tui improvements

* replaced fxhash with gxhash

.cargo/config.toml

@@ -0,0 +1,2 @@
+[build]
+rustflags = ["-C", "target-feature=+aes,+sse2"]

.github/ISSUE_TEMPLATE/bug_report.md

@@ -0,0 +1,30 @@
+---
+name: Bug report
+about: Create a report to help us improve
+title: "[Bug] Title"
+labels: ''
+assignees: ''
+
+---
+
+**Describe the bug**
+A clear and concise description of what the bug is.
+
+** Runtime Info **
+App Arguments: [e.g. `-i --nocache`] 
+Install Type: [e.g. `cargo install`]
+App Version: [e.g. v0.0.7]
+
+**Expected behavior**
+A clear and concise description of what you expected to happen.
+
+**Screenshots**
+If applicable, add screenshots to help explain your problem.
+
+**Platform Details (please complete the following information):**
+ - OS: [e.g. Arch Linux]
+ - Terminal Emulator: [e.g Alacritty]
+ - Shell [e.g. Zshell]
+
+**Additional context**
+Add any other context about the problem here.

.github/ISSUE_TEMPLATE/feature-request.md

@@ -0,0 +1,20 @@
+---
+name: Feature request
+about: Suggest an idea for this project
+title: "[Feature] Title"
+labels: ''
+assignees: ''
+
+---
+
+**Is your feature request related to a problem? Please describe.**
+A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
+
+**Describe the solution you'd like**
+A clear and concise description of what you want to happen.
+
+**Describe alternatives you've considered**
+A clear and concise description of any alternative solutions or features you've considered.
+
+**Additional context**
+Add any other context or screenshots about the feature request here.

.github/workflows/release.yml

@@ -0,0 +1,137 @@
+# CI that:
+#
+# * checks for a Git Tag that looks like a release
+# * creates a Github Release™ and fills in its text
+# * builds artifacts with cargo-dist (executable-zips, installers)
+# * uploads those artifacts to the Github Release™
+#
+# Note that the Github Release™ will be created before the artifacts,
+# so there will be a few minutes where the release has no artifacts
+# and then they will slowly trickle in, possibly failing. To make
+# this more pleasant we mark the release as a "draft" until all
+# artifacts have been successfully uploaded. This allows you to
+# choose what to do with partial successes and avoids spamming
+# anyone with notifications before the release is actually ready.
+name: Release
+
+permissions:
+  contents: write
+
+# This task will run whenever you push a git tag that looks like a version
+# like "v1", "v1.2.0", "v0.1.0-prerelease01", "my-app-v1.0.0", etc.
+# The version will be roughly parsed as ({PACKAGE_NAME}-)?v{VERSION}, where
+# PACKAGE_NAME must be the name of a Cargo package in your workspace, and VERSION
+# must be a Cargo-style SemVer Version.
+#
+# If PACKAGE_NAME is specified, then we will create a Github Release™ for that
+# package (erroring out if it doesn't have the given version or isn't cargo-dist-able).
+#
+# If PACKAGE_NAME isn't specified, then we will create a Github Release™ for all
+# (cargo-dist-able) packages in the workspace with that version (this is mode is
+# intended for workspaces with only one dist-able package, or with all dist-able
+# packages versioned/released in lockstep).
+#
+# If you push multiple tags at once, separate instances of this workflow will
+# spin up, creating an independent Github Release™ for each one.
+#
+# If there's a prerelease-style suffix to the version then the Github Release™
+# will be marked as a prerelease.
+on:
+  push:
+    tags:
+      - '*-?v[0-9]+*'
+
+jobs:
+  # Create the Github Release™ so the packages have something to be uploaded to
+  create-release:
+    runs-on: ubuntu-latest
+    outputs:
+      has-releases: ${{ steps.create-release.outputs.has-releases }}
+    env:
+      GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+    steps:
+      - uses: actions/checkout@v3
+      - name: Install Rust
+        run: rustup update 1.71.0 --no-self-update && rustup default 1.71.0
+      - name: Install cargo-dist
+        run: curl --proto '=https' --tlsv1.2 -LsSf https://github.com/axodotdev/cargo-dist/releases/download/v0.0.7/cargo-dist-installer.sh | sh
+      - id: create-release
+        run: |
+          cargo dist plan --tag=${{ github.ref_name }} --output-format=json > dist-manifest.json
+          echo "dist plan ran successfully"
+          cat dist-manifest.json
+
+          # Create the Github Release™ based on what cargo-dist thinks it should be
+          ANNOUNCEMENT_TITLE=$(jq --raw-output ".announcement_title" dist-manifest.json)
+          IS_PRERELEASE=$(jq --raw-output ".announcement_is_prerelease" dist-manifest.json)
+          jq --raw-output ".announcement_github_body" dist-manifest.json > new_dist_announcement.md
+          gh release create ${{ github.ref_name }} --draft --prerelease="$IS_PRERELEASE" --title="$ANNOUNCEMENT_TITLE" --notes-file=new_dist_announcement.md
+          echo "created announcement!"
+
+          # Upload the manifest to the Github Release™
+          gh release upload ${{ github.ref_name }} dist-manifest.json
+          echo "uploaded manifest!"
+
+          # Disable all the upload-artifacts tasks if we have no actual releases
+          HAS_RELEASES=$(jq --raw-output ".releases != null" dist-manifest.json)
+          echo "has-releases=$HAS_RELEASES" >> "$GITHUB_OUTPUT"
+
+  # Build and packages all the things
+  upload-artifacts:
+    # Let the initial task tell us to not run (currently very blunt)
+    needs: create-release
+    if: ${{ needs.create-release.outputs.has-releases == 'true' }}
+    strategy:
+      matrix:
+        # For these target platforms
+        include:
+        - os: macos-11
+          dist-args: --artifacts=local --target=aarch64-apple-darwin --target=x86_64-apple-darwin
+          install-dist: curl --proto '=https' --tlsv1.2 -LsSf https://github.com/axodotdev/cargo-dist/releases/download/v0.0.7/cargo-dist-installer.sh | sh
+        - os: ubuntu-20.04
+          dist-args: --artifacts=local --target=x86_64-unknown-linux-gnu
+          install-dist: curl --proto '=https' --tlsv1.2 -LsSf https://github.com/axodotdev/cargo-dist/releases/download/v0.0.7/cargo-dist-installer.sh | sh
+        - os: windows-2019
+          dist-args: --artifacts=local --target=x86_64-pc-windows-msvc
+          install-dist: irm  https://github.com/axodotdev/cargo-dist/releases/download/v0.0.7/cargo-dist-installer.ps1 | iex
+
+    runs-on: ${{ matrix.os }}
+    env:
+      GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+    steps:
+      - uses: actions/checkout@v3
+      - name: Install Rust
+        run: rustup update 1.71.0 --no-self-update && rustup default 1.71.0
+      - name: Install cargo-dist
+        run: ${{ matrix.install-dist }}
+      - name: Run cargo-dist
+        # This logic is a bit janky because it's trying to be a polyglot between
+        # powershell and bash since this will run on windows, macos, and linux!
+        # The two platforms don't agree on how to talk about env vars but they
+        # do agree on 'cat' and '$()' so we use that to marshal values between commands.
+        run: |
+          # Actually do builds and make zips and whatnot
+          cargo dist build --tag=${{ github.ref_name }} --output-format=json ${{ matrix.dist-args }} > dist-manifest.json
+          echo "dist ran successfully"
+          cat dist-manifest.json
+
+          # Parse out what we just built and upload it to the Github Release™
+          jq --raw-output ".artifacts[]?.path | select( . != null )" dist-manifest.json > uploads.txt
+          echo "uploading..."
+          cat uploads.txt
+          gh release upload ${{ github.ref_name }} $(cat uploads.txt)
+          echo "uploaded!"
+
+  # Mark the Github Release™ as a non-draft now that everything has succeeded!
+  publish-release:
+    # Only run after all the other tasks, but it's ok if upload-artifacts was skipped
+    needs: [create-release, upload-artifacts]
+    if: ${{ always() && needs.create-release.result == 'success' && (needs.upload-artifacts.result == 'skipped' || needs.upload-artifacts.result == 'success') }}
+    runs-on: ubuntu-latest
+    env:
+      GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+    steps:
+      - uses: actions/checkout@v3
+      - name: mark release as non-draft
+        run: |
+          gh release edit ${{ github.ref_name }} --draft=false

.gitignore

@@ -1,2 +1,4 @@
 /target
-/test_data
+/Cargo.lock
+/.bacon-locations
+/result-bin

