]> git.madduck.net Git - etc/vim.git/blobdiff - blib2to3/pgen2/tokenize.py

madduck's git repository

Every one of the projects in this repository is available at the canonical URL git://git.madduck.net/madduck/pub/<projectpath> — see each project's metadata for the exact URL.

All patches and comments are welcome. Please squash your changes to logical commits before using git-format-patch and git-send-email to patches@git.madduck.net. If you'd read over the Git project's submission guidelines and adhered to them, I'd be especially grateful.

SSH access, as well as push access can be individually arranged.

If you use my repositories frequently, consider adding the following snippet to ~/.gitconfig and using the third clone URL listed for each project:

[url "git://git.madduck.net/madduck/"]
  insteadOf = madduck:

Silence expected stderr (#621)
[etc/vim.git] / blib2to3 / pgen2 / tokenize.py
index a352713f7deaba741e1d13c2a10da43be544d26a..1f51ff0039fd0227df0a5d7f691bbcd684fea795 100644 (file)
@@ -29,7 +29,7 @@ __author__ = 'Ka-Ping Yee <ping@lfw.org>'
 __credits__ = \
     'GvR, ESR, Tim Peters, Thomas Wouters, Fred Drake, Skip Montanaro'
 
-import string, re, unicodedata
+import re
 from codecs import BOM_UTF8, lookup
 from blib2to3.pgen2.token import *
 
@@ -56,7 +56,7 @@ def _combinations(*l):
 Whitespace = r'[ \f\t]*'
 Comment = r'#[^\r\n]*'
 Ignore = Whitespace + any(r'\\\r?\n' + Whitespace) + maybe(Comment)
-Name = r'[^\d\W]\w*'
+Name = r'\w+'  # this is invalid but it's fine because Name comes after Number in all groups
 
 Binnumber = r'0[bB]_?[01]+(?:_[01]+)*'
 Hexnumber = r'0[xX]_?[\da-fA-F]+(?:_[\da-fA-F]+)*[lL]?'
@@ -334,8 +334,6 @@ def untokenize(iterable):
     ut = Untokenizer()
     return ut.untokenize(iterable)
 
-InitialCategories = {'Lu', 'Ll', 'Lt', 'Lm', 'Lo', 'Nl', 'Mn', 'Mc', 'Nd', 'Pc'}
-
 def generate_tokens(readline):
     """
     The generate_tokens() generator requires one argument, readline, which
@@ -353,7 +351,7 @@ def generate_tokens(readline):
     logical line; continuation lines are included.
     """
     lnum = parenlev = continued = 0
-    namechars, numchars = string.ascii_letters + '_', '0123456789'
+    numchars = '0123456789'
     contstr, needcont = '', 0
     contline = None
     indents = [0]
@@ -506,8 +504,7 @@ def generate_tokens(readline):
                             yield stashed
                             stashed = None
                         yield (STRING, token, spos, epos, line)
-                elif (initial in namechars or              # ordinary name
-                      unicodedata.category(initial) in InitialCategories):
+                elif initial.isidentifier():               # ordinary name
                     if token in ('async', 'await'):
                         if async_def:
                             yield (ASYNC if token == 'async' else AWAIT,
@@ -519,13 +516,14 @@ def generate_tokens(readline):
                         stashed = tok
                         continue
 
-                    if token == 'def':
+                    if token in ('def', 'for'):
                         if (stashed
                                 and stashed[0] == NAME
                                 and stashed[1] == 'async'):
 
-                            async_def = True
-                            async_def_indent = indents[-1]
+                            if token == 'def':
+                                async_def = True
+                                async_def_indent = indents[-1]
 
                             yield (ASYNC, stashed[1],
                                    stashed[2], stashed[3],