Merge pull request #47 from sreedevk/development

Version 0.1.5

.github/workflows/release.yml

@@ -0,0 +1,31 @@
+name: Release
+
+env:
+  PROJECT_NAME: deduplicator
+  PROJECT_DESC: "Filter, Sort & Delete Duplicate Files Recursively"
+  PROJECT_AUTH: "sreedevk"
+
+on:
+  release:
+    types:
+      - created
+
+jobs:
+  upload-assets:
+    strategy:
+      matrix:
+        os:
+          - ubuntu-latest
+          - macos-latest
+          - windows-latest
+    runs-on: ${{ matrix.os }}
+    steps:
+      - uses: actions/checkout@v3
+      - uses: taiki-e/upload-rust-binary-action@v1
+        with:
+          bin: deduplicator
+          tar: unix
+          zip: windows
+          token: ${{ secrets.GITHUB_TOKEN }}
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/rust.yml

@@ -1,20 +0,0 @@
-name: Rust
-
-on:
-  push:
-    branches: [ "main" ]
-  pull_request:
-    branches: [ "main" ]
-
-env:
-  CARGO_TERM_COLOR: always
-
-jobs:
-  build:
-    runs-on: ubuntu-latest
-    steps:
-    - uses: actions/checkout@v3
-    - name: Build
-      run: cargo build --verbose
-    - name: Run tests
-      run: cargo test --verbose

.gitignore

@@ -1,2 +1,3 @@
 /target
 /test_data
+.envrc

Cargo.lock

@@ -2,6 +2,15 @@
 # It is not intended for manual editing.
 version = 3
 
+[[package]]
+name = "aho-corasick"
+version = "0.7.20"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "cc936419f96fa211c1b9166887b38e5e40b19958e5b895be7c1f93adec7071ac"
+dependencies = [
+ "memchr",
+]
+
 [[package]]
 name = "android_system_properties"
 version = "0.1.5"
@@ -52,6 +61,16 @@ dependencies = [
  "serde",
 ]
 
+[[package]]
+name = "bstr"
+version = "1.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b45ea9b00a7b3f2988e9a65ad3917e62123c38dba709b666506207be96d1790b"
+dependencies = [
+ "memchr",
+ "serde",
+]
+
 [[package]]
 name = "bumpalo"
 version = "3.11.1"
@@ -229,7 +248,7 @@ version = "1.1.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "22813a6dc45b335f9bade10bf7271dc477e81113e89eb251a0bc2a8a81c536e1"
 dependencies = [
- "bstr",
+ "bstr 0.2.17",
  "csv-core",
  "itoa",
  "ryu",
@@ -305,7 +324,7 @@ dependencies = [
 
 [[package]]
 name = "deduplicator"
-version = "0.1.2"
+version = "0.1.5"
 dependencies = [
  "anyhow",
  "bytesize",
@@ -314,7 +333,7 @@ dependencies = [
  "colored",
  "dashmap",
  "fxhash",
- "glob",
+ "globwalk",
  "indicatif",
  "itertools",
  "memmap2",
@@ -385,6 +404,12 @@ dependencies = [
  "libc",
 ]
 
+[[package]]
+name = "fnv"
+version = "1.0.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3f9eec918d3f24069decb9af1554cad7c880e2da24a9afd88aca000531ab82c1"
+
 [[package]]
 name = "fxhash"
 version = "0.2.1"
@@ -406,10 +431,28 @@ dependencies = [
 ]
 
 [[package]]
-name = "glob"
-version = "0.3.0"
+name = "globset"
+version = "0.4.10"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9b919933a397b79c37e33b77bb2aa3dc8eb6e165ad809e58ff75bc7db2e34574"
+checksum = "029d74589adefde59de1a0c4f4732695c32805624aec7b68d91503d4dba79afc"
+dependencies = [
+ "aho-corasick",
+ "bstr 1.1.0",
+ "fnv",
+ "log",
+ "regex",
+]
+
+[[package]]
+name = "globwalk"
+version = "0.8.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "93e3af942408868f6934a7b85134a3230832b9977cf66125df2f9edcfce4ddcc"
+dependencies = [
+ "bitflags",
+ "ignore",
+ "walkdir",
+]
 
