Merge branch 'feat_megalodon_update' into 'main'

⬆️: megalodon 1.0.0

See merge request veretcle/oolatoocs!27

.gitignore

@@ -1,3 +1,4 @@
 /target
 .last_tweet
 .config.toml
+.config.json

Cargo.toml

@@ -1,23 +1,29 @@
 [package]
 name = "oolatoocs"
-version = "0.1.0"
+version = "4.1.3"
 edition = "2021"
 
 # See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
 
 [dependencies]
+chrono = "^0.4"
 clap = "^4"
-dissolve = "0.2.2"
 env_logger = "^0.10"
+futures = "^0.3"
+html-escape = "^0.2"
 log = "^0.4"
-megalodon = "^0.11"
+megalodon = "^1.0"
 oauth1-request = "^0.6"
-regex = "1.10.2"
-reqwest = { version = "0.11.22", features = ["json"] }
-rusqlite = "^0.27"
+regex = "^1.10"
+reqwest = { version = "^0.11", features = ["json", "stream", "multipart"] }
+rusqlite = { version = "^0.30", features = ["chrono"] }
 serde = { version = "^1.0", features = ["derive"] }
 tokio = { version = "^1.33", features = ["rt-multi-thread", "macros"] }
 toml = "^0.8"
+bsky-sdk = "^0.1"
+atrium-api = "^0.24"
+image = "^0.25"
+webp = "^0.3"
 
 [profile.release]
 strip = true

README.md

@@ -0,0 +1,81 @@
+# oolatoocs, a Mastodon to Bluesky bot
+## A little bit of history
+
+So what is it? Originally, I wrote, with some help, [Scootaloo](https://framagit.org/veretcle/scootaloo/) which was a Twitter to Mastodon Bot to help the [writers at NintendojoFR](https://www.nintendojo.fr) not to worry about Mastodon: the vast majority of writers were posting to Twitter, the bot scooped everything and arranged it properly for Mastodon and everything was fine and dandy. It was also used, in an altered beefed-up version, for the (now defunct) Mastodon Instance [Nupes.social](https://nupes.social) to make the tweets from the NUPES political alliance on Twitter, more easily accessible for Mastodon users.
+
+But then Elon came, and we couldn’t read data from Twitter anymore. So we had to rely on copy/pasting things from one to another, which is not fun nor efficient.
+
+## And now…
+
+Hence `oolatoocs`, which takes a Mastodon Timeline and reposts it to Bluesky as properly as possible.
+
+Since 2025-01-20, Twitter is now longer supported.
+
+# Remarkable features
+
+What it can do:
+* Reproduces the Toot content into the Record;
+* Cuts (poorly) the Toot in half in it’s too long for Bluesky and thread it (this is cut using a word count, not the best method, but it gets the job done);
+* Reuploads images/gifs/videos from Mastodon to Bluesky
+    * ⚠️ Bluesky does not support mixing images and videos. You can have up to 4 images on a Bsky record **or** 1 video but not mix around. If you do so, only the video will be posted on Bluesky.
+    * ⚠️ Bluesky does not support images greater than 1Mb (that is 1,000,000,000 bytes or 976.6 KiB). I might incorporate soon a image quality reducer or WebP transcoding to avoid this issue.
+* Can reproduce threads from Mastodon to Bluesky
+* ⚠️ Bluesky does support polls for now. So the poll itself is just presented as text from Mastodon instead which is not the most elegant.
+* Can prevent a Toot from being recorded to Bluesky by using the #NoTweet (case-insensitive) hashtag in Mastodon
+
+# Configuration file
+
+The configuration is relatively easy to follow:
+
+```toml
+[oolatoocs]
+db_path = "/var/lib/oolatoocs/db.sqlite3" # the path to the DB where toots/tweets/records are stored
+
+[mastodon] # This part can be generated, see below
+base = "https://m.nintendojo.fr"
+client_id = "<REDACTED>"
+client_secret = "<REDACTED>"
+redirect = "urn:ietf:wg:oauth:2.0:oob"
+token = "<REDACTED>"
+
+[bluesky] # this is your Bsky handle and password + a writable path for the session handling
+handle = "nintendojofr.bsky.social"
+password = "<REDACTED>"
+config_path = "/var/lib/oolatoocs/bsky.json"
+```
+
+## How to generate the Mastodon keys?
+
+Just run:
+
+```bash
+oolatoocs register --host https://<your-instance>
+```
+
+And follow the instructions.
+
+## How to generate the Bluesky part?
+
+You’ll need your handle and password. I strongly recommend a dedicated application password. You’ll also need a writable path to store the Bsky session.
+
+# How to run
+
+First of all, the `--help`:
+
+```bash
+A Mastodon to Twitter Bot
+
+Usage: oolatoocs [OPTIONS] [COMMAND]
+
+Commands:
+  init      Command to init the DB
+  register  Command to register to Mastodon Instance
+  help      Print this message or the help of the given subcommand(s)
+
+Options:
+  -c, --config <CONFIG_FILE>  TOML config file for oolatoocs [default: /usr/local/etc/oolatoocs.toml]
+  -h, --help                  Print help
+  -V, --version               Print version
+```
+
+Ideally, you’ll put it an cron (from a non-root user), with the default path for config file and let it do its job. Yeah, that’s it.

