Depedency on release CI

.gitea/workflows/release.yaml

@@ -0,0 +1,31 @@
+name: Release
+
+on:
+  push:
+    tags:
+      - 'v*.*.*'
+
+env:
+  RUSTUP_TOOLCHAIN: nightly
+
+jobs:
+  build_release:
+    runs-on: ubuntu-latest
+    needs: build_and_test
+    env:
+      GITEA_TOKEN: ${{ secrets.GITEA_TOKEN }}
+      GITEA_SERVER: ${{ secrets.GITEA_SERVER }}
+    steps:
+      - uses: actions/checkout@v6
+
+      - uses: actions-rust-lang/setup-rust-toolchain@v1
+        with:
+          toolchain: nightly
+
+      - name: Build release
+        run: |
+          cargo build --release
+      - uses: akkuman/gitea-release-action@v1
+        with:
+          files: |-
+            target/release/teachertracker-rs

.gitea/workflows/test.yaml

@@ -0,0 +1,13 @@
+name: Rust
+
+on: [push, pull_request]
+
+jobs:
+  build_and_test:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions-rust-lang/setup-rust-toolchain@v1
+        with:
+          toolchain: nightly
+      - run: cargo test --all-features

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "teachertracker-rs"
-version = "0.1.3"
+version = "0.1.6"
 edition = "2024"
 authors = ["Lukas Wölfer <coding@thasky.one>"]
 description = "A MediaWiki bot that updates score information of teachers"
@@ -12,15 +12,18 @@ categories = ["web-programming", "api-bindings", "automation"]
 
 [dependencies]
 chrono = "0.4.41"
+clap = { version = "4.5.54", features = ["derive"] }
 futures = "0.3.31"
-# mwbot = { git = "https://gitlab.wikimedia.org/repos/mwbot-rs/mwbot.git", rev = "05cbb12188f18e2da710de158d89a9a4f1b42689", default-features = false, features = ["generators", "mwbot_derive"] }
+mwbot = { version = "0.7.1", default-features = false, features = ["generators", "mwbot_derive"] }
-mwbot = { version = "0.7.0", default-features = false, features = ["generators", "mwbot_derive"] }
 rand = "0.9.2"
 reqwest = "0.12.22"
 scraper = "0.24.0"
+sentry = { version = "0.45.0", features = ["tracing"] }
+sentry-tracing = { version = "0.45.0", features = ["backtrace", "logs"] }
 serde = { version = "1.0.219", features = ["derive"] }
 serde_plain = "1.0.2"
 thiserror = "2.0.12"
 tokio = { version = "1.46.1", features = ["rt"] }
 tracing = { version = "0.1.41", default-features = false, features = ["std"] }
 tracing-subscriber = "0.3.19"
+async-trait = "0.1.79"

idea.md

@@ -1 +0,0 @@
-https://dancing.thasky.one/api.php?action=query&format=json&list=querypage&formatversion=2&qppage=Wantedpages

src/dance_info.rs

@@ -24,7 +24,7 @@ pub enum DanceRank {
     Newcomer,
     Novice,
     Intermediate,
-    #[serde(rename = "Advance")]
+    #[serde(rename = "Advance", alias = "Advanced")]
     Advanced,
     #[serde(rename = "All Star", alias = "All-Stars")]
     AllStars,

src/fetching/mod.rs

@@ -0,0 +1,34 @@
+use crate::dance_info::DanceInfo;
+use crate::fetching::types::DanceInfoError;
+
+mod scoringdance;
+mod worldsdc;
+pub mod types;
+
+use async_trait::async_trait;
+use std::sync::Arc;
+
+#[async_trait]
+pub trait WsdcFetcher: Send + Sync {
+    async fn fetch(&self, id: u32) -> Result<DanceInfo, DanceInfoError>;
+}
+
+pub struct WorldsdcFetcher;
+pub struct ScoringDanceFetcher;
+
+#[async_trait]
+impl WsdcFetcher for WorldsdcFetcher {
+    async fn fetch(&self, id: u32) -> Result<DanceInfo, DanceInfoError> {
+        worldsdc::fetch_wsdc_info_wsdc(id).await
+    }
+}
+
+#[async_trait]
+impl WsdcFetcher for ScoringDanceFetcher {
+    async fn fetch(&self, id: u32) -> Result<DanceInfo, DanceInfoError> {
+        scoringdance::fetch_wsdc_info_scoring_dance(id).await
+    }
+}
+
+/// Convenience alias for a shared, dynamic fetcher
+pub type DynWsdcFetcher = Arc<dyn WsdcFetcher>;

