Add new file

wordtable.c

+
+#include <stdio.h>
+#include <string.h>
+#include <ctype.h>
+
+#define MAX_LINE 1024
+#define MAX_WORDS 50000  // Increased limit for unique words
+#define MAX_WORD_LENGTH 100
+
+// Structure to store unique words and their counts
+typedef struct {
+    char word[MAX_WORD_LENGTH];
+    int count;
+} WordCount;
+
+// Function prototypes
+void process_file(const char *filename, const char *output_filename);
+int count_unique_words(char *line, WordCount *word_counts, int *unique_word_count);
+int find_word(WordCount *word_counts, int unique_word_count, const char *word);
+void print_word_counts(WordCount *word_counts, int unique_word_count, FILE *output_file);
+void sort_word_counts(WordCount *word_counts, int unique_word_count);
+void remove_punctuation(char *word);
+void split_and_process_word(char *word, WordCount *word_counts, int *unique_word_count);
+int contains_number(const char *word);
+
+int main() 
+{
+    process_file("raamat1184.txt", "wordtable.txt");
+    return 0;
+}
+
+// Function to process the file and count unique words
+void process_file(const char *filename, const char *output_filename) 
+{
+    FILE *file = fopen(filename, "r");
+    FILE *output_file = fopen(output_filename, "w");
+
+    if (file == NULL) 
+    {
+        printf("Error: Could not open file.\n");
+        return;
+    } 
+
+    if (output_file == NULL) 
+    {
+        printf("Error: Could not open output file.\n");
+        fclose(file);
+        return;
+    }
+
+    char line[MAX_LINE];
+    int unique_word_count = 0;
+    WordCount word_counts[MAX_WORDS] = {0}; // Array to store unique words and their counts
+
+    while (fgets(line, sizeof(line), file)) 
+    {
+        count_unique_words(line, word_counts, &unique_word_count);
+    }
+
+    fclose(file);
+
+    // Sort word counts alphabetically
+    sort_word_counts(word_counts, unique_word_count);
+
+    // Print word counts to output file
+    print_word_counts(word_counts, unique_word_count, output_file);
+
+    fclose(output_file);
+    printf("There are %d different words in this text.\n", unique_word_count);
+    printf("Output written to wordtable.txt\n");
+}
+
+// Function to count unique words in a line
+int count_unique_words(char *line, WordCount *word_counts, int *unique_word_count) 
+{
+    char *word = strtok(line, " \t\n");
+
+    while (word != NULL) 
+    {
+        split_and_process_word(word, word_counts, unique_word_count);
+        word = strtok(NULL, " \t\n");
+    }
+
+    return *unique_word_count;
+}
+
+// Function to find a word in the word_counts array
+int find_word(WordCount *word_counts, int unique_word_count, const char *word) 
+{
+    for (int i = 0; i < unique_word_count; i++) 
+    {
+        if (strcmp(word_counts[i].word, word) == 0) 
+        {
+            return i;
+        }
+    }
+    return -1;
+}
+
+// Function to sort word counts alphabetically
+void sort_word_counts(WordCount *word_counts, int unique_word_count) 
+{
+    for (int i = 0; i < unique_word_count - 1; i++) 
+    {
+        for (int j = i + 1; j < unique_word_count; j++) 
+        {
+            if (strcmp(word_counts[i].word, word_counts[j].word) > 0) 
+            {
+                WordCount temp = word_counts[i];
+                word_counts[i] = word_counts[j];
+                word_counts[j] = temp;
+            }
+        }
+    }
+}
+
+// Function to print word counts
+void print_word_counts(WordCount *word_counts, int unique_word_count, FILE *output_file) 
+{
+    fprintf(output_file, "Word Count Table:\n");
+    fprintf(output_file, "%-20s | %s\n", "Word", "Count");
+    fprintf(output_file, "--------------------|------\n");
+
+    for (int i = 0; i < unique_word_count; i++) 
+    {
+        fprintf(output_file, "%-20s | %d\n", word_counts[i].word, word_counts[i].count);
+    }
+}
+
+// Function to remove punctuation from a word
+void remove_punctuation(char *word) 
+{
+    // Remove punctuation from the beginning of the word, except for apostrophes
+    while (*word && ispunct((unsigned char)*word) && *word != '\'') 
+    {
+        memmove(word, word + 1, strlen(word));
+    }
+
+    // Remove punctuation from the end of the word
+    char *end = word + strlen(word) - 1;
+    while (end >= word && ispunct((unsigned char)*end)) 
+    {
+        *end = '\0';
+        end--;
+    }
+
+    // Remove leading apostrophes
+    while (*word == '\'') 
+    {
+        memmove(word, word + 1, strlen(word));
+    }
+}
+
+// Function to split and process words with hyphens or underscores
+void split_and_process_word(char *word, WordCount *word_counts, int *unique_word_count) 
+{
+    char *subword = strtok(word, "-_");
+    while (subword != NULL) 
+    {
+        remove_punctuation(subword);
+        if (!contains_number(subword)) 
+        {
+            int index = find_word(word_counts, *unique_word_count, subword);
+            if (index == -1) 
+            {
+                // New unique word
+                if (*unique_word_count < MAX_WORDS) 
+                {
+                    strncpy(word_counts[*unique_word_count].word, subword, MAX_WORD_LENGTH - 1);
+                    word_counts[*unique_word_count].word[MAX_WORD_LENGTH - 1] = '\0'; // Ensure null-termination
+                    word_counts[*unique_word_count].count = 1;
+                    (*unique_word_count)++;
+                } 
+                else 
+                {
+                    printf("Error: Exceeded maximum number of unique words.\n");
+                    return;
+                }
+            } 
+            else 
+            {
+                // Existing word
+                word_counts[index].count++;
+            }
+        }
+        subword = strtok(NULL, "-_");
+    }
+}
+
+// Function to check if a word contains a number
+int contains_number(const char *word) 
+{
+    for (int i = 0; word[i] != '\0'; i++) 
+    {
+        if (isdigit((unsigned char)word[i])) 
+        {
+            return 1;
+        }
+    }
+    return 0;
+}