キーワード出現率チェックツールを自作してみた【ソースコード付き】

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <ctype.h>
#include <mecab.h>

typedef struct WordNode {
    char *word;
        int count;
    double percentage;
        struct WordNode *next;
} WordNode;

const char *EXCLUDE_LIST[] = { 
    ",", "，", ".", "。", "、", "!", "！", "?", "？", ":", "：", ";", "；", "(", ")", "（", "）", 
        "\"", "“", "”", "'", "‘", "’", "-", "ー", "～", "[", "]", "{", "}", "「", "」", "『", "』", "【", "】",
    "と", "が", "に", "の", "は", "を", "で", "や", "から", "まで", "0", "1", "2", "3", "4", "5", "6", "7", "8", "9",
        "０", "１", "２", "３", "４", "５", "６", "７", "８", "９",
    "あ", "い", "う", "え", "お", "か", "き", "く", "け", "こ", "さ", "し", "す", "せ", "そ",
        "た", "ち", "つ", "て", "と", "な", "に", "ぬ", "ね", "の",
    "は", "ひ", "ふ", "へ", "ほ", "ま", "み", "む", "め", "も", "や", "ゆ", "よ", "ら", "り", "る", "れ", "ろ", "わ", "を", "ん",
        "が", "ぎ", "ぐ", "げ", "ご", "ざ", "じ", "ず", "ぜ", "ぞ", "だ", "ぢ", "づ", "で", "ど", "ば", "び", "ぶ", "べ", "ぼ",
    "、", "。", "，", "．", "・", "：", "；", "？", "！", "゛", "゜", "´", "｀", "¨", 
        "＾", " ￣", "＿", "ヽ", "ヾ", "ゝ", "ゞ", "〃", "仝", "々", "〆", "〇", "ー", "―", "‐", "／", 
    "＼", "～", "∥", "｜", "…", "‥", "‘", "’", "“", "”", "（", "）", "〔", "〕", "［", "］", 
        "｛", "｝", "〈", "〉", "《", "》", "「", "」", "『", "』", "【", "】", "＋", "－", "±", "×", 

    "÷", "＝","≠","＜","＞","≦","≧","∞","∴","♂","♀","°","′","″","℃","￥", "/", 

        "＄", "￠", "￡", "％", "＃", "＆", "＊", "＠", "§", "☆", "★", "○", "●", "◎", "◇", 

    "◆", "□", "■", "△", "▲", "▽", "▼", "※", "〒", "→", "←", "↑", "↓", " ", "　", "\n", "\r", NULL 
};

int is_excluded_word(const char *word) {
    if (strlen(word) == 0) return 1;
        for (int i = 0; EXCLUDE_LIST[i] != NULL; i++) {
        if (strcmp(word, EXCLUDE_LIST[i]) == 0) {
            return 1;
            }
    }
    for (int i = 0; word[i] != '\0'; i++) {
            if (isdigit((unsigned char)word[i])) {
                return 1;
        }
        }
        if ((strlen(word) == 1) && ((word[0] >= 0x3040 && word[0] <= 0x309F) || (word[0] >= 0x30A0 && word[0] <= 0x30FF))) {
        return 1;
    }
    return 0;
}

WordNode *add_or_increment_word(WordNode *head, const char *word) {
    if (is_excluded_word(word)) {
            return head;
        }
        WordNode *current = head;
    while (current != NULL) {
            if (strcmp(current->word, word) == 0) {
                current->count++;
            return head;
            }
            current = current->next;
        }
        WordNode *new_node = (WordNode *)malloc(sizeof(WordNode));
    new_node->word = strdup(word);
        new_node->count = 1;
    new_node->percentage = 0.0;
        new_node->next = head;
    return new_node;
}

void free_word_list(WordNode *head) {
    WordNode *current = head;
        while (current != NULL) {
        WordNode *next = current->next;
        free(current->word);
        free(current);
        current = next;
    }
}

int count_specific_word_in_text(const char *text, const char *word) {
    int count = 0;
        const char *temp = text;
    while ((temp = strstr(temp, word)) != NULL) {
            count++;
            temp += strlen(word);
        }
        return count;
}

int compare_words(const void *a, const void *b) {
    WordNode *wordA = *(WordNode **)a;
        WordNode *wordB = *(WordNode **)b;
    return wordB->count - wordA->count;
}

