[Python-checkins] cpython (2.7): startswith and endswith don't accept None as slice index. Patch by Torsten

Wed Apr 20 17:59:51 CEST 2011

http://hg.python.org/cpython/rev/f4da64529e8c
changeset: 69471:f4da64529e8c
branch: 2.7
parent: 69464:83a426e969f5
user: Jesus Cea <jcea at jcea.es>
date: Wed Apr 20 16:39:15 2011 +0200
summary:
 startswith and endswith don't accept None as slice index. Patch by Torsten Becker. (closes #11828)
files:
 Lib/test/string_tests.py | 57 ++++++++++++++++++++++
 Lib/test/test_bytes.py | 62 ++++++++++++++++++++++++
 Misc/ACKS | 1 +
 Misc/NEWS | 3 +
 Objects/bytearrayobject.c | 13 ++---
 Objects/stringlib/find.h | 67 +++++++++++++++++++-------
 Objects/stringobject.c | 25 ++-------
 Objects/unicodeobject.c | 35 ++++++-------
 8 files changed, 198 insertions(+), 65 deletions(-)

diff --git a/Lib/test/string_tests.py b/Lib/test/string_tests.py
--- a/Lib/test/string_tests.py
+++ b/Lib/test/string_tests.py
@@ -1177,6 +1177,63 @@
 # mixed use of str and unicode
 self.assertEqual('a/b/c'.rpartition(u'/'), ('a/b', '/', 'c'))
 
+ def test_none_arguments(self):
+ # issue 11828
+ s = 'hello'
+ self.checkequal(2, s, 'find', 'l', None)
+ self.checkequal(3, s, 'find', 'l', -2, None)
+ self.checkequal(2, s, 'find', 'l', None, -2)
+ self.checkequal(0, s, 'find', 'h', None, None)
+
+ self.checkequal(3, s, 'rfind', 'l', None)
+ self.checkequal(3, s, 'rfind', 'l', -2, None)
+ self.checkequal(2, s, 'rfind', 'l', None, -2)
+ self.checkequal(0, s, 'rfind', 'h', None, None)
+
+ self.checkequal(2, s, 'index', 'l', None)
+ self.checkequal(3, s, 'index', 'l', -2, None)
+ self.checkequal(2, s, 'index', 'l', None, -2)
+ self.checkequal(0, s, 'index', 'h', None, None)
+
+ self.checkequal(3, s, 'rindex', 'l', None)
+ self.checkequal(3, s, 'rindex', 'l', -2, None)
+ self.checkequal(2, s, 'rindex', 'l', None, -2)
+ self.checkequal(0, s, 'rindex', 'h', None, None)
+
+ self.checkequal(2, s, 'count', 'l', None)
+ self.checkequal(1, s, 'count', 'l', -2, None)
+ self.checkequal(1, s, 'count', 'l', None, -2)
+ self.checkequal(0, s, 'count', 'x', None, None)
+
+ self.checkequal(True, s, 'endswith', 'o', None)
+ self.checkequal(True, s, 'endswith', 'lo', -2, None)
+ self.checkequal(True, s, 'endswith', 'l', None, -2)
+ self.checkequal(False, s, 'endswith', 'x', None, None)
+
+ self.checkequal(True, s, 'startswith', 'h', None)
+ self.checkequal(True, s, 'startswith', 'l', -2, None)
+ self.checkequal(True, s, 'startswith', 'h', None, -2)
+ self.checkequal(False, s, 'startswith', 'x', None, None)
+
+ def test_find_etc_raise_correct_error_messages(self):
+ # issue 11828
+ s = 'hello'
+ x = 'x'
+ self.assertRaisesRegexp(TypeError, r'\bfind\b', s.find,
+ x, None, None, None)
+ self.assertRaisesRegexp(TypeError, r'\brfind\b', s.rfind,
+ x, None, None, None)
+ self.assertRaisesRegexp(TypeError, r'\bindex\b', s.index,
+ x, None, None, None)
+ self.assertRaisesRegexp(TypeError, r'\brindex\b', s.rindex,
+ x, None, None, None)
+ self.assertRaisesRegexp(TypeError, r'^count\(', s.count,
+ x, None, None, None)
+ self.assertRaisesRegexp(TypeError, r'^startswith\(', s.startswith,
+ x, None, None, None)
+ self.assertRaisesRegexp(TypeError, r'^endswith\(', s.endswith,
+ x, None, None, None)
+
 class MixinStrStringUserStringTest:
 # Additional tests for 8bit strings, i.e. str, UserString and
 # the string module
diff --git a/Lib/test/test_bytes.py b/Lib/test/test_bytes.py
--- a/Lib/test/test_bytes.py
+++ b/Lib/test/test_bytes.py
@@ -456,6 +456,68 @@
 self.assertEqual([ord(b[i:i+1]) for i in range(len(b))],
 [0, 65, 127, 128, 255])
 
+ def test_none_arguments(self):
+ # issue 11828
+ b = self.type2test(b'hello')
+ l = self.type2test(b'l')
+ h = self.type2test(b'h')
+ x = self.type2test(b'x')
+ o = self.type2test(b'o')
+
+ self.assertEqual(2, b.find(l, None))
+ self.assertEqual(3, b.find(l, -2, None))
+ self.assertEqual(2, b.find(l, None, -2))
+ self.assertEqual(0, b.find(h, None, None))
+
+ self.assertEqual(3, b.rfind(l, None))
+ self.assertEqual(3, b.rfind(l, -2, None))
+ self.assertEqual(2, b.rfind(l, None, -2))
+ self.assertEqual(0, b.rfind(h, None, None))
+
+ self.assertEqual(2, b.index(l, None))
+ self.assertEqual(3, b.index(l, -2, None))
+ self.assertEqual(2, b.index(l, None, -2))
+ self.assertEqual(0, b.index(h, None, None))
+
+ self.assertEqual(3, b.rindex(l, None))
+ self.assertEqual(3, b.rindex(l, -2, None))
+ self.assertEqual(2, b.rindex(l, None, -2))
+ self.assertEqual(0, b.rindex(h, None, None))
+
+ self.assertEqual(2, b.count(l, None))
+ self.assertEqual(1, b.count(l, -2, None))
+ self.assertEqual(1, b.count(l, None, -2))
+ self.assertEqual(0, b.count(x, None, None))
+
+ self.assertEqual(True, b.endswith(o, None))
+ self.assertEqual(True, b.endswith(o, -2, None))
+ self.assertEqual(True, b.endswith(l, None, -2))
+ self.assertEqual(False, b.endswith(x, None, None))
+
+ self.assertEqual(True, b.startswith(h, None))
+ self.assertEqual(True, b.startswith(l, -2, None))
+ self.assertEqual(True, b.startswith(h, None, -2))
+ self.assertEqual(False, b.startswith(x, None, None))
+
+ def test_find_etc_raise_correct_error_messages(self):
+ # issue 11828
+ b = self.type2test(b'hello')
+ x = self.type2test(b'x')
+ self.assertRaisesRegexp(TypeError, r'\bfind\b', b.find,
+ x, None, None, None)
+ self.assertRaisesRegexp(TypeError, r'\brfind\b', b.rfind,
+ x, None, None, None)
+ self.assertRaisesRegexp(TypeError, r'\bindex\b', b.index,
+ x, None, None, None)
+ self.assertRaisesRegexp(TypeError, r'\brindex\b', b.rindex,
+ x, None, None, None)
+ self.assertRaisesRegexp(TypeError, r'\bcount\b', b.count,
+ x, None, None, None)
+ self.assertRaisesRegexp(TypeError, r'\bstartswith\b', b.startswith,
+ x, None, None, None)
+ self.assertRaisesRegexp(TypeError, r'\bendswith\b', b.endswith,
+ x, None, None, None)
+
 
 class ByteArrayTest(BaseBytesTest):
 type2test = bytearray
diff --git a/Misc/ACKS b/Misc/ACKS
--- a/Misc/ACKS
+++ b/Misc/ACKS
@@ -60,6 +60,7 @@
 David Beazley
 Robin Becker
 Neal Becker
+Torsten Becker
 Bill Bedford
 Reimer Behrends
 Ben Bell
diff --git a/Misc/NEWS b/Misc/NEWS
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -43,6 +43,9 @@
 rather than the Py_IsInitialized flag, avoiding a Fatal Python
 error in certain circumstances when an import is done in __del__.
 
