From 145f9db4a999a387c22e735e37918e3c0b28228a Mon Sep 17 00:00:00 2001
From: Serhiy Storchaka <storchaka@gmail.com>
Date: Sun, 9 Oct 2016 23:44:48 +0300
Subject: Issue #28400: Removed uncessary checks in unicode_char and
 resize_copy.

1. In resize_copy we don't need to PyUnicode_READY(unicode) since when
it's not PyUnicode_WCHAR_KIND it should be ready.
2. In unicode_char, PyUnicode_1BYTE_KIND is handled by get_latin1_char.

Patch by Xiang Zhang.
---
 Objects/unicodeobject.c | 14 +++++---------
 1 file changed, 5 insertions(+), 9 deletions(-)

(limited to 'Objects/unicodeobject.c')

diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
index b58cf02a8c..8f34e01232 100644
--- a/Objects/unicodeobject.c
+++ b/Objects/unicodeobject.c
@@ -1029,8 +1029,7 @@ resize_copy(PyObject *unicode, Py_ssize_t length)
     if (_PyUnicode_KIND(unicode) != PyUnicode_WCHAR_KIND) {
         PyObject *copy;
 
-        if (PyUnicode_READY(unicode) == -1)
-            return NULL;
+        assert(PyUnicode_IS_READY(unicode));
 
         copy = PyUnicode_New(length, PyUnicode_MAX_CHAR_VALUE(unicode));
         if (copy == NULL)
@@ -1974,14 +1973,11 @@ unicode_char(Py_UCS4 ch)
     unicode = PyUnicode_New(1, ch);
     if (unicode == NULL)
         return NULL;
-    switch (PyUnicode_KIND(unicode)) {
-    case PyUnicode_1BYTE_KIND:
-        PyUnicode_1BYTE_DATA(unicode)[0] = (Py_UCS1)ch;
-        break;
-    case PyUnicode_2BYTE_KIND:
+
+    assert(PyUnicode_KIND(unicode) != PyUnicode_1BYTE_KIND);
+    if (PyUnicode_KIND(unicode) == PyUnicode_2BYTE_KIND) {
         PyUnicode_2BYTE_DATA(unicode)[0] = (Py_UCS2)ch;
-        break;
-    default:
+    } else {
         assert(PyUnicode_KIND(unicode) == PyUnicode_4BYTE_KIND);
         PyUnicode_4BYTE_DATA(unicode)[0] = ch;
     }
-- 
cgit v1.2.1


From 1838227e043f62a985ee112c3666b214696a27d7 Mon Sep 17 00:00:00 2001
From: Serhiy Storchaka <storchaka@gmail.com>
Date: Sat, 22 Oct 2016 23:18:31 +0300
Subject: Issue #28504: Cleanup unicode_decode_call_errorhandler_wchar/writer.
 Patch by Xiang Zhang.

---
 Objects/unicodeobject.c | 24 ++++++++----------------
 1 file changed, 8 insertions(+), 16 deletions(-)

(limited to 'Objects/unicodeobject.c')

diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
index 05f4d30e08..af95bb6b4a 100644
--- a/Objects/unicodeobject.c
+++ b/Objects/unicodeobject.c
@@ -4240,7 +4240,7 @@ unicode_decode_call_errorhandler_wchar(
     Py_ssize_t *endinpos, PyObject **exceptionObject, const char **inptr,
     PyObject **output, Py_ssize_t *outpos)
 {
-    static const char *argparse = "O!n;decoding error handler must return (str, int) tuple";
+    static const char *argparse = "Un;decoding error handler must return (str, int) tuple";
 
     PyObject *restuple = NULL;
     PyObject *repunicode = NULL;
@@ -4273,10 +4273,10 @@ unicode_decode_call_errorhandler_wchar(
     if (restuple == NULL)
         goto onError;
     if (!PyTuple_Check(restuple)) {
-        PyErr_SetString(PyExc_TypeError, &argparse[4]);
+        PyErr_SetString(PyExc_TypeError, &argparse[3]);
         goto onError;
     }
-    if (!PyArg_ParseTuple(restuple, argparse, &PyUnicode_Type, &repunicode, &newpos))
+    if (!PyArg_ParseTuple(restuple, argparse, &repunicode, &newpos))
         goto onError;
 
     /* Copy back the bytes variables, which might have been modified by the
@@ -4284,9 +4284,6 @@ unicode_decode_call_errorhandler_wchar(
     inputobj = PyUnicodeDecodeError_GetObject(*exceptionObject);
     if (!inputobj)
         goto onError;
-    if (!PyBytes_Check(inputobj)) {
-        PyErr_Format(PyExc_TypeError, "exception attribute object must be bytes");
-    }
     *input = PyBytes_AS_STRING(inputobj);
     insize = PyBytes_GET_SIZE(inputobj);
     *inend = *input + insize;
@@ -4327,7 +4324,7 @@ unicode_decode_call_errorhandler_wchar(
     *inptr = *input + newpos;
 
     /* we made it! */
-    Py_XDECREF(restuple);
+    Py_DECREF(restuple);
     return 0;
 
   overflow:
@@ -4348,7 +4345,7 @@ unicode_decode_call_errorhandler_writer(
     Py_ssize_t *endinpos, PyObject **exceptionObject, const char **inptr,
     _PyUnicodeWriter *writer /* PyObject **output, Py_ssize_t *outpos */)
 {
-    static const char *argparse = "O!n;decoding error handler must return (str, int) tuple";
+    static const char *argparse = "Un;decoding error handler must return (str, int) tuple";
 
     PyObject *restuple = NULL;
     PyObject *repunicode = NULL;
@@ -4375,10 +4372,10 @@ unicode_decode_call_errorhandler_writer(
     if (restuple == NULL)
         goto onError;
     if (!PyTuple_Check(restuple)) {
-        PyErr_SetString(PyExc_TypeError, &argparse[4]);
+        PyErr_SetString(PyExc_TypeError, &argparse[3]);
         goto onError;
     }
-    if (!PyArg_ParseTuple(restuple, argparse, &PyUnicode_Type, &repunicode, &newpos))
+    if (!PyArg_ParseTuple(restuple, argparse, &repunicode, &newpos))
         goto onError;
 
     /* Copy back the bytes variables, which might have been modified by the
@@ -4386,9 +4383,6 @@ unicode_decode_call_errorhandler_writer(
     inputobj = PyUnicodeDecodeError_GetObject(*exceptionObject);
     if (!inputobj)
         goto onError;
-    if (!PyBytes_Check(inputobj)) {
-        PyErr_Format(PyExc_TypeError, "exception attribute object must be bytes");
-    }
     *input = PyBytes_AS_STRING(inputobj);
     insize = PyBytes_GET_SIZE(inputobj);
     *inend = *input + insize;
@@ -4403,8 +4397,6 @@ unicode_decode_call_errorhandler_writer(
         goto onError;
     }
 
-    if (PyUnicode_READY(repunicode) < 0)
-        goto onError;
     replen = PyUnicode_GET_LENGTH(repunicode);
     if (replen > 1) {
         writer->min_length += replen - 1;
@@ -4420,7 +4412,7 @@ unicode_decode_call_errorhandler_writer(
     *inptr = *input + newpos;
 
     /* we made it! */
-    Py_XDECREF(restuple);
+    Py_DECREF(restuple);
     return 0;
 
   onError:
-- 
cgit v1.2.1


From 6ed55b2d31ec9afacbecd309d2c3a4c099848a6c Mon Sep 17 00:00:00 2001
From: Serhiy Storchaka <storchaka@gmail.com>
Date: Sun, 23 Oct 2016 15:12:25 +0300
Subject: Issue #28511: Use the "U" format instead of "O!" in PyArg_Parse*.

---
 Objects/unicodeobject.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'Objects/unicodeobject.c')

diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
index af95bb6b4a..6ab691ff25 100644
--- a/Objects/unicodeobject.c
+++ b/Objects/unicodeobject.c
@@ -8621,7 +8621,7 @@ unicode_translate_call_errorhandler(const char *errors,
                                     Py_ssize_t startpos, Py_ssize_t endpos,
                                     Py_ssize_t *newpos)
 {
-    static const char *argparse = "O!n;translating error handler must return (str, int) tuple";
+    static const char *argparse = "Un;translating error handler must return (str, int) tuple";
 
     Py_ssize_t i_newpos;
     PyObject *restuple;
@@ -8643,11 +8643,11 @@ unicode_translate_call_errorhandler(const char *errors,
     if (restuple == NULL)
         return NULL;
     if (!PyTuple_Check(restuple)) {
-        PyErr_SetString(PyExc_TypeError, &argparse[4]);
+        PyErr_SetString(PyExc_TypeError, &argparse[3]);
         Py_DECREF(restuple);
         return NULL;
     }
-    if (!PyArg_ParseTuple(restuple, argparse, &PyUnicode_Type,
+    if (!PyArg_ParseTuple(restuple, argparse,
                           &resunicode, &i_newpos)) {
         Py_DECREF(restuple);
         return NULL;
-- 
cgit v1.2.1


From 5303b85718c671e17716d3ddfb4f1440ca4abef0 Mon Sep 17 00:00:00 2001
From: Serhiy Storchaka <storchaka@gmail.com>
Date: Sun, 23 Oct 2016 15:41:36 +0300
Subject: Issue #28439: Remove redundant checks in PyUnicode_EncodeLocale and
 PyUnicode_DecodeLocaleAndSize.  Patch by Xiang Zhang.

---
 Objects/unicodeobject.c | 47 ++++++++++++++++++++---------------------------
 1 file changed, 20 insertions(+), 27 deletions(-)

(limited to 'Objects/unicodeobject.c')

diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
index 6ab691ff25..cd8b33c594 100644
--- a/Objects/unicodeobject.c
+++ b/Objects/unicodeobject.c
@@ -3400,11 +3400,9 @@ PyUnicode_EncodeLocale(PyObject *unicode, const char *errors)
 {
     Py_ssize_t wlen, wlen2;
     wchar_t *wstr;
-    PyObject *bytes = NULL;
     char *errmsg;
-    PyObject *reason = NULL;
-    PyObject *exc;
-    size_t error_pos;
+    PyObject *bytes, *reason, *exc;
+    size_t error_pos, errlen;
     int surrogateescape;
 
     if (locale_error_handler(errors, &surrogateescape) < 0)
@@ -3459,6 +3457,7 @@ PyUnicode_EncodeLocale(PyObject *unicode, const char *errors)
 
         len2 = wcstombs(PyBytes_AS_STRING(bytes), wstr, len+1);
         if (len2 == (size_t)-1 || len2 > len) {
+            Py_DECREF(bytes);
             error_pos = (size_t)-1;
             goto encode_error;
         }
@@ -3474,17 +3473,15 @@ encode_error:
         error_pos = wcstombs_errorpos(wstr);
 
     PyMem_Free(wstr);
-    Py_XDECREF(bytes);
-
-    if (errmsg != NULL) {
-        size_t errlen;
-        wstr = Py_DecodeLocale(errmsg, &errlen);
-        if (wstr != NULL) {
-            reason = PyUnicode_FromWideChar(wstr, errlen);
-            PyMem_RawFree(wstr);
-        } else
-            errmsg = NULL;
+
+    wstr = Py_DecodeLocale(errmsg, &errlen);
+    if (wstr != NULL) {
+        reason = PyUnicode_FromWideChar(wstr, errlen);
+        PyMem_RawFree(wstr);
+    } else {
+        errmsg = NULL;
     }
+
     if (errmsg == NULL)
         reason = PyUnicode_FromString(
             "wcstombs() encountered an unencodable "
@@ -3500,7 +3497,7 @@ encode_error:
     Py_DECREF(reason);
     if (exc != NULL) {
         PyCodec_StrictErrors(exc);
-        Py_XDECREF(exc);
+        Py_DECREF(exc);
     }
     return NULL;
 }
@@ -3702,10 +3699,9 @@ PyUnicode_DecodeLocaleAndSize(const char *str, Py_ssize_t len,
     size_t wlen, wlen2;
     PyObject *unicode;
     int surrogateescape;
-    size_t error_pos;
+    size_t error_pos, errlen;
     char *errmsg;
-    PyObject *reason = NULL;   /* initialize to prevent gcc warning */
-    PyObject *exc;
+    PyObject *exc, *reason = NULL;   /* initialize to prevent gcc warning */
 
     if (locale_error_handler(errors, &surrogateescape) < 0)
         return NULL;
@@ -3763,19 +3759,16 @@ PyUnicode_DecodeLocaleAndSize(const char *str, Py_ssize_t len,
     return unicode;
 
 decode_error:
-    reason = NULL;
     errmsg = strerror(errno);
     assert(errmsg != NULL);
 
     error_pos = mbstowcs_errorpos(str, len);
-    if (errmsg != NULL) {
-        size_t errlen;
-        wstr = Py_DecodeLocale(errmsg, &errlen);
-        if (wstr != NULL) {
-            reason = PyUnicode_FromWideChar(wstr, errlen);
-            PyMem_RawFree(wstr);
-        }
+    wstr = Py_DecodeLocale(errmsg, &errlen);
+    if (wstr != NULL) {
+        reason = PyUnicode_FromWideChar(wstr, errlen);
+        PyMem_RawFree(wstr);
     }
+
     if (reason == NULL)
         reason = PyUnicode_FromString(
             "mbstowcs() encountered an invalid multibyte sequence");
@@ -3790,7 +3783,7 @@ decode_error:
     Py_DECREF(reason);
     if (exc != NULL) {
         PyCodec_StrictErrors(exc);
-        Py_XDECREF(exc);
+        Py_DECREF(exc);
     }
     return NULL;
 }
-- 
cgit v1.2.1


From 770891917b1ffe9eb66e72c61355c3a95d4a6db5 Mon Sep 17 00:00:00 2001
From: "Eric V. Smith" <eric@trueblade.com>
Date: Mon, 31 Oct 2016 09:22:08 -0400
Subject: Issue 28128: Print out better error/warning messages for invalid
 string escapes.

---
 Objects/unicodeobject.c | 38 ++++++++++++++++++++++++++++++++------
 1 file changed, 32 insertions(+), 6 deletions(-)

(limited to 'Objects/unicodeobject.c')

diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
index 134fa07600..6e63e009a9 100644
--- a/Objects/unicodeobject.c
+++ b/Objects/unicodeobject.c
@@ -5877,9 +5877,10 @@ PyUnicode_AsUTF16String(PyObject *unicode)
 static _PyUnicode_Name_CAPI *ucnhash_CAPI = NULL;
 
 PyObject *
-PyUnicode_DecodeUnicodeEscape(const char *s,
-                              Py_ssize_t size,
-                              const char *errors)
+_PyUnicode_DecodeUnicodeEscape(const char *s,
+                               Py_ssize_t size,
+                               const char *errors,
+                               const char **first_invalid_escape)
 {
     const char *starts = s;
     _PyUnicodeWriter writer;
@@ -5887,6 +5888,9 @@ PyUnicode_DecodeUnicodeEscape(const char *s,
     PyObject *errorHandler = NULL;
     PyObject *exc = NULL;
 
+    // so we can remember if we've seen an invalid escape char or not
+    *first_invalid_escape = NULL;
+
     if (size == 0) {
         _Py_RETURN_UNICODE_EMPTY();
     }
@@ -6061,9 +6065,10 @@ PyUnicode_DecodeUnicodeEscape(const char *s,
             goto error;
 
         default:
-            if (PyErr_WarnFormat(PyExc_DeprecationWarning, 1,
-                                 "invalid escape sequence '\\%c'", c) < 0)
-                goto onError;
+            if (*first_invalid_escape == NULL) {
+                *first_invalid_escape = s-1; /* Back up one char, since we've
+                                                already incremented s. */
+            }
             WRITE_ASCII_CHAR('\\');
             WRITE_CHAR(c);
             continue;
@@ -6098,6 +6103,27 @@ PyUnicode_DecodeUnicodeEscape(const char *s,
     return NULL;
 }
 
+PyObject *
+PyUnicode_DecodeUnicodeEscape(const char *s,
+                              Py_ssize_t size,
+                              const char *errors)
+{
+    const char *first_invalid_escape;
+    PyObject *result = _PyUnicode_DecodeUnicodeEscape(s, size, errors,
+                                                      &first_invalid_escape);
+    if (result == NULL)
+        return NULL;
+    if (first_invalid_escape != NULL) {
+        if (PyErr_WarnFormat(PyExc_DeprecationWarning, 1,
+                             "invalid escape sequence '\\%c'",
+                             *first_invalid_escape) < 0) {
+            Py_DECREF(result);
+            return NULL;
+        }
+    }
+    return result;
+}
+
 /* Return a Unicode-Escape string version of the Unicode object.
 
    If quotes is true, the string is enclosed in u"" or u'' quotes as
-- 
cgit v1.2.1


From ba86008aac6890c5c4a2c6d30ea8110f228d483e Mon Sep 17 00:00:00 2001
From: Serhiy Storchaka <storchaka@gmail.com>
Date: Sun, 20 Nov 2016 12:16:46 +0200
Subject: Issue #19569: Compiler warnings are now emitted if use most of
 deprecated functions.

---
 Objects/unicodeobject.c | 94 +++++++++++++++++++++++--------------------------
 1 file changed, 45 insertions(+), 49 deletions(-)

(limited to 'Objects/unicodeobject.c')

diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
index 02f726d0ce..0e88fca43f 100644
--- a/Objects/unicodeobject.c
+++ b/Objects/unicodeobject.c
@@ -1987,13 +1987,33 @@ unicode_char(Py_UCS4 ch)
 
 PyObject *
 PyUnicode_FromUnicode(const Py_UNICODE *u, Py_ssize_t size)
+{
+    if (u == NULL)
+        return (PyObject*)_PyUnicode_New(size);
+
+    if (size < 0) {
+        PyErr_BadInternalCall();
+        return NULL;
+    }
+
+    return PyUnicode_FromWideChar(u, size);
+}
+
+PyObject *
+PyUnicode_FromWideChar(const wchar_t *u, Py_ssize_t size)
 {
     PyObject *unicode;
     Py_UCS4 maxchar = 0;
     Py_ssize_t num_surrogates;
 
-    if (u == NULL)
-        return (PyObject*)_PyUnicode_New(size);
+    if (u == NULL && size != 0) {
+        PyErr_BadInternalCall();
+        return NULL;
+    }
+
+    if (size == -1) {
+        size = wcslen(u);
+    }
 
     /* If the Unicode data is known at construction time, we can apply
        some optimizations which share commonly used objects. */
@@ -2478,27 +2498,6 @@ PyUnicode_AsUCS4Copy(PyObject *string)
     return as_ucs4(string, NULL, 0, 1);
 }
 
-#ifdef HAVE_WCHAR_H
-
-PyObject *
-PyUnicode_FromWideChar(const wchar_t *w, Py_ssize_t size)
-{
-    if (w == NULL) {
-        if (size == 0)
-            _Py_RETURN_UNICODE_EMPTY();
-        PyErr_BadInternalCall();
-        return NULL;
-    }
-
-    if (size == -1) {
-        size = wcslen(w);
-    }
-
-    return PyUnicode_FromUnicode(w, size);
-}
-
-#endif /* HAVE_WCHAR_H */
-
 /* maximum number of characters required for output of %lld or %p.
    We need at most ceil(log10(256)*SIZEOF_LONG_LONG) digits,
    plus 1 for the sign.  53/22 is an upper bound for log10(256). */
@@ -3296,7 +3295,7 @@ PyUnicode_Encode(const Py_UNICODE *s,
 {
     PyObject *v, *unicode;
 
-    unicode = PyUnicode_FromUnicode(s, size);
+    unicode = PyUnicode_FromWideChar(s, size);
     if (unicode == NULL)
         return NULL;
     v = PyUnicode_AsEncodedString(unicode, encoding, errors);
@@ -4129,7 +4128,11 @@ PyUnicode_GetSize(PyObject *unicode)
         PyErr_BadArgument();
         goto onError;
     }
-    return PyUnicode_GET_SIZE(unicode);
+    if (_PyUnicode_WSTR(unicode) == NULL) {
+        if (PyUnicode_AsUnicode(unicode) == NULL)
+            goto onError;
+    }
+    return PyUnicode_WSTR_LENGTH(unicode);
 
   onError:
     return -1;
@@ -4815,7 +4818,7 @@ PyUnicode_EncodeUTF7(const Py_UNICODE *s,
                      const char *errors)
 {
     PyObject *result;
-    PyObject *tmp = PyUnicode_FromUnicode(s, size);
+    PyObject *tmp = PyUnicode_FromWideChar(s, size);
     if (tmp == NULL)
         return NULL;
     result = _PyUnicode_EncodeUTF7(tmp, base64SetO,
@@ -5171,7 +5174,7 @@ PyUnicode_EncodeUTF8(const Py_UNICODE *s,
 {
     PyObject *v, *unicode;
 
-    unicode = PyUnicode_FromUnicode(s, size);
+    unicode = PyUnicode_FromWideChar(s, size);
     if (unicode == NULL)
         return NULL;
     v = _PyUnicode_AsUTF8String(unicode, errors);
@@ -5496,7 +5499,7 @@ PyUnicode_EncodeUTF32(const Py_UNICODE *s,
                       int byteorder)
 {
     PyObject *result;
-    PyObject *tmp = PyUnicode_FromUnicode(s, size);
+    PyObject *tmp = PyUnicode_FromWideChar(s, size);
     if (tmp == NULL)
         return NULL;
     result = _PyUnicode_EncodeUTF32(tmp, errors, byteorder);
@@ -5849,7 +5852,7 @@ PyUnicode_EncodeUTF16(const Py_UNICODE *s,
                       int byteorder)
 {
     PyObject *result;
-    PyObject *tmp = PyUnicode_FromUnicode(s, size);
+    PyObject *tmp = PyUnicode_FromWideChar(s, size);
     if (tmp == NULL)
         return NULL;
     result = _PyUnicode_EncodeUTF16(tmp, errors, byteorder);
@@ -6246,7 +6249,7 @@ PyUnicode_EncodeUnicodeEscape(const Py_UNICODE *s,
                               Py_ssize_t size)
 {
     PyObject *result;
-    PyObject *tmp = PyUnicode_FromUnicode(s, size);
+    PyObject *tmp = PyUnicode_FromWideChar(s, size);
     if (tmp == NULL) {
         return NULL;
     }
@@ -6463,7 +6466,7 @@ PyUnicode_EncodeRawUnicodeEscape(const Py_UNICODE *s,
                                  Py_ssize_t size)
 {
     PyObject *result;
-    PyObject *tmp = PyUnicode_FromUnicode(s, size);
+    PyObject *tmp = PyUnicode_FromWideChar(s, size);
     if (tmp == NULL)
         return NULL;
     result = PyUnicode_AsRawUnicodeEscapeString(tmp);
@@ -6874,7 +6877,7 @@ PyUnicode_EncodeLatin1(const Py_UNICODE *p,
                        const char *errors)
 {
     PyObject *result;
-    PyObject *unicode = PyUnicode_FromUnicode(p, size);
+    PyObject *unicode = PyUnicode_FromWideChar(p, size);
     if (unicode == NULL)
         return NULL;
     result = unicode_encode_ucs1(unicode, errors, 256);
@@ -7015,7 +7018,7 @@ PyUnicode_EncodeASCII(const Py_UNICODE *p,
                       const char *errors)
 {
     PyObject *result;
-    PyObject *unicode = PyUnicode_FromUnicode(p, size);
+    PyObject *unicode = PyUnicode_FromWideChar(p, size);
     if (unicode == NULL)
         return NULL;
     result = unicode_encode_ucs1(unicode, errors, 128);
@@ -7741,7 +7744,7 @@ PyUnicode_EncodeMBCS(const Py_UNICODE *p,
                      const char *errors)
 {
     PyObject *unicode, *res;
-    unicode = PyUnicode_FromUnicode(p, size);
+    unicode = PyUnicode_FromWideChar(p, size);
     if (unicode == NULL)
         return NULL;
     res = encode_code_page(CP_ACP, unicode, errors);
@@ -8589,7 +8592,7 @@ PyUnicode_EncodeCharmap(const Py_UNICODE *p,
                         const char *errors)
 {
     PyObject *result;
-    PyObject *unicode = PyUnicode_FromUnicode(p, size);
+    PyObject *unicode = PyUnicode_FromWideChar(p, size);
     if (unicode == NULL)
         return NULL;
     result = _PyUnicode_EncodeCharmap(unicode, mapping, errors);
@@ -9029,7 +9032,7 @@ PyUnicode_TranslateCharmap(const Py_UNICODE *p,
                            const char *errors)
 {
     PyObject *result;
-    PyObject *unicode = PyUnicode_FromUnicode(p, size);
+    PyObject *unicode = PyUnicode_FromWideChar(p, size);
     if (!unicode)
         return NULL;
     result = _PyUnicode_TranslateCharmap(unicode, mapping, errors);
@@ -9157,14 +9160,10 @@ PyUnicode_EncodeDecimal(Py_UNICODE *s,
         return -1;
     }
 
-    unicode = PyUnicode_FromUnicode(s, length);
+    unicode = PyUnicode_FromWideChar(s, length);
     if (unicode == NULL)
         return -1;
 
-    if (PyUnicode_READY(unicode) == -1) {
-        Py_DECREF(unicode);
-        return -1;
-    }
     kind = PyUnicode_KIND(unicode);
     data = PyUnicode_DATA(unicode);
 
@@ -15332,7 +15331,7 @@ unicodeiter_reduce(unicodeiterobject *it)
         return Py_BuildValue("N(O)n", _PyObject_GetBuiltin("iter"),
                              it->it_seq, it->it_index);
     } else {
-        PyObject *u = PyUnicode_FromUnicode(NULL, 0);
+        PyObject *u = (PyObject *)_PyUnicode_New(0);
         if (u == NULL)
             return NULL;
         return Py_BuildValue("N(N)", _PyObject_GetBuiltin("iter"), u);
@@ -15427,10 +15426,7 @@ unicode_iter(PyObject *seq)
 size_t
 Py_UNICODE_strlen(const Py_UNICODE *u)
 {
-    int res = 0;
-    while(*u++)
-        res++;
-    return res;
+    return wcslen(u);
 }
 
 Py_UNICODE*
@@ -15455,8 +15451,8 @@ Py_UNICODE*
 Py_UNICODE_strcat(Py_UNICODE *s1, const Py_UNICODE *s2)
 {
     Py_UNICODE *u1 = s1;
-    u1 += Py_UNICODE_strlen(u1);
-    Py_UNICODE_strcpy(u1, s2);
+    u1 += wcslen(u1);
+    while ((*u1++ = *s2++));
     return s1;
 }
 
@@ -15505,7 +15501,7 @@ Py_UNICODE*
 Py_UNICODE_strrchr(const Py_UNICODE *s, Py_UNICODE c)
 {
     const Py_UNICODE *p;
-    p = s + Py_UNICODE_strlen(s);
+    p = s + wcslen(s);
     while (p != s) {
         p--;
         if (*p == c)
-- 
cgit v1.2.1


From ac89262abd868aed4b06bb0ebf898e97fbab6293 Mon Sep 17 00:00:00 2001
From: Xiang Zhang <angwerzx@126.com>
Date: Wed, 23 Nov 2016 19:34:01 +0800
Subject: Issue #28774: Fix start/end pos in unicode_encode_ucs1().

Fix error position of the unicode error in ASCII and Latin1
encoders when a string returned by the error handler contains multiple
non-encodable characters (non-ASCII for the ASCII codec, characters out
of the U+0000-U+00FF range for Latin1).
---
 Objects/unicodeobject.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'Objects/unicodeobject.c')

diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
index e88a126eba..2bf48b756f 100644
--- a/Objects/unicodeobject.c
+++ b/Objects/unicodeobject.c
@@ -6798,7 +6798,7 @@ unicode_encode_ucs1(PyObject *unicode,
                     goto onError;
 
                 /* subtract preallocated bytes */
-                writer.min_size -= 1;
+                writer.min_size -= newpos - collstart;
 
                 if (PyBytes_Check(rep)) {
                     /* Directly copy bytes result to output. */
@@ -6835,7 +6835,7 @@ unicode_encode_ucs1(PyObject *unicode,
                             ch = PyUnicode_READ_CHAR(rep, i);
                             if (ch >= limit) {
                                 raise_encode_exception(&exc, encoding, unicode,
-                                                       pos, pos+1, reason);
+                                                       collstart, collend, reason);
                                 goto onError;
                             }
                             *str = (char)ch;
-- 
cgit v1.2.1


From 2e722071c4726e050d85fd842cd1120288bbbc56 Mon Sep 17 00:00:00 2001
From: Serhiy Storchaka <storchaka@gmail.com>
Date: Wed, 23 Nov 2016 15:13:00 +0200
Subject: Issue #28774: Simplified encoding a str result of an error handler in
 ASCII and Latin1 encoders.

---
 Objects/unicodeobject.c | 38 ++++++++++++--------------------------
 1 file changed, 12 insertions(+), 26 deletions(-)

(limited to 'Objects/unicodeobject.c')

diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
index 2bf48b756f..1c2257e141 100644
--- a/Objects/unicodeobject.c
+++ b/Objects/unicodeobject.c
@@ -6814,33 +6814,19 @@ unicode_encode_ucs1(PyObject *unicode,
                     if (PyUnicode_READY(rep) < 0)
                         goto onError;
 
-                    if (PyUnicode_IS_ASCII(rep)) {
-                        /* Fast path: all characters are smaller than limit */
-                        assert(limit >= 128);
-                        assert(PyUnicode_KIND(rep) == PyUnicode_1BYTE_KIND);
-                        str = _PyBytesWriter_WriteBytes(&writer, str,
-                                                        PyUnicode_DATA(rep),
-                                                        PyUnicode_GET_LENGTH(rep));
-                    }
-                    else {
-                        Py_ssize_t repsize = PyUnicode_GET_LENGTH(rep);
-
-                        str = _PyBytesWriter_Prepare(&writer, str, repsize);
-                        if (str == NULL)
-                            goto onError;
-
-                        /* check if there is anything unencodable in the
-                           replacement and copy it to the output */
-                        for (i = 0; repsize-->0; ++i, ++str) {
-                            ch = PyUnicode_READ_CHAR(rep, i);
-                            if (ch >= limit) {
-                                raise_encode_exception(&exc, encoding, unicode,
-                                                       collstart, collend, reason);
-                                goto onError;
-                            }
-                            *str = (char)ch;
-                        }
+                    if (limit == 256 ?
+                        PyUnicode_KIND(rep) != PyUnicode_1BYTE_KIND :
+                        !PyUnicode_IS_ASCII(rep))
+                    {
+                        /* Not all characters are smaller than limit */
+                        raise_encode_exception(&exc, encoding, unicode,
+                                               collstart, collend, reason);
+                        goto onError;
                     }
+                    assert(PyUnicode_KIND(rep) == PyUnicode_1BYTE_KIND);
+                    str = _PyBytesWriter_WriteBytes(&writer, str,
+                                                    PyUnicode_DATA(rep),
+                                                    PyUnicode_GET_LENGTH(rep));
                 }
                 pos = newpos;
                 Py_CLEAR(rep);
-- 
cgit v1.2.1


From 366f4ee4da4420842eac26b3fa00c2b01d4515a6 Mon Sep 17 00:00:00 2001
From: Victor Stinner <victor.stinner@gmail.com>
Date: Thu, 1 Dec 2016 14:43:22 +0100
Subject: Replace PyObject_CallFunctionObjArgs() with fastcall

* PyObject_CallFunctionObjArgs(func, NULL) => _PyObject_CallNoArg(func)
* PyObject_CallFunctionObjArgs(func, arg, NULL) => _PyObject_CallArg1(func, arg)

PyObject_CallFunctionObjArgs() allocates 40 bytes on the C stack and requires
extra work to "parse" C arguments to build a C array of PyObject*.

_PyObject_CallNoArg() and _PyObject_CallArg1() are simpler and don't allocate
memory on the C stack.

This change is part of the fastcall project. The change on listsort() is
related to the issue #23507.
---
 Objects/unicodeobject.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

(limited to 'Objects/unicodeobject.c')

diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
index 1c2257e141..8f6f6c675f 100644
--- a/Objects/unicodeobject.c
+++ b/Objects/unicodeobject.c
@@ -4269,7 +4269,7 @@ unicode_decode_call_errorhandler_wchar(
     if (*exceptionObject == NULL)
         goto onError;
 
-    restuple = PyObject_CallFunctionObjArgs(*errorHandler, *exceptionObject, NULL);
+    restuple = _PyObject_CallArg1(*errorHandler, *exceptionObject);
     if (restuple == NULL)
         goto onError;
     if (!PyTuple_Check(restuple)) {
@@ -4368,7 +4368,7 @@ unicode_decode_call_errorhandler_writer(
     if (*exceptionObject == NULL)
         goto onError;
 
-    restuple = PyObject_CallFunctionObjArgs(*errorHandler, *exceptionObject, NULL);
+    restuple = _PyObject_CallArg1(*errorHandler, *exceptionObject);
     if (restuple == NULL)
         goto onError;
     if (!PyTuple_Check(restuple)) {
@@ -6649,8 +6649,7 @@ unicode_encode_call_errorhandler(const char *errors,
     if (*exceptionObject == NULL)
         return NULL;
 
-    restuple = PyObject_CallFunctionObjArgs(
-        *errorHandler, *exceptionObject, NULL);
+    restuple = _PyObject_CallArg1(*errorHandler, *exceptionObject);
     if (restuple == NULL)
         return NULL;
     if (!PyTuple_Check(restuple)) {
@@ -8644,8 +8643,7 @@ unicode_translate_call_errorhandler(const char *errors,
     if (*exceptionObject == NULL)
         return NULL;
 
-    restuple = PyObject_CallFunctionObjArgs(
-        *errorHandler, *exceptionObject, NULL);
+    restuple = _PyObject_CallArg1(*errorHandler, *exceptionObject);
     if (restuple == NULL)
         return NULL;
     if (!PyTuple_Check(restuple)) {
-- 
cgit v1.2.1


From 39ae5bedd90f9caf9a78efa82f4d11e838933b3a Mon Sep 17 00:00:00 2001
From: Victor Stinner <victor.stinner@gmail.com>
Date: Sun, 4 Dec 2016 22:59:09 +0100
Subject: Backed out changeset b9c9691c72c5

Issue #28858: The change b9c9691c72c5 introduced a regression. It seems like
_PyObject_CallArg1() uses more stack memory than
PyObject_CallFunctionObjArgs().
---
 Objects/unicodeobject.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

(limited to 'Objects/unicodeobject.c')

diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
index 8f6f6c675f..1c2257e141 100644
--- a/Objects/unicodeobject.c
+++ b/Objects/unicodeobject.c
@@ -4269,7 +4269,7 @@ unicode_decode_call_errorhandler_wchar(
     if (*exceptionObject == NULL)
         goto onError;
 
-    restuple = _PyObject_CallArg1(*errorHandler, *exceptionObject);
+    restuple = PyObject_CallFunctionObjArgs(*errorHandler, *exceptionObject, NULL);
     if (restuple == NULL)
         goto onError;
     if (!PyTuple_Check(restuple)) {
@@ -4368,7 +4368,7 @@ unicode_decode_call_errorhandler_writer(
     if (*exceptionObject == NULL)
         goto onError;
 
-    restuple = _PyObject_CallArg1(*errorHandler, *exceptionObject);
+    restuple = PyObject_CallFunctionObjArgs(*errorHandler, *exceptionObject, NULL);
     if (restuple == NULL)
         goto onError;
     if (!PyTuple_Check(restuple)) {
@@ -6649,7 +6649,8 @@ unicode_encode_call_errorhandler(const char *errors,
     if (*exceptionObject == NULL)
         return NULL;
 
-    restuple = _PyObject_CallArg1(*errorHandler, *exceptionObject);
+    restuple = PyObject_CallFunctionObjArgs(
+        *errorHandler, *exceptionObject, NULL);
     if (restuple == NULL)
         return NULL;
     if (!PyTuple_Check(restuple)) {
@@ -8643,7 +8644,8 @@ unicode_translate_call_errorhandler(const char *errors,
     if (*exceptionObject == NULL)
         return NULL;
 
-    restuple = _PyObject_CallArg1(*errorHandler, *exceptionObject);
+    restuple = PyObject_CallFunctionObjArgs(
+        *errorHandler, *exceptionObject, NULL);
     if (restuple == NULL)
         return NULL;
     if (!PyTuple_Check(restuple)) {
-- 
cgit v1.2.1


From bed50e1fd3e82021bd51be24920880518268372e Mon Sep 17 00:00:00 2001
From: Xiang Zhang <angwerzx@126.com>
Date: Tue, 20 Dec 2016 22:52:33 +0800
Subject: Issue #28822: Adjust indices handling of PyUnicode_FindChar().

---
 Objects/unicodeobject.c | 12 ++++--------
 1 file changed, 4 insertions(+), 8 deletions(-)

(limited to 'Objects/unicodeobject.c')

diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
index 3fdce82ae6..bbda4d884c 100644
--- a/Objects/unicodeobject.c
+++ b/Objects/unicodeobject.c
@@ -9461,16 +9461,12 @@ PyUnicode_FindChar(PyObject *str, Py_UCS4 ch,
                    int direction)
 {
     int kind;
-    Py_ssize_t result;
+    Py_ssize_t len, result;
     if (PyUnicode_READY(str) == -1)
         return -2;
-    if (start < 0 || end < 0) {
-        PyErr_SetString(PyExc_IndexError, "string index out of range");
-        return -2;
-    }
-    if (end > PyUnicode_GET_LENGTH(str))
-        end = PyUnicode_GET_LENGTH(str);
-    if (start >= end)
+    len = PyUnicode_GET_LENGTH(str);
+    ADJUST_INDICES(start, end, len);
+    if (end - start < 1)
         return -1;
     kind = PyUnicode_KIND(str);
     result = findchar(PyUnicode_1BYTE_DATA(str) + kind*start,
-- 
cgit v1.2.1


From 70249059aaa99129a75a69f75dddfb5731a71585 Mon Sep 17 00:00:00 2001
From: INADA Naoki <songofacandy@gmail.com>
Date: Mon, 16 Jan 2017 20:41:20 +0900
Subject: Issue #20180: convert unicode methods to AC.

---
 Objects/unicodeobject.c | 919 +++++++++++++++++++++++++++---------------------
 1 file changed, 511 insertions(+), 408 deletions(-)

(limited to 'Objects/unicodeobject.c')

diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
index e322c0cf25..acf59e4d13 100644
--- a/Objects/unicodeobject.c
+++ b/Objects/unicodeobject.c
@@ -51,7 +51,21 @@ OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
 /*[clinic input]
 class str "PyUnicodeObject *" "&PyUnicode_Type"
 [clinic start generated code]*/
-/*[clinic end generated code: output=da39a3ee5e6b4b0d input=604e916854800fa8]*/
+/*[clinic end generated code: output=da39a3ee5e6b4b0d input=4884c934de622cf6]*/
+
+/*[python input]
+class Py_UCS4_converter(CConverter):
+    type = 'Py_UCS4'
+    converter = 'convert_uc'
+
+    def converter_init(self):
+        if self.default is not unspecified:
+            self.c_default = ascii(self.default)
+            if len(self.c_default) > 4 or self.c_default[0] != "'":
+                self.c_default = hex(ord(self.default))
+
+[python start generated code]*/
+/*[python end generated code: output=da39a3ee5e6b4b0d input=88f5dd06cd8e7a61]*/
 
 /* --- Globals ------------------------------------------------------------
 
@@ -299,6 +313,8 @@ static const unsigned char ascii_linebreak[] = {
     0, 0, 0, 0, 0, 0, 0, 0
 };
 
+static int convert_uc(PyObject *obj, void *addr);
+
 #include "clinic/unicodeobject.c.h"
 
 typedef enum {
@@ -10710,28 +10726,36 @@ replace(PyObject *self, PyObject *str1,
 
 /* --- Unicode Object Methods --------------------------------------------- */
 
-PyDoc_STRVAR(title__doc__,
-             "S.title() -> str\n\
-\n\
-Return a titlecased version of S, i.e. words start with title case\n\
-characters, all remaining cased characters have lower case.");
+/*[clinic input]
+str.title as unicode_title
 
-static PyObject*
-unicode_title(PyObject *self)
+Return a version of the string where each word is titlecased.
+
+More specifically, words start with uppercased characters and all remaining
+cased characters have lower case.
+[clinic start generated code]*/
+
+static PyObject *
+unicode_title_impl(PyObject *self)
+/*[clinic end generated code: output=c75ae03809574902 input=4eb12c1bb8642cb9]*/
 {
     if (PyUnicode_READY(self) == -1)
         return NULL;
     return case_operation(self, do_title);
 }
 
-PyDoc_STRVAR(capitalize__doc__,
-             "S.capitalize() -> str\n\
-\n\
-Return a capitalized version of S, i.e. make the first character\n\
-have upper case and the rest lower case.");
+/*[clinic input]
+str.capitalize as unicode_capitalize
 
-static PyObject*
-unicode_capitalize(PyObject *self)
+Return a capitalized version of the string.
+
+More specifically, make the first character have upper case and the rest lower
+case.
+[clinic start generated code]*/
+
+static PyObject *
+unicode_capitalize_impl(PyObject *self)
+/*[clinic end generated code: output=e49a4c333cdb7667 input=f4cbf1016938da6d]*/
 {
     if (PyUnicode_READY(self) == -1)
         return NULL;
@@ -10740,13 +10764,15 @@ unicode_capitalize(PyObject *self)
     return case_operation(self, do_capitalize);
 }
 
-PyDoc_STRVAR(casefold__doc__,
-             "S.casefold() -> str\n\
-\n\
-Return a version of S suitable for caseless comparisons.");
+/*[clinic input]
+str.casefold as unicode_casefold
+
+Return a version of the string suitable for caseless comparisons.
+[clinic start generated code]*/
 
 static PyObject *
-unicode_casefold(PyObject *self)
+unicode_casefold_impl(PyObject *self)
+/*[clinic end generated code: output=0120daf657ca40af input=a96f2b0d3daabd94]*/
 {
     if (PyUnicode_READY(self) == -1)
         return NULL;
@@ -10780,21 +10806,23 @@ convert_uc(PyObject *obj, void *addr)
     return 1;
 }
 
-PyDoc_STRVAR(center__doc__,
-             "S.center(width[, fillchar]) -> str\n\
-\n\
-Return S centered in a string of length width. Padding is\n\
-done using the specified fill character (default is a space)");
+/*[clinic input]
+str.center as unicode_center
+
+    width: Py_ssize_t
+    fillchar: Py_UCS4 = ' '
+    /
+
+Return a centered string of length width.
+
+Padding is done using the specified fill character (default is a space).
+[clinic start generated code]*/
 
 static PyObject *
-unicode_center(PyObject *self, PyObject *args)
+unicode_center_impl(PyObject *self, Py_ssize_t width, Py_UCS4 fillchar)
+/*[clinic end generated code: output=420c8859effc7c0c input=b42b247eb26e6519]*/
 {
     Py_ssize_t marg, left;
-    Py_ssize_t width;
-    Py_UCS4 fillchar = ' ';
-
-    if (!PyArg_ParseTuple(args, "n|O&:center", &width, convert_uc, &fillchar))
-        return NULL;
 
     if (PyUnicode_READY(self) == -1)
         return NULL;
@@ -11465,51 +11493,49 @@ unicode_count(PyObject *self, PyObject *args)
     return result;
 }
 
-PyDoc_STRVAR(encode__doc__,
-             "S.encode(encoding='utf-8', errors='strict') -> bytes\n\
-\n\
-Encode S using the codec registered for encoding. Default encoding\n\
-is 'utf-8'. errors may be given to set a different error\n\
-handling scheme. Default is 'strict' meaning that encoding errors raise\n\
-a UnicodeEncodeError. Other possible values are 'ignore', 'replace' and\n\
-'xmlcharrefreplace' as well as any other name registered with\n\
-codecs.register_error that can handle UnicodeEncodeErrors.");
+/*[clinic input]
+str.encode as unicode_encode
+
+    encoding: str(c_default="NULL") = 'utf-8'
+        The encoding in which to encode the string.
+    errors: str(c_default="NULL") = 'strict'
+        The error handling scheme to use for encoding errors.
+        The default is 'strict' meaning that encoding errors raise a
+        UnicodeEncodeError.  Other possible values are 'ignore', 'replace' and
+        'xmlcharrefreplace' as well as any other name registered with
+        codecs.register_error that can handle UnicodeEncodeErrors.
+
+Encode the string using the codec registered for encoding.
+[clinic start generated code]*/
 
 static PyObject *
-unicode_encode(PyObject *self, PyObject *args, PyObject *kwargs)
+unicode_encode_impl(PyObject *self, const char *encoding, const char *errors)
+/*[clinic end generated code: output=bf78b6e2a9470e3c input=12fcb2e5798e96dc]*/
 {
-    static char *kwlist[] = {"encoding", "errors", 0};
-    char *encoding = NULL;
-    char *errors = NULL;
-
-    if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|ss:encode",
-                                     kwlist, &encoding, &errors))
-        return NULL;
     return PyUnicode_AsEncodedString(self, encoding, errors);
 }
 
-PyDoc_STRVAR(expandtabs__doc__,
-             "S.expandtabs(tabsize=8) -> str\n\
-\n\
-Return a copy of S where all tab characters are expanded using spaces.\n\
-If tabsize is not given, a tab size of 8 characters is assumed.");
+/*[clinic input]
+str.expandtabs as unicode_expandtabs
 
-static PyObject*
-unicode_expandtabs(PyObject *self, PyObject *args, PyObject *kwds)
+    tabsize: int = 8
+
+Return a copy where all tab characters are expanded using spaces.
+
+If tabsize is not given, a tab size of 8 characters is assumed.
+[clinic start generated code]*/
+
+static PyObject *
+unicode_expandtabs_impl(PyObject *self, int tabsize)
+/*[clinic end generated code: output=3457c5dcee26928f input=8a01914034af4c85]*/
 {
     Py_ssize_t i, j, line_pos, src_len, incr;
     Py_UCS4 ch;
     PyObject *u;
     void *src_data, *dest_data;
-    static char *kwlist[] = {"tabsize", 0};
-    int tabsize = 8;
     int kind;
     int found;
 
-    if (!PyArg_ParseTupleAndKeywords(args, kwds, "|i:expandtabs",
-                                     kwlist, &tabsize))
-        return NULL;
-
     if (PyUnicode_READY(self) == -1)
         return NULL;
 
@@ -11693,14 +11719,18 @@ unicode_index(PyObject *self, PyObject *args)
     return PyLong_FromSsize_t(result);
 }
 
-PyDoc_STRVAR(islower__doc__,
-             "S.islower() -> bool\n\
-\n\
-Return True if all cased characters in S are lowercase and there is\n\
-at least one cased character in S, False otherwise.");
+/*[clinic input]
+str.islower as unicode_islower
 
-static PyObject*
-unicode_islower(PyObject *self)
+Return True if the string is a lowercase string, False otherwise.
+
+A string is lowercase if all cased characters in the string are lowercase and
+there is at least one cased character in the string.
+[clinic start generated code]*/
+
+static PyObject *
+unicode_islower_impl(PyObject *self)
+/*[clinic end generated code: output=dbd41995bd005b81 input=46eeb20d935af050]*/
 {
     Py_ssize_t i, length;
     int kind;
@@ -11734,14 +11764,18 @@ unicode_islower(PyObject *self)
     return PyBool_FromLong(cased);
 }
 
-PyDoc_STRVAR(isupper__doc__,
-             "S.isupper() -> bool\n\
-\n\
-Return True if all cased characters in S are uppercase and there is\n\
-at least one cased character in S, False otherwise.");
+/*[clinic input]
+str.isupper as unicode_isupper
 
-static PyObject*
-unicode_isupper(PyObject *self)
+Return True if the string is an uppercase string, False otherwise.
+
+A string is uppercase if all cased characters in the string are uppercase and
+there is at least one cased character in the string.
+[clinic start generated code]*/
+
+static PyObject *
+unicode_isupper_impl(PyObject *self)
+/*[clinic end generated code: output=049209c8e7f15f59 input=dd0a595fc871eee0]*/
 {
     Py_ssize_t i, length;
     int kind;
@@ -11775,16 +11809,18 @@ unicode_isupper(PyObject *self)
     return PyBool_FromLong(cased);
 }
 
-PyDoc_STRVAR(istitle__doc__,
-             "S.istitle() -> bool\n\
-\n\
-Return True if S is a titlecased string and there is at least one\n\
-character in S, i.e. upper- and titlecase characters may only\n\
-follow uncased characters and lowercase characters only cased ones.\n\
-Return False otherwise.");
+/*[clinic input]
+str.istitle as unicode_istitle
 
-static PyObject*
-unicode_istitle(PyObject *self)
+Return True if the string is a title-cased string, False otherwise.
+
+In a title-cased string, upper- and title-case characters may only
+follow uncased characters and lowercase characters only cased ones.
+[clinic start generated code]*/
+
+static PyObject *
+unicode_istitle_impl(PyObject *self)
+/*[clinic end generated code: output=e9bf6eb91f5d3f0e input=2c56883d113d644d]*/
 {
     Py_ssize_t i, length;
     int kind;
@@ -11831,14 +11867,18 @@ unicode_istitle(PyObject *self)
     return PyBool_FromLong(cased);
 }
 
-PyDoc_STRVAR(isspace__doc__,
-             "S.isspace() -> bool\n\
-\n\
-Return True if all characters in S are whitespace\n\
-and there is at least one character in S, False otherwise.");
+/*[clinic input]
+str.isspace as unicode_isspace
 
-static PyObject*
-unicode_isspace(PyObject *self)
+Return True if the string is a whitespace string, False otherwise.
+
+A string is whitespace if all characters in the string are whitespace and there
+is at least one character in the string.
+[clinic start generated code]*/
+
+static PyObject *
+unicode_isspace_impl(PyObject *self)
+/*[clinic end generated code: output=163a63bfa08ac2b9 input=b9506a23e312d203]*/
 {
     Py_ssize_t i, length;
     int kind;
@@ -11867,14 +11907,18 @@ unicode_isspace(PyObject *self)
     return PyBool_FromLong(1);
 }
 
-PyDoc_STRVAR(isalpha__doc__,
-             "S.isalpha() -> bool\n\
-\n\
-Return True if all characters in S are alphabetic\n\
-and there is at least one character in S, False otherwise.");
+/*[clinic input]
+str.isalpha as unicode_isalpha
 
-static PyObject*
-unicode_isalpha(PyObject *self)
+Return True if the string is an alphabetic string, False otherwise.
+
+A string is alphabetic if all characters in the string are alphabetic and there
+is at least one character in the string.
+[clinic start generated code]*/
+
+static PyObject *
+unicode_isalpha_impl(PyObject *self)
+/*[clinic end generated code: output=cc81b9ac3883ec4f input=17e3788814472079]*/
 {
     Py_ssize_t i, length;
     int kind;
@@ -11902,14 +11946,18 @@ unicode_isalpha(PyObject *self)
     return PyBool_FromLong(1);
 }
 