 [[package]]
 name = "hashbrown"
@@ -465,6 +508,23 @@ dependencies = [
  "cxx-build",
 ]
 
+[[package]]
+name = "ignore"
+version = "0.4.20"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "dbe7873dab538a9a44ad79ede1faf5f30d49f9a5c883ddbab48bce81b64b7492"
+dependencies = [
+ "globset",
+ "lazy_static",
+ "log",
+ "memchr",
+ "regex",
+ "same-file",
+ "thread_local",
+ "walkdir",
+ "winapi-util",
+]
+
 [[package]]
 name = "indicatif"
 version = "0.17.2"
@@ -787,12 +847,29 @@ dependencies = [
  "thiserror",
 ]
 
+[[package]]
+name = "regex"
+version = "1.7.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "48aaa5748ba571fb95cd2c85c09f629215d3a6ece942baa100950af03a34f733"
+dependencies = [
+ "aho-corasick",
+ "memchr",
+ "regex-syntax",
+]
+
 [[package]]
 name = "regex-automata"
 version = "0.1.10"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "6c230d73fb8d8c1b9c0b3135c5142a8acee3a0558fb8db5cf1cb65f8d7862132"
 
+[[package]]
+name = "regex-syntax"
+version = "0.6.28"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "456c603be3e8d448b072f410900c09faf164fbce2d480456f50eea6e25f9c848"
+
 [[package]]
 name = "rustix"
 version = "0.36.5"
@@ -819,6 +896,15 @@ version = "1.0.12"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "7b4b9743ed687d4b4bcedf9ff5eaa7398495ae14e61cba0a295704edbc7decde"
 
+[[package]]
+name = "same-file"
+version = "1.0.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "93fc1dc3aaa9bfed95e02e6eadabb4baf7e3078b0bd1b4d7b6b0b68378900502"
+dependencies = [
+ "winapi-util",
+]
+
 [[package]]
 name = "scopeguard"
 version = "1.1.0"
@@ -919,6 +1005,15 @@ dependencies = [
  "syn",
 ]
 
+[[package]]
+name = "thread_local"
+version = "1.1.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5516c27b78311c50bf42c071425c560ac799b11c30b31f87e3081965fe5e0180"
+dependencies = [
+ "once_cell",
+]
+
 [[package]]
 name = "time"
 version = "0.1.45"
@@ -932,9 +1027,9 @@ dependencies = [
 
 [[package]]
 name = "tokio"
-version = "1.23.0"
+version = "1.23.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "eab6d665857cc6ca78d6e80303a02cea7a7851e85dfbd77cbdc09bd129f1ef46"
+checksum = "38a54aca0c15d014013256222ba0ebed095673f89345dd79119d912eb561b7a8"
 dependencies = [
  "autocfg",
  "bytes",
@@ -985,6 +1080,17 @@ version = "0.9.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "49874b5167b65d7193b8aba1567f5c7d93d001cafc34600cee003eda787e483f"
 
+[[package]]
+name = "walkdir"
+version = "2.3.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "808cf2735cd4b6866113f648b791c6adc5714537bc222d9347bb203386ffda56"
+dependencies = [
+ "same-file",
+ "winapi",
+ "winapi-util",
+]
+
 [[package]]
 name = "wasi"
 version = "0.10.0+wasi-snapshot-preview1"