src/bsky.rs

@@ -0,0 +1,280 @@
+use crate::config::BlueskyConfig;
+use atrium_api::{
+    app::bsky::feed::post::RecordData, com::atproto::repo::upload_blob::Output,
+    types::string::Datetime, types::string::Language,
+};
+use bsky_sdk::{
+    agent::config::{Config, FileStore},
+    rich_text::RichText,
+    BskyAgent,
+};
+use futures::{stream, StreamExt};
+use image::ImageReader;
+use log::{debug, error, warn};
+use megalodon::entities::attachment::{Attachment, AttachmentType};
+use regex::Regex;
+use std::{error::Error, fs::exists, io::Cursor};
+use webp::*;
+
+/// Intermediary struct to deal with replies more easily
+#[derive(Debug)]
+pub struct BskyReply {
+    pub record_uri: String,
+    pub root_record_uri: String,
+}
+
+pub async fn get_session(config: &BlueskyConfig) -> Result<BskyAgent, Box<dyn Error>> {
+    if exists(&config.config_path)? {
+        let bluesky = BskyAgent::builder()
+            .config(Config::load(&FileStore::new(&config.config_path)).await?)
+            .build()
+            .await?;
+
+        if bluesky.api.com.atproto.server.get_session().await.is_ok() {
+            bluesky
+                .to_config()
+                .await
+                .save(&FileStore::new(&config.config_path))
+                .await?;
+            return Ok(bluesky);
+        }
+    }
+
+    let bluesky = BskyAgent::builder().build().await?;
+    bluesky.login(&config.handle, &config.password).await?;
+    bluesky
+        .to_config()
+        .await
+        .save(&FileStore::new(&config.config_path))
+        .await?;
+
+    Ok(bluesky)
+}
+
+pub async fn build_post_record(
+    config: &BlueskyConfig,
+    text: &str,
+    language: &Option<String>,
+    embed: Option<atrium_api::types::Union<atrium_api::app::bsky::feed::post::RecordEmbedRefs>>,
+    reply_to: &Option<BskyReply>,
+) -> Result<RecordData, Box<dyn Error>> {
+    let mut rt = RichText::new_with_detect_facets(text).await?;
+
+    let insert_chars = "…";
+
+    let re = Regex::new(r#"(https?://)(www\.)?(\S{1,26})(\S*)"#).unwrap();
+
+    while let Some(found) = re.captures(&rt.text.clone()) {
+        if let Some(group) = found.get(4) {
+            if !group.is_empty() {
+                rt.insert(group.start(), insert_chars);
+                rt.delete(
+                    group.start() + insert_chars.len(),
+                    group.start() + insert_chars.len() + group.len(),
+                );
+            }
+        }
+        if let Some(group) = found.get(1) {
+            let www: usize = found.get(2).map_or(0, |x| x.len());
+            rt.delete(group.start(), group.start() + www + group.len());
+        }
+    }
+
+    let langs = language.clone().map(|s| vec![Language::new(s).unwrap()]);
+
+    let reply = if let Some(x) = reply_to {
+        let root_record = get_record(&config.handle, &rkey(&x.root_record_uri)).await?;
+        let parent_record = get_record(&config.handle, &rkey(&x.record_uri)).await?;
+
+        Some(
+            atrium_api::app::bsky::feed::post::ReplyRefData {
+                parent: atrium_api::com::atproto::repo::strong_ref::MainData {
+                    cid: parent_record.data.cid.unwrap(),
+                    uri: parent_record.data.uri.to_owned(),
+                }
+                .into(),
+                root: atrium_api::com::atproto::repo::strong_ref::MainData {
+                    cid: root_record.data.cid.unwrap(),
+                    uri: root_record.data.uri.to_owned(),
+                }
+                .into(),
+            }
+            .into(),
+        )
+    } else {
+        None
+    };
+
+    Ok(RecordData {
+        created_at: Datetime::now(),
+        embed,
+        entities: None,
+        facets: rt.facets,
+        labels: None,
+        langs,
+        reply,
+        tags: None,
+        text: rt.text,
+    })
+}
+
+async fn get_record(
+    config: &str,
+    rkey: &str,
+) -> Result<
+    atrium_api::types::Object<atrium_api::com::atproto::repo::get_record::OutputData>,
+    Box<dyn Error>,
+> {
+    let bsky = BskyAgent::builder().build().await?;
+    let record = bsky
+        .api
+        .com
+        .atproto
+        .repo
+        .get_record(
+            atrium_api::com::atproto::repo::get_record::ParametersData {
+                cid: None,
+                collection: atrium_api::types::string::Nsid::new("app.bsky.feed.post".to_string())?,
+                repo: atrium_api::types::string::Handle::new(config.to_string())?.into(),
+                rkey: rkey.to_string(),
+            }
+            .into(),
+        )
+        .await?;
+
+    Ok(record)
+}
+
+// it’s ugly af but it gets the job done for now
+pub async fn generate_media_records(
+    bsky: &BskyAgent,
+    media_attach: &[Attachment],
+) -> Option<atrium_api::types::Union<atrium_api::app::bsky::feed::post::RecordEmbedRefs>> {
+    let mut embed: Option<
+        atrium_api::types::Union<atrium_api::app::bsky::feed::post::RecordEmbedRefs>,
+    > = None;
+
+    let image_media_attach: Vec<_> = media_attach
+        .iter()
+        .filter(|x| x.r#type == AttachmentType::Image)
+        .cloned()
+        .collect();
+    let video_media_attach: Vec<_> = media_attach
+        .iter()
+        .filter(|x| (x.r#type == AttachmentType::Video || x.r#type == AttachmentType::Gifv))
+        .cloned()
+        .collect();
+
+    // Bsky only tasks 1 video per post, so we’ll try to treat that first and exit
+    if !video_media_attach.is_empty() {
+        // treat only the very first video, ignore the rest
+        let media = &video_media_attach[0];
+        let blob = upload_media(false, bsky, &media.url).await.unwrap();
+
+        embed = Some(atrium_api::types::Union::Refs(
+            atrium_api::app::bsky::feed::post::RecordEmbedRefs::AppBskyEmbedVideoMain(Box::new(
+                atrium_api::app::bsky::embed::video::MainData {
+                    alt: media.description.clone(),
+                    aspect_ratio: None,
+                    captions: None,
+                    video: blob.data.blob,
+                }
+                .into(),
+            )),
+        ));
+
+        // returns immediately, we don’t want to treat the other medias
+        return embed;
+    }
+
+    let mut stream = stream::iter(image_media_attach)
+        .map(|media| {
+            let bsky = bsky.clone();
+            tokio::task::spawn(async move {
+                debug!("Treating media {}", &media.url);
+                upload_media(true, &bsky, &media.url).await.map(|i| {
+                    atrium_api::app::bsky::embed::images::ImageData {
+                        alt: media
+                            .description
+                            .clone()
+                            .map_or("".to_string(), |v| v.to_owned()),
+                        aspect_ratio: None,
+                        image: i.data.blob,
+                    }
+                })
+            })
+        })
+        .buffered(4);
+
+    let mut images = Vec::new();
+
+    while let Some(result) = stream.next().await {
+        match result {
+            Ok(Ok(v)) => images.push(v.into()),
+            Ok(Err(e)) => warn!("Cannot treat a specific media: {}", e),
+            Err(e) => error!("Something went wrong when joining main thread: {}", e),
+        }
+    }
+
+    if !images.is_empty() {
+        embed = Some(atrium_api::types::Union::Refs(
+            atrium_api::app::bsky::feed::post::RecordEmbedRefs::AppBskyEmbedImagesMain(Box::new(
+                atrium_api::app::bsky::embed::images::MainData { images }.into(),
+            )),
+        ));
+    }
+
+    embed
+}
+
+async fn upload_media(
+    is_image: bool,
+    bsky: &BskyAgent,
+    u: &str,
+) -> Result<Output, Box<dyn Error + Send + Sync>> {
+    let dl = reqwest::get(u).await?;
+    let content_length = dl.content_length().ok_or("Content length unavailable")?;
+    let bytes = if content_length <= 1_000_000 || !is_image {
+        dl.bytes().await?.as_ref().to_vec()
+    } else {
+        // this is an image and it’s over 1Mb long
+        debug!("Img file too large: {}", content_length);
+        let img = ImageReader::new(Cursor::new(dl.bytes().await?))
+            .with_guessed_format()?
+            .decode()?;
+        let encoder: Encoder = Encoder::from_image(&img)?;
+        let webp: WebPMemory = encoder.encode(90f32);
+        webp.to_vec()
+    };
+
+    let record = bsky.api.com.atproto.repo.upload_blob(bytes).await?;
+
+    Ok(record)
+}
+
+fn rkey(record_id: &str) -> String {
+    record_id.split('/').nth(4).unwrap().to_string()
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[tokio::test]
+    async fn test_build_post_record() {
+        let text = "@factornews@piaille.fr Retrouvez-nous ici https://www.nintendojo.fr/articles/editos/le-mod-renovation-de-8bitdo-pour-manette-n64 et là https://www.nintendojo.fr/articles/analyses/vite-vu/vite-vu-morbid-the-lords-of-ire et un lien très court http://vsl.ie/TaMere et un autre https://p.nintendojo.fr/w/kV3CBbKKt1nPEChHhZiNve + http://www.xxx.com + https://www.youtube.com/watch?v=dQw4w9WgXcQ&pp=ygUJcmljayByb2xs";
+        let expected_text = "@factornews@piaille.fr Retrouvez-nous ici nintendojo.fr/articles/edi… et là nintendojo.fr/articles/ana… et un lien très court vsl.ie/TaMere et un autre p.nintendojo.fr/w/kV3CBbKK… + xxx.com + youtube.com/watch?v=dQw4w9…";
+
+        let bsky_conf = BlueskyConfig {
+            handle: "tamerelol.bsky.social".to_string(),
+            password: "dtc".to_string(),
+            config_path: "nope".to_string(),
+        };
+
+        let created_record_data = build_post_record(&bsky_conf, text, &None, None, &None)
+            .await
+            .unwrap();
+
+        assert_eq!(expected_text, &created_record_data.text);
+    }
+}

