Issue #26765: Moved common code and docstrings for bytes and bytearray methods

to bytes_methods.c.

Include/bytes_methods.h

@@ -21,6 +21,15 @@ extern void _Py_bytes_title(char *result, const char *s, Py_ssize_t len);
 extern void _Py_bytes_capitalize(char *result, const char *s, Py_ssize_t len);
 extern void _Py_bytes_swapcase(char *result, const char *s, Py_ssize_t len);
 
+extern PyObject *_Py_bytes_find(const char *str, Py_ssize_t len, PyObject *args);
+extern PyObject *_Py_bytes_index(const char *str, Py_ssize_t len, PyObject *args);
+extern PyObject *_Py_bytes_rfind(const char *str, Py_ssize_t len, PyObject *args);
+extern PyObject *_Py_bytes_rindex(const char *str, Py_ssize_t len, PyObject *args);
+extern PyObject *_Py_bytes_count(const char *str, Py_ssize_t len, PyObject *args);
+extern int _Py_bytes_contains(const char *str, Py_ssize_t len, PyObject *arg);
+extern PyObject *_Py_bytes_startswith(const char *str, Py_ssize_t len, PyObject *args);
+extern PyObject *_Py_bytes_endswith(const char *str, Py_ssize_t len, PyObject *args);
+
 /* The maketrans() static method. */
 extern PyObject* _Py_bytes_maketrans(Py_buffer *frm, Py_buffer *to);
 
@@ -37,7 +46,19 @@ extern const char _Py_upper__doc__[];
 extern const char _Py_title__doc__[];
 extern const char _Py_capitalize__doc__[];
 extern const char _Py_swapcase__doc__[];
+extern const char _Py_count__doc__[];
+extern const char _Py_find__doc__[];
+extern const char _Py_index__doc__[];
+extern const char _Py_rfind__doc__[];
+extern const char _Py_rindex__doc__[];
+extern const char _Py_startswith__doc__[];
+extern const char _Py_endswith__doc__[];
 extern const char _Py_maketrans__doc__[];
+extern const char _Py_expandtabs__doc__[];
+extern const char _Py_ljust__doc__[];
+extern const char _Py_rjust__doc__[];
+extern const char _Py_center__doc__[];
+extern const char _Py_zfill__doc__[];
 
 /* this is needed because some docs are shared from the .o, not static */
 #define PyDoc_STRVAR_shared(name,str) const char name[] = PyDoc_STR(str)

Objects/bytearrayobject.c

@@ -1097,147 +1097,16 @@ bytearray_dealloc(PyByteArrayObject *self)
 #include "stringlib/transmogrify.h"
 
 
-/* The following Py_LOCAL_INLINE and Py_LOCAL functions
-were copied from the old char* style string object. */
-
-/* helper macro to fixup start/end slice values */
-#define ADJUST_INDICES(start, end, len)         \
-    if (end > len)                              \
-        end = len;                              \
-    else if (end < 0) {                         \
-        end += len;                             \
-        if (end < 0)                            \
-            end = 0;                            \
-    }                                           \
-    if (start < 0) {                            \
-        start += len;                           \
-        if (start < 0)                          \
-            start = 0;                          \
-    }
-
-Py_LOCAL_INLINE(Py_ssize_t)
-bytearray_find_internal(PyByteArrayObject *self, PyObject *args, int dir)
-{
-    PyObject *subobj;
-    char byte;
-    Py_buffer subbuf;
-    const char *sub;
-    Py_ssize_t len, sub_len;
-    Py_ssize_t start=0, end=PY_SSIZE_T_MAX;
-    Py_ssize_t res;
-
-    if (!stringlib_parse_args_finds_byte("find/rfind/index/rindex",
-                                         args, &subobj, &byte, &start, &end))
-        return -2;
-
-    if (subobj) {
-        if (PyObject_GetBuffer(subobj, &subbuf, PyBUF_SIMPLE) != 0)
-            return -2;
-
-        sub = subbuf.buf;
-        sub_len = subbuf.len;
-    }
-    else {
-        sub = &byte;
-        sub_len = 1;
-    }
-    len = PyByteArray_GET_SIZE(self);
-
-    ADJUST_INDICES(start, end, len);
-    if (end - start < sub_len)
-        res = -1;
-    else if (sub_len == 1) {
-        if (dir > 0)
-            res = stringlib_find_char(
-                PyByteArray_AS_STRING(self) + start, end - start,
-                *sub);
-        else
-            res = stringlib_rfind_char(
-                PyByteArray_AS_STRING(self) + start, end - start,
-                *sub);
-        if (res >= 0)
-            res += start;
-    }
-    else {
-        if (dir > 0)
-            res = stringlib_find_slice(
-                PyByteArray_AS_STRING(self), len,
-                sub, sub_len, start, end);
-        else
-            res = stringlib_rfind_slice(
-                PyByteArray_AS_STRING(self), len,
-                sub, sub_len, start, end);
-    }
-
-    if (subobj)
-        PyBuffer_Release(&subbuf);
-
-    return res;
-}
-
-PyDoc_STRVAR(find__doc__,
-"B.find(sub[, start[, end]]) -> int\n\
-\n\
-Return the lowest index in B where subsection sub is found,\n\
-such that sub is contained within B[start,end].  Optional\n\
-arguments start and end are interpreted as in slice notation.\n\
-\n\
-Return -1 on failure.");
-
 static PyObject *
 bytearray_find(PyByteArrayObject *self, PyObject *args)
 {
-    Py_ssize_t result = bytearray_find_internal(self, args, +1);
+    return _Py_bytes_find(PyByteArray_AS_STRING(self), PyByteArray_GET_SIZE(self), args);
-    if (result == -2)
-        return NULL;
-    return PyLong_FromSsize_t(result);
 }
 
-PyDoc_STRVAR(count__doc__,
-"B.count(sub[, start[, end]]) -> int\n\
-\n\
-Return the number of non-overlapping occurrences of subsection sub in\n\
-bytes B[start:end].  Optional arguments start and end are interpreted\n\
-as in slice notation.");
-
 static PyObject *
 bytearray_count(PyByteArrayObject *self, PyObject *args)
 {
-    PyObject *sub_obj;
+    return _Py_bytes_count(PyByteArray_AS_STRING(self), PyByteArray_GET_SIZE(self), args);
-    const char *str = PyByteArray_AS_STRING(self), *sub;
-    Py_ssize_t sub_len;
-    char byte;
-    Py_ssize_t start = 0, end = PY_SSIZE_T_MAX;
-
-    Py_buffer vsub;
-    PyObject *count_obj;
-
-    if (!stringlib_parse_args_finds_byte("count", args, &sub_obj, &byte,
-                                         &start, &end))
-        return NULL;
-
-    if (sub_obj) {
-        if (PyObject_GetBuffer(sub_obj, &vsub, PyBUF_SIMPLE) != 0)
-            return NULL;
-
-        sub = vsub.buf;
-        sub_len = vsub.len;
-    }
-    else {
-        sub = &byte;
-        sub_len = 1;
-    }
-
-    ADJUST_INDICES(start, end, PyByteArray_GET_SIZE(self));
-
-    count_obj = PyLong_FromSsize_t(
-        stringlib_count(str + start, end - start, sub, sub_len, PY_SSIZE_T_MAX)
-        );
-
-    if (sub_obj)
-        PyBuffer_Release(&vsub);
-
-    return count_obj;
 }
 
 /*[clinic input]
@@ -1269,216 +1138,40 @@ bytearray_copy_impl(PyByteArrayObject *self)
                                          PyByteArray_GET_SIZE(self));
 }
 
