Mercurial > cpython-lru_cache-weakref

changeset 68208:378ee328b60e

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Issue #8923: cache str.encode() result When a string is encoded to UTF-8 in strict mode, the result is cached into the object. Examples: str.encode(), str.encode('utf-8'), PyUnicode_AsUTF8String() and PyUnicode_AsEncodedString(unicode, "utf-8", NULL).
author Victor Stinner <victor.stinner@haypocalc.com>
date Wed, 02 Mar 2011 01:03:14 +0000
parents c7a936362281
children a1dbe53f3798
files Misc/NEWS Objects/unicodeobject.c
diffstat 2 files changed, 21 insertions(+), 9 deletions(-) [+]
line wrap: on
line diff
--- a/Misc/NEWS	Wed Mar 02 01:03:11 2011 +0000
+++ b/Misc/NEWS	Wed Mar 02 01:03:14 2011 +0000
@@ -10,6 +10,11 @@
 Core and Builtins
 -----------------
 
+- Issue #8923: When a string is encoded to UTF-8 in strict mode, the result is
+  cached into the object. Examples: str.encode(), str.encode('utf-8'),
+  PyUnicode_AsUTF8String() and PyUnicode_AsEncodedString(unicode, "utf-8",
+  NULL).
+
 - Issue #10831: PyUnicode_FromFormat() supports %li, %lli and %zi formats.
 
 - Issue #10829: Refactor PyUnicode_FromFormat(), use the same function to parse
--- a/Objects/unicodeobject.c	Wed Mar 02 01:03:11 2011 +0000
+++ b/Objects/unicodeobject.c	Wed Mar 02 01:03:14 2011 +0000
@@ -1710,17 +1710,21 @@
     }
 
     if (encoding == NULL)
-        return PyUnicode_EncodeUTF8(PyUnicode_AS_UNICODE(unicode),
-                                    PyUnicode_GET_SIZE(unicode),
-                                    errors);
+        return PyUnicode_AsUTF8String(unicode);
 
     /* Shortcuts for common default encodings */
     if (normalize_encoding(encoding, lower, sizeof(lower))) {
         if ((strcmp(lower, "utf-8") == 0) ||
             (strcmp(lower, "utf8") == 0))
-            return PyUnicode_EncodeUTF8(PyUnicode_AS_UNICODE(unicode),
-                                        PyUnicode_GET_SIZE(unicode),
-                                        errors);
+        {
+            if (errors == NULL || strcmp(errors, "strict") == 0) {
+                return PyUnicode_AsUTF8String(unicode);
+            } else {
+                return PyUnicode_EncodeUTF8(PyUnicode_AS_UNICODE(unicode),
+                                            PyUnicode_GET_SIZE(unicode),
+                                            errors);
+            }
+        }
         else if ((strcmp(lower, "latin-1") == 0) ||
                  (strcmp(lower, "latin1") == 0) ||
                  (strcmp(lower, "iso-8859-1") == 0))
@@ -3077,13 +3081,16 @@
 PyObject *
 PyUnicode_AsUTF8String(PyObject *unicode)
 {
+    PyObject *utf8;
     if (!PyUnicode_Check(unicode)) {
         PyErr_BadArgument();
         return NULL;
     }
-    return PyUnicode_EncodeUTF8(PyUnicode_AS_UNICODE(unicode),
-                                PyUnicode_GET_SIZE(unicode),
-                                NULL);
+    utf8 = _PyUnicode_AsDefaultEncodedString(unicode);
+    if (utf8 == NULL)
+        return NULL;
+    Py_INCREF(utf8);
+    return utf8;
 }
 
 /* --- UTF-32 Codec ------------------------------------------------------- */