CONTRIBUTING.md

@@ -0,0 +1,28 @@
+## How to contribute to Deduplicator
+
+#### **Did you find a bug?**
+
+* **Ensure the bug was not already reported** by searching on GitHub under [Issues](https://github.com/sreedevk/deduplicator/issues).
+
+* If you're unable to find an open issue addressing the problem, [open a new one](https://github.com/sreedevk/deduplicator/issues/new). Be sure to include a **title and clear description**, as much relevant information as possible, and a **code sample** or an **executable test case** demonstrating the expected behavior that is not occurring.
+
+* If possible, use the [bug report template](https://github.com/sreedevk/deduplicator/blob/main/.github/ISSUE_TEMPLATE/bug_report.md) to create the issue.
+
+#### **Would you like to write a fix for the bug?**
+* Assign the Issue to yourself (if unassigned) before you start working in order to avoid any conficts. 
+* Open a new GitHub pull request with the patch.
+* Ensure the PR description clearly describes the problem and solution. Include the relevant issue number.
+* Make sure that the PR points to the development branch.
+
+#### **Did you fix whitespace, format code, or make a purely cosmetic patch?**
+
+Changes that are cosmetic in nature and do not add anything substantial to the stability, functionality, or testability of Deduplicator will generally not be accepted/
+
+#### **Do you intend to add a new feature or change an existing one?**
+
+* First open an issue with the sugggestion using the [feature request template](https://github.com/sreedevk/deduplicator/blob/main/.github/ISSUE_TEMPLATE/feature-request.md)
+* Do not create a PR before one of the core contributors has conveyed acceptance for a feature request.
+
+#### **Do you have questions about the source code?**
+
+* If you have a question, raise an issue in the repository with a "question" label.

Cargo.toml

@@ -1,24 +1,51 @@
 [package]
 name = "deduplicator"
-version = "0.0.2"
+version = "0.2.2"
 edition = "2021"
 description = "find,filter,delete Duplicates"
+repository = "https://github.com/sreedevk/deduplicator"
 license = "MIT"
+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"
-crossterm = "0.25.0"
-fxhash = "0.2.1"
-glob = "0.3.0"
-humansize = "2.1.2"
+dashmap = { version = "5.4.0", features = ["rayon"] }
+globwalk = "0.8.1"
+gxhash = "3.4.1"
+indicatif = { version = "0.17.2", features = ["rayon"] }
 itertools = "0.10.5"
+memmap2 = "0.5.8"
+pathdiff = "0.2.1"
+prettytable-rs = "0.10.0"
+ratatui = "0.29.0"
 rayon = "1.6.1"
-sqlite = "0.30.3"
-thiserror = "1.0.38"
-tokio = { version = "1.23.0", features = ["full"] }
-tui = "0.19.0"
+serde = { version = "1.0.192", features = ["derive"] }
+serde_json = "1.0.108"
+tempfile = "3.20.0"
+threadpool = "1.8.1"
+unicode-segmentation = "1.10.0"
+uuid = { version = "1.17.0", features = ["v4"] }
+
+[profile.release]
+strip = true
+
+# generated by 'cargo dist init'
+[profile.dist]
+inherits = "release"
+lto = "thin"
+
+[workspace.metadata.dist]
+rust-toolchain-version = "1.78.0"
+ci = ["github"]
+targets = ["x86_64-unknown-linux-gnu", "x86_64-apple-darwin", "x86_64-pc-windows-msvc", "aarch64-apple-darwin"]
+cargo-dist-version = "0.0.7"

README.md

@@ -4,42 +4,132 @@
   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
-  -n, --nocache        Don't use cache for indexing files (default = true)
-  -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
+      --json                    
+```
+### 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
+
+> [!WARNING] Note from GxHash: GxHash relies on aes hardware acceleration, you must make sure the aes feature is enabled when building (otherwise it won't build). This can be done by setting the RUSTFLAGS environment variable to -C target-feature=+aes or -C target-cpu=native (the latter should work if your CPU is properly recognized by rustc, which is the case most of the time).
+> please install version `0.2.1`  if you are unable to install `0.2.2`
+
+```bash
+$ RUSTFLAGS="-C target-cpu=native" 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 | Filecount | Mean [ms] | Min [ms] | Max [ms] | Relative |
+|:---|:---|---:|---:|---:|---:|---:|
+| `deduplicator ~/Data/tmp` | (~120G) | 721 files | 33.5 ± 28.6 | 25.3 | 151.5 | 1.87 ± 1.60 |
+| `deduplicator ~/Data/books` | (~8.6G) | 1419 files | 24.5 ± 1.0 | 22.9 | 28.1 | 1.37 ± 0.08 |
+| `deduplicator ~/Data/books --min-size 10M` | (~8.6G) | 1419 files | 17.9 ± 0.7 | 16.8 | 20.0 | 1.00 |
+| `deduplicator ~/Data/ --types pdf,jpg,png,jpeg` | (~290G) | 104222 files | 1207.2 ± 37.0 | 1172.2 | 1287.7 | 67.27 ± 3.33 |
+
+* 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>
+## Screenshots
 
-<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>
+![](https://user-images.githubusercontent.com/36154121/213618143-e5182e39-731e-4817-87dd-1a6a0f38a449.gif)
 
-  <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>
-
-![_039](https://user-images.githubusercontent.com/36154121/210031222-d8b79143-5a1e-47ca-926e-8855d5bbab60.png)
+## Roadmap
+    - Tree format output for duplicate file listing
+    - GUI
+    - Packages for different operating system repositories (currently only installable via cargo) 
+    - TUI: Improve Key Handling

src/app.rs

@@ -0,0 +1,72 @@
+use std::sync::mpsc::channel;
+use std::sync::Arc;
+
+use anyhow::{anyhow, Result};
+use threadpool::ThreadPool;
+
+use crate::params::Params;
+use crate::server::{Message, Server};
+use crate::tui::Tui;
+
+pub struct App {
+    tpool: ThreadPool,
+    server: Arc<Server>,
+    app_opts: Arc<Params>,
+}
+
+impl App {
+    pub fn new(app_opts: Arc<Params>) -> Self {
+        Self {
+            tpool: ThreadPool::new(8),
+            server: Arc::new(Server::new().expect("server init failed")),
+            app_opts,
+        }
+    }
+
+    pub fn start(&self) -> Result<()> {
+        let (server_tx, server_rx) = channel::<Message>();
+        let (app_tx, app_rx) = channel::<Message>();
+
+        let server_ptr = self.server.clone();
+        let tui_server_ptr = self.server.clone();
+        let mut ui = Tui::new(app_tx.clone(), tui_server_ptr);
+        let root_dir = self
+            .app_opts
+            .get_directory()?
+            .into_os_string()
+            .into_string()
+            .map_err(|_| anyhow!("path to str conv failed"))?
+            .into_boxed_str();
+
+        self.tpool.execute(move || {
+            server_ptr.start(server_rx).expect("server init failed");
+        });
+
+        self.tpool.execute(move || {
+            ui.start().expect("ui init failed");
+        });
+
+        self.tpool.execute(move || loop {
+            match app_rx.try_recv() {
+                Ok(Message::Exit) => {
+                    server_tx
+                        .send(Message::Exit)
+                        .expect("message passing to app from ui failed.");
+                    break;
+                }
+                Ok(Message::AddScanDirectory(dir)) => {
+                    server_tx
+                        .send(Message::AddScanDirectory(dir))
+                        .expect("message passing to server failed.");
+                }
+                _ => continue,
+            }
+        });
+
+        app_tx.send(Message::AddScanDirectory(root_dir))?;
+
+        self.tpool.join();
+
+        Ok(())
+    }
+}

src/app/event_handler.rs

@@ -1,28 +0,0 @@
-use std::time::Duration;
-
-use crossterm::event::{self, KeyCode, KeyEvent};
-use anyhow::Result;
-use super::events;
-
-pub struct EventHandler;
-
-impl EventHandler {
-    pub fn init() -> Result<events::Event> {
-        if crossterm::event::poll(Duration::from_millis(10))? {
-            match event::read()? {
-                event::Event::Key(keycode) => Self::handle_keypress(keycode),
-                _ => Ok(events::Event::Noop),
-            }
-        } else {
-            Ok(events::Event::Noop)
-        }
-    }
-
-    fn handle_keypress(keyevent: KeyEvent) -> Result<events::Event> {
-        match keyevent.code {
-            KeyCode::Char('q') => Ok(events::Event::Exit),
-            _ => Ok(events::Event::Noop)
-        }
-    }
-}
-

