chore: add build, run, benchmark and publish steps to CI workflow and introduce isspam_v4 spam analysis module

12bitfloat_rust/isspam_v4.rs

@@ -0,0 +1,157 @@
+#![feature(let_chains)]
+
+use rayon::prelude::*;
+//use rayon::prelude::*;
+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) -> usize {
+	let sentences = content.split('.')
+		.map(|s| s.trim_start()) // Remove leading whitespace
+		.count();
+	
+//	// 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(content: &str, words: &mut usize, caps: &mut usize, fw: &mut usize) {
+	fn check_forbidden(w: &str) -> bool {
+		FORBIDDEN_WORDS.iter()
+			.find(|fw| str::eq_ignore_ascii_case(w, fw))
+			.is_some()
+	}
+	
+	for word in content.split_whitespace() {
+		*words += 1;
+		
+		if is_fully_capitalized_word(word) {
+			*caps += 1;
+		}
+		if check_forbidden(word) {
+			*fw += 1;
+		}
+	}
+}
+
+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) -> usize {
+//	let sentences = get_sentences(content);
+////	let mut cap_words = vec![];
+//	let mut count = 0;
+//	
+//	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) {
+//				count += 1;
+//			}
+//		}
+//	}
+//	
+//	count
+//}
+
+fn get_numbers(clean_content: &str) -> usize {
+	clean_content.split(|c: char| !c.is_ascii_digit())
+		.count()
+}
+
+//fn get_forbidden_words(content: &str) -> usize {
+//	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 mut words = 0;
+	let mut fw = 0;
+	let mut cap_words = 0;
+	get_words(&clean_data, &mut words, &mut fw, &mut cap_words);
+	
+	println!("All capitalized words: {}", cap_words);
+	
+	// All sentences
+	let sentences = get_sentences(data);
+	println!("Sentences: {}", sentences);
+	
+	// All words
+	println!("Words: {}", words);
+	
+	// Numbers
+	let numbers = get_numbers(&clean_data);
+	println!("Numbers: {}", numbers);
+	
+	// Forbidden words
+	println!("Forbidden words: {}", fw);
+	
+	if sentences > 0 {
+		let word_count_per_sentence = words / sentences;
+		println!("Word count per sentence: {}", word_count_per_sentence);
+	}
+}
+
+fn main() {
+    // Read in files from args
+	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);
+	};
+	
+	if !do_parallel {
+		files.iter().for_each(work);
+	} else {
+		files.par_iter().for_each(work)
+	}
+}
+
+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"
+];
+
+