From 93e2b45fd5fca966ec477b7ec80173746010e064 Mon Sep 17 00:00:00 2001
From: Martin Vassor <martin.vassor@alumni.epfl.ch>
Date: Fri, 19 Jul 2024 11:19:06 +0100
Subject: [PATCH] Add feature to disable robots.txt and sitemap.xml from the
 config file.

Addresses feature request #2248
---
 components/config/src/config/mod.rs | 41 +++++++++++++++++++++++++++++
 components/site/src/lib.rs          | 12 ++++++---
 2 files changed, 49 insertions(+), 4 deletions(-)

diff --git a/components/config/src/config/mod.rs b/components/config/src/config/mod.rs
index 57ff1a805..467eabec1 100644
--- a/components/config/src/config/mod.rs
+++ b/components/config/src/config/mod.rs
@@ -98,6 +98,10 @@ pub struct Config {
     pub markdown: markup::Markdown,
     /// All user params set in `[extra]` in the config
     pub extra: HashMap<String, Toml>,
+    /// Disable the generation of Sitemap.xml
+    pub no_sitemap: bool,
+    /// Disable the generation of robots.txt
+    pub no_robots: bool,
 }
 
 #[derive(Serialize)]
@@ -117,6 +121,8 @@ pub struct SerializedConfig<'a> {
     extra: &'a HashMap<String, Toml>,
     markdown: &'a markup::Markdown,
     search: search::SerializedSearch<'a>,
+    no_sitemap: bool,
+    no_robots: bool,
 }
 
 impl Config {
@@ -332,6 +338,8 @@ impl Config {
             extra: &self.extra,
             markdown: &self.markdown,
             search: self.search.serialize(),
+            no_sitemap: self.no_sitemap,
+            no_robots: self.no_robots,
         }
     }
 }
@@ -395,6 +403,8 @@ impl Default for Config {
             search: search::Search::default(),
             markdown: markup::Markdown::default(),
             extra: HashMap::new(),
+            no_sitemap: false,
+            no_robots: false,
         }
     }
 }
@@ -992,4 +1002,35 @@ feed_filename = "test.xml"
 
         Config::parse(config).unwrap();
     }
+
+    #[test]
+    fn parse_no_sitemap() {
+        let config = r#"
+title = "My Site"
+base_url = "example.com"
+no_sitemap = true
+"#;
+        let config = Config::parse(config).unwrap();
+        assert!(config.no_sitemap);
+    }
+
+    #[test]
+    fn default_no_sitemap_false() {
+        let config = r#"
+title = "My Site"
+base_url = "example.com"
+"#;
+        let config = Config::parse(config).unwrap();
+        assert!(!config.no_sitemap);
+    }
+
+    #[test]
+    fn default_no_robots_false() {
+        let config = r#"
+title = "My Site"
+base_url = "example.com"
+"#;
+        let config = Config::parse(config).unwrap();
+        assert!(!config.no_robots);
+    }
 }
diff --git a/components/site/src/lib.rs b/components/site/src/lib.rs
index 46c62c959..27a332dc3 100644
--- a/components/site/src/lib.rs
+++ b/components/site/src/lib.rs
@@ -742,8 +742,10 @@ impl Site {
         start = log_time(start, "Rendered sections");
         self.render_orphan_pages()?;
         start = log_time(start, "Rendered orphan pages");
-        self.render_sitemap()?;
-        start = log_time(start, "Rendered sitemap");
+        if !self.config.no_sitemap {
+            self.render_sitemap()?;
+            start = log_time(start, "Rendered sitemap");
+        }
 
         let library = self.library.read().unwrap();
         if self.config.generate_feeds {
@@ -769,8 +771,10 @@ impl Site {
         start = log_time(start, "Rendered themes css");
         self.render_404()?;
         start = log_time(start, "Rendered 404");
-        self.render_robots()?;
-        start = log_time(start, "Rendered robots.txt");
+        if !self.config.no_robots {
+            self.render_robots()?;
+            start = log_time(start, "Rendered robots.txt");
+        }
         self.render_taxonomies()?;
         start = log_time(start, "Rendered taxonomies");
         // We process images at the end as we might have picked up images to process from markdown