src/fetching/scoringdance.rs

@@ -6,7 +6,7 @@ use scraper::{ElementRef, Html, Selector};
 use crate::{
     app_signature,
     dance_info::{CompState, DanceInfo, DanceRank, DanceRole},
-    worldsdc::DanceInfoError,
+    fetching::DanceInfoError,
 };
 #[derive(thiserror::Error, Debug)]
 pub enum ScoringParseError {
@@ -135,14 +135,11 @@ fn parse_stats(
         rank: *rank,
     });
     Ok((primary_role, dominant_comp, non_dominant_comp))
-
-    // dbg!(chapters.collect::<Vec<_>>());
 }
 
 fn extract_tables(html: &str) -> Result<Vec<(String, Vec<Vec<String>>)>, ScoringParseError> {
     let document = Html::parse_document(html);
     let card_selector = Selector::parse("div:has( > div.card-header)").unwrap();
-
     document.select(&card_selector).map(parse_card).collect()
 }
 
@@ -171,11 +168,6 @@ fn parse_info(html: &str) -> Result<DanceInfo, ScoringParseError> {
     })
 }
 
-#[test]
-fn test_parse_table() {
-    dbg!(parse_info(include_str!("../../polina.html")));
-}
-
 pub async fn fetch_wsdc_info_scoring_dance(id: u32) -> Result<DanceInfo, DanceInfoError> {
     let client = ClientBuilder::new()
         .user_agent(app_signature())
@@ -194,3 +186,16 @@ pub async fn fetch_wsdc_info_scoring_dance(id: u32) -> Result<DanceInfo, DanceIn
 
     parse_info(response.text().await.unwrap().as_str()).map_err(DanceInfoError::HtmlParse)
 }
+
+#[cfg(test)]
+mod tests {
+    #![allow(clippy::unwrap_used)]
+    use super::*;
+
+    #[test]
+    fn test_parse_table() {
+        let info = parse_info(include_str!("../../test_data/2025-10-02_polina.html")).unwrap();
+        assert_eq!(info.firstname, "Polina");
+        assert_eq!(info.lastname, "Gorushkina");
+    }
+}

src/fetching/types.rs

@@ -0,0 +1,13 @@
+#[derive(thiserror::Error, Debug)]
+pub enum DanceInfoError {
+    #[error("Failed to build client: {0}")]
+    ClientBuild(reqwest::Error),
+    #[error("Failed to build request: {0}")]
+    RequestBuild(reqwest::Error),
+    #[error("Request error: {0:#?}")]
+    Request(reqwest::Error),
+    #[error("Failed to parse response: {0}")]
+    JsonParse(reqwest::Error),
+    #[error("Failed to parse html: {0}")]
+    HtmlParse(#[from] super::scoringdance::ScoringParseError),
+}

src/fetching/worldsdc.rs

@@ -3,10 +3,9 @@ use std::collections::HashMap;
 use crate::{
     app_signature,
     dance_info::{CompState, DanceInfo, DanceRank, DanceRole},
-    worldsdc::scoringdance::fetch_wsdc_info_scoring_dance,
+    fetching::DanceInfoError,
 };
 use reqwest::ClientBuilder;
-mod scoringdance;
 
 pub async fn fetch_wsdc_info_wsdc(id: u32) -> Result<DanceInfo, DanceInfoError> {
     let client = ClientBuilder::new()
@@ -17,7 +16,6 @@ pub async fn fetch_wsdc_info_wsdc(id: u32) -> Result<DanceInfo, DanceInfoError>
     let mut params = HashMap::new();
 
     let url = if cfg!(test) {
-        // "https://o5grQU3Y.free.beeceptor.com/lookup2020/find"
         "http://localhost:8000"
     } else {
         "https://points.worldsdc.com/lookup2020/find"
@@ -37,14 +35,11 @@ pub async fn fetch_wsdc_info_wsdc(id: u32) -> Result<DanceInfo, DanceInfoError>
     Ok(x.into())
 }
 