Cargo.toml

@@ -1,10 +1,14 @@
 [package]
 name = "deduplicator"
-version = "0.1.2"
+version = "0.1.5"
 edition = "2021"
 description = "find,filter,delete Duplicates"
 license = "MIT"
-authors = ["Sreedev Kodichath <sreedevpadmakumar@gmail.com>", "Valentin Bersier <vbersier@gmail.com>", "Dhruva Sagar <dhruva.sagar@gmail.com>"]
+authors = [
+    "Sreedev Kodichath <sreedevpadmakumar@gmail.com>",
+    "Valentin Bersier <vbersier@gmail.com>",
+    "Dhruva Sagar <dhruva.sagar@gmail.com>",
+]
 
 # See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
 
@@ -16,12 +20,12 @@ clap = { version = "4.0.32", features = ["derive"] }
 colored = "2.0.0"
 dashmap = { version = "5.4.0", features = ["rayon"] }
 fxhash = "0.2.1"
-glob = "0.3.0"
+globwalk = "0.8.1"
 indicatif = { version = "0.17.2", features = ["rayon", "tokio"] }
 itertools = "0.10.5"
 memmap2 = "0.5.8"
 prettytable-rs = "0.10.0"
 rayon = "1.6.1"
 thiserror = "1.0.38"
-tokio = { version = "1.23.0", features = ["full"] }
+tokio = { version = "1.23.1", features = ["full"] }
 unicode-segmentation = "1.10.0"

README.md

@@ -4,48 +4,120 @@
   Find, Sort, Filter & Delete duplicate files 
 </p>
 
-<p align="center">
-NOTE: This project is still being developed. At the moment, as shown in the screenshot below, deduplicator is able to scan through and list duplicates with and without caching. Contributions are welcome.
-</p>
-
-<h2 align="center">Usage</h2>
+## Usage
 
 ```bash
-Usage: deduplicator [OPTIONS]
+Usage: deduplicator [OPTIONS] [scan_dir_path]
+
+Arguments:
+  [scan_dir_path]  Run Deduplicator on dir different from pwd (e.g., ~/Pictures )
 
 Options:
-  -t, --types <TYPES>      Filetypes to deduplicate (default = all)
-      --dir <DIR>          Run Deduplicator on dir different from pwd
-  -i, --interactive        Delete files interactively
-  -m, --minsize <MINSIZE>  Minimum filesize of duplicates to scan (e.g., 100B/1K/2M/3G/4T). [default = 0]
-  -h, --help               Print help information
-  -V, --version            Print version information
+  -t, --types <TYPES>          Filetypes to deduplicate [default = all]
+  -i, --interactive            Delete files interactively
+  -s, --min-size <MIN_SIZE>    Minimum filesize of duplicates to scan (e.g., 100B/1K/2M/3G/4T) [default: 1b]
+  -d, --max-depth <MAX_DEPTH>  Max Depth to scan while looking for duplicates
+      --min-depth <MIN_DEPTH>  Min Depth to scan while looking for duplicates
+  -f, --follow-links           Follow links while scanning directories
+  -h, --help                   Print help information
+  -V, --version                Print version information
+```
+### Examples
+
+```bash
+# Scan for duplicates recursively from the current dir, only look for png, jpg & pdf file types & interactively delete files
+deduplicator -t pdf,jpg,png -i
+
+# Scan for duplicates recursively from the ~/Pictures dir, only look for png, jpeg, jpg & pdf file types & interactively delete files
+deduplicator ~/Pictures/ -t png,jpeg,jpg,pdf -i
+
+# Scan for duplicates in the ~/Pictures without recursing into subdirectories
+deduplicator ~/Pictures --max-depth 0
+
+# look for duplicates in the ~/.config directory while also recursing into symbolic link paths
+deduplicator ~/.config --follow-links
+
+# scan for duplicates that are greater than 100mb in the ~/Media directory
+deduplicator ~/Media --min-size 100mb
 ```
 
