As part of the edX course, CS50, I'm trying to load all the dictionary information into an array of char pointers. This would give random access and therefore a pretty fast load and unload time. The file compiles fine, but when I execute it, it stops at "MISSPELLED WORDS" and does not proceed.
I think it might be because I am implementing the "check" function wrong. Gdb tells me that all the words were loaded correctly, but it does not progress in searching for the first word.
The executable file "speller" uses two source files: dictionary.c and speller.c. The assignment is to only edit dictionary.c and dictionary.h in order to implement the executable file.
Thanks beforehand.
dictionary.c
#include <stdio.h>
#include <stdlib.h>
#include <ctype.h>
#include <string.h>
#include "dictionary.h"
// storage and file pointer globalization
//open the dictionary file to read from
FILE* supply;
//allocate memory for the array of char pointers.
char** storage;
//initialization of variable for size function
int dictionarysize = 0;
//length of each word and indices
char supplyword[46];
int wordindex = 0;
int storageindex = 0;
//implement a binary search
bool search(int lower, int upper, const char* value)
{
int middle = (upper + lower)/2;
while (lower <= upper)
{
if (storage[middle] == value)
{
return true;
}
else if (storage[middle] < value)
{
lower = middle + 1;
search(lower, upper, value);
}
else if (storage[middle] > value)
{
upper = middle - 1;
search(lower, upper, value);
}
}
return false;
}
/**
* Returns true if word is in dictionary else false.
*/
bool check(const char* word)
{
return search(0, (LISTLENGTH - 1), word);
}
/**
* Loads dictionary into memory. Returns true if successful else false.
*/
bool load(const char* dictionary)
{
//supply is to read the dictionary file. word is to store individual words from file. index is the nth letter being stored
supply = fopen(dictionary, "r");
//allocate memory for the array of char pointers.
storage = malloc(LISTLENGTH * sizeof(char*));
for (int i = 0; i < LISTLENGTH; i++)
{
storage[i] = malloc((LENGTH + 1) * sizeof(char));
}
if (supply == NULL)
{
printf("Wasn't able to open dictionary file.\n");
return false;
}
else if (storage == NULL)
{
printf("Wasn't able to open storage.\n");
return false;
}
for (int i = fgetc(supply); i != EOF; i = fgetc(supply))
{
// allow only alphabetical characters and apostrophes
if (isalpha(i) || (i == '\''))
{
supplyword[wordindex] = i;
wordindex++;
}
else if (isdigit(i))
{
while((i = fgetc(supply)) != EOF && isalpha(i));
wordindex = 0;
}
else
{
supplyword[wordindex] = '\0';
dictionarysize++;
strncpy(storage[storageindex], supplyword, sizeof(supplyword) + 1);
storageindex++;
wordindex = 0;
}
}
return true;
// if success return true
}
/**
* Returns number of words in dictionary if loaded else 0 if not yet loaded.
*/
unsigned int size(void)
{
if (size == NULL)
{
return 0;
}
return dictionarysize;
}
/**
* Unloads dictionary from memory. Returns true if successful else false.
*/
bool unload(void)
{
if (storage == NULL)
{
return false;
}
free(storage);
fclose(supply);
return true;
}
For further reference, I am attaching the two files:
dictionary.h
#ifndef DICTIONARY_H
#define DICTIONARY_H
#include <stdbool.h>
// maximum length for a word
// (e.g., pneumonoultramicroscopicsilicovolcanoconiosis)
#define LENGTH 45
#define LISTLENGTH 143091
/**
* Returns true if word is in dictionary else false.
*/
bool check(const char* word);
/**
* Loads dictionary into memory. Returns true if successful else false.
*/
bool load(const char* dictionary);
/**
* Returns number of words in dictionary if loaded else 0 if not yet loaded.
*/
unsigned int size(void);
/**
* Unloads dictionary from memory. Returns true if successful else false.