+- issue #11828: startswith and endswith don't accept None as slice index.
+ Patch by Torsten Becker.
+
 - Issue #10674: Remove unused 'dictmaker' rule from grammar.
 
 - Issue #10596: Fix float.__mod__ to have the same behaviour as
diff --git a/Objects/bytearrayobject.c b/Objects/bytearrayobject.c
--- a/Objects/bytearrayobject.c
+++ b/Objects/bytearrayobject.c
@@ -1149,8 +1149,8 @@
 Py_ssize_t start=0, end=PY_SSIZE_T_MAX;
 Py_ssize_t res;
 
- if (!PyArg_ParseTuple(args, "O|O&O&:find/rfind/index/rindex", &subobj,
- _PyEval_SliceIndex, &start, _PyEval_SliceIndex, &end))
+ if (!stringlib_parse_args_finds("find/rfind/index/rindex",
+ args, &subobj, &start, &end))
 return -2;
 if (_getbuffer(subobj, &subbuf) < 0)
 return -2;
@@ -1200,8 +1200,7 @@
 Py_buffer vsub;
 PyObject *count_obj;
 
- if (!PyArg_ParseTuple(args, "O|O&O&:count", &sub_obj,
- _PyEval_SliceIndex, &start, _PyEval_SliceIndex, &end))
+ if (!stringlib_parse_args_finds("count", args, &sub_obj, &start, &end))
 return NULL;
 
 if (_getbuffer(sub_obj, &vsub) < 0)
@@ -1359,8 +1358,7 @@
 PyObject *subobj;
 int result;
 
- if (!PyArg_ParseTuple(args, "O|O&O&:startswith", &subobj,
- _PyEval_SliceIndex, &start, _PyEval_SliceIndex, &end))
+ if (!stringlib_parse_args_finds("startswith", args, &subobj, &start, &end))
 return NULL;
 if (PyTuple_Check(subobj)) {
 Py_ssize_t i;
@@ -1399,8 +1397,7 @@
 PyObject *subobj;
 int result;
 
- if (!PyArg_ParseTuple(args, "O|O&O&:endswith", &subobj,
- _PyEval_SliceIndex, &start, _PyEval_SliceIndex, &end))
+ if (!stringlib_parse_args_finds("endswith", args, &subobj, &start, &end))
 return NULL;
 if (PyTuple_Check(subobj)) {
 Py_ssize_t i;
diff --git a/Objects/stringlib/find.h b/Objects/stringlib/find.h
--- a/Objects/stringlib/find.h
+++ b/Objects/stringlib/find.h
@@ -93,32 +93,33 @@
 
 #endif /* STRINGLIB_WANT_CONTAINS_OBJ */
 
-#if STRINGLIB_IS_UNICODE
-
 /*
 This function is a helper for the "find" family (find, rfind, index,
-rindex) of unicodeobject.c file, because they all have the same 
-behaviour for the arguments.
+rindex) and for count, startswith and endswith, because they all have
+the same behaviour for the arguments.
 
 It does not touch the variables received until it knows everything 
 is ok.
-
-Note that we receive a pointer to the pointer of the substring object,
-so when we create that object in this function we don't DECREF it,
-because it continues living in the caller functions (those functions, 
-after finishing using the substring, must DECREF it).
 */
 
+#define FORMAT_BUFFER_SIZE 50
+
 Py_LOCAL_INLINE(int)
-_ParseTupleFinds (PyObject *args, PyObject **substring, 
- Py_ssize_t *start, Py_ssize_t *end) {
- PyObject *tmp_substring;
+stringlib_parse_args_finds(const char * function_name, PyObject *args,
+ PyObject **subobj,
+ Py_ssize_t *start, Py_ssize_t *end)
+{
+ PyObject *tmp_subobj;
 Py_ssize_t tmp_start = 0;
 Py_ssize_t tmp_end = PY_SSIZE_T_MAX;
 PyObject *obj_start=Py_None, *obj_end=Py_None;
+ char format[FORMAT_BUFFER_SIZE] = "O|OO:";
+ size_t len = strlen(format);
 