-PyDoc_STRVAR(isalnum__doc__,
-             "S.isalnum() -> bool\n\
-\n\
-Return True if all characters in S are alphanumeric\n\
-and there is at least one character in S, False otherwise.");
+/*[clinic input]
+str.isalnum as unicode_isalnum
 
-static PyObject*
-unicode_isalnum(PyObject *self)
+Return True if the string is an alpha-numeric string, False otherwise.
+
+A string is alpha-numeric if all characters in the string are alpha-numeric and
+there is at least one character in the string.
+[clinic start generated code]*/
+
+static PyObject *
+unicode_isalnum_impl(PyObject *self)
+/*[clinic end generated code: output=a5a23490ffc3660c input=d350c4f7c59b4758]*/
 {
     int kind;
     void *data;
@@ -11940,14 +11988,18 @@ unicode_isalnum(PyObject *self)
     return PyBool_FromLong(1);
 }
 
-PyDoc_STRVAR(isdecimal__doc__,
-             "S.isdecimal() -> bool\n\
-\n\
-Return True if there are only decimal characters in S,\n\
-False otherwise.");
+/*[clinic input]
+str.isdecimal as unicode_isdecimal
 
-static PyObject*
-unicode_isdecimal(PyObject *self)
+Return True if the string is a decimal string, False otherwise.
+
+A string is a decimal string if all characters in the string are decimal and
+there is at least one character in the string.
+[clinic start generated code]*/
+
+static PyObject *
+unicode_isdecimal_impl(PyObject *self)
+/*[clinic end generated code: output=fb2dcdb62d3fc548 input=40536fb80e5f1dc1]*/
 {
     Py_ssize_t i, length;
     int kind;
@@ -11975,14 +12027,18 @@ unicode_isdecimal(PyObject *self)
     return PyBool_FromLong(1);
 }
 
-PyDoc_STRVAR(isdigit__doc__,
-             "S.isdigit() -> bool\n\
-\n\
-Return True if all characters in S are digits\n\
-and there is at least one character in S, False otherwise.");
+/*[clinic input]
+str.isdigit as unicode_isdigit
 
-static PyObject*
-unicode_isdigit(PyObject *self)
+Return True if the string is a digit string, False otherwise.
+
+A string is a digit string if all characters in the string are digits and there
+is at least one character in the string.
+[clinic start generated code]*/
+
+static PyObject *
+unicode_isdigit_impl(PyObject *self)
+/*[clinic end generated code: output=10a6985311da6858 input=c6a222be1aaec2af]*/
 {
     Py_ssize_t i, length;
     int kind;
@@ -12011,14 +12067,18 @@ unicode_isdigit(PyObject *self)
     return PyBool_FromLong(1);
 }
 
-PyDoc_STRVAR(isnumeric__doc__,
-             "S.isnumeric() -> bool\n\
-\n\
-Return True if there are only numeric characters in S,\n\
-False otherwise.");
+/*[clinic input]
+str.isnumeric as unicode_isnumeric
 
-static PyObject*
-unicode_isnumeric(PyObject *self)
+Return True if the string is a numeric string, False otherwise.
+
+A string is numeric if all characters in the string are numeric and there is at
+least one character in the string.
+[clinic start generated code]*/
+
+static PyObject *
+unicode_isnumeric_impl(PyObject *self)
+/*[clinic end generated code: output=9172a32d9013051a input=e3b37b2cc8854f35]*/
 {
     Py_ssize_t i, length;
     int kind;
@@ -12083,29 +12143,34 @@ PyUnicode_IsIdentifier(PyObject *self)
     return 1;
 }
 
-PyDoc_STRVAR(isidentifier__doc__,
-             "S.isidentifier() -> bool\n\
-\n\
-Return True if S is a valid identifier according\n\
-to the language definition.\n\
-\n\
-Use keyword.iskeyword() to test for reserved identifiers\n\
-such as \"def\" and \"class\".\n");
+/*[clinic input]
+str.isidentifier as unicode_isidentifier
 
-static PyObject*
-unicode_isidentifier(PyObject *self)
+Return True if the string is a valid Python identifier, False otherwise.
+
+Use keyword.iskeyword() to test for reserved identifiers such as "def" and
+"class".
+[clinic start generated code]*/
+
+static PyObject *
+unicode_isidentifier_impl(PyObject *self)
+/*[clinic end generated code: output=fe585a9666572905 input=95eebe40d6d91234]*/
 {
     return PyBool_FromLong(PyUnicode_IsIdentifier(self));
 }
 
-PyDoc_STRVAR(isprintable__doc__,
-             "S.isprintable() -> bool\n\
-\n\
-Return True if all characters in S are considered\n\
-printable in repr() or S is empty, False otherwise.");
+/*[clinic input]
+str.isprintable as unicode_isprintable
 
-static PyObject*
-unicode_isprintable(PyObject *self)
+Return True if the string is printable, False otherwise.
+
+A string is printable if all of its characters are considered printable in
+repr() or if it is empty.
+[clinic start generated code]*/
+
+static PyObject *
+unicode_isprintable_impl(PyObject *self)
+/*[clinic end generated code: output=3ab9626cd32dd1a0 input=20c53134171af84e]*/
 {
     Py_ssize_t i, length;
     int kind;
@@ -12130,16 +12195,25 @@ unicode_isprintable(PyObject *self)
     Py_RETURN_TRUE;
 }
 
-PyDoc_STRVAR(join__doc__,
-             "S.join(iterable) -> str\n\
-\n\
-Return a string which is the concatenation of the strings in the\n\
-iterable.  The separator between elements is S.");
+/*[clinic input]
+str.join as unicode_join
 
-static PyObject*
-unicode_join(PyObject *self, PyObject *data)
+    iterable: object
+    /
+
+Concatenate any number of strings.
+
+The string whose method is called is inserted in between each given strings.
+The result is returned as a new string.
+
+Example: '.'.join(['ab', 'pq', 'rs']) -> 'ab.pq.rs'
+[clinic start generated code]*/
+
+static PyObject *
+unicode_join(PyObject *self, PyObject *iterable)
+/*[clinic end generated code: output=6857e7cecfe7bf98 input=465f62626109db6b]*/
 {
-    return PyUnicode_Join(self, data);
+    return PyUnicode_Join(self, iterable);
 }
 
 static Py_ssize_t
@@ -12150,21 +12224,22 @@ unicode_length(PyObject *self)
     return PyUnicode_GET_LENGTH(self);
 }
 
-PyDoc_STRVAR(ljust__doc__,
-             "S.ljust(width[, fillchar]) -> str\n\
-\n\
-Return S left-justified in a Unicode string of length width. Padding is\n\
-done using the specified fill character (default is a space).");
+/*[clinic input]
+str.ljust as unicode_ljust
 
-static PyObject *
-unicode_ljust(PyObject *self, PyObject *args)
-{
-    Py_ssize_t width;
-    Py_UCS4 fillchar = ' ';
+    width: Py_ssize_t
+    fillchar: Py_UCS4 = ' '
+    /
 
-    if (!PyArg_ParseTuple(args, "n|O&:ljust", &width, convert_uc, &fillchar))
-        return NULL;
+Return a left-justified string of length width.
 
+Padding is done using the specified fill character (default is a space).
+[clinic start generated code]*/
+
+static PyObject *
+unicode_ljust_impl(PyObject *self, Py_ssize_t width, Py_UCS4 fillchar)
+/*[clinic end generated code: output=1cce0e0e0a0b84b3 input=3ab599e335e60a32]*/
+{
     if (PyUnicode_READY(self) == -1)
         return NULL;
 
@@ -12174,13 +12249,15 @@ unicode_ljust(PyObject *self, PyObject *args)
     return pad(self, 0, width - PyUnicode_GET_LENGTH(self), fillchar);
 }
 
-PyDoc_STRVAR(lower__doc__,
-             "S.lower() -> str\n\
-\n\
-Return a copy of the string S converted to lowercase.");
+/*[clinic input]
+str.lower as unicode_lower
 
-static PyObject*
-unicode_lower(PyObject *self)
+Return a copy of the string converted to lowercase.
+[clinic start generated code]*/
+
+static PyObject *
+unicode_lower_impl(PyObject *self)
+/*[clinic end generated code: output=84ef9ed42efad663 input=60a2984b8beff23a]*/
 {
     if (PyUnicode_READY(self) == -1)
         return NULL;
@@ -12194,9 +12271,9 @@ unicode_lower(PyObject *self)
 #define BOTHSTRIP 2
 
 /* Arrays indexed by above */
-static const char * const stripformat[] = {"|O:lstrip", "|O:rstrip", "|O:strip"};
+static const char *stripfuncnames[] = {"lstrip", "rstrip", "strip"};
 
-#define STRIPNAME(i) (stripformat[i]+3)
+#define STRIPNAME(i) (stripfuncnames[i])
 
 /* externally visible for str.strip(unicode) */
 PyObject *
@@ -12353,13 +12430,8 @@ do_strip(PyObject *self, int striptype)
 
 
 static PyObject *
-do_argstrip(PyObject *self, int striptype, PyObject *args)
+do_argstrip(PyObject *self, int striptype, PyObject *sep)
 {
-    PyObject *sep = NULL;
-
-    if (!PyArg_ParseTuple(args, stripformat[striptype], &sep))
-        return NULL;
-
     if (sep != NULL && sep != Py_None) {
         if (PyUnicode_Check(sep))
             return _PyUnicode_XStrip(self, striptype, sep);
@@ -12375,52 +12447,60 @@ do_argstrip(PyObject *self, int striptype, PyObject *args)
 }
 
 
-PyDoc_STRVAR(strip__doc__,
-             "S.strip([chars]) -> str\n\
-\n\
-Return a copy of the string S with leading and trailing\n\
-whitespace removed.\n\
-If chars is given and not None, remove characters in chars instead.");
+/*[clinic input]
+str.strip as unicode_strip
+
+    chars: object = None
+    /
+
+Return a copy of the string with leading and trailing whitespace removed.
+
+If chars is given and not None, remove characters in chars instead.
+[clinic start generated code]*/
 
 static PyObject *
-unicode_strip(PyObject *self, PyObject *args)
+unicode_strip_impl(PyObject *self, PyObject *chars)
+/*[clinic end generated code: output=ca19018454345d57 input=385289c6f423b954]*/
 {
-    if (PyTuple_GET_SIZE(args) == 0)
-        return do_strip(self, BOTHSTRIP); /* Common case */
-    else
-        return do_argstrip(self, BOTHSTRIP, args);
+    return do_argstrip(self, BOTHSTRIP, chars);
 }
 
 
-PyDoc_STRVAR(lstrip__doc__,
-             "S.lstrip([chars]) -> str\n\
-\n\
-Return a copy of the string S with leading whitespace removed.\n\
-If chars is given and not None, remove characters in chars instead.");
+/*[clinic input]
+str.lstrip as unicode_lstrip
+
+    chars: object = NULL
+    /
+
+Return a copy of the string with leading whitespace removed.
+
+If chars is given and not None, remove characters in chars instead.
+[clinic start generated code]*/
 
 static PyObject *
-unicode_lstrip(PyObject *self, PyObject *args)
+unicode_lstrip_impl(PyObject *self, PyObject *chars)
+/*[clinic end generated code: output=3b43683251f79ca7 input=9e56f3c45f5ff4c3]*/
 {
-    if (PyTuple_GET_SIZE(args) == 0)
-        return do_strip(self, LEFTSTRIP); /* Common case */
-    else
-        return do_argstrip(self, LEFTSTRIP, args);
+    return do_argstrip(self, LEFTSTRIP, chars);
 }
 
 
-PyDoc_STRVAR(rstrip__doc__,
-             "S.rstrip([chars]) -> str\n\
-\n\
-Return a copy of the string S with trailing whitespace removed.\n\
-If chars is given and not None, remove characters in chars instead.");
+/*[clinic input]
+str.rstrip as unicode_rstrip
+
+    chars: object = NULL
+    /
+
+Return a copy of the string with trailing whitespace removed.
+
+If chars is given and not None, remove characters in chars instead.
+[clinic start generated code]*/
 
 static PyObject *
-unicode_rstrip(PyObject *self, PyObject *args)
+unicode_rstrip_impl(PyObject *self, PyObject *chars)
+/*[clinic end generated code: output=4a59230017cc3b7a input=ac89d0219cb411ee]*/
 {
-    if (PyTuple_GET_SIZE(args) == 0)
-        return do_strip(self, RIGHTSTRIP); /* Common case */
-    else
-        return do_argstrip(self, RIGHTSTRIP, args);
+    return do_argstrip(self, RIGHTSTRIP, chars);
 }
 
 
@@ -12500,25 +12580,30 @@ PyUnicode_Replace(PyObject *str,
     return replace(str, substr, replstr, maxcount);
 }
 
-PyDoc_STRVAR(replace__doc__,
-             "S.replace(old, new[, count]) -> str\n\
-\n\
-Return a copy of S with all occurrences of substring\n\
-old replaced by new.  If the optional argument count is\n\
-given, only the first count occurrences are replaced.");
+/*[clinic input]
+str.replace as unicode_replace
 
