endprog
contstr, needcont = line[start:], 1
contline = line
break