Skip to content

Commit

Permalink
lsp: Use Path instead of String for path handling (#22762)
Browse files Browse the repository at this point in the history 
During my work on PR #22616, while trying to fix the
`test_reporting_fs_changes_to_language_servers` test case, I noticed
that we are currently handling paths using `String` in some places.
However, this approach causes issues on Windows.

This draft PR modifies `rebuild_watched_paths_inner` and
`glob_literal_prefix`. For example, take the `glob_literal_prefix`
function modified in this PR:

```rust
assert_eq!(
    glob_literal_prefix("node_modules/**/*.js"), 
    "node_modules"
);    // This works on Unix, fails on Windows

assert_eq!(
    glob_literal_prefix("node_modules\\**\\*.js"), 
    "node_modules"
);    // This works on Windows

assert_eq!(
    glob_literal_prefix("node_modules\\**/*.js"), 
    "node_modules"
);    // This fails on Windows
```

The current implementation treats path as `String` and relies on `\` as
the path separator on Windows, but on Windows, both `/` and `\` can be
used as separators. This means that `node_modules\**/*.js` is also a
valid path representation.

There are two potential solutions to this issue:

1. **Continue handling paths with `String`**, and on Windows, replace
all `/` with `\`.
2. **Use `Path` for path handling**, which is the solution implemented
in this PR.

### Advantages of Solution 1:
- Simple and direct.

### Advantages of Solution 2:
- More robust, especially in handling `strip_prefix`.

Currently, the logic for removing a path prefix looks like this:

```rust
let path = "/some/path/to/file.rs";
let parent = "/some/path/to";
// remove prefix
let file = path.strip_prefix(parent).unwrap();    // which is `/file.rs`
let file = file.strip_prefix("/").unwrap();
```

However, using `Path` simplifies this process and makes it more robust:

```rust
let path = Path::new("C:/path/to/src/main.rs");
let parent = Path::new("C:/path/to/src"); 
let file = path.strip_prefix(&parent).unwrap(); // which is `main.rs`

let path = Path::new("C:\\path\\to/src/main.rs");
let parent = Path::new("C:/path/to\\src\\"); 
let file = path.strip_prefix(&parent).unwrap(); // which is `main.rs`
```

Release Notes:

- N/A

---------

Co-authored-by: Kirill Bulatov <mail4score@gmail.com>
  • Loading branch information
@JunkuiZhang @SomeoneToIgnore
JunkuiZhang and SomeoneToIgnore authored Jan 19, 2025
1 parent 7578834 commit 7302be8
Show file tree
Hide file tree
Showing 2 changed files with 194 additions and 146 deletions.
256 changes: 140 additions & 116 deletions crates/project/src/lsp_store.rs
View file
Original file line number Diff line number Diff line change
Expand Up @@ -79,7 +79,8 @@ use std::{
};
use text::{Anchor, BufferId, LineEnding, OffsetRangeExt};
use util::{
debug_panic, defer, maybe, merge_json_value_into, post_inc, ResultExt, TryFutureExt as _,
debug_panic, defer, maybe, merge_json_value_into, paths::SanitizedPath, post_inc, ResultExt,
TryFutureExt as _,
};

pub use fs::*;
Expand Down Expand Up @@ -2546,112 +2547,119 @@ impl LocalLspStore {
let mut found_host = false;
for worktree in &worktrees {
let glob_is_inside_worktree = worktree.update(cx, |tree, _| {
if let Some(worktree_root_path) = tree.abs_path().to_str() {
let path_to_watch = match &watcher.glob_pattern {
lsp::GlobPattern::String(s) => {
match s.strip_prefix(worktree_root_path) {
Some(relative) => {
let pattern = relative
.strip_prefix(std::path::MAIN_SEPARATOR)
.unwrap_or(relative)
.to_owned();
let literal_prefix = glob_literal_prefix(&pattern);

let literal_prefix = Arc::from(PathBuf::from(
literal_prefix
.strip_prefix(std::path::MAIN_SEPARATOR)
.unwrap_or(literal_prefix),
));
PathToWatch::Worktree {
literal_prefix,
pattern,
}
let worktree_root_path = tree.abs_path();
let path_to_watch = match &watcher.glob_pattern {
lsp::GlobPattern::String(s) => {
let watcher_path = SanitizedPath::from(s);
match watcher_path.as_path().strip_prefix(&worktree_root_path) {
Ok(relative) => {
let pattern = relative.to_string_lossy().to_string();
let literal_prefix = glob_literal_prefix(relative).into();

PathToWatch::Worktree {
literal_prefix,
pattern,
}
None => {
let path = glob_literal_prefix(s);
let glob = &s[path.len()..];
let pattern = glob
.strip_prefix(std::path::MAIN_SEPARATOR)
.unwrap_or(glob)
.to_owned();
let path = if Path::new(path).components().next().is_none()
{
Arc::from(Path::new(worktree_root_path))
} else {
PathBuf::from(path).into()
};
}
Err(_) => {
let path = glob_literal_prefix(watcher_path.as_path());
let pattern = watcher_path
.as_path()
.strip_prefix(&path)
.map(|p| p.to_string_lossy().to_string())
.unwrap_or_else(|e| {
debug_panic!(
"Failed to strip prefix for string pattern: {}, with prefix: {}, with error: {}",
s,
path.display(),
e
);
watcher_path.as_path().to_string_lossy().to_string()
});
let path = if path.components().next().is_none() {
worktree_root_path.clone()
} else {
path.into()
};

PathToWatch::Absolute { path, pattern }
}
PathToWatch::Absolute { path, pattern }
}
}
lsp::GlobPattern::Relative(rp) => {
let Ok(mut base_uri) = match &rp.base_uri {
lsp::OneOf::Left(workspace_folder) => &workspace_folder.uri,
lsp::OneOf::Right(base_uri) => base_uri,
}
lsp::GlobPattern::Relative(rp) => {
let Ok(mut base_uri) = match &rp.base_uri {
lsp::OneOf::Left(workspace_folder) => &workspace_folder.uri,
lsp::OneOf::Right(base_uri) => base_uri,
}
.to_file_path() else {
return false;
};

match base_uri.strip_prefix(&worktree_root_path) {
Ok(relative) => {
let mut literal_prefix = relative.to_owned();
literal_prefix
.push(glob_literal_prefix(Path::new(&rp.pattern)));

PathToWatch::Worktree {
literal_prefix: literal_prefix.into(),
pattern: rp.pattern.clone(),
}
}
.to_file_path() else {
return false;
};

match base_uri.strip_prefix(worktree_root_path) {
Ok(relative) => {
let mut literal_prefix = relative.to_owned();
literal_prefix.push(glob_literal_prefix(&rp.pattern));
Err(_) => {
let path = glob_literal_prefix(Path::new(&rp.pattern));
let pattern = Path::new(&rp.pattern)
.strip_prefix(&path)
.map(|p| p.to_string_lossy().to_string())
.unwrap_or_else(|e| {
debug_panic!(
"Failed to strip prefix for relative pattern: {}, with prefix: {}, with error: {}",
rp.pattern,
path.display(),
e
);
rp.pattern.clone()
});
base_uri.push(path);

PathToWatch::Worktree {
literal_prefix: literal_prefix.into(),
pattern: rp.pattern.clone(),
}
}
Err(_) => {
let path = glob_literal_prefix(&rp.pattern);
let glob = &rp.pattern[path.len()..];
let pattern = glob
.strip_prefix(std::path::MAIN_SEPARATOR)
.unwrap_or(glob)
.to_owned();
base_uri.push(path);