-pub async fn fetch_wsdc_info(id: u32) -> Result<DanceInfo, DanceInfoError> {
-    fetch_wsdc_info_scoring_dance(id).await
-}
-
 #[cfg(test)]
 mod tests {
     #![allow(clippy::unwrap_used, reason = "Allow unwrap in tests")]
-    use crate::worldsdc::fetch_wsdc_info;
+
+    use super::fetch_wsdc_info_wsdc;
 
     #[test]
     #[ignore = "Only run when the mock api is setup"]
@@ -59,28 +54,14 @@ mod tests {
                 return;
             }
         };
-        let x = rt.block_on(fetch_wsdc_info(7));
+        let x = rt.block_on(fetch_wsdc_info_wsdc(7));
         dbg!(&x);
         x.unwrap();
     }
 }
 
-#[derive(thiserror::Error, Debug)]
-pub enum DanceInfoError {
-    #[error("Failed to build client: {0}")]
-    ClientBuild(reqwest::Error),
-    #[error("Failed to build request: {0}")]
-    RequestBuild(reqwest::Error),
-    #[error("Request error: {0}")]
-    Request(reqwest::Error),
-    #[error("Failed to parse response: {0}")]
-    JsonParse(reqwest::Error),
-    #[error("Failed to parse html: {0}")]
-    HtmlParse(#[from] scoringdance::ScoringParseError),
-}
-
 #[derive(serde::Deserialize, Debug)]
-enum OptionalDanceRank {
+pub enum OptionalDanceRank {
     #[serde(rename = "N/A")]
     NotAvailable,
     #[serde(untagged)]
@@ -88,7 +69,7 @@ enum OptionalDanceRank {
 }
 
 #[derive(serde::Deserialize, Debug)]
-enum OptionalDancePoints {
+pub enum OptionalDancePoints {
     #[serde(rename = "N/A")]
     NotAvailable,
     #[serde(untagged)]
@@ -96,7 +77,7 @@ enum OptionalDancePoints {
 }
 
 #[derive(serde::Deserialize, Debug)]
-struct DanceInfoParser {
+pub struct DanceInfoParser {
     pub dancer_first: String,
     pub dancer_last: String,
     pub short_dominate_role: DanceRole,

src/main.rs

@@ -16,7 +16,6 @@
     clippy::cast_possible_wrap,
     reason = "Disable this for most of the time, enable this for cleanup later"
 )]
-#![feature(hash_map_macro)]
 #![feature(never_type)]
 
 use mwbot::{
@@ -24,15 +23,18 @@ use mwbot::{
     generators::{Generator, SortDirection, categories::CategoryMemberSort},
 };
 use std::path::Path;
+use tracing::level_filters::LevelFilter;
+use tracing_subscriber::{Layer, layer::SubscriberExt, util::SubscriberInitExt};
 
-use crate::watchdog::watch_wanted;
+use crate::fetching::{DynWsdcFetcher, ScoringDanceFetcher, WorldsdcFetcher};
+use crate::watchdog::{update_wanted_ids, watch_wanted};
 
 mod dance_info;
+mod fetching;
 mod updater;
 mod watchdog;
 mod wikiinfo;
 mod wikipage;
-mod worldsdc;
 
 #[allow(dead_code)]
 #[allow(clippy::print_stdout, reason = "We want to print here")]
@@ -60,24 +62,163 @@ pub enum AppError {
     BotError(#[from] ConfigError),
 }
 
-fn main() -> Result<(), AppError> {
+fn init_sentry() -> Option<sentry::ClientInitGuard> {
-    tracing_subscriber::fmt()
+    let fmt_filter = tracing_subscriber::fmt::layer().with_filter(
-        .with_level(true)
+        tracing_subscriber::EnvFilter::builder()
-        .with_max_level(tracing::Level::INFO)
+            .with_default_directive(LevelFilter::INFO.into())
-        .init();
+            .from_env_lossy(),
-    tracing::info!("Starting {}", app_signature());
+    );
+    let guard: Option<sentry::ClientInitGuard> = match std::fs::read_to_string("sentry_dsn.txt") {
+        Ok(dsn) => {
+            let guard = sentry::init((
+                dsn,
+                sentry::ClientOptions {
+                    release: sentry::release_name!(),
+                    traces_sample_rate: 1.0,
+                    ..Default::default()
+                },
+            ));
 
