From b33cc218827c9f9235dc0f7a3209251c7616dbce Mon Sep 17 00:00:00 2001
From: Ed Guloien <ed.guloien@gmail.com>
Date: Wed, 13 May 2026 17:34:45 -0400
Subject: [PATCH] removed an unnecessary copy

---
 src/main.rs | 35 +++++++++++++++++++----------------
 1 file changed, 19 insertions(+), 16 deletions(-)

diff --git a/src/main.rs b/src/main.rs
index 6beda9d..f347612 100644
--- a/src/main.rs
+++ b/src/main.rs
@@ -15,6 +15,7 @@
 // CTRL chars are preserved in tokens, though whitespace ones will get dropped
 // bytes cannot be fed since they would be &[u8]; str ensures valid UTF-8
 // hypenated words are preserved
+// Since we need to modify the string we have to return a set of new owned Strings
 pub fn tokenize(input: &str) -> Vec<String> {
     let mut s = String::new();
     for c in input.chars() {
@@ -32,16 +33,18 @@ pub fn tokenize(input: &str) -> Vec<String> {
     s.split_whitespace().map(|l| l.to_string()).collect()
 }
 
-// todo: can the input type be better?
 // total runtime complexity worst-case O(n log n)
-pub fn create_frequency_vec(input: &[String]) -> Vec<(String,usize)> {
-    let mut sorted = input.to_vec(); // copy: O(n)
-    sorted.sort(); // O(n log n)
+// Since our tokenize function returns new Strings, there is not much sense in
+// taking &[&str] here since this would require an extra allocation to move the
+// string slices to a new vector. This doesn't copy heap on the way in anyway.
+pub fn create_frequency_vec(input: &mut [String]) -> Vec<(String,usize)> {
+    // save a copy on the way in by allowing mutation of the passed input
+    input.sort(); // O(n log n)
 
     let mut counts : Vec<(String, usize)> = Vec::new();
-    for w in sorted { // O(n)
+    for w in input { // O(n)
         match counts.last_mut() {
-            Some((last, count)) if last == &w => *count += 1,
+            Some((last, count)) if last == w => *count += 1,
             _ => counts.push((w.to_string(), 1)),
         }
     }
@@ -127,8 +130,8 @@ fn main() {
 }
 
 pub fn test_print() {
-    let tokens = tokenize("Hellow, wod! hello hello hello ok bye then oa more plz");
-    let freq_vec = create_frequency_vec(&tokens);
+    let mut tokens = tokenize("Hellow, wod! hello hello hello ok bye then oa more plz");
+    let freq_vec = create_frequency_vec(&mut tokens);
     print_analysis(&freq_vec);
 }
 
@@ -138,10 +141,10 @@ pub mod test {
 
     #[test]
     pub fn empty() {
-        let tokens = tokenize("");
+        let mut tokens = tokenize("");
         assert_eq!(tokens.len(), 0);
 
-        let freq_vec = create_frequency_vec(&tokens);
+        let freq_vec = create_frequency_vec(&mut tokens);
         assert_eq!(freq_vec.len(), 0);
         
         let wc = analyze_word_count(&freq_vec);
@@ -161,10 +164,10 @@ pub mod test {
 
     #[test]
     pub fn basic() {
-        let tokens = tokenize("Hello, world! hello");
+        let mut tokens = tokenize("Hello, world! hello");
         assert_eq!(tokens.len(), 3);
 
-        let freq_vec = create_frequency_vec(&tokens);
+        let freq_vec = create_frequency_vec(&mut tokens);
         assert_eq!(freq_vec.len(), 2);
 
         let wc = analyze_word_count(&freq_vec);
@@ -184,10 +187,10 @@ pub mod test {
 
     #[test]
     pub fn unicode_and_ctrl() {
-        let tokens = tokenize("Hello\u{0000} world! hello ß");
+        let mut tokens = tokenize("Hello\u{0000} world! hello ß");
         assert_eq!(tokens.len(), 4);
 
-        let freq_vec = create_frequency_vec(&tokens);
+        let freq_vec = create_frequency_vec(&mut tokens);
         assert_eq!(freq_vec.len(), 4);
 
         let wc = analyze_word_count(&freq_vec);
@@ -207,10 +210,10 @@ pub mod test {
 
     #[test]
     pub fn unicode_2() {
-        let tokens = tokenize("café");
+        let mut tokens = tokenize("café");
         assert_eq!(tokens.len(), 1);
 
-        let freq_vec = create_frequency_vec(&tokens);
+        let freq_vec = create_frequency_vec(&mut tokens);
         assert_eq!(freq_vec.len(), 1);
 
         let wc = analyze_word_count(&freq_vec);