src/app/events.rs

@@ -1,4 +0,0 @@
-pub enum Event {
-    Exit,
-    Noop
-}

src/app/mod.rs

@@ -1,80 +0,0 @@
-mod event_handler;
-mod events;
-mod ui;
-mod formatter;
-
-use crate::database;
-use crate::output;
-use crate::params::Params;
-use crate::scanner;
-use anyhow::{anyhow, Result};
-use crossterm::{event, execute, terminal};
-use event_handler::EventHandler;
-use std::io;
-use std::thread;
-use std::time::Duration;
-use tui::{
-    backend::CrosstermBackend,
-    widgets::{Block, Borders, Widget},
-    Terminal,
-};
-use ui::Ui;
-
-pub struct App;
-
-impl App {
-    pub fn init(app_args: &Params) -> Result<()> {
-        // let mut term = Self::init_terminal()?;
-
-        let connection = database::get_connection(&app_args)?;
-        let duplicates = scanner::duplicates(&app_args, &connection)?;
-
-        // Self::init_render_loop(&mut term)?;
-        // Self::cleanup(&mut term)?;
-
-        output::print(duplicates, &app_args); /* TODO: APP TUI INIT FUNCTION */
-        Ok(())
-    }
-
-    fn cleanup(term: &mut Terminal<CrosstermBackend<io::Stdout>>) -> Result<()> {
-        terminal::disable_raw_mode()?;
-        execute!(
-            term.backend_mut(),
-            terminal::LeaveAlternateScreen,
-            event::DisableMouseCapture
-        )?;
-
-        term.show_cursor()?;
-        Ok(())
-    }
-
-    fn render_cycle(term: &mut Terminal<CrosstermBackend<io::Stdout>>) -> Result<()> {
-        match EventHandler::init()? {
-            events::Event::Noop => Ui::render_frame(term),
-            events::Event::Exit => Err(anyhow!("Exit")),
-        }
-    }
-
-    fn init_render_loop(term: &mut Terminal<CrosstermBackend<io::Stdout>>) -> Result<()> {
-        loop {
-            match Self::render_cycle(term) {
-                Ok(_) => continue,
-                Err(_) => break,
-            }
-        }
-
-        Ok(())
-    }
-
-    fn init_terminal() -> Result<Terminal<CrosstermBackend<io::Stdout>>> {
-        terminal::enable_raw_mode()?;
-        let mut stdout = io::stdout();
-        execute!(
-            stdout,
-            terminal::EnterAlternateScreen,
-            event::EnableMouseCapture
-        )?;
-        let backend = CrosstermBackend::new(stdout);
-        Ok(Terminal::new(backend)?)
-    }
-}

src/app/ui.rs

@@ -1,53 +0,0 @@
-use anyhow::Result;
-use std::io;
-use tui::{
-    backend::{Backend, CrosstermBackend},
-    layout::{Constraint, Direction, Layout, Rect},
-    style::{Modifier, Style},
-    text::{Span, Spans},
-    widgets::{Block, Borders, List, ListItem, Widget},
-    Frame, Terminal,
-};
-
-pub struct Ui;
-
-impl Ui {
-    fn generate_file_list() -> impl Widget {
-        let tasks: Vec<ListItem> = vec!["Sreedev"; 100]
-            .into_iter()
-            .map(|item| ListItem::new(vec![Spans::from(Span::raw(item))]))
-            .collect();
-
-        List::new(tasks)
-            .block(Block::default().borders(Borders::ALL).title("List"))
-            .highlight_style(Style::default().add_modifier(Modifier::BOLD))
-            .highlight_symbol("> ")
-    }
-
-    fn generate_info_bar() -> impl Widget {
-        Block::default().title("Description").borders(Borders::ALL)
-    }
-
-    fn generate_file_desc() -> impl Widget {
-        Block::default().title("Description").borders(Borders::ALL)
-    }
-
-    pub fn render_frame(term: &mut Terminal<CrosstermBackend<io::Stdout>>) -> Result<()> {
-        term.draw(|f| {
-            let windows = Layout::default()
-                .direction(Direction::Vertical)
-                .constraints([Constraint::Ratio(2, 16), Constraint::Ratio(14, 16)].as_ref())
-                .split(f.size());
-
-            let subwindows = Layout::default()
-                .direction(Direction::Horizontal)
-                .constraints([Constraint::Ratio(1, 4), Constraint::Ratio(3, 4)].as_ref())
-                .split(windows[1]);
-
-            f.render_widget(Self::generate_info_bar(), windows[0]);
-            f.render_widget(Self::generate_file_list(), subwindows[0]);
-            f.render_widget(Self::generate_file_desc(), subwindows[1]);
-        })?;
-        Ok(())
-    }
-}

src/database.rs

@@ -1,83 +0,0 @@
-use anyhow::Result;
-use crate::params::Params;
-
-#[derive(Debug, Clone)]
-pub struct File {
-    pub path: String,
-    pub hash: String,
-}
-
-pub fn get_connection(args: &Params) -> Result<sqlite::Connection, sqlite::Error> {
-    let connection_url = match args.nocache {
-        false => "/tmp/deduplicator.db",
-        true => ":memory:"
-    };
-
-    sqlite::open(connection_url).and_then(|conn| {
-        setup(&conn).ok();
-        Ok(conn)
-    })
-}
-
-pub fn setup(connection: &sqlite::Connection) -> Result<()> {
-    let query = "CREATE TABLE files (file_identifier STRING, hash STRING)";
-    connection.execute(query).ok();
-    Ok(())
-}
-
-pub fn put(file: &File, connection: &sqlite::Connection) -> Result<()> {
-    let query = format!(
-        "INSERT INTO files (file_identifier, hash) VALUES (\"{}\", \"{}\")",
-        file.path, file.hash
-    );
-    let result = connection.execute(query)?;
-
-    Ok(result)
-}
-
-pub fn indexed_paths(connection: &sqlite::Connection) -> Result<Vec<File>> {
-    let query = format!(
-        "SELECT * FROM files"
-        );
-
-    let result: Vec<File> = connection
-        .prepare(query)?
-        .into_iter()
-        .map(|row_result| row_result.unwrap())
-        .map(|row| {
-            let path = row.read::<&str, _>("file_identifier").to_string();
-            let hash = row.read::<i64, _>("hash").to_string();
-            File { path, hash }
-        })
-    .collect();
-
-    Ok(result)
-}
-
-pub fn duplicate_hashes(connection: &sqlite::Connection, path: &String) -> Result<Vec<File>> {
-    let query = format!(
-        " 
-            SELECT a.* FROM files a
-            JOIN (SELECT file_identifier, hash, COUNT(*)
-            FROM files 
-            GROUP BY hash
-            HAVING count(*) > 1 ) b
-            ON a.hash = b.hash
-            WHERE a.file_identifier LIKE \"{}%\"
-            ORDER BY a.file_identifier
-        ", path
-    );
-
-    let result: Vec<File> = connection
-        .prepare(query)?
-        .into_iter()
-        .map(|row_result| row_result.unwrap())
-        .map(|row| {
-            let path = row.read::<&str, _>("file_identifier").to_string();
-            let hash = row.read::<i64, _>("hash").to_string();
-            File { path, hash }
-        })
-        .collect();
-
-    Ok(result)
-}

src/fileinfo.rs

@@ -0,0 +1,43 @@
+use anyhow::Result;
+use gxhash::GxHasher;
+use memmap2::Mmap;
+use serde::Serialize;
+use std::fs;
+use std::hash::Hasher;
+use std::{fs::Metadata, path::PathBuf};
+
+#[derive(Debug, Clone, Serialize)]
+pub struct FileInfo {
+    pub path: PathBuf,
+    pub hash: Option<String>,
+    pub size: u64,
+    #[serde(skip)]
+    pub filemeta: Metadata,
+}
+
+impl FileInfo {
+    pub fn hash(&self) -> Result<Self> {
+        let file = fs::File::open(self.path.clone())?;
+        let mapper = unsafe { Mmap::map(&file)? };
+        let mut primhasher = GxHasher::default();
+
+        mapper
+            .chunks(1_000_000)
+            .for_each(|chunk| primhasher.write(chunk));
+
+        Ok(Self {
+            hash: Some(primhasher.finish().to_string()),
+            ..self.clone()
+        })
+    }
+
+    pub fn new(path: PathBuf) -> Result<Self> {
+        let filemeta = std::fs::metadata(path.clone())?;
+        Ok(Self {
+            path,
+            filemeta: filemeta.clone(),
+            hash: None,
+            size: filemeta.len(),
+        })
+    }
+}

