feat: add initial Rust spam detection module with isspam and risspam variants

Implement core spam analysis functions including content cleaning, sentence splitting, capitalized word detection, and forbidden word filtering across three Rust source files with nightly let_chains feature

12bitfloat_rust/risspam/src/main.rs

@@ -0,0 +1,121 @@
+#![feature(let_chains)]
+
+use std::{env, fs};
+
+fn clean_content(content: &str) -> String {
+	let alloed_ichars = "01234567891abcdefghijklmnopqrstuvwxyz \n.,!?";
+	
+	let clean_content = content.chars()
+		.filter(|&c| alloed_ichars.contains(c))
+		.collect::<String>();
+	
+	clean_content
+}
+
+fn get_sentences(content: &str) -> Vec<&str> {
+	let mut sentences = content.split('.')
+		.map(|s| s.trim_start()) // Remove leading whitespace
+		.collect::<Vec<_>>();
+	
+	// Remove last "sentence" if didn't end with a dot
+	if let Some(last) = sentences.last() && !last.ends_with('.') {
+		sentences.pop();
+	}
+	
+	sentences
+}
+
+fn get_words(sentences: &str) -> impl Iterator<Item = &str> + Clone {
+	sentences.split_whitespace()
+}
+
+fn is_fully_capitalized_word(word: &str) -> bool {
+	word.chars()
+		.all(|c| !c.is_ascii_alphanumeric() || c.is_ascii_uppercase())
+}
+
+fn get_capitalized_words(content: &str) -> Vec<&str> {
+	let sentences = get_sentences(content);
+	let mut cap_words = vec![];
+	
+	for sentence in sentences {
+		// Always skip the first word since sentences start with
+		for word in get_words(sentence).skip(1) {
+			if is_fully_capitalized_word(word) {
+				cap_words.push(word);
+			}
+		}
+	}
+	
+	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())
+		.collect()
+}
+
+fn get_forbidden_words(content: &str) -> Vec<&str> {
+	fn check_forbidden(w: &str) -> bool {
+		FORBIDDEN_WORDS.iter()
+			.find(|fw| str::eq_ignore_ascii_case(w, fw))
+			.is_some()
+	}
+	
+	get_words(content)
+		.filter(|w| check_forbidden(w))
+		.collect()
+}
+
+fn analyze(data: &str) {
+	let clean_data = clean_content(data);
+	drop(clean_data); // You aren't actually using clean_data :O
+	
+	// All capitalized words
+	let cap_words = get_capitalized_words(data);
+	println!("All capitalized words: {}", cap_words.len());
+	
+	// All sentences
+	let sentences = get_sentences(data);
+	println!("Sentences: {}", sentences.len());
+	
+	// All words
+	let words = get_words(data);
+	println!("Words: {}", words.clone().count());
+	
+	// Numbers
+	let numbers = get_numbers(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);
+}
+
+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;
+    	};
+    	
+    	analyze(&text);
+    }
+    
+//	analyze(&SPAM1);
+}
+
+static FORBIDDEN_WORDS: &'static [&'static str] = &[
+    "recovery",    "techie",    "http",     "https",   "digital",    "hack",          "::",       "//",    "com",
+    "@",           "crypto",    "bitcoin",  "wallet",  "hacker",     "welcome",       "whatsapp", "email", "cryptocurrency",
+    "stolen",      "freeze",    "quick",    "crucial", "tracing",    "scammers",      "expers",   "hire",  "century",
+    "transaction", "essential", "managing", "contact", "contacting", "understanding", "assets",   "funds"
+];
+