- if (!PyArg_ParseTuple(args, "O|OO:find", &tmp_substring,
- &obj_start, &obj_end))
+ strncpy(format + len, function_name, FORMAT_BUFFER_SIZE - len - 1);
+ format[FORMAT_BUFFER_SIZE - 1] = '0円';
+
+ if (!PyArg_ParseTuple(args, format, &tmp_subobj, &obj_start, &obj_end))
 return 0;
 
 /* To support None in "start" and "end" arguments, meaning
@@ -131,16 +132,44 @@
 if (!_PyEval_SliceIndex(obj_end, &tmp_end))
 return 0;
 
- tmp_substring = PyUnicode_FromObject(tmp_substring);
- if (!tmp_substring)
- return 0;
-
 *start = tmp_start;
 *end = tmp_end;
- *substring = tmp_substring;
+ *subobj = tmp_subobj;
 return 1;
 }
 
+#undef FORMAT_BUFFER_SIZE
+
+#if STRINGLIB_IS_UNICODE
+
+/*
+Wraps stringlib_parse_args_finds() and additionally ensures that the
+first argument is a unicode object.
+
+Note that we receive a pointer to the pointer of the substring object,
+so when we create that object in this function we don't DECREF it,
+because it continues living in the caller functions (those functions, 
+after finishing using the substring, must DECREF it).
+*/
+
+Py_LOCAL_INLINE(int)
+stringlib_parse_args_finds_unicode(const char * function_name, PyObject *args,
+ PyUnicodeObject **substring,
+ Py_ssize_t *start, Py_ssize_t *end)
+{
+ PyObject *tmp_substring;
+
+ if(stringlib_parse_args_finds(function_name, args, &tmp_substring,
+ start, end)) {
+ tmp_substring = PyUnicode_FromObject(tmp_substring);
+ if (!tmp_substring)
+ return 0;
+ *substring = (PyUnicodeObject *)tmp_substring;
+ return 1;
+ }
+ return 0;
+}
+
 #endif /* STRINGLIB_IS_UNICODE */
 
 #endif /* STRINGLIB_FIND_H */
diff --git a/Objects/stringobject.c b/Objects/stringobject.c
--- a/Objects/stringobject.c
+++ b/Objects/stringobject.c
@@ -1693,19 +1693,9 @@
 const char *sub;
 Py_ssize_t sub_len;
 Py_ssize_t start=0, end=PY_SSIZE_T_MAX;
- PyObject *obj_start=Py_None, *obj_end=Py_None;
-
- if (!PyArg_ParseTuple(args, "O|OO:find/rfind/index/rindex", &subobj,
- &obj_start, &obj_end))
- return -2;
- /* To support None in "start" and "end" arguments, meaning
- the same as if they were not passed.
- */
- if (obj_start != Py_None)
- if (!_PyEval_SliceIndex(obj_start, &start))
- return -2;
- if (obj_end != Py_None)
- if (!_PyEval_SliceIndex(obj_end, &end))
+
+ if (!stringlib_parse_args_finds("find/rfind/index/rindex",
+ args, &subobj, &start, &end))
 return -2;
 
 if (PyString_Check(subobj)) {
@@ -2117,8 +2107,7 @@
 Py_ssize_t sub_len;
 Py_ssize_t start = 0, end = PY_SSIZE_T_MAX;
 
- if (!PyArg_ParseTuple(args, "O|O&O&:count", &sub_obj,
- _PyEval_SliceIndex, &start, _PyEval_SliceIndex, &end))
+ if (!stringlib_parse_args_finds("count", args, &sub_obj, &start, &end))
 return NULL;
 
 if (PyString_Check(sub_obj)) {
@@ -2912,8 +2901,7 @@
 PyObject *subobj;
 int result;
 
- if (!PyArg_ParseTuple(args, "O|O&O&:startswith", &subobj,
- _PyEval_SliceIndex, &start, _PyEval_SliceIndex, &end))
+ if (!stringlib_parse_args_finds("startswith", args, &subobj, &start, &end))
 return NULL;
 if (PyTuple_Check(subobj)) {
 Py_ssize_t i;
@@ -2953,8 +2941,7 @@
 PyObject *subobj;
 int result;
 