src/config.rs

@@ -5,15 +5,7 @@ use std::fs::read_to_string;
 pub struct Config {
     pub oolatoocs: OolatoocsConfig,
     pub mastodon: MastodonConfig,
-    pub twitter: TwitterConfig,
-}
-
-#[derive(Debug, Deserialize)]
-pub struct TwitterConfig {
-    pub consumer_key: String,
-    pub consumer_secret: String,
-    pub oauth_token: String,
-    pub oauth_token_secret: String,
+    pub bluesky: BlueskyConfig,
 }
 
 #[derive(Debug, Deserialize)]
@@ -30,6 +22,13 @@ pub struct MastodonConfig {
     pub token: String,
 }
 
+#[derive(Debug, Deserialize)]
+pub struct BlueskyConfig {
+    pub handle: String,
+    pub password: String,
+    pub config_path: String,
+}
+
 /// parses TOML file into Config struct
 pub fn parse_toml(toml_file: &str) -> Config {
     let toml_config =

src/error.rs

@@ -0,0 +1,25 @@
+use std::{
+    error::Error,
+    fmt::{Display, Formatter, Result},
+};
+
+#[derive(Debug)]
+pub struct OolatoocsError {
+    details: String,
+}
+
+impl OolatoocsError {
+    pub fn new(msg: &str) -> OolatoocsError {
+        OolatoocsError {
+            details: msg.to_string(),
+        }
+    }
+}
+
+impl Error for OolatoocsError {}
+
+impl Display for OolatoocsError {
+    fn fmt(&self, f: &mut Formatter) -> Result {
+        write!(f, "{}", self.details)
+    }
+}

src/lib.rs

@@ -1,21 +1,24 @@
+use log::debug;
+
+mod error;
+pub use error::OolatoocsError;
+
 mod config;
 pub use config::{parse_toml, Config};
 
 mod state;
-pub use state::init_db;
-#[allow(unused_imports)]
-use state::{read_state, write_state, TweetToToot};
+use state::{delete_state, read_all_state, read_state, write_state, TootRecord};
+pub use state::{init_db, migrate_db};
 
 mod mastodon;
-use mastodon::get_mastodon_timeline_since;
 pub use mastodon::register;
+use mastodon::{get_mastodon_instance, get_mastodon_timeline_since, get_status_edited_at};
 
 mod utils;
-use utils::strip_everything;
+use utils::{generate_multi_tweets, strip_everything};
 
-mod twitter;
-#[allow(unused_imports)]
-use twitter::{post_tweet, upload_media};
+mod bsky;
+use bsky::{build_post_record, generate_media_records, get_session, BskyReply};
 
 use rusqlite::Connection;
 
@@ -24,31 +27,163 @@ pub async fn run(config: &Config) {
     let conn = Connection::open(&config.oolatoocs.db_path)
         .unwrap_or_else(|e| panic!("Cannot open DB: {}", e));
 
-    let last_toot_id = read_state(&conn, None)
-        .unwrap_or_else(|e| panic!("Cannot get last toot id: {}", e))
-        .map(|r| r.toot_id);
+    let mastodon = get_mastodon_instance(&config.mastodon)
+        .unwrap_or_else(|e| panic!("Cannot instantiate Mastodon: {}", e));
 
-    let timeline = get_mastodon_timeline_since(&config.mastodon, last_toot_id)
+    let bluesky = get_session(&config.bluesky)
+        .await
+        .unwrap_or_else(|e| panic!("Cannot get Bsky session: {}", e));
+
+    let last_entry =
+        read_state(&conn, None).unwrap_or_else(|e| panic!("Cannot get last toot id: {}", e));
+
+    let last_toot_id: Option<u64> = match last_entry {
+        None => None, // Does not exist, this is the same as previously
+        Some(t) => {
+            match get_status_edited_at(&mastodon, t.toot_id).await {
+                None => Some(t.toot_id),
+                Some(d) => {
+                    // a date has been found
+                    if d > t.datetime.unwrap() {
+                        debug!("Last toot date is posterior to the previously written tweet, deleting…");
+                        let local_record_uris =
+                            read_all_state(&conn, t.toot_id).unwrap_or_else(|e| {
+                                panic!(
+                                    "Cannot fetch all records associated with Toot ID {}: {}",
+                                    t.toot_id, e
+                                )
+                            });
+                        for local_record_uri in local_record_uris.into_iter() {
+                            bluesky
+                                .delete_record(&local_record_uri)
+                                .await
+                                .unwrap_or_else(|e| {
+                                    panic!("Cannot delete record ID ({}): {}", &t.record_uri, e)
+                                });
+                        }
+                        delete_state(&conn, t.toot_id).unwrap_or_else(|e| {
+                            panic!("Cannot delete Toot ID ({}): {}", t.toot_id, e)
+                        });
+                        read_state(&conn, None)
+                            .unwrap_or_else(|e| panic!("Cannot get last toot id: {}", e))
+                            .map(|a| a.toot_id)
+                    } else {
+                        Some(t.toot_id)
+                    }
+                }
+            }
+        }
+    };
+
+    let timeline = get_mastodon_timeline_since(&mastodon, last_toot_id)
         .await
         .unwrap_or_else(|e| panic!("Cannot get instance: {}", e));
 