src/formatter.rs

@@ -0,0 +1,134 @@
+pub struct Formatter;
+use crate::fileinfo::FileInfo;
+use crate::params::Params;
+use anyhow::Result;
+use chrono::{DateTime, Utc};
+use colored::Colorize;
+use dashmap::DashMap;
+use indicatif::{
+    ParallelProgressIterator, ProgressBar, ProgressFinish, ProgressIterator, ProgressStyle,
+};
+use pathdiff::diff_paths;
+use prettytable::{format, row, Table};
+use rayon::prelude::*;
+use std::borrow::Cow;
+use std::path::PathBuf;
+use std::time::Duration;
+
+impl Formatter {
+    pub fn human_path(
+        file: &FileInfo,
+        app_args: &Params,
+        min_path_length: usize,
+    ) -> Result<String> {
+        let base_directory: PathBuf = app_args.get_directory()?;
+        let relative_path = diff_paths(file.path.clone(), base_directory).unwrap_or_default();
+
+        let formatted_path = format!(
+            "{:<0width$}",
+            relative_path.to_str().unwrap_or_default().to_string(),
+            width = min_path_length
+        );
+
+        Ok(formatted_path)
+    }
+
+    pub fn human_filesize(file: &FileInfo) -> Result<String> {
+        Ok(format!("{:>12}", bytesize::ByteSize::b(file.size)))
+    }
+
+    pub fn human_mtime(file: &FileInfo) -> Result<String> {
+        let modified_time: DateTime<Utc> = file.filemeta.modified()?.into();
+        Ok(modified_time.format("%Y-%m-%d %H:%M:%S").to_string())
+    }
+
+    pub fn generate_table(raw: Vec<FileInfo>, app_args: &Params) -> Result<Table> {
+        let basepath_length = app_args.get_directory()?.to_str().unwrap_or_default().len();
+        let max_filepath_length = raw
+            .iter()
+            .map(|file| file.path.to_str().unwrap_or_default().len())
+            .max()
+            .unwrap_or_default();
+
+        let min_path_length = if max_filepath_length > basepath_length {
+            max_filepath_length - basepath_length
+        } else {
+            0
+        };
+
+        let progress_style = ProgressStyle::with_template(
+            "[{elapsed_precise}] {bar:40.cyan/blue} {pos:>7}/{len:7} {msg}",
+        )?;
+        let progress_bar = ProgressBar::new(raw.len() as u64);
+        progress_bar.set_style(progress_style);
+        progress_bar.enable_steady_tick(Duration::from_millis(50));
+        progress_bar.set_message("reconciling data");
+
+        let duplicates_table: DashMap<String, Vec<FileInfo>> = DashMap::new();
+        raw.into_par_iter()
+            .progress_with(progress_bar)
+            .with_finish(ProgressFinish::WithMessage(Cow::from("data reconciled")))
+            .map(|file| file.hash())
+            .filter_map(Result::ok)
+            .for_each(|file| {
+                duplicates_table
+                    .entry(file.hash.clone().unwrap_or_default())
+                    .and_modify(|fileset| fileset.push(file.clone()))
+                    .or_insert_with(|| vec![file]);
+            });
+
+        let mut output_table = Table::new();
+        output_table.set_titles(row!["hash", "duplicates"]);
+
+        let progress_style = ProgressStyle::with_template(
+            "[{elapsed_precise}] {bar:40.cyan/blue} {pos:>7}/{len:7} {msg}",
+        )?;
+
+        let progress_bar = ProgressBar::new(duplicates_table.len() as u64);
+        progress_bar.set_style(progress_style);
+        progress_bar.enable_steady_tick(Duration::from_millis(50));
+        progress_bar.set_message("generating output");
+
+        duplicates_table
+            .into_iter()
+            .progress_with(progress_bar)
+            .with_finish(ProgressFinish::WithMessage(Cow::from("output generated")))
+            .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![
+                        Self::human_path(file, app_args, min_path_length)
+                            .unwrap_or_default()
+                            .blue(),
+                        Self::human_filesize(file).unwrap_or_default().red(),
+                        Self::human_mtime(file).unwrap_or_default().yellow()
+                    ]);
+                });
+
+                output_table.add_row(row![hash.green(), inner_table]);
+            });
+
+        Ok(output_table)
+    }
+
+    pub fn print(raw: Vec<FileInfo>, app_args: &Params) -> Result<()> {
+        if raw.is_empty() {
+            println!(
+                "\n\n{}\n",
+                "No duplicates found matching your search criteria.".green()
+            );
+            return Ok(());
+        }
+
+        if app_args.json {
+            let output_json = serde_json::to_string_pretty(&raw)?;
+            println!("{}", output_json);
+        } else {
+            let output_table = Self::generate_table(raw, app_args)?;
+            output_table.printstd();
+        }
+
+        Ok(())
+    }
+}

src/interactive.rs

@@ -0,0 +1,154 @@
+use crate::formatter::Formatter;
+use crate::{fileinfo::FileInfo, params::Params};
+use anyhow::Result;
+use colored::Colorize;
+use dashmap::DashMap;
+use indicatif::{ParallelProgressIterator, ProgressBar, ProgressFinish, ProgressStyle};
+use prettytable::{format, row, Table};
+use rayon::prelude::*;
+use std::{
+    borrow::Cow,
+    io::{self, Write},
+    time::Duration,
+};
+
+pub fn scan_group_confirmation() -> Result<bool> {
+    print!("\nconfirm? [y/N]: ");
+    std::io::stdout().flush()?;
+    let mut user_input = String::new();
+    io::stdin().read_line(&mut user_input)?;
+
+    match user_input.trim() {
+        "Y" | "y" => Ok(true),
+        _ => Ok(false),
+    }
+}
+
+pub 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.");
+    println!("example: 1,2");
+    print!("\n> ");
+    std::io::stdout().flush()?;
+    let mut user_input = String::new();
+    io::stdin().read_line(&mut user_input)?;
+
+    Ok(user_input)
+}
+
+pub fn init(result: Vec<FileInfo>, app_args: &Params) -> Result<()> {
+    let basepath_length = app_args.get_directory()?.to_str().unwrap_or_default().len();
+    let max_filepath_length = result
+        .iter()
+        .map(|file| file.path.to_str().unwrap_or_default().len())
+        .max()
+        .unwrap_or_default();
+
+    let min_path_length = if max_filepath_length > basepath_length {
+        max_filepath_length - basepath_length
+    } else {
+        0
+    };
+
+    let progress_style = ProgressStyle::with_template(
+        "[{elapsed_precise}] {bar:40.cyan/blue} {pos:>7}/{len:7} {msg}",
+    )?;
+    let progress_bar = ProgressBar::new(result.len() as u64);
+    progress_bar.set_style(progress_style);
+    progress_bar.enable_steady_tick(Duration::from_millis(50));
+    progress_bar.set_message("reconciling data");
+
+    let duplicates: DashMap<String, Vec<FileInfo>> = DashMap::new();
+    result
+        .into_par_iter()
+        .progress_with(progress_bar)
+        .with_finish(ProgressFinish::WithMessage(Cow::from("data reconciled")))
+        .map(|file| file.hash())
+        .filter_map(Result::ok)
+        .for_each(|file| {
+            duplicates
+                .entry(file.hash.clone().unwrap_or_default())
+                .and_modify(|fileset| fileset.push(file.clone()))
+                .or_insert_with(|| vec![file]);
+        });
+
+    duplicates
+        .clone()
+        .into_iter()
+        .enumerate()
+        .for_each(|(gindex, (_, group))| {
+            let mut itable = Table::new();
+            itable.set_format(*format::consts::FORMAT_NO_BORDER_LINE_SEPARATOR);
+            itable.set_titles(row!["index", "filename", "size", "updated_at"]);
+            group.iter().enumerate().for_each(|(index, file)| {
+                itable.add_row(row![
+                    index,
+                    Formatter::human_path(file, app_args, min_path_length)
+                        .unwrap_or_default()
+                        .blue(),
+                    Formatter::human_filesize(file).unwrap_or_default().red(),
+                    Formatter::human_mtime(file).unwrap_or_default().yellow()
+                ]);
+            });
+
+            process_group_action(&group, gindex, duplicates.len(), itable);
+        });
+
+    Ok(())
+}
+
+pub fn process_group_action(
+    duplicates: &Vec<FileInfo>,
+    dup_index: usize,
+    dup_size: usize,
+    table: Table,
+) {
+    println!("\nDuplicate Set {} of {}\n", dup_index + 1, dup_size);
+    table.printstd();
+    let files_to_delete = scan_group_instruction().unwrap_or_default();
+    let parsed_file_indices = files_to_delete
+        .trim()
+        .split(',')
+        .filter(|element| !element.is_empty())
+        .map(|index| index.parse::<usize>().unwrap_or_default())
+        .collect::<Vec<usize>>();
+
+    if parsed_file_indices
+        .clone()
+        .into_iter()
+        .any(|index| index > (duplicates.len() - 1))
+    {
+        println!("{}", "Err: File Index Out of Bounds!".red());
+        return process_group_action(duplicates, dup_index, dup_size, table);
+    }
+
+    print!("{esc}[2J{esc}[1;1H", esc = 27 as char);
+
+    if parsed_file_indices.is_empty() {
+        return;
+    }
+
+    let files_to_delete = parsed_file_indices
+        .into_iter()
+        .map(|index| duplicates[index].clone());
+
+    println!("\n{}", "The following files will be deleted:".red());
+    files_to_delete
+        .clone()
+        .enumerate()
+        .for_each(|(index, file)| {
+            println!("{}: {}", index.to_string().blue(), file.path.display());
+        });
+
+    match scan_group_confirmation().unwrap() {
+        true => {
+            files_to_delete.into_iter().for_each(|file| {
+                match std::fs::remove_file(file.path.clone()) {
+                    Ok(_) => println!("{}: {}", "DELETED".green(), file.path.display()),
+                    Err(_) => println!("{}: {}", "FAILED".red(), file.path.display()),
+                }
+            });
+        }
+        false => println!("{}", "\nCancelled Delete Operation.".red()),
+    }
+}

src/main.rs

@@ -1,14 +1,40 @@
-mod params;
-mod database;
-mod output;
-mod scanner;
 mod app;
+mod fileinfo;
+mod formatter;
+mod interactive;
+mod params;
+mod processor;
+mod scanner;
+
+/* version 2.0 modules*/
+mod cli;
+mod server;
+mod tui;
 
 use anyhow::Result;
-use clap::Parser;
-use app::App;
 
-#[tokio::main]
-async fn main() -> Result<()> {
-    App::init(&params::Params::parse())
+use self::app::App;
+use clap::Parser;
+use params::Params;
+use std::sync::Arc;
+// use formatter::Formatter;
+// use processor::Processor;
+// use scanner::Scanner;
+
+fn main() -> Result<()> {
+    let app_args = Params::parse();
+    // let scan_results = Scanner::build(&app_args)?.scan()?;
+    // let processor = Processor::new(scan_results);
+    // let results = processor.sizewise()?.hashwise()?;
+
+    // match app_args.interactive {
+    //     false => Formatter::print(results.files, &app_args)?,
+    //     true => interactive::init(results.files, &app_args)?,
+    // }
+
+    App::new(Arc::new(app_args))
+        .start()
+        .expect("app init failed.");
+
+    Ok(())
 }

src/output.rs

@@ -1,66 +0,0 @@
-use crate::database::File;
-use chrono::offset::Utc;
-use chrono::DateTime;
-use colored::Colorize;
-use humansize::{format_size, DECIMAL};
-use std::{collections::HashMap, fs};
-use crate::params::Params;
-
-fn format_path(path: &String, opts: &Params) -> String {
-    let display_path = path.replace(&opts.get_directory().unwrap(), "");
-    let display_range = if display_path.len() > 32 {
-            &display_path[(display_path.len() - 32)..]
-    } else {
-        &display_path[..]
-    };
-    
-    format!("...{}", display_range)
-}
-
-fn file_size(path: &String) -> String {
-    let mdata = fs::metadata(path).unwrap();
-    let formatted_size = format_size(mdata.len(), DECIMAL);
-    format!("{}", formatted_size)
-}
-
-fn modified_time(path: &String) -> String {
-    let mdata = fs::metadata(path).unwrap();
-    let modified_time: DateTime<Utc> = mdata.modified().unwrap().into();
-
-    modified_time.format("%Y-%m-%d %H:%M:%S").to_string()
-}
-
-fn print_divider() {
-    println!("-------------------+-------------------------------------+------------------+----------------------------------+");
-}
-
-pub fn print(duplicates: Vec<File>, opts: &Params) {
-    print_divider();
-    println!(
-        "| {0: <16} | {1: <35} | {2: <16} | {3: <32} |",
-        "hash", "filename", "size", "updated_at"
-    );
-    print_divider();
-
-    let mut dup_index: HashMap<String, Vec<File>> = HashMap::new();
-
-    duplicates.into_iter().for_each(|file| {
-        dup_index
-            .entry(file.hash.clone())
-            .and_modify(|value| value.push(file.clone()))
-            .or_insert(vec![file]);
-    });
-
-    dup_index.into_iter().for_each(|(_, group)| {
-        group.into_iter().for_each(|file| {
-            println!(
-                "| {0: <16} | {1: <35} | {2: <16} | {3: <32} |",
-                file.hash.red(),
-                format_path(&file.path, opts).yellow(),
-                file_size(&file.path).blue(),
-                modified_time(&file.path).blue()
-            );
-        });
-        print_divider();
-    });
-}

src/params.rs

@@ -1,40 +1,56 @@
-use std::path::PathBuf;
-use clap::Parser;
-use anyhow::Result;
-use std::fs;
+use std::{fs, path::PathBuf};
 
-#[derive(Parser, Debug)]
+use anyhow::Result;
+use clap::{Parser, ValueHint};
+
+#[derive(Parser, Debug, Clone)]
 #[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)]
+    /// Run Deduplicator on dir different from pwd (e.g., ~/Pictures )
+    #[arg(value_hint = ValueHint::DirPath, value_name = "scan_dir_path")]
     pub dir: Option<PathBuf>,
-    /// Don't use cache for indexing files (default = true)
+    /// Delete files interactively
     #[arg(long, short)]
-    pub nocache: bool,
+    pub interactive: bool,
+    /// 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 follow_links: bool,
+    /// print json output
+    #[arg(long)]
+    pub json: bool,
 }
 
 impl Params {
-    pub fn get_directory(&self) -> Result<String> {
-        let dir_string: String = self
-            .dir
-            .clone()
-            .unwrap_or(std::env::current_dir()?)
-            .as_os_str()
-            .to_str()
-            .unwrap()
-            .to_string();
-
-        let dir_pathbuf = PathBuf::from(&dir_string);
-        let dir = fs::canonicalize(&dir_pathbuf)?
-            .as_os_str()
-            .to_str()
-            .unwrap()
-            .to_string();
+    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,
+            },
+            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_types(&self) -> Option<String> {
+        self.types.clone()
+    }
 }

src/processor.rs

@@ -0,0 +1,107 @@
+use anyhow::Result;
+use dashmap::DashMap;
+use indicatif::{ParallelProgressIterator, ProgressBar, ProgressStyle, ProgressFinish};
+use rayon::prelude::{IntoParallelIterator, ParallelIterator};
+use std::{time::Duration, borrow::Cow};
+
+use crate::fileinfo::FileInfo;
+
+#[derive(Debug, Clone)]
+pub enum State {
+    Initial,
+    SizeWise,
+    HashWise,
+}
+
+#[derive(Debug, Clone)]
+pub struct Processor {
+    pub files: Vec<FileInfo>,
+    pub state: State,
+}
+
+impl Processor {
+    pub fn new(files: Vec<FileInfo>) -> Self {
+        Self {
+            files,
+            state: State::Initial,
+        }
+    }
+
+    pub fn hashwise(&self) -> Result<Self> {
+        if self.files.is_empty() {
+            return Ok(self.clone());
+        }
+
+        let progress_style = ProgressStyle::with_template("[{elapsed_precise}] {bar:40.cyan/blue} {pos:>7}/{len:7} {msg}")?;
+        let progress_bar = ProgressBar::new(self.files.len() as u64);
+        progress_bar.set_style(progress_style);
+        progress_bar.enable_steady_tick(Duration::from_millis(50));
+        progress_bar.set_message("indexing file hashes");
+
+        let duplicates_table: DashMap<String, Vec<FileInfo>> = DashMap::new();
+        self.files
+            .clone()
+            .into_par_iter()
+            .progress_with(progress_bar)
+            .with_finish(ProgressFinish::WithMessage(Cow::from("indexed files hashes")))
+            .map(|file| file.hash())
+            .filter_map(Result::ok)
+            .for_each(|file| {
+                duplicates_table
+                    .entry(file.hash.clone().unwrap_or_default())
+                    .and_modify(|fileset| fileset.push(file.clone()))
+                    .or_insert_with(|| vec![file]);
+            });
+
+        let files = duplicates_table
+            .into_read_only()
+            .values()
+            .cloned()
+            .filter(|subfiles| subfiles.len() > 1)
+            .flatten()
+            .collect::<Vec<FileInfo>>();
+
+        Ok(Self {
+            files,
+            state: State::HashWise,
+        })
+    }
+
+    pub fn sizewise(&self) -> Result<Self> {
+        if self.files.is_empty() {
+            return Ok(self.clone());
+        }
+
+        let progress_style = ProgressStyle::with_template("[{elapsed_precise}] {bar:40.cyan/blue} {pos:>7}/{len:7} {msg}")?;
+        let progress_bar = ProgressBar::new(self.files.len() as u64);
+        progress_bar.set_style(progress_style);
+        progress_bar.enable_steady_tick(Duration::from_millis(50));
+        progress_bar.set_message("indexing file sizes");
+
+        let duplicates_table: DashMap<u64, Vec<FileInfo>> = DashMap::new();
+        self.files
+            .clone()
+            .into_par_iter()
+            .progress_with(progress_bar)
+            .with_finish(ProgressFinish::WithMessage(Cow::from("indexed files sizes")))
+            .for_each(|file| {
+                duplicates_table
+                    .entry(file.size)
+                    .and_modify(|fileset| fileset.push(file.clone()))
+                    .or_insert_with(|| vec![file]);
+            });
+
+        let files = duplicates_table
+            .into_read_only()
+            .values()
+            .cloned()
+            .filter(|subfiles| subfiles.len() > 1)
+            .flatten()
+            .collect::<Vec<FileInfo>>();
+
+        Ok(Self {
+            files,
+            state: State::SizeWise,
+        })
+    }
+}

src/scanner.rs

@@ -1,79 +1,173 @@
-use crate::database;
-use crate::{params::Params, database::File};
+#![allow(unused)]
+use crate::{fileinfo::FileInfo, params::Params};
 use anyhow::Result;
-use glob::glob;
-use itertools::Itertools;
-use rayon::prelude::*;
-use std::fs;
-use std::path::PathBuf;
-use fxhash::hash32 as hasher;
+use indicatif::{ProgressBar, ProgressStyle};
+use std::{fs, path::PathBuf, time::Duration};
 
-pub fn duplicates(app_opts: &Params, connection: &sqlite::Connection) -> Result<Vec<File>> {
-    let scan_results = scan(app_opts, connection)?;
-    let base_path = app_opts.get_directory()?;
+use globwalk::{GlobWalker, GlobWalkerBuilder};
 
-    index_files(scan_results, connection);
-    database::duplicate_hashes(connection, &base_path)
+#[derive(Debug, Clone)]
+pub struct Scanner {
+    pub directory: Option<PathBuf>,
+    pub filetypes: Option<String>,
+    pub min_depth: Option<usize>,
+    pub max_depth: Option<usize>,
+    pub min_size: Option<u64>,
+    pub follow_links: bool,
 }
 
-fn get_glob_patterns(opts: &Params, directory: &String) -> Vec<PathBuf> {
-    opts.types
-        .clone()
-        .unwrap_or(String::from("*"))
-        .split(",")
-        .map(|filetype| format!("*.{}", filetype))
-        .map(|filetype| {
-            vec![directory.clone(), String::from("**"), filetype]
-                .iter()
-                .collect()
+impl Scanner {
+    pub fn new() -> Self {
+        Self {
+            directory: None,
+            filetypes: None,
+            min_depth: None,
+            max_depth: None,
+            min_size: None,
+            follow_links: true,
+        }
+    }
+
+    pub fn build(app_args: &Params) -> Result<Self> {
+        let scan_directory = app_args.get_directory()?;
+        Ok(Scanner::new())
+            .map(|scanner| scanner.directory(scan_directory))
+            .map(|scanner| match app_args.get_min_size() {
+                Some(min_size) => scanner.min_size(min_size),
+                None => scanner,
+            })
+            .map(|scanner| match app_args.get_types() {
+                Some(ftypes) => scanner.filetypes(ftypes),
+                None => scanner,
+            })
+            .map(|scanner| match app_args.min_depth {
+                Some(min_depth) => scanner.min_depth(min_depth),
+                None => scanner,
+            })
+            .map(|scanner| match app_args.max_depth {
+                Some(max_depth) => scanner.max_depth(max_depth),
+                None => scanner,
+            })
+    }
+
+    pub fn min_size(&self, min_size: u64) -> Self {
+        Self {
+            min_size: Some(min_size),
+            ..self.clone()
+        }
+    }
+
+    pub fn min_depth(&self, min_depth: usize) -> Self {
+        Self {
+            min_depth: Some(min_depth),
+            ..self.clone()
+        }
+    }
+
+    pub fn max_depth(&self, max_depth: usize) -> Self {
+        Self {
+            max_depth: Some(max_depth),
+            ..self.clone()
+        }
+    }
+
+    pub fn directory(&self, dir: PathBuf) -> Self {
+        Self {
+            directory: Some(dir),
+            ..self.clone()
+        }
+    }
+
+    pub fn filetypes(&self, patterns: String) -> Self {
+        Self {
+            filetypes: Some(patterns),
+            ..self.clone()
+        }
+    }
+
+    pub fn ignore_links(&self) -> Self {
+        Self {
+            follow_links: false,
+            ..self.clone()
+        }
+    }
+
+    pub fn follow_links(&self) -> Self {
+        Self {
+            follow_links: true,
+            ..self.clone()
+        }
+    }
+
+    fn scan_patterns(&self) -> Result<String> {
+        Ok(match self.filetypes.clone() {
+            Some(ftypes) => format!("**/*{{{ftypes}}}"),
+            None => "**/*".to_string(),
         })
-        .collect()
-}
-
-fn is_indexed_file(path: &String, indexed: &Vec<File>) -> bool {
-    indexed
-        .into_iter()
-        .map(|file| file.path.clone())
-        .contains(path)
-}
-
-fn scan(app_opts: &Params, connection: &sqlite::Connection) -> Result<Vec<String>> {
-    let directory = app_opts.get_directory()?;
-    let glob_patterns: Vec<PathBuf> = get_glob_patterns(&app_opts, &directory);
-    let indexed_paths = database::indexed_paths(connection)?;
-    let files: Vec<String> = glob_patterns
-        .into_par_iter()
-        .map(|glob_pattern| glob(&glob_pattern.as_os_str().to_str().unwrap()))
-        .map(|glob_result| glob_result.unwrap())
-        .flat_map(|file_vec| {
-            file_vec
-                .map(|x| x.unwrap().as_os_str().to_str().unwrap().to_string())
-                .filter(|fpath| !is_indexed_file(fpath, &indexed_paths))
-                .filter(|glob_result| fs::metadata(glob_result).unwrap().is_file())
-                .collect::<Vec<String>>()
-        })
-        .collect();
-
-    Ok(files)
-}
-
-fn index_files(files: Vec<String>, connection: &sqlite::Connection) {
-    let hashed: Vec<File> = files
-        .into_par_iter()
-        .map(|file| {
-            let hash = hash_file(&file).unwrap();
-            database::File { path: file, hash }
-        })
-        .collect();
-
-    hashed.into_iter().for_each(|file| {
-        database::put(&file, connection).unwrap();
-    });
-}
-
-pub fn hash_file(filepath: &str) -> Result<String> {
-    let file = fs::read(filepath)?;
-    let hash = hasher(&*file).to_string();
-
-    Ok(hash)
+    }
+
+    fn scan_dir(&self) -> Result<PathBuf> {
+        let scan_dir = match self.directory.clone() {
+            Some(path) => path,
+            None => std::env::current_dir()?,
+        };
+
+        Ok(fs::canonicalize(scan_dir)?)
+    }
+
+    fn attach_link_opts(&self, walker: GlobWalkerBuilder) -> Result<GlobWalkerBuilder> {
+        Ok(walker.follow_links(self.follow_links))
+    }
+
+    fn attach_walker_min_depth(&self, walker: GlobWalkerBuilder) -> Result<GlobWalkerBuilder> {
+        match self.min_depth {
+            Some(min_depth) => Ok(walker.min_depth(min_depth)),
+            None => Ok(walker),
+        }
+    }
+
+    fn attach_walker_max_depth(&self, walker: GlobWalkerBuilder) -> Result<GlobWalkerBuilder> {
+        match self.max_depth {
+            Some(max_depth) => Ok(walker.max_depth(max_depth)),
+            None => Ok(walker),
+        }
+    }
+    fn build_walker(&self) -> Result<GlobWalker> {
+        let walker = Ok(GlobWalkerBuilder::from_patterns(
+            self.scan_dir()?,
+            &[self.scan_patterns()?],
+        ))
+        .and_then(|walker| self.attach_walker_min_depth(walker))
+        .and_then(|walker| self.attach_walker_max_depth(walker))
+        .and_then(|walker| self.attach_link_opts(walker))?;
+
+        Ok(walker.build()?)
+    }
+
+    pub fn scan(&self) -> Result<Vec<FileInfo>> {
+        let progress_style = ProgressStyle::with_template("[{elapsed_precise}] {pos:>7} {msg}")?;
+        let progress_bar = ProgressBar::new_spinner();
+        progress_bar.set_style(progress_style);
+        progress_bar.enable_steady_tick(Duration::from_millis(50));
+        progress_bar.set_message("paths mapped");
+        let min_size = self.min_size.unwrap_or_default();
+
+        let results = self
+            .build_walker()?
+            .filter_map(Result::ok)
+            .map(|entity| entity.into_path())
+            .map(|path| {
+                progress_bar.inc(1);
+                path
+            })
+            .filter(|path| path.is_file())
+            .map(FileInfo::new)
+            .filter_map(Result::ok)
+            .filter(|file| file.size > min_size)
+            .collect::<Vec<FileInfo>>();
+
+        progress_bar.finish_with_message("paths mapped");
+
+        Ok(results)
+    }
 }

