Merge pull request #38 from sreedevk/development

Version 0.1.4
versioning changes
2026-08-26 18:15:33 +00:00 · 2023-01-23 18:35:28 -05:00 · 2023-01-23 18:33:06 -05:00 · 2023-01-23 18:30:56 -05:00 · 2023-01-23 18:29:41 -05:00 · 2023-01-23 17:50:09 -05:00
11 changed files with 370 additions and 188 deletions
--- a/.github/workflows/release.yml
+++ b/.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 }}
--- a/.github/workflows/rust.yml
+++ b/.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
--- a/.gitignore
+++ b/.gitignore
@@ -1,2 +1,3 @@
 /target
 /test_data
+.envrc
--- a/Cargo.lock
+++ b/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"
@@ -70,6 +89,12 @@ version = "1.3.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "dfb24e866b15a1af2a1b663f10c6b6b8f397a84aadb828f12e5b289ec23a3a3c"

+[[package]]
+name = "bytesize"
+version = "1.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6c58ec36aac5066d5ca17df51b3e70279f5670a72102f5752cb7e7c856adfc70"
+
 [[package]]
 name = "cc"
 version = "1.0.78"
@@ -223,7 +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",
@@ -299,16 +324,16 @@ dependencies = [

 [[package]]
 name = "deduplicator"
-version = "0.1.1"
+version = "0.1.4"
 dependencies = [
 "anyhow",
+ "bytesize",
 "chrono",
 "clap",
 "colored",
 "dashmap",
 "fxhash",
- "glob",
- "humansize",
+ "globwalk",
 "indicatif",
 "itertools",
 "memmap2",
@@ -379,6 +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"
@@ -400,10 +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"
@@ -435,15 +484,6 @@ dependencies = [
 "libc",
 ]

-[[package]]
-name = "humansize"
-version = "2.1.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4e682e2bd70ecbcce5209f11a992a4ba001fea8e60acf7860ce007629e6d2756"
-dependencies = [
- "libm",
-]
-
 [[package]]
 name = "iana-time-zone"
 version = "0.1.53"
@@ -468,6 +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"
@@ -540,12 +597,6 @@ version = "0.2.139"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "201de327520df007757c1f0adce6e827fe8562fbc28bfd9c15571c66ca1f5f79"

-[[package]]
-name = "libm"
-version = "0.2.6"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "348108ab3fba42ec82ff6e9564fc4ca0247bdccdc68dd8af9764bbc79c3c8ffb"
-
 [[package]]
 name = "link-cplusplus"
 version = "1.0.8"
@@ -796,12 +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"
@@ -828,6 +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"
@@ -928,6 +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"
@@ -941,9 +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",
@@ -994,6 +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"
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -1,27 +1,31 @@
 [package]
 name = "deduplicator"
-version = "0.1.1"
+version = "0.1.4"
 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

 [dependencies]
 anyhow = "1.0.68"
+bytesize = "1.1.0"
 chrono = "0.4.23"
 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"
-humansize = "2.1.2"
+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"
--- a/README.md
+++ b/README.md
@@ -4,46 +4,97 @@
  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]

