Skip to content

C
cpython
Kaydet (Commit) 75c00efc authored tarafından Hye-Shik Chang's avatar Hye-Shik Chang
Dosyalara gözat
Seçenekler

[SF #866875] Add a specialized routine for one character 

separaters on str.split() and str.rsplit().
üst cb2117a8
Hide whitespace changes
Inline Side-by-side
Showing with 150 additions and 59 deletions
Lib/test/string_tests.py
Dosyayı görüntüle @ 75c00efc
......@@ -175,41 +175,82 @@ class CommonTest(unittest.TestCase):
def test_split(self):
self.checkequal(['this', 'is', 'the', 'split', 'function'],
'this is the split function', 'split')
self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'split', '|')
self.checkequal(['a', 'b', 'c|d'], 'a|b|c|d', 'split', '|', 2)
# by whitespace
self.checkequal(['a', 'b', 'c', 'd'], 'a b c d ', 'split')
self.checkequal(['a', 'b c d'], 'a b c d', 'split', None, 1)
self.checkequal(['a', 'b', 'c d'], 'a b c d', 'split', None, 2)
self.checkequal(['a', 'b', 'c', 'd'], 'a b c d', 'split', None, 3)
self.checkequal(['a', 'b', 'c', 'd'], 'a b c d', 'split', None, 4)
self.checkequal(['a b c d'], 'a b c d', 'split', None, 0)
self.checkequal(['a', 'b', 'c d'], 'a b c d', 'split', None, 2)
self.checkequal(['a', 'b', 'c', 'd'], 'a b c d ', 'split')
# by a char
self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'split', '|')
self.checkequal(['a', 'b|c|d'], 'a|b|c|d', 'split', '|', 1)
self.checkequal(['a', 'b', 'c|d'], 'a|b|c|d', 'split', '|', 2)
self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'split', '|', 3)
self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'split', '|', 4)
self.checkequal(['a|b|c|d'], 'a|b|c|d', 'split', '|', 0)
self.checkequal(['a', '', 'b||c||d'], 'a||b||c||d', 'split', '|', 2)
self.checkequal(['endcase ', ''], 'endcase |', 'split', '|')
self.checkequal(['a', '', 'b\x00c\x00d'], 'a\x00\x00b\x00c\x00d', 'split', '\x00', 2)
# by string
self.checkequal(['a', 'b', 'c', 'd'], 'a//b//c//d', 'split', '//')
self.checkequal(['a', 'b//c//d'], 'a//b//c//d', 'split', '//', 1)
self.checkequal(['a', 'b', 'c//d'], 'a//b//c//d', 'split', '//', 2)
self.checkequal(['a', 'b', 'c', 'd'], 'a//b//c//d', 'split', '//', 3)
self.checkequal(['a', 'b', 'c', 'd'], 'a//b//c//d', 'split', '//', 4)
self.checkequal(['a//b//c//d'], 'a//b//c//d', 'split', '//', 0)
self.checkequal(['a', '', 'b////c////d'], 'a////b////c////d', 'split', '//', 2)
self.checkequal(['endcase ', ''], 'endcase test', 'split', 'test')
# mixed use of str and unicode
self.checkequal([u'a', u'b', u'c d'], 'a b c d', 'split', u' ', 2)
# argument type
self.checkraises(TypeError, 'hello', 'split', 42, 42, 42)
def test_rsplit(self):
self.checkequal(['this', 'is', 'the', 'rsplit', 'function'],
'this is the rsplit function', 'rsplit')
self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'rsplit', '|')
self.checkequal(['a|b', 'c', 'd'], 'a|b|c|d', 'rsplit', '|', 2)
# by whitespace
self.checkequal(['a', 'b', 'c', 'd'], 'a b c d ', 'rsplit')
self.checkequal(['a b c', 'd'], 'a b c d', 'rsplit', None, 1)
self.checkequal(['a b', 'c', 'd'], 'a b c d', 'rsplit', None, 2)
self.checkequal(['a', 'b', 'c', 'd'], 'a b c d', 'rsplit', None, 3)
self.checkequal(['a', 'b', 'c', 'd'], 'a b c d', 'rsplit', None, 4)
self.checkequal(['a b c d'], 'a b c d', 'rsplit', None, 0)
self.checkequal(['a, b, c', 'd'], 'a, b, c, d', 'rsplit', ', ', 1)
