From 0799cb81f79b9d2ceb2cea087da702bc67b4f469 Mon Sep 17 00:00:00 2001
From: Fadi Imani <fadi.imani.etu@univ-lille.fr>
Date: Wed, 3 Apr 2024 16:33:24 +0200
Subject: [PATCH] big project
---
.../Testing/Temporary/LastTest.log | 4 +-
include/compt_frequence.h | 3 +
src/compt_frequence.c | 150 +++++++++---------
tests/ExampleTests.cpp | 30 ++--
4 files changed, 100 insertions(+), 87 deletions(-)
diff --git a/cmake-build-debug/Testing/Temporary/LastTest.log b/cmake-build-debug/Testing/Temporary/LastTest.log
index 43cdcde..9554a11 100644
--- a/cmake-build-debug/Testing/Temporary/LastTest.log
+++ b/cmake-build-debug/Testing/Temporary/LastTest.log
@@ -1,3 +1,3 @@
-Start testing: Apr 03 16:13 Romance Daylight Time
+Start testing: Apr 03 16:22 Romance Daylight Time
----------------------------------------------------------
-End testing: Apr 03 16:13 Romance Daylight Time
+End testing: Apr 03 16:22 Romance Daylight Time
diff --git a/include/compt_frequence.h b/include/compt_frequence.h
index b40ef6f..dbae499 100644
--- a/include/compt_frequence.h
+++ b/include/compt_frequence.h
@@ -1,6 +1,8 @@
#ifndef FREQUENCY_COUNTER_H
#define FREQUENCY_COUNTER_H
+#define MAX_STRING_LENGTH 100
+
// Structure pour représenter un mot avec sa fréquence
typedef struct {
char *word; // the word
@@ -35,6 +37,7 @@ void write_results(const FrequencyCounter *counter, const char *filename);
void filter_stop_words(FrequencyCounter *counter, const char *filename);
int count_words_in_file(const char *filename);
+void concatenate_strings(const char *strings[], int num_strings, char *result);
void read_and_count_ngrams(FrequencyCounter *counter, const char *filename, int ngram_size);
void mode_interactive();
diff --git a/src/compt_frequence.c b/src/compt_frequence.c
index 0190cb1..c3fe9eb 100644
--- a/src/compt_frequence.c
+++ b/src/compt_frequence.c
@@ -282,78 +282,78 @@ void concatenate_strings(const char *strings[], int num_strings, char *result) {
}
}
-void read_and_count_ngrams(FrequencyCounter *counter, const char *filename, int ngram_size) {
-
- int word_count = count_words_in_file(filename);
-
- char *ngram_array[ngram_size];
-
- FILE *file = fopen(filename, "r");
- if (file == NULL) {
- fprintf(stderr, "Erreur : Impossible d'ouvrir le fichier %s.\n", filename);
- exit(EXIT_FAILURE);
- }
-
- if (ngram_size > word_count) {
- printf("Error: n-gram size exceeds word count\n");
- exit(EXIT_FAILURE);
- }
-
- char word[MAX_WORD_LENGTH];
- int word_nb_read_now = 0;
- int word_nb_in_ngram = 0;
- while (fscanf(file, "%s", word) == 1) {
- word_nb_read_now++;
- word_nb_in_ngram++;
-
- // Convertit le mot en minuscules
- for (int i = 0; word[i]; ++i) {
- word[i] = tolower(word[i]);
- }
-
- // Supprime la ponctuation du mot at the beginning
- if (ispunct(word[0])) {
- deleteFirstChar(word);
- }
-
- // Supprime la ponctuation du mot at the end
- int len = strlen(word);
- if (ispunct(word[len - 1])) {
- word[len - 1] = '\0'; // Supprime le dernier caractère (ponctuation)
- }
- len = strlen(word);
- if (ispunct(word[len - 1])) {
- word[len - 1] = '\0'; // Supprime le dernier caractère (ponctuation)
- }
-
- // reset the ngram array
- if (word_nb_in_ngram % word_nb_read_now == 0) {word_nb_in_ngram = 0;}
-
-
- // Vérifie si le mot existe déjà dans le compteur
- int found = 0;
- for (int i = 0; i < counter->count; ++i) {
- if (strcmp(counter->words[i].word, word) == 0) {
- // Si trouvé, incrémente la fréquence
- counter->words[i].frequency++;
- found = 1;
- break;
- }
- }
-
- // Si le mot n'a pas été trouvé, l'ajoute au compteur
- if (!found) {
- counter->count++;
- counter->words = realloc(counter->words, counter->count * sizeof(WordFrequency));
- if (counter->words == NULL) {
- fprintf(stderr, "Erreur d'allocation mémoire.\n");
- exit(EXIT_FAILURE);
- }
- counter->words[counter->count - 1].word = strdup(word);
