static PyObject *
Splitter_split(Splitter *self, PyObject *args)
{
PyObject *doc;
char *encoding = "iso-8859-15";
Py_XDECREF(self->list);
self->list = PyList_New(0);
if (! (PyArg_ParseTuple(args,"O|s",&doc, &encoding))) return NULL;
if (PyBytes_Check(doc)) {
if (strlen(encoding) == 0 || !strcmp(encoding,"ascii"))
splitString(self, doc);
else {
PyObject *doc1;
if (! (doc1 = PyUnicode_FromEncodedObject(doc, encoding, "strict"))) {
PyErr_SetString(PyExc_UnicodeError,"unicode conversion failed (maybe wrong encoding parameter)");
return NULL;
}
splitUnicodeString(self, doc1);
Py_XDECREF(doc1);
}
} else if (PyUnicode_Check(doc)) {
PyObject *doc1; // create a *real* copy since we need to modify the string
doc1 = PyUnicode_FromUnicode(NULL, PyUnicode_GET_SIZE(doc));
Py_UNICODE_COPY(PyUnicode_AS_UNICODE(doc1),
PyUnicode_AS_UNICODE(doc),
PyUnicode_GET_SIZE(doc));
splitUnicodeString(self, doc1);
Py_DECREF(doc1);
} else {
PyErr_SetString(PyExc_TypeError, "first argument must be string or unicode");
return NULL;
}
Py_XINCREF(self->list);
return self->list;
}
static PyObject *
newSplitter(PyObject *modinfo, PyObject *args,PyObject *keywds)
{
Splitter *self=NULL;
PyObject *doc=NULL, *unicodedoc=NULL,*synstop=NULL;
char *encoding = "latin1";
int index_numbers = 0;
int max_len=64;
int single_char = 0;
int casefolding=1;
if (! (PyArg_ParseTupleAndKeywords(args,keywds,"O|Osiiii",splitter_args,&doc,&synstop,&encoding,&index_numbers,&single_char,&max_len,&casefolding))) return NULL;
#ifdef DEBUG
puts("got text");
PyObject_Print(doc,stdout,0);
fflush(stdout);
#endif
if (index_numbers<0 || index_numbers>1) {
PyErr_SetString(PyExc_ValueError,"indexnumbers must be 0 or 1");
return NULL;
}
if (casefolding<0 || casefolding>1) {
PyErr_SetString(PyExc_ValueError,"casefolding must be 0 or 1");
return NULL;
}
if (single_char<0 || single_char>1) {
PyErr_SetString(PyExc_ValueError,"singlechar must be 0 or 1");
return NULL;
}
if (max_len<1 || max_len>128) {
PyErr_SetString(PyExc_ValueError,"maxlen must be between 1 and 128");
return NULL;
}
if (PyString_Check(doc)) {
unicodedoc = PyUnicode_FromEncodedObject(doc,encoding,"strict");
if (unicodedoc ==NULL) {
PyErr_SetString(PyExc_UnicodeError, "Problem converting encoded string");
return NULL;
}
} else if( PyUnicode_Check(doc)) {
unicodedoc = doc;
Py_INCREF(unicodedoc);
} else {
PyErr_SetString(PyExc_TypeError, "first argument is neither string nor unicode.");
return NULL;
}
if (! (self = PyObject_NEW(Splitter, &SplitterType))) return NULL;
if (synstop) {
self->synstop = synstop;
Py_INCREF(synstop);
} else self->synstop=NULL;
self->index_numbers = index_numbers;
self->max_len = max_len;
self->allow_single_chars = single_char;
self->casefolding = casefolding;
if ((splitUnicodeString(self,(PyUnicodeObject *)unicodedoc)) < 0)
goto err;
Py_DECREF(unicodedoc);
return (PyObject*)self;
err:
Py_DECREF(self);
Py_DECREF(unicodedoc);
return NULL;
}