- if (!PyArg_ParseTuple(args, "O|O&O&:endswith", &subobj,
- _PyEval_SliceIndex, &start, _PyEval_SliceIndex, &end))
+ if (!stringlib_parse_args_finds("endswith", args, &subobj, &start, &end))
 return NULL;
 if (PyTuple_Check(subobj)) {
 Py_ssize_t i;
diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
--- a/Objects/unicodeobject.c
+++ b/Objects/unicodeobject.c
@@ -6308,13 +6308,8 @@
 Py_ssize_t end = PY_SSIZE_T_MAX;
 PyObject *result;
 
- if (!PyArg_ParseTuple(args, "O|O&O&:count", &substring,
- _PyEval_SliceIndex, &start, _PyEval_SliceIndex, &end))
- return NULL;
-
- substring = (PyUnicodeObject *)PyUnicode_FromObject(
- (PyObject *)substring);
- if (substring == NULL)
+ if (!stringlib_parse_args_finds_unicode("count", args, &substring,
+ &start, &end))
 return NULL;
 
 ADJUST_INDICES(start, end, self->length);
@@ -6504,12 +6499,13 @@
 static PyObject *
 unicode_find(PyUnicodeObject *self, PyObject *args)
 {
- PyObject *substring;
+ PyUnicodeObject *substring;
 Py_ssize_t start;
 Py_ssize_t end;
 Py_ssize_t result;
 
- if (!_ParseTupleFinds(args, &substring, &start, &end))
+ if (!stringlib_parse_args_finds_unicode("find", args, &substring,
+ &start, &end))
 return NULL;
 
 result = stringlib_find_slice(
@@ -6570,11 +6566,12 @@
 unicode_index(PyUnicodeObject *self, PyObject *args)
 {
 Py_ssize_t result;
- PyObject *substring;
+ PyUnicodeObject *substring;
 Py_ssize_t start;
 Py_ssize_t end;
 
- if (!_ParseTupleFinds(args, &substring, &start, &end))
+ if (!stringlib_parse_args_finds_unicode("index", args, &substring,
+ &start, &end))
 return NULL;
 
 result = stringlib_find_slice(
@@ -7237,12 +7234,13 @@
 static PyObject *
 unicode_rfind(PyUnicodeObject *self, PyObject *args)
 {
- PyObject *substring;
+ PyUnicodeObject *substring;
 Py_ssize_t start;
 Py_ssize_t end;
 Py_ssize_t result;
 
- if (!_ParseTupleFinds(args, &substring, &start, &end))
+ if (!stringlib_parse_args_finds_unicode("rfind", args, &substring,
+ &start, &end))
 return NULL;
 
 result = stringlib_rfind_slice(
@@ -7264,12 +7262,13 @@
 static PyObject *
 unicode_rindex(PyUnicodeObject *self, PyObject *args)
 {
- PyObject *substring;
+ PyUnicodeObject *substring;
 Py_ssize_t start;
 Py_ssize_t end;
 Py_ssize_t result;
 
- if (!_ParseTupleFinds(args, &substring, &start, &end))
+ if (!stringlib_parse_args_finds_unicode("rindex", args, &substring,
+ &start, &end))
 return NULL;
 
 result = stringlib_rfind_slice(
@@ -7648,8 +7647,7 @@
 Py_ssize_t end = PY_SSIZE_T_MAX;
 int result;
 
- if (!PyArg_ParseTuple(args, "O|O&O&:startswith", &subobj,
- _PyEval_SliceIndex, &start, _PyEval_SliceIndex, &end))
+ if (!stringlib_parse_args_finds("startswith", args, &subobj, &start, &end))
 return NULL;
 if (PyTuple_Check(subobj)) {
 Py_ssize_t i;
@@ -7694,8 +7692,7 @@
 Py_ssize_t end = PY_SSIZE_T_MAX;
 int result;
 
- if (!PyArg_ParseTuple(args, "O|O&O&:endswith", &subobj,
- _PyEval_SliceIndex, &start, _PyEval_SliceIndex, &end))
+ if (!stringlib_parse_args_finds("endswith", args, &subobj, &start, &end))
 return NULL;
 if (PyTuple_Check(subobj)) {
 Py_ssize_t i;
-- 
Repository URL: http://hg.python.org/cpython
