From 0f5c6610e691c4126e8f6684b1056bfd8711d28c Mon Sep 17 00:00:00 2001
From: Ed Guloien <ed.guloien@gmail.com>
Date: Wed, 13 May 2026 17:48:29 -0400
Subject: [PATCH] made it a little more rust idiomatic

---
 src/main.rs | 57 +++++++++++++++++++++++++----------------------------
 1 file changed, 27 insertions(+), 30 deletions(-)

diff --git a/src/main.rs b/src/main.rs
index f347612..1ec4dc3 100644
--- a/src/main.rs
+++ b/src/main.rs
@@ -37,15 +37,16 @@ pub fn tokenize(input: &str) -> Vec<String> {
 // 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)
+pub fn create_frequency_vec(input: &[String]) -> Vec<(String,usize)> {
+    // perhaps unnecessary copy, but this preserves the original token list
+    let mut sorted = input.to_vec();
+    sorted.sort(); // O(n log n)
 
     let mut counts : Vec<(String, usize)> = Vec::new();
-    for w in input { // O(n)
+    for w in sorted { // O(n)
         match counts.last_mut() {
-            Some((last, count)) if last == w => *count += 1,
-            _ => counts.push((w.to_string(), 1)),
+            Some((last, count)) if last == &w => *count += 1,
+            _ => counts.push((w.clone(), 1)),
         }
     }
     counts.sort_by(|a,b| b.1.cmp(&a.1)); // sort by frequency, O(m log m)
@@ -53,9 +54,7 @@ pub fn create_frequency_vec(input: &mut [String]) -> Vec<(String,usize)> {
 }
 
 pub fn analyze_word_count(input: &[(String,usize)]) -> usize {
-    let mut count = 0;
-    input.iter().for_each(|(_,c)| { count+=c });
-    count
+    input.iter().map(|(_,c)| c).sum()
 }
 
 pub fn analyze_unique_word_count(input: &[(String,usize)]) -> usize {
@@ -64,7 +63,7 @@ pub fn analyze_unique_word_count(input: &[(String,usize)]) -> usize {
 
 pub fn average_word_length(input: &[(String, usize)]) -> f64 {
     if input.is_empty() {
-        return 0 as f64;
+        return 0.0;
     }
     let mut len = 0;
     let mut tokens = 0;
@@ -86,9 +85,7 @@ pub fn top_n_most_used(input: &[(String, usize)], n: usize) -> &[(String, usize)
 
 // todo: option
 pub fn longest_word(input: &[(String, usize)]) -> usize {
-    let mut max = 0;
-    input.iter().for_each(|(w,_)| if w.len() > max { max = w.len() });
-    max
+    input.iter().map(|(w,_)| w.len()).max().unwrap_or(0)
 }
 
 pub fn num_digits(n: usize) -> usize {
@@ -119,7 +116,7 @@ pub fn print_analysis(input: &[(String, usize)]) {
     println!("{:<col1$} {:<col2$} {:<col3$}", "Word", "Count",  "%_of_total");
     println!("{:-<end$}", "");
     for (w, c) in counts {
-        println!("{:<col1$} {:<col2$} {:<col3$.2}%", w, c, (*c as f64/(wc as f64) * 100 as f64));
+        println!("{:<col1$} {:<col2$} {:<col3$.2}%", w, c, (*c as f64/(wc as f64) * 100.0));
     }
 }
 
@@ -130,8 +127,8 @@ fn main() {
 }
 
 pub fn test_print() {
-    let mut tokens = tokenize("Hellow, wod! hello hello hello ok bye then oa more plz");
-    let freq_vec = create_frequency_vec(&mut tokens);
+    let tokens = tokenize("Hellow, wod! hello hello hello ok bye then oa more plz");
+    let freq_vec = create_frequency_vec(&tokens);
     print_analysis(&freq_vec);
 }
 
@@ -140,11 +137,11 @@ pub mod test {
     use super::*;
 
     #[test]
-    pub fn empty() {
-        let mut tokens = tokenize("");
+    fn empty() {
+        let tokens = tokenize("");
         assert_eq!(tokens.len(), 0);
 
-        let freq_vec = create_frequency_vec(&mut tokens);
+        let freq_vec = create_frequency_vec(&tokens);
         assert_eq!(freq_vec.len(), 0);
         
         let wc = analyze_word_count(&freq_vec);
@@ -154,7 +151,7 @@ pub mod test {
         assert_eq!(uwc, 0);
 
         let avg_len = average_word_length(&freq_vec);
-        assert_eq!(avg_len, 0 as f64);
+        assert_eq!(avg_len, 0.0);
 
         let top_n = top_n_most_used(&freq_vec, 4);
         assert_eq!(top_n.len(), 0);
@@ -163,11 +160,11 @@ pub mod test {
     }
 
     #[test]
-    pub fn basic() {
-        let mut tokens = tokenize("Hello, world! hello");
+    fn basic() {
+        let tokens = tokenize("Hello, world! hello");
         assert_eq!(tokens.len(), 3);
 
-        let freq_vec = create_frequency_vec(&mut tokens);
+        let freq_vec = create_frequency_vec(&tokens);
         assert_eq!(freq_vec.len(), 2);
 
         let wc = analyze_word_count(&freq_vec);
@@ -177,7 +174,7 @@ pub mod test {
         assert_eq!(uwc, 2);
 
         let avg_len = average_word_length(&freq_vec);
-        assert_eq!(avg_len, 5 as f64);
+        assert_eq!(avg_len, 5.0);
 
         let top_n = top_n_most_used(&freq_vec, 4);
         assert_eq!(top_n[0].0, "hello");
@@ -186,11 +183,11 @@ pub mod test {
     }
 
     #[test]
-    pub fn unicode_and_ctrl() {
-        let mut tokens = tokenize("Hello\u{0000} world! hello ß");
+    fn unicode_and_ctrl() {
+        let tokens = tokenize("Hello\u{0000} world! hello ß");
         assert_eq!(tokens.len(), 4);
 
-        let freq_vec = create_frequency_vec(&mut tokens);
+        let freq_vec = create_frequency_vec(&tokens);
         assert_eq!(freq_vec.len(), 4);
 
         let wc = analyze_word_count(&freq_vec);
@@ -209,11 +206,11 @@ pub mod test {
     }
 
     #[test]
-    pub fn unicode_2() {
-        let mut tokens = tokenize("café");
+    fn unicode_2() {
+        let tokens = tokenize("café");
         assert_eq!(tokens.len(), 1);
 
-        let freq_vec = create_frequency_vec(&mut tokens);
+        let freq_vec = create_frequency_vec(&tokens);
         assert_eq!(freq_vec.len(), 1);
 
         let wc = analyze_word_count(&freq_vec);