-<h2 align="center">Installation</h2>
+## Installation
 
-<p align="center">Currently, deduplicator is only installable via rust's cargo package manager</p>
+### Cargo Install
+
+#### Stable
+
+```bash
+$ cargo install deduplicator
+```
+
+#### Nightly
+
+if you'd like to install with nightly features, you can use
+
+```bash
+$ cargo install --git https://github.com/sreedevk/deduplicator
+```
+Please note that if you use a version manager to install rust (like asdf), you need to reshim (`asdf reshim rust`).
+
+### Linux (Pre-built Binary)
+
+you can download the pre-built binary from the [Releases](https://github.com/sreedevk/deduplicator/releases) page.
+download the `deduplicator-x86_64-unknown-linux-gnu.tar.gz` for linux. Once you have the tarball file with the executable,
+you can follow these steps to install:
+
+```bash
+$ tar -zxvf deduplicator-x86_64-unknown-linux-gnu.tar.gz
+$ sudo mv deduplicator /usr/bin/
+```
+
+### Mac OS (Pre-built Binary)
+
+you can download the pre-build binary from the [Releases](https://github.com/sreedevk/deduplicator/releases) page.
+download the `deduplicator-x86_64-apple-darwin.tar.gz` tarball for mac os. Once you have the tarball file with the executable, you can follow these steps to install:
+
+```bash
+$ tar -zxvf deduplicator-x86_64-unknown-linux-gnu.tar.gz
+$ sudo mv deduplicator /usr/bin/
+```
+
+### Windows (Pre-built Binary)
+
+you can download the pre-build binary from the [Releases](https://github.com/sreedevk/deduplicator/releases) page.
+download the `deduplicator-x86_64-pc-windows-msvc.zip` zip file for windows. unzip the `zip`  file & move the `deduplicator.exe` to a location in the PATH system environment variable.
+
+Note: If you Run into an msvc error, please install MSCV from [here](https://learn.microsoft.com/en-us/cpp/windows/latest-supported-vc-redist?view=msvc-170)
+
+## Performance
+
+Deduplicator uses size comparison and fxhash (a non non-cryptographic hashing algo) to quickly scan through large number of files to find duplicates. its also highly parallel (uses rayon and dashmap). I was able to scan through 120GB of files (Videos, PDFs, Images) in ~300ms. checkout the benchmarks
+
+## benchmarks
+
+| Command | Dirsize | Mean [ms] | Min [ms] | Max [ms] | Relative |
+|:---|:---|---:|---:|---:|---:|
+| `deduplicator --dir ~/Data/tmp` | (~120G) | 27.5 ± 1.0 | 26.0 | 32.1 | 1.70 ± 0.09 |
+| `deduplicator --dir ~/Data/books` | (~8.6G) | 21.8 ± 0.7 | 20.5 | 24.4 | 1.35 ± 0.07 |
+| `deduplicator --dir ~/Data/books --min-size 10M` | (~8.6G) | 16.1 ± 0.6 | 14.9 | 18.8 | 1.00 |
+| `deduplicator --dir ~/Data/ --types pdf,jpg,png,jpeg` | (~290G) | 1857.4 ± 24.5 | 1817.0 | 1895.5 | 115.07 ± 4.64 |
+
+* The last entry is lower because of the number of files deduplicator had to go through (~660895 Files). The average size of the files rarely affect the performance of deduplicator.
+
+These benchmarks were run using [hyperfine](https://github.com/sharkdp/hyperfine). Here are the specs of the machine used to benchmark deduplicator:
 
 ```
-cargo install deduplicator
+OS: Arch Linux x86_64 
+Host: Precision 5540
+Kernel: 5.15.89-1-lts 
+Uptime: 4 hours, 44 mins 
+Shell: zsh 5.9                        
+Terminal: kitty 
+CPU: Intel i9-9880H (16) @ 4.800GHz 
+GPU: NVIDIA Quadro T2000 Mobile / Max-Q 
+GPU: Intel CoffeeLake-H GT2 [UHD Graphics 630] 
+Memory: 31731MiB (~32GiB)
 ```
-<p align="center">
-  note that if you use a version manager to install rust (like asdf), you need to reshim (`asdf reshim rust`).
-</p>
 