self.checkequal(['a, b', 'c', 'd'], 'a, b, c, d', 'rsplit', ', ', 2)
self.checkequal(['a', 'b', 'c', 'd'], 'a, b, c, d', 'rsplit', ', ', 3)
self.checkequal(['a', 'b', 'c', 'd'], 'a, b, c, d', 'rsplit', ', ', 4)
self.checkequal(['a, b, c, d'], 'a, b, c, d', 'rsplit', ', ', 0)
self.checkequal(['a b', 'c', 'd'], 'a b c d', 'rsplit', None, 2)
self.checkequal(['a\x00b', 'c'], 'a\x00b\x00c', 'rsplit', '\x00', 1)
self.checkequal(['', ''], 'abcd', 'rsplit', 'abcd')
# by a char
self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'rsplit', '|')
self.checkequal(['a|b|c', 'd'], 'a|b|c|d', 'rsplit', '|', 1)
self.checkequal(['a|b', 'c', 'd'], 'a|b|c|d', 'rsplit', '|', 2)
self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'rsplit', '|', 3)
self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'rsplit', '|', 4)
self.checkequal(['a|b|c|d'], 'a|b|c|d', 'rsplit', '|', 0)
self.checkequal(['a||b||c', '', 'd'], 'a||b||c||d', 'rsplit', '|', 2)
self.checkequal(['', ' begincase'], '| begincase', 'rsplit', '|')
self.checkequal(['a\x00\x00b', 'c', 'd'], 'a\x00\x00b\x00c\x00d', 'rsplit', '\x00', 2)
# by string
self.checkequal(['a', 'b', 'c', 'd'], 'a//b//c//d', 'rsplit', '//')
self.checkequal(['a//b//c', 'd'], 'a//b//c//d', 'rsplit', '//', 1)
self.checkequal(['a//b', 'c', 'd'], 'a//b//c//d', 'rsplit', '//', 2)
self.checkequal(['a', 'b', 'c', 'd'], 'a//b//c//d', 'rsplit', '//', 3)
self.checkequal(['a', 'b', 'c', 'd'], 'a//b//c//d', 'rsplit', '//', 4)
self.checkequal(['a//b//c//d'], 'a//b//c//d', 'rsplit', '//', 0)
self.checkequal(['a////b////c', '', 'd'], 'a////b////c////d', 'rsplit', '//', 2)
self.checkequal(['', ' begincase'], 'test begincase', 'rsplit', 'test')
# mixed use of str and unicode
self.checkequal([u'a b', u'c', u'd'], 'a b c d', 'rsplit', u' ', 2)
self.checkequal(['', ' endcase'], '| endcase', 'rsplit', '|')
self.checkequal(['', ' endcase'], 'test endcase', 'rsplit', 'test')
# argument type
self.checkraises(TypeError, 'hello', 'rsplit', 42, 42, 42)
def test_strip(self):
self.checkequal('hello', ' hello ', 'strip')
......
Objects/stringobject.c
Dosyayı görüntüle @ 75c00efc
......@@ -1282,12 +1282,35 @@ static const char *stripformat[] = {"|O:lstrip", "|O:rstrip", "|O:strip"};
#define STRIPNAME(i) (stripformat[i]+3)
#define SPLIT_APPEND(data, left, right) \
str = PyString_FromStringAndSize((data) + (left), \
(right) - (left)); \
if (str == NULL) \
goto onError; \
if (PyList_Append(list, str)) { \
Py_DECREF(str); \
goto onError; \
} \
else \
Py_DECREF(str);
#define SPLIT_INSERT(data, left, right) \
str = PyString_FromStringAndSize((data) + (left), \
(right) - (left)); \
if (str == NULL) \
goto onError; \
if (PyList_Insert(list, 0, str)) { \
Py_DECREF(str); \
goto onError; \
} \
else \
Py_DECREF(str);
static PyObject *
split_whitespace(const char *s, int len, int maxsplit)
{
int i, j, err;
PyObject* item;
int i, j;
PyObject *str;
PyObject *list = PyList_New(0);
if (list == NULL)
......@@ -1302,33 +1325,49 @@ split_whitespace(const char *s, int len, int maxsplit)
if (j < i) {
if (maxsplit-- <= 0)
break;
item = PyString_FromStringAndSize(s+j, (int)(i-j));
if (item == NULL)
goto finally;
err = PyList_Append(list, item);
Py_DECREF(item);
if (err < 0)
goto finally;
SPLIT_APPEND(s, j, i);
while (i < len && isspace(Py_CHARMASK(s[i])))