     for toot in timeline {
-        let Ok(tweet_content) = strip_everything(&toot.content, &toot.tags) else {
+        // detecting tag #NoTweet and skipping the toot
+        if toot.tags.iter().any(|f| &f.name == "notweet") {
+            continue;
+        }
+
+        // form tweet_content and strip everything useless in it
+        let Ok(mut tweet_content) = strip_everything(&toot.content, &toot.tags) else {
             continue; // skip in case we can’t strip something
         };
-        // if we wanted to cut toot in half, now would be the right time to do so
-        // treating medias (nothing for now)
-        let tweet_id = post_tweet(&config.twitter, &tweet_content, &[])
-            .await
-            .unwrap_or_else(|e| panic!("Cannot Tweet {}: {}", toot.id, e));
 
+        // threads if necessary
+        let mut record_reply_to = toot.in_reply_to_id.and_then(|t| {
+            read_state(&conn, Some(t.parse::<u64>().unwrap()))
+                .ok()
+                .flatten()
+                .map(|s| BskyReply {
+                    record_uri: s.record_uri.to_owned(),
+                    root_record_uri: s.root_record_uri.to_owned(),
+                })
+        });
+
+        // if the toot is too long, we cut it in half here
+        if let Some((first_half, second_half)) = generate_multi_tweets(&tweet_content) {
+            tweet_content = second_half;
+            // post the first half
+            let record = build_post_record(
+                &config.bluesky,
+                &first_half,
+                &toot.language,
+                None,
+                &record_reply_to,
+            )
+            .await
+            .unwrap_or_else(|e| panic!("Cannot create valid record for {}: {}", &toot.id, e));
+            let record_reply_id = bluesky.create_record(record).await.unwrap_or_else(|e| {
+                panic!(
+                    "Cannot post the first half of {} for Bluesky: {}",
+                    &toot.id, e
+                )
+            });
+            // write it to db
+            write_state(
+                &conn,
+                TootRecord {
+                    toot_id: toot.id.parse::<u64>().unwrap(),
+                    record_uri: record_reply_id.data.uri.to_owned(),
+                    root_record_uri: record_reply_to
+                        .as_ref()
+                        .map_or(record_reply_id.data.uri.to_owned(), |v| {
+                            v.root_record_uri.to_owned()
+                        }),
+                    datetime: None,
+                },
+            )
+            .unwrap_or_else(|e| {
+                panic!(
+                    "Cannot store Toot/Tweet/Record ({}/{}): {}",
+                    &toot.id, &record_reply_id.data.uri, e
+                )
+            });
+
+            record_reply_to = Some(BskyReply {
+                record_uri: record_reply_id.data.uri.to_owned(),
+                root_record_uri: record_reply_to
+                    .as_ref()
+                    .map_or(record_reply_id.data.uri.clone(), |v| {
+                        v.root_record_uri.clone()
+                    }),
+            });
+        };
+
+        // treats medias
+        let record_medias = generate_media_records(&bluesky, &toot.media_attachments).await;
+
+        // posts corresponding tweet
+        let record = build_post_record(
+            &config.bluesky,
+            &tweet_content,
+            &toot.language,
+            record_medias,
+            &record_reply_to,
+        )
+        .await
+        .unwrap_or_else(|e| panic!("Cannot build record for {}: {}", &toot.id, e));
+
+        let created_record = bluesky
+            .create_record(record)
+            .await
+            .unwrap_or_else(|e| panic!("Cannot put record {}: {}", &toot.id, e));
+
+        // writes the current state of the tweet
         write_state(
             &conn,
-            TweetToToot {
-                tweet_id,
+            TootRecord {
                 toot_id: toot.id.parse::<u64>().unwrap(),
+                record_uri: created_record.data.uri.clone(),
+                root_record_uri: record_reply_to
+                    .as_ref()
+                    .map_or(created_record.data.uri.clone(), |v| {
+                        v.root_record_uri.clone()
+                    }),
+                datetime: None,
             },
         )
-        .unwrap_or_else(|e| panic!("Cannot store Toot/Tweet ({}/{}): {}", &toot.id, tweet_id, e));
+        .unwrap_or_else(|e| panic!("Cannot store Toot/Tweet ({}): {}", &toot.id, e));
     }
 }

src/main.rs

@@ -49,6 +49,21 @@ fn main() {
                         .display_order(1),
                 ),
         )
+        .subcommand(
+            Command::new("migrate")
+                .version(env!("CARGO_PKG_VERSION"))
+                .about("Command to register to Mastodon Instance")
+                .arg(
+                    Arg::new("config")
+                        .short('c')
+                        .long("config")
+                        .value_name("CONFIG_FILE")
+                        .help(format!("TOML config file for {}", env!("CARGO_PKG_NAME")))
+                        .num_args(1)
+                        .default_value(DEFAULT_CONFIG_PATH)
+                        .display_order(1),
+                ),
+        )
         .get_matches();
 
     env_logger::init();
@@ -63,6 +78,11 @@ fn main() {
             register(sub_m.get_one::<String>("host").unwrap());
             return;
         }
+        Some(("migrate", sub_m)) => {
+            let config = parse_toml(sub_m.get_one::<String>("config").unwrap());
+            migrate_db(&config.oolatoocs.db_path).unwrap();
+            return;
+        }
         _ => (),
     }
 

src/mastodon.rs

@@ -1,4 +1,5 @@
 use crate::config::MastodonConfig;
+use chrono::{DateTime, Utc};
 use megalodon::{
     entities::{Status, StatusVisibility},
     generator,
@@ -10,16 +11,29 @@ use megalodon::{
 use std::error::Error;
 use std::io::stdin;
 
-pub async fn get_mastodon_timeline_since(
-    config: &MastodonConfig,
-    id: Option<u64>,
-) -> Result<Vec<Status>, Box<dyn Error>> {
-    let mastodon = Mastodon::new(
+/// Get Mastodon Object instance
+pub fn get_mastodon_instance(config: &MastodonConfig) -> Result<Mastodon, Box<dyn Error>> {
+    Ok(Mastodon::new(
         config.base.to_string(),
         Some(config.token.to_string()),
         None,
-    );
+    )?)
+}
 
+/// Get the edited_at field from the specified toot
+pub async fn get_status_edited_at(mastodon: &Mastodon, t: u64) -> Option<DateTime<Utc>> {
+    mastodon
+        .get_status(t.to_string())
+        .await
+        .ok()
+        .and_then(|t| t.json.edited_at)
+}
+
+/// Get the home timeline since the last toot
+pub async fn get_mastodon_timeline_since(
+    mastodon: &Mastodon,
+    id: Option<u64>,
+) -> Result<Vec<Status>, Box<dyn Error>> {
     let input_options = GetHomeTimelineInputOptions {
         only_media: Some(false),
         limit: None,
@@ -34,7 +48,6 @@ pub async fn get_mastodon_timeline_since(
         .await?
         .json()
         .iter()
-        .cloned()
         .filter(|t| {
             // this excludes the reply to other users
             t.in_reply_to_account_id.is_none()
@@ -45,6 +58,7 @@ pub async fn get_mastodon_timeline_since(
         .filter(|t| t.visibility == StatusVisibility::Public) // excludes everything that isn’t
         // public
         .filter(|t| t.reblog.is_none()) // excludes reblogs
+        .cloned()
         .collect();
 
     timeline.reverse();
@@ -57,7 +71,8 @@ pub async fn get_mastodon_timeline_since(
 /// Most of this function is a direct copy/paste of the official `elefren` crate
 #[tokio::main]
 pub async fn register(host: &str) {
-    let mastodon = generator(megalodon::SNS::Mastodon, host.to_string(), None, None);
+    let mastodon = generator(megalodon::SNS::Mastodon, host.to_string(), None, None)
+        .expect("Cannot build Mastodon generator object");
 
     let options = AppInputOptions {
         redirect_uris: None,

src/state.rs

@@ -1,33 +1,67 @@
+use chrono::{DateTime, Utc};
 use log::debug;
 use rusqlite::{params, Connection, OptionalExtension};
 use std::error::Error;
 
 /// Struct for each query line
 #[derive(Debug)]
-pub struct TweetToToot {
-    pub tweet_id: u64,
+pub struct TootRecord {
+    // Mastodon part
     pub toot_id: u64,
+    // Bluesky part
+    pub record_uri: String,
+    pub root_record_uri: String,
+    pub datetime: Option<DateTime<Utc>>,
+}
+
+/// Deletes a given state
+pub fn delete_state(conn: &Connection, toot_id: u64) -> Result<(), Box<dyn Error>> {
+    debug!("Deleting Toot ID {}", toot_id);
+    conn.execute(
+        &format!("DELETE FROM toot_record WHERE toot_id = {}", toot_id),
+        [],
+    )?;
+    Ok(())
+}
+
+/// Retrieves all tweets associated to a toot in the form of a vector
+pub fn read_all_state(conn: &Connection, toot_id: u64) -> Result<Vec<String>, Box<dyn Error>> {
+    let query = format!(
+        "SELECT record_uri FROM toot_record WHERE toot_id = {};",
+        toot_id
+    );
+    let mut stmt = conn.prepare(&query)?;
+    let mut rows = stmt.query([])?;
+
+    let mut record_v: Vec<String> = Vec::new();
+    while let Some(row) = rows.next()? {
+        record_v.push(row.get(0)?);
+    }
+
+    Ok(record_v)
 }
 
 /// if None is passed, read the last tweet from DB
 /// if a tweet_id is passed, read this particular tweet from DB
-pub fn read_state(
-    conn: &Connection,
-    s: Option<u64>,
-) -> Result<Option<TweetToToot>, Box<dyn Error>> {
+pub fn read_state(conn: &Connection, s: Option<u64>) -> Result<Option<TootRecord>, Box<dyn Error>> {
     debug!("Reading toot_id {:?}", s);
+    let begin_query = "SELECT *, UNIXEPOCH(datetime) AS unix_datetime FROM toot_record";
     let query: String = match s {
-        Some(i) => format!("SELECT * FROM tweet_to_toot WHERE toot_id = {i}"),
-        None => "SELECT * FROM tweet_to_toot ORDER BY toot_id DESC LIMIT 1".to_string(),
+        Some(i) => format!("{begin_query} WHERE toot_id = {i} ORDER BY record_uri DESC LIMIT 1"),
+        None => format!("{begin_query} ORDER BY toot_id DESC LIMIT 1"),
     };
 
     let mut stmt = conn.prepare(&query)?;
 
     let t = stmt
         .query_row([], |row| {
-            Ok(TweetToToot {
-                tweet_id: row.get("tweet_id")?,
+            Ok(TootRecord {
                 toot_id: row.get("toot_id")?,
+                record_uri: row.get("record_uri")?,
+                root_record_uri: row.get("root_record_uri")?,
+                datetime: Some(
+                    DateTime::from_timestamp(row.get("unix_datetime").unwrap(), 0).unwrap(),
+                ),
             })
         })
         .optional()?;
@@ -36,11 +70,11 @@ pub fn read_state(
 }
 
 /// Writes last treated tweet id and toot id to the db
-pub fn write_state(conn: &Connection, t: TweetToToot) -> Result<(), Box<dyn Error>> {
+pub fn write_state(conn: &Connection, t: TootRecord) -> Result<(), Box<dyn Error>> {
     debug!("Write struct {:?}", t);
     conn.execute(
-        "INSERT INTO tweet_to_toot (tweet_id, toot_id) VALUES (?1, ?2)",
-        params![t.tweet_id, t.toot_id],
+        "INSERT INTO toot_record (toot_id, record_uri, root_record_uri) VALUES (?1, ?2, ?3)",
+        params![t.toot_id, t.record_uri, t.root_record_uri],
     )?;
 
     Ok(())
@@ -55,9 +89,11 @@ pub fn init_db(d: &str) -> Result<(), Box<dyn Error>> {
     let conn = Connection::open(d)?;
 
     conn.execute(
-        "CREATE TABLE IF NOT EXISTS tweet_to_toot (
-            tweet_id            INTEGER,
-            toot_id             INTEGER PRIMARY KEY
+        "CREATE TABLE IF NOT EXISTS toot_record (
+            toot_id             INTEGER,
+            record_uri          VARCHAR(128) PRIMARY KEY,
+            root_record_uri     VARCHAR(128) DEFAULT '',
+            datetime            INTEGER DEFAULT CURRENT_TIMESTAMP
             )",
         [],
     )?;
@@ -65,6 +101,55 @@ pub fn init_db(d: &str) -> Result<(), Box<dyn Error>> {
     Ok(())
 }
 
+/// Migrate DB from 3+ to 4+
+pub fn migrate_db(d: &str) -> Result<(), Box<dyn Error>> {
+    debug!("Migration DB for Oolatoocs");
+
+    let conn = Connection::open(d)?;
+
+    let res = conn.execute("SELECT datetime FROM toot_record;", []);
+
+    // If the column can be selected then, it’s OK
+    // if not, see if the error is a missing column and add it
+    match res {
+        Err(e) => match e.to_string().as_str() {
+            "no such table: toot_record" => migrate_db_alter_table(&conn), // table does not exist
+            "Execute returned results - did you mean to call query?" => Ok(()), // return results,
+            // column does
+            // exist
+            _ => Err(e.into()),
+        },
+        Ok(_) => Ok(()),
+    }
+}
+
+/// Creates a new table, copy the data from the old table and rename it
+fn migrate_db_alter_table(c: &Connection) -> Result<(), Box<dyn Error>> {
+    // create the new table
+    c.execute(
+        "CREATE TABLE IF NOT EXISTS toot_record (
+            toot_id             INTEGER,
+            record_uri          VARCHAR(128) PRIMARY KEY,
+            root_record_uri     VARCHAR(128) DEFAULT '',
+            datetime            INTEGER DEFAULT CURRENT_TIMESTAMP
+            )",
+        [],
+    )?;
+
+    // copy data from the old table
+    c.execute(
+        "INSERT INTO toot_record (toot_id, record_uri, root_record_uri, datetime)
+        SELECT toot_id, record_uri, root_record_uri, datetime FROM toot_tweet_record
+        WHERE record_uri != '';",
+        [],
+    )?;
+
+    // drop the old table
+    c.execute("DROP TABLE IF EXISTS toot_tweet_record;", [])?;
+
+    Ok(())
+}
+
 #[cfg(test)]
 mod tests {
     use super::*;
@@ -81,7 +166,7 @@ mod tests {
 
         // open said file
         let conn = Connection::open(d).unwrap();
-        conn.execute("SELECT * from tweet_to_toot;", []).unwrap();
+        conn.execute("SELECT * from toot_record;", []).unwrap();
 
         remove_file(d).unwrap();
     }
@@ -96,9 +181,9 @@ mod tests {
         let conn = Connection::open(d).unwrap();
 
         conn.execute(
-            "INSERT INTO tweet_to_toot (tweet_id, toot_id)
+            "INSERT INTO toot_record (record_uri, toot_id)
             VALUES
-            (100, 1001);",
+            ('a', 1001);",
             [],
         )
         .unwrap();
@@ -116,26 +201,35 @@ mod tests {
 
         let conn = Connection::open(d).unwrap();
 
-        let t_in = TweetToToot {
-            tweet_id: 123456789,
+        let t_in = TootRecord {
             toot_id: 987654321,
+            record_uri: "a".to_string(),
+            root_record_uri: "c".to_string(),
+            datetime: None,
         };
 
         write_state(&conn, t_in).unwrap();
 
-        let mut stmt = conn.prepare("SELECT * FROM tweet_to_toot;").unwrap();
+        let mut stmt = conn
+            .prepare("SELECT *, UNIXEPOCH(datetime) AS unix_datetime FROM toot_record;")
+            .unwrap();
 
         let t_out = stmt
             .query_row([], |row| {
-                Ok(TweetToToot {
-                    tweet_id: row.get("tweet_id").unwrap(),
+                Ok(TootRecord {
                     toot_id: row.get("toot_id").unwrap(),
+                    record_uri: row.get("record_uri").unwrap(),
+                    root_record_uri: row.get("root_record_uri").unwrap(),
+                    datetime: Some(
+                        DateTime::from_timestamp(row.get("unix_datetime").unwrap(), 0).unwrap(),
+                    ),
                 })
             })
             .unwrap();
 
-        assert_eq!(t_out.tweet_id, 123456789);
         assert_eq!(t_out.toot_id, 987654321);
+        assert_eq!(t_out.record_uri, "a".to_string());
+        assert_eq!(t_out.root_record_uri, "c".to_string());
 
         remove_file(d).unwrap();
     }
@@ -149,10 +243,10 @@ mod tests {
         let conn = Connection::open(d).unwrap();
 
         conn.execute(
-            "INSERT INTO tweet_to_toot (tweet_id, toot_id)
+            "INSERT INTO toot_record (toot_id, record_uri)
             VALUES
-            (101, 1001),
-            (102, 1002);",
+            (101, 'abc'),
+            (102, 'def');",
             [],
         )
         .unwrap();
@@ -161,8 +255,8 @@ mod tests {
 
         remove_file(d).unwrap();
 
-        assert_eq!(t_out.tweet_id, 102);
-        assert_eq!(t_out.toot_id, 1002);
+        assert_eq!(t_out.toot_id, 102);
+        assert_eq!(t_out.record_uri, "def".to_string());
     }
 
     #[test]
@@ -189,9 +283,9 @@ mod tests {
         let conn = Connection::open(d).unwrap();
 
         conn.execute(
-            "INSERT INTO tweet_to_toot (tweet_id, toot_id)
+            "INSERT INTO toot_record (toot_id, record_uri)
             VALUES
-            (100, 1000);",
+            (100, 'abc');",
             [],
         )
         .unwrap();
@@ -212,9 +306,34 @@ mod tests {
         let conn = Connection::open(d).unwrap();
 
         conn.execute(
-            "INSERT INTO tweet_to_toot (tweet_id, toot_id)
+            "INSERT INTO toot_record (toot_id, record_uri)
             VALUES
-            (100, 1000);",
+            (100, 'abc');",
+            [],
+        )
+        .unwrap();
+
+        let t_out = read_state(&conn, Some(100)).unwrap().unwrap();
+
+        remove_file(d).unwrap();
+
+        assert_eq!(t_out.toot_id, 100);
+        assert_eq!(t_out.record_uri, "abc".to_string());
+    }
+
+    #[test]
+    fn test_last_toot_id_read_state() {
+        let d = "/tmp/test_last_toot_id_read_state.sqlite";
+
+        init_db(d).unwrap();
+
+        let conn = Connection::open(d).unwrap();
+
+        conn.execute(
+            "INSERT INTO toot_record (toot_id, record_uri)
+            VALUES
+            (1000, 'abc'),
+            (1000, 'def');",
             [],
         )
         .unwrap();
@@ -223,7 +342,126 @@ mod tests {
 
         remove_file(d).unwrap();
 
