feat: split toot into 2 tweets when necessary

src/utils.rs

@@ -3,6 +3,50 @@ use megalodon::entities::status::Tag;
 use regex::Regex;
 use std::error::Error;
 
+/// Generate 2 contents out of 1 if that content is > 280 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) <= 280 {
+        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(' ');
+    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"));
 
@@ -48,6 +92,51 @@ fn strip_html_tags(input: &str) -> String {
 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);
+    }
+
+    #[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]
+    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![