-PyDoc_STRVAR(index__doc__,
-"B.index(sub[, start[, end]]) -> int\n\
-\n\
-Like B.find() but raise ValueError when the subsection is not found.");
-
 static PyObject *
 bytearray_index(PyByteArrayObject *self, PyObject *args)
 {
-    Py_ssize_t result = bytearray_find_internal(self, args, +1);
+    return _Py_bytes_index(PyByteArray_AS_STRING(self), PyByteArray_GET_SIZE(self), args);
-    if (result == -2)
-        return NULL;
-    if (result == -1) {
-        PyErr_SetString(PyExc_ValueError,
-                        "subsection not found");
-        return NULL;
-    }
-    return PyLong_FromSsize_t(result);
 }
 
-
-PyDoc_STRVAR(rfind__doc__,
-"B.rfind(sub[, start[, end]]) -> int\n\
-\n\
-Return the highest index in B where subsection sub is found,\n\
-such that sub is contained within B[start,end].  Optional\n\
-arguments start and end are interpreted as in slice notation.\n\
-\n\
-Return -1 on failure.");
-
 static PyObject *
 bytearray_rfind(PyByteArrayObject *self, PyObject *args)
 {
-    Py_ssize_t result = bytearray_find_internal(self, args, -1);
+    return _Py_bytes_rfind(PyByteArray_AS_STRING(self), PyByteArray_GET_SIZE(self), args);
-    if (result == -2)
-        return NULL;
-    return PyLong_FromSsize_t(result);
 }
 
-
-PyDoc_STRVAR(rindex__doc__,
-"B.rindex(sub[, start[, end]]) -> int\n\
-\n\
-Like B.rfind() but raise ValueError when the subsection is not found.");
-
 static PyObject *
 bytearray_rindex(PyByteArrayObject *self, PyObject *args)
 {
-    Py_ssize_t result = bytearray_find_internal(self, args, -1);
+    return _Py_bytes_rindex(PyByteArray_AS_STRING(self), PyByteArray_GET_SIZE(self), args);
-    if (result == -2)
-        return NULL;
-    if (result == -1) {
-        PyErr_SetString(PyExc_ValueError,
-                        "subsection not found");
-        return NULL;
-    }
-    return PyLong_FromSsize_t(result);
 }
 
-
 static int
 bytearray_contains(PyObject *self, PyObject *arg)
 {
-    Py_ssize_t ival = PyNumber_AsSsize_t(arg, PyExc_ValueError);
+    return _Py_bytes_contains(PyByteArray_AS_STRING(self), PyByteArray_GET_SIZE(self), arg);
-    if (ival == -1 && PyErr_Occurred()) {
-        Py_buffer varg;
-        Py_ssize_t pos;
-        PyErr_Clear();
-        if (PyObject_GetBuffer(arg, &varg, PyBUF_SIMPLE) != 0)
-            return -1;
-        pos = stringlib_find(PyByteArray_AS_STRING(self), Py_SIZE(self),
-                             varg.buf, varg.len, 0);
-        PyBuffer_Release(&varg);
-        return pos >= 0;
-    }
-    if (ival < 0 || ival >= 256) {
-        PyErr_SetString(PyExc_ValueError, "byte must be in range(0, 256)");
-        return -1;
-    }
-
-    return memchr(PyByteArray_AS_STRING(self), (int) ival, Py_SIZE(self)) != NULL;
 }
 
-
-/* Matches the end (direction >= 0) or start (direction < 0) of self
- * against substr, using the start and end arguments. Returns
- * -1 on error, 0 if not found and 1 if found.
- */
-Py_LOCAL(int)
-_bytearray_tailmatch(PyByteArrayObject *self, PyObject *substr, Py_ssize_t start,
-                 Py_ssize_t end, int direction)
-{
-    Py_ssize_t len = PyByteArray_GET_SIZE(self);
-    const char* str;
-    Py_buffer vsubstr;
-    int rv = 0;
-
-    str = PyByteArray_AS_STRING(self);
-
-    if (PyObject_GetBuffer(substr, &vsubstr, PyBUF_SIMPLE) != 0)
-        return -1;
-
-    ADJUST_INDICES(start, end, len);
-
-    if (direction < 0) {
-        /* startswith */
-        if (start+vsubstr.len > len) {
-            goto done;
-        }
-    } else {
-        /* endswith */
-        if (end-start < vsubstr.len || start > len) {
-            goto done;
-        }
-
-        if (end-vsubstr.len > start)
-            start = end - vsubstr.len;
-    }
-    if (end-start >= vsubstr.len)
-        rv = ! memcmp(str+start, vsubstr.buf, vsubstr.len);
-
-done:
-    PyBuffer_Release(&vsubstr);
-    return rv;
-}
-
-
-PyDoc_STRVAR(startswith__doc__,
-"B.startswith(prefix[, start[, end]]) -> bool\n\
-\n\
-Return True if B starts with the specified prefix, False otherwise.\n\
-With optional start, test B beginning at that position.\n\
-With optional end, stop comparing B at that position.\n\
-prefix can also be a tuple of bytes to try.");
-
 static PyObject *
 bytearray_startswith(PyByteArrayObject *self, PyObject *args)
 {
-    Py_ssize_t start = 0;
+    return _Py_bytes_startswith(PyByteArray_AS_STRING(self), PyByteArray_GET_SIZE(self), args);
-    Py_ssize_t end = PY_SSIZE_T_MAX;
-    PyObject *subobj;
-    int result;
-
-    if (!stringlib_parse_args_finds("startswith", args, &subobj, &start, &end))
-        return NULL;
-    if (PyTuple_Check(subobj)) {
-        Py_ssize_t i;
-        for (i = 0; i < PyTuple_GET_SIZE(subobj); i++) {
-            result = _bytearray_tailmatch(self,
-                                      PyTuple_GET_ITEM(subobj, i),
-                                      start, end, -1);
-            if (result == -1)
-                return NULL;
-            else if (result) {
-                Py_RETURN_TRUE;
-            }
-        }
-        Py_RETURN_FALSE;
-    }
-    result = _bytearray_tailmatch(self, subobj, start, end, -1);
-    if (result == -1) {
-        if (PyErr_ExceptionMatches(PyExc_TypeError))
-            PyErr_Format(PyExc_TypeError, "startswith first arg must be bytes "
-                         "or a tuple of bytes, not %s", Py_TYPE(subobj)->tp_name);
-        return NULL;
-    }
-    else
-        return PyBool_FromLong(result);
 }
 
-PyDoc_STRVAR(endswith__doc__,
-"B.endswith(suffix[, start[, end]]) -> bool\n\
-\n\
-Return True if B ends with the specified suffix, False otherwise.\n\
-With optional start, test B beginning at that position.\n\
-With optional end, stop comparing B at that position.\n\
-suffix can also be a tuple of bytes to try.");
-
 static PyObject *
 bytearray_endswith(PyByteArrayObject *self, PyObject *args)
 {
-    Py_ssize_t start = 0;
+    return _Py_bytes_endswith(PyByteArray_AS_STRING(self), PyByteArray_GET_SIZE(self), args);
-    Py_ssize_t end = PY_SSIZE_T_MAX;
-    PyObject *subobj;
-    int result;
-
-    if (!stringlib_parse_args_finds("endswith", args, &subobj, &start, &end))
-        return NULL;
-    if (PyTuple_Check(subobj)) {
-        Py_ssize_t i;
-        for (i = 0; i < PyTuple_GET_SIZE(subobj); i++) {
-            result = _bytearray_tailmatch(self,
-                                      PyTuple_GET_ITEM(subobj, i),
-                                      start, end, +1);
-            if (result == -1)
-                return NULL;
-            else if (result) {
-                Py_RETURN_TRUE;
-            }
-        }
-        Py_RETURN_FALSE;
-    }
-    result = _bytearray_tailmatch(self, subobj, start, end, +1);
-    if (result == -1) {
-        if (PyErr_ExceptionMatches(PyExc_TypeError))
-            PyErr_Format(PyExc_TypeError, "endswith first arg must be bytes or "
-                         "a tuple of bytes, not %s", Py_TYPE(subobj)->tp_name);
-        return NULL;
-    }
-    else
-        return PyBool_FromLong(result);
 }
 