+            let sentry_layer = sentry::integrations::tracing::layer()
+                .event_filter(|md| match *md.level() {
+                    tracing::Level::ERROR => sentry_tracing::EventFilter::Event,
+                    _ => sentry_tracing::EventFilter::Ignore,
+                })
+                .span_filter(|md| {
+                    matches!(*md.level(), tracing::Level::ERROR | tracing::Level::WARN)
+                });
+
+            tracing_subscriber::registry()
+                .with(fmt_filter)
+                .with(sentry_layer)
+                .init();
+            tracing::info!("Starting {} with sentry", app_signature());
+
+            Some(guard)
+        }
+        Err(error) => {
+            tracing_subscriber::registry().with(fmt_filter).init();
+            tracing::warn!("Could not load 'sentry_dsn.txt': {}", error);
+            None
+        }
+    };
+    guard
+}
+
+use clap::{Parser, Subcommand};
+
+#[derive(Parser)]
+#[command(name = "teachertracking")]
+#[command(about = "MediaWiki Bot to keep West Coast Swing Teacher Scores updated", long_about = None)]
+struct Cli {
+    #[command(subcommand)]
+    command: Option<Commands>,
+
+    #[clap(value_enum)]
+    #[arg(default_value_t)]
+    backend: WsdcPointsBackend,
+}
+
+#[derive(clap::ValueEnum, Debug, Clone, Default)]
+enum WsdcPointsBackend {
+    ScoringDance,
+    #[default]
+    WorldSDC,
+}
+
+#[derive(Subcommand)]
+enum Commands {
+    /// Continuously watch for missing or outdated teachers and update them
+    Watch,
+    /// Build pages for all missing teachers
+    FixMissing,
+    /// List all missing teachers
+    ListMissing,
+    /// Update info for all teachers
+    FetchInfo(FetchInfoArgs),
+}
+
+#[derive(Parser)]
+struct FetchInfoArgs {
+    id: u32,
+}
+
+fn main() -> Result<(), AppError> {
+    let _guard = init_sentry();
+
+    // Register the Sentry tracing layer to capture breadcrumbs, events, and spans:
     let rt = tokio::runtime::Builder::new_current_thread()
         .enable_all()
         .build()?;
 
+    let cli = Cli::parse();
+
     let bot = rt.block_on(Bot::from_path(Path::new("./mwbot.toml")))?;
 
+    // Build a dynamic fetcher based on CLI selection
+    let fetcher: DynWsdcFetcher = match cli.backend {
+        WsdcPointsBackend::ScoringDance => std::sync::Arc::new(ScoringDanceFetcher {}),
+        WsdcPointsBackend::WorldSDC => std::sync::Arc::new(WorldsdcFetcher {}),
+    };
+    let command = cli.command.as_ref().map_or(&Commands::Watch, |cmd| cmd);
+
+    match command {
+        Commands::ListMissing => {
+            rt.block_on(async {
+                let wanted = wikiinfo::wanted_ids(bot.clone(), fetcher.clone()).await;
+                tracing::info!(
+                    "Missing ids: {}",
+                    wanted
+                        .iter()
+                        .map(|(v, _)| v)
+                        .map(u32::to_string)
+                        .collect::<Vec<_>>()
+                        .join("\n")
+                );
+                update_wanted_ids(&wanted, &[], fetcher.clone()).await;
+            });
+        }
+        Commands::FetchInfo(args) => {
+            rt.block_on(async {
+                let info = fetcher.fetch(args.id).await;
+                #[allow(
+                    clippy::print_stdout,
+                    clippy::print_stderr,
+                    reason = "We want to print here"
+                )]
+                match info {
+                    Ok(info) => println!("Fetched info: {info:?}"),
+                    Err(err) => eprintln!("Error fetching info: {err}"),
+                }
+            });
+        }
+        Commands::FixMissing => {
+            rt.block_on(async {
+                let wanted = wikiinfo::wanted_ids(bot.clone(), fetcher.clone()).await;
+                tracing::info!(
+                    "Missing ids: {}",
+                    wanted
+                        .iter()
+                        .map(|(v, _)| v)
+                        .map(u32::to_string)
+                        .collect::<Vec<_>>()
+                        .join("\n")
+                );
+                update_wanted_ids(&wanted, &[], fetcher.clone()).await;
+            });
+        }
+        Commands::Watch => {
             #[allow(
                 unreachable_code,
                 reason = "This is a false positive I think, I just want to loop infinitely on two futures"
             )]
-    rt.block_on(async { futures::join!(watch_wanted(bot.clone()), updater::update_wsdc(bot)) });
+            rt.block_on(async {
-
+                futures::join!(
+                    watch_wanted(bot.clone(), fetcher.clone()),
+                    updater::update_wsdc(bot, fetcher.clone())
+                )
+            });
+        }
+    }
     Ok(())
 }

