Merge pull request #20 from sreedevk/development

Version 0.0.9

.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.

CONTRIBUTING.md

@@ -0,0 +1,27 @@
+## 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.
+
+#### **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.lock

@@ -40,6 +40,18 @@ version = "1.3.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "bef38d45163c2f1dde094a7dfd33ccf595c92905c8f8f4fdc18d06fb1037718a"
 
+[[package]]
+name = "bstr"
+version = "0.2.17"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ba3569f383e8f1598449f1a423e72e99569137b47740b1da11ef19af3d5c3223"
+dependencies = [
+ "lazy_static",
+ "memchr",
+ "regex-automata",
+ "serde",
+]
+
 [[package]]
 name = "bumpalo"
 version = "3.11.1"
@@ -149,6 +161,19 @@ dependencies = [
  "winapi",
 ]
 
+[[package]]
+name = "console"
+version = "0.15.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c9b6515d269224923b26b5febea2ed42b2d5f2ce37284a4dd670fedd6cb8347a"
+dependencies = [
+ "encode_unicode 0.3.6",
+ "lazy_static",
+ "libc",
+ "unicode-width",
+ "windows-sys",
+]
+
 [[package]]
 name = "core-foundation-sys"
 version = "0.8.3"
@@ -223,6 +248,28 @@ dependencies = [
  "winapi",
 ]
 
+[[package]]
+name = "csv"
+version = "1.1.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "22813a6dc45b335f9bade10bf7271dc477e81113e89eb251a0bc2a8a81c536e1"
+dependencies = [
+ "bstr",
+ "csv-core",
+ "itoa",
+ "ryu",
+ "serde",
+]
+
+[[package]]
+name = "csv-core"
+version = "0.1.10"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2b2466559f260f48ad25fe6317b3c8dac77b5bdb5763ac7d9d6103530663bc90"
+dependencies = [
+ "memchr",
+]
+
 [[package]]
 name = "cxx"
 version = "1.0.85"
@@ -269,7 +316,7 @@ dependencies = [
 
 [[package]]
 name = "deduplicator"
-version = "0.0.1"
+version = "0.0.9"
 dependencies = [
  "anyhow",
  "chrono",
@@ -279,12 +326,36 @@ dependencies = [
  "fxhash",
  "glob",
  "humansize",
+ "indicatif",
  "itertools",
+ "prettytable-rs",
  "rayon",
  "sqlite",
  "thiserror",
  "tokio",
  "tui",
+ "unicode-segmentation",
+]
+
+[[package]]
+name = "dirs-next"
+version = "2.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b98cf8ebf19c3d1b223e151f99a4f9f0690dca41414773390fc824184ac833e1"
+dependencies = [
+ "cfg-if",
+ "dirs-sys-next",
+]
+
+[[package]]
+name = "dirs-sys-next"
+version = "0.1.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4ebda144c4fe02d1f7ea1a7d9641b6fc6b580adcfa024ae48797ecdeb6825b4d"
+dependencies = [
+ "libc",
+ "redox_users",
+ "winapi",
 ]
 
 [[package]]
@@ -293,6 +364,18 @@ version = "1.8.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "90e5c1c8368803113bf0c9584fc495a58b86dc8a29edbf8fe877d21d9507e797"
 
+[[package]]
+name = "encode_unicode"
+version = "0.3.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a357d28ed41a50f9c765dbfe56cbc04a64e53e5fc58ba79fbc34c10ef3df831f"
+
+[[package]]
+name = "encode_unicode"
+version = "1.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "34aa73646ffb006b8f5147f3dc182bd4bcb190227ce861fc4a4844bf8e3cb2c0"
+
 [[package]]
 name = "errno"
 version = "0.2.8"
@@ -323,6 +406,17 @@ dependencies = [
  "byteorder",
 ]
 
+[[package]]
+name = "getrandom"
+version = "0.2.8"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c05aeb6a22b8f62540c194aac980f2115af067bfe15a0734d7277a768d396b31"
+dependencies = [
+ "cfg-if",
+ "libc",
+ "wasi 0.11.0+wasi-snapshot-preview1",
+]
+
 [[package]]
 name = "glob"
 version = "0.3.0"
@@ -386,6 +480,20 @@ dependencies = [
  "cxx-build",
 ]
 
+[[package]]
+name = "indicatif"
+version = "0.17.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4295cbb7573c16d310e99e713cf9e75101eb190ab31fccd35f2d2691b4352b19"
+dependencies = [
+ "console",
+ "number_prefix",
+ "portable-atomic",
+ "rayon",
+ "tokio",
+ "unicode-width",
+]
+
 [[package]]
 name = "io-lifetimes"
 version = "1.0.3"
@@ -417,6 +525,12 @@ dependencies = [
  "either",
 ]
 
