needforspeed: added rpartition implementation

diff --git a/Include/unicodeobject.h b/Include/unicodeobject.h
index 664578223c9853fd582d565e3b05f061c2732c43..0531aedb30dcca309c7b06357c413f2bf8533a5f 100644 (file)
--- a/Include/unicodeobject.h
+++ b/Include/unicodeobject.h
@@ -185,11 +185,12 @@ typedef PY_UNICODE_TYPE Py_UNICODE;
 # define PyUnicode_GetSize PyUnicodeUCS2_GetSize
 # define PyUnicode_Join PyUnicodeUCS2_Join
 # define PyUnicode_Partition PyUnicodeUCS2_Partition
+# define PyUnicode_RPartition PyUnicodeUCS2_RPartition
+# define PyUnicode_RSplit PyUnicodeUCS2_RSplit
 # define PyUnicode_Replace PyUnicodeUCS2_Replace
 # define PyUnicode_Resize PyUnicodeUCS2_Resize
 # define PyUnicode_SetDefaultEncoding PyUnicodeUCS2_SetDefaultEncoding
 # define PyUnicode_Split PyUnicodeUCS2_Split
-# define PyUnicode_RSplit PyUnicodeUCS2_RSplit
 # define PyUnicode_Splitlines PyUnicodeUCS2_Splitlines
 # define PyUnicode_Tailmatch PyUnicodeUCS2_Tailmatch
 # define PyUnicode_Translate PyUnicodeUCS2_Translate
@@ -261,6 +262,8 @@ typedef PY_UNICODE_TYPE Py_UNICODE;
 # define PyUnicode_GetSize PyUnicodeUCS4_GetSize
 # define PyUnicode_Join PyUnicodeUCS4_Join
 # define PyUnicode_Partition PyUnicodeUCS4_Partition
+# define PyUnicode_RPartition PyUnicodeUCS4_RPartition
+# define PyUnicode_RSplit PyUnicodeUCS4_RSplit
 # define PyUnicode_Replace PyUnicodeUCS4_Replace
 # define PyUnicode_Resize PyUnicodeUCS4_Resize
 # define PyUnicode_SetDefaultEncoding PyUnicodeUCS4_SetDefaultEncoding
@@ -1027,6 +1030,14 @@ PyAPI_FUNC(PyObject*) PyUnicode_Partition(
     PyObject *sep              /* String separator */
     );         
 
+/* Partition a string using a given separator, searching from the end of the
+   string. */
+
+PyAPI_FUNC(PyObject*) PyUnicode_RPartition(
+    PyObject *s,               /* String to partition */
+    PyObject *sep              /* String separator */
+    );         
+
 /* Split a string giving a list of Unicode strings.
 
    If sep is NULL, splitting will be done at all whitespace

diff --git a/Objects/stringlib/fastsearch.h b/Objects/stringlib/fastsearch.h
index 1ce7f13ff62aa396c4898f8da0a2287137d3e112..3d2f92aa5425d6345f8f8bc1b6397ae947a133a4 100644 (file)
--- a/Objects/stringlib/fastsearch.h
+++ b/Objects/stringlib/fastsearch.h
@@ -95,3 +95,10 @@ fastsearch(const STRINGLIB_CHAR* s, Py_ssize_t n,
 }
 
 #endif
+
+/*
+Local variables:
+c-basic-offset: 4
+indent-tabs-mode: nil
+End:
+*/

diff --git a/Objects/stringlib/partition.h b/Objects/stringlib/partition.h
index 38afb3387b297a5bb261e861a50be0203ac92fb5..71e80a91ea20c1f70cd2429f0671b8d84ad38721 100644 (file)
--- a/Objects/stringlib/partition.h
+++ b/Objects/stringlib/partition.h
@@ -5,7 +5,7 @@
 
 Py_LOCAL(PyObject*)
 partition(PyObject* str_obj, const STRINGLIB_CHAR* str, Py_ssize_t str_len,
-         PyObject* sep_obj, const STRINGLIB_CHAR* sep, Py_ssize_t sep_len)
+          PyObject* sep_obj, const STRINGLIB_CHAR* sep, Py_ssize_t sep_len)
 {
     PyObject* out;
     Py_ssize_t pos;
@@ -45,4 +45,64 @@ partition(PyObject* str_obj, const STRINGLIB_CHAR* str, Py_ssize_t str_len,
     return out;
 }
 