src/server/file.rs

@@ -0,0 +1,44 @@
+use anyhow::Result;
+use std::fs::File;
+use std::io::Read;
+use std::os::unix::fs::MetadataExt;
+use std::sync::Arc;
+use uuid::Uuid;
+
+const PARTIAL_SIZE: u64 = 4096;
+
+#[allow(unused)]
+#[derive(Clone, Debug)]
+pub struct FileMeta {
+    pub id: Uuid,
+    pub path: Box<str>,
+    pub size: u64,
+    pub modtime: i64,
+    pub partial: Arc<[u8]>,
+    pub full_hash: Arc<[u8]>,
+}
+
+impl FileMeta {
+    fn create_partial(path: &str) -> Result<Arc<[u8]>> {
+        let mut partial_take = File::open(path)?.take(PARTIAL_SIZE);
+        let mut partial_buffer = Vec::with_capacity(PARTIAL_SIZE as usize);
+        partial_take.read_to_end(&mut partial_buffer)?;
+
+        Ok(Arc::from(partial_buffer))
+    }
+
+    pub fn new(path: Box<str>) -> Result<Self> {
+        let pstr = path.to_string();
+        let filemeta = std::fs::metadata(&pstr)?;
+        let partial = Self::create_partial(&pstr)?;
+
+        Ok(Self {
+            id: Uuid::new_v4(),
+            size: filemeta.size(),
+            modtime: filemeta.mtime(),
+            full_hash: Arc::new([]),
+            path,
+            partial,
+        })
+    }
+}

src/server/mod.rs

@@ -0,0 +1,79 @@
+pub mod file;
+mod processor;
+mod scanner;
+mod store;
+
+use anyhow::Result;
+use std::sync::mpsc;
+use std::sync::mpsc::channel;
+use std::sync::Arc;
+use std::sync::Mutex;
+use threadpool::ThreadPool;
+
+use self::processor::Processor;
+use self::scanner::Scanner;
+use self::store::Store;
+
+pub type FileQueue = Arc<Mutex<Vec<Box<str>>>>;
+
+pub enum Message {
+    AddScanDirectory(Box<str>),
+    Exit,
+    None,
+}
+
+pub struct Server {
+    pub fq: FileQueue,
+    pub dupstore: Arc<Store>,
+    pub tpool: ThreadPool,
+}
+
+impl Server {
+    pub fn new() -> Result<Self> {
+        Ok(Self {
+            fq: Arc::new(Mutex::new(vec![])),
+            dupstore: Arc::new(Store::new()),
+            tpool: ThreadPool::new(4),
+        })
+    }
+
+    pub fn start(&self, rx: mpsc::Receiver<Message>) -> Result<()> {
+        let processor_fq = self.fq.clone();
+        let processor_store = self.dupstore.clone();
+        let (processor_tx, processor_rx) = channel::<Message>();
+
+        self.tpool.execute(move || {
+            Processor::new(processor_fq, processor_store, processor_rx)
+                .process()
+                .expect("processer execution interrupted.");
+        });
+
+        let scanner_fq = self.fq.clone();
+        let (scanner_tx, scanner_rx) = channel::<Message>();
+        self.tpool.execute(move || {
+            Scanner::new(scanner_fq, scanner_rx)
+                .index()
+                .expect("scanner indexing interrupted.");
+        });
+
+        self.tpool.execute(move || loop {
+            match rx.recv() {
+                Ok(Message::AddScanDirectory(path)) => {
+                    scanner_tx
+                        .send(Message::AddScanDirectory(path))
+                        .expect("scanner tx message passing failed.");
+                }
+                Ok(Message::None) => {}
+                Ok(Message::Exit) | Err(_) => {
+                    scanner_tx.send(Message::Exit).unwrap_or_default();
+                    processor_tx.send(Message::Exit).unwrap_or_default();
+                    break;
+                }
+            };
+        });
+
+        self.tpool.join();
+
+        Ok(())
+    }
+}

src/server/processor.rs

@@ -0,0 +1,146 @@
+use anyhow::Result;
+use std::sync::mpsc::{Receiver, TryRecvError};
+use std::sync::Arc;
+
+use super::file::FileMeta;
+use super::store::{Index, Store};
+use super::{FileQueue, Message};
+
+pub struct Processor {
+    files: FileQueue,
+    duplicates: Arc<Store>,
+    msg_rx: Receiver<Message>,
+}
+
+impl Processor {
+    pub fn new(files: FileQueue, duplicates: Arc<Store>, msg_rx: Receiver<Message>) -> Self {
+        Self {
+            files,
+            duplicates,
+            msg_rx,
+        }
+    }
+
+    pub fn process(&self) -> Result<()> {
+        loop {
+            match self.msg_rx.try_recv() {
+                Ok(Message::Exit) => break,
+                Err(TryRecvError::Empty) => {},
+                _ => {}
+            }
+
+            let next_file = {
+                let mut cfiles = self.files.lock().unwrap();
+                cfiles.pop()
+            };
+
+            match next_file {
+                None => continue,
+                Some(file_res) => match FileMeta::new(file_res) {
+                    Err(_) => continue,
+                    Ok(fm) => {
+                        let fm_arc = Arc::new(fm);
+                        self.duplicates
+                            .add(Index::Size(fm_arc.size), fm_arc.clone());
+                    }
+                },
+            }
+        }
+
+        Ok(())
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use anyhow::Result;
+    use std::sync::mpsc;
+    use std::sync::{Arc, Mutex};
+    use std::thread;
+    use tempfile::TempDir;
+    use std::fs::File;
+    use std::io::Write;
+
+    #[test]
+    fn processor_differentiates_files_with_different_sizes() -> Result<()> {
+        let file_queue = Arc::new(Mutex::new(vec![]));
+        let (tx, rx) = mpsc::channel::<Message>();
+        let root = TempDir::new()?;
+        let store = Arc::new(Store::new());
+
+        let fq_c = file_queue.clone();
+        let store_c = store.clone();
+        let proc_thread = thread::spawn(move || {
+            let processor = Processor::new(fq_c, store_c, rx);
+            processor.process().expect("processor failed");
+        });
+
+        let files = 
+            [("hello.txt", "Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat"), 
+            ("hello_dup.txt", "Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum")];
+
+        for (filename, content) in files.into_iter() {
+            let fpath = root.path().join(filename);
+            let mut tf = File::create(fpath.clone())?;
+            tf.write_all(content.as_bytes())?;
+
+            let mut mfq = file_queue.lock().unwrap();
+            mfq.push(fpath.into_os_string().into_string().unwrap().into_boxed_str());
+        }
+
+        for _ in 0..10 {
+            if store.entries().len() < 2 {
+                thread::sleep(std::time::Duration::from_millis(100));
+            } 
+        }
+
+        tx.send(Message::Exit).expect("unable to send msg to processor");
+        proc_thread.join().expect("failed to join on thread!");
+
+        assert!(store.entries().len() == 2);
+
+        Ok(())
+    }
+
+    #[test]
+    fn processor_groups_files_with_same_size() -> Result<()> {
+        let file_queue = Arc::new(Mutex::new(vec![]));
+        let (tx, rx) = mpsc::channel::<Message>();
+        let root = TempDir::new()?;
+        let store = Arc::new(Store::new());
+
+        let fq_c = file_queue.clone();
+        let store_c = store.clone();
+        let proc_thread = thread::spawn(move || {
+            let processor = Processor::new(fq_c, store_c, rx);
+            processor.process().expect("processor failed");
+        });
+
+        let files = 
+            [("hello.txt", "Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum"), 
+            ("hello_dup.txt", "Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum")];
+
+        for (filename, content) in files.into_iter() {
+            let fpath = root.path().join(filename);
+            let mut tf = File::create(fpath.clone())?;
+            tf.write_all(content.as_bytes())?;
+
+            let mut mfq = file_queue.lock().unwrap();
+            mfq.push(fpath.into_os_string().into_string().unwrap().into_boxed_str());
+        }
+
+        for _ in 0..10 {
+            if store.entries().is_empty() {
+                thread::sleep(std::time::Duration::from_millis(100));
+            } 
+        }
+
+        tx.send(Message::Exit).expect("unable to send msg to processor");
+        proc_thread.join().expect("failed to join on thread!");
+
+        assert!(store.entries().len() == 1);
+
+        Ok(())
+    }
+}

