Improve multiline string handling (#1879)

[etc/vim.git] / src / blib2to3 / pgen2 / tokenize.py

diff --git a/src/blib2to3/pgen2/tokenize.py b/src/blib2to3/pgen2/tokenize.py
index 283fac2d5375a8f9de49879447fb80bf622c8111..257dbef4a194b60ef81eabc22cd373891abec232 100644 (file)
--- a/src/blib2to3/pgen2/tokenize.py
+++ b/src/blib2to3/pgen2/tokenize.py
@@ -52,7 +52,7 @@ from blib2to3.pgen2.grammar import Grammar
 __author__ = "Ka-Ping Yee <ping@lfw.org>"
 __credits__ = "GvR, ESR, Tim Peters, Thomas Wouters, Fred Drake, Skip Montanaro"
 
 __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 *
 
 from codecs import BOM_UTF8, lookup
 from blib2to3.pgen2.token import *
 


@@ -86,7 +86,7 @@ Whitespace = r"[ \f\t]*"
 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
 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]+)*"
 )
 
 Binnumber = r"0[bB]_?[01]+(?:_[01]+)*"


@@ -293,7 +293,7 @@ class Untokenizer:
 
 
 cookie_re = re.compile(r"^[ \t\f]*#.*?coding[:=][ \t]*([-\w.]+)", re.ASCII)
 
 
 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:
 
 
 def _get_normal_name(orig_enc: str) -> str: