From de950fa11cae498bad25a831121957024e6feb94 Mon Sep 17 00:00:00 2001
From: seb <sebgreenbus@gmail.com>
Date: Fri, 18 Apr 2025 08:52:18 +0200
Subject: [PATCH] Enhance string handling in similarity_search.c with input
 validation and memory management improvements; update test.js to utilize new
 SimilaritySearch class for index creation.

---
 similarity_search.c | 35 +++++++++++++++++++++++++++++------
 test.js             |  5 ++++-
 2 files changed, 33 insertions(+), 7 deletions(-)

diff --git a/similarity_search.c b/similarity_search.c
index 04d035a..00e3fe8 100644
--- a/similarity_search.c
+++ b/similarity_search.c
@@ -21,14 +21,26 @@ int str_case_cmp(const char *s1, const char *s2) {
 
 // Split a string into words
 int split_into_words(const char *string, char *words[MAX_WORDS]) {
+    if (!string || strlen(string) >= MAX_STRING_LEN) {
+        return 0;
+    }
+    
     char temp[MAX_STRING_LEN];
-    strcpy(temp, string);
+    strncpy(temp, string, MAX_STRING_LEN - 1);
+    temp[MAX_STRING_LEN - 1] = '\0';
     
     int word_count = 0;
     char *token = strtok(temp, " \t\n");
     
     while (token != NULL && word_count < MAX_WORDS) {
         words[word_count] = strdup(token);
+        if (!words[word_count]) {
+            // Free any already allocated words on error
+            for (int i = 0; i < word_count; i++) {
+                free(words[i]);
+            }
+            return 0;
+        }
         word_count++;
         token = strtok(NULL, " \t\n");
     }
@@ -99,17 +111,28 @@ void generate_random_word(char *word, int max_len) {
 
 // Generate a random string consisting of multiple words
 void generate_random_string(char *string, int max_len) {
+    if (!string || max_len <= 0) {
+        return;
+    }
+    
     int num_words = 2 + rand() % 5; // Random number of words between 2 and 6
     string[0] = '\0';
+    size_t current_len = 0;
     
     for (int i = 0; i < num_words; i++) {
         char word[20];
-        generate_random_word(word, 10);
+        generate_random_word(word, sizeof(word) - 1);
         
-        // Check if there's enough space to add this word
-        if (strlen(string) + strlen(word) + 1 < (size_t)max_len) {
-            if (i > 0) strcat(string, " ");
-            strcat(string, word);
+        size_t word_len = strlen(word);
+        size_t space_needed = word_len + (i > 0 ? 1 : 0); // +1 for space if not first word
+        
+        if (current_len + space_needed < (size_t)max_len - 1) {
+            if (i > 0) {
+                strncat(string, " ", max_len - current_len - 1);
+                current_len++;
+            }
+            strncat(string, word, max_len - current_len - 1);
+            current_len += word_len;
         } else {
             break;
         }
diff --git a/test.js b/test.js
index 24f33fa..dafd369 100644
--- a/test.js
+++ b/test.js
@@ -2,7 +2,10 @@ const SimilaritySearch = require('./index');
 
 // Create a test index with 500 strings
 console.log('Creating test index with 500 strings...');
-const index = SimilaritySearch.createTestIndex(500);
+const index = new SimilaritySearch();
+index.addString('bio bizz');
+index.addString('lightmix bizz btio substrate');
+index.addString('bizz bio mix light');
 console.log(`Index created with ${index.size()} strings`);
 
 // Test queries to run