PyObject *
PyInt_FromUnicode(Py_UNICODE *s, int length, int base)
{
char buffer[256];
if (length >= sizeof(buffer)) {
PyErr_SetString(PyExc_ValueError,
"int() literal too large to convert");
return NULL;
}
if (PyUnicode_EncodeDecimal(s, length, buffer, NULL))
return NULL;
return PyInt_FromString(buffer, NULL, base);
}
PyObject* PyInt_FromUnicode(Py_UNICODE* s, Py_ssize_t length, int base) noexcept {
PyObject* result;
char* buffer = (char*)PyMem_MALLOC(length + 1);
if (buffer == NULL)
return PyErr_NoMemory();
if (PyUnicode_EncodeDecimal(s, length, buffer, NULL)) {
PyMem_FREE(buffer);
return NULL;
}
result = PyInt_FromString(buffer, NULL, base);
PyMem_FREE(buffer);
return result;
}
static PyObject *
complex_subtype_from_string(PyTypeObject *type, PyObject *v)
{
const char *s;
PyObject *result = NULL;
#ifdef Py_USING_UNICODE
char *s_buffer = NULL;
#endif
Py_ssize_t len;
if (PyString_Check(v)) {
s = PyString_AS_STRING(v);
len = PyString_GET_SIZE(v);
}
#ifdef Py_USING_UNICODE
else if (PyUnicode_Check(v)) {
s_buffer = (char *)PyMem_MALLOC(PyUnicode_GET_SIZE(v)+1);
if (s_buffer == NULL)
return PyErr_NoMemory();
if (PyUnicode_EncodeDecimal(PyUnicode_AS_UNICODE(v),
PyUnicode_GET_SIZE(v),
s_buffer,
NULL))
goto exit;
s = s_buffer;
len = strlen(s);
}
#endif
else {
PyErr_SetString(PyExc_TypeError,
"complex() arg is not a string");
return NULL;
}
result = _Py_string_to_number_with_underscores(s, len, "complex", v, type,
complex_from_string_inner);
exit:
#ifdef Py_USING_UNICODE
if (s_buffer)
PyMem_FREE(s_buffer);
#endif
return result;
}
static PyObject *
complex_subtype_from_string(PyTypeObject *type, PyObject *v)
{
const char *s, *start;
char *end;
double x=0.0, y=0.0, z;
int got_re=0, got_im=0, got_bracket=0, done=0;
int digit_or_dot;
int sw_error=0;
int sign;
char buffer[256]; /* For errors */
#ifdef Py_USING_UNICODE
char s_buffer[256];
#endif
Py_ssize_t len;
if (PyString_Check(v)) {
s = PyString_AS_STRING(v);
len = PyString_GET_SIZE(v);
}
#ifdef Py_USING_UNICODE
else if (PyUnicode_Check(v)) {
if (PyUnicode_GET_SIZE(v) >= (Py_ssize_t)sizeof(s_buffer)) {
PyErr_SetString(PyExc_ValueError,
"complex() literal too large to convert");
return NULL;
}
if (PyUnicode_EncodeDecimal(PyUnicode_AS_UNICODE(v),
PyUnicode_GET_SIZE(v),
s_buffer,
NULL))
return NULL;
s = s_buffer;
len = strlen(s);
}
#endif
else if (PyObject_AsCharBuffer(v, &s, &len)) {
PyErr_SetString(PyExc_TypeError,
"complex() arg is not a string");
return NULL;
}
/* position on first nonblank */
start = s;
while (*s && isspace(Py_CHARMASK(*s)))
s++;
if (s[0] == '\0') {
PyErr_SetString(PyExc_ValueError,
"complex() arg is an empty string");
return NULL;
}
if (s[0] == '(') {
/* Skip over possible bracket from repr(). */
got_bracket = 1;
s++;
while (*s && isspace(Py_CHARMASK(*s)))
s++;
}
z = -1.0;
sign = 1;
