Python Cookbook

Accessing a Python Sequence Item-by-Item with the Iterator Protocol

Credit: Luther Blissett

Problem

You want to write a Python callable C extension that takes as an argument a Python sequence (or iterator) and accesses it sequentially, requiring no extra storage.

Solution

If you can afford to access the sequence item by item without knowing in advance the number of items it has, and you are running Python 2.2 or better, you can sometimes save memory by using PyObject_GetIter instead of PySequence_Fast:

#include <Python.h>

static PyObject *totalIter(PyObject *self, PyObject *args)
{
    PyObject* seq;
    PyObject* item;
    double result;

    /* get one argument as an iterator */
    if(!PyArg_ParseTuple(args, "O", &seq))
        return 0;
    seq = PyObject_GetIter(seq);
    if(!seq)
        return 0;

    /* process data sequentially */
    result = 0.0;
    while((item=PyIter_Next(seq))) {
        PyObject *fitem;
        fitem = PyNumber_Float(item);
        if(!fitem) {
            Py_DECREF(seq);
            Py_DECREF(item);
            PyErr_SetString(PyExc_TypeError, "all items must be numbers");
            return 0;
        }
        result += PyFloat_AS_DOUBLE(fitem);
        Py_DECREF(fitem);
        Py_DECREF(item);
    }    

    /* clean up and return result */
    Py_DECREF(seq);
    return Py_BuildValue("d", result);
}

static PyMethodDef totitMethods[] = {
    {"totit", totalIter, METH_VARARGS, "Sum a sequence of numbers."},
    {0} /* sentinel */
};

void
inittotit(void)
{
    (void) Py_InitModule("totit", totitMethods);
}

Discussion

PyObject_GetIter is available only in Python 2.2, and it is appropriate only when it’s okay for the rest of your C code to get ...