Merge pull request #3 from dreamer-coding/soap_upgrade

dreamer-coding · web-flow · commit a23c1fc3a6bd · 2025-01-26T16:24:14.000-06:00
Soap upgrade
diff --git a/code/logic/fossil/io/soap.h b/code/logic/fossil/io/soap.h
@@ -31,29 +31,93 @@ extern "C" {
 void fossil_soap_sanitize(char *input);
 
 /**
- * Check if a word is a curse word or racist phrase.
- * This function checks whether a given word is considered offensive.
- * It compares the word against a predefined list of offensive words and phrases
- * to determine its offensiveness.
- *
- * @param word The word to be checked for offensiveness.
- * @return     True if the word is offensive, false otherwise.
+ * Check if a word is an offensive word or phrase.
+ * Returns EXIT_FAILURE if the word is considered offensive, EXIT_SUCCESS otherwise.
  */
 int32_t fossil_soap_is_offensive(const char *word);
 
 /**
- * Get the number of offensive words found in a string.
- * This function counts the number of offensive words found in the input string.
- * It scans the entire string and checks each word against a list of offensive words
- * to determine the count of offensive occurrences.
- *
- * @param input The input string to be checked for offensive words.
- * @return      The number of offensive words found.
+ * Check if a word is meme speak.
+ * Returns EXIT_FAILURE if the word is considered meme speak, EXIT_SUCCESS otherwise.
+ */
+int32_t fossil_soap_is_rotbrain(const char *word);
+
+/**
+ * Count offensive words in a string.
+ * Returns the number of offensive words found in the input string.
  */
 int32_t fossil_soap_count_offensive(const char *input);
 
+/**
+ * Count meme speak words in a string.
+ * Returns the number of meme speak words found in the input string.
+ */
+int32_t fossil_soap_count_rotbrain(const char *input);
+
 #ifdef __cplusplus
 }
+
+/**
+ * C++ wrapper for the SOAP API.
+ */
+namespace fossil {
+
+    /**
+     * Namespace for I/O operations.
+     */
+    namespace io {
+        /**
+         * SOAP API for sanitizing strings.
+         */
+        class Soap {
+        public:
+            /**
+             * Sanitize a string by replacing curse words with asterisks.
+             * This function scans the input string for offensive words and replaces them with asterisks,
+             * thereby making the string suitable for use in contexts where offensive language is not allowed.
+             * The input string is modified in place.
+             *
+             * @param input The input string to be sanitized in-place.
+             */
+            static void sanitize(char *input) {
+                fossil_soap_sanitize(input);
+            }
+
+            /**
+             * Check if a word is an offensive word or phrase.
+             * Returns EXIT_FAILURE if the word is considered offensive, EXIT_SUCCESS otherwise.
+             */
+            static int32_t is_offensive(const char *word) {
+                return fossil_soap_is_offensive(word);
+            }
+
+            /**
+             * Check if a word is meme speak.
+             * Returns EXIT_FAILURE if the word is considered meme speak, EXIT_SUCCESS otherwise.
+             */
+            static int32_t is_rotbrain(const char *word) {
+                return fossil_soap_is_rotbrain(word);
+            }
+
+            /**
+             * Count offensive words in a string.
+             * Returns the number of offensive words found in the input string.
+             */
+            static int32_t count_offensive(const char *input) {
+                return fossil_soap_count_offensive(input);
+            }
+
+            /**
+             * Count meme speak words in a string.
+             * Returns the number of meme speak words found in the input string.
+             */
+            static int32_t count_rotbrain(const char *input) {
+                return fossil_soap_count_rotbrain(input);
+            }
+        };
+    }
+}
+
 #endif
 
 #endif /* FOSSIL_IO_FRAMEWORK_H */
diff --git a/code/logic/soap.c b/code/logic/soap.c
@@ -22,7 +22,7 @@
 #include <stdlib.h>
 
 // List of offensive words and phrases (super hard to mainting thisw list as GitHub Copilot doesnt wanna help with this part of the SOAP API)
-static const char *offensive_words[] = {
+static const char *FOSSIL_SOAP_OFFENSIVE[] = {
     "curse1",
     "curse2",
     "racist_phrase1",
@@ -55,7 +55,18 @@ static const char *offensive_words[] = {
     // Support for other languages can be added via PR to this repository
 };
 
