Upstream Pagefind/pagefind state of the touched files before f1eedafd11

pagefind/src/fossick/mod.rs

@@ -7,7 +7,6 @@ use hashbrown::HashMap;
 use lazy_static::lazy_static;
 use pagefind_stem::{Algorithm, Stemmer};
 use path_slash::PathExt as _;
-use percent_encoding::{utf8_percent_encode, AsciiSet, CONTROLS};
 use regex::Regex;
 use std::collections::BTreeMap;
 use std::io::BufRead;
@@ -590,20 +589,6 @@ impl Fossicker {
 
 }
 
-/// The URL spec's path percent-encode set, minus `/` so that the separators
-/// between the path segments survive. `%` is deliberately left alone, so a file
-/// that is already named in encoded form keeps the URL it has today.
-const PATH_ENCODE_SET: &AsciiSet = &CONTROLS
-    .add(b' ')
-    .add(b'"')
-    .add(b'#')
-    .add(b'<')
-    .add(b'>')
-    .add(b'?')
-    .add(b'`')
-    .add(b'{')
-    .add(b'}');
-
 fn strip_index_html(url: &str) -> &str {
     if url.ends_with("/index.html") {
         &url[..url.len() - 10]
@@ -636,7 +621,13 @@ fn build_url(page_url: &Path, relative_to: Option<&Path>, options: &SearchOption
         url.to_slash_lossy().to_owned().to_string()
     };
 
-    format!("/{}", utf8_percent_encode(&final_url, PATH_ENCODE_SET))
+    format!(
+        "/{}",
+        final_url
+            .replace('%', "%25")
+            .replace('#', "%23")
+            .replace('?', "%3F")
+    )
 }
 
 fn normalize_content(content: &str) -> String {
@@ -1260,29 +1251,9 @@ mod tests {
         let p: PathBuf = cwd.join::<PathBuf>("hello/world/index.html".into());
         let root: PathBuf = cwd.join::<PathBuf>("hello".into());
         assert_eq!(&build_url(&p, Some(&root), &opts), "/world/");
-    }
 
-    #[cfg(not(target_os = "windows"))]
-    #[test]
-    fn building_urls_with_characters_that_need_encoding() {
-        std::env::set_var("PAGEFIND_SITE", "hello/world");
-        let config =
-            PagefindInboundConfig::with_layers(&[Layer::Env(Some("PAGEFIND_".into()))]).unwrap();
-        let opts = SearchOptions::load(config).unwrap();
-
-        let cwd = std::env::current_dir().unwrap();
-
-        let p: PathBuf = cwd.join::<PathBuf>("hello/world/Müsli.html".into());
-        assert_eq!(&build_url(&p, None, &opts), "/M%C3%BCsli.html");
-
-        let p: PathBuf = cwd.join::<PathBuf>("hello/world/Müsli/index.html".into());
-        assert_eq!(&build_url(&p, None, &opts), "/M%C3%BCsli/");
-
-        let p: PathBuf = cwd.join::<PathBuf>("hello/world/a b/c#d?e.html".into());
-        assert_eq!(&build_url(&p, None, &opts), "/a%20b/c%23d%3Fe.html");
-
-        let p: PathBuf = cwd.join::<PathBuf>("hello/world/M%C3%BCsli.html".into());
-        assert_eq!(&build_url(&p, None, &opts), "/M%C3%BCsli.html");
+        let p: PathBuf = cwd.join::<PathBuf>("hello/world/100%/C#/why?.html".into());
+        assert_eq!(&build_url(&p, None, &opts), "/100%25/C%23/why%3F.html");
     }
 
     #[cfg(target_os = "windows")]

pagefind/src/options.rs

@@ -4,7 +4,7 @@ use anyhow::{bail, Result};
 use clap::Parser;
 use rust_patch::Patch;
 use serde::{Deserialize, Serialize};
-use std::{collections::BTreeMap, env, path::PathBuf};
+use std::{env, path::PathBuf};
 use twelf::config;
 use typed_builder::TypedBuilder;
 
@@ -22,15 +22,6 @@ use crate::{
 // No options should be added that are required.
 //
 
-/// A selector paired with the Pagefind attributes to set on the elements it matches,
-/// so a site can be configured with the same vocabulary its HTML would use.
-#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, Eq, Default)]
-pub(crate) struct PagefindRule {
-    pub(crate) selector: String,
-    #[serde(default)]
-    pub(crate) attributes: BTreeMap<String, String>,
-}
-
 #[config]
 #[derive(Parser, Debug, Clone)]
 #[clap(author, version, about, long_about = None)]
@@ -83,11 +74,6 @@ pub(crate) struct PagefindInboundConfig {
     #[serde(default)]
     pub(crate) exclude_selectors: Vec<String>,
 
-    /// Not a CLI flag: a list of selectors with attribute maps does not fit an argument.
-    #[clap(skip)]
-    #[serde(default)]
-    pub(crate) rules: Vec<PagefindRule>,
-
     #[clap(
         long,
         help = "The file glob Pagefind uses to find HTML files. Defaults to \"**/*.{html}\""
@@ -241,7 +227,6 @@ pub(crate) struct SearchOptions {
     pub(crate) bundle_output: PathBuf,
     pub(crate) root_selector: String,
     pub(crate) exclude_selectors: Vec<String>,
-    pub(crate) rules: Vec<PagefindRule>,
     pub(crate) glob: String,
     pub(crate) force_language: Option<String>,
     pub(crate) include_characters: Vec<char>,
@@ -323,7 +308,6 @@ impl SearchOptions {
                 bundle_output,
                 root_selector: config.root_selector,
                 exclude_selectors: config.exclude_selectors,
-                rules: config.rules,
                 glob: config.glob,
                 force_language: config.force_language,
                 include_characters,