Issue #26581: Use the first coding cookie on a line, not the last one.

diff --git a/Lib/idlelib/IOBinding.py b/Lib/idlelib/IOBinding.py
index a4cc205c3072ec5e4007855669eca8149de5c1a4..84f39a2fee8e55d4aed872d0b066fe05d4157735 100644 (file)
--- a/Lib/idlelib/IOBinding.py
+++ b/Lib/idlelib/IOBinding.py
@@ -62,7 +62,7 @@ locale_encoding = locale_encoding.lower()
 encoding = locale_encoding  ### KBK 07Sep07  This is used all over IDLE, check!
                             ### 'encoding' is used below in encode(), check!
 
-coding_re = re.compile(r'^[ \t\f]*#.*coding[:=][ \t]*([-\w.]+)', re.ASCII)
+coding_re = re.compile(r'^[ \t\f]*#.*?coding[:=][ \t]*([-\w.]+)', re.ASCII)
 blank_re = re.compile(r'^[ \t\f]*(?:[#\r\n]|$)', re.ASCII)
 
 def coding_spec(data):

diff --git a/Lib/lib2to3/pgen2/tokenize.py b/Lib/lib2to3/pgen2/tokenize.py
index 1ff1c61ee2250a8114be4fb8e09d05134552baf7..d14db60f7da89ea4d63e9a1af1c30e70ac4aeb1b 100644 (file)
--- a/Lib/lib2to3/pgen2/tokenize.py
+++ b/Lib/lib2to3/pgen2/tokenize.py
@@ -236,7 +236,7 @@ class Untokenizer:
                 startline = False
             toks_append(tokval)
 
-cookie_re = re.compile(r'^[ \t\f]*#.*coding[:=][ \t]*([-\w.]+)', re.ASCII)
+cookie_re = re.compile(r'^[ \t\f]*#.*?coding[:=][ \t]*([-\w.]+)', re.ASCII)
 blank_re = re.compile(br'^[ \t\f]*(?:[#\r\n]|$)', re.ASCII)
 
 def _get_normal_name(orig_enc):

diff --git a/Lib/test/test_importlib/source/test_source_encoding.py b/Lib/test/test_importlib/source/test_source_encoding.py
index b604afb5ec882dbf6ac34f98a6e7e81f678bc2cd..1e0771b19debce6521a947e8c8a7e578cbe312d7 100644 (file)
--- a/Lib/test/test_importlib/source/test_source_encoding.py
+++ b/Lib/test/test_importlib/source/test_source_encoding.py
@@ -14,7 +14,7 @@ import unittest
 import warnings
 
 
-CODING_RE = re.compile(r'^[ \t\f]*#.*coding[:=][ \t]*([-\w.]+)', re.ASCII)
+CODING_RE = re.compile(r'^[ \t\f]*#.*?coding[:=][ \t]*([-\w.]+)', re.ASCII)
 
 
 class EncodingTest:

diff --git a/Lib/test/test_source_encoding.py b/Lib/test/test_source_encoding.py
index 7979c820109c9c56fb2900fb6a570364ef987071..38734009c0085248de1b92841d787b79715415b6 100644 (file)
--- a/Lib/test/test_source_encoding.py
+++ b/Lib/test/test_source_encoding.py
@@ -178,7 +178,7 @@ class AbstractSourceEncodingTest:
     def test_double_coding_same_line(self):
         src = (b'#coding:iso8859-15 coding:latin1\n'
                b'print(ascii("\xc3\xa4"))\n')
-        self.check_script_output(src, br"'\xc3\xa4'")
+        self.check_script_output(src, br"'\xc3\u20ac'")
 
     def test_first_non_utf8_coding_line(self):
         src = (b'#coding:iso-8859-15 \xa4\n'

diff --git a/Lib/tokenize.py b/Lib/tokenize.py
index 9fd676c5b24b36ff8eadbfdc1b6e4c296af86940..b1d0c8326361939a45f62ba147c9214ae685470c 100644 (file)
--- a/Lib/tokenize.py
+++ b/Lib/tokenize.py
@@ -33,7 +33,7 @@ import re
 import sys
 from token import *
 
-cookie_re = re.compile(r'^[ \t\f]*#.*coding[:=][ \t]*([-\w.]+)', re.ASCII)
+cookie_re = re.compile(r'^[ \t\f]*#.*?coding[:=][ \t]*([-\w.]+)', re.ASCII)
 blank_re = re.compile(br'^[ \t\f]*(?:[#\r\n]|$)', re.ASCII)
 
 import token

diff --git a/Misc/NEWS b/Misc/NEWS
index bdcfebf856545390cd284de5d091220689be89d9..b5672c228baa9f21076604cef1f4e1ce750b991a 100644 (file)
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -10,6 +10,9 @@ Release date: tba
 Core and Builtins
 -----------------
 
+- Issue #26581: If coding cookie is specified multiple times on a line in
+  Python source code file, only the first one is taken to account.
+
 - Issue #26464: Fix str.translate() when string is ASCII and first replacements
   removes character, but next replacement uses a non-ASCII character or a
   string longer than 1 character. Regression introduced in Python 3.5.0.

diff --git a/Parser/tokenizer.c b/Parser/tokenizer.c
index 1cdbae20dc4bc69b5abc17a19db36fa86dd3f1a5..50ce2e88c969356c07be01c90c6a9fe9040d5a68 100644 (file)
--- a/Parser/tokenizer.c
+++ b/Parser/tokenizer.c
@@ -275,6 +275,7 @@ get_coding_spec(const char *s, char **spec, Py_ssize_t size, struct tok_state *t
                         return 0;
                 }
                 *spec = r;
+                break;
             }
         }
     }

diff --git a/Tools/scripts/findnocoding.py b/Tools/scripts/findnocoding.py
index 5f3795e65754dbcfbf70c2a0028532628b5b75f8..6c16b1ce151852da1a54e7aedb515c0e5c898290 100755 (executable)
--- a/Tools/scripts/findnocoding.py
+++ b/Tools/scripts/findnocoding.py
@@ -32,7 +32,7 @@ except ImportError:
                          "no sophisticated Python source file search will be done.", file=sys.stderr)
 
 
-decl_re = re.compile(rb'^[ \t\f]*#.*coding[:=][ \t]*([-\w.]+)')
+decl_re = re.compile(rb'^[ \t\f]*#.*?coding[:=][ \t]*([-\w.]+)')
 blank_re = re.compile(rb'^[ \t\f]*(?:[#\r\n]|$)')
 
 def get_declaration(line):