Type-safe generic data structures in plain-old C?

Question

I have done far more C++ programming than \"plain old C\" programming. One thing I sorely miss when programming in plain C is type-safe generic data structures, which are p

Answer 1

I use void pointers (void*) to represent generic data structures defined with structs and typedefs. Below I share my implementation of a lib which I'm working on.

With this kind of implementation, you can think of each new type, defined with typedef, like a pseudo-class. Here, this pseudo-class is the set of the source code (some_type_implementation.c) and its header file (some_type_implementation.h).

In the source code, you have to define the struct that will present the new type. Note the struct in the "node.c" source file. There I made a void pointer to the "info" atribute. This pointer may carry any type of pointer (I think), but the price you have to pay is a type identifier inside the struct (int type), and all the switchs to make the propper handle of each type defined. So, in the node.h" header file, I defined the type "Node" (just to avoid have to type struct node every time), and also I had to define the constants "EMPTY_NODE", "COMPLEX_NODE", and "MATRIX_NODE".

You can perform the compilation, by hand, with "gcc *.c -lm".

main.c Source File

#include <stdio.h>
#include <math.h>

#define PI M_PI

#include "complex.h"
#include "matrix.h"
#include "node.h" 


int main()
{
    //testCpx();
    //testMtx();
    testNode();

    return 0;
}

node.c Source File

#include <stdio.h>
#include <stdlib.h>
#include <math.h>

#include "node.h"
#include "complex.h"
#include "matrix.h"

#define PI M_PI


struct node
{
    int type;

    void* info;
};


Node* newNode(int type,void* info)
{
    Node* newNode = (Node*) malloc(sizeof(Node));

    newNode->type = type;

    if(info != NULL)
    {
        switch(type)
        {
            case COMPLEX_NODE:
                newNode->info = (Complex*) info;
            break;

            case MATRIX_NODE:
                newNode->info = (Matrix*) info;
            break;
        }
    }
    else
        newNode->info = NULL;

    return newNode;
}

int emptyInfoNode(Node* node)
{
    return (node->info == NULL);
}

void printNode(Node* node)
{
    if(emptyInfoNode(node))
    {
        printf("Type:%d\n",node->type);
        printf("Empty info\n");
    }
    else
    {
        switch(node->type)
        {
            case COMPLEX_NODE:
                printCpx(node->info);
            break;

            case MATRIX_NODE:
                printMtx(node->info);
            break;
        }
    }
}

void testNode()
{
    Node *node1,*node2, *node3;
    Complex *Z;
    Matrix *M;

    Z = mkCpx(POLAR,5,3*PI/4);

    M = newMtx(3,4,PI);

    node1 = newNode(COMPLEX_NODE,Z);
    node2 = newNode(MATRIX_NODE,M);
    node3 = newNode(EMPTY_NODE,NULL);



    printNode(node1);
    printNode(node2);
    printNode(node3);
}

node.h Header File

#define EMPTY_NODE   0
#define COMPLEX_NODE 1
#define MATRIX_NODE  2


typedef struct node Node;


Node* newNode(int type,void* info);
int emptyInfoNode(Node* node);
void printNode(Node* node);
void testNode();

matrix.c Source File

#include <stdio.h>
#include <stdlib.h>
#include <math.h>

#include "matrix.h"

struct matrix
{
    // Meta-information about the matrix 
    int rows;
    int cols;

    // The elements of the matrix, in the form of a vector 
    double** MTX;
};

Matrix* newMtx(int rows,int cols,double value)
{
    register int row , col;
    Matrix* M = (Matrix*)malloc(sizeof(Matrix));