do {
switch (*s) {
case '\0':
if (s-start != len) {
PyErr_SetString(
PyExc_ValueError,
"complex() arg contains a null byte");
return NULL;
}
if(!done) sw_error=1;
break;
case ')':
if (!got_bracket || !(got_re || got_im)) {
sw_error=1;
break;
}
got_bracket=0;
done=1;
s++;
while (*s && isspace(Py_CHARMASK(*s)))
s++;
if (*s) sw_error=1;
break;
case '-':
sign = -1;
/* Fallthrough */
case '+':
if (done) sw_error=1;
s++;
if ( *s=='\0'||*s=='+'||*s=='-'||*s==')'||
isspace(Py_CHARMASK(*s)) ) sw_error=1;
break;
case 'J':
case 'j':
if (got_im || done) {
sw_error = 1;
break;
}
if (z<0.0) {
y=sign;
}
else{
y=sign*z;
}
got_im=1;
s++;
if (*s!='+' && *s!='-' )
done=1;
break;
default:
if (isspace(Py_CHARMASK(*s))) {
while (*s && isspace(Py_CHARMASK(*s)))
s++;
if (*s && *s != ')')
sw_error=1;
else
done = 1;
break;
}
digit_or_dot =
(*s=='.' || isdigit(Py_CHARMASK(*s)));
if (done||!digit_or_dot) {
sw_error=1;
break;
}
errno = 0;
PyFPE_START_PROTECT("strtod", return 0)
z = PyOS_ascii_strtod(s, &end) ;
PyFPE_END_PROTECT(z)
if (errno != 0) {
PyOS_snprintf(buffer, sizeof(buffer),
"float() out of range: %.150s", s);
PyErr_SetString(
PyExc_ValueError,
buffer);
return NULL;
}
s=end;
if (*s=='J' || *s=='j') {
break;
}
if (got_re) {
sw_error=1;
break;
}
/* accept a real part */
x=sign*z;
got_re=1;
if (got_im) done=1;
z = -1.0;
sign = 1;
break;
} /* end of switch */
} while (s - start < len && !sw_error);
if (sw_error || got_bracket) {
PyErr_SetString(PyExc_ValueError,
"complex() arg is a malformed string");
return NULL;
}
return complex_subtype_from_doubles(type, x, y);
}
static PyObject *
complex_subtype_from_string(PyTypeObject *type, PyObject *v)
{
const char *s, *start;
char *end;
double x=0.0, y=0.0, z;
int got_bracket=0;
char s_buffer[256];
Py_ssize_t len;
if (PyUnicode_Check(v)) {
if (PyUnicode_GET_SIZE(v) >= (Py_ssize_t)sizeof(s_buffer)) {
PyErr_SetString(PyExc_ValueError,
"complex() literal too large to convert");
return NULL;
}
if (PyUnicode_EncodeDecimal(PyUnicode_AS_UNICODE(v),
PyUnicode_GET_SIZE(v),
s_buffer,
NULL))
return NULL;
s = s_buffer;
len = strlen(s);
}
else if (PyObject_AsCharBuffer(v, &s, &len)) {
PyErr_SetString(PyExc_TypeError,
"complex() arg is not a string");
return NULL;
}
/* position on first nonblank */
start = s;
while (Py_ISSPACE(*s))
s++;
if (*s == '(') {
/* Skip over possible bracket from repr(). */
got_bracket = 1;
s++;
while (Py_ISSPACE(*s))
s++;
}
/* a valid complex string usually takes one of the three forms:
<float> - real part only
<float>j - imaginary part only
<float><signed-float>j - real and imaginary parts
where <float> represents any numeric string that's accepted by the
float constructor (including 'nan', 'inf', 'infinity', etc.), and
<signed-float> is any string of the form <float> whose first
character is '+' or '-'.