 
@@ -1544,7 +1237,7 @@ bytearray_translate_impl(PyByteArrayObject *self, PyObject *table,
     result = PyByteArray_FromStringAndSize((char *)NULL, inlen);
     if (result == NULL)
         goto done;
-    output_start = output = PyByteArray_AsString(result);
+    output_start = output = PyByteArray_AS_STRING(result);
     input = PyByteArray_AS_STRING(input_obj);
 
     if (vdel.len == 0 && table_chars != NULL) {
@@ -2919,19 +2612,22 @@ bytearray_methods[] = {
     BYTEARRAY_APPEND_METHODDEF
     {"capitalize", (PyCFunction)stringlib_capitalize, METH_NOARGS,
      _Py_capitalize__doc__},
-    {"center", (PyCFunction)stringlib_center, METH_VARARGS, center__doc__},
+    {"center", (PyCFunction)stringlib_center, METH_VARARGS, _Py_center__doc__},
     BYTEARRAY_CLEAR_METHODDEF
     BYTEARRAY_COPY_METHODDEF
-    {"count", (PyCFunction)bytearray_count, METH_VARARGS, count__doc__},
+    {"count", (PyCFunction)bytearray_count, METH_VARARGS,
+     _Py_count__doc__},
     BYTEARRAY_DECODE_METHODDEF
-    {"endswith", (PyCFunction)bytearray_endswith, METH_VARARGS, endswith__doc__},
+    {"endswith", (PyCFunction)bytearray_endswith, METH_VARARGS,
+     _Py_endswith__doc__},
     {"expandtabs", (PyCFunction)stringlib_expandtabs, METH_VARARGS | METH_KEYWORDS,
-     expandtabs__doc__},
+     _Py_expandtabs__doc__},
     BYTEARRAY_EXTEND_METHODDEF
-    {"find", (PyCFunction)bytearray_find, METH_VARARGS, find__doc__},
+    {"find", (PyCFunction)bytearray_find, METH_VARARGS,
+     _Py_find__doc__},
     BYTEARRAY_FROMHEX_METHODDEF
     {"hex", (PyCFunction)bytearray_hex, METH_NOARGS, hex__doc__},
-    {"index", (PyCFunction)bytearray_index, METH_VARARGS, index__doc__},
+    {"index", (PyCFunction)bytearray_index, METH_VARARGS, _Py_index__doc__},
     BYTEARRAY_INSERT_METHODDEF
     {"isalnum", (PyCFunction)stringlib_isalnum, METH_NOARGS,
      _Py_isalnum__doc__},
@@ -2948,7 +2644,7 @@ bytearray_methods[] = {
     {"isupper", (PyCFunction)stringlib_isupper, METH_NOARGS,
      _Py_isupper__doc__},
     BYTEARRAY_JOIN_METHODDEF
-    {"ljust", (PyCFunction)stringlib_ljust, METH_VARARGS, ljust__doc__},
+    {"ljust", (PyCFunction)stringlib_ljust, METH_VARARGS, _Py_ljust__doc__},
     {"lower", (PyCFunction)stringlib_lower, METH_NOARGS, _Py_lower__doc__},
     BYTEARRAY_LSTRIP_METHODDEF
     BYTEARRAY_MAKETRANS_METHODDEF
@@ -2957,23 +2653,23 @@ bytearray_methods[] = {
     BYTEARRAY_REMOVE_METHODDEF
     BYTEARRAY_REPLACE_METHODDEF
     BYTEARRAY_REVERSE_METHODDEF
-    {"rfind", (PyCFunction)bytearray_rfind, METH_VARARGS, rfind__doc__},
+    {"rfind", (PyCFunction)bytearray_rfind, METH_VARARGS, _Py_rfind__doc__},
-    {"rindex", (PyCFunction)bytearray_rindex, METH_VARARGS, rindex__doc__},
+    {"rindex", (PyCFunction)bytearray_rindex, METH_VARARGS, _Py_rindex__doc__},
-    {"rjust", (PyCFunction)stringlib_rjust, METH_VARARGS, rjust__doc__},
+    {"rjust", (PyCFunction)stringlib_rjust, METH_VARARGS, _Py_rjust__doc__},
     BYTEARRAY_RPARTITION_METHODDEF
     BYTEARRAY_RSPLIT_METHODDEF
     BYTEARRAY_RSTRIP_METHODDEF
     BYTEARRAY_SPLIT_METHODDEF
     BYTEARRAY_SPLITLINES_METHODDEF
     {"startswith", (PyCFunction)bytearray_startswith, METH_VARARGS ,
-     startswith__doc__},
+     _Py_startswith__doc__},
     BYTEARRAY_STRIP_METHODDEF
     {"swapcase", (PyCFunction)stringlib_swapcase, METH_NOARGS,
      _Py_swapcase__doc__},
     {"title", (PyCFunction)stringlib_title, METH_NOARGS, _Py_title__doc__},
     BYTEARRAY_TRANSLATE_METHODDEF
     {"upper", (PyCFunction)stringlib_upper, METH_NOARGS, _Py_upper__doc__},
-    {"zfill", (PyCFunction)stringlib_zfill, METH_VARARGS, zfill__doc__},
+    {"zfill", (PyCFunction)stringlib_zfill, METH_VARARGS, _Py_zfill__doc__},
     {NULL}
 };
 

Objects/bytes_methods.c

@@ -387,3 +387,427 @@ _Py_bytes_maketrans(Py_buffer *frm, Py_buffer *to)
 