-<h2 align="center">Performance</h2>
-
-<p align="center">
-  Deduplicator uses fxhash (a non-cryptographic hashing algorithm) which is extremely fast. As a result, deduplicator is able to process huge amounts of data in a <del>couple of seconds.</del> few milliseconds.</p>
-
-<p align="center">
-  <del>While testing, Deduplicator was able to go through 8.6GB of pdf files and detect duplicates in 2.9 seconds</del>
-  As of version 0.1.1, on testing locally, deduplicator was able to process and find duplicates in 120GB of files (Videos, PDFs, Images) in ~300ms
-</p>
-
-<h2 align="center">Screenshots</h2>
-
-
-<img src="https://user-images.githubusercontent.com/36154121/211948081-63c12b94-6251-487b-a49f-ac5418169d5a.gif" />
-<img src="https://user-images.githubusercontent.com/36154121/211458077-90092aa3-496c-492f-a061-618059890d5f.png" />
+## Screenshots
 
+![](https://user-images.githubusercontent.com/36154121/213618143-e5182e39-731e-4817-87dd-1a6a0f38a449.gif)

src/filters.rs

@@ -1,8 +1,8 @@
 use crate::file_manager::File;
 use crate::params::Params;
 
-pub fn is_file_gt_minsize(app_opts: &Params, file: &File) -> bool {
-    match app_opts.get_minsize() {
+pub fn is_file_gt_min_size(app_opts: &Params, file: &File) -> bool {
+    match app_opts.get_min_size() {
         Some(msize) => match file.size {
             Some(fsize) => fsize >= msize,
             None => true,

src/output.rs

@@ -5,6 +5,7 @@ use chrono::offset::Utc;
 use chrono::DateTime;
 use colored::Colorize;
 use dashmap::DashMap;
+use indicatif::{ProgressBar, ProgressIterator, ProgressStyle};
 use itertools::Itertools;
 use prettytable::{format, row, Table};
 use std::io::Write;
@@ -12,7 +13,7 @@ use std::{fs, io};
 use unicode_segmentation::UnicodeSegmentation;
 
 fn format_path(path: &str, opts: &Params) -> Result<String> {
-    let display_path = path.replace(&opts.get_directory()?, "");
+    let display_path = path.replace(opts.get_directory()?.to_string_lossy().as_ref(), "");
     let display_range = if display_path.chars().count() > 32 {
         display_path
             .graphemes(true)
@@ -26,7 +27,7 @@ fn format_path(path: &str, opts: &Params) -> Result<String> {
         display_path
     };
 
-    Ok(format!("...{:<32}", display_range))
+    Ok(format!("...{display_range:<32}"))
 }
 
 fn file_size(file: &File) -> Result<String> {
@@ -40,10 +41,6 @@ fn modified_time(path: &String) -> Result<String> {
     Ok(modified_time.format("%Y-%m-%d %H:%M:%S").to_string())
 }
 
-fn print_meta_info() {
-    println!("Deduplicator v{}", std::env!("CARGO_PKG_VERSION"));
-}
-
 fn scan_group_instruction() -> Result<String> {
     println!("\nEnter the indices of the files you want to delete.");
     println!("You can enter multiple files using commas to seperate file indices.");
@@ -115,8 +112,6 @@ fn process_group_action(duplicates: &Vec<File>, dup_index: usize, dup_size: usiz
 }
 