src/updater.rs

@@ -5,32 +5,38 @@ use rand::seq::SliceRandom as _;
 use tokio::time::sleep;
 
 use crate::{watchdog::generate_page, wikiinfo::index_wsdc_ids};
+use crate::fetching::DynWsdcFetcher;
 
-pub async fn update_wsdc(bot: Bot) -> ! {
+pub async fn update_wsdc(bot: Bot, fetcher: DynWsdcFetcher) -> ! {
     loop {
-        update_all_teachers(&bot).await;
+        update_all_teachers(&bot, fetcher.clone()).await;
     }
 }
 
 /// Updates all teachers once
-async fn update_all_teachers(bot: &Bot) {
+async fn update_all_teachers(bot: &Bot, fetcher: DynWsdcFetcher) {
-    let mut l = index_wsdc_ids(bot).await;
+    let mut l = index_wsdc_ids(bot, fetcher.clone()).await;
     l.shuffle(&mut rand::rng());
     tracing::info!("We have to update {} pages", l.len());
     let wait_duration = Duration::from_hours(6);
 
     for (index, page) in l {
-        process_page(wait_duration, index, page).await;
+        process_page(wait_duration, index, page, fetcher.clone()).await;
     }
     tracing::info!("Updates all pages");
 }
 
-#[tracing::instrument(skip(page, wait_duration))]
+#[tracing::instrument(skip(page, wait_duration, fetcher))]
-async fn process_page(wait_duration: Duration, index: u32, page: mwbot::Page) {
+async fn process_page(
+    wait_duration: Duration,
+    index: u32,
+    page: mwbot::Page,
+    fetcher: DynWsdcFetcher,
+) {
     tracing::info!("Next up");
     sleep(wait_duration).await;
 
-    match generate_page(index, page).await {
+    match generate_page(index, page, fetcher).await {
         Ok(()) => (),
         Err(err) => {
             tracing::error!("Error updating: {err}");

src/watchdog.rs

@@ -2,8 +2,9 @@ use std::time::Duration;
 
 use crate::app_signature;
 use crate::wikipage::InfoCompileError;
-use crate::worldsdc::DanceInfoError;
+use crate::fetching::types::DanceInfoError;
-use crate::{wikiinfo::wanted_ids, wikipage::page_from_info, worldsdc::fetch_wsdc_info};
+use crate::{wikiinfo::wanted_ids, wikipage::page_from_info};
+use crate::fetching::DynWsdcFetcher;
 use mwbot::SaveOptions;
 use mwbot::{Bot, Page};
 