-        assert_eq!(t_out.tweet_id, 100);
         assert_eq!(t_out.toot_id, 1000);
+        assert_eq!(t_out.record_uri, "def".to_string());
+    }
+
+    #[test]
+    fn test_migrate_db() {
+        // this should be idempotent
+        let d = "/tmp/test_migrate_db.sqlite";
+
+        let conn = Connection::open(d).unwrap();
+        conn.execute(
+            "CREATE TABLE IF NOT EXISTS toot_tweet_record (
+            toot_id             INTEGER,
+            tweet_id            INTEGER PRIMARY KEY,
+            record_uri          VARCHAR(128) DEFAULT '',
+            root_record_uri     VARCHAR(128) DEFAULT '',
+            datetime            INTEGER DEFAULT CURRENT_TIMESTAMP
+            )",
+            [],
+        )
+        .unwrap();
+
+        conn.execute(
+            "INSERT INTO toot_tweet_record (tweet_id, toot_id, record_uri) VALUES (0, 0, ''), (1, 1, 'abc');",
+            [],
+        )
+        .unwrap();
+
+        migrate_db(d).unwrap();
+
+        let last_state = read_state(&conn, None).unwrap().unwrap();
+
+        assert_eq!(last_state.toot_id, 1);
+
+        migrate_db(d).unwrap(); // shouldn’t do anything
+
+        remove_file(d).unwrap();
+    }
+
+    #[test]
+    fn test_delete_state() {
+        let d = "/tmp/test_delete_state.sqlite";
+
+        init_db(d).unwrap();
+
+        let conn = Connection::open(d).unwrap();
+
+        conn.execute(
+            "INSERT INTO toot_record(toot_id, record_uri) VALUES (0, 'abc');",
+            [],
+        )
+        .unwrap();
+
+        delete_state(&conn, 0).unwrap();
+
+        let mut stmt = conn
+            .prepare("SELECT *, UNIXEPOCH(datetime) AS unix_datetime FROM toot_record;")
+            .unwrap();
+
+        let t_out = stmt.query_row([], |row| {
+            Ok(TootRecord {
+                toot_id: row.get("toot_id").unwrap(),
+                record_uri: row.get("record_uri").unwrap(),
+                root_record_uri: row.get("root_record_uri").unwrap(),
+                datetime: Some(
+                    DateTime::from_timestamp(row.get("unix_datetime").unwrap(), 0).unwrap(),
+                ),
+            })
+        });
+
+        assert!(t_out.is_err_and(|x| x == rusqlite::Error::QueryReturnedNoRows));
+
+        conn.execute(
+            "INSERT INTO toot_record(toot_id, record_uri) VALUES(42, 'abc'), (42, 'def');",
+            [],
+        )
+        .unwrap();
+
+        delete_state(&conn, 42).unwrap();
+
+        let mut stmt = conn
+            .prepare("SELECT *, UNIXEPOCH(datetime) AS unix_datetime FROM toot_record;")
+            .unwrap();
+
+        let t_out = stmt.query_row([], |row| {
+            Ok(TootRecord {
+                toot_id: row.get("toot_id").unwrap(),
+                record_uri: row.get("record_uri").unwrap(),
+                root_record_uri: row.get("root_record_uri").unwrap(),
+                datetime: Some(
+                    DateTime::from_timestamp(row.get("unix_datetime").unwrap(), 0).unwrap(),
+                ),
+            })
+        });
+
+        assert!(t_out.is_err_and(|x| x == rusqlite::Error::QueryReturnedNoRows));
+
+        remove_file(d).unwrap();
+    }
+
+    #[test]
+    fn test_read_all_state() {
+        let d = "/tmp/read_all_state.sqlite";
+
+        init_db(d).unwrap();
+
+        let conn = Connection::open(d).unwrap();
+
+        conn.execute(
+            "INSERT INTO toot_record (toot_id, record_uri) VALUES (42, 'abc'), (42, 'def'), (43, 'ghi');",
+            [],
+        )
+        .unwrap();
+
+        let record_v1 = read_all_state(&conn, 43).unwrap();
+        let record_v2 = read_all_state(&conn, 42).unwrap();
+
+        assert_eq!(record_v1, vec!["ghi".to_string()]);
+        assert_eq!(record_v2, vec!["abc".to_string(), "def".to_string()]);
+
+        remove_file(d).unwrap();
     }
 }

src/twitter.rs

@@ -1,70 +0,0 @@
-use crate::config::TwitterConfig;
-use oauth1_request::Token;
-use reqwest::Client;
-use serde::{Deserialize, Serialize};
-use std::error::Error;
-
-/// I don’t know, don’t ask me
-#[derive(oauth1_request::Request)]
-struct EmptyRequest {}
-
-#[derive(Serialize, Debug)]
-pub struct Tweet {
-    pub text: String,
-}
-
-#[derive(Deserialize, Debug)]
-pub struct TweetResponse {
-    pub data: TweetResponseData,
-}
-
-#[derive(Deserialize, Debug)]
-pub struct TweetResponseData {
-    pub id: String,
-}
-
-/// This function returns the OAuth1 Token object from TwitterConfig
-fn get_token(config: &TwitterConfig) -> Token {
-    oauth1_request::Token::from_parts(
-        config.consumer_key.to_string(),
-        config.consumer_secret.to_string(),
-        config.oauth_token.to_string(),
-        config.oauth_token_secret.to_string(),
-    )
-}
-
-/// This function uploads media from Mastodon to Twitter and returns the media id from Twitter
-#[allow(dead_code)]
-pub async fn upload_media(_u: &str) -> Result<u64, Box<dyn Error>> {
-    Ok(0)
-}
-
-/// This posts Tweets with all the associated medias
-pub async fn post_tweet(
-    config: &TwitterConfig,
-    content: &str,
-    _medias: &[u64],
-) -> Result<u64, Box<dyn Error>> {
-    let uri = "https://api.twitter.com/2/tweets";
-    let empty_request = EmptyRequest {}; // Why? Because fuck you, that’s why!
-    let token = get_token(config);
-
-    let tweet = Tweet {
-        text: content.to_string(),
-    };
-
-    let client = Client::new();
-    let res = client
-        .post(uri)
-        .header(
-            "Authorization",
-            oauth1_request::post(uri, &empty_request, &token, oauth1_request::HMAC_SHA1),
-        )
-        .json(&tweet)
-        .send()
-        .await?
-        .json::<TweetResponse>()
-        .await?;
-
-    Ok(res.data.id.parse::<u64>().unwrap())
-}

src/utils.rs

@@ -1,15 +1,59 @@
-use dissolve::strip_html_tags;
+use html_escape::decode_html_entities;
 use megalodon::entities::status::Tag;
 use regex::Regex;
 use std::error::Error;
 