+[[package]]
+name = "itoa"
+version = "0.4.8"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b71991ff56294aa922b450139ee08b3bfc70982c6b2c7562771375cf73542dd4"
+
 [[package]]
 name = "js-sys"
 version = "0.3.60"
@@ -534,6 +648,12 @@ dependencies = [
  "libc",
 ]
 
+[[package]]
+name = "number_prefix"
+version = "0.4.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "830b246a0e5f20af87141b25c173cd1b609bd7779a4617d6ec582abaf90870f3"
+
 [[package]]
 name = "once_cell"
 version = "1.16.0"
@@ -581,6 +701,26 @@ version = "0.3.26"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "6ac9a59f73473f1b8d852421e59e64809f025994837ef743615c6d0c5b305160"
 
+[[package]]
+name = "portable-atomic"
+version = "0.3.19"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "26f6a7b87c2e435a3241addceeeff740ff8b7e76b74c13bf9acb17fa454ea00b"
+
+[[package]]
+name = "prettytable-rs"
+version = "0.10.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "eea25e07510aa6ab6547308ebe3c036016d162b8da920dbb079e3ba8acf3d95a"
+dependencies = [
+ "csv",
+ "encode_unicode 1.0.0",
+ "is-terminal",
+ "lazy_static",
+ "term",
+ "unicode-width",
+]
+
 [[package]]
 name = "proc-macro-error"
 version = "1.0.4"
@@ -654,6 +794,23 @@ dependencies = [
  "bitflags",
 ]
 
+[[package]]
+name = "redox_users"
+version = "0.4.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b033d837a7cf162d7993aded9304e30a83213c648b6e389db233191f891e5c2b"
+dependencies = [
+ "getrandom",
+ "redox_syscall",
+ "thiserror",
+]
+
+[[package]]
+name = "regex-automata"
+version = "0.1.10"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6c230d73fb8d8c1b9c0b3135c5142a8acee3a0558fb8db5cf1cb65f8d7862132"
+
 [[package]]
 name = "rustix"
 version = "0.36.5"
@@ -668,6 +825,18 @@ dependencies = [
  "windows-sys",
 ]
 
+[[package]]
+name = "rustversion"
+version = "1.0.11"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5583e89e108996506031660fe09baa5011b9dd0341b89029313006d1fb508d70"
+
+[[package]]
+name = "ryu"
+version = "1.0.12"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7b4b9743ed687d4b4bcedf9ff5eaa7398495ae14e61cba0a295704edbc7decde"
+
 [[package]]
 name = "scopeguard"
 version = "1.1.0"
@@ -680,6 +849,12 @@ version = "1.0.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "ddccb15bcce173023b3fedd9436f882a0739b8dfb45e4f6b6002bee5929f61b2"
 
+[[package]]
+name = "serde"
+version = "1.0.152"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bb7d1f0d3021d347a83e556fc4683dea2ea09d87bccdf88ff5c12545d89d5efb"
+
 [[package]]
 name = "signal-hook"
 version = "0.3.14"
@@ -773,6 +948,17 @@ dependencies = [
  "unicode-ident",
 ]
 
+[[package]]
+name = "term"
+version = "0.7.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c59df8ac95d96ff9bede18eb7300b0fda5e5d8d90960e76f8e14ae765eedbf1f"
+dependencies = [
+ "dirs-next",
+ "rustversion",
+ "winapi",
+]
+
 [[package]]
 name = "termcolor"
 version = "1.1.3"

Cargo.toml

@@ -1,9 +1,10 @@
 [package]
 name = "deduplicator"
-version = "0.0.2"
+version = "0.0.9"
 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>"]
 
 # See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
 
@@ -16,9 +17,12 @@ crossterm = "0.25.0"
 fxhash = "0.2.1"
 glob = "0.3.0"
 humansize = "2.1.2"
+indicatif = { version = "0.17.2", features = ["rayon", "tokio"] }
 itertools = "0.10.5"
+prettytable-rs = "0.10.0"
 rayon = "1.6.1"
 sqlite = "0.30.3"
 thiserror = "1.0.38"
 tokio = { version = "1.23.0", features = ["full"] }
 tui = "0.19.0"
+unicode-segmentation = "1.10.0"

