#16152: fix tokenize to ignore whitespace at the end of the code when no...

#16152: fix tokenize to ignore whitespace at the end of the code when no newline is found.  Patch by Ned Batchelder.

Lib/test/test_tokenize.py

@@ -550,6 +550,10 @@ Evil tabs
     NAME       'pass'        (3, 9) (3, 13)
     DEDENT     ''            (4, 0) (4, 0)
     DEDENT     ''            (4, 0) (4, 0)
+
+Pathological whitespace (http://bugs.python.org/issue16152)
+    >>> dump_tokens("@          ")
+    OP         '@'           (1, 0) (1, 1)
 """
 
 

Lib/tokenize.py

@@ -95,7 +95,7 @@ ContStr = group(r"[uUbB]?[rR]?'[^\n'\\]*(?:\\.[^\n'\\]*)*" +
                 group("'", r'\\\r?\n'),
                 r'[uUbB]?[rR]?"[^\n"\\]*(?:\\.[^\n"\\]*)*' +
                 group('"', r'\\\r?\n'))
-PseudoExtras = group(r'\\\r?\n', Comment, Triple)
+PseudoExtras = group(r'\\\r?\n|\Z', Comment, Triple)
 PseudoToken = Whitespace + group(PseudoExtras, Number, Funny, ContStr, Name)
 
 tokenprog, pseudoprog, single3prog, double3prog = map(
@@ -362,6 +362,8 @@ def generate_tokens(readline):
             if pseudomatch:                                # scan for tokens
                 start, end = pseudomatch.span(1)
                 spos, epos, pos = (lnum, start), (lnum, end), end
+                if start == end:
+                    continue
                 token, initial = line[start:end], line[start]
 
                 if initial in numchars or \

Misc/ACKS

@@ -64,6 +64,7 @@ Des Barry
 Ulf Bartelt
 Don Bashford
 Nick Bastin
+Ned Batchelder
 Jeff Bauer
 Mike Bayer
 Michael R Bax

Misc/NEWS

@@ -130,6 +130,9 @@ Core and Builtins
 Library
 -------
 
+- Issue #16152: fix tokenize to ignore whitespace at the end of the code when
+  no newline is found.  Patch by Ned Batchelder.
+
 - Issue #1207589: Add Cut/Copy/Paste items to IDLE right click Context Menu
   Patch by Todd Rovito.