-static inline char* _custom_fossil_strdup(const char* str) {
+// garbage words and phrases
+// (slightly easier to maintain since it's just slang from social media spoken from people who need to touch grass)
+static const char *FOSSIL_SOAP_ROTBRAIN[] = {
+    "rizz", "skibidi", "yeet", "sus", "vibe", "lit", "no cap", "bet", "fam", "bruh",
+    "flex", "ghost", "goat", "gucci", "hype", "janky", "lowkey", "mood", "salty", "shade",
+    "slay", "snatched", "stan", "tea", "thirsty", "woke", "yolo", "zaddy", "drip", "fire",
+    "lol", "omg", "brb", "sus"
+
+    // Support for other terms can be added via PR to this repository
+};
+
+static inline char* custom_strdup(const char* str) {
     if (!str) return NULL; // Handle NULL pointer gracefully
 
     size_t len = 0;
@@ -90,7 +101,7 @@ static char *custom_strcasestr(const char *haystack, const char *needle) {
 // Function to replace a substring in a string (case-insensitive)
 static void replace_substring_case_insensitive(char *str, const char *old_substr, const char *new_substr) {
     char *position = custom_strcasestr(str, old_substr);
-    if (position != NULL) {
+    while (position != NULL) {
         size_t old_len = strlen(old_substr);
         size_t new_len = strlen(new_substr);
         size_t tail_len = strlen(position + old_len);
@@ -100,28 +111,33 @@ static void replace_substring_case_insensitive(char *str, const char *old_substr
             memmove(position + new_len, position + old_len, tail_len + 1);
         } else {
             memmove(position + new_len, position + old_len, tail_len + 1);
-            memcpy(position, new_substr, new_len);
         }
+        memcpy(position, new_substr, new_len);
+
+        // Find the next occurrence
+        position = custom_strcasestr(position + new_len, old_substr);
     }
 }
 
 void fossil_soap_sanitize(char *input) {
     if (input == NULL || *input == '\0') return;
 
     // Perform single-threaded sanitization
-    for (size_t i = 0; i < sizeof(offensive_words) / sizeof(offensive_words[0]); ++i) {
-        while (custom_strcasestr(input, offensive_words[i]) != NULL) {
-            replace_substring_case_insensitive(input, offensive_words[i], "***");
-        }
+    for (size_t i = 0; i < sizeof(FOSSIL_SOAP_OFFENSIVE) / sizeof(FOSSIL_SOAP_OFFENSIVE[0]); ++i) {
+        replace_substring_case_insensitive(input, FOSSIL_SOAP_OFFENSIVE[i], "***");
+    }
+
+    for (size_t i = 0; i < sizeof(FOSSIL_SOAP_ROTBRAIN) / sizeof(FOSSIL_SOAP_ROTBRAIN[0]); ++i) {
+        replace_substring_case_insensitive(input, FOSSIL_SOAP_ROTBRAIN[i], "***");
     }
 }
 
 // Function to check if a word is an offensive word or phrase
 int32_t fossil_soap_is_offensive(const char *word) {
     if (word == NULL || *word == '\0') return EXIT_SUCCESS;
 
-    for (size_t i = 0; i < sizeof(offensive_words) / sizeof(offensive_words[0]); ++i) {
-        if (strcasecmp(word, offensive_words[i]) == 0) {
+    for (size_t i = 0; i < sizeof(FOSSIL_SOAP_OFFENSIVE) / sizeof(FOSSIL_SOAP_OFFENSIVE[0]); ++i) {
+        if (strcasecmp(word, FOSSIL_SOAP_OFFENSIVE[i]) == 0) {
             return EXIT_FAILURE;
         }
     }
@@ -133,15 +149,44 @@ int32_t fossil_soap_count_offensive(const char *input) {
     if (input == NULL || *input == '\0') return 0;
 
     int count = 0;
-    char *copy = _custom_fossil_strdup(input);
+    char *copy = custom_strdup(input);
     if (copy == NULL) return EXIT_SUCCESS;
 
