MIME type

The aim of this puzzle is to match files with their MIME type by reading their extensions. It involves without naming it a peculiar data structure : dictionaries. Let us see a simple implementation in C, and how to use standards in Java and Python.

C

  1. #include <stdlib.h>
  2. #include <stdio.h>
  3. #include <string.h>
  4.  
  5. // Represents an association between an extension, and its mime type
  6. struct pair { char *ext; char *mime; };
  7.  
  8. // A dictionnary can be implented very simply as a pair array
  9. struct dict {
  10.     int size;
  11.     struct pair *elmts;
  12. };
  13.  
  14. /* Returns the MIME type of label 'ext' in dictionnary 'dict'
  15.    or "UNKNOWN" if there is no matching extension */
  16. char *assoc (struct dict *d, char *ext) {
  17.     for (int i = 0; i < d->size; i++)
  18.         if (strcmp(d->elmts[i].ext, ext) == 0)
  19.             return d->elmts[i].mime;
  20.     return "UNKNOWN";
  21. }
  22.  
  23. // Replaces all uppercase chars of 'str' by the corresponding lowercase chars
  24. void toLower (char *str) {
  25.     for (; *str != '\0'; str++)
  26.         *str = tolower(*str);
  27. }
  28.  
  29. // Returns a pointer on the first char of the extension of 'str' if it has one
  30. // or NULL else
  31. char *getExt (char *str) {
  32.     for (char *ext = str+strlen(str); ext != str; ext--)
  33.         if (*(ext-1) == '.')
  34.             return ext;
  35.     return NULL;
  36. }
  37.  
  38. int main(int argc, char** argv)
  39. {
  40.     int dictSize, nbFiles;
  41.     scanf("%d\n%d\n", &dictSize, &nbFiles);
  42.  
  43.     // Initializes the dictionary extension-MIME type
  44.     struct dict d;
  45.     struct pair *p;
  46.     d.size = dictSize;
  47.     d.elmts = malloc(d.size*sizeof(struct pair));
  48.     for (int i = 0; i < dictSize; i++) {
  49.         p = d.elmts+i;
  50.         p->ext = malloc(11*sizeof(char));
  51.         p->mime = malloc(51*sizeof(char));
  52.         // here using scanf is quite safe because maximal lengths are known
  53.         scanf("%s %s\n", p->ext, p->mime);
  54.         toLower(p->ext);
  55.     }
  56.  
  57.     // processes file 1 by 1, by isolating ext and matching it with a MIME type
  58.     char file[257];
  59.     char *ext;
  60.     for (int i = 0; i < nbFiles; i++) {
  61.         gets(file);
  62.         toLower(file);
  63.         ext = getExt(file);
  64.         printf("%s\n", assoc(&d, ext?ext:""));
  65.     }
  66.  
  67.     for (int i = 0; i < dictSize; i++) {
  68.         p = d.elmts+i;
  69.         free(p->ext);
  70.         free(p->mime);
  71.     }
  72.     free(d.elmts);
  73.  
  74.     return EXIT_SUCCESS;
  75. }
  76.

Java

  1. import java.util.*;
  2.  
  3. class Solution {
  4.     public static void main(String args[]) {
  5.         Scanner in = new Scanner(System.in);
  6.  
  7.         int nbAssociations = in.nextInt();
  8.         int nbFiles = in.nextInt();
  9.         in.nextLine();
  10.         
  11.         // assoc associates to each file extension the corresponding MIME type
  12.         Map assoc = new HashMap();
  13.         for (int i = 0; i < nbAssociations; i++) {
  14.             assoc.put(in.next().toLowerCase(), in.next());
  15.             in.nextLine();
  16.         }
  17.  
  18.         for (int i = 0; i < nbFiles; i++) {
  19.             // isolates the extension, which is the part after the last . 
  20.             String fileName = in.nextLine().toLowerCase();
  21.             int pos = fileName.lastIndexOf('.');
  22.             String extension = (pos == -1) ? "" : fileName.substring(pos+1, fileName.length());
  23.             // prints the corresponding MIME type, or UNKNOWN
  24.             System.out.println((String)(assoc.getOrDefault(extension, "UNKNOWN")));
  25.         }
  26.     }
  27. }
  28.

Python 3

  1. import sys
  2.  
  3. nbAssociations, nbFiles = int(input()), int(input())
  4.  
  5. # assoc associates to each file extension the corresponding MIME type
  6. assoc = {}
  7. for i in range(nbAssociations):
  8.     ext, mime = input().split()
  9.     assoc[ext.lower()] = mime
  10.  
  11. for i in range(nbFiles):
  12.     name = input().lower().split('.') 
  13.     ext = name[-1] if len(name) != 1 else None
  14.     print(assoc[ext] if ext in assoc else "UNKNOWN")
  15.