     return res;
 }
+
+#define FASTSEARCH fastsearch
+#define STRINGLIB(F) stringlib_##F
+#define STRINGLIB_CHAR char
+#define STRINGLIB_SIZEOF_CHAR 1
+
+#include "stringlib/fastsearch.h"
+#include "stringlib/count.h"
+#include "stringlib/find.h"
+
+/*
+Wraps stringlib_parse_args_finds() and additionally checks whether the
+first argument is an integer in range(0, 256).
+
+If this is the case, writes the integer value to the byte parameter
+and sets subobj to NULL. Otherwise, sets the first argument to subobj
+and doesn't touch byte. The other parameters are similar to those of
+stringlib_parse_args_finds().
+*/
+
+Py_LOCAL_INLINE(int)
+parse_args_finds_byte(const char *function_name, PyObject *args,
+                      PyObject **subobj, char *byte,
+                      Py_ssize_t *start, Py_ssize_t *end)
+{
+    PyObject *tmp_subobj;
+    Py_ssize_t ival;
+    PyObject *err;
+
+    if(!stringlib_parse_args_finds(function_name, args, &tmp_subobj,
+                                   start, end))
+        return 0;
+
+    if (!PyNumber_Check(tmp_subobj)) {
+        *subobj = tmp_subobj;
+        return 1;
+    }
+
+    ival = PyNumber_AsSsize_t(tmp_subobj, PyExc_OverflowError);
+    if (ival == -1) {
+        err = PyErr_Occurred();
+        if (err && !PyErr_GivenExceptionMatches(err, PyExc_OverflowError)) {
+            PyErr_Clear();
+            *subobj = tmp_subobj;
+            return 1;
+        }
+    }
+
+    if (ival < 0 || ival > 255) {
+        PyErr_SetString(PyExc_ValueError, "byte must be in range(0, 256)");
+        return 0;
+    }
+
+    *subobj = NULL;
+    *byte = (char)ival;
+    return 1;
+}
+
+/* helper macro to fixup start/end slice values */
+#define ADJUST_INDICES(start, end, len)         \
+    if (end > len)                          \
+        end = len;                          \
+    else if (end < 0) {                     \
+        end += len;                         \
+        if (end < 0)                        \
+        end = 0;                        \
+    }                                       \
+    if (start < 0) {                        \
+        start += len;                       \
+        if (start < 0)                      \
+        start = 0;                      \
+    }
+
+Py_LOCAL_INLINE(Py_ssize_t)
+find_internal(const char *str, Py_ssize_t len,
+              const char *function_name, PyObject *args, int dir)
+{
+    PyObject *subobj;
+    char byte;
+    Py_buffer subbuf;
+    const char *sub;
+    Py_ssize_t sub_len;
+    Py_ssize_t start = 0, end = PY_SSIZE_T_MAX;
+    Py_ssize_t res;
+
+    if (!parse_args_finds_byte(function_name, args,
+                               &subobj, &byte, &start, &end))
+        return -2;
+
+    if (subobj) {
+        if (PyObject_GetBuffer(subobj, &subbuf, PyBUF_SIMPLE) != 0)
+            return -2;
+
+        sub = subbuf.buf;
+        sub_len = subbuf.len;
+    }
+    else {
+        sub = &byte;
+        sub_len = 1;
+    }
+
+    ADJUST_INDICES(start, end, len);
+    if (end - start < sub_len)
+        res = -1;
+    else if (sub_len == 1) {
+        if (dir > 0)
+            res = stringlib_find_char(
+                str + start, end - start,
+                *sub);
+        else
+            res = stringlib_rfind_char(
+                str + start, end - start,
+                *sub);
+        if (res >= 0)
+            res += start;
+    }
+    else {
+        if (dir > 0)
+            res = stringlib_find_slice(
+                str, len,
+                sub, sub_len, start, end);
+        else
+            res = stringlib_rfind_slice(
+                str, len,
+                sub, sub_len, start, end);
+    }
+
+    if (subobj)
+        PyBuffer_Release(&subbuf);
+
+    return res;
+}
+
+PyDoc_STRVAR_shared(_Py_find__doc__,
+"B.find(sub[, start[, end]]) -> int\n\
+\n\
+Return the lowest index in B where subsection sub is found,\n\
+such that sub is contained within B[start,end].  Optional\n\
+arguments start and end are interpreted as in slice notation.\n\
+\n\
+Return -1 on failure.");
+
+PyObject *
+_Py_bytes_find(const char *str, Py_ssize_t len, PyObject *args)
+{
+    Py_ssize_t result = find_internal(str, len, "find", args, +1);
+    if (result == -2)
+        return NULL;
+    return PyLong_FromSsize_t(result);
+}
+
+PyDoc_STRVAR_shared(_Py_index__doc__,
+"B.index(sub[, start[, end]]) -> int\n\
+\n\
+Like B.find() but raise ValueError when the subsection is not found.");
+
+PyObject *
+_Py_bytes_index(const char *str, Py_ssize_t len, PyObject *args)
+{
+    Py_ssize_t result = find_internal(str, len, "index", args, +1);
+    if (result == -2)
+        return NULL;
+    if (result == -1) {
+        PyErr_SetString(PyExc_ValueError,
+                        "subsection not found");
+        return NULL;
+    }
+    return PyLong_FromSsize_t(result);
+}
+
+PyDoc_STRVAR_shared(_Py_rfind__doc__,
+"B.rfind(sub[, start[, end]]) -> int\n\
+\n\
+Return the highest index in B where subsection sub is found,\n\
+such that sub is contained within B[start,end].  Optional\n\
+arguments start and end are interpreted as in slice notation.\n\
+\n\
+Return -1 on failure.");
+
+PyObject *
+_Py_bytes_rfind(const char *str, Py_ssize_t len, PyObject *args)
+{
+    Py_ssize_t result = find_internal(str, len, "rfind", args, -1);
+    if (result == -2)
+        return NULL;
+    return PyLong_FromSsize_t(result);
+}
+
+PyDoc_STRVAR_shared(_Py_rindex__doc__,
+"B.rindex(sub[, start[, end]]) -> int\n\
+\n\
+Like B.rfind() but raise ValueError when the subsection is not found.");
+
+PyObject *
+_Py_bytes_rindex(const char *str, Py_ssize_t len, PyObject *args)
+{
+    Py_ssize_t result = find_internal(str, len, "rindex", args, -1);
+    if (result == -2)
+        return NULL;
+    if (result == -1) {
+        PyErr_SetString(PyExc_ValueError,
+                        "subsection not found");
+        return NULL;
+    }
+    return PyLong_FromSsize_t(result);
+}
+
+PyDoc_STRVAR_shared(_Py_count__doc__,
+"B.count(sub[, start[, end]]) -> int\n\
+\n\
+Return the number of non-overlapping occurrences of subsection sub in\n\
+bytes B[start:end].  Optional arguments start and end are interpreted\n\
+as in slice notation.");
+
+PyObject *
+_Py_bytes_count(const char *str, Py_ssize_t len, PyObject *args)
+{
+    PyObject *sub_obj;
+    const char *sub;
+    Py_ssize_t sub_len;
+    char byte;
+    Py_ssize_t start = 0, end = PY_SSIZE_T_MAX;
+
+    Py_buffer vsub;
+    PyObject *count_obj;
+
+    if (!parse_args_finds_byte("count", args,
+                               &sub_obj, &byte, &start, &end))
+        return NULL;
+
+    if (sub_obj) {
+        if (PyObject_GetBuffer(sub_obj, &vsub, PyBUF_SIMPLE) != 0)
+            return NULL;
+
+        sub = vsub.buf;
+        sub_len = vsub.len;
+    }
+    else {
+        sub = &byte;
+        sub_len = 1;
+    }
+
+    ADJUST_INDICES(start, end, len);
+
+    count_obj = PyLong_FromSsize_t(
+        stringlib_count(str + start, end - start, sub, sub_len, PY_SSIZE_T_MAX)
+        );
+
+    if (sub_obj)
+        PyBuffer_Release(&vsub);
+
+    return count_obj;
+}
+
+int
+_Py_bytes_contains(const char *str, Py_ssize_t len, PyObject *arg)
+{
+    Py_ssize_t ival = PyNumber_AsSsize_t(arg, PyExc_ValueError);
+    if (ival == -1 && PyErr_Occurred()) {
+        Py_buffer varg;
+        Py_ssize_t pos;
+        PyErr_Clear();
+        if (PyObject_GetBuffer(arg, &varg, PyBUF_SIMPLE) != 0)
+            return -1;
+        pos = stringlib_find(str, len,
+                             varg.buf, varg.len, 0);
+        PyBuffer_Release(&varg);
+        return pos >= 0;
+    }
+    if (ival < 0 || ival >= 256) {
+        PyErr_SetString(PyExc_ValueError, "byte must be in range(0, 256)");
+        return -1;
+    }
+
+    return memchr(str, (int) ival, len) != NULL;
+}
+
+
+/* Matches the end (direction >= 0) or start (direction < 0) of the buffer
+ * against substr, using the start and end arguments. Returns
+ * -1 on error, 0 if not found and 1 if found.
+ */
+Py_LOCAL(int)
+tailmatch(const char *str, Py_ssize_t len, PyObject *substr,
+          Py_ssize_t start, Py_ssize_t end, int direction)
+{
+    Py_buffer sub_view = {NULL, NULL};
+    const char *sub;
+    Py_ssize_t slen;
+
+    if (PyBytes_Check(substr)) {
+        sub = PyBytes_AS_STRING(substr);
+        slen = PyBytes_GET_SIZE(substr);
+    }
+    else {
+        if (PyObject_GetBuffer(substr, &sub_view, PyBUF_SIMPLE) != 0)
+            return -1;
+        sub = sub_view.buf;
+        slen = sub_view.len;
+    }
+
+    ADJUST_INDICES(start, end, len);
+
+    if (direction < 0) {
+        /* startswith */
+        if (start + slen > len)
+            goto notfound;
+    } else {
+        /* endswith */
+        if (end - start < slen || start > len)
+            goto notfound;
+
+        if (end - slen > start)
+            start = end - slen;
+    }
+    if (end - start < slen)
+        goto notfound;
+    if (memcmp(str + start, sub, slen) != 0)
+        goto notfound;
+
+    PyBuffer_Release(&sub_view);
+    return 1;
+
+notfound:
+    PyBuffer_Release(&sub_view);
+    return 0;
+}
+
+Py_LOCAL(PyObject *)
+_Py_bytes_tailmatch(const char *str, Py_ssize_t len,
+                    const char *function_name, PyObject *args,
+                    int direction)
+{
+    Py_ssize_t start = 0;
+    Py_ssize_t end = PY_SSIZE_T_MAX;
+    PyObject *subobj;
+    int result;
+
+    if (!stringlib_parse_args_finds(function_name, args, &subobj, &start, &end))
+        return NULL;
+    if (PyTuple_Check(subobj)) {
+        Py_ssize_t i;
+        for (i = 0; i < PyTuple_GET_SIZE(subobj); i++) {
+            result = tailmatch(str, len, PyTuple_GET_ITEM(subobj, i),
+                               start, end, direction);
+            if (result == -1)
+                return NULL;
+            else if (result) {
+                Py_RETURN_TRUE;
+            }
+        }
+        Py_RETURN_FALSE;
+    }
+    result = tailmatch(str, len, subobj, start, end, direction);
+    if (result == -1) {
+        if (PyErr_ExceptionMatches(PyExc_TypeError))
+            PyErr_Format(PyExc_TypeError,
+                         "%s first arg must be bytes or a tuple of bytes, "
+                         "not %s",
+                         function_name, Py_TYPE(subobj)->tp_name);
+        return NULL;
+    }
+    else
+        return PyBool_FromLong(result);
+}
+
+PyDoc_STRVAR_shared(_Py_startswith__doc__,
+"B.startswith(prefix[, start[, end]]) -> bool\n\
+\n\
+Return True if B starts with the specified prefix, False otherwise.\n\
+With optional start, test B beginning at that position.\n\
+With optional end, stop comparing B at that position.\n\
+prefix can also be a tuple of bytes to try.");
+
+PyObject *
+_Py_bytes_startswith(const char *str, Py_ssize_t len, PyObject *args)
+{
+    return _Py_bytes_tailmatch(str, len, "startswith", args, -1);
+}
+
+PyDoc_STRVAR_shared(_Py_endswith__doc__,
+"B.endswith(suffix[, start[, end]]) -> bool\n\
+\n\
+Return True if B ends with the specified suffix, False otherwise.\n\
+With optional start, test B beginning at that position.\n\
+With optional end, stop comparing B at that position.\n\
+suffix can also be a tuple of bytes to try.");
+
+PyObject *
+_Py_bytes_endswith(const char *str, Py_ssize_t len, PyObject *args)
+{
+    return _Py_bytes_tailmatch(str, len, "endswith", args, +1);
+}
+
+PyDoc_STRVAR_shared(_Py_expandtabs__doc__,
+"B.expandtabs(tabsize=8) -> copy of B\n\
+\n\
+Return a copy of B where all tab characters are expanded using spaces.\n\
+If tabsize is not given, a tab size of 8 characters is assumed.");
+
+PyDoc_STRVAR_shared(_Py_ljust__doc__,
+"B.ljust(width[, fillchar]) -> copy of B\n"
+"\n"
+"Return B left justified in a string of length width. Padding is\n"
+"done using the specified fill character (default is a space).");
+
+PyDoc_STRVAR_shared(_Py_rjust__doc__,
+"B.rjust(width[, fillchar]) -> copy of B\n"
+"\n"
+"Return B right justified in a string of length width. Padding is\n"
+"done using the specified fill character (default is a space)");
+
+PyDoc_STRVAR_shared(_Py_center__doc__,
+"B.center(width[, fillchar]) -> copy of B\n"
+"\n"
+"Return B centered in a string of length width.  Padding is\n"
+"done using the specified fill character (default is a space).");
+
+PyDoc_STRVAR_shared(_Py_zfill__doc__,
+"B.zfill(width) -> copy of B\n"
+"\n"
+"Pad a numeric string B with zeros on the left, to fill a field\n"
+"of the specified width.  B is never truncated.");
+