    M->rows = rows;
    M->cols = cols;
    M->MTX = (double**) malloc(rows*sizeof(double*));

    for(row = 0; row < rows ; row++)
    {
        M->MTX[row] = (double*) malloc(cols*sizeof(double));

        for(col = 0; col < cols ; col++) 
            M->MTX[row][col] = value;
    }

    return M;
}

Matrix* mkMtx(int rows,int cols,double** MTX)
{   
    Matrix* M;
    if(MTX == NULL)
    {
        M = newMtx(rows,cols,0);
    }
    else
    {
        M = (Matrix*)malloc(sizeof(Matrix));
        M->rows = rows;
        M->cols = cols;
        M->MTX  = MTX;
    }
    return M;
}

double getElemMtx(Matrix* M , int row , int col)
{
    return M->MTX[row][col];
}

void printRowMtx(double* row,int cols)
{
    register int j;
    for(j = 0 ; j < cols ; j++) 
        printf("%g ",row[j]);           
}

void printMtx(Matrix* M)
{
    register int row = 0, col = 0;

    printf("\vSize\n");
    printf("\tRows:%d\n",M->rows);
    printf("\tCols:%d\n",M->cols);
    printf("\n");
    for(; row < M->rows ; row++)
    {
        printRowMtx(M->MTX[row],M->cols);
        printf("\n");
    }

    printf("\n");
}

void testMtx()
{
    Matrix* M = mkMtx(10,10,NULL);
    printMtx(M);
}

matrix.h Header File

typedef struct matrix Matrix;

Matrix* newMtx(int rows,int cols,double value);
Matrix* mkMatrix(int rows,int cols,double** MTX);
void print(Matrix* M);
double getMtx(Matrix* M , int row , int col);
void printRowMtx(double* row,int cols);
void printMtx(Matrix* M);
void testMtx();

complex.c Source File

#include <stdio.h>
#include <stdlib.h>
#include <math.h>

#include "complex.h"

struct complex
{
    int type;

    double a;
    double b;
};

Complex* mkCpx(int type,double a,double b)
{
    /** Doc - {{{
     * This function makes a new Complex number.
     * 
     * @params:
     * |-->type: Is an interger that denotes if the number is in
     * |         the analitic or in the polar form.
     * |         ANALITIC:0
     * |         POLAR   :1
     * |
     * |-->a: Is the real part if type = 0 and is the radius if 
     * |      type = 1
     * |
     * `-->b: Is the imaginary part if type = 0 and is the argument
     *        if type = 1
     * 
     * @return:
     *      Returns the new Complex number initialized with the values 
     *      passed
     *}}} */

    Complex* number = (Complex*)malloc(sizeof(Complex));

    number->type = type;
    number->a    = a;
    number->b    = b;

    return number;
}

void printCpx(Complex* number)
{
    switch(number->type)
    {
        case ANALITIC:
            printf("Re:%g | Im:%g\n",number->a,number->b);
        break;

        case POLAR:
            printf("Radius:%g | Arg:%g\n",number->a,number->b);
        break;
    }
}

void testCpx()
{
    Complex* Z = mkCpx(ANALITIC,3,2);
    printCpx(Z);
}

complex.h Header File

#define ANALITIC 0 
#define POLAR    1 

typedef struct complex Complex;

Complex* mkCpx(int type,double a,double b);
void printCpx(Complex* number);
void testCpx();

I hope I hadn't missed nothing.

Answer 2

Your option 1 is what most old time c programmers would go for, possibly salted with a little of 2 to cut down on the repetitive typing, and just maybe employing a few function pointers for a flavor of polymorphism.

Answer 3

You could check out https://github.com/clehner/ll.c

It's easy to use:

#include <stdio.h>
#include <string.h>
#include "ll.h"

int main()
{
   int *numbers = NULL;
   *( numbers = ll_new(numbers) ) = 100;
   *( numbers = ll_new(numbers) ) = 200;

   printf("num is %d\n", *numbers);
   numbers = ll_next(numbers);
   printf("num is %d\n", *numbers);

   typedef struct _s {
      char *word;
   } s;

   s *string = NULL;
   *( string = ll_new(string) ) = (s) {"a string"};
   *( string = ll_new(string) ) = (s) {"another string"};

   printf("string is %s\n", string->word);
   string = ll_next( string );
   printf("string is %s\n", string->word);

   return 0;
}

Output:

num is 200
num is 100
string is another string
string is a string

Answer 4

Option 1, either using void * or some union based variant is what most C programs use, and it may give you BETTER performance than the C++/macro style of having multiple implementations for different types, as it has less code duplication, and thus less icache pressure and fewer icache misses.