 pub fn interactive(duplicates: DashMap<String, Vec<File>>, opts: &Params) {
-    print_meta_info();
-
     if duplicates.is_empty() {
         println!(
             "\n{}",
@@ -128,8 +123,8 @@ pub fn interactive(duplicates: DashMap<String, Vec<File>>, opts: &Params) {
     duplicates
         .clone()
         .into_iter()
-        .sorted_unstable_by_key(|f| {
-            -(f.1.first().and_then(|ff| ff.size).unwrap_or_default() as i64)
+        .sorted_unstable_by_key(|(_, f)| {
+            -(f.first().and_then(|ff| ff.size).unwrap_or_default() as i64)
         }) // sort by descending file size in interactive mode
         .enumerate()
         .for_each(|(gindex, (_, group))| {
@@ -140,7 +135,7 @@ pub fn interactive(duplicates: DashMap<String, Vec<File>>, opts: &Params) {
                 itable.add_row(row![
                     index,
                     format_path(&file.path, opts).unwrap_or_default().blue(),
-                    file_size(&file).unwrap_or_default().red(),
+                    file_size(file).unwrap_or_default().red(),
                     modified_time(&file.path).unwrap_or_default().yellow()
                 ]);
             });
@@ -150,8 +145,6 @@ pub fn interactive(duplicates: DashMap<String, Vec<File>>, opts: &Params) {
 }
 
 pub fn print(duplicates: DashMap<String, Vec<File>>, opts: &Params) {
-    print_meta_info();
-
     if duplicates.is_empty() {
         println!(
             "\n{}",
@@ -161,17 +154,25 @@ pub fn print(duplicates: DashMap<String, Vec<File>>, opts: &Params) {
     }
 
     let mut output_table = Table::new();
+    let progress_bar = ProgressBar::new(duplicates.len() as u64);
+    let progress_style = ProgressStyle::default_bar()
+        .template("{spinner:.green} [generating output] [{wide_bar:.cyan/blue}] {pos}/{len} files")
+        .unwrap();
+
+    progress_bar.set_style(progress_style);
     output_table.set_titles(row!["hash", "duplicates"]);
+
     duplicates
         .into_iter()
-        .sorted_unstable_by_key(|f| f.1.first().and_then(|ff| ff.size).unwrap_or_default()) // sort by ascending size
+        .sorted_unstable_by_key(|(_, f)| f.first().and_then(|ff| ff.size).unwrap_or_default())
+        .progress_with(progress_bar)
         .for_each(|(hash, group)| {
             let mut inner_table = Table::new();
             inner_table.set_format(*format::consts::FORMAT_NO_BORDER_LINE_SEPARATOR);
             group.iter().for_each(|file| {
                 inner_table.add_row(row![
                     format_path(&file.path, opts).unwrap_or_default().blue(),
-                    file_size(&file).unwrap_or_default().red(),
+                    file_size(file).unwrap_or_default().red(),
                     modified_time(&file.path).unwrap_or_default().yellow()
                 ]);
             });

src/params.rs

@@ -1,27 +1,38 @@
+use std::{fs, path::PathBuf};
+
 use anyhow::{anyhow, Result};
 use clap::{Parser, ValueHint};
-use std::{fs, path::PathBuf};
+use globwalk::{GlobWalker, GlobWalkerBuilder};
 
 #[derive(Parser, Debug)]
 #[command(author, version, about, long_about = None)]
 pub struct Params {
-    /// Filetypes to deduplicate (default = all)
+    /// Filetypes to deduplicate [default = all]
     #[arg(short, long)]
     pub types: Option<String>,
-    /// Run Deduplicator on dir different from pwd
-    #[arg(long, value_hint = ValueHint::DirPath)]
+    /// Run Deduplicator on dir different from pwd (e.g., ~/Pictures )
+    #[arg(value_hint = ValueHint::DirPath, value_name = "scan_dir_path")]
     pub dir: Option<PathBuf>,
     /// Delete files interactively
     #[arg(long, short)]
     pub interactive: bool,
-    /// Minimum filesize of duplicates to scan (e.g., 100B/1K/2M/3G/4T). [default = 0]
+    /// Minimum filesize of duplicates to scan (e.g., 100B/1K/2M/3G/4T).
+    #[arg(long, short = 's', default_value = "1b")]
+    pub min_size: Option<String>,
+    /// Max Depth to scan while looking for duplicates
+    #[arg(long, short = 'd')]
+    pub max_depth: Option<usize>,
+    /// Min Depth to scan while looking for duplicates
+    #[arg(long)]
+    pub min_depth: Option<usize>,
+    /// Follow links while scanning directories
     #[arg(long, short)]
-    pub minsize: Option<String>,
+    pub follow_links: bool,
 }
 
