diff options
Diffstat (limited to 'Objects/stringlib/find.h')
-rw-r--r-- | Objects/stringlib/find.h | 149 |
1 files changed, 81 insertions, 68 deletions
diff --git a/Objects/stringlib/find.h b/Objects/stringlib/find.h index fbe99c75ae..ce615dcb8a 100644 --- a/Objects/stringlib/find.h +++ b/Objects/stringlib/find.h @@ -19,7 +19,7 @@ stringlib_find(const STRINGLIB_CHAR* str, Py_ssize_t str_len, if (sub_len == 0) return offset; - pos = fastsearch(str, str_len, sub, sub_len, FAST_SEARCH); + pos = fastsearch(str, str_len, sub, sub_len, -1, FAST_SEARCH); if (pos >= 0) pos += offset; @@ -32,42 +32,43 @@ stringlib_rfind(const STRINGLIB_CHAR* str, Py_ssize_t str_len, const STRINGLIB_CHAR* sub, Py_ssize_t sub_len, Py_ssize_t offset) { - /* XXX - create reversefastsearch helper! */ - if (sub_len == 0) { - if (str_len < 0) - return -1; - return str_len + offset; - } else { - Py_ssize_t j, pos = -1; - for (j = str_len - sub_len; j >= 0; --j) - if (STRINGLIB_CMP(str+j, sub, sub_len) == 0) { - pos = j + offset; - break; - } - return pos; - } + Py_ssize_t pos; + + if (str_len < 0) + return -1; + if (sub_len == 0) + return str_len + offset; + + pos = fastsearch(str, str_len, sub, sub_len, -1, FAST_RSEARCH); + + if (pos >= 0) + pos += offset; + + return pos; } +/* 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) stringlib_find_slice(const STRINGLIB_CHAR* str, Py_ssize_t str_len, const STRINGLIB_CHAR* sub, Py_ssize_t sub_len, Py_ssize_t start, Py_ssize_t end) { - if (start < 0) - start += str_len; - if (start < 0) - start = 0; - if (end > str_len) - end = str_len; - if (end < 0) - end += str_len; - if (end < 0) - end = 0; - - return stringlib_find( - str + start, end - start, - sub, sub_len, start - ); + ADJUST_INDICES(start, end, str_len); + return stringlib_find(str + start, end - start, sub, sub_len, start); } Py_LOCAL_INLINE(Py_ssize_t) @@ -75,21 +76,11 @@ stringlib_rfind_slice(const STRINGLIB_CHAR* str, Py_ssize_t str_len, const STRINGLIB_CHAR* sub, Py_ssize_t sub_len, Py_ssize_t start, Py_ssize_t end) { - if (start < 0) - start += str_len; - if (start < 0) - start = 0; - if (end > str_len) - end = str_len; - if (end < 0) - end += str_len; - if (end < 0) - end = 0; - + ADJUST_INDICES(start, end, str_len); return stringlib_rfind(str + start, end - start, sub, sub_len, start); } -#if defined(STRINGLIB_STR) && !defined(FROM_BYTEARRAY) +#ifdef STRINGLIB_WANT_CONTAINS_OBJ Py_LOCAL_INLINE(int) stringlib_contains_obj(PyObject* str, PyObject* sub) @@ -100,34 +91,35 @@ stringlib_contains_obj(PyObject* str, PyObject* sub) ) != -1; } -#endif /* STRINGLIB_STR */ - -#ifdef FROM_UNICODE +#endif /* STRINGLIB_WANT_CONTAINS_OBJ */ /* 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'; + + if (!PyArg_ParseTuple(args, format, &tmp_subobj, &obj_start, &obj_end)) return 0; /* To support None in "start" and "end" arguments, meaning @@ -140,23 +132,44 @@ _ParseTupleFinds (PyObject *args, PyObject **substring, 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; } -#endif /* FROM_UNICODE */ +#undef FORMAT_BUFFER_SIZE -#endif /* STRINGLIB_FIND_H */ +#if STRINGLIB_IS_UNICODE /* -Local variables: -c-basic-offset: 4 -indent-tabs-mode: nil -End: +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 */ |