*/
bool unload(void);
bool search(int lower, int upper, const char* value);
#endif // DICTIONARY_H
speller.c
#include <ctype.h>
#include <stdio.h>
#include <sys/resource.h>
#include <sys/time.h>
#include "dictionary.h"
#undef calculate
#undef getrusage
// default dictionary
#define DICTIONARY "/home/cs50/pset5/dictionaries/large"
// prototype
double calculate(const struct rusage* b, const struct rusage* a);
int main(int argc, char* argv[])
{
// check for correct number of args
if (argc != 2 && argc != 3)
{
printf("Usage: speller [dictionary] text\n");
return 1;
}
// structs for timing data
struct rusage before, after;
// benchmarks
double time_load = 0.0, time_check = 0.0, time_size = 0.0, time_unload = 0.0;
// determine dictionary to use
char* dictionary = (argc == 3) ? argv[1] : DICTIONARY;
// load dictionary
getrusage(RUSAGE_SELF, &before);
bool loaded = load(dictionary);
getrusage(RUSAGE_SELF, &after);
// abort if dictionary not loaded
if (!loaded)
{
printf("Could not load %s.\n", dictionary);
return 1;
}
// calculate time to load dictionary
time_load = calculate(&before, &after);
// try to open text
char* text = (argc == 3) ? argv[2] : argv[1];
FILE* fp = fopen(text, "r");
if (fp == NULL)
{
printf("Could not open %s.\n", text);
unload();
return 1;
}
// prepare to report misspellings
printf("\nMISSPELLED WORDS\n\n");
// prepare to spell-check
int index = 0, misspellings = 0, words = 0;
char word[LENGTH+1];
// spell-check each word in text
for (int c = fgetc(fp); c != EOF; c = fgetc(fp))
{
// allow only alphabetical characters and apostrophes
if (isalpha(c) || (c == '\'' && index > 0))
{
// append character to word
word[index] = c;
index++;
// ignore alphabetical strings too long to be words
if (index > LENGTH)
{
// consume remainder of alphabetical string
while ((c = fgetc(fp)) != EOF && isalpha(c));
// prepare for new word
index = 0;
}
}
// ignore words with numbers (like MS Word can)
else if (isdigit(c))
{
// consume remainder of alphanumeric string
while ((c = fgetc(fp)) != EOF && isalnum(c));
// prepare for new word
index = 0;
}
// we must have found a whole word
else if (index > 0)
{
// terminate current word
word[index] = '\0';
// update counter
words++;
// check word's spelling
getrusage(RUSAGE_SELF, &before);
bool misspelled = !check(word);
getrusage(RUSAGE_SELF, &after);
// update benchmark
time_check += calculate(&before, &after);
// print word if misspelled
if (misspelled)
{
printf("%s\n", word);
misspellings++;
}
// prepare for next word
index = 0;
}
}
// check whether there was an error
if (ferror(fp))
{
fclose(fp);
printf("Error reading %s.\n", text);
unload();
return 1;
}
// close text
fclose(fp);
// determine dictionary's size
getrusage(RUSAGE_SELF, &before);
unsigned int n = size();
getrusage(RUSAGE_SELF, &after);
// calculate time to determine dictionary's size
time_size = calculate(&before, &after);
// unload dictionary
getrusage(RUSAGE_SELF, &before);
bool unloaded = unload();
getrusage(RUSAGE_SELF, &after);
// abort if dictionary not unloaded
if (!unloaded)
{
printf("Could not unload %s.\n", dictionary);
return 1;
}
// calculate time to unload dictionary
time_unload = calculate(&before, &after);
// report benchmarks
printf("\nWORDS MISSPELLED: %d\n", misspellings);
printf("WORDS IN DICTIONARY: %d\n", n);
printf("WORDS IN TEXT: %d\n", words);
printf("TIME IN load: %.2f\n", time_load);
printf("TIME IN check: %.2f\n", time_check);
printf("TIME IN size: %.2f\n", time_size);
printf("TIME IN unload: %.2f\n", time_unload);
printf("TIME IN TOTAL: %.2f\n\n",
time_load + time_check + time_size + time_unload);
// that's all folks
return 0;
}
/**
* Returns number of seconds between b and a.
*/
double calculate(const struct rusage* b, const struct rusage* a)
{
if (b == NULL || a == NULL)
{
return 0.0;
}
else
{
return ((((a->ru_utime.tv_sec * 1000000 + a->ru_utime.tv_usec) -
(b->ru_utime.tv_sec * 1000000 + b->ru_utime.tv_usec)) +
((a->ru_stime.tv_sec * 1000000 + a->ru_stime.tv_usec) -
(b->ru_stime.tv_sec * 1000000 + b->ru_stime.tv_usec)))
/ 1000000.0);
}
}
