feat: fix some bugs, improve some perf, add some tests (#38)

* feat: fix some bugs, improve some perf, add some tests

* fix: lint

Author: ParthJadhav

.github/workflows/ci.yml

@@ -32,25 +32,10 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
 
       - name: Install Rust toolchain
-        uses: actions-rs/toolchain@v1
-        with:
-          toolchain: stable
-          target: ${{ matrix.target }}
-          profile: minimal
-          override: true
-
-      - name: Install Rust library source
-        if: matrix.target == 'x86_64-unknown-linux-gnu'
-        uses: actions-rs/toolchain@v1
-        with:
-          toolchain: stable
-          target: ${{ matrix.target }}
-          profile: minimal
-          override: true
-          components: rust-src
+        run: rustup toolchain install stable --target ${{ matrix.target }} --profile minimal
 
       - name: Build
         run: cargo build --verbose --target ${{ matrix.target }}
@@ -59,15 +44,13 @@ jobs:
         run: cargo test --verbose --target ${{ matrix.target }}
 
   lint:
-    name: Formatter
-
-    needs: build-test
+    name: Lint & Format
 
     runs-on: ubuntu-latest
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
 
       - name: Install Rust
         run: |
@@ -79,5 +62,5 @@ jobs:
       - name: Check formatting
         run: cargo fmt --all -- --check
 
-      - name: Check code for possible improvements
+      - name: Run clippy
         run: cargo clippy -- -D warnings

README.md

@@ -28,52 +28,48 @@ rust_search = "2.0.0"
 ```rust
 use rust_search::SearchBuilder;
 
-fn main(){
-    let search: Vec<String> = SearchBuilder::default()
-        .location("~/path/to/directory")
-        .search_input("what to search")
-        .more_locations(vec!["/anotherPath/to/search", "/keepAddingIfYouWant/"])
-        .limit(1000) // results to return
-        .ext("extension")
-        .strict()
-        .depth(1)
-        .ignore_case()
-        .hidden()
-        .build()
-        .collect();
-
-    for path in search {
-        println!("{}", path);
-    }
+let search: Vec<String> = SearchBuilder::default()
+    .location("~/path/to/directory")
+    .search_input("what to search")
+    .more_locations(vec!["/anotherPath/to/search", "/keepAddingIfYouWant/"])
+    .limit(1000) // results to return
+    .ext("extension")
+    .strict()
+    .depth(1)
+    .ignore_case()
+    .hidden()
+    .build()
+    .collect();
+
+for path in search {
+    println!("{}", path);
 }
 ```
 
 - Sort the output by similarity with the input
 
 ```rust
- use rust_search::{SearchBuilder, similarity_sort};
- fn main() {
-     let search_input = "fly";
-     let mut search: Vec<String> = SearchBuilder::default()
-         .location("~/Desktop/")
-         .search_input(search_input)
-         .depth(1)
-         .ignore_case()
-         .build()
-        .collect();
-
-     similarity_sort(&mut search, &search_input);
-     for path in search {
-        println!("{:?}", path);
-     }
- }
- 
+use rust_search::{SearchBuilder, similarity_sort};
+
+let search_input = "fly";
+let mut search: Vec<String> = SearchBuilder::default()
+    .location("~/Desktop/")
+    .search_input(search_input)
+    .depth(1)
+    .ignore_case()
+    .build()
+    .collect();
+
+similarity_sort(&mut search, &search_input);
+for path in search {
+    println!("{:?}", path);
+}
 ```
 > search **without** similarity sort
-`["afly.txt", "bfly.txt", "flyer.txt", "fly.txt"]`
+> `["afly.txt", "bfly.txt", "flyer.txt", "fly.txt"]`
 
 > search **with** similarity sort
-`["fly.txt", "flyer.txt", "afly.txt", "bfly.txt",]`
+> `["fly.txt", "flyer.txt", "afly.txt", "bfly.txt",]`
 
 - To get all the files with a specific extension in a directory, use:
 
@@ -98,7 +94,7 @@ let files: Vec<String> = SearchBuilder::default()
     .build()
     .collect();
 ```
-To filter files by date_created, date_modified, file_size and/or custom_filter, use:
+To filter files by `date_created`, `date_modified`, `file_size` and/or `custom_filter`, use:
 
 ```rust
 use rust_search::{FileSize, FilterExt, SearchBuilder};
@@ -121,7 +117,7 @@ let search: Vec<String> = SearchBuilder::default()
 
 ## ⚙️ Benchmarks
 
-The difference in sample size is due to the fact that fd and glob are different tools and have different use cases. fd is a command line tool that searches for files and directories. glob is a library that can be used to search for files and directories. The benchmark is done on a MacBook Air M2, 16 GB Unified memory.
+The difference in sample size is due to the fact that fd and glob are different tools and have different use cases. fd is a command line tool that searches for files and directories. glob is a library that can be used to search for files and directories. The benchmark is done on a `MacBook` Air M2, 16 GB Unified memory.
 