i++;
j = i;
}
}
if (j < len) {
item = PyString_FromStringAndSize(s+j, (int)(len - j));
if (item == NULL)
goto finally;
err = PyList_Append(list, item);
Py_DECREF(item);
if (err < 0)
goto finally;
SPLIT_APPEND(s, j, len);
}
return list;
finally:
onError:
Py_DECREF(list);
return NULL;
}
static PyObject *
split_char(const char *s, int len, char ch, int maxcount)
{
register int i, j;
PyObject *str;
PyObject *list = PyList_New(0);
if (list == NULL)
return NULL;
for (i = j = 0; i < len; ) {
if (s[i] == ch) {
if (maxcount-- <= 0)
break;
SPLIT_APPEND(s, j, i);
i = j = i + 1;
} else
i++;
}
if (j <= len) {
SPLIT_APPEND(s, j, len);
}
return list;
onError:
Py_DECREF(list);
return NULL;
}
PyDoc_STRVAR(split__doc__,
"S.split([sep [,maxsplit]]) -> list of strings\n\
......@@ -1362,10 +1401,13 @@ string_split(PyStringObject *self, PyObject *args)
#endif
else if (PyObject_AsCharBuffer(subobj, &sub, &n))
return NULL;
if (n == 0) {
PyErr_SetString(PyExc_ValueError, "empty separator");
return NULL;
}
else if (n == 1)
return split_char(s, len, sub[0], maxsplit);
list = PyList_New(0);
if (list == NULL)
......@@ -1406,8 +1448,8 @@ string_split(PyStringObject *self, PyObject *args)
static PyObject *
rsplit_whitespace(const char *s, int len, int maxsplit)
{
int i, j, err;
PyObject* item;
int i, j;
PyObject *str;
PyObject *list = PyList_New(0);
if (list == NULL)
......@@ -1422,33 +1464,49 @@ rsplit_whitespace(const char *s, int len, int maxsplit)
if (j > i) {
if (maxsplit-- <= 0)
break;
item = PyString_FromStringAndSize(s+i+1, (int)(j-i));
if (item == NULL)
goto finally;
err = PyList_Insert(list, 0, item);
Py_DECREF(item);
if (err < 0)
goto finally;
SPLIT_INSERT(s, i + 1, j + 1);
while (i >= 0 && isspace(Py_CHARMASK(s[i])))
i--;
j = i;
}
}
if (j >= 0) {
item = PyString_FromStringAndSize(s, (int)(j + 1));
if (item == NULL)
goto finally;
err = PyList_Insert(list, 0, item);
Py_DECREF(item);
if (err < 0)
goto finally;
SPLIT_INSERT(s, 0, j + 1);
}
return list;
finally:
onError:
Py_DECREF(list);
return NULL;
}
static PyObject *
rsplit_char(const char *s, int len, char ch, int maxcount)
{
register int i, j;
PyObject *str;
PyObject *list = PyList_New(0);
if (list == NULL)
return NULL;
for (i = j = len - 1; i >= 0; ) {
if (s[i] == ch) {
if (maxcount-- <= 0)
break;
SPLIT_INSERT(s, i + 1, j + 1);
j = i = i - 1;
} else
i--;
}
if (j >= -1) {
SPLIT_INSERT(s, 0, j + 1);
}
return list;
onError:
Py_DECREF(list);
return NULL;
}
PyDoc_STRVAR(rsplit__doc__,
"S.rsplit([sep [,maxsplit]]) -> list of strings\n\
......@@ -1483,10 +1541,13 @@ string_rsplit(PyStringObject *self, PyObject *args)
#endif
else if (PyObject_AsCharBuffer(subobj, &sub, &n))
return NULL;
if (n == 0) {
PyErr_SetString(PyExc_ValueError, "empty separator");
return NULL;
}
else if (n == 1)
return rsplit_char(s, len, sub[0], maxsplit);
list = PyList_New(0);
if (list == NULL)
......@@ -3104,17 +3165,6 @@ 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.");
#define SPLIT_APPEND(data, left, right) \
str = PyString_FromStringAndSize(data + left, right - left); \
if (!str) \
goto onError; \
if (PyList_Append(list, str)) { \
Py_DECREF(str); \
goto onError; \
} \
else \
Py_DECREF(str);
static PyObject*
string_splitlines(PyStringObject *self, PyObject *args)
{
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment