Generalised to multiple runtime directories with priorities (#5411)

* Generalised to multiple runtime directories with priorities

This is an implementation for #3346.

Previously, one of the following runtime directories were used:

1. `$HELIX_RUNTIME`
2. sibling directory to `$CARGO_MANIFEST_DIR`
3. subdirectory of user config directory
4. subdirectory of path to helix executable

The first directory provided / found to exist in this order was used as a
root for all runtime file searches (grammars, themes, queries).

This change lowers the priority of `$HELIX_RUNTIME` so that the user
config runtime has higher priority. More significantly, all of these
directories are now searched for runtime files, enabling a user to override
default or system-level runtime files. If the same file name appears
in multiple runtime directories, the following priority is now used:

1. sibling directory to `$CARGO_MANIFEST_DIR`
2. subdirectory of user config directory
3. `$HELIX_RUNTIME`
4. subdirectory of path to helix executable

One exception to this rule is that a user can have a `themes`
directory directly in the user config directory that has higher piority
to `themes` directories in runtime directories. That behaviour has been
preserved.

As part of implementing this feature `theme::Loader` was simplified
and the cycle detection logic of the theme inheritance was improved to
cover more cases and to be more explicit.

* Removed AsRef usage to avoid binary growth

* Health displaying ;-separated runtime dirs

* Changed HELIX_RUNTIME build from src instructions

* Updated doc for more detail on runtime directories

* Improved health symlink printing and theme cycle errors

The health display of runtime symlinks now prints both ends of the
link.

Separate errors are given when theme file is not found and when the
only theme file found would form an inheritence cycle.

* Satisfied clippy on passing Path

* Clarified highest priority runtime directory purpose

* Further clarified multiple runtime details in book

Also gave markdown headings to subsections.

Fixed a error with table indentation not building
table that also appears present on master.

---------

Co-authored-by: Paul Scott <paul.scott@anu.edu.au>
Co-authored-by: Blaž Hrastnik <blaz@mxxn.io>

2 files changed, 81 insertions, 23 deletions

diff --git a/helix-loader/src/grammar.rs b/helix-loader/src/grammar.rs
index 01c966c8..a85cb274 100644
--- a/helix-loader/src/grammar.rs
+++ b/helix-loader/src/grammar.rs
@@ -67,8 +67,9 @@ pub fn get_language(name: &str) -> Result<Language> {
 #[cfg(not(target_arch = "wasm32"))]
 pub fn get_language(name: &str) -> Result<Language> {
     use libloading::{Library, Symbol};
-    let mut library_path = crate::runtime_dir().join("grammars").join(name);
-    library_path.set_extension(DYLIB_EXTENSION);
+    let mut rel_library_path = PathBuf::new().join("grammars").join(name);
+    rel_library_path.set_extension(DYLIB_EXTENSION);
+    let library_path = crate::runtime_file(&rel_library_path);
 
     let library = unsafe { Library::new(&library_path) }
         .with_context(|| format!("Error opening dynamic library {:?}", library_path))?;
@@ -252,7 +253,9 @@ fn fetch_grammar(grammar: GrammarConfiguration) -> Result<FetchStatus> {
         remote, revision, ..
     } = grammar.source
     {
-        let grammar_dir = crate::runtime_dir()
+        let grammar_dir = crate::runtime_dirs()
+            .first()
+            .expect("No runtime directories provided") // guaranteed by post-condition
             .join("grammars")
             .join("sources")
             .join(&grammar.grammar_id);
@@ -350,7 +353,9 @@ fn build_grammar(grammar: GrammarConfiguration, target: Option<&str>) -> Result<
     let grammar_dir = if let GrammarSource::Local { path } = &grammar.source {
         PathBuf::from(&path)
     } else {
-        crate::runtime_dir()
+        crate::runtime_dirs()
+            .first()
+            .expect("No runtime directories provided") // guaranteed by post-condition
             .join("grammars")
             .join("sources")
             .join(&grammar.grammar_id)
@@ -401,7 +406,10 @@ fn build_tree_sitter_library(
             None
         }
     };
-    let parser_lib_path = crate::runtime_dir().join("grammars");
+    let parser_lib_path = crate::runtime_dirs()
+        .first()
+        .expect("No runtime directories provided") // guaranteed by post-condition
+        .join("grammars");
     let mut library_path = parser_lib_path.join(&grammar.grammar_id);
     library_path.set_extension(DYLIB_EXTENSION);
 
@@ -511,9 +519,6 @@ fn mtime(path: &Path) -> Result<SystemTime> {
 /// Gives the contents of a file from a language's `runtime/queries/<lang>`
 /// directory
 pub fn load_runtime_file(language: &str, filename: &str) -> Result<String, std::io::Error> {
-    let path = crate::RUNTIME_DIR
-        .join("queries")
-        .join(language)
-        .join(filename);
+    let path = crate::runtime_file(&PathBuf::new().join("queries").join(language).join(filename));
     std::fs::read_to_string(path)
 }
diff --git a/helix-loader/src/lib.rs b/helix-loader/src/lib.rs
index 8dc2928a..04b44b5a 100644
--- a/helix-loader/src/lib.rs
+++ b/helix-loader/src/lib.rs
@@ -2,11 +2,12 @@ pub mod config;
 pub mod grammar;
 
 use etcetera::base_strategy::{choose_base_strategy, BaseStrategy};
-use std::path::PathBuf;
+use std::path::{Path, PathBuf};
 
 pub const VERSION_AND_GIT_HASH: &str = env!("VERSION_AND_GIT_HASH");
 
-pub static RUNTIME_DIR: once_cell::sync::Lazy<PathBuf> = once_cell::sync::Lazy::new(runtime_dir);
+static RUNTIME_DIRS: once_cell::sync::Lazy<Vec<PathBuf>> =
+    once_cell::sync::Lazy::new(prioritize_runtime_dirs);
 
 static CONFIG_FILE: once_cell::sync::OnceCell<PathBuf> = once_cell::sync::OnceCell::new();
 
@@ -25,31 +26,83 @@ pub fn initialize_config_file(specified_file: Option<PathBuf>) {
     CONFIG_FILE.set(config_file).ok();
 }
 
-pub fn runtime_dir() -> PathBuf {
-    if let Ok(dir) = std::env::var("HELIX_RUNTIME") {
-        return dir.into();
-    }
-
+/// A list of runtime directories from highest to lowest priority
+///
+/// The priority is:
+///
+/// 1. sibling directory to `CARGO_MANIFEST_DIR` (if environment variable is set)
+/// 2. subdirectory of user config directory (always included)
+/// 3. `HELIX_RUNTIME` (if environment variable is set)
+/// 4. subdirectory of path to helix executable (always included)
+///
+/// Postcondition: returns at least two paths (they might not exist).
+fn prioritize_runtime_dirs() -> Vec<PathBuf> {
+    const RT_DIR: &str = "runtime";
+    // Adding higher priority first
+    let mut rt_dirs = Vec::new();
     if let Ok(dir) = std::env::var("CARGO_MANIFEST_DIR") {
         // this is the directory of the crate being run by cargo, we need the workspace path so we take the parent
         let path = std::path::PathBuf::from(dir).parent().unwrap().join(RT_DIR);
         log::debug!("runtime dir: {}", path.to_string_lossy());
-        return path;
+        rt_dirs.push(path);
     }
 
-    const RT_DIR: &str = "runtime";
-    let conf_dir = config_dir().join(RT_DIR);
-    if conf_dir.exists() {
-        return conf_dir;
+    let conf_rt_dir = config_dir().join(RT_DIR);
+    rt_dirs.push(conf_rt_dir);
+
+    if let Ok(dir) = std::env::var("HELIX_RUNTIME") {
+        rt_dirs.push(dir.into());
     }
 
     // fallback to location of the executable being run
     // canonicalize the path in case the executable is symlinked
-    std::env::current_exe()
+    let exe_rt_dir = std::env::current_exe()
         .ok()
         .and_then(|path| std::fs::canonicalize(path).ok())
         .and_then(|path| path.parent().map(|path| path.to_path_buf().join(RT_DIR)))
-        .unwrap()
+        .unwrap();
+    rt_dirs.push(exe_rt_dir);
+    rt_dirs
+}
+
+/// Runtime directories ordered from highest to lowest priority
+///
+/// All directories should be checked when looking for files.
+///
+/// Postcondition: returns at least one path (it might not exist).
+pub fn runtime_dirs() -> &'static [PathBuf] {
+    &RUNTIME_DIRS
+}
+
+/// Find file with path relative to runtime directory
+///
+/// `rel_path` should be the relative path from within the `runtime/` directory.
+/// The valid runtime directories are searched in priority order and the first
+/// file found to exist is returned, otherwise None.
+fn find_runtime_file(rel_path: &Path) -> Option<PathBuf> {
+    RUNTIME_DIRS.iter().find_map(|rt_dir| {
+        let path = rt_dir.join(rel_path);
+        if path.exists() {
+            Some(path)
+        } else {
+            None
+        }
+    })
+}
+
+/// Find file with path relative to runtime directory
+///
+/// `rel_path` should be the relative path from within the `runtime/` directory.
+/// The valid runtime directories are searched in priority order and the first
+/// file found to exist is returned, otherwise the path to the final attempt
+/// that failed.
+pub fn runtime_file(rel_path: &Path) -> PathBuf {
+    find_runtime_file(rel_path).unwrap_or_else(|| {
+        RUNTIME_DIRS
+            .last()
+            .map(|dir| dir.join(rel_path))
+            .unwrap_or_default()
+    })
 }
 
 pub fn config_dir() -> PathBuf {