let path = if base_uri.components().next().is_none() {
Arc::from(Path::new("/"))
} else {
base_uri.into()
};
PathToWatch::Absolute { path, pattern }
}
let path = if base_uri.components().next().is_none() {
debug_panic!("base_uri is empty, {}", base_uri.display());
worktree_root_path.clone()
} else {
base_uri.into()
};
PathToWatch::Absolute { path, pattern }
}
}
};
match path_to_watch {
PathToWatch::Worktree {
literal_prefix,
pattern,
} => {
if let Some((tree, glob)) =
tree.as_local_mut().zip(Glob::new(&pattern).log_err())
{
tree.add_path_prefix_to_scan(literal_prefix);
worktree_globs
.entry(tree.id())
.or_insert_with(GlobSetBuilder::new)
.add(glob);
} else {
return false;
}
}
};
match path_to_watch {
PathToWatch::Worktree {
literal_prefix,
pattern,
} => {
if let Some((tree, glob)) =
tree.as_local_mut().zip(Glob::new(&pattern).log_err())
{
tree.add_path_prefix_to_scan(literal_prefix);
worktree_globs
.entry(tree.id())
.or_insert_with(GlobSetBuilder::new)
.add(glob);
} else {
return false;
}
PathToWatch::Absolute { path, pattern } => {
if let Some(glob) = Glob::new(&pattern).log_err() {
abs_globs
.entry(path)
.or_insert_with(GlobSetBuilder::new)
.add(glob);
}
}
PathToWatch::Absolute { path, pattern } => {
if let Some(glob) = Glob::new(&pattern).log_err() {
abs_globs
.entry(path)
.or_insert_with(GlobSetBuilder::new)
.add(glob);
}
}
return true;
}
false
true
});
if glob_is_inside_worktree {
log::trace!(
Expand Down Expand Up @@ -8319,23 +8327,13 @@ impl DiagnosticSummary {
}
}

fn glob_literal_prefix(glob: &str) -> &str {
let is_absolute = glob.starts_with(path::MAIN_SEPARATOR);

let mut literal_end = is_absolute as usize;
for (i, part) in glob.split(path::MAIN_SEPARATOR).enumerate() {
if part.contains(['*', '?', '{', '}']) {
break;
} else {
if i > 0 {
// Account for separator prior to this part
literal_end += path::MAIN_SEPARATOR.len_utf8();
}
literal_end += part.len();
}
}
let literal_end = literal_end.min(glob.len());
&glob[..literal_end]
fn glob_literal_prefix(glob: &Path) -> PathBuf {
glob.components()
.take_while(|component| match component {
path::Component::Normal(part) => !part.to_string_lossy().contains(['*', '?', '{', '}']),
_ => true,
})
.collect()
}

pub struct SshLspAdapter {
Expand Down Expand Up @@ -8715,8 +8713,34 @@ fn include_text(server: &lsp::LanguageServer) -> Option<bool> {
#[cfg(test)]
#[test]
fn test_glob_literal_prefix() {
assert_eq!(glob_literal_prefix("**/*.js"), "");
assert_eq!(glob_literal_prefix("node_modules/**/*.js"), "node_modules");
assert_eq!(glob_literal_prefix("foo/{bar,baz}.js"), "foo");
assert_eq!(glob_literal_prefix("foo/bar/baz.js"), "foo/bar/baz.js");
assert_eq!(glob_literal_prefix(Path::new("**/*.js")), Path::new(""));
assert_eq!(
glob_literal_prefix(Path::new("node_modules/**/*.js")),
Path::new("node_modules")
);
assert_eq!(
glob_literal_prefix(Path::new("foo/{bar,baz}.js")),
Path::new("foo")
);
assert_eq!(
glob_literal_prefix(Path::new("foo/bar/baz.js")),
Path::new("foo/bar/baz.js")
);

#[cfg(target_os = "windows")]
{
assert_eq!(glob_literal_prefix(Path::new("**\\*.js")), Path::new(""));
assert_eq!(
glob_literal_prefix(Path::new("node_modules\\**/*.js")),
Path::new("node_modules")
);
assert_eq!(
glob_literal_prefix(Path::new("foo/{bar,baz}.js")),
Path::new("foo")
);
assert_eq!(
glob_literal_prefix(Path::new("foo\\bar\\baz.js")),
Path::new("foo/bar/baz.js")
);
}
}
Loading

0 comments on commit 7302be8

Please sign in to comment.