Skip to content

Fix: Avoid indexing extensionless files #19

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
echobt wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Fix: Avoid indexing extensionless files #19

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
118 changes: 118 additions & 0 deletions src/core/index_filter.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,118 @@
use std::fs;
use std::path::Path;

pub(crate) fn should_index_path(path: &Path, max_file_size: u64) -> bool {
if let Ok(metadata) = fs::metadata(path) {
if metadata.len() > max_file_size {
return false;
}
}

let ext = path
.extension()
.and_then(|e| e.to_str())
.unwrap_or("")
.to_lowercase();

matches!(
ext.as_str(),
"rs" | "py"
| "js"
| "ts"
| "tsx"
| "jsx"
| "go"
| "c"
| "cpp"
| "h"
| "hpp"
| "java"
| "kt"
| "swift"
| "rb"
| "php"
| "cs"
| "fs"
| "scala"
| "clj"
| "ex"
| "exs"
| "erl"
| "hs"
| "ml"
| "lua"
| "r"
| "jl"
| "dart"
| "vue"
| "svelte"
| "astro"
| "html"
| "htm"
| "css"
| "scss"
| "sass"
| "less"
| "json"
| "yaml"
| "yml"
| "toml"
| "xml"
| "md"
| "markdown"
| "txt"
| "rst"
| "tex"
| "sh"
| "bash"
| "zsh"
| "fish"
| "ps1"
| "bat"
| "cmd"
| "sql"
| "graphql"
| "proto"
) || path.file_name().is_some_and(|n| {
let name = n.to_string_lossy().to_lowercase();
matches!(
name.as_str(),
"dockerfile"
| "makefile"
| "cmakelists.txt"
| "rakefile"
| "gemfile"
| "podfile"
| "vagrantfile"
| ".gitignore"
| ".dockerignore"
| ".env.example"
| "readme"
| "license"
| "changelog"
)
})
}

#[cfg(test)]
mod tests {
use super::*;

#[test]
fn does_not_index_extensionless_files_by_default() {
assert!(!should_index_path(Path::new("my_binary"), 512 * 1024));
}

#[test]
fn indexes_known_extensionless_filenames() {
assert!(should_index_path(Path::new("Makefile"), 512 * 1024));
assert!(should_index_path(Path::new("Dockerfile"), 512 * 1024));
assert!(should_index_path(Path::new("README"), 512 * 1024));
}

#[test]
fn indexes_known_extensions() {
assert!(should_index_path(Path::new("src/main.rs"), 512 * 1024));
assert!(should_index_path(Path::new("script.SH"), 512 * 1024));
}
}
184 changes: 2 additions & 182 deletions src/core/indexer.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -236,97 +236,7 @@ impl Indexer {
}

fn should_index(&self, path: &Path) -> bool {
if let Ok(metadata) = fs::metadata(path) {
if metadata.len() > self.max_file_size {
return false;
}
}

let ext = path
.extension()
.and_then(|e| e.to_str())
.unwrap_or("")
.to_lowercase();

matches!(
ext.as_str(),
"rs" | "py"
| "js"
| "ts"
| "tsx"
| "jsx"
| "go"
| "c"
| "cpp"
| "h"
| "hpp"
| "java"
| "kt"
| "swift"
| "rb"
| "php"
| "cs"
| "fs"
| "scala"
| "clj"
| "ex"
| "exs"
| "erl"
| "hs"
| "ml"
| "lua"
| "r"
| "jl"
| "dart"
| "vue"
| "svelte"
| "astro"
| "html"
| "htm"
| "css"
| "scss"
| "sass"
| "less"
| "json"
| "yaml"
| "yml"
| "toml"
| "xml"
| "md"
| "markdown"
| "txt"
| "rst"
| "tex"
| "sh"
| "bash"
| "zsh"
| "fish"
| "ps1"
| "bat"
| "cmd"
| "sql"
| "graphql"
| "proto"
| ""
) || path.file_name().is_some_and(|n| {
let name = n.to_string_lossy().to_lowercase();
matches!(
name.as_str(),
"dockerfile"
| "makefile"
| "cmakelists.txt"
| "rakefile"
| "gemfile"
| "podfile"
| "vagrantfile"
| ".gitignore"
| ".dockerignore"
| ".env.example"
| "readme"
| "license"
| "changelog"
)
})
super::index_filter::should_index_path(path, self.max_file_size)
}

fn chunk_content(&self, content: &str) -> Vec<FileChunk> {
Expand Down Expand Up @@ -612,97 +522,7 @@ impl ServerIndexer {
}

fn should_index(&self, path: &Path) -> bool {
if let Ok(metadata) = fs::metadata(path) {
if metadata.len() > self.max_file_size {
return false;
}
}

let ext = path
.extension()
.and_then(|e| e.to_str())
.unwrap_or("")
.to_lowercase();

matches!(
ext.as_str(),
"rs" | "py"
| "js"
| "ts"
| "tsx"
| "jsx"
| "go"
| "c"
| "cpp"
| "h"
| "hpp"
| "java"
| "kt"
| "swift"
| "rb"
| "php"
| "cs"
| "fs"
| "scala"
| "clj"
| "ex"
| "exs"
| "erl"
| "hs"
| "ml"
| "lua"
| "r"
| "jl"
| "dart"
| "vue"
| "svelte"
| "astro"
| "html"
| "htm"
| "css"
| "scss"
| "sass"
| "less"
| "json"
| "yaml"
| "yml"
| "toml"
| "xml"
| "md"
| "markdown"
| "txt"
| "rst"
| "tex"
| "sh"
| "bash"
| "zsh"
| "fish"
| "ps1"
| "bat"
| "cmd"
| "sql"
| "graphql"
| "proto"
| ""
) || path.file_name().is_some_and(|n| {
let name = n.to_string_lossy().to_lowercase();
matches!(
name.as_str(),
"dockerfile"
| "makefile"
| "cmakelists.txt"
| "rakefile"
| "gemfile"
| "podfile"
| "vagrantfile"
| ".gitignore"
| ".dockerignore"
| ".env.example"
| "readme"
| "license"
| "changelog"
)
})
super::index_filter::should_index_path(path, self.max_file_size)
}

fn chunk_content(&self, content: &str) -> Vec<FileChunk> {
Expand Down
1 change: 1 addition & 0 deletions src/core/mod.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,7 @@

mod db;
mod embeddings;
pub(crate) mod index_filter;
mod indexer;
mod search;

Expand Down
Loading
Loading