initial commit

.gitignore

@@ -0,0 +1 @@
+/target

CLAUDE.md

@@ -0,0 +1,38 @@
+# Telegram Bot
+
+General-purpose Telegram bot with modular handler architecture.
+
+## Build & Run
+
+```bash
+cargo build --release
+cargo run
+```
+
+## Configuration
+
+Bot token must be placed at: `/var/trust/instagram_link_stripper/telegram_token`
+
+## Architecture
+
+- `src/main.rs` - Entry point, dispatcher setup
+- `src/config.rs` - Token loading from /var/trust/
+- `src/handlers/` - Message handlers (modular, each feature in own file)
+- `src/utils/` - Shared utilities
+
+## Adding New Handlers
+
+1. Create `src/handlers/new_feature.rs`
+2. Export in `src/handlers/mod.rs`
+3. Add handler branch in `handlers::schema()`
+
+## Current Features
+
+### Instagram Link Cleaning (`handlers/instagram.rs`)
+
+Strips tracking parameters from Instagram links:
+- `igsh`, `igshid` - Instagram share tracking
+- `utm_*` - UTM campaign tracking
+- `ref` - Referral tracking
+- `fbclid` - Facebook click ID
+- `si` - Session identifier

Cargo.toml

@@ -0,0 +1,11 @@
+[package]
+name = "instagram_link_stripper"
+version = "0.1.0"
+edition = "2024"
+
+[dependencies]
+teloxide = { version = "0.17", default-features = false, features = ["macros", "rustls", "ctrlc_handler"] }
+tokio = { version = "1", features = ["rt-multi-thread", "macros"] }
+url = "2"
+log = "0.4"
+pretty_env_logger = "0.5"

src/config.rs

@@ -0,0 +1,18 @@
+use std::fs;
+use std::path::Path;
+
+const TOKEN_PATH: &str = "/var/trust/instagram_link_stripper/telegram_token";
+
+pub fn load_token() -> String {
+    let path = Path::new(TOKEN_PATH);
+
+    fs::read_to_string(path)
+        .unwrap_or_else(|e| {
+            panic!(
+                "Failed to read Telegram bot token from {}: {}",
+                TOKEN_PATH, e
+            )
+        })
+        .trim()
+        .to_string()
+}

src/handlers/instagram.rs

@@ -0,0 +1,56 @@
+use teloxide::dispatching::UpdateHandler;
+use teloxide::prelude::*;
+use teloxide::types::ReplyParameters;
+
+use crate::utils::url::strip_tracking_params;
+
+const INSTAGRAM_PATTERN: &str = "instagram.com/";
+
+fn get_message_text(msg: &Message) -> Option<&str> {
+    msg.text().or_else(|| msg.caption())
+}
+
+fn contains_instagram_link(text: &str) -> bool {
+    text.contains(INSTAGRAM_PATTERN)
+}
+
+fn extract_instagram_urls(text: &str) -> Vec<&str> {
+    text.split_whitespace()
+        .filter(|word| word.contains(INSTAGRAM_PATTERN))
+        .collect()
+}
+
+async fn handle_instagram_links(
+    bot: Bot,
+    msg: Message,
+) -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
+    let Some(text) = get_message_text(&msg) else {
+        return Ok(());
+    };
+
+    let urls = extract_instagram_urls(text);
+    let cleaned: Vec<String> = urls
+        .into_iter()
+        .filter_map(strip_tracking_params)
+        .collect();
+
+    if cleaned.is_empty() {
+        return Ok(());
+    }
+
+    let reply_text = cleaned.join("\n");
+
+    bot.send_message(msg.chat.id, reply_text)
+        .reply_parameters(ReplyParameters::new(msg.id))
+        .await?;
+
+    Ok(())
+}
+
+pub fn handler() -> UpdateHandler<Box<dyn std::error::Error + Send + Sync + 'static>> {
+    Update::filter_message()
+        .filter(|msg: Message| {
+            get_message_text(&msg).map_or(false, contains_instagram_link)
+        })
+        .endpoint(handle_instagram_links)
+}

src/handlers/mod.rs

@@ -0,0 +1,8 @@
+pub mod instagram;
+
+use teloxide::dispatching::UpdateHandler;
+use teloxide::prelude::*;
+
+pub fn schema() -> UpdateHandler<Box<dyn std::error::Error + Send + Sync + 'static>> {
+    dptree::entry().branch(instagram::handler())
+}

src/main.rs

@@ -0,0 +1,20 @@
+mod config;
+mod handlers;
+mod utils;
+
+use teloxide::prelude::*;
+
+#[tokio::main]
+async fn main() {
+    pretty_env_logger::init();
+    log::info!("Starting bot...");
+
+    let token = config::load_token();
+    let bot = Bot::new(token);
+
+    Dispatcher::builder(bot, handlers::schema())
+        .enable_ctrlc_handler()
+        .build()
+        .dispatch()
+        .await;
+}

src/utils/mod.rs

@@ -0,0 +1 @@
+pub mod url;

src/utils/url.rs

@@ -0,0 +1,82 @@
+use url::Url;
+
+const TRACKING_PARAMS: &[&str] = &[
+    "igsh",
+    "igshid",
+    "utm_source",
+    "utm_medium",
+    "utm_campaign",
+    "utm_content",
+    "utm_term",
+    "ref",
+    "fbclid",
+    "si",
+];
+
+/// Removes tracking parameters from a URL.
+/// Returns Some(cleaned_url) if parameters were removed, None if URL was already clean.
+pub fn strip_tracking_params(url_str: &str) -> Option<String> {
+    let mut url = Url::parse(url_str).ok()?;
+
+    let original_query = url.query().map(String::from);
+
+    let filtered_params: Vec<(String, String)> = url
+        .query_pairs()
+        .filter(|(key, _)| !TRACKING_PARAMS.contains(&key.as_ref()))
+        .map(|(k, v)| (k.into_owned(), v.into_owned()))
+        .collect();
+
+    if filtered_params.is_empty() {
+        url.set_query(None);
+    } else {
+        url.query_pairs_mut()
+            .clear()
+            .extend_pairs(filtered_params);
+    }
+
+    let new_query = url.query().map(String::from);
+
+    if original_query != new_query {
+        Some(url.to_string())
+    } else {
+        None
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn test_strips_igsh() {
+        let url = "https://www.instagram.com/reel/ABC123/?igsh=xyz789";
+        let cleaned = strip_tracking_params(url).unwrap();
+        assert_eq!(cleaned, "https://www.instagram.com/reel/ABC123/");
+    }
+
+    #[test]
+    fn test_strips_multiple_params() {
+        let url = "https://www.instagram.com/p/ABC/?igsh=xyz&utm_source=share&fbclid=123";
+        let cleaned = strip_tracking_params(url).unwrap();
+        assert_eq!(cleaned, "https://www.instagram.com/p/ABC/");
+    }
+
+    #[test]
+    fn test_preserves_non_tracking_params() {
+        let url = "https://www.instagram.com/p/ABC/?img_index=2&igsh=xyz";
+        let cleaned = strip_tracking_params(url).unwrap();
+        assert_eq!(cleaned, "https://www.instagram.com/p/ABC/?img_index=2");
+    }
+
+    #[test]
+    fn test_returns_none_if_already_clean() {
+        let url = "https://www.instagram.com/reel/ABC123/";
+        assert!(strip_tracking_params(url).is_none());
+    }
+
+    #[test]
+    fn test_returns_none_for_clean_url_with_non_tracking_params() {
+        let url = "https://www.instagram.com/p/ABC/?img_index=2";
+        assert!(strip_tracking_params(url).is_none());
+    }
+}