 impl Params {
-    pub fn get_minsize(&self) -> Option<u64> {
-        match &self.minsize {
+    pub fn get_min_size(&self) -> Option<u64> {
+        match &self.min_size {
             Some(msize) => match msize.parse::<bytesize::ByteSize>() {
                 Ok(units) => Some(units.0),
                 Err(_) => None,
@@ -30,34 +41,48 @@ impl Params {
         }
     }
 
-    pub fn get_directory(&self) -> Result<String> {
-        let dir_pathbuf: PathBuf = self
-            .dir
-            .clone()
-            .unwrap_or(std::env::current_dir()?)
-            .as_os_str()
-            .into();
-
-        let dir = fs::canonicalize(dir_pathbuf)?
-            .as_os_str()
-            .to_str()
-            .ok_or_else(|| anyhow!("Invalid directory"))?
-            .to_string();
-
+    pub fn get_directory(&self) -> Result<PathBuf> {
+        let current_dir = std::env::current_dir()?;
+        let dir_path = self.dir.as_ref().unwrap_or(&current_dir).as_path();
+        let dir = fs::canonicalize(dir_path)?;
         Ok(dir)
     }
 
-    pub fn get_glob_patterns(&self) -> Vec<PathBuf> {
-        self.types
-            .clone()
-            .unwrap_or_else(|| String::from("*"))
-            .split(',')
-            .map(|filetype| format!("*.{}", filetype))
-            .map(|filetype| {
-                vec![self.get_directory().unwrap(), String::from("**"), filetype]
-                    .iter()
-                    .collect()
-            })
-            .collect()
+    fn add_glob_min_depth(&self, builder: GlobWalkerBuilder) -> Result<GlobWalkerBuilder> {
+        match self.min_depth {
+            Some(mindepth) => Ok(builder.min_depth(mindepth)),
+            None => Ok(builder),
+        }
+    }
+
+    fn add_glob_max_depth(&self, builder: GlobWalkerBuilder) -> Result<GlobWalkerBuilder> {
+        match self.max_depth {
+            Some(maxdepth) => Ok(builder.max_depth(maxdepth)),
+            None => Ok(builder),
+        }
+    }
+
+    fn add_glob_follow_links(&self, builder: GlobWalkerBuilder) -> Result<GlobWalkerBuilder> {
+        match self.follow_links {
+            true => Ok(builder.follow_links(true)),
+            false => Ok(builder.follow_links(false)),
+        }
+    }
+
+    pub fn get_glob_walker(&self) -> Result<GlobWalker> {
+        let pattern: String = match self.types.as_ref() {
+            Some(filetypes) => format!("**/*{{{filetypes}}}"),
+            None => "**/*".to_string(),
+        };
+
+        let glob_walker_builder = self
+            .add_glob_min_depth(GlobWalkerBuilder::from_patterns(
+                self.get_directory()?,
+                &[pattern],
+            ))
+            .and_then(|builder| self.add_glob_max_depth(builder))
+            .and_then(|builder| self.add_glob_follow_links(builder))?;
+
+        glob_walker_builder.build().map_err(|e| anyhow!(e))
     }
 }

src/scanner.rs

@@ -2,11 +2,11 @@ use crate::{file_manager::File, filters, params::Params};
 use anyhow::Result;
 use dashmap::DashMap;
 use fxhash::hash64 as hasher;
-use glob::glob;
-use indicatif::{ParallelProgressIterator, ProgressStyle};
+use indicatif::{ParallelProgressIterator, ProgressBar, ProgressIterator, ProgressStyle};
 use memmap2::Mmap;
 use rayon::prelude::*;
 use std::hash::Hasher;
+use std::time::Duration;
 use std::{fs, path::PathBuf};
 