Objects/bytesobject.c

@@ -486,11 +486,11 @@ formatlong(PyObject *v, int flags, int prec, int type)
 static int
 byte_converter(PyObject *arg, char *p)
 {
-    if (PyBytes_Check(arg) && PyBytes_Size(arg) == 1) {
+    if (PyBytes_Check(arg) && PyBytes_GET_SIZE(arg) == 1) {
         *p = PyBytes_AS_STRING(arg)[0];
         return 1;
     }
-    else if (PyByteArray_Check(arg) && PyByteArray_Size(arg) == 1) {
+    else if (PyByteArray_Check(arg) && PyByteArray_GET_SIZE(arg) == 1) {
         *p = PyByteArray_AS_STRING(arg)[0];
         return 1;
     }
@@ -1488,24 +1488,7 @@ bytes_repeat(PyBytesObject *a, Py_ssize_t n)
 static int
 bytes_contains(PyObject *self, PyObject *arg)
 {
-    Py_ssize_t ival = PyNumber_AsSsize_t(arg, PyExc_ValueError);
+    return _Py_bytes_contains(PyBytes_AS_STRING(self), PyBytes_GET_SIZE(self), arg);
-    if (ival == -1 && PyErr_Occurred()) {
-        Py_buffer varg;
-        Py_ssize_t pos;
-        PyErr_Clear();
-        if (PyObject_GetBuffer(arg, &varg, PyBUF_SIMPLE) != 0)
-            return -1;
-        pos = stringlib_find(PyBytes_AS_STRING(self), Py_SIZE(self),
-                             varg.buf, varg.len, 0);
-        PyBuffer_Release(&varg);
-        return pos >= 0;
-    }
-    if (ival < 0 || ival >= 256) {
-        PyErr_SetString(PyExc_ValueError, "byte must be in range(0, 256)");
-        return -1;
-    }
-
-    return memchr(PyBytes_AS_STRING(self), (int) ival, Py_SIZE(self)) != NULL;
 }
 
 static PyObject *
@@ -1890,157 +1873,30 @@ _PyBytes_Join(PyObject *sep, PyObject *x)
     return bytes_join((PyBytesObject*)sep, x);
 }
 
-/* helper macro to fixup start/end slice values */
-#define ADJUST_INDICES(start, end, len)         \
-    if (end > len)                          \
-        end = len;                          \
-    else if (end < 0) {                     \
-        end += len;                         \
-        if (end < 0)                        \
-        end = 0;                        \
-    }                                       \
-    if (start < 0) {                        \
-        start += len;                       \
-        if (start < 0)                      \
-        start = 0;                      \
-    }
-
-Py_LOCAL_INLINE(Py_ssize_t)
-bytes_find_internal(PyBytesObject *self, PyObject *args, int dir)
-{
-    PyObject *subobj;
-    char byte;
-    Py_buffer subbuf;
-    const char *sub;
-    Py_ssize_t len, sub_len;
-    Py_ssize_t start=0, end=PY_SSIZE_T_MAX;
-    Py_ssize_t res;
-
-    if (!stringlib_parse_args_finds_byte("find/rfind/index/rindex",
-                                         args, &subobj, &byte, &start, &end))
-        return -2;
-
-    if (subobj) {
-        if (PyObject_GetBuffer(subobj, &subbuf, PyBUF_SIMPLE) != 0)
-            return -2;
-
-        sub = subbuf.buf;
-        sub_len = subbuf.len;
-    }
-    else {
-        sub = &byte;
-        sub_len = 1;
-    }
-    len = PyBytes_GET_SIZE(self);
-
-    ADJUST_INDICES(start, end, len);
-    if (end - start < sub_len)
-        res = -1;
-    else if (sub_len == 1) {
-        if (dir > 0)
-            res = stringlib_find_char(
-                PyBytes_AS_STRING(self) + start, end - start,
-                *sub);
-        else
-            res = stringlib_rfind_char(
-                PyBytes_AS_STRING(self) + start, end - start,
-                *sub);
-        if (res >= 0)
-            res += start;
-    }
-    else {
-        if (dir > 0)
-            res = stringlib_find_slice(
-                PyBytes_AS_STRING(self), len,
-                sub, sub_len, start, end);
-        else
-            res = stringlib_rfind_slice(
-                PyBytes_AS_STRING(self), len,
-                sub, sub_len, start, end);
-    }
-
-    if (subobj)
-        PyBuffer_Release(&subbuf);
-
-    return res;
-}
-
-
-PyDoc_STRVAR(find__doc__,
-"B.find(sub[, start[, end]]) -> int\n\
-\n\
-Return the lowest index in B where substring sub is found,\n\
-such that sub is contained within B[start:end].  Optional\n\
-arguments start and end are interpreted as in slice notation.\n\
-\n\
-Return -1 on failure.");
-
 static PyObject *
 bytes_find(PyBytesObject *self, PyObject *args)
 {
-    Py_ssize_t result = bytes_find_internal(self, args, +1);
+    return _Py_bytes_find(PyBytes_AS_STRING(self), PyBytes_GET_SIZE(self), args);
-    if (result == -2)
-        return NULL;
-    return PyLong_FromSsize_t(result);
 }
 