-static PyObject*
-unicode_replace(PyObject *self, PyObject *args)
-{
-    PyObject *str1;
-    PyObject *str2;
-    Py_ssize_t maxcount = -1;
+    old: unicode
+    new: unicode
+    count: Py_ssize_t = -1
+        Maximum number of occurrences to replace.
+        -1 (the default value) means replace all occurrences.
+    /
 
-    if (!PyArg_ParseTuple(args, "UU|n:replace", &str1, &str2, &maxcount))
-        return NULL;
+Return a copy with all occurrences of substring old replaced by new.
+
+If the optional argument count is given, only the first count occurrences are
+replaced.
+[clinic start generated code]*/
+
+static PyObject *
+unicode_replace_impl(PyObject *self, PyObject *old, PyObject *new,
+                     Py_ssize_t count)
+/*[clinic end generated code: output=b63f1a8b5eebf448 input=147d12206276ebeb]*/
+{
     if (PyUnicode_READY(self) == -1)
         return NULL;
-    return replace(self, str1, str2, maxcount);
+    return replace(self, old, new, count);
 }
 
 static PyObject *
@@ -12750,21 +12835,22 @@ unicode_rindex(PyObject *self, PyObject *args)
     return PyLong_FromSsize_t(result);
 }
 
-PyDoc_STRVAR(rjust__doc__,
-             "S.rjust(width[, fillchar]) -> str\n\
-\n\
-Return S right-justified in a string of length width. Padding is\n\
-done using the specified fill character (default is a space).");
+/*[clinic input]
+str.rjust as unicode_rjust
 
-static PyObject *
-unicode_rjust(PyObject *self, PyObject *args)
-{
-    Py_ssize_t width;
-    Py_UCS4 fillchar = ' ';
+    width: Py_ssize_t
+    fillchar: Py_UCS4 = ' '
+    /
 
-    if (!PyArg_ParseTuple(args, "n|O&:rjust", &width, convert_uc, &fillchar))
-        return NULL;
+Return a right-justified string of length width.
+
+Padding is done using the specified fill character (default is a space).
+[clinic start generated code]*/
 
+static PyObject *
+unicode_rjust_impl(PyObject *self, Py_ssize_t width, Py_UCS4 fillchar)
+/*[clinic end generated code: output=804a1a57fbe8d5cf input=d05f550b5beb1f72]*/
+{
     if (PyUnicode_READY(self) == -1)
         return NULL;
 
@@ -12783,35 +12869,32 @@ PyUnicode_Split(PyObject *s, PyObject *sep, Py_ssize_t maxsplit)
     return split(s, sep, maxsplit);
 }
 
-PyDoc_STRVAR(split__doc__,
-             "S.split(sep=None, maxsplit=-1) -> list of strings\n\
-\n\
-Return a list of the words in S, using sep as the\n\
-delimiter string.  If maxsplit is given, at most maxsplit\n\
-splits are done. If sep is not specified or is None, any\n\
-whitespace string is a separator and empty strings are\n\
-removed from the result.");
-
-static PyObject*
-unicode_split(PyObject *self, PyObject *args, PyObject *kwds)
-{
-    static char *kwlist[] = {"sep", "maxsplit", 0};
-    PyObject *substring = Py_None;
-    Py_ssize_t maxcount = -1;
+/*[clinic input]
+str.split as unicode_split
 
-    if (!PyArg_ParseTupleAndKeywords(args, kwds, "|On:split",
-                                     kwlist, &substring, &maxcount))
-        return NULL;
+    sep: object = None
+        The delimiter according which to split the string.
+        None (the default value) means split according to any whitespace,
+        and discard empty strings from the result.
+    maxsplit: Py_ssize_t = -1
+        Maximum number of splits to do.
+        -1 (the default value) means no limit.
 
-    if (substring == Py_None)
-        return split(self, NULL, maxcount);
+Return a list of the words in the string, using sep as the delimiter string.
+[clinic start generated code]*/
 
-    if (PyUnicode_Check(substring))
-        return split(self, substring, maxcount);
+static PyObject *
+unicode_split_impl(PyObject *self, PyObject *sep, Py_ssize_t maxsplit)
+/*[clinic end generated code: output=3a65b1db356948dc input=606e750488a82359]*/
+{
+    if (sep == Py_None)
+        return split(self, NULL, maxsplit);
+    if (PyUnicode_Check(sep))
+        return split(self, sep, maxsplit);
 
     PyErr_Format(PyExc_TypeError,
                  "must be str or None, not %.100s",
-                 Py_TYPE(substring)->tp_name);
+                 Py_TYPE(sep)->tp_name);
     return NULL;
 }
 
@@ -12930,30 +13013,47 @@ PyUnicode_RPartition(PyObject *str_obj, PyObject *sep_obj)
     return out;
 }
 
-PyDoc_STRVAR(partition__doc__,
-             "S.partition(sep) -> (head, sep, tail)\n\
-\n\
-Search for the separator sep in S, and return the part before it,\n\
-the separator itself, and the part after it.  If the separator is not\n\
-found, return S and two empty strings.");
+/*[clinic input]
+str.partition as unicode_partition
 
-static PyObject*
-unicode_partition(PyObject *self, PyObject *separator)
+    sep: object
+    /
+
+Partition the string into three parts using the given separator.
+
+This will search for the separator in the string.  If the separator is found,
+returns a 3-tuple containing the part before the separator, the separator
+itself, and the part after it.
+
+If the separator is not found, returns a 3-tuple containing the original string
+and two empty strings.
+[clinic start generated code]*/
+
+static PyObject *
+unicode_partition(PyObject *self, PyObject *sep)
+/*[clinic end generated code: output=e4ced7bd253ca3c4 input=f29b8d06c63e50be]*/
 {
-    return PyUnicode_Partition(self, separator);
+    return PyUnicode_Partition(self, sep);
 }
 
-PyDoc_STRVAR(rpartition__doc__,
-             "S.rpartition(sep) -> (head, sep, tail)\n\
-\n\
-Search for the separator sep in S, starting at the end of S, and return\n\
-the part before it, the separator itself, and the part after it.  If the\n\
-separator is not found, return two empty strings and S.");
+/*[clinic input]
+str.rpartition as unicode_rpartition = str.partition
 
-static PyObject*
-unicode_rpartition(PyObject *self, PyObject *separator)
+Partition the string into three parts using the given separator.
+
+This will search for the separator in the string, starting and the end. If
+the separator is found, returns a 3-tuple containing the part before the
+separator, the separator itself, and the part after it.
+
+If the separator is not found, returns a 3-tuple containing two empty strings
+and the original string.
+[clinic start generated code]*/
+
+static PyObject *
+unicode_rpartition(PyObject *self, PyObject *sep)
+/*[clinic end generated code: output=1aa13cf1156572aa input=e77c7acb69bdfca6]*/
 {
-    return PyUnicode_RPartition(self, separator);
+    return PyUnicode_RPartition(self, sep);
 }
 
 PyObject *
@@ -12965,55 +13065,44 @@ PyUnicode_RSplit(PyObject *s, PyObject *sep, Py_ssize_t maxsplit)
     return rsplit(s, sep, maxsplit);
 }
 
-PyDoc_STRVAR(rsplit__doc__,
-             "S.rsplit(sep=None, maxsplit=-1) -> list of strings\n\
-\n\
-Return a list of the words in S, using sep as the\n\
-delimiter string, starting at the end of the string and\n\
-working to the front.  If maxsplit is given, at most maxsplit\n\
-splits are done. If sep is not specified, any whitespace string\n\
-is a separator.");
-
-static PyObject*
-unicode_rsplit(PyObject *self, PyObject *args, PyObject *kwds)
-{
-    static char *kwlist[] = {"sep", "maxsplit", 0};
-    PyObject *substring = Py_None;
-    Py_ssize_t maxcount = -1;
+/*[clinic input]
+str.rsplit as unicode_rsplit = str.split
 
-    if (!PyArg_ParseTupleAndKeywords(args, kwds, "|On:rsplit",
-                                     kwlist, &substring, &maxcount))
-        return NULL;
+Return a list of the words in the string, using sep as the delimiter string.
 
-    if (substring == Py_None)
-        return rsplit(self, NULL, maxcount);
+Splits are done starting at the end of the string and working to the front.
+[clinic start generated code]*/
 
-    if (PyUnicode_Check(substring))
-        return rsplit(self, substring, maxcount);
+static PyObject *
+unicode_rsplit_impl(PyObject *self, PyObject *sep, Py_ssize_t maxsplit)
+/*[clinic end generated code: output=c2b815c63bcabffc input=12ad4bf57dd35f15]*/
+{
+    if (sep == Py_None)
+        return rsplit(self, NULL, maxsplit);
+    if (PyUnicode_Check(sep))
+        return rsplit(self, sep, maxsplit);
 
     PyErr_Format(PyExc_TypeError,
                  "must be str or None, not %.100s",
-                 Py_TYPE(substring)->tp_name);
+                 Py_TYPE(sep)->tp_name);
     return NULL;
 }
 
-PyDoc_STRVAR(splitlines__doc__,
-             "S.splitlines([keepends]) -> list of strings\n\
-\n\
-Return a list of the lines in S, breaking at line boundaries.\n\
-Line breaks are not included in the resulting list unless keepends\n\
-is given and true.");
+/*[clinic input]
+str.splitlines as unicode_splitlines
 
-static PyObject*
-unicode_splitlines(PyObject *self, PyObject *args, PyObject *kwds)
-{
-    static char *kwlist[] = {"keepends", 0};
-    int keepends = 0;
+    keepends: int(c_default="0") = False
 
-    if (!PyArg_ParseTupleAndKeywords(args, kwds, "|i:splitlines",
-                                     kwlist, &keepends))
-        return NULL;
+Return a list of the lines in the string, breaking at line boundaries.
+
+Line breaks are not included in the resulting list unless keepends is given and
+true.
+[clinic start generated code]*/
 
+static PyObject *
+unicode_splitlines_impl(PyObject *self, int keepends)
+/*[clinic end generated code: output=f664dcdad153ec40 input=d6ff99fe43465b0f]*/
+{
     return PyUnicode_Splitlines(self, keepends);
 }
 
@@ -13023,14 +13112,15 @@ PyObject *unicode_str(PyObject *self)
     return unicode_result_unchanged(self);
 }
 
-PyDoc_STRVAR(swapcase__doc__,
-             "S.swapcase() -> str\n\
-\n\
-Return a copy of S with uppercase characters converted to lowercase\n\
-and vice versa.");
+/*[clinic input]
+str.swapcase as unicode_swapcase
 
-static PyObject*
-unicode_swapcase(PyObject *self)
+Convert uppercase characters to lowercase and lowercase characters to uppercase.
+[clinic start generated code]*/
+
+static PyObject *
+unicode_swapcase_impl(PyObject *self)
+/*[clinic end generated code: output=5d28966bf6d7b2af input=3f3ef96d5798a7bb]*/
 {
     if (PyUnicode_READY(self) == -1)
         return NULL;
@@ -13167,29 +13257,37 @@ unicode_maketrans_impl(PyObject *x, PyObject *y, PyObject *z)
     return NULL;
 }
 
-PyDoc_STRVAR(translate__doc__,
-             "S.translate(table) -> str\n\
-\n\
-Return a copy of the string S in which each character has been mapped\n\
-through the given translation table. The table must implement\n\
-lookup/indexing via __getitem__, for instance a dictionary or list,\n\
-mapping Unicode ordinals to Unicode ordinals, strings, or None. If\n\
-this operation raises LookupError, the character is left untouched.\n\
-Characters mapped to None are deleted.");
+/*[clinic input]
+str.translate as unicode_translate
 
-static PyObject*
+    table: object
+        Translation table, which must be a mapping of Unicode ordinals to
+        Unicode ordinals, strings, or None.
+    /
+
+Replace each character in the string using the given translation table.
+
+The table must implement lookup/indexing via __getitem__, for instance a
+dictionary or list.  If this operation raises LookupError, the character is
+left untouched.  Characters mapped to None are deleted.
+[clinic start generated code]*/
+
+static PyObject *
 unicode_translate(PyObject *self, PyObject *table)
+/*[clinic end generated code: output=3cb448ff2fd96bf3 input=6d38343db63d8eb0]*/
 {
     return _PyUnicode_TranslateCharmap(self, table, "ignore");
 }
 
-PyDoc_STRVAR(upper__doc__,
-             "S.upper() -> str\n\
-\n\
-Return a copy of S converted to uppercase.");
+/*[clinic input]
+str.upper as unicode_upper
 
-static PyObject*
-unicode_upper(PyObject *self)
+Return a copy of the string converted to uppercase.
+[clinic start generated code]*/
+
+static PyObject *
+unicode_upper_impl(PyObject *self)
+/*[clinic end generated code: output=1b7ddd16bbcdc092 input=db3d55682dfe2e6c]*/
 {
     if (PyUnicode_READY(self) == -1)
         return NULL;
@@ -13198,25 +13296,27 @@ unicode_upper(PyObject *self)
     return case_operation(self, do_upper);
 }
 