For backwards compatibility, the extra forms
<float><sign>j
<sign>j
j
are also accepted, though support for these forms may be removed from
a future version of Python.
*/
/* first look for forms starting with <float> */
z = PyOS_string_to_double(s, &end, NULL);
if (z == -1.0 && PyErr_Occurred()) {
if (PyErr_ExceptionMatches(PyExc_ValueError))
PyErr_Clear();
else
return NULL;
}
if (end != s) {
/* all 4 forms starting with <float> land here */
s = end;
if (*s == '+' || *s == '-') {
/* <float><signed-float>j | <float><sign>j */
x = z;
y = PyOS_string_to_double(s, &end, NULL);
if (y == -1.0 && PyErr_Occurred()) {
if (PyErr_ExceptionMatches(PyExc_ValueError))
PyErr_Clear();
else
return NULL;
}
if (end != s)
/* <float><signed-float>j */
s = end;
else {
/* <float><sign>j */
y = *s == '+' ? 1.0 : -1.0;
s++;
}
if (!(*s == 'j' || *s == 'J'))
goto parse_error;
s++;
}
else if (*s == 'j' || *s == 'J') {
/* <float>j */
s++;
y = z;
}
else
/* <float> */
x = z;
}
else {
/* not starting with <float>; must be <sign>j or j */
if (*s == '+' || *s == '-') {
/* <sign>j */
y = *s == '+' ? 1.0 : -1.0;
s++;
}
else
/* j */
y = 1.0;
if (!(*s == 'j' || *s == 'J'))
goto parse_error;
s++;
}
/* trailing whitespace and closing bracket */
while (Py_ISSPACE(*s))
s++;
if (got_bracket) {
/* if there was an opening parenthesis, then the corresponding
closing parenthesis should be right here */
if (*s != ')')
goto parse_error;
s++;
while (Py_ISSPACE(*s))
s++;
}
/* we should now be at the end of the string */
if (s-start != len)
goto parse_error;
return complex_subtype_from_doubles(type, x, y);
parse_error:
PyErr_SetString(PyExc_ValueError,
"complex() arg is a malformed string");
return NULL;
}
static PyObject *next(PyObject *self)
{
ligolw_Tokenizer *tokenizer = (ligolw_Tokenizer *) self;
PyObject *type;
PyObject *token;
Py_UNICODE *start, *end;
/*
* Identify the start and end of the next token.
*/
do {
type = next_token(tokenizer, &start, &end);
if(!type)
return NULL;
} while(type == Py_None);
/*
* Extract token as desired type.
*/
if(start == NULL) {
/*
* unquoted zero-length string == None
*/
Py_INCREF(Py_None);
token = Py_None;
} else if(type == (PyObject *) &PyFloat_Type) {
char ascii_buffer[end - start + 1];
char *ascii_end;
if(PyUnicode_EncodeDecimal(start, end - start, ascii_buffer, NULL))
return NULL;
token = PyFloat_FromDouble(strtod(ascii_buffer, &ascii_end));
if(ascii_end == ascii_buffer || *ascii_end != 0) {
/*
* strtod() couldn't convert the token, emulate
* float()'s error message
*/
Py_XDECREF(token);
PyErr_Format(PyExc_ValueError, "invalid literal for float(): '%s'", ascii_buffer);
token = NULL;
}
} else if(type == (PyObject *) &PyUnicode_Type) {
token = PyUnicode_FromUnicode(start, end - start);
} else if(type == (PyObject *) &PyString_Type) {
token = PyUnicode_Encode(start, end - start, NULL, NULL);
} else if(type == (PyObject *) &PyInt_Type) {
token = PyInt_FromUnicode(start, end - start, 0);
} else if(type == (PyObject *) &PyLong_Type) {
token = PyLong_FromUnicode(start, end - start, 0);
} else {
token = PyObject_CallFunction(type, "u#", start, end - start);
}
/*
* Done.
*/
return token;
}