-
-PyDoc_STRVAR(index__doc__,
-"B.index(sub[, start[, end]]) -> int\n\
-\n\
-Like B.find() but raise ValueError when the substring is not found.");
-
 static PyObject *
 bytes_index(PyBytesObject *self, PyObject *args)
 {
-    Py_ssize_t result = bytes_find_internal(self, args, +1);
+    return _Py_bytes_index(PyBytes_AS_STRING(self), PyBytes_GET_SIZE(self), args);
-    if (result == -2)
-        return NULL;
-    if (result == -1) {
-        PyErr_SetString(PyExc_ValueError,
-                        "substring not found");
-        return NULL;
-    }
-    return PyLong_FromSsize_t(result);
 }
 
 
-PyDoc_STRVAR(rfind__doc__,
-"B.rfind(sub[, start[, end]]) -> int\n\
-\n\
-Return the highest index in B where substring sub is found,\n\
-such that sub is contained within B[start:end].  Optional\n\
-arguments start and end are interpreted as in slice notation.\n\
-\n\
-Return -1 on failure.");
-
 static PyObject *
 bytes_rfind(PyBytesObject *self, PyObject *args)
 {
-    Py_ssize_t result = bytes_find_internal(self, args, -1);
+    return _Py_bytes_rfind(PyBytes_AS_STRING(self), PyBytes_GET_SIZE(self), args);
-    if (result == -2)
-        return NULL;
-    return PyLong_FromSsize_t(result);
 }
 
 
-PyDoc_STRVAR(rindex__doc__,
-"B.rindex(sub[, start[, end]]) -> int\n\
-\n\
-Like B.rfind() but raise ValueError when the substring is not found.");
-
 static PyObject *
 bytes_rindex(PyBytesObject *self, PyObject *args)
 {
-    Py_ssize_t result = bytes_find_internal(self, args, -1);
+    return _Py_bytes_rindex(PyBytes_AS_STRING(self), PyBytes_GET_SIZE(self), args);
-    if (result == -2)
-        return NULL;
-    if (result == -1) {
-        PyErr_SetString(PyExc_ValueError,
-                        "substring not found");
-        return NULL;
-    }
-    return PyLong_FromSsize_t(result);
 }
 
 
@@ -2179,51 +2035,10 @@ bytes_rstrip_impl(PyBytesObject *self, PyObject *bytes)
 }
 
 
-PyDoc_STRVAR(count__doc__,
-"B.count(sub[, start[, end]]) -> int\n\
-\n\
-Return the number of non-overlapping occurrences of substring sub in\n\
-string B[start:end].  Optional arguments start and end are interpreted\n\
-as in slice notation.");
-
 static PyObject *
 bytes_count(PyBytesObject *self, PyObject *args)
 {
-    PyObject *sub_obj;
+    return _Py_bytes_count(PyBytes_AS_STRING(self), PyBytes_GET_SIZE(self), args);
-    const char *str = PyBytes_AS_STRING(self), *sub;
-    Py_ssize_t sub_len;
-    char byte;
-    Py_ssize_t start = 0, end = PY_SSIZE_T_MAX;
-
-    Py_buffer vsub;
-    PyObject *count_obj;
-
-    if (!stringlib_parse_args_finds_byte("count", args, &sub_obj, &byte,
-                                         &start, &end))
-        return NULL;
-
-    if (sub_obj) {
-        if (PyObject_GetBuffer(sub_obj, &vsub, PyBUF_SIMPLE) != 0)
-            return NULL;
-
-        sub = vsub.buf;
-        sub_len = vsub.len;
-    }
-    else {
-        sub = &byte;
-        sub_len = 1;
-    }
-
-    ADJUST_INDICES(start, end, PyBytes_GET_SIZE(self));
-
-    count_obj = PyLong_FromSsize_t(
-        stringlib_count(str + start, end - start, sub, sub_len, PY_SSIZE_T_MAX)
-        );
-
-    if (sub_obj)
-        PyBuffer_Release(&vsub);
-
-    return count_obj;
 }
 
 
@@ -2307,7 +2122,7 @@ bytes_translate_impl(PyBytesObject *self, PyObject *table, int group_right_1,
         PyBuffer_Release(&table_view);
         return NULL;
     }
-    output_start = output = PyBytes_AsString(result);
+    output_start = output = PyBytes_AS_STRING(result);
     input = PyBytes_AS_STRING(input_obj);
 
     if (dellen == 0 && table_chars != NULL) {
@@ -2914,145 +2729,17 @@ bytes_replace_impl(PyBytesObject *self, Py_buffer *old, Py_buffer *new,
 
 /** End DALKE **/
 
-/* Matches the end (direction >= 0) or start (direction < 0) of self
- * against substr, using the start and end arguments. Returns
- * -1 on error, 0 if not found and 1 if found.
- */
-Py_LOCAL(int)
-_bytes_tailmatch(PyBytesObject *self, PyObject *substr, Py_ssize_t start,
-                  Py_ssize_t end, int direction)
-{
-    Py_ssize_t len = PyBytes_GET_SIZE(self);
-    Py_ssize_t slen;
-    Py_buffer sub_view = {NULL, NULL};
-    const char* sub;
-    const char* str;
-
-    if (PyBytes_Check(substr)) {
-        sub = PyBytes_AS_STRING(substr);
-        slen = PyBytes_GET_SIZE(substr);
-    }
-    else {
-        if (PyObject_GetBuffer(substr, &sub_view, PyBUF_SIMPLE) != 0)
-            return -1;
-        sub = sub_view.buf;
-        slen = sub_view.len;
-    }
-    str = PyBytes_AS_STRING(self);
-
-    ADJUST_INDICES(start, end, len);
-
-    if (direction < 0) {
-        /* startswith */
-        if (start+slen > len)
-            goto notfound;
-    } else {
-        /* endswith */
-        if (end-start < slen || start > len)
-            goto notfound;
-
-        if (end-slen > start)
-            start = end - slen;
-    }
-    if (end-start < slen)
-        goto notfound;
-    if (memcmp(str+start, sub, slen) != 0)
-        goto notfound;
-
-    PyBuffer_Release(&sub_view);
-    return 1;
-
-notfound:
-    PyBuffer_Release(&sub_view);
-    return 0;
-}
-
-
-PyDoc_STRVAR(startswith__doc__,
-"B.startswith(prefix[, start[, end]]) -> bool\n\
-\n\
-Return True if B starts with the specified prefix, False otherwise.\n\
-With optional start, test B beginning at that position.\n\
-With optional end, stop comparing B at that position.\n\
-prefix can also be a tuple of bytes to try.");
 