 Options:
-  -t, --types <TYPES>  Filetypes to deduplicate (default = all)
-      --dir <DIR>      Run Deduplicator on dir different from pwd
-  -i, --interactive    Delete files interactively
-  -h, --help           Print help information
-  -V, --version        Print version information
+  -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
 ```

-<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 --minsize 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 couple of seconds.</p>
-
-<p align="center">
-  While testing, Deduplicator was able to go through 8.6GB of pdf files and detect duplicates in 2.9 seconds
-</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)
--- a/src/filters.rs
+++ b/src/filters.rs
@@ -0,0 +1,12 @@
+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() {
+        Some(msize) => match file.size {
+            Some(fsize) => fsize >= msize,
+            None => true,
+        },
+        None => true,
+    }
+}
--- a/src/main.rs
+++ b/src/main.rs
@@ -3,6 +3,7 @@ mod file_manager;
 mod output;
 mod params;
 mod scanner;
+mod filters;

 use anyhow::Result;
 use app::App;
--- a/src/output.rs
+++ b/src/output.rs
@@ -5,7 +5,7 @@ use chrono::offset::Utc;
 use chrono::DateTime;
 use colored::Colorize;
 use dashmap::DashMap;
-use humansize::{format_size, DECIMAL};
+use indicatif::{ProgressBar, ProgressIterator, ProgressStyle};
 use itertools::Itertools;
 use prettytable::{format, row, Table};
 use std::io::Write;
@@ -13,7 +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)
@@ -27,13 +27,11 @@ fn format_path(path: &str, opts: &Params) -> Result<String> {
        display_path
    };

-    Ok(format!("...{:<32}", display_range))
+    Ok(format!("...{display_range:<32}"))
 }

-fn file_size(path: &String) -> Result<String> {
-    let mdata = fs::metadata(path)?;
-    let formatted_size = format!("{:>12}", format_size(mdata.len(), DECIMAL));
-    Ok(formatted_size)
+fn file_size(file: &File) -> Result<String> {
+    Ok(format!("{:>12}", bytesize::ByteSize::b(file.size.unwrap())))
 }

 fn modified_time(path: &String) -> Result<String> {
@@ -43,10 +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.");
@@ -118,10 +112,20 @@ 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{}",
+            "No duplicates found matching your search criteria.".green()
+        );
+        return;
+    }
+
    duplicates
        .clone()
        .into_iter()
+        .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))| {
            let mut itable = Table::new();
@@ -131,7 +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.path).unwrap_or_default().red(),
+                    file_size(file).unwrap_or_default().red(),
                    modified_time(&file.path).unwrap_or_default().yellow()
                ]);
            });
@@ -141,22 +145,39 @@ 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{}",
+            "No duplicates found matching your search criteria.".green()
+        );
+        return;
+    }

    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().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.path).unwrap_or_default().red(),
-                modified_time(&file.path).unwrap_or_default().yellow()
-            ]);
+
+    duplicates
+        .into_iter()
+        .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(),
+                    modified_time(&file.path).unwrap_or_default().yellow()
+                ]);
+            });
+            output_table.add_row(row![hash.green(), inner_table]);
        });
-        output_table.add_row(row![hash.green(), inner_table]);
-    });

    output_table.printstd();
 }
--- a/src/params.rs
+++ b/src/params.rs
@@ -1,7 +1,9 @@
-use anyhow::{anyhow, Result};
-use clap::Parser;
 use std::{fs, path::PathBuf};

+use anyhow::{anyhow, Result};
+use clap::{Parser, ValueHint};
+use globwalk::{GlobWalker, GlobWalkerBuilder};
+
 #[derive(Parser, Debug)]
 #[command(author, version, about, long_about = None)]
 pub struct Params {
@@ -9,42 +11,42 @@ pub struct Params {
    #[arg(short, long)]
    pub types: Option<String>,
    /// Run Deduplicator on dir different from pwd
-    #[arg(long)]
+    #[arg(long, value_hint = ValueHint::DirPath)]
    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]
+    #[arg(long, short)]
+    pub minsize: Option<String>,
 }

 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_minsize(&self) -> Option<u64> {
+        match &self.minsize {
+            Some(msize) => match msize.parse::<bytesize::ByteSize>() {
+                Ok(units) => Some(units.0),