README.md

@@ -16,7 +16,8 @@ Usage: deduplicator [OPTIONS]
 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)
+  -n, --nocache        Don't use cache for indexing files (default = false)
+  -i, --interactive    Delete files interactively
   -h, --help           Print help information
   -V, --version        Print version information
 ```
@@ -37,9 +38,13 @@ cargo install deduplicator
 <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">
+<p align="center">
-    While testing, Deduplicator was able to go through 8.6GB of pdf files and detect duplicates in 2.9 seconds
+  While testing, Deduplicator was able to go through 8.6GB of pdf files and detect duplicates in 2.9 seconds
-  </p>
+</p>
+
 <h2 align="center">Screenshots</h2>
 
-![_039](https://user-images.githubusercontent.com/36154121/210031222-d8b79143-5a1e-47ca-926e-8855d5bbab60.png)
+
+<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" />
+

src/app/event_handler.rs

@@ -1,7 +1,8 @@
 use std::time::Duration;
 
-use crossterm::event::{self, KeyCode, KeyEvent};
 use anyhow::Result;
+use crossterm::event::{self, KeyCode, KeyEvent};
+
 use super::events;
 
 pub struct EventHandler;
@@ -21,8 +22,7 @@ impl EventHandler {
     fn handle_keypress(keyevent: KeyEvent) -> Result<events::Event> {
         match keyevent.code {
             KeyCode::Char('q') => Ok(events::Event::Exit),
-            _ => Ok(events::Event::Noop)
+            _ => Ok(events::Event::Noop),
         }
     }
 }
-

src/app/events.rs

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

src/app/file_manager.rs

@@ -0,0 +1,14 @@
+use crate::database::File;
+use anyhow::Result;
+use colored::Colorize;
+
+pub fn delete_files(files: Vec<File>) -> Result<()> {
+    files.into_iter().for_each(|file| {
+        match std::fs::remove_file(file.path.clone()) {
+            Ok(_) => println!("{}: {}", "DELETED".green(), file.path),
+            Err(e) => println!("{}: {}", "FAILED".red(), file.path)
+        }
+    });
+
+    Ok(())
+}

src/app/mod.rs

@@ -1,18 +1,16 @@
+#![allow(unused)]
+
 mod event_handler;
 mod events;
-mod ui;
 mod formatter;
+mod ui;
+pub mod file_manager;
+
+use std::{io, thread, time::Duration};
 
-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},
@@ -20,19 +18,28 @@ use tui::{
 };
 use ui::Ui;
 
+use crate::database;
+use crate::output;
+use crate::params::Params;
+use crate::scanner;
+
 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 connection = database::get_connection(app_args)?;
-        let duplicates = scanner::duplicates(&app_args, &connection)?;
+        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 */
+        match app_args.interactive {
+            true => output::interactive(duplicates, app_args),
+            false => output::print(duplicates, app_args) /* TODO: APP TUI INIT FUNCTION */
+        }
+        
         Ok(())
     }
 
@@ -56,6 +63,8 @@ impl App {
     }
 
     fn init_render_loop(term: &mut Terminal<CrosstermBackend<io::Stdout>>) -> Result<()> {
+        // this could be simplified with a `while Self::render_cycle(term).is_ok() {}` in the current state, but maybe
+        // it's good to keep it to handle errors in the future
         loop {
             match Self::render_cycle(term) {
                 Ok(_) => continue,

src/app/ui.rs

@@ -1,5 +1,6 @@
-use anyhow::Result;
 use std::io;
+
+use anyhow::Result;
 use tui::{
     backend::{Backend, CrosstermBackend},
     layout::{Constraint, Direction, Layout, Rect},

src/database.rs

@@ -1,4 +1,7 @@
+use std::env::temp_dir;
+
 use anyhow::Result;
+
 use crate::params::Params;
 
 #[derive(Debug, Clone)]
@@ -7,13 +10,18 @@ pub struct File {
     pub hash: String,
 }
 
-pub fn get_connection(args: &Params) -> Result<sqlite::Connection, sqlite::Error> {
+fn db_connection_url(args: &Params) -> String {
-    let connection_url = match args.nocache {
+    match args.nocache {
-        false => "/tmp/deduplicator.db",
+        true => String::from(":memory:"),
-        true => ":memory:"
+        false => {
-    };
+            let temp_dir_path = temp_dir();
+            format!("{}/deduplicator.db", temp_dir_path.display())
+        }
+    }
+}
 
-    sqlite::open(connection_url).and_then(|conn| {
+pub fn get_connection(args: &Params) -> Result<sqlite::Connection, sqlite::Error> {
