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/Cargo.lock

@@ -0,0 +1,7 @@
+# This file is automatically @generated by Cargo.
+# It is not intended for manual editing.
+version = 3
+
+[[package]]
+name = "risspam"
+version = "0.1.0"

12bitfloat_rust/risspam/Cargo.toml

@@ -0,0 +1,6 @@
+[package]
+name = "risspam"
+version = "0.1.0"
+edition = "2021"
+
+[dependencies]

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"
+];
+

12bitfloat_rust/risspam/target/.rustc_info.json

@@ -0,0 +1 @@
+{"rustc_fingerprint":10200614701319076238,"outputs":{"4614504638168534921":{"success":true,"status":"","code":0,"stdout":"rustc 1.85.0-nightly (d10a6823f 2024-11-29)\nbinary: rustc\ncommit-hash: d10a6823f4c3176be7a05a2454e5c33b861cb05f\ncommit-date: 2024-11-29\nhost: x86_64-unknown-linux-gnu\nrelease: 1.85.0-nightly\nLLVM version: 19.1.4\n","stderr":""},"15729799797837862367":{"success":true,"status":"","code":0,"stdout":"___\nlib___.rlib\nlib___.so\nlib___.so\nlib___.a\nlib___.so\n/home/retoor/.rustup/toolchains/nightly-x86_64-unknown-linux-gnu\noff\npacked\nunpacked\n___\ndebug_assertions\nfmt_debug=\"full\"\noverflow_checks\npanic=\"unwind\"\nproc_macro\nrelocation_model=\"pic\"\ntarget_abi=\"\"\ntarget_arch=\"x86_64\"\ntarget_endian=\"little\"\ntarget_env=\"gnu\"\ntarget_family=\"unix\"\ntarget_feature=\"fxsr\"\ntarget_feature=\"sse\"\ntarget_feature=\"sse2\"\ntarget_has_atomic\ntarget_has_atomic=\"16\"\ntarget_has_atomic=\"32\"\ntarget_has_atomic=\"64\"\ntarget_has_atomic=\"8\"\ntarget_has_atomic=\"ptr\"\ntarget_has_atomic_equal_alignment=\"16\"\ntarget_has_atomic_equal_alignment=\"32\"\ntarget_has_atomic_equal_alignment=\"64\"\ntarget_has_atomic_equal_alignment=\"8\"\ntarget_has_atomic_equal_alignment=\"ptr\"\ntarget_has_atomic_load_store\ntarget_has_atomic_load_store=\"16\"\ntarget_has_atomic_load_store=\"32\"\ntarget_has_atomic_load_store=\"64\"\ntarget_has_atomic_load_store=\"8\"\ntarget_has_atomic_load_store=\"ptr\"\ntarget_os=\"linux\"\ntarget_pointer_width=\"64\"\ntarget_thread_local\ntarget_vendor=\"unknown\"\nub_checks\nunix\n","stderr":""}},"successes":{}}

12bitfloat_rust/risspam/target/CACHEDIR.TAG

@@ -0,0 +1,3 @@
+Signature: 8a477f597d28d172789f06886806bc55
+# This file is a cache directory tag created by cargo.
+# For information about cache directory tags see https://bford.info/cachedir/

12bitfloat_rust/risspam/target/release/.fingerprint/risspam-588b7c16f8fda172/bin-risspam

@@ -0,0 +1 @@
+bcbff30c781130f6

12bitfloat_rust/risspam/target/release/.fingerprint/risspam-588b7c16f8fda172/bin-risspam.json

@@ -0,0 +1 @@
+{"rustc":7959095874983568062,"features":"[]","declared_features":"[]","target":10519780086885261595,"profile":18277820415669657429,"path":10602529704205407992,"deps":[],"local":[{"CheckDepInfo":{"dep_info":"release/.fingerprint/risspam-588b7c16f8fda172/dep-bin-risspam","checksum":false}}],"rustflags":[],"metadata":7797948686568424061,"config":2202906307356721367,"compile_kind":0}

12bitfloat_rust/risspam/target/release/.fingerprint/risspam-588b7c16f8fda172/invoked.timestamp

@@ -0,0 +1 @@
+This file has an mtime of when this was started.

