From 567d8f5a960c5fcec36afa6f1281e86961e6353b Mon Sep 17 00:00:00 2001
From: Ed Guloien <ed.guloien@gmail.com>
Date: Tue, 12 May 2026 18:16:04 -0400
Subject: [PATCH] init

---
 .gitignore  |   1 +
 Cargo.lock  |   7 ++++
 Cargo.toml  |   6 ++++
 src/main.rs | 101 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 115 insertions(+)
 create mode 100644 .gitignore
 create mode 100644 Cargo.lock
 create mode 100644 Cargo.toml
 create mode 100644 src/main.rs

diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..ea8c4bf
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1 @@
+/target
diff --git a/Cargo.lock b/Cargo.lock
new file mode 100644
index 0000000..490f027
--- /dev/null
+++ b/Cargo.lock
@@ -0,0 +1,7 @@
+# This file is automatically @generated by Cargo.
+# It is not intended for manual editing.
+version = 4
+
+[[package]]
+name = "word-count"
+version = "0.1.0"
diff --git a/Cargo.toml b/Cargo.toml
new file mode 100644
index 0000000..2d7098a
--- /dev/null
+++ b/Cargo.toml
@@ -0,0 +1,6 @@
+[package]
+name = "word-count"
+version = "0.1.0"
+edition = "2024"
+
+[dependencies]
diff --git a/src/main.rs b/src/main.rs
new file mode 100644
index 0000000..682eed0
--- /dev/null
+++ b/src/main.rs
@@ -0,0 +1,101 @@
+
+// Write some functions to:
+// 1. tokenize a string
+// 2. manually make a map of tokens:their_counts
+// 3. analyze the token structure:
+// 3.a. count the words
+// 3.b. count the unique words
+// 3.c. get the first n most frequently used words
+// 3.d. count the average word length 
+// 4. (pretty) print the info
+
+const PUNC: &str = ",.?:;'~|!@#$%^&*\"";
+
+
+// todo: what about CTRL chars?
+// todo: what about feeding Bytes?
+// todo: return Result for whitespace input
+fn tokenize(input: &str) -> Vec<String> {
+    // filter punctuation
+    let mut s = String::new();
+    for c in input.chars() {
+        if !PUNC.contains(c) {
+            s.push(c.to_lowercase().next().unwrap());
+        }
+    }
+
+    // convert to vec of strings
+    s.split_whitespace().map(|l| l.to_string()).collect()
+}
+
+// todo: can the input type be better?
+fn count_words(input: &[String]) -> Vec<(String,usize)> {
+    let mut counts : Vec<(String, usize)> = Vec::new();
+    for w in input {
+        match counts.iter_mut().find(|(c,_)| c == w) {
+            Some((_, count)) => *count += 1,
+            _ => counts.push((w.to_string(), 1)),
+        }
+    }
+    counts.sort_by(|a,b| b.1.cmp(&a.1));
+    counts
+}
+
+fn analyze_word_count(input: &[(String,usize)]) -> usize {
+    let mut count = 0;
+    input.iter().for_each(|(_,c)| { count+=c });
+    count
+}
+
+fn analyze_unique_word_count(input: &[(String,usize)]) -> usize {
+    input.len()
+}
+
+fn average_word_length(input: &[(String, usize)]) -> usize {
+    let mut len = 0;
+    let mut tokens = 0;
+    input.iter().for_each(|(s,c)| {
+        len += s.len() * c;
+        tokens += c;
+    });
+
+    len/tokens
+}
+
+fn top_n_most_used(input: &[(String, usize)], n: usize) -> &[(String, usize)] {
+    let n = n.min(input.len());
+    &input[..n]
+}
+
+fn print(input: &[(String, usize)]) {
+    let counts = input;
+    let wc = analyze_word_count(&counts);
+
+    // todo: clean this up a bit 
+    println!("Word Count % of total");
+    println!("---------------------");
+    for (w, c) in counts {
+        println!("{} {} {}", w, c, *c as f64/(wc as f64));
+    }
+}
+
+fn main() {
+    let tokens = tokenize("Hello, world! hello");
+    assert_eq!(tokens.len(), 3);
+
+    let counts = count_words(&tokens);
+    let wc = analyze_word_count(&counts);
+    assert_eq!(wc, 3);
+
+    let uwc = analyze_unique_word_count(&counts);
+    assert_eq!(uwc, 2);
+
+    let avg_len = average_word_length(&counts);
+    assert_eq!(avg_len, 5);
+
+    let top_n = top_n_most_used(&counts, 4);
+    assert_eq!(top_n[0].0, "hello");
+
+    print(&counts);
+
+}