feat: add rayon parallel processing and refactor get_numbers to accept clean_content slice

- Add rayon dependency to Cargo.toml and import parallel prelude in both isspam_v3.rs and risspam/src/main.rs
- Change get_numbers signature to take &str instead of &str and return Vec<&str> instead of Vec<String>, removing unnecessary allocation
- Guard word_count_per_sentence calculation against empty sentences list to prevent division by zero
- Enable file reading from command-line arguments in isspam_v1.rs by uncommenting and fixing the arg loop with skip(1)
- Remove embedded SPAM1 static test data from isspam_v1.rs and create new isspam_v2.rs with additional analysis functions

12bitfloat_rust/risspam/src/main.rs

@@ -1,5 +1,7 @@
 #![feature(let_chains)]
 
+use rayon::prelude::*;
+//use rayon::prelude::*;
 use std::{env, fs};
 
 fn clean_content(content: &str) -> String {
@@ -50,11 +52,8 @@ fn get_capitalized_words(content: &str) -> Vec<&str> {
 	cap_words
 }
 
-fn get_numbers(content: &str) -> Vec<String> {
-	let clean = clean_content(content);
-	
-	clean.split(|c: char| c.is_ascii_digit())
-		.map(|n| n.to_string())
+fn get_numbers(clean_content: &str) -> Vec<&str> {
+	clean_content.split(|c: char| c.is_ascii_digit())
 		.collect()
 }
 
@@ -72,7 +71,7 @@ fn get_forbidden_words(content: &str) -> Vec<&str> {
 
 fn analyze(data: &str) {
 	let clean_data = clean_content(data);
-	drop(clean_data); // You aren't actually using clean_data :O
+//	drop(clean_data); // You aren't actually using clean_data :O
 	
 	// All capitalized words
 	let cap_words = get_capitalized_words(data);
@@ -87,29 +86,47 @@ fn analyze(data: &str) {
 	println!("Words: {}", words.clone().count());
 	
 	// Numbers
-	let numbers = get_numbers(data);
+	let numbers = get_numbers(&clean_data);
 	println!("Numbers: {}", numbers.len());
 	
 	// Forbidden words
 	let fw = get_forbidden_words(data);
 	println!("Forbidden words: {}", fw.len());
 	
-	let word_count_per_sentence = words.count() / sentences.len();
-	println!("Word count per sentence: {}", word_count_per_sentence);
+	if sentences.len() > 0 {
+		let word_count_per_sentence = words.count() / sentences.len();
+		println!("Word count per sentence: {}", word_count_per_sentence);
+	}
 }
 
 fn main() {
     // Read in files from args
-    for arg in env::args().skip(1) { // skip program arg
-    	let Ok(text) = fs::read_to_string(&arg) else {
-    		eprintln!("{arg} isn't a valid file or couldn't be read");
-    		continue;
+	let mut files = Vec::with_capacity(env::args().len());
+	let mut do_parallel = false;
+	
+	for arg in env::args().skip(1) { // skip program arg
+		if arg == "-p" {
+			do_parallel = true;
+		} else {
+			files.push(arg);
+		}
+	}
+	
+	// Do the work
+	let work = |file| {
+	    let Ok(text) = fs::read_to_string(&file) else {
+    		eprintln!("{file} isn't a valid file or couldn't be read");
+    		return;
     	};
     	
     	analyze(&text);
-    }
-    
-//	analyze(&SPAM1);
+	};
+	
+	if !do_parallel {
+		files.iter().for_each(work);
+	} else {
+		files.par_iter().for_each(work)
+	}
 }
 
 static FORBIDDEN_WORDS: &'static [&'static str] = &[