SWIG interfacing C library to Python (Creating 'iterable' Python data type from C 'sequence' struct)

Question

I have written a Python extension for a C library. I have a data structure that looks like this:

typedef struct _mystruct{
   double * clientdata;
   size_t          


        

Answer 1

The simplest solution to this is to implement __getitem__ and throw an IndexError exception for an invalid index.

I put together an example of this, using %extend and %exception in SWIG to implement __getitem__ and raise an exception respectively:

%module test

%include "exception.i"

%{
#include 
#include "test.h"
static int myErr = 0; // flag to save error state
%}

%exception MyStruct::__getitem__ {
  assert(!myErr);
  $action
  if (myErr) {
    myErr = 0; // clear flag for next time
    // You could also check the value in $result, but it's a PyObject here
    SWIG_exception(SWIG_IndexError, "Index out of bounds");
  }
}

%include "test.h"

%extend MyStruct {
  double __getitem__(size_t i) {
    if (i >= $self->len) {
      myErr = 1;
      return 0;
    }
    return $self->clientdata[i];
  }
}

I tested it by adding to test.h:

static MyStruct *test() {
  static MyStruct inst = {0,0};
  if (!inst.clientdata) {
    inst.len = 10;
    inst.clientdata = malloc(sizeof(double)*inst.len);
    for (size_t i = 0; i < inst.len; ++i) {
      inst.clientdata[i] = i;
    }
  }
  return &inst;
}

And running the following Python:

import test

for i in test.test():
  print i

Which prints:

python run.py
0.0
1.0
2.0
3.0
4.0
5.0
6.0
7.0
8.0
9.0

and then finishes.

---

An alternative approach, using a typemap to map MyStruct onto a PyList directly is possible too:

%module test

%{
#include "test.h"
%}

%typemap(out) (MyStruct *) {
  PyObject *list = PyList_New($1->len);
  for (size_t i = 0; i < $1->len; ++i) {
    PyList_SetItem(list, i, PyFloat_FromDouble($1->clientdata[i]));
  }

  $result = list;
}

%include "test.h"

This will create a PyList with the return value from any function that returns a MyStruct *. I tested this %typemap(out) with the exact same function as the previous method.

You can also write a corresponding %typemap(in) and %typemap(freearg) for the reverse, something like this untested code:

%typemap(in) (MyStruct *) {
  if (!PyList_Check($input)) {
    SWIG_exception(SWIG_TypeError, "Expecting a PyList");
    return NULL;
  }
  MyStruct *tmp = malloc(sizeof(MyStruct));
  tmp->len = PyList_Size($input);
  tmp->clientdata = malloc(sizeof(double) * tmp->len);
  for (size_t i = 0; i < tmp->len; ++i) {
    tmp->clientdata[i] = PyFloat_AsDouble(PyList_GetItem($input, i));
    if (PyErr_Occured()) {
      free(tmp->clientdata);
      free(tmp);
      SWIG_exception(SWIG_TypeError, "Expecting a double");
      return NULL;
    }
  }
  $1 = tmp;
}

%typemap(freearg) (MyStruct *) {
  free($1->clientdata);
  free($1);
}

---

Using an iterator would make more sense for containers like linked lists, but for completeness sake here's how you might go about doing it for MyStruct with __iter__. The key bit is that you get SWIG to wrap another type for you, which provides the __iter__() and next() needed, in this case MyStructIter which is defined and wrapped at the same time using %inline since it's not part of the normal C API:

%module test

%include "exception.i"

%{
#include 
#include "test.h"
static int myErr = 0;
%}

%exception MyStructIter::next {
  assert(!myErr);
  $action
  if (myErr) {
    myErr = 0; // clear flag for next time
    PyErr_SetString(PyExc_StopIteration, "End of iterator");
    return NULL;
  }
}

%inline %{
  struct MyStructIter {
    double *ptr;
    size_t len;
  };
%}

%include "test.h"

%extend MyStructIter {
  struct MyStructIter *__iter__() {
    return $self;
  }

  double next() {
    if ($self->len--) {
      return *$self->ptr++;
    }
    myErr = 1;
    return 0;
  }
}

%extend MyStruct {
  struct MyStructIter __iter__() {
    struct MyStructIter ret = { $self->clientdata, $self->len };
    return ret;
  }
}

The requirements for iteration over containers are such that the container needs to implement __iter__() and return a new iterator, but in addition to next() which returns the next item and increments the iterator the iterator itself must also supply a __iter__() method. This means that either the container or an iterator can be used identically.

MyStructIter needs to keep track of the current state of iteration - where we are and how much we have left. In this example I did that by keeping a pointer to the next item and a counter that we use to tell when we hit the end. You could also have kept track of the sate by keeping a pointer to the MyStruct the iterator is using and a counter for the position within that, something like:

%inline %{
  struct MyStructIter {
    MyStruct *list;
    size_t pos;
  };
%}

%include "test.h"

%extend MyStructIter {
  struct MyStructIter *__iter__() {
    return $self;
  }

  double next() {
    if ($self->pos < $self->list->len) {
      return $self->list->clientdata[$self->pos++];
    }
    myErr = 1;
    return 0;
  }
}

%extend MyStruct {
  struct MyStructIter __iter__() {
    struct MyStructIter ret = { $self, 0 };
    return ret;
  }
}

(In this instance we could actually have just used the container itself as the iterator as an iterator, by supplying an __iter__() that returned a copy of the container and a next() similar to the first type. I didn't do that in my original answer because I thought that would be less clear than have two distinct types - a container and an iterator for that container)