+    sqlite::open(db_connection_url(args)).and_then(|conn| {
         setup(&conn).ok();
         Ok(conn)
     })
@@ -30,31 +38,28 @@ pub fn put(file: &File, connection: &sqlite::Connection) -> Result<()> {
         "INSERT INTO files (file_identifier, hash) VALUES (\"{}\", \"{}\")",
         file.path, file.hash
     );
-    let result = connection.execute(query)?;
+    connection.execute(query)?;
-
+    Ok(())
-    Ok(result)
 }
 
 pub fn indexed_paths(connection: &sqlite::Connection) -> Result<Vec<File>> {
-    let query = format!(
+    let query = "SELECT * FROM files";
-        "SELECT * FROM files"
-        );
 
     let result: Vec<File> = connection
         .prepare(query)?
         .into_iter()
-        .map(|row_result| row_result.unwrap())
+        .filter_map(|row_result| row_result.ok())
         .map(|row| {
             let path = row.read::<&str, _>("file_identifier").to_string();
             let hash = row.read::<i64, _>("hash").to_string();
             File { path, hash }
         })
-    .collect();
+        .collect();
 
     Ok(result)
 }
 
-pub fn duplicate_hashes(connection: &sqlite::Connection, path: &String) -> Result<Vec<File>> {
+pub fn duplicate_hashes(connection: &sqlite::Connection, path: &str) -> Result<Vec<File>> {
     let query = format!(
         "
             SELECT a.* FROM files a
@@ -65,13 +70,14 @@ pub fn duplicate_hashes(connection: &sqlite::Connection, path: &String) -> Resul
             ON a.hash = b.hash
             WHERE a.file_identifier LIKE \"{}%\"
             ORDER BY a.file_identifier
-        ", path
+        ",
+        path
     );
 
     let result: Vec<File> = connection
         .prepare(query)?
         .into_iter()
-        .map(|row_result| row_result.unwrap())
+        .filter_map(|row_result| row_result.ok())
         .map(|row| {
             let path = row.read::<&str, _>("file_identifier").to_string();
             let hash = row.read::<i64, _>("hash").to_string();

src/main.rs

@@ -1,12 +1,13 @@
-mod params;
+#![allow(unused)] // TODO: remove this once TUI is implemented
+mod app;
 mod database;
 mod output;
+mod params;
 mod scanner;
-mod app;
 
 use anyhow::Result;
-use clap::Parser;
 use app::App;
+use clap::Parser;
 
 #[tokio::main]
 async fn main() -> Result<()> {

src/output.rs

@@ -1,66 +1,170 @@
-use crate::database::File;
+use std::{collections::HashMap, fs, io};
+use std::io::Write;
+
+use anyhow::Result;
 use chrono::offset::Utc;
 use chrono::DateTime;
 use colored::Colorize;
 use humansize::{format_size, DECIMAL};
-use std::{collections::HashMap, fs};
+use itertools::Itertools;
-use crate::params::Params;
 
-fn format_path(path: &String, opts: &Params) -> String {
+use crate::app::file_manager;
-    let display_path = path.replace(&opts.get_directory().unwrap(), "");
+use crate::database::File;
-    let display_range = if display_path.len() > 32 {
+use crate::params::Params;
-            &display_path[(display_path.len() - 32)..]
+use prettytable::{format, row, Cell, Row, Table};
+use unicode_segmentation::UnicodeSegmentation;
+
+fn format_path(path: &str, opts: &Params) -> Result<String> {
+    let display_path = path.replace(&opts.get_directory()?, "");
+
+    let display_range = if display_path.chars().count() > 32 {
+        display_path
+            .graphemes(true)
+            .collect::<Vec<&str>>()
+            .into_iter()
+            .rev()
+            .take(32)
+            .rev()
+            .collect()
     } else {
-        &display_path[..]
+        display_path
     };
 
-    format!("...{}", display_range)
+    Ok(format!("...{:<32}", display_range))
 }
 
-fn file_size(path: &String) -> String {
+fn file_size(path: &String) -> Result<String> {
-    let mdata = fs::metadata(path).unwrap();
+    let mdata = fs::metadata(path)?;
-    let formatted_size = format_size(mdata.len(), DECIMAL);
+    let formatted_size = format!("{:>12}", format_size(mdata.len(), DECIMAL));
-    format!("{}", formatted_size)
+    Ok(formatted_size)
 }
 
-fn modified_time(path: &String) -> String {
+fn modified_time(path: &String) -> Result<String> {
-    let mdata = fs::metadata(path).unwrap();
+    let mdata = fs::metadata(path)?;
-    let modified_time: DateTime<Utc> = mdata.modified().unwrap().into();
+    let modified_time: DateTime<