+Py_LOCAL(PyObject*)
+rpartition(PyObject* str_obj, const STRINGLIB_CHAR* str, Py_ssize_t str_len,
+          PyObject* sep_obj, const STRINGLIB_CHAR* sep, Py_ssize_t sep_len)
+{
+    PyObject* out;
+    Py_ssize_t pos;
+
+    if (sep_len == 0) {
+        PyErr_SetString(PyExc_ValueError, "empty separator");
+       return NULL;
+    }
+
+    out = PyTuple_New(3);
+    if (!out)
+       return NULL;
+
+    /* XXX - create reversefastsearch helper! */
+    if (sep_len == 0)
+       pos = str_len;
+    else {
+       Py_ssize_t j;
+        pos = -1;
+       for (j = str_len - sep_len; j >= 0; --j)
+            if (STRINGLIB_CMP(str+j, sep, sep_len) == 0) {
+                pos = j;
+                break;
+            }
+    }
+
+    if (pos < 0) {
+       Py_INCREF(str_obj);
+       PyTuple_SET_ITEM(out, 0, (PyObject*) str_obj);
+       Py_INCREF(STRINGLIB_EMPTY);
+       PyTuple_SET_ITEM(out, 1, (PyObject*) STRINGLIB_EMPTY);
+       Py_INCREF(STRINGLIB_EMPTY);
+       PyTuple_SET_ITEM(out, 2, (PyObject*) STRINGLIB_EMPTY);
+       return out;
+    }
+
+    PyTuple_SET_ITEM(out, 0, STRINGLIB_NEW(str, pos));
+    Py_INCREF(sep_obj);
+    PyTuple_SET_ITEM(out, 1, sep_obj);
+    pos += sep_len;
+    PyTuple_SET_ITEM(out, 2, STRINGLIB_NEW(str + pos, str_len - pos));
+
+    if (PyErr_Occurred()) {
+       Py_DECREF(out);
+       return NULL;
+    }
+
+    return out;
+}
+
 #endif
+
+/*
+Local variables:
+c-basic-offset: 4
+indent-tabs-mode: nil
+End:
+*/

diff --git a/Objects/stringobject.c b/Objects/stringobject.c
index ded1907fcaa1667ed02a65d222879694af8aca13..44deeed6468521e6b9f0ad2b0815df60c94cf47b 100644 (file)
--- a/Objects/stringobject.c
+++ b/Objects/stringobject.c
@@ -768,7 +768,10 @@ PyString_AsStringAndSize(register PyObject *obj,
 /* stringlib components */
 
 #define STRINGLIB_CHAR char
+
 #define STRINGLIB_NEW PyString_FromStringAndSize
+#define STRINGLIB_CMP memcmp
+
 #define STRINGLIB_EMPTY nullstring
 
 #include "stringlib/fastsearch.h"
@@ -1530,6 +1533,37 @@ string_partition(PyStringObject *self, PyObject *sep_obj)
                );
 }
 
+PyDoc_STRVAR(rpartition__doc__,
+"S.rpartition(sep) -> (head, sep, tail)\n\
+\n\
+Searches for the separator sep in S, starting at the end of S, and returns\n\
+the part before it, the separator itself, and the part after it.  If the\n\
+separator is not found, returns S and two empty strings.");
+
+static PyObject *
+string_rpartition(PyStringObject *self, PyObject *sep_obj)
+{
+       const char *sep;
+       Py_ssize_t sep_len;
+
+       if (PyString_Check(sep_obj)) {
+               sep = PyString_AS_STRING(sep_obj);
+               sep_len = PyString_GET_SIZE(sep_obj);
+       }
+#ifdef Py_USING_UNICODE
+       else if (PyUnicode_Check(sep_obj))
+               return PyUnicode_Partition((PyObject *) self, sep_obj);
+#endif
+       else if (PyObject_AsCharBuffer(sep_obj, &sep, &sep_len))
+               return NULL;
+
+       return rpartition(
+               (PyObject*) self,
+               PyString_AS_STRING(self), PyString_GET_SIZE(self),
+               sep_obj, sep, sep_len
+               );
+}
+
 Py_LOCAL(PyObject *)
 rsplit_whitespace(const char *s, Py_ssize_t len, Py_ssize_t maxsplit)
 {
@@ -3810,6 +3844,8 @@ string_methods[] = {
        {"rfind", (PyCFunction)string_rfind, METH_VARARGS, rfind__doc__},
        {"rindex", (PyCFunction)string_rindex, METH_VARARGS, rindex__doc__},
        {"rstrip", (PyCFunction)string_rstrip, METH_VARARGS, rstrip__doc__},
+       {"rpartition", (PyCFunction)string_rpartition, METH_O,
+        rpartition__doc__},
        {"startswith", (PyCFunction)string_startswith, METH_VARARGS,
         startswith__doc__},
        {"strip", (PyCFunction)string_strip, METH_VARARGS, strip__doc__},

diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
index 0ebc30a2bc275eb0ea6cad224eae7d9bacb08777..df15f4be88ade03cacdbcf3bfda1d05b34de8f78 100644 (file)
--- a/Objects/unicodeobject.c
+++ b/Objects/unicodeobject.c
@@ -3858,6 +3858,14 @@ int PyUnicode_EncodeDecimal(Py_UNICODE *s,
 
 #define STRINGLIB_NEW PyUnicode_FromUnicode
 
+Py_LOCAL(int)
+STRINGLIB_CMP(const Py_UNICODE* str, const Py_UNICODE* other, Py_ssize_t len)
+{
+    if (str[0] == other[0])
+        return 0;
+    return memcmp((void*) str, (void*) other, len * sizeof(Py_UNICODE));
+}
+
 #define STRINGLIB_EMPTY unicode_empty
 
 #include "stringlib/fastsearch.h"
@@ -6225,6 +6233,34 @@ PyUnicode_Partition(PyObject *str_in, PyObject *sep_in)
     return out;
 }
 
+
+PyObject *
+PyUnicode_RPartition(PyObject *str_in, PyObject *sep_in)
+{
+    PyObject* str_obj;
+    PyObject* sep_obj;
+    PyObject* out;
+
+    str_obj = PyUnicode_FromObject(str_in);
+    if (!str_obj)
+       return NULL;
+    sep_obj = PyUnicode_FromObject(sep_in);
+    if (!sep_obj) {
+        Py_DECREF(str_obj);
+        return NULL;
+    }
+
+    out = rpartition(
+        str_obj, PyUnicode_AS_UNICODE(str_obj), PyUnicode_GET_SIZE(str_obj),
+        sep_obj, PyUnicode_AS_UNICODE(sep_obj), PyUnicode_GET_SIZE(sep_obj)
+        );
+
+    Py_DECREF(sep_obj);
+    Py_DECREF(str_obj);
+
+    return out;
+}
+
 PyDoc_STRVAR(partition__doc__,
 "S.partition(sep) -> (head, sep, tail)\n\
 \n\
@@ -6238,6 +6274,19 @@ unicode_partition(PyUnicodeObject *self, PyObject *separator)
     return PyUnicode_Partition((PyObject *)self, separator);
 }
 
+PyDoc_STRVAR(rpartition__doc__,
+"S.rpartition(sep) -> (head, sep, tail)\n\
+\n\
+Searches for the separator sep in S, starting at the end of S, and returns\n\
+the part before it, the separator itself, and the part after it.  If the\n\
+separator is not found, returns S and two empty strings.");
+
+static PyObject*
+unicode_rpartition(PyUnicodeObject *self, PyObject *separator)
+{
+    return PyUnicode_RPartition((PyObject *)self, separator);
+}
+
 PyObject *PyUnicode_RSplit(PyObject *s,
                           PyObject *sep,
                           Py_ssize_t maxsplit)
@@ -6502,6 +6551,7 @@ static PyMethodDef unicode_methods[] = {
     {"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, splitlines__doc__},
     {"strip", (PyCFunction) unicode_strip, METH_VARARGS, strip__doc__},
     {"swapcase", (PyCFunction) unicode_swapcase, METH_NOARGS, swapcase__doc__},