+/// Generate 2 contents out of 1 if that content is > 300 chars, None else
+pub fn generate_multi_tweets(content: &str) -> Option<(String, String)> {
+    // Twitter webforms are utf-8 encoded, so we cannot count on len(), we don’t need
+    // encode_utf16().count()
+    if twitter_count(content) <= 300 {
+        return None;
+    }
+
+    let split_content = content.split(' ');
+
+    let split_count = split_content.clone().count();
+
+    let first_half: String = split_content
+        .clone()
+        .take(split_count / 2)
+        .collect::<Vec<_>>()
+        .join(" ");
+    let second_half: String = split_content
+        .clone()
+        .skip(split_count / 2)
+        .collect::<Vec<_>>()
+        .join(" ");
+
+    Some((first_half, second_half))
+}
+
+/// Twitter doesn’t count words the same we do, so you’ll have to improvise
+fn twitter_count(content: &str) -> usize {
+    let mut count = 0;
+
+    let split_content = content.split(&[' ', '\n']);
+    count += split_content.clone().count() - 1; // count the spaces
+
+    for word in split_content {
+        if word.starts_with("http://") || word.starts_with("https://") {
+            count += 23;
+        } else {
+            count += word.chars().count();
+        }
+    }
+
+    count
+}
+
 pub fn strip_everything(content: &str, tags: &Vec<Tag>) -> Result<String, Box<dyn Error>> {
-    let mut res =
-        strip_html_tags(&content.replace("</p><p>", "\n\n").replace("<br />", "\n")).join("");
+    let mut res = strip_html_tags(&content.replace("</p><p>", "\n\n").replace("<br />", "\n"));
 
     strip_mastodon_tags(&mut res, tags).unwrap();
 
     res = res.trim_end_matches('\n').trim_end_matches(' ').to_string();
+    res = decode_html_entities(&res).to_string();
 
     Ok(res)
 }
@@ -22,3 +66,124 @@ fn strip_mastodon_tags(content: &mut String, tags: &Vec<Tag>) -> Result<(), Box<
 
     Ok(())
 }
+
+fn strip_html_tags(input: &str) -> String {
+    let mut data = String::new();
+    let mut inside = false;
+
+    for c in input.chars() {
+        if c == '<' {
+            inside = true;
+            continue;
+        }
+        if c == '>' {
+            inside = false;
+            continue;
+        }
+        if !inside {
+            data.push(c);
+        }
+    }
+
+    data
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn test_twitter_count() {
+        let content = "tamerelol?! 🐵";
+
+        assert_eq!(twitter_count(content), content.chars().count());
+
+        let content = "Shoot out to https://y.ml/ !";
+
+        assert_eq!(twitter_count(content), 38);
+
+        let content = "this is the link https://www.google.com/tamerelol/youpi/tonperemdr/tarace.html if you like! What if I shit a final";
+
+        assert_eq!(twitter_count(content), 76);
+
+        let content = "multi  ple     space";
+
+        assert_eq!(twitter_count(content), content.chars().count());
+
+        let content = "This link is LEEEEET\n\nhttps://www.factornews.com/actualites/ca-sent-le-sapin-pour-free-radical-design-49985.html";
+
+        assert_eq!(twitter_count(content), 45);
+    }
+
+    #[test]
+    fn test_generate_multi_tweets_to_none() {
+        // test « standard » text
+        let tweet_content =
+            "LOLOLOL, je suis bien trop petit pour être coupé en deux voyons :troll:".to_string();
+
+        let youpi = generate_multi_tweets(&tweet_content);
+
+        assert_eq!(None, youpi);
+
+        // test with « complex » emoji (2 utf-8 chars)
+        let tweet_content = "🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷🇫🇷".to_string();
+
+        let youpi = generate_multi_tweets(&tweet_content);
+
+        assert_eq!(None, youpi);
+
+        // test with 299 chars
+        let tweet_content = "Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate vulver amico tio".to_string();
+
+        let youpi = generate_multi_tweets(&tweet_content);
+
+        assert_eq!(None, youpi);
+    }
+
+    #[test]
+    fn test_generate_multi_tweets_to_some() {
+        let tweet_content = "Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ipsum dolor sit amet consectetur adipiscing elit pellentesque. Pharetra pharetra massa massa ultricies mi quis hendrerit dolor. Mauris nunc congue nisi vitae. Scelerisque varius morbi enim nunc faucibus a pellentesque sit amet. Morbi leo urna molestie at elementum. Tristique et egestas quis ipsum suspendisse ultrices gravida dictum fusce. Amet porttitor eget dolor morbi.".to_string();
+
+        let youpi = generate_multi_tweets(&tweet_content);
+
+        let first_half = "Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ipsum dolor sit amet consectetur adipiscing elit pellentesque. Pharetra pharetra massa massa ultricies mi quis hendrerit dolor.".to_string();
+        let second_half = "Mauris nunc congue nisi vitae. Scelerisque varius morbi enim nunc faucibus a pellentesque sit amet. Morbi leo urna molestie at elementum. Tristique et egestas quis ipsum suspendisse ultrices gravida dictum fusce. Amet porttitor eget dolor morbi.".to_string();
+
+        assert_eq!(youpi, Some((first_half, second_half)));
+    }
+
+    #[test]
+    fn test_strip_mastodon_tags() {
+        let tags = vec![
+            Tag {
+                name: "putaclic".to_string(),
+                url: "https://m.nintendojo.fr/tags/putaclic".to_string(),
+            },
+            Tag {
+                name: "tamerelol".to_string(),
+                url: "https://m.nintendojo.fr/tags/tamerelol".to_string(),
+            },
+            Tag {
+                name: "JeFaisNawakEnCamelCase".to_string(),
+                url: "https://m.nintendojo.fr/tags/jefaisnawakencamelcase".to_string(),
+            },
+        ];
+
+        let mut content =
+            "C’est super ça ! #putaclic #TAMERELOL #JeFaisNawakEnCamelCase".to_string();
+        let sample = "C’est super ça ! ".to_string();
+
+        strip_mastodon_tags(&mut content, &tags).unwrap();
+
+        assert_eq!(content, sample);
+    }
+
+    #[test]
+    fn test_strip_everything() {
+        let content = "<p>Ce soir à 21h, c&#39;est le Dojobar ! Au programme ce soir, une rétrospective sur la série Mario &amp; Luigi.<br />Comme d&#39;hab, le Twitch sera ici : <a href=\"https://twitch.tv/nintendojofr\" target=\"_blank\" rel=\"nofollow noopener noreferrer\" translate=\"no\"><span class=\"invisible\">https://</span><span class=\"\">twitch.tv/nintendojofr</span><span class=\"invisible\"></span></a><br />Ou juste l&#39;audio là : <a href=\"https://nintendojo.fr/dojobar\" target=\"_blank\" rel=\"nofollow noopener noreferrer\" translate=\"no\"><span class=\"invisible\">https://</span><span class=\"\">nintendojo.fr/dojobar</span><span class=\"invisible\"></span></a><br />A toute !</p>";
+        let expected_result = "Ce soir à 21h, c'est le Dojobar ! Au programme ce soir, une rétrospective sur la série Mario & Luigi.\nComme d'hab, le Twitch sera ici : https://twitch.tv/nintendojofr\nOu juste l'audio là : https://nintendojo.fr/dojobar\nA toute !".to_string();
+        let result = strip_everything(content, &vec![]).unwrap();
+
+        assert_eq!(result, expected_result);
+    }
+}