12bitfloat_rust/risspam/target/release/.fingerprint/risspam-edd96cae17e7d87c/invoked.timestamp

@@ -0,0 +1 @@
+This file has an mtime of when this was started.

12bitfloat_rust/risspam/target/release/.fingerprint/risspam-edd96cae17e7d87c/output-bin-risspam

@@ -0,0 +1,3 @@
+{"$message_type":"diagnostic","message":"`#![feature]` may not be used on the stable release channel","code":{"code":"E0554","explanation":"Feature attributes are only allowed on the nightly release channel. Stable or\nbeta compilers will not comply.\n\nErroneous code example:\n\n```ignore (depends on release channel)\n#![feature(lang_items)] // error: `#![feature]` may not be used on the\n                        //        stable release channel\n```\n\nIf you need the feature, make sure to use a nightly release of the compiler\n(but be warned that the feature may be removed or altered in the future).\n"},"level":"error","spans":[{"file_name":"src/main.rs","byte_start":0,"byte_end":23,"line_start":1,"line_end":1,"column_start":1,"column_end":24,"is_primary":true,"text":[{"text":"#![feature(let_chains)]","highlight_start":1,"highlight_end":24}],"label":null,"suggested_replacement":null,"suggestion_applicability":null,"expansion":null}],"children":[],"rendered":"\u001b[0m\u001b[1m\u001b[38;5;9merror[E0554]\u001b[0m\u001b[0m\u001b[1m: `#![feature]` may not be used on the stable release channel\u001b[0m\n\u001b[0m \u001b[0m\u001b[0m\u001b[1m\u001b[38;5;12m--> \u001b[0m\u001b[0msrc/main.rs:1:1\u001b[0m\n\u001b[0m  \u001b[0m\u001b[0m\u001b[1m\u001b[38;5;12m|\u001b[0m\n\u001b[0m\u001b[1m\u001b[38;5;12m1\u001b[0m\u001b[0m \u001b[0m\u001b[0m\u001b[1m\u001b[38;5;12m|\u001b[0m\u001b[0m \u001b[0m\u001b[0m#![feature(let_chains)]\u001b[0m\n\u001b[0m  \u001b[0m\u001b[0m\u001b[1m\u001b[38;5;12m|\u001b[0m\u001b[0m \u001b[0m\u001b[0m\u001b[1m\u001b[38;5;9m^^^^^^^^^^^^^^^^^^^^^^^\u001b[0m\n\n"}
+{"$message_type":"diagnostic","message":"aborting due to 1 previous error","code":null,"level":"error","spans":[],"children":[],"rendered":"\u001b[0m\u001b[1m\u001b[38;5;9merror\u001b[0m\u001b[0m\u001b[1m: aborting due to 1 previous error\u001b[0m\n\n"}
+{"$message_type":"diagnostic","message":"For more information about this error, try `rustc --explain E0554`.","code":null,"level":"failure-note","spans":[],"children":[],"rendered":"\u001b[0m\u001b[1mFor more information about this error, try `rustc --explain E0554`.\u001b[0m\n"}

12bitfloat_rust/risspam/target/release/deps/risspam-588b7c16f8fda172.d

@@ -0,0 +1,5 @@
+/home/retoor/projects/spam/rust/risspam/target/release/deps/risspam-588b7c16f8fda172: src/main.rs
+
+/home/retoor/projects/spam/rust/risspam/target/release/deps/risspam-588b7c16f8fda172.d: src/main.rs
+
+src/main.rs:

12bitfloat_rust/risspam/target/release/deps/risspam-edd96cae17e7d87c.d

@@ -0,0 +1,5 @@
+/home/retoor/projects/spam/rust/risspam/target/release/deps/risspam-edd96cae17e7d87c: src/main.rs
+
+/home/retoor/projects/spam/rust/risspam/target/release/deps/risspam-edd96cae17e7d87c.d: src/main.rs
+
+src/main.rs:

12bitfloat_rust/risspam/target/release/risspam.d

@@ -0,0 +1 @@
+/home/retoor/projects/spam/rust/risspam/target/release/risspam: /home/retoor/projects/spam/rust/risspam/src/main.rs