@@ -31,27 +32,31 @@ impl Ticker {
 
 /// Continuously monitors teacher IDs that do not have a corresponding teacher WSDC page, ignoring those that fail processing.
 #[tracing::instrument(skip_all)]
-pub async fn watch_wanted(bot: Bot) -> ! {
+pub async fn watch_wanted(bot: Bot, fetcher: DynWsdcFetcher) -> ! {
     let mut ignored_ids = vec![];
     let mut heartbeat_ticker = Ticker::new(120);
     loop {
         if heartbeat_ticker.tick() {
             tracing::info!(failed_id_count = ignored_ids.len(), "Watchdog check...");
         }
-        let wanted = wanted_ids(bot.clone()).await;
+        let wanted = wanted_ids(bot.clone(), fetcher.clone()).await;
-        let new_ignored = update_wanted_ids(&wanted, &ignored_ids).await;
+        let new_ignored = update_wanted_ids(&wanted, &ignored_ids, fetcher.clone()).await;
         ignored_ids.extend(new_ignored);
         tokio::time::sleep(Duration::from_secs(30)).await;
     }
 }
 
-async fn update_wanted_ids(wanted: &[(u32, Page)], ignored_ids: &[u32]) -> Vec<u32> {
+pub async fn update_wanted_ids(
+    wanted: &[(u32, Page)],
+    ignored_ids: &[u32],
+    fetcher: DynWsdcFetcher,
+) -> Vec<u32> {
     let mut new_ignored = vec![];
 
-    for (id, page) in wanted.iter().filter(|(x, _)| ignored_ids.contains(x)) {
+    for (id, page) in wanted.iter().filter(|(x, _)| !ignored_ids.contains(x)) {
         let span = tracing::info_span!("update", id);
         let _enter = span.enter();
-        if let Err(e) = generate_page(*id, page.clone()).await {
+        if let Err(e) = generate_page(*id, page.clone(), fetcher.clone()).await {
             tracing::error!("{e}");
             new_ignored.push(*id);
         }
@@ -71,9 +76,13 @@ pub enum GeneratePageError {
     Save(#[from] mwbot::Error),
 }
 
-pub async fn generate_page(id: u32, page: mwbot::Page) -> Result<(), GeneratePageError> {
+pub async fn generate_page(
+    id: u32,
+    page: mwbot::Page,
+    fetcher: DynWsdcFetcher,
+) -> Result<(), GeneratePageError> {
     tracing::info!("Generating page for {id}");
-    let info = fetch_wsdc_info(id).await?;
+    let info = fetcher.fetch(id).await?;
 
     let code = page_from_info(info)?;
 

src/wikiinfo.rs

@@ -2,15 +2,24 @@ use mwbot::{
     Bot, Page,
     generators::{Generator, querypage::QueryPage, search::Search},
 };
+use crate::fetching::DynWsdcFetcher;
 
-pub async fn wanted_ids(bot: Bot) -> Vec<(u32, Page)> {
+pub async fn wanted_ids(bot: Bot, _fetcher: DynWsdcFetcher) -> Vec<(u32, Page)> {
     let mut gene = QueryPage::new("Wantedpages").generate(&bot);
     let mut result = vec![];
     while let Some(x) = gene.recv().await {
         let p = match x {
             Ok(p) => p,
             Err(e) => {
+                match e {
+                    mwbot::Error::ApiError(a) if &a.code == "assertuserfailed" => {
+                        tracing::error!("Bot is logged out: {a}");
+                        panic!();
+                    }
+                    _ => {
                         tracing::error!("Could not get search result: {e}");
+                    }
+                }
                 continue;
             }
         };
@@ -42,20 +51,8 @@ fn parse_wsdc_page_name(name: &str) -> Result<u32, TitleParseError> {
     }
 }
 
-// fn get_wsdc_page_date(bot: &Bot, page: &Page) -> Option<SystemTime> {
-// todo!();
-// let prefix = "Updated-On: ";
-// page.filter_comments()
-//     .iter()
-//     .filter_map(|x| {
-//         let c = x.text_contents();
-//         if c.starts_with(prefix) { Some(c) } else { None }
-//     })
-//     .map(|x| x.trim_start_matches(prefix).parse::<u64>());
-// }
-
 #[allow(dead_code)]
-pub async fn index_wsdc_ids(bot: &Bot) -> Vec<(u32, Page)> {
+pub async fn index_wsdc_ids(bot: &Bot, _fetcher: DynWsdcFetcher) -> Vec<(u32, Page)> {
     let mut gene = Search::new("WSDC/").generate(bot);
     let mut result = vec![];
     while let Some(x) = gene.recv().await {