-    char *token = strtok(copy, " "); // Tokenize the string by space
+    char *token = strtok(copy, " ,.!?;:"); // Tokenize the string by space and punctuation
     while (token != NULL) {
         if (fossil_soap_is_offensive(token)) {
             count++;
         }
-        token = strtok(NULL, " ");
+        token = strtok(NULL, " ,.!?;:");
+    }
+    free(copy); // Free the memory allocated for the copy
+    return count;
+}
+
+int32_t fossil_soap_is_rotbrain(const char *word) {
+    if (word == NULL || *word == '\0') return EXIT_SUCCESS;
+
+    for (size_t i = 0; i < sizeof(FOSSIL_SOAP_ROTBRAIN) / sizeof(FOSSIL_SOAP_ROTBRAIN[0]); ++i) {
+        if (strcasecmp(word, FOSSIL_SOAP_ROTBRAIN[i]) == 0) {
+            return EXIT_FAILURE;
+        }
+    }
+    return EXIT_SUCCESS;
+}
+
+int32_t fossil_soap_count_rotbrain(const char *input) {
+    if (input == NULL || *input == '\0') return 0;
+
+    int count = 0;
+    char *copy = custom_strdup(input);
+    if (copy == NULL) return EXIT_SUCCESS;
+
+    char *token = strtok(copy, " ,.!?;:"); // Tokenize the string by space and punctuation
+    while (token != NULL) {
+        if (fossil_soap_is_rotbrain(token)) {
+            count++;
+        }
+        token = strtok(NULL, " ,.!?;:");
     }
     free(copy); // Free the memory allocated for the copy
     return count;
diff --git a/code/tests/cases/test_soap.c b/code/tests/cases/test_soap.c
@@ -63,6 +63,94 @@ FOSSIL_TEST_CASE(c_test_soap_count_offensive) {
     ASSUME_ITS_EQUAL_I32(2, fossil_soap_count_offensive(input));
 }
 