- counter->words[counter->count - 1].frequency = 1;
- }
-
- }
-
- fclose(file);
-}
\ No newline at end of file
+//void read_and_count_ngrams(FrequencyCounter *counter, const char *filename, int ngram_size) {
+//
+// int word_count = count_words_in_file(filename);
+//
+// char *ngram_array[ngram_size];
+//
+// FILE *file = fopen(filename, "r");
+// if (file == NULL) {
+// fprintf(stderr, "Erreur : Impossible d'ouvrir le fichier %s.\n", filename);
+// exit(EXIT_FAILURE);
+// }
+//
+// if (ngram_size > word_count) {
+// printf("Error: n-gram size exceeds word count\n");
+// exit(EXIT_FAILURE);
+// }
+//
+// char word[MAX_WORD_LENGTH];
+// int word_nb_read_now = 0;
+// int word_nb_in_ngram = 0;
+// while (fscanf(file, "%s", word) == 1) {
+// word_nb_read_now++;
+// word_nb_in_ngram++;
+//
+// // Convertit le mot en minuscules
+// for (int i = 0; word[i]; ++i) {
+// word[i] = tolower(word[i]);
+// }
+//
+// // Supprime la ponctuation du mot at the beginning
+// if (ispunct(word[0])) {
+// deleteFirstChar(word);
+// }
+//
+// // Supprime la ponctuation du mot at the end
+// int len = strlen(word);
+// if (ispunct(word[len - 1])) {
+// word[len - 1] = '\0'; // Supprime le dernier caractère (ponctuation)
+// }
+// len = strlen(word);
+// if (ispunct(word[len - 1])) {
+// word[len - 1] = '\0'; // Supprime le dernier caractère (ponctuation)
+// }
+//
+// // reset the ngram array
+// if (word_nb_in_ngram % word_nb_read_now == 0) {word_nb_in_ngram = 0;}
+//
+//
+// // Vérifie si le mot existe déjà dans le compteur
+// int found = 0;
+// for (int i = 0; i < counter->count; ++i) {
+// if (strcmp(counter->words[i].word, word) == 0) {
+// // Si trouvé, incrémente la fréquence
+// counter->words[i].frequency++;
+// found = 1;
+// break;
+// }
+// }
+//
+// // Si le mot n'a pas été trouvé, l'ajoute au compteur
+// if (!found) {
+// counter->count++;
+// counter->words = realloc(counter->words, counter->count * sizeof(WordFrequency));
+// if (counter->words == NULL) {
+// fprintf(stderr, "Erreur d'allocation mémoire.\n");
+// exit(EXIT_FAILURE);
+// }
+// counter->words[counter->count - 1].word = strdup(word);
+// counter->words[counter->count - 1].frequency = 1;
+// }
+//
+// }
+//
+// fclose(file);
+//}
\ No newline at end of file
diff --git a/tests/ExampleTests.cpp b/tests/ExampleTests.cpp
index d5bc6d0..367e9d5 100644
--- a/tests/ExampleTests.cpp
+++ b/tests/ExampleTests.cpp
@@ -88,18 +88,28 @@ TEST(ExampleTests, test_count_words_in_file) {
EXPECT_EQ(6, count_words_in_file("test.txt"));
}
-TEST(ExampleTests, test_read_and_count_ngrams) {
- FrequencyCounter counter;
- init_frequency_counter(&counter);
- read_and_count_ngrams(&counter, "test.txt", 2);
- EXPECT_EQ(2, counter.count);
- EXPECT_STREQ("hello world", counter.words[0].word);
- EXPECT_EQ(1, counter.words[0].frequency);
- EXPECT_STREQ("world foo", counter.words[1].word);
- EXPECT_EQ(1, counter.words[1].frequency);
- cleanup_frequency_counter(&counter);
+TEST(ExampleTests, test_concatenate_strings) {
+ const char *arr[] = {"This", "is", "an", "array", "of", "strings"};
+ int num_strings = sizeof(arr) / sizeof(arr[0]);
+ char result[MAX_STRING_LENGTH] = "";
+
+ concatenate_strings(arr, num_strings, result);
+ EXPECT_STREQ("This is an array of strings", result);
+ free(result);
}
+//TEST(ExampleTests, test_read_and_count_ngrams) {
+// FrequencyCounter counter;
+// init_frequency_counter(&counter);
+// read_and_count_ngrams(&counter, "test.txt", 2);
+// EXPECT_EQ(2, counter.count);
+// EXPECT_STREQ("hello world", counter.words[0].word);
+// EXPECT_EQ(1, counter.words[0].frequency);
+// EXPECT_STREQ("world foo", counter.words[1].word);
+// EXPECT_EQ(1, counter.words[1].frequency);
+// cleanup_frequency_counter(&counter);
+//}
+
TEST(ExampleTests, test_mode_interactive) {
// this is just to make sure the function does not crash
mode_interactive();
--
GitLab