actions/black
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Accelerate Unicode identifier support (backport from Lib/tokenize.py)

Browse Source
This commit is contained in:
Łukasz Langa 2018-04-23 14:31:35 -07:00
parent 82198030ee
commit c86fb36232
1 changed files with 4 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
blib2to3/pgen2/tokenize.py
View File

@ -29,7 +29,7 @@
__credits__ = \ __credits__ = \
'GvR, ESR, Tim Peters, Thomas Wouters, Fred Drake, Skip Montanaro' 'GvR, ESR, Tim Peters, Thomas Wouters, Fred Drake, Skip Montanaro'
import string, re, unicodedata import re
from codecs import BOM_UTF8, lookup from codecs import BOM_UTF8, lookup
from blib2to3.pgen2.token import * from blib2to3.pgen2.token import *
@ -56,7 +56,7 @@ def _combinations(*l):
Whitespace = r'[ \f\t]*' Whitespace = r'[ \f\t]*'
Comment = r'#[^\r\n]*' Comment = r'#[^\r\n]*'
Ignore = Whitespace + any(r'\\\r?\n' + Whitespace) + maybe(Comment) 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]+)*' Binnumber = r'0[bB]_?[01]+(?:_[01]+)*'
Hexnumber = r'0[xX]_?[\da-fA-F]+(?:_[\da-fA-F]+)*[lL]?' Hexnumber = r'0[xX]_?[\da-fA-F]+(?:_[\da-fA-F]+)*[lL]?'
@ -334,8 +334,6 @@ def untokenize(iterable):
ut = Untokenizer() ut = Untokenizer()
return ut.untokenize(iterable) return ut.untokenize(iterable)
InitialCategories = {'Lu', 'Ll', 'Lt', 'Lm', 'Lo', 'Nl', 'Mn', 'Mc', 'Nd', 'Pc'}
def generate_tokens(readline): def generate_tokens(readline):
""" """
The generate_tokens() generator requires one argument, readline, which The generate_tokens() generator requires one argument, readline, which
@ -353,7 +351,7 @@ def generate_tokens(readline):
logical line; continuation lines are included. logical line; continuation lines are included.
""" """
lnum = parenlev = continued = 0 lnum = parenlev = continued = 0
namechars, numchars = string.ascii_letters + '_', '0123456789' numchars = '0123456789'
contstr, needcont = '', 0 contstr, needcont = '', 0
contline = None contline = None
indents = [0] indents = [0]
@ -506,8 +504,7 @@ def generate_tokens(readline):
yield stashed yield stashed
stashed = None stashed = None
yield (STRING, token, spos, epos, line) yield (STRING, token, spos, epos, line)
elif (initial in namechars or # ordinary name elif initial.isidentifier(): # ordinary name
unicodedata.category(initial) in InitialCategories):
if token in ('async', 'await'): if token in ('async', 'await'):
if async_def: if async_def:
yield (ASYNC if token == 'async' else AWAIT, yield (ASYNC if token == 'async' else AWAIT,