The site is cleaner without the 'Related' cruft.

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

diff --git a/blib2to3/pgen2/tokenize.py b/blib2to3/pgen2/tokenize.py
index 14560e4fddff6224abbafd228229ed88605bd1a3..669c3f183bb8907a01e863167be8c1c2680b1e85 100644 (file)
--- a/blib2to3/pgen2/tokenize.py
+++ b/blib2to3/pgen2/tokenize.py
@@ -31,7 +31,7 @@ __credits__ = \
 
 import string, re
 from codecs import BOM_UTF8, lookup
-from lib2to3.pgen2.token import *
+from blib2to3.pgen2.token import *
 
 from . import token
 __all__ = [x for x in dir(token) if x[0] != '_'] + ["tokenize",
@@ -234,7 +234,7 @@ class Untokenizer:
         for tok in iterable:
             toknum, tokval = tok[:2]
 
-            if toknum in (NAME, NUMBER):
+            if toknum in (NAME, NUMBER, ASYNC, AWAIT):
                 tokval += ' '
 
             if toknum == INDENT:
@@ -380,6 +380,12 @@ def generate_tokens(readline):
     contline = None
     indents = [0]
 
+    # 'stashed' and 'async_*' are used for async/await parsing
+    stashed = None
+    async_def = False
+    async_def_indent = 0
+    async_def_nl = False
+
     while 1:                                   # loop over lines in stream
         try:
             line = readline()
@@ -420,6 +426,14 @@ def generate_tokens(readline):
                 pos = pos + 1
             if pos == max: break
 
+            if stashed:
+                yield stashed
+                stashed = None
+
+            if column > indents[-1]:           # count indents
+                indents.append(column)
+                yield (INDENT, line[:pos], (lnum, 0), (lnum, pos), line)
+
             if line[pos] in '#\r\n':           # skip comments or blank lines
                 if line[pos] == '#':
                     comment_token = line[pos:].rstrip('\r\n')
@@ -433,18 +447,25 @@ def generate_tokens(readline):
                            (lnum, pos), (lnum, len(line)), line)
                 continue
 
-            if column > indents[-1]:           # count indents or dedents
-                indents.append(column)
-                yield (INDENT, line[:pos], (lnum, 0), (lnum, pos), line)
-            while column < indents[-1]:
+            while column < indents[-1]:         # count dedents
                 if column not in indents:
                     raise IndentationError(
                         "unindent does not match any outer indentation level",
                         ("<tokenize>", lnum, pos, line))
                 indents = indents[:-1]
 
+                if async_def and async_def_indent >= indents[-1]:
+                    async_def = False
+                    async_def_nl = False
+                    async_def_indent = 0
+
                 yield (DEDENT, '', (lnum, pos), (lnum, pos), line)
 
+            if async_def and async_def_nl and async_def_indent >= indents[-1]:
+                async_def = False
+                async_def_nl = False
+                async_def_indent = 0
+
         else:                                  # continued statement
             if not line:
                 raise TokenError("EOF in multi-line statement", (lnum, 0))
@@ -464,10 +485,18 @@ def generate_tokens(readline):
                     newline = NEWLINE
                     if parenlev > 0:
                         newline = NL
+                    elif async_def:
+                        async_def_nl = True
+                    if stashed:
+                        yield stashed
+                        stashed = None
                     yield (newline, token, spos, epos, line)
 
                 elif initial == '#':
                     assert not token.endswith("\n")
+                    if stashed:
+                        yield stashed
+                        stashed = None
                     yield (COMMENT, token, spos, epos, line)
                 elif token in triple_quoted:
                     endprog = endprogs[token]
@@ -475,6 +504,9 @@ def generate_tokens(readline):
                     if endmatch:                           # all on one line
                         pos = endmatch.end(0)
                         token = line[start:pos]
+                        if stashed:
+                            yield stashed
+                            stashed = None
                         yield (STRING, token, spos, (lnum, pos), line)
                     else:
                         strstart = (lnum, start)           # multiple lines
@@ -492,22 +524,63 @@ def generate_tokens(readline):
                         contline = line
                         break
                     else:                                  # ordinary string
+                        if stashed:
+                            yield stashed
+                            stashed = None
                         yield (STRING, token, spos, epos, line)
                 elif initial in namechars:                 # ordinary name
-                    yield (NAME, token, spos, epos, line)
+                    if token in ('async', 'await'):
+                        if async_def:
+                            yield (ASYNC if token == 'async' else AWAIT,
+                                   token, spos, epos, line)
+                            continue
+
+                    tok = (NAME, token, spos, epos, line)
+                    if token == 'async' and not stashed:
+                        stashed = tok
+                        continue
+
+                    if token == 'def':
+                        if (stashed
+                                and stashed[0] == NAME
+                                and stashed[1] == 'async'):
+
+                            async_def = True
+                            async_def_indent = indents[-1]
+
+                            yield (ASYNC, stashed[1],
+                                   stashed[2], stashed[3],
+                                   stashed[4])
+                            stashed = None
+
+                    if stashed:
+                        yield stashed
+                        stashed = None
+
+                    yield tok
                 elif initial == '\\':                      # continued stmt
                     # This yield is new; needed for better idempotency:
+                    if stashed:
+                        yield stashed
+                        stashed = None
                     yield (NL, token, spos, (lnum, pos), line)
                     continued = 1
                 else:
                     if initial in '([{': parenlev = parenlev + 1
                     elif initial in ')]}': parenlev = parenlev - 1
+                    if stashed:
+                        yield stashed
+                        stashed = None
                     yield (OP, token, spos, epos, line)
             else:
                 yield (ERRORTOKEN, line[pos],
                            (lnum, pos), (lnum, pos+1), line)
                 pos = pos + 1
 
+    if stashed:
+        yield stashed
+        stashed = None
+
     for indent in indents[1:]:                 # pop remaining indent levels
         yield (DEDENT, '', (lnum, 0), (lnum, 0), '')
     yield (ENDMARKER, '', (lnum, 0), (lnum, 0), '')