 static PyObject *
 bytes_startswith(PyBytesObject *self, PyObject *args)
 {
-    Py_ssize_t start = 0;
+    return _Py_bytes_startswith(PyBytes_AS_STRING(self), PyBytes_GET_SIZE(self), args);
-    Py_ssize_t end = PY_SSIZE_T_MAX;
-    PyObject *subobj;
-    int result;
-
-    if (!stringlib_parse_args_finds("startswith", args, &subobj, &start, &end))
-        return NULL;
-    if (PyTuple_Check(subobj)) {
-        Py_ssize_t i;
-        for (i = 0; i < PyTuple_GET_SIZE(subobj); i++) {
-            result = _bytes_tailmatch(self,
-                            PyTuple_GET_ITEM(subobj, i),
-                            start, end, -1);
-            if (result == -1)
-                return NULL;
-            else if (result) {
-                Py_RETURN_TRUE;
-            }
-        }
-        Py_RETURN_FALSE;
-    }
-    result = _bytes_tailmatch(self, subobj, start, end, -1);
-    if (result == -1) {
-        if (PyErr_ExceptionMatches(PyExc_TypeError))
-            PyErr_Format(PyExc_TypeError, "startswith first arg must be bytes "
-                         "or a tuple of bytes, not %s", Py_TYPE(subobj)->tp_name);
-        return NULL;
-    }
-    else
-        return PyBool_FromLong(result);
 }
 
-
-PyDoc_STRVAR(endswith__doc__,
-"B.endswith(suffix[, start[, end]]) -> bool\n\
-\n\
-Return True if B ends with the specified suffix, False otherwise.\n\
-With optional start, test B beginning at that position.\n\
-With optional end, stop comparing B at that position.\n\
-suffix can also be a tuple of bytes to try.");
-
 static PyObject *
 bytes_endswith(PyBytesObject *self, PyObject *args)
 {
-    Py_ssize_t start = 0;
+    return _Py_bytes_endswith(PyBytes_AS_STRING(self), PyBytes_GET_SIZE(self), args);
-    Py_ssize_t end = PY_SSIZE_T_MAX;
-    PyObject *subobj;
-    int result;
-
-    if (!stringlib_parse_args_finds("endswith", args, &subobj, &start, &end))
-        return NULL;
-    if (PyTuple_Check(subobj)) {
-        Py_ssize_t i;
-        for (i = 0; i < PyTuple_GET_SIZE(subobj); i++) {
-            result = _bytes_tailmatch(self,
-                            PyTuple_GET_ITEM(subobj, i),
-                            start, end, +1);
-            if (result == -1)
-                return NULL;
-            else if (result) {
-                Py_RETURN_TRUE;
-            }
-        }
-        Py_RETURN_FALSE;
-    }
-    result = _bytes_tailmatch(self, subobj, start, end, +1);
-    if (result == -1) {
-        if (PyErr_ExceptionMatches(PyExc_TypeError))
-            PyErr_Format(PyExc_TypeError, "endswith first arg must be bytes or "
-                         "a tuple of bytes, not %s", Py_TYPE(subobj)->tp_name);
-        return NULL;
-    }
-    else
-        return PyBool_FromLong(result);
 }
 
 
@@ -3224,17 +2911,20 @@ bytes_methods[] = {
     {"__getnewargs__",          (PyCFunction)bytes_getnewargs,  METH_NOARGS},
     {"capitalize", (PyCFunction)stringlib_capitalize, METH_NOARGS,
      _Py_capitalize__doc__},
-    {"center", (PyCFunction)stringlib_center, METH_VARARGS, center__doc__},
+    {"center", (PyCFunction)stringlib_center, METH_VARARGS,
-    {"count", (PyCFunction)bytes_count, METH_VARARGS, count__doc__},
+     _Py_center__doc__},
+    {"count", (PyCFunction)bytes_count, METH_VARARGS,
+     _Py_count__doc__},
     BYTES_DECODE_METHODDEF
     {"endswith", (PyCFunction)bytes_endswith, METH_VARARGS,
-     endswith__doc__},
+     _Py_endswith__doc__},
     {"expandtabs", (PyCFunction)stringlib_expandtabs, METH_VARARGS | METH_KEYWORDS,
-     expandtabs__doc__},
+     _Py_expandtabs__doc__},
-    {"find", (PyCFunction)bytes_find, METH_VARARGS, find__doc__},
+    {"find", (PyCFunction)bytes_find, METH_VARARGS,
+     _Py_find__doc__},
     BYTES_FROMHEX_METHODDEF
     {"hex", (PyCFunction)bytes_hex, METH_NOARGS, hex__doc__},
-    {"index", (PyCFunction)bytes_index, METH_VARARGS, index__doc__},
+    {"index", (PyCFunction)bytes_index, METH_VARARGS, _Py_index__doc__},
     {"isalnum", (PyCFunction)stringlib_isalnum, METH_NOARGS,
      _Py_isalnum__doc__},
     {"isalpha", (PyCFunction)stringlib_isalpha, METH_NOARGS,
@@ -3250,29 +2940,29 @@ bytes_methods[] = {
     {"isupper", (PyCFunction)stringlib_isupper, METH_NOARGS,
      _Py_isupper__doc__},
     BYTES_JOIN_METHODDEF
-    {"ljust", (PyCFunction)stringlib_ljust, METH_VARARGS, ljust__doc__},
+    {"ljust", (PyCFunction)stringlib_ljust, METH_VARARGS, _Py_ljust__doc__},
     {"lower", (PyCFunction)stringlib_lower, METH_NOARGS, _Py_lower__doc__},
     BYTES_LSTRIP_METHODDEF
     BYTES_MAKETRANS_METHODDEF
     BYTES_PARTITION_METHODDEF
     BYTES_REPLACE_METHODDEF
-    {"rfind", (PyCFunction)bytes_rfind, METH_VARARGS, rfind__doc__},
+    {"rfind", (PyCFunction)bytes_rfind, METH_VARARGS, _Py_rfind__doc__},
-    {"rindex", (PyCFunction)bytes_rindex, METH_VARARGS, rindex__doc__},
+    {"rindex", (PyCFunction)bytes_rindex, METH_VARARGS, _Py_rindex__doc__},
-    {"rjust", (PyCFunction)stringlib_rjust, METH_VARARGS, rjust__doc__},
+    {"rjust", (PyCFunction)stringlib_rjust, METH_VARARGS, _Py_rjust__doc__},
     BYTES_RPARTITION_METHODDEF
     BYTES_RSPLIT_METHODDEF
     BYTES_RSTRIP_METHODDEF
     BYTES_SPLIT_METHODDEF
     BYTES_SPLITLINES_METHODDEF
     {"startswith", (PyCFunction)bytes_startswith, METH_VARARGS,
-     startswith__doc__},
+     _Py_startswith__doc__},
     BYTES_STRIP_METHODDEF
     {"swapcase", (PyCFunction)stringlib_swapcase, METH_NOARGS,
      _Py_swapcase__doc__},
     {"title", (PyCFunction)stringlib_title, METH_NOARGS, _Py_title__doc__},
     BYTES_TRANSLATE_METHODDEF
     {"upper", (PyCFunction)stringlib_upper, METH_NOARGS, _Py_upper__doc__},
-    {"zfill", (PyCFunction)stringlib_zfill, METH_VARARGS, zfill__doc__},
+    {"zfill", (PyCFunction)stringlib_zfill, METH_VARARGS, _Py_zfill__doc__},
     {NULL,     NULL}                         /* sentinel */
 };
 

Objects/stringlib/find.h

@@ -117,76 +117,3 @@ STRINGLIB(parse_args_finds)(const char * function_name, PyObject *args,
 }
 
