[Python-checkins] cpython (merge 3.5 -> default): Merge 3.5

[victor.stinner]

https://hg.python.org/cpython/rev/aafbe5042024
changeset:   100380:aafbe5042024
parent:      100378:c092148a1b55
parent:      100379:27ba9ba5deb1
user:        Victor Stinner <victor.stinner at gmail.com>
date:        Tue Mar 01 21:30:50 2016 +0100
summary:
  Merge 3.5

files:
  Lib/test/test_unicode.py |  4 ++++
  Misc/NEWS                |  4 ++++
  Objects/unicodeobject.c  |  7 ++++---
  3 files changed, 12 insertions(+), 3 deletions(-)


diff --git a/Lib/test/test_unicode.py b/Lib/test/test_unicode.py
--- a/Lib/test/test_unicode.py
+++ b/Lib/test/test_unicode.py
@@ -347,6 +347,10 @@
                          "[a]")
         self.assertEqual("[\xe9]".translate(str.maketrans({'\xe9': None})),
                          "[]")
+        self.assertEqual('axb'.translate(str.maketrans({'a': None, 'b': '123'})),
+                         "x123")
+        self.assertEqual('axb'.translate(str.maketrans({'a': None, 'b': '\xe9'})),
+                         "x\xe9")
 
         # invalid Unicode characters
         invalid_char = 0x10ffff+1
diff --git a/Misc/NEWS b/Misc/NEWS
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -10,6 +10,10 @@
 Core and Builtins
 -----------------
 
+- 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.
+
 - Issue #22836: Ensure exception reports from PyErr_Display() and
   PyErr_WriteUnraisable() are sensible even when formatting them produces
   secondary errors.  This affects the reports produced by
diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
--- a/Objects/unicodeobject.c
+++ b/Objects/unicodeobject.c
@@ -8783,7 +8783,8 @@
    translated into writer, raise an exception and return -1 on error. */
 static int
 unicode_fast_translate(PyObject *input, PyObject *mapping,
-                       _PyUnicodeWriter *writer, int ignore)
+                       _PyUnicodeWriter *writer, int ignore,
+                       Py_ssize_t *input_pos)
 {
     Py_UCS1 ascii_table[128], ch, ch2;
     Py_ssize_t len;
@@ -8830,6 +8831,7 @@
 
 exit:
     writer->pos = out - PyUnicode_1BYTE_DATA(writer->buffer);
+    *input_pos = in - PyUnicode_1BYTE_DATA(input);
     return res;
 }
 
@@ -8875,7 +8877,7 @@
 
     ignore = (errors != NULL && strcmp(errors, "ignore") == 0);
 
-    res = unicode_fast_translate(input, mapping, &writer, ignore);
+    res = unicode_fast_translate(input, mapping, &writer, ignore, &i);
     if (res < 0) {
         _PyUnicodeWriter_Dealloc(&writer);
         return NULL;
@@ -8883,7 +8885,6 @@
     if (res == 1)
         return _PyUnicodeWriter_Finish(&writer);
 
-    i = writer.pos;
     while (i<size) {
         /* try to encode it */
         int translate;

-- 
Repository URL: https://hg.python.org/cpython