 #[derive(Clone, Copy)]
@@ -40,44 +40,37 @@ pub fn duplicates(app_opts: &Params) -> Result<DashMap<String, Vec<File>>> {
 }
 
 fn scan(app_opts: &Params) -> Result<Vec<File>> {
-    let glob_patterns: Vec<PathBuf> = app_opts.get_glob_patterns();
-    let files: Vec<File> = glob_patterns
-        .par_iter()
+    let walker = app_opts.get_glob_walker()?;
+    let progress = ProgressBar::new_spinner();
+    let progress_style =
+        ProgressStyle::with_template("{spinner:.green} [mapping paths] {pos} paths")?;
+    progress.set_style(progress_style);
+    progress.enable_steady_tick(Duration::from_millis(100));
+
+    let files = walker
+        .progress_with(progress)
+        .filter_map(Result::ok)
+        .map(|file| file.into_path())
+        .filter(|fpath| fpath.is_file())
+        .collect::<Vec<PathBuf>>()
+        .into_par_iter()
         .progress_with_style(ProgressStyle::with_template(
-            "{spinner:.green} [scanning files] [{wide_bar:.cyan/blue}] {pos}/{len} files",
+            "{spinner:.green} [processing mapped paths] [{wide_bar:.cyan/blue}] {pos}/{len} files",
         )?)
-        .filter_map(|glob_pattern| glob(glob_pattern.as_os_str().to_str()?).ok())
-        .flat_map(|file_vec| {
-            file_vec
-                .filter_map(|x| Some(x.ok()?.as_os_str().to_str()?.to_string()))
-                .filter(|glob_result| {
-                    fs::metadata(glob_result)
-                        .map(|f| f.is_file())
-                        .unwrap_or(false)
-                })
-                .collect::<Vec<String>>()
-        })
-        .map(|file_path| File {
-            path: file_path.clone(),
+        .map(|fpath| fpath.display().to_string())
+        .map(|fpath| File {
+            path: fpath.clone(),
             hash: None,
-            size: Some(fs::metadata(file_path).unwrap().len()),
+            size: Some(fs::metadata(fpath).unwrap().len()),
         })
-        .filter(|file| filters::is_file_gt_minsize(app_opts, file))
+        .filter(|file| filters::is_file_gt_min_size(app_opts, file))
         .collect();
 
     Ok(files)
 }
 
-fn process_file_hash_index(file: &File) -> Result<File> {
-    Ok(File {
-        path: file.path.clone(),
-        size: file.size,
-        hash: Some(hash_file(&file.path).unwrap_or_default()),
-    })
-}
-
 fn process_file_index(
-    file: File,
+    mut file: File,
     store: &DashMap<String, Vec<File>>,
     index_criteria: IndexCritera,
 ) {
@@ -89,13 +82,11 @@ fn process_file_index(
                 .or_insert_with(|| vec![file]);
         }
         IndexCritera::Hash => {
-            let processed_file = process_file_hash_index(&file).unwrap();
-            let indexhash = processed_file.clone().hash.unwrap_or_default();
-
+            file.hash = Some(hash_file(&file.path).unwrap_or_default());
             store
-                .entry(indexhash)
-                .and_modify(|fileset| fileset.push(processed_file.clone()))
-                .or_insert_with(|| vec![processed_file]);
+                .entry(file.clone().hash.unwrap())
+                .and_modify(|fileset| fileset.push(file.clone()))
+                .or_insert_with(|| vec![file]);
         }
     }
 }