+                Err(_) => None,
+            },
+            None => None,
+        }
+    }

+    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()
+    pub fn get_glob_walker(&self) -> Result<GlobWalker> {
+        let pattern: String = match self.types.as_ref() {
+            Some(filetypes) => format!("**/*{{{filetypes}}}"),
+            None => "**/*".to_string(),
+        };
+        // TODO: add params for maximum depth and following symlinks, then pass them to this builder
+        GlobWalkerBuilder::from_patterns(self.get_directory()?, &[pattern])
+            .build()
+            .map_err(|e| anyhow!(e))
    }
 }
--- a/src/scanner.rs
+++ b/src/scanner.rs
@@ -1,15 +1,14 @@
+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};

-use crate::{file_manager::File, params::Params};
-
 #[derive(Clone, Copy)]
 enum IndexCritera {
    Size,
@@ -28,12 +27,7 @@ pub fn duplicates(app_opts: &Params) -> Result<DashMap<String, Vec<File>>> {
        .collect::<Vec<File>>();

    if sizewize_duplicate_files.len() > 1 {
-        let size_wise_duplicate_paths = sizewize_duplicate_files
-            .into_par_iter()
-            .map(|file| file.path)
-            .collect::<Vec<String>>();
-
-        let hash_index_store = index_files(size_wise_duplicate_paths, IndexCritera::Hash)?;
+        let hash_index_store = index_files(sizewize_duplicate_files, IndexCritera::Hash)?;
        let duplicate_files = hash_index_store
            .into_par_iter()
            .filter(|(_, files)| files.len() > 1)
@@ -45,72 +39,60 @@ pub fn duplicates(app_opts: &Params) -> Result<DashMap<String, Vec<File>>> {
    }
 }

-fn scan(app_opts: &Params) -> Result<Vec<String>> {
-    let glob_patterns: Vec<PathBuf> = app_opts.get_glob_patterns();
-    let files: Vec<String> = glob_patterns
-        .par_iter()
+fn scan(app_opts: &Params) -> Result<Vec<File>> {
+    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(|fpath| fpath.display().to_string())
+        .map(|fpath| File {
+            path: fpath.clone(),
+            hash: None,
+            size: Some(fs::metadata(fpath).unwrap().len()),
        })
+        .filter(|file| filters::is_file_gt_minsize(app_opts, file))
        .collect();

    Ok(files)
 }

-fn process_file_size_index(fpath: String) -> Result<File> {
-    Ok(File {
-        path: fpath.clone(),
-        size: Some(fs::metadata(fpath)?.len()),
-        hash: None,
-    })
-}
-
-fn process_file_hash_index(fpath: String) -> Result<File> {
-    Ok(File {
-        path: fpath.clone(),
-        size: None,
-        hash: Some(hash_file(&fpath).unwrap_or_default()),
-    })
-}
-
 fn process_file_index(
-    fpath: String,
+    mut file: File,
    store: &DashMap<String, Vec<File>>,
    index_criteria: IndexCritera,
 ) {
    match index_criteria {
        IndexCritera::Size => {
-            let processed_file = process_file_size_index(fpath).unwrap();
            store
-                .entry(processed_file.size.unwrap_or_default().to_string())
-                .and_modify(|fileset| fileset.push(processed_file.clone()))
-                .or_insert_with(|| vec![processed_file]);
+                .entry(file.size.unwrap_or_default().to_string())
+                .and_modify(|fileset| fileset.push(file.clone()))
+                .or_insert_with(|| vec![file]);
        }
        IndexCritera::Hash => {
-            let processed_file = process_file_hash_index(fpath).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]);
        }
    }
 }

 fn index_files(
-    files: Vec<String>,
+    files: Vec<File>,
    index_criteria: IndexCritera,
 ) -> Result<DashMap<String, Vec<File>>> {
    let store: DashMap<String, Vec<File>> = DashMap::new();
@@ -124,7 +106,7 @@ fn index_files(
    Ok(store)
 }

-pub fn incremental_hashing(filepath: &str) -> Result<String> {
+fn incremental_hashing(filepath: &str) -> Result<String> {
    let file = fs::File::open(filepath)?;
    let fmap = unsafe { Mmap::map(&file)? };
    let mut inchasher = fxhash::FxHasher::default();
@@ -135,12 +117,12 @@ pub fn incremental_hashing(filepath: &str) -> Result<String> {
    Ok(format!("{}", inchasher.finish()))
 }

-pub fn standard_hashing(filepath: &str) -> Result<String> {
+fn standard_hashing(filepath: &str) -> Result<String> {
    let file = fs::read(filepath)?;
    Ok(hasher(&*file).to_string())
 }

-pub fn hash_file(filepath: &str) -> Result<String> {
+fn hash_file(filepath: &str) -> Result<String> {
    let filemeta = fs::metadata(filepath)?;

    // NOTE: USE INCREMENTAL HASHING ONLY FOR FILES > 100MB
Author	SHA1	Message	Date
