From 2d7315676b40cbce8eb3d33a390410d2bc68b41b Mon Sep 17 00:00:00 2001
From: Thomas Hurst <tom@hur.st>
Date: Wed, 12 Sep 2018 23:52:51 +0100
Subject: [PATCH 1/2] Use a HashSet for detecting orphan pages

This offers a big performance bump for large sites:

  small-kb (100 pages)
    before: 530ms
     after: 500ms

  medium-kb (1000 pages)
    before: 2.9s
     after: 1.5s

  huge-kb (10,000 pages)
    before: 150s
     after:   9.1s
---
 components/site/src/lib.rs | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/components/site/src/lib.rs b/components/site/src/lib.rs
index 29d59167..f5a72a4a 100644
--- a/components/site/src/lib.rs
+++ b/components/site/src/lib.rs
@@ -21,7 +21,7 @@ extern crate imageproc;
 #[cfg(test)]
 extern crate tempfile;
 
-use std::collections::HashMap;
+use std::collections::{HashMap, HashSet};
 use std::fs::{create_dir_all, remove_dir_all, copy};
 use std::mem;
 use std::path::{Path, PathBuf};
@@ -149,7 +149,7 @@ impl Site {
 
     /// Get all the orphan (== without section) pages in the site
     pub fn get_all_orphan_pages(&self) -> Vec<&Page> {
-        let mut pages_in_sections = vec![];
+        let mut pages_in_sections = HashSet::new();
         let mut orphans = vec![];
 
         for s in self.sections.values() {

From 34d17e613df49f3c09490b16c7c778724682c90c Mon Sep 17 00:00:00 2001
From: Thomas Hurst <tom@hur.st>
Date: Thu, 13 Sep 2018 00:23:49 +0100
Subject: [PATCH 2/2] Make get_all_orphan_pages more idiomatic

---
 components/site/src/lib.rs | 21 ++++++++-------------
 1 file changed, 8 insertions(+), 13 deletions(-)

diff --git a/components/site/src/lib.rs b/components/site/src/lib.rs
index f5a72a4a..ba70aef9 100644
--- a/components/site/src/lib.rs
+++ b/components/site/src/lib.rs
@@ -149,20 +149,15 @@ impl Site {
 
     /// Get all the orphan (== without section) pages in the site
     pub fn get_all_orphan_pages(&self) -> Vec<&Page> {
-        let mut pages_in_sections = HashSet::new();
-        let mut orphans = vec![];
+        let pages_in_sections = self.sections
+            .values()
+            .flat_map(|s| s.all_pages_path())
+            .collect::<HashSet<_>>();
 
-        for s in self.sections.values() {
-            pages_in_sections.extend(s.all_pages_path());
-        }
-
-        for page in self.pages.values() {
-            if !pages_in_sections.contains(&page.file.path) {
-                orphans.push(page);
-            }
-        }
-
-        orphans
+        self.pages
+            .values()
+            .filter(|page| !pages_in_sections.contains(&page.file.path))
+            .collect()
     }
 
     pub fn set_base_url(&mut self, base_url: String) {