 #undef FORMAT_BUFFER_SIZE
-
-#if STRINGLIB_IS_UNICODE
-
-/*
-Wraps stringlib_parse_args_finds() and additionally ensures that the
-first argument is a unicode object.
-*/
-
-Py_LOCAL_INLINE(int)
-STRINGLIB(parse_args_finds_unicode)(const char * function_name, PyObject *args,
-                                   PyObject **substring,
-                                   Py_ssize_t *start, Py_ssize_t *end)
-{
-    if(STRINGLIB(parse_args_finds)(function_name, args, substring,
-                                  start, end)) {
-        if (ensure_unicode(*substring) < 0)
-            return 0;
-        return 1;
-    }
-    return 0;
-}
-
-#else /* !STRINGLIB_IS_UNICODE */
-
-/*
-Wraps stringlib_parse_args_finds() and additionally checks whether the
-first argument is an integer in range(0, 256).
-
-If this is the case, writes the integer value to the byte parameter
-and sets subobj to NULL. Otherwise, sets the first argument to subobj
-and doesn't touch byte. The other parameters are similar to those of
-stringlib_parse_args_finds().
-*/
-
-Py_LOCAL_INLINE(int)
-STRINGLIB(parse_args_finds_byte)(const char *function_name, PyObject *args,
-                                 PyObject **subobj, char *byte,
-                                 Py_ssize_t *start, Py_ssize_t *end)
-{
-    PyObject *tmp_subobj;
-    Py_ssize_t ival;
-    PyObject *err;
-
-    if(!STRINGLIB(parse_args_finds)(function_name, args, &tmp_subobj,
-                                    start, end))
-        return 0;
-
-    if (!PyNumber_Check(tmp_subobj)) {
-        *subobj = tmp_subobj;
-        return 1;
-    }
-
-    ival = PyNumber_AsSsize_t(tmp_subobj, PyExc_OverflowError);
-    if (ival == -1) {
-        err = PyErr_Occurred();
-        if (err && !PyErr_GivenExceptionMatches(err, PyExc_OverflowError)) {
-            PyErr_Clear();
-            *subobj = tmp_subobj;
-            return 1;
-        }
-    }
-
-    if (ival < 0 || ival > 255) {
-        PyErr_SetString(PyExc_ValueError, "byte must be in range(0, 256)");
-        return 0;
-    }
-
-    *subobj = NULL;
-    *byte = (char)ival;
-    return 1;
-}
-
-#endif /* STRINGLIB_IS_UNICODE */

Objects/stringlib/transmogrify.h

@@ -4,12 +4,6 @@
 /* the more complicated methods.  parts of these should be pulled out into the
    shared code in bytes_methods.c to cut down on duplicate code bloat.  */
 
-PyDoc_STRVAR(expandtabs__doc__,
-"B.expandtabs(tabsize=8) -> copy of B\n\
-\n\
-Return a copy of B where all tab characters are expanded using spaces.\n\
-If tabsize is not given, a tab size of 8 characters is assumed.");
-
 static PyObject*
 stringlib_expandtabs(PyObject *self, PyObject *args, PyObject *kwds)
 {
@@ -120,12 +114,6 @@ pad(PyObject *self, Py_ssize_t left, Py_ssize_t right, char fill)
     return u;
 }
 
-PyDoc_STRVAR(ljust__doc__,
-"B.ljust(width[, fillchar]) -> copy of B\n"
-"\n"
-"Return B left justified in a string of length width. Padding is\n"
-"done using the specified fill character (default is a space).");
-
 static PyObject *
 stringlib_ljust(PyObject *self, PyObject *args)
 {
@@ -150,12 +138,6 @@ stringlib_ljust(PyObject *self, PyObject *args)
 }
 
 
-PyDoc_STRVAR(rjust__doc__,
-"B.rjust(width[, fillchar]) -> copy of B\n"
-"\n"
-"Return B right justified in a string of length width. Padding is\n"
-"done using the specified fill character (default is a space)");
-
 static PyObject *
 stringlib_rjust(PyObject *self, PyObject *args)
 {
@@ -180,12 +162,6 @@ stringlib_rjust(PyObject *self, PyObject *args)
 }
 
 
-PyDoc_STRVAR(center__doc__,
-"B.center(width[, fillchar]) -> copy of B\n"
-"\n"
-"Return B centered in a string of length width.  Padding is\n"
-"done using the specified fill character (default is a space).");
-
 static PyObject *
 stringlib_center(PyObject *self, PyObject *args)
 {
@@ -213,12 +189,6 @@ stringlib_center(PyObject *self, PyObject *args)
     return pad(self, left, marg - left, fillchar);
 }
 
-PyDoc_STRVAR(zfill__doc__,
-"B.zfill(width) -> copy of B\n"
-"\n"
-"Pad a numeric string B with zeros on the left, to fill a field\n"
-"of the specified width.  B is never truncated.");
-
 static PyObject *
 stringlib_zfill(PyObject *self, PyObject *args)
 {

Objects/unicodeobject.c

@@ -11244,6 +11244,25 @@ PyUnicode_AppendAndDel(PyObject **pleft, PyObject *right)
     Py_XDECREF(right);
 }
 
+/*
+Wraps stringlib_parse_args_finds() and additionally ensures that the
+first argument is a unicode object.
+*/
+
+Py_LOCAL_INLINE(int)
+parse_args_finds_unicode(const char * function_name, PyObject *args,
+                         PyObject **substring,
+                         Py_ssize_t *start, Py_ssize_t *end)
+{
+    if(stringlib_parse_args_finds(function_name, args, substring,
+                                  start, end)) {
+        if (ensure_unicode(*substring) < 0)
+            return 0;
+        return 1;
+    }
+    return 0;
+}
+
 PyDoc_STRVAR(count__doc__,
              "S.count(sub[, start[, end]]) -> int\n\
 \n\
@@ -11262,8 +11281,7 @@ unicode_count(PyObject *self, PyObject *args)
     void *buf1, *buf2;
     Py_ssize_t len1, len2, iresult;
 
-    if (!stringlib_parse_args_finds_unicode("count", args, &substring,
+    if (!parse_args_finds_unicode("count", args, &substring, &start, &end))
-                                            &start, &end))
         return NULL;
 
     kind1 = PyUnicode_KIND(self);
@@ -11445,8 +11463,7 @@ unicode_find(PyObject *self, PyObject *args)
     Py_ssize_t end = 0;
     Py_ssize_t result;
 
-    if (!stringlib_parse_args_finds_unicode("find", args, &substring,
+    if (!parse_args_finds_unicode("find", args, &substring, &start, &end))
-                                            &start, &end))
         return NULL;
 
     if (PyUnicode_READY(self) == -1)
@@ -11525,8 +11542,7 @@ unicode_index(PyObject *self, PyObject *args)
     Py_ssize_t start = 0;
     Py_ssize_t end = 0;
 
-    if (!stringlib_parse_args_finds_unicode("index", args, &substring,
+    if (!parse_args_finds_unicode("index", args, &substring, &start, &end))
-                                            &start, &end))
         return NULL;
 
     if (PyUnicode_READY(self) == -1)
@@ -12555,8 +12571,7 @@ unicode_rfind(PyObject *self, PyObject *args)
     Py_ssize_t end = 0;
     Py_ssize_t result;
 
-    if (!stringlib_parse_args_finds_unicode("rfind", args, &substring,
+    if (!parse_args_finds_unicode("rfind", args, &substring, &start, &end))
-                                            &start, &end))
         return NULL;
 
     if (PyUnicode_READY(self) == -1)
@@ -12584,8 +12599,7 @@ unicode_rindex(PyObject *self, PyObject *args)
     Py_ssize_t end = 0;
     Py_ssize_t result;
 
-    if (!stringlib_parse_args_finds_unicode("rindex", args, &substring,
+    if (!parse_args_finds_unicode("rindex", args, &substring, &start, &end))
-                                            &start, &end))
         return NULL;
 
     if (PyUnicode_READY(self) == -1)