Sreedev Kodichath	163e8d85c0	Merge pull request #38 from sreedevk/development Version 0.1.4	2023-01-23 18:35:28 -05:00
sreedev	b1c508e9e7	versioning changes	2023-01-23 18:33:06 -05:00
Sreedev Kodichath	4125b18d67	Merge pull request #42 from sreedevk/feature/add-outputgen-spinner Added more progress bars to avoid blank states	2023-01-23 18:30:56 -05:00
sreedev	10329015f7	added more progress bars to avoid blank states	2023-01-23 18:29:41 -05:00
Sreedev Kodichath	de6d2e325e	Merge pull request #41 from beeb/globwalk-builder refactor: use globwalk builder pattern	2023-01-23 17:50:09 -05:00
beeb	850c274adc	refactor: use globwalk builder pattern	2023-01-23 22:28:48 +01:00
sreedev	31d35aae51	Merge branch 'main' into development	2023-01-23 16:07:26 -05:00
Sreedev Kodichath	087f36ac52	Merge pull request #37 from beeb/globwalk Switch to globwalk	2023-01-23 16:06:14 -05:00
beeb	6f8b1d55df	feat: switch to globwalk	2023-01-23 21:53:44 +01:00
sreedev	c6318a310b	added benchmarks	2023-01-23 15:37:34 -05:00
Sreedev Kodichath	76c69ef8a0	Update README.md	2023-01-23 15:14:31 -05:00
sreedev	fd4e882aa8	updated README	2023-01-23 14:54:19 -05:00
sreedev	fd1d214d62	updated github workflows	2023-01-23 03:36:47 -05:00
sreedev	1a573fbf3f	release github flow changes	2023-01-23 03:24:12 -05:00
sreedev	b12b662ba1	workflow updates	2023-01-23 03:19:57 -05:00
sreedev	96337b6b48	artifacts upload options added to github workflows	2023-01-23 02:39:37 -05:00
sreedev	02f70aa55f	updated release github actions	2023-01-23 02:28:57 -05:00
Sreedev Kodichath	4a18b3fd91	Merge pull request #33 from sreedevk/development Version 0.1.3	2023-01-23 02:20:59 -05:00
sreedev	876fdc69ac	added version changes	2023-01-23 02:20:42 -05:00
sreedev	8acc3f8c8f	added github workflow for building binaries with releases	2023-01-23 02:18:23 -05:00
Sreedev Kodichath	38f6c48452	Merge pull request #35 from sreedevk/dependabot/cargo/tokio-1.23.1 build(deps): bump tokio from 1.23.0 to 1.23.1	2023-01-21 19:31:49 -05:00
sreedev	3e1e9c0e2e	Merge branch 'main' into development	2023-01-20 21:01:50 -05:00
Sreedev Kodichath	0674ab55bf	Update README.md	2023-01-20 21:01:47 -05:00
dependabot[bot]	ccff95dfc5	build(deps): bump tokio from 1.23.0 to 1.23.1 Bumps [tokio](https://github.com/tokio-rs/tokio) from 1.23.0 to 1.23.1. - [Release notes](https://github.com/tokio-rs/tokio/releases) - [Commits](https://github.com/tokio-rs/tokio/compare/tokio-1.23.0...tokio-1.23.1) --- updated-dependencies: - dependency-name: tokio dependency-type: direct:production ... Signed-off-by: dependabot[bot] <support@github.com>	2023-01-21 01:57:43 +00:00
Sreedev Kodichath	53d28abb62	Merge pull request #32 from sreedevk/performance/glob_improvements Performance/glob improvements	2023-01-20 19:17:39 -05:00
Sreedev Kodichath	ea6cf94952	Update README.md	2023-01-19 23:37:13 -05:00
sreedev	7b275d40d0	min opts 2	2023-01-19 23:27:40 -05:00
sreedev	30398c3ca9	min opts	2023-01-19 23:25:16 -05:00
sreedev	c0042fc9f7	version 0.1.2 release changes	2023-01-19 09:40:58 -05:00
Sreedev Kodichath	5aea0eb6f4	Merge pull request #28 from sreedevk/development Version 0.1.2	2023-01-19 09:39:59 -05:00
Sreedev Kodichath	f0ff1ec325	Merge pull request #27 from beeb/sorted_by_size Sort table results by ascending file size	2023-01-18 10:36:11 -05:00
Sreedev Kodichath	b267fcdedf	Merge pull request #29 from beeb/cli_value_hint feat(cli): add value hint for --dir argument	2023-01-18 10:28:15 -05:00
Valentin Bersier	84b194efca	feat(cli): add value hint for --dir argument	2023-01-18 15:40:10 +01:00
Valentin Bersier	d162ca98ef	docs: comment	2023-01-18 15:34:58 +01:00
Valentin Bersier	dfb73ceb5c	feat: sort interactive results by descending size	2023-01-18 15:33:23 +01:00
Valentin Bersier	72ca7c7a44	Merge branch 'development' into sorted_by_size	2023-01-18 15:24:47 +01:00
Sreedev Kodichath	2f3cfd3162	Merge pull request #26 from sreedevk/feature/min-filesize Min Size Filter Feature	2023-01-18 02:40:17 -05:00
sreedev	9b1f591c20	adds minsize option to README.md	2023-01-18 02:39:29 -05:00
sreedev	e24603c645	output enhancements	2023-01-18 02:34:08 -05:00
sreedev	0e624b042d	added minsize filter	2023-01-18 02:30:48 -05:00
Valentin Bersier	e61d1f1475	perf: unwrap the size once	2023-01-18 08:07:51 +01:00
Valentin Bersier	8c76c6a3c8	refactor: simplify iterator to get size	2023-01-18 08:00:53 +01:00
Valentin Bersier	df3bea3d4f	feat: display results in ascending size order	2023-01-18 07:59:51 +01:00
sreedev	7ace0bde63	scanner optimizations	2023-01-18 01:33:51 -05:00
sreedev	70de402eab	performance updates in README.md	2023-01-18 00:45:24 -05:00