 Benchmarks are done using [hyperfine](https://github.com/sharkdp/hyperfine),
 Benchmarks files are available in the [benchmarks](https://drive.google.com/drive/folders/1ug6ojNixS5jAe6Lh6M0o2d3tku73zQ9w?usp=sharing) drive folder.

src/builder.rs

@@ -96,7 +96,10 @@ impl SearchBuilder {
     pub fn ext(mut self, ext: impl Into<String>) -> Self {
         let ext: String = ext.into();
         // Remove the dot if it's there.
-        self.file_ext = Some(ext.strip_prefix('.').map_or(ext.clone(), str::to_owned));
+        self.file_ext = Some(
+            ext.strip_prefix('.')
+                .map_or_else(|| ext.clone(), str::to_owned),
+        );
         self
     }
 
@@ -201,7 +204,7 @@ impl SearchBuilder {
     /// use rust_search::SearchBuilder;
     ///
     /// let search: Vec<String> = SearchBuilder::default()
-    ///     .with_hidden()
+    ///     .hidden()
     ///     .build()
     ///     .collect();
     /// ```

src/filter.rs

@@ -57,12 +57,11 @@ fn convert(b: f64, pow: u32) -> u64 {
     (b * 1024_u64.pow(pow) as f64) as u64
 }
 
-#[allow(clippy::from_over_into)]
-impl Into<u64> for FileSize {
-    fn into(self) -> u64 {
+impl From<FileSize> for u64 {
+    fn from(size: FileSize) -> Self {
         use self::FileSize::{Byte, Gigabyte, Kilobyte, Megabyte, Terabyte};
 
-        match self {
+        match size {
             Byte(b) => b,
             Kilobyte(b) => convert(b, 1),
             Megabyte(b) => convert(b, 2),
@@ -94,7 +93,12 @@ pub trait FilterExt {
     fn file_size_greater(self, size: FileSize) -> Self;
     /// custom filter that exposes the [`DirEntry`] directly
     /// ```rust
-    /// builder.custom_filter(|dir| dir.metadata().unwrap().is_file())
+    /// use rust_search::{SearchBuilder, FilterExt};
+    ///
+    /// let search: Vec<String> = SearchBuilder::default()
+    ///     .custom_filter(|dir| dir.metadata().unwrap().is_file())
+    ///     .build()
+    ///     .collect();
     /// ```
     fn custom_filter(self, f: FilterFn) -> Self;
 }

src/search.rs

@@ -1,12 +1,15 @@
 use std::{
     cmp,
     path::Path,
-    sync::mpsc::{self, Sender},
+    sync::{
+        atomic::{AtomicUsize, Ordering},
+        mpsc::{self, Sender},
+        Arc,
+    },
 };
 
 use crate::{filter::FilterType, utils, SearchBuilder};
 use ignore::{WalkBuilder, WalkState};
-use regex::Regex;
 
 /// A struct that holds the receiver for the search results
 ///
@@ -17,9 +20,13 @@ use regex::Regex;
 /// ## Iterate on the results
 ///
 /// ```
-/// use rust_search::Search;
+/// use rust_search::SearchBuilder;
 ///
-/// let search = Search::new("src", None, Some(".rs"), Some(1));
+/// let search = SearchBuilder::default()
+///     .location("src")
+///     .ext("rs")
+///     .depth(1)
+///     .build();
 ///
 /// for path in search {
 ///    println!("{:?}", path);
@@ -29,11 +36,14 @@ use regex::Regex;
 /// ## Collect results into a vector
 ///
 /// ```
-/// use rust_search::Search;
+/// use rust_search::SearchBuilder;
 ///
-/// let search = Search::new("src", None, Some(".rs"), Some(1));
-///
-/// let paths_vec: Vec<String> = search.collect();
+/// let paths_vec: Vec<String> = SearchBuilder::default()
+///     .location("src")
+///     .ext("rs")
+///     .depth(1)
+///     .build()
+///     .collect();
 /// ```
 pub struct Search {
     rx: Box<dyn Iterator<Item = String>>,
@@ -94,10 +104,13 @@ impl Search {
         }
 
         let (tx, rx) = mpsc::channel::<String>();
+        let reg_exp = Arc::new(regex_search_input);
+        let counter = Arc::new(AtomicUsize::new(0));
+
         walker.build_parallel().run(|| {
             let tx: Sender<String> = tx.clone();
-            let reg_exp: Regex = regex_search_input.clone();
-            let mut counter = 0;
+            let reg_exp = Arc::clone(&reg_exp);
+            let counter = Arc::clone(&counter);
 
             Box::new(move |path_entry| {
                 if let Ok(entry) = path_entry {
@@ -106,17 +119,13 @@ impl Search {
                         // Lossy means that if the file name is not valid UTF-8
                         // it will be replaced with �.
                         // Will return the file name with extension.
-                        let file_name = file_name.to_string_lossy().to_string();
+                        let file_name = file_name.to_string_lossy();
                         if reg_exp.is_match(&file_name) {
-                            // Continue searching if the send was successful
-                            // and there is no limit or the limit has not been reached
-                            if tx.send(path.display().to_string()).is_ok()
-                                && (limit.is_none() || counter < limit.unwrap())
+                            if limit.is_none_or(|l| counter.fetch_add(1, Ordering::Relaxed) < l)
+                                && tx.send(path.display().to_string()).is_ok()
                             {
-                                counter += 1;
                                 return WalkState::Continue;
                             }
-
                             return WalkState::Quit;
                         }
                     }