Clean up code

src/main.rs

@@ -17,44 +17,42 @@ use rayon::prelude::*;
 
 fn main() -> Result<(), Box<dyn Error>> {
     simple_logger::init_with_level(log::Level::Info).unwrap();
+    let main_post_count = 24;
+    let archive_size = 100;
 
-    let all_posts = utilities::read_feed("feeds.txt");
+    let mut all_posts = utilities::read_feed("feeds.txt");
+
+    // Give featured a small boost in points
+    let featured = utilities::read_feed("featured_feeds.txt")
+        .iter_mut()
+        .map(|post| {
+            post.score += post.score / 2;
+            post.clone()
+        })
+        .collect::<Vec<_>>();
+
+    all_posts.extend(featured);
 
     let mut posts = all_posts.clone();
     posts.retain(|post| post.score.is_positive());
 
+    posts.par_iter_mut().for_each(utilities::validate);
+
+    posts.sort();
+
+    // Move the post with an image_url to the head of the list which is the featured post
+    if let Some(pos) = posts.iter().position(|post| post.image_url.is_some()) {
+        let post_with_image = posts.remove(pos);
+        posts.insert(0, post_with_image);
+    }
+
     // Keep only the first occurence of each main_url
     {
         let mut seen_urls = HashSet::new();
         posts.retain(|post| seen_urls.insert(post.main_url.clone()));
     }
 
-    let mut featured = utilities::read_feed("featured_feeds.txt");
-    // Give featured a small boost in points
-    featured = featured
-        .iter_mut()
-        .map(|post| {
-            post.score = (post.score as f64 * 1.5) as i64;
-            post.clone()
-        })
-        .collect::<Vec<_>>();
-
-    posts.extend(featured);
-
-    posts.par_iter_mut().for_each(utilities::find_image);
-    posts.par_iter_mut().for_each(utilities::validate);
-
-    posts.sort();
-
-    // Move the post with an image_url to the head of the list
-    if let Some(pos) = posts.iter().position(|post| post.image_url.is_some()) {
-        let post_with_image = posts.remove(pos);
-        posts.insert(0, post_with_image);
-    }
-
-    utilities::retain_most_recent_based_on_main_url(&mut posts);
-
-    posts.truncate(24);
+    posts.truncate(main_post_count);
 
     let mut old_posts = all_posts;
 
@@ -62,7 +60,6 @@ fn main() -> Result<(), Box<dyn Error>> {
     old_posts.shuffle(&mut thread_rng());
 
     let mut archive_posts: Vec<utilities::Post> = Vec::new();
-    let archive_size = 100;
 
     while (archive_posts.len() < archive_size) && (old_posts.len() > 50) {
         let iter_size = archive_size - archive_posts.len();

src/site_generator.rs

@@ -100,7 +100,7 @@ fn generate_header() -> Markup {
                                 li { a href="#" data-theme-switcher="auto" { "Auto" }}
                                 li { a href="#" data-theme-switcher="light" { "Light" }}
                                 li { a href="#" data-theme-switcher="dark" { "Dark" }}
-                            
+
                             }
                         }
                     }

src/utilities.rs

@@ -3,7 +3,6 @@ use chrono::{DateTime, Utc};
 use feed_rs::model::Entry;
 use rayon::prelude::*;
 use scraper::{Html, Selector};
-use std::collections::HashSet;
 
 use anyhow::Result;
 use html_escape::decode_html_entities;
@@ -216,6 +215,44 @@ pub fn group_by_nth<T: Clone>(slice: &[T], n: usize) -> Vec<Vec<T>> {
         .collect()
 }
 
+pub fn validate(post: &mut Post) {
+    if post.title.is_empty() {
+        post.score = 0;
+        println!("{} has no title", post.link.as_str());
+        return;
+    }
+
+    if !post.lang.is_empty() && post.lang != "en" {
+        post.score = 0;
+        println!("{} is not english", post.link.as_str());
+        return;
+    }
+
+    if post.truncated_description.is_empty() {
+        post.score = post.score / 2;
+    };
+
+    if !is_valid_url(post.link.as_str()) {
+        post.score = 0;
+        println!("post link {} is not valid", post.link.as_str());
+        return;
+    };
+
+    if !is_valid_url(&("http://".to_owned() + post.main_url.as_str())) {
+        post.score = 0;
+        println!("main_url {} is not valid", post.main_url.as_str());
+        return;
+    };
+
+    find_image(post);
+
+    if let Some(image_url) = &post.image_url {
+        if image_url.ends_with("favicon.ico") {
+            post.image_url = None;
+        }
+    }
+}
+
 pub fn find_image(post: &mut Post) {
     if let Some(image_url) = &post.image_url {
         match web_fetchers::is_valid_image_url(image_url) {
@@ -238,44 +275,3 @@ pub fn find_image(post: &mut Post) {
         }
     }
 }
-
-pub fn validate(post: &mut Post) {
-    if post.title.is_empty() {
-        post.score = 0;
-        println!("{} has no title", post.link.as_str());
-        return;
-    }
-
-    if !post.lang.is_empty() && post.lang != "en" {
-        post.score = 0;
-        println!("{} is not english", post.link.as_str());
-        return;
-    }
-
-    if post.truncated_description.is_empty() {
-        post.score = (post.score as f64 * 0.5) as i64;
-    };
-
-    if !is_valid_url(post.link.as_str()) {
-        post.score = 0;
-        println!("post link {} is not valid", post.link.as_str());
-        return;
-    };
-
-    if !is_valid_url(&("http://".to_owned() + post.main_url.as_str())) {
-        post.score = 0;
-        println!("main_url {} is not valid", post.main_url.as_str());
-        return;
-    };
-
-    if let Some(image_url) = &post.image_url {
-        if image_url.ends_with("favicon.ico") {
-            post.image_url = None;
-        }
-    }
-}
-
-pub fn retain_most_recent_based_on_main_url(posts: &mut Vec<Post>) {
-    let mut seen_urls = HashSet::new();
-    posts.retain(|post| seen_urls.insert(post.main_url.clone()));
-}