void calculate_percentages(WordNode *head, int total_words) {
    WordNode *current = head;
        while (current != NULL) {
        current->percentage = ((double)current->count / total_words) * 100;
        current = current->next;
    }
}

void print_word_list_to_csv(FILE *csv_file, WordNode **word_array, int word_count, int total_words) {
    fprintf(csv_file, "\xEF\xBB\xBF"); // BOMの追加
        fprintf(csv_file, "Word,Count,Percentage\n");
    for (int i = 0; i < word_count; i++) {
            fprintf(csv_file, "%s,%d,%.2f%%\n", word_array[i]->word, word_array[i]->count, word_array[i]->percentage);
        }
        fprintf(csv_file, "Total Words,%d\n", total_words);
}

void print_specific_words_to_csv(FILE *csv_file, const char **search_words, int search_word_count, const char *buffer, int total_words) {
    for (int i = 0; i < search_word_count; i++) {
            if (search_words[i] != NULL) {
                int specific_word_count = count_specific_word_in_text(buffer, search_words[i]);
            double percentage = ((double)specific_word_count / total_words) * 100;
                fprintf(csv_file, "%s,%d,%.2f%%\n", search_words[i], specific_word_count, percentage);
        }
        }
}

int main(int argc, char **argv) {
    if (argc < 3 || argc > 6) {
            fprintf(stderr, "Usage: %s <input file> <output file> <word1> <word2> <word3>\n", argv[0]);
            return 1;
        }

        const char *input_filename = argv[1];
    const char *output_filename = argv[2];
        const char *search_words[3] = { NULL, NULL, NULL };
    for (int i = 3; i < argc; i++) {
            search_words[i - 3] = argv[i];
        }

        FILE *fp = fopen(input_filename, "r");
    if (fp == NULL) {
            perror("fopen");
            return 1;
        }

        fseek(fp, 0, SEEK_END);
    long length = ftell(fp);
        fseek(fp, 0, SEEK_SET);

    char *buffer = (char *)malloc(length + 1);
        fread(buffer, 1, length, fp);
    buffer[length] = '\0';
        fclose(fp);

    int total_characters = strlen(buffer); // Count total characters

        mecab_t *mecab = mecab_new2("-d /usr/lib/x86_64-linux-gnu/mecab/dic/mecab-ipadic-neologd");
    if (mecab == NULL) {
            fprintf(stderr, "error in mecab_new2\n");
            return 1;
        }

        const mecab_node_t *node = mecab_sparse_tonode(mecab, buffer);
    if (node == NULL) {
            fprintf(stderr, "error in mecab_sparse_tonode\n");
            mecab_destroy(mecab);
            return 1;
        }

        int total_words = 0;
    WordNode *word_list = NULL;

        for (; node; node = node->next) {
        if (node->stat == MECAB_BOS_NODE || node->stat == MECAB_EOS_NODE) {
            continue;
            }
        char surface[1024];
        strncpy(surface, node->surface, node->length);
        surface[node->length] = '\0';
        if (!is_excluded_word(surface)) {
            word_list = add_or_increment_word(word_list, surface);
                total_words++;
        }
    }

    calculate_percentages(word_list, total_words);

        int word_count = 0;
    WordNode *current = word_list;
        while (current != NULL) {
        word_count++;
        current = current->next;
    }

    WordNode **word_array = (WordNode **)malloc(word_count * sizeof(WordNode *));
        current = word_list;
    for (int i = 0; i < word_count; i++) {
            word_array[i] = current;
            current = current->next;
        }

        qsort(word_array, word_count, sizeof(WordNode *), compare_words);

    FILE *csv_file = fopen(output_filename, "w");
        if (csv_file == NULL) {
        perror("fopen");
        return 1;
    }

    print_word_list_to_csv(csv_file, word_array, word_count, total_words);
        print_specific_words_to_csv(csv_file, search_words, 3, buffer, total_words);

    //Output total characters count to the CSV file
        fprintf(csv_file, "Total Characters,%d\n", total_characters);

        fclose(csv_file);
    free(word_array);
        free_word_list(word_list);
    mecab_destroy(mecab);
        free(buffer);
    return 0;
}