src/server/scanner.rs

@@ -0,0 +1,128 @@
+use super::{FileQueue, Message};
+use anyhow::Result;
+use std::fs;
+use std::sync::mpsc::{self, Receiver};
+use std::sync::Arc;
+use std::sync::Mutex;
+
+#[derive(Debug)]
+pub struct Scanner {
+    files: FileQueue,
+    proc_queue: FileQueue,
+    msg_rx: Receiver<Message>,
+}
+
+impl Scanner {
+    pub fn new(fq: FileQueue, rx: Receiver<Message>) -> Self {
+        Self {
+            files: fq,
+            proc_queue: Arc::new(Mutex::new(vec![])),
+            msg_rx: rx,
+        }
+    }
+
+    pub fn index(&self) -> Result<()> {
+        loop {
+            match self.msg_rx.try_recv() {
+                Ok(Message::AddScanDirectory(path)) => {
+                    let mut mfq = self.proc_queue.lock().unwrap();
+                    mfq.push(path);
+                }
+                Err(mpsc::TryRecvError::Empty) | Ok(Message::None) => {}
+                Ok(Message::Exit) | Err(_) => break,
+            }
+
+            let npath = {
+                match self.proc_queue.try_lock() {
+                    Ok(mut q) => q.pop(),
+                    Err(_) => None,
+                }
+            };
+
+            match npath {
+                None => continue,
+                Some(path) => {
+                    std::fs::read_dir(path.as_ref())?
+                        .filter_map(Result::ok)
+                        .for_each(|entry: fs::DirEntry| {
+                            let mdata =
+                                fs::metadata(entry.path()).expect("unable to read file metadata.");
+
+                            let mpath = entry
+                                .path()
+                                .into_os_string()
+                                .into_string()
+                                .expect("invalid path conversion failed.")
+                                .into_boxed_str();
+
+                            match mdata.is_dir() {
+                                true => {
+                                    let mut pq = self
+                                        .proc_queue
+                                        .lock()
+                                        .expect("proc queue lock acq failed.");
+                                    pq.push(mpath);
+                                }
+                                false => {
+                                    let mut fq = self
+                                        .files
+                                        .lock()
+                                        .expect("file queue lock acq failed.");
+                                    fq.push(mpath)
+                                }
+                            }
+                        });
+                }
+            }
+        }
+
+        Ok(())
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use anyhow::Result;
+    use std::fs::File;
+    use std::io::Write;
+    use std::sync::mpsc::channel;
+    use tempfile::TempDir;
+    use std::thread;
+
+    #[test]
+    fn scanner_scans_files() -> Result<()> {
+        let files = 
+            [("hello.txt", "Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum"), 
+            ("hello_dup.txt", "Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum")];
+
+        let file_queue: FileQueue = Arc::new(Mutex::new(vec![]));
+        let (tx, rx) = channel::<Message>();
+        let root = TempDir::new()?;
+
+        for (filename, content) in files.into_iter() {
+            let mut tf = File::create(root.path().join(filename))?;
+            tf.write_all(content.as_bytes())?;
+        }
+
+        let rpath = root.path().to_str().unwrap().to_string().into_boxed_str();
+        let fq_clone = file_queue.clone();
+        let scanner_thread = thread::spawn(move || {
+            let scanner = Scanner::new(fq_clone, rx);
+            scanner.index().unwrap();
+        });
+
+        tx.send(Message::AddScanDirectory(rpath))?;
+        tx.send(Message::Exit)?;
+        scanner_thread.join().unwrap();
+
+        let fq_len = {
+            let v = file_queue.lock().unwrap();
+            v.len()
+        };
+
+        assert_eq!(files.len(), fq_len);
+
+        Ok(())
+    }
+}

src/server/store.rs

@@ -0,0 +1,35 @@
+use super::file::FileMeta;
+use dashmap::DashMap;
+use std::sync::Arc;
+
+#[allow(unused)]
+#[derive(Debug, Hash, PartialEq, Eq)]
+pub enum Index {
+    Size(u64),
+    Partial(Arc<[u8]>),
+    Full(Box<str>),
+}
+
+#[derive(Debug)]
+pub struct Store {
+    internal: Arc<DashMap<Index, Vec<Arc<FileMeta>>>>,
+}
+
+impl Store {
+    pub fn new() -> Self {
+        Self {
+            internal: Arc::new(DashMap::new()),
+        }
+    }
+
+    pub fn entries(&self) -> Arc<DashMap<Index, Vec<Arc<FileMeta>>>> {
+        self.internal.clone()
+    }
+
+    pub fn add(&self, index: Index, file: Arc<FileMeta>) {
+        self.internal
+            .entry(index)
+            .and_modify(|fg| fg.push(file.clone()))
+            .or_insert(vec![file]);
+    }
+}

src/tui/mod.rs

@@ -0,0 +1,99 @@
+use std::sync::mpsc::Sender;
+use std::time::Duration;
+
+use anyhow::{Context, Result};
+use ratatui::crossterm::event::{self, Event, KeyCode};
+use ratatui::layout::{Constraint, Direction, Layout};
+use ratatui::widgets::{Block, Borders, List, ListItem, Paragraph};
+use ratatui::{DefaultTerminal, Frame};
+
+use crate::server::{Message, Server};
+use std::sync::Arc;
+
+pub struct Tui {
+    app_tx: Sender<Message>,
+    server: Arc<Server>,
+}
+
+impl Tui {
+    pub fn new(app_tx: Sender<Message>, server: Arc<Server>) -> Self {
+        Self { app_tx, server }
+    }
+
+    pub fn start(&mut self) -> Result<()> {
+        let terminal = ratatui::init();
+        self.run(terminal).expect("ui loop failed.");
+        ratatui::restore();
+
+        Ok(())
+    }
+
+    fn poll_events() -> Result<Message> {
+        match event::poll(Duration::from_millis(100)).context("event polling failed.")? {
+            true => match event::read().context("event read failed.")? {
+                Event::Key(key) => match key.code {
+                    KeyCode::Char('q') => Ok(Message::Exit),
+                    _ => Ok(Message::None),
+                },
+                _ => Ok(Message::None),
+            },
+            false => Ok(Message::None),
+        }
+    }
+
+    fn handle_events(&self) -> Result<Message> {
+        match Self::poll_events() {
+            Ok(Message::Exit) => {
+                self.app_tx
+                    .send(Message::Exit)
+                    .expect("app event send failed.");
+                Ok(Message::Exit)
+            }
+            _ => Ok(Message::None),
+        }
+    }
+
+    fn draw(&mut self, frame: &mut Frame) {
+        let listitems = self
+            .server
+            .dupstore
+            .entries()
+            .iter()
+            .flat_map(|val| {
+                let mut group = vec![ListItem::new(format!("{:?}", val.key()))];
+                val.value().iter().for_each(|f| {
+                    group.push(ListItem::new(format!("|-{}", f.path)));
+                });
+                group
+            })
+            .collect::<Vec<ListItem>>();
+
+        let list = List::new(listitems.clone());
+        let layout_chunks = Layout::default()
+            .direction(Direction::Horizontal)
+            .constraints([Constraint::Percentage(50), Constraint::Percentage(50)])
+            .split(frame.area());
+
+        frame.render_widget(
+            list.block(Block::new().borders(Borders::ALL)),
+            layout_chunks[0],
+        );
+
+        frame.render_widget(
+            Paragraph::new(String::new()).block(Block::new().borders(Borders::ALL)),
+            layout_chunks[1],
+        );
+    }
+
+    fn run(&mut self, mut terminal: DefaultTerminal) -> Result<()> {
+        loop {
+            terminal.draw(|f| self.draw(f))?;
+            match self.handle_events() {
+                Ok(Message::Exit) => break,
+                _ => {}
+            }
+        }
+
+        Ok(())
+    }
+}