-PyDoc_STRVAR(zfill__doc__,
-             "S.zfill(width) -> str\n\
-\n\
-Pad a numeric string S with zeros on the left, to fill a field\n\
-of the specified width. The string S is never truncated.");
+/*[clinic input]
+str.zfill as unicode_zfill
+
+    width: Py_ssize_t
+    /
+
+Pad a numeric string with zeros on the left, to fill a field of the given width.
+
+The string is never truncated.
+[clinic start generated code]*/
 
 static PyObject *
-unicode_zfill(PyObject *self, PyObject *args)
+unicode_zfill_impl(PyObject *self, Py_ssize_t width)
+/*[clinic end generated code: output=e13fb6bdf8e3b9df input=3559257ab7bfed6e]*/
 {
     Py_ssize_t fill;
     PyObject *u;
-    Py_ssize_t width;
     int kind;
     void *data;
     Py_UCS4 chr;
 
-    if (!PyArg_ParseTuple(args, "n:zfill", &width))
-        return NULL;
-
     if (PyUnicode_READY(self) == -1)
         return NULL;
 
@@ -13703,16 +13803,22 @@ PyDoc_STRVAR(format_map__doc__,
 Return a formatted version of S, using substitutions from mapping.\n\
 The substitutions are identified by braces ('{' and '}').");
 
+/*[clinic input]
+str.__format__ as unicode___format__
+
+    format_spec: unicode
+    /
+
+Return a formatted version of the string as described by format_spec.
+[clinic start generated code]*/
+
 static PyObject *
-unicode__format__(PyObject* self, PyObject* args)
+unicode___format___impl(PyObject *self, PyObject *format_spec)
+/*[clinic end generated code: output=45fceaca6d2ba4c8 input=1f0623ca7b7c5981]*/
 {
-    PyObject *format_spec;
     _PyUnicodeWriter writer;
     int ret;
 
-    if (!PyArg_ParseTuple(args, "U:__format__", &format_spec))
-        return NULL;
-
     if (PyUnicode_READY(self) == -1)
         return NULL;
     _PyUnicodeWriter_Init(&writer);
@@ -13726,44 +13832,43 @@ unicode__format__(PyObject* self, PyObject* args)
     return _PyUnicodeWriter_Finish(&writer);
 }
 
-PyDoc_STRVAR(p_format__doc__,
-             "S.__format__(format_spec) -> str\n\
-\n\
-Return a formatted version of S as described by format_spec.");
+/*[clinic input]
+str.__sizeof__ as unicode_sizeof
+
+Return the size of the string in memory, in bytes.
+[clinic start generated code]*/
 
 static PyObject *
-unicode__sizeof__(PyObject *v)
+unicode_sizeof_impl(PyObject *self)
+/*[clinic end generated code: output=6dbc2f5a408b6d4f input=6dd011c108e33fb0]*/
 {
     Py_ssize_t size;
 
     /* If it's a compact object, account for base structure +
        character data. */
-    if (PyUnicode_IS_COMPACT_ASCII(v))
-        size = sizeof(PyASCIIObject) + PyUnicode_GET_LENGTH(v) + 1;
-    else if (PyUnicode_IS_COMPACT(v))
+    if (PyUnicode_IS_COMPACT_ASCII(self))
+        size = sizeof(PyASCIIObject) + PyUnicode_GET_LENGTH(self) + 1;
+    else if (PyUnicode_IS_COMPACT(self))
         size = sizeof(PyCompactUnicodeObject) +
-            (PyUnicode_GET_LENGTH(v) + 1) * PyUnicode_KIND(v);
+            (PyUnicode_GET_LENGTH(self) + 1) * PyUnicode_KIND(self);
     else {
         /* If it is a two-block object, account for base object, and
            for character block if present. */
         size = sizeof(PyUnicodeObject);
-        if (_PyUnicode_DATA_ANY(v))
-            size += (PyUnicode_GET_LENGTH(v) + 1) *
-                PyUnicode_KIND(v);
+        if (_PyUnicode_DATA_ANY(self))
+            size += (PyUnicode_GET_LENGTH(self) + 1) *
+                PyUnicode_KIND(self);
     }
     /* If the wstr pointer is present, account for it unless it is shared
        with the data pointer. Check if the data is not shared. */
-    if (_PyUnicode_HAS_WSTR_MEMORY(v))
-        size += (PyUnicode_WSTR_LENGTH(v) + 1) * sizeof(wchar_t);
-    if (_PyUnicode_HAS_UTF8_MEMORY(v))
-        size += PyUnicode_UTF8_LENGTH(v) + 1;
+    if (_PyUnicode_HAS_WSTR_MEMORY(self))
+        size += (PyUnicode_WSTR_LENGTH(self) + 1) * sizeof(wchar_t);
+    if (_PyUnicode_HAS_UTF8_MEMORY(self))
+        size += PyUnicode_UTF8_LENGTH(self) + 1;
 
     return PyLong_FromSsize_t(size);
 }
 
-PyDoc_STRVAR(sizeof__doc__,
-             "S.__sizeof__() -> size of S in memory, in bytes");
-
 static PyObject *
 unicode_getnewargs(PyObject *v)
 {
@@ -13774,54 +13879,52 @@ unicode_getnewargs(PyObject *v)
 }
 
 static PyMethodDef unicode_methods[] = {
-    {"encode", (PyCFunction) unicode_encode, METH_VARARGS | METH_KEYWORDS, encode__doc__},
-    {"replace", (PyCFunction) unicode_replace, METH_VARARGS, replace__doc__},
-    {"split", (PyCFunction) unicode_split, METH_VARARGS | METH_KEYWORDS, split__doc__},
-    {"rsplit", (PyCFunction) unicode_rsplit, METH_VARARGS | METH_KEYWORDS, rsplit__doc__},
-    {"join", (PyCFunction) unicode_join, METH_O, join__doc__},
-    {"capitalize", (PyCFunction) unicode_capitalize, METH_NOARGS, capitalize__doc__},
-    {"casefold", (PyCFunction) unicode_casefold, METH_NOARGS, casefold__doc__},
-    {"title", (PyCFunction) unicode_title, METH_NOARGS, title__doc__},
-    {"center", (PyCFunction) unicode_center, METH_VARARGS, center__doc__},
+    UNICODE_ENCODE_METHODDEF
+    UNICODE_REPLACE_METHODDEF
+    UNICODE_SPLIT_METHODDEF
+    UNICODE_RSPLIT_METHODDEF
+    UNICODE_JOIN_METHODDEF
+    UNICODE_CAPITALIZE_METHODDEF
+    UNICODE_CASEFOLD_METHODDEF
+    UNICODE_TITLE_METHODDEF
+    UNICODE_CENTER_METHODDEF
     {"count", (PyCFunction) unicode_count, METH_VARARGS, count__doc__},
-    {"expandtabs", (PyCFunction) unicode_expandtabs,
-     METH_VARARGS | METH_KEYWORDS, expandtabs__doc__},
+    UNICODE_EXPANDTABS_METHODDEF
     {"find", (PyCFunction) unicode_find, METH_VARARGS, find__doc__},
-    {"partition", (PyCFunction) unicode_partition, METH_O, partition__doc__},
+    UNICODE_PARTITION_METHODDEF
     {"index", (PyCFunction) unicode_index, METH_VARARGS, index__doc__},
-    {"ljust", (PyCFunction) unicode_ljust, METH_VARARGS, ljust__doc__},
-    {"lower", (PyCFunction) unicode_lower, METH_NOARGS, lower__doc__},
-    {"lstrip", (PyCFunction) unicode_lstrip, METH_VARARGS, lstrip__doc__},
+    UNICODE_LJUST_METHODDEF
+    UNICODE_LOWER_METHODDEF
+    UNICODE_LSTRIP_METHODDEF
     {"rfind", (PyCFunction) unicode_rfind, METH_VARARGS, rfind__doc__},
     {"rindex", (PyCFunction) unicode_rindex, METH_VARARGS, rindex__doc__},
-    {"rjust", (PyCFunction) unicode_rjust, METH_VARARGS, rjust__doc__},
-    {"rstrip", (PyCFunction) unicode_rstrip, METH_VARARGS, rstrip__doc__},
-    {"rpartition", (PyCFunction) unicode_rpartition, METH_O, rpartition__doc__},
-    {"splitlines", (PyCFunction) unicode_splitlines,
-     METH_VARARGS | METH_KEYWORDS, splitlines__doc__},
-    {"strip", (PyCFunction) unicode_strip, METH_VARARGS, strip__doc__},
-    {"swapcase", (PyCFunction) unicode_swapcase, METH_NOARGS, swapcase__doc__},
-    {"translate", (PyCFunction) unicode_translate, METH_O, translate__doc__},
-    {"upper", (PyCFunction) unicode_upper, METH_NOARGS, upper__doc__},
+    UNICODE_RJUST_METHODDEF
+    UNICODE_RSTRIP_METHODDEF
+    UNICODE_RPARTITION_METHODDEF
+    UNICODE_SPLITLINES_METHODDEF
+    UNICODE_STRIP_METHODDEF
+    UNICODE_SWAPCASE_METHODDEF
+    UNICODE_TRANSLATE_METHODDEF
+    UNICODE_UPPER_METHODDEF
     {"startswith", (PyCFunction) unicode_startswith, METH_VARARGS, startswith__doc__},
     {"endswith", (PyCFunction) unicode_endswith, METH_VARARGS, endswith__doc__},
-    {"islower", (PyCFunction) unicode_islower, METH_NOARGS, islower__doc__},
-    {"isupper", (PyCFunction) unicode_isupper, METH_NOARGS, isupper__doc__},
-    {"istitle", (PyCFunction) unicode_istitle, METH_NOARGS, istitle__doc__},
-    {"isspace", (PyCFunction) unicode_isspace, METH_NOARGS, isspace__doc__},
-    {"isdecimal", (PyCFunction) unicode_isdecimal, METH_NOARGS, isdecimal__doc__},
-    {"isdigit", (PyCFunction) unicode_isdigit, METH_NOARGS, isdigit__doc__},
-    {"isnumeric", (PyCFunction) unicode_isnumeric, METH_NOARGS, isnumeric__doc__},
-    {"isalpha", (PyCFunction) unicode_isalpha, METH_NOARGS, isalpha__doc__},
-    {"isalnum", (PyCFunction) unicode_isalnum, METH_NOARGS, isalnum__doc__},
-    {"isidentifier", (PyCFunction) unicode_isidentifier, METH_NOARGS, isidentifier__doc__},
-    {"isprintable", (PyCFunction) unicode_isprintable, METH_NOARGS, isprintable__doc__},
-    {"zfill", (PyCFunction) unicode_zfill, METH_VARARGS, zfill__doc__},
+    UNICODE_ISLOWER_METHODDEF
+    UNICODE_ISUPPER_METHODDEF
+    UNICODE_ISTITLE_METHODDEF
+    UNICODE_ISSPACE_METHODDEF
+    UNICODE_ISDECIMAL_METHODDEF
+    UNICODE_ISDIGIT_METHODDEF
+    UNICODE_ISNUMERIC_METHODDEF
+    UNICODE_ISALPHA_METHODDEF
+    UNICODE_ISALNUM_METHODDEF
+    UNICODE_ISIDENTIFIER_METHODDEF
+    UNICODE_ISPRINTABLE_METHODDEF
+    UNICODE_ZFILL_METHODDEF
     {"format", (PyCFunction) do_string_format, METH_VARARGS | METH_KEYWORDS, format__doc__},
     {"format_map", (PyCFunction) do_string_format_map, METH_O, format_map__doc__},
-    {"__format__", (PyCFunction) unicode__format__, METH_VARARGS, p_format__doc__},
+    UNICODE___FORMAT___METHODDEF
     UNICODE_MAKETRANS_METHODDEF
-    {"__sizeof__", (PyCFunction) unicode__sizeof__, METH_NOARGS, sizeof__doc__},
+    UNICODE_SIZEOF_METHODDEF
 #if 0
     /* These methods are just used for debugging the implementation. */
     {"_decimal2ascii", (PyCFunction) unicode__decimal2ascii, METH_NOARGS},
-- 
cgit v1.2.1


From 6c812b4a4ef712e449e029dc7253e34c29ec3cff Mon Sep 17 00:00:00 2001
From: INADA Naoki <songofacandy@gmail.com>
Date: Mon, 16 Jan 2017 21:49:13 +0900
Subject: Issue #20180: forgot to update AC output.