+FOSSIL_TEST_CASE(c_test_soap_is_rotbrain) {
+    ASSUME_ITS_TRUE(fossil_soap_is_rotbrain("lol"));
+    ASSUME_ITS_TRUE(fossil_soap_is_rotbrain("brb"));
+    ASSUME_ITS_FALSE(fossil_soap_is_rotbrain("hello"));
+}
+
+FOSSIL_TEST_CASE(c_test_soap_count_rotbrain) {
+    char input[] = "This is a test with lol and brb";
+    ASSUME_ITS_EQUAL_I32(2, fossil_soap_count_rotbrain(input));
+}
+
+FOSSIL_TEST_CASE(c_test_soap_sanitize_multiple_offensive) {
+    char input[] = "curse1 curse2 racist_phrase1 racist_phrase2";
+    char expected[] = "*** *** *** ***";
+
+    fossil_soap_sanitize(input);
+
+    ASSUME_ITS_EQUAL_CSTR(expected, input);
+}
+
+FOSSIL_TEST_CASE(c_test_soap_sanitize_no_offensive) {
+    char input[] = "This is a clean sentence.";
+    char expected[] = "This is a clean sentence.";
+
+    fossil_soap_sanitize(input);
+
+    ASSUME_ITS_EQUAL_CSTR(expected, input);
+}
+
+FOSSIL_TEST_CASE(c_test_soap_is_offensive_case_insensitive) {
+    ASSUME_ITS_TRUE(fossil_soap_is_offensive("CuRsE1"));
+    ASSUME_ITS_TRUE(fossil_soap_is_offensive("RaCiSt_PhrAsE2"));
+    ASSUME_ITS_FALSE(fossil_soap_is_offensive("Non_Offensive_Word"));
+}
+
+FOSSIL_TEST_CASE(c_test_soap_count_offensive_mixed_case) {
+    char input[] = "This is a test with CuRsE1 and RaCiSt_PhrAsE1";
+    ASSUME_ITS_EQUAL_I32(2, fossil_soap_count_offensive(input));
+}
+
+FOSSIL_TEST_CASE(c_test_soap_is_rotbrain_case_insensitive) {
+    ASSUME_ITS_TRUE(fossil_soap_is_rotbrain("LoL"));
+    ASSUME_ITS_TRUE(fossil_soap_is_rotbrain("BrB"));
+    ASSUME_ITS_FALSE(fossil_soap_is_rotbrain("Hello"));
+}
+
+FOSSIL_TEST_CASE(c_test_soap_count_rotbrain_mixed_case) {
+    char input[] = "This is a test with LoL and BrB";
+    ASSUME_ITS_EQUAL_I32(2, fossil_soap_count_rotbrain(input));
+}
+
+FOSSIL_TEST_CASE(c_test_soap_sanitize_synonyms) {
+    char input[] = "This is a test with rizz and sus.";
+    char expected[] = "This is a test with *** and ***.";
+
+    fossil_soap_sanitize(input);
+
+    ASSUME_ITS_EQUAL_CSTR(expected, input);
+}
+
+FOSSIL_TEST_CASE(c_test_soap_sanitize_with_punctuation) {
+    char input[] = "This is a test with curse1, and racist_phrase1!";
+    char expected[] = "This is a test with ***, and ***!";
+
+    fossil_soap_sanitize(input);
+
+    ASSUME_ITS_EQUAL_CSTR(expected, input);
+}
+
+FOSSIL_TEST_CASE(c_test_soap_count_offensive_with_punctuation) {
+    char input[] = "This is a test with curse1, and racist_phrase1!";
+    ASSUME_ITS_EQUAL_I32(2, fossil_soap_count_offensive(input));
+}
+
+FOSSIL_TEST_CASE(c_test_soap_sanitize_rotbrain_with_punctuation) {
+    char input[] = "This is a test with lol, and brb!";
+    char expected[] = "This is a test with ***, and ***!";
+
+    fossil_soap_sanitize(input);
+
+    ASSUME_ITS_EQUAL_CSTR(expected, input);
+}
+
+FOSSIL_TEST_CASE(c_test_soap_count_rotbrain_with_punctuation) {
+    char input[] = "This is a test with lol, and brb!";
+    ASSUME_ITS_EQUAL_I32(2, fossil_soap_count_rotbrain(input));
+}
+
 // * * * * * * * * * * * * * * * * * * * * * * * *
 // * Fossil Logic Test Pool
 // * * * * * * * * * * * * * * * * * * * * * * * *
@@ -71,6 +159,19 @@ FOSSIL_TEST_GROUP(c_soap_tests) {
     FOSSIL_TEST_ADD(c_soap_suite, c_test_soap_sanitize);
     FOSSIL_TEST_ADD(c_soap_suite, c_test_soap_is_offensive);
     FOSSIL_TEST_ADD(c_soap_suite, c_test_soap_count_offensive);
+    FOSSIL_TEST_ADD(c_soap_suite, c_test_soap_is_rotbrain);
+    FOSSIL_TEST_ADD(c_soap_suite, c_test_soap_count_rotbrain);
+    FOSSIL_TEST_ADD(c_soap_suite, c_test_soap_sanitize_multiple_offensive);
+    FOSSIL_TEST_ADD(c_soap_suite, c_test_soap_sanitize_no_offensive);
+    FOSSIL_TEST_ADD(c_soap_suite, c_test_soap_is_offensive_case_insensitive);
+    FOSSIL_TEST_ADD(c_soap_suite, c_test_soap_count_offensive_mixed_case);
+    FOSSIL_TEST_ADD(c_soap_suite, c_test_soap_is_rotbrain_case_insensitive);
+    FOSSIL_TEST_ADD(c_soap_suite, c_test_soap_count_rotbrain_mixed_case);
+    FOSSIL_TEST_ADD(c_soap_suite, c_test_soap_sanitize_synonyms);
+    FOSSIL_TEST_ADD(c_soap_suite, c_test_soap_sanitize_with_punctuation);
+    FOSSIL_TEST_ADD(c_soap_suite, c_test_soap_count_offensive_with_punctuation);
+    FOSSIL_TEST_ADD(c_soap_suite, c_test_soap_sanitize_rotbrain_with_punctuation);
+    FOSSIL_TEST_ADD(c_soap_suite, c_test_soap_count_rotbrain_with_punctuation);
 
     FOSSIL_TEST_REGISTER(c_soap_suite);
 }
diff --git a/code/tests/cases/test_soap.cpp b/code/tests/cases/test_soap.cpp
