]> 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:

Add support for pyi files (#210)
[etc/vim.git] / blib2to3 / pgen2 / tokenize.py
index 4f031306378ab20d13aec985e3c8715f59c8606a..9a7664bbf95bf81d1809922dcaf53433bae61454 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]
@@ -412,10 +410,6 @@ def generate_tokens(readline):
                 yield (NL, line[pos:], (lnum, pos), (lnum, len(line)), line)
                 continue
 
-            if column > indents[-1]:           # count indents
-                indents.append(column)
-                yield (INDENT, line[:pos], (lnum, 0), (lnum, pos), line)
-
             if line[pos] == '#':               # skip comments
                 comment_token = line[pos:].rstrip('\r\n')
                 nl_pos = pos + len(comment_token)
@@ -425,6 +419,10 @@ def generate_tokens(readline):
                         (lnum, nl_pos), (lnum, len(line)), line)
                 continue
 
+            if column > indents[-1]:           # count indents
+                indents.append(column)
+                yield (INDENT, line[:pos], (lnum, 0), (lnum, pos), line)
+
             while column < indents[-1]:        # count dedents
                 if column not in indents:
                     raise IndentationError(
@@ -451,8 +449,6 @@ def generate_tokens(readline):
 
         while pos < max:
             pseudomatch = pseudoprog.match(line, pos)
-            if not pseudomatch:
-                print('no pseudomatch')
             if pseudomatch:                                # scan for tokens
                 start, end = pseudomatch.span(1)
                 spos, epos, pos = (lnum, start), (lnum, end), end
@@ -508,8 +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,