---
 Objects/unicodeobject.c | 36 ++++++++++++++++++------------------
 1 file changed, 18 insertions(+), 18 deletions(-)

(limited to 'Objects/unicodeobject.c')

diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
index acf59e4d13..e2bdf088ab 100644
--- a/Objects/unicodeobject.c
+++ b/Objects/unicodeobject.c
@@ -49,7 +49,7 @@ OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
 #endif
 
 /*[clinic input]
-class str "PyUnicodeObject *" "&PyUnicode_Type"
+class str "PyObject *" "&PyUnicode_Type"
 [clinic start generated code]*/
 /*[clinic end generated code: output=da39a3ee5e6b4b0d input=4884c934de622cf6]*/
 
@@ -10737,7 +10737,7 @@ cased characters have lower case.
 
 static PyObject *
 unicode_title_impl(PyObject *self)
-/*[clinic end generated code: output=c75ae03809574902 input=4eb12c1bb8642cb9]*/
+/*[clinic end generated code: output=c75ae03809574902 input=fa945d669b26e683]*/
 {
     if (PyUnicode_READY(self) == -1)
         return NULL;
@@ -10772,7 +10772,7 @@ Return a version of the string suitable for caseless comparisons.
 
 static PyObject *
 unicode_casefold_impl(PyObject *self)
-/*[clinic end generated code: output=0120daf657ca40af input=a96f2b0d3daabd94]*/
+/*[clinic end generated code: output=0120daf657ca40af input=384d66cc2ae30daf]*/
 {
     if (PyUnicode_READY(self) == -1)
         return NULL;
@@ -11510,7 +11510,7 @@ Encode the string using the codec registered for encoding.
 
 static PyObject *
 unicode_encode_impl(PyObject *self, const char *encoding, const char *errors)
-/*[clinic end generated code: output=bf78b6e2a9470e3c input=12fcb2e5798e96dc]*/
+/*[clinic end generated code: output=bf78b6e2a9470e3c input=f0a9eb293d08fe02]*/
 {
     return PyUnicode_AsEncodedString(self, encoding, errors);
 }
@@ -11730,7 +11730,7 @@ there is at least one cased character in the string.
 
 static PyObject *
 unicode_islower_impl(PyObject *self)
-/*[clinic end generated code: output=dbd41995bd005b81 input=46eeb20d935af050]*/
+/*[clinic end generated code: output=dbd41995bd005b81 input=acec65ac6821ae47]*/
 {
     Py_ssize_t i, length;
     int kind;
@@ -11775,7 +11775,7 @@ there is at least one cased character in the string.
 
 static PyObject *
 unicode_isupper_impl(PyObject *self)
-/*[clinic end generated code: output=049209c8e7f15f59 input=dd0a595fc871eee0]*/
+/*[clinic end generated code: output=049209c8e7f15f59 input=e9b1feda5d17f2d3]*/
 {
     Py_ssize_t i, length;
     int kind;
@@ -11820,7 +11820,7 @@ follow uncased characters and lowercase characters only cased ones.
 
 static PyObject *
 unicode_istitle_impl(PyObject *self)
-/*[clinic end generated code: output=e9bf6eb91f5d3f0e input=2c56883d113d644d]*/
+/*[clinic end generated code: output=e9bf6eb91f5d3f0e input=98d32bd2e1f06f8c]*/
 {
     Py_ssize_t i, length;
     int kind;
@@ -11878,7 +11878,7 @@ is at least one character in the string.
 
 static PyObject *
 unicode_isspace_impl(PyObject *self)
-/*[clinic end generated code: output=163a63bfa08ac2b9 input=b9506a23e312d203]*/
+/*[clinic end generated code: output=163a63bfa08ac2b9 input=fe462cb74f8437d8]*/
 {
     Py_ssize_t i, length;
     int kind;
@@ -11918,7 +11918,7 @@ is at least one character in the string.
 
 static PyObject *
 unicode_isalpha_impl(PyObject *self)
-/*[clinic end generated code: output=cc81b9ac3883ec4f input=17e3788814472079]*/
+/*[clinic end generated code: output=cc81b9ac3883ec4f input=d0fd18a96cbca5eb]*/
 {
     Py_ssize_t i, length;
     int kind;
@@ -11957,7 +11957,7 @@ there is at least one character in the string.
 
 static PyObject *
 unicode_isalnum_impl(PyObject *self)
-/*[clinic end generated code: output=a5a23490ffc3660c input=d350c4f7c59b4758]*/
+/*[clinic end generated code: output=a5a23490ffc3660c input=5c6579bf2e04758c]*/
 {
     int kind;
     void *data;
@@ -11999,7 +11999,7 @@ there is at least one character in the string.
 
 static PyObject *
 unicode_isdecimal_impl(PyObject *self)
-/*[clinic end generated code: output=fb2dcdb62d3fc548 input=40536fb80e5f1dc1]*/
+/*[clinic end generated code: output=fb2dcdb62d3fc548 input=336bc97ab4c8268f]*/
 {
     Py_ssize_t i, length;
     int kind;
@@ -12038,7 +12038,7 @@ is at least one character in the string.
 
 static PyObject *
 unicode_isdigit_impl(PyObject *self)
-/*[clinic end generated code: output=10a6985311da6858 input=c6a222be1aaec2af]*/
+/*[clinic end generated code: output=10a6985311da6858 input=901116c31deeea4c]*/
 {
     Py_ssize_t i, length;
     int kind;
@@ -12078,7 +12078,7 @@ least one character in the string.
 
 static PyObject *
 unicode_isnumeric_impl(PyObject *self)
-/*[clinic end generated code: output=9172a32d9013051a input=e3b37b2cc8854f35]*/
+/*[clinic end generated code: output=9172a32d9013051a input=722507db976f826c]*/
 {
     Py_ssize_t i, length;
     int kind;
@@ -12154,7 +12154,7 @@ Use keyword.iskeyword() to test for reserved identifiers such as "def" and
 
 static PyObject *
 unicode_isidentifier_impl(PyObject *self)
-/*[clinic end generated code: output=fe585a9666572905 input=95eebe40d6d91234]*/
+/*[clinic end generated code: output=fe585a9666572905 input=916b0a3c9f57e919]*/
 {
     return PyBool_FromLong(PyUnicode_IsIdentifier(self));
 }
@@ -12170,7 +12170,7 @@ repr() or if it is empty.
 
 static PyObject *
 unicode_isprintable_impl(PyObject *self)
-/*[clinic end generated code: output=3ab9626cd32dd1a0 input=20c53134171af84e]*/
+/*[clinic end generated code: output=3ab9626cd32dd1a0 input=98a0e1c2c1813209]*/
 {
     Py_ssize_t i, length;
     int kind;
@@ -12211,7 +12211,7 @@ Example: '.'.join(['ab', 'pq', 'rs']) -> 'ab.pq.rs'
 
 static PyObject *
 unicode_join(PyObject *self, PyObject *iterable)
-/*[clinic end generated code: output=6857e7cecfe7bf98 input=465f62626109db6b]*/
+/*[clinic end generated code: output=6857e7cecfe7bf98 input=d8311e5ccbafbeb6]*/
 {
     return PyUnicode_Join(self, iterable);
 }
@@ -13309,7 +13309,7 @@ The string is never truncated.
 
 static PyObject *
 unicode_zfill_impl(PyObject *self, Py_ssize_t width)
-/*[clinic end generated code: output=e13fb6bdf8e3b9df input=3559257ab7bfed6e]*/
+/*[clinic end generated code: output=e13fb6bdf8e3b9df input=c6b2f772c6f27799]*/
 {
     Py_ssize_t fill;
     PyObject *u;
@@ -13814,7 +13814,7 @@ Return a formatted version of the string as described by format_spec.
 
 static PyObject *
 unicode___format___impl(PyObject *self, PyObject *format_spec)
-/*[clinic end generated code: output=45fceaca6d2ba4c8 input=1f0623ca7b7c5981]*/
+/*[clinic end generated code: output=45fceaca6d2ba4c8 input=5e135645d167a214]*/
 {
     _PyUnicodeWriter writer;
     int ret;
-- 
cgit v1.2.1


From 104cb4a3bacdf9764f9f8670a80da16390231337 Mon Sep 17 00:00:00 2001
From: Victor Stinner <victor.stinner@gmail.com>
Date: Tue, 17 Jan 2017 02:21:47 +0100
Subject: Run Argument Clinic: METH_VARARGS=>METH_FASTCALL

Issue #29286. Run Argument Clinic to get the new faster METH_FASTCALL calling
convention for functions using "boring" positional arguments.

Manually fix _elementtree: _elementtree_XMLParser_doctype() must remain
consistent with the clinic code.
---
 Objects/unicodeobject.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'Objects/unicodeobject.c')

diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
index e2bdf088ab..5fbe56cce1 100644
--- a/Objects/unicodeobject.c
+++ b/Objects/unicodeobject.c
@@ -12453,14 +12453,14 @@ str.strip as unicode_strip
     chars: object = None
     /
 
-Return a copy of the string with leading and trailing whitespace removed.
+Return a copy of the string with leading and trailing whitespace remove.
 
 If chars is given and not None, remove characters in chars instead.
 [clinic start generated code]*/
 
 static PyObject *
 unicode_strip_impl(PyObject *self, PyObject *chars)
-/*[clinic end generated code: output=ca19018454345d57 input=385289c6f423b954]*/
+/*[clinic end generated code: output=ca19018454345d57 input=eefe24a1059c352b]*/
 {
     return do_argstrip(self, BOTHSTRIP, chars);
 }
-- 
cgit v1.2.1


From 72ded8136b92c1b107f629021cf231fd3163f041 Mon Sep 17 00:00:00 2001
From: Serhiy Storchaka <storchaka@gmail.com>
Date: Sun, 22 Jan 2017 23:07:07 +0200
Subject: Issue #28769: The result of PyUnicode_AsUTF8AndSize() and
 PyUnicode_AsUTF8() is now of type "const char *" rather of "char *".

---
 Objects/unicodeobject.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'Objects/unicodeobject.c')

diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
index 5fbe56cce1..b711f0ccce 100644
--- a/Objects/unicodeobject.c
+++ b/Objects/unicodeobject.c
@@ -3972,7 +3972,7 @@ PyUnicode_FSDecoder(PyObject* arg, void* addr)
 }
 
 
-char*
+const char *
 PyUnicode_AsUTF8AndSize(PyObject *unicode, Py_ssize_t *psize)
 {
     PyObject *bytes;
@@ -4007,7 +4007,7 @@ PyUnicode_AsUTF8AndSize(PyObject *unicode, Py_ssize_t *psize)
     return PyUnicode_UTF8(unicode);
 }
 
-char*
+const char *
 PyUnicode_AsUTF8(PyObject *unicode)
 {
     return PyUnicode_AsUTF8AndSize(unicode, NULL);
-- 
cgit v1.2.1


From bfeec6d871e3db2e0ddfdef01387913bc19cadd4 Mon Sep 17 00:00:00 2001
From: Serhiy Storchaka <storchaka@gmail.com>
Date: Mon, 23 Jan 2017 09:47:21 +0200
Subject: Issue #28999: Use Py_RETURN_NONE, Py_RETURN_TRUE and Py_RETURN_FALSE
 wherever possible.  Patch is writen with Coccinelle.

---
 Objects/unicodeobject.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

(limited to 'Objects/unicodeobject.c')

diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
index b711f0ccce..0b79c5bd1a 100644
--- a/Objects/unicodeobject.c
+++ b/Objects/unicodeobject.c
@@ -8254,9 +8254,7 @@ charmapencode_lookup(Py_UCS4 c, PyObject *mapping)
         if (PyErr_ExceptionMatches(PyExc_LookupError)) {
             /* No mapping found means: mapping is undefined. */
             PyErr_Clear();
-            x = Py_None;
-            Py_INCREF(x);
-            return x;
+            Py_RETURN_NONE;
         } else
             return NULL;
     }
-- 
cgit v1.2.1


From 8882e556eef08ade01461b9f4ccfe2d82bdae694 Mon Sep 17 00:00:00 2001
From: Martin Panter <vadmium+py@gmail.com>
Date: Tue, 24 Jan 2017 00:30:06 +0000
Subject: Fix grammar in doc string, RST markup

---
 Objects/unicodeobject.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'Objects/unicodeobject.c')

diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
index 0b79c5bd1a..d3516fa45f 100644
--- a/Objects/unicodeobject.c
+++ b/Objects/unicodeobject.c
@@ -12201,7 +12201,7 @@ str.join as unicode_join
 
 Concatenate any number of strings.
 
-The string whose method is called is inserted in between each given strings.
+The string whose method is called is inserted in between each given string.
 The result is returned as a new string.
 
 Example: '.'.join(['ab', 'pq', 'rs']) -> 'ab.pq.rs'
@@ -12209,7 +12209,7 @@ Example: '.'.join(['ab', 'pq', 'rs']) -> 'ab.pq.rs'
 
 static PyObject *
 unicode_join(PyObject *self, PyObject *iterable)
-/*[clinic end generated code: output=6857e7cecfe7bf98 input=d8311e5ccbafbeb6]*/
+/*[clinic end generated code: output=6857e7cecfe7bf98 input=2f70422bfb8fa189]*/
 {
     return PyUnicode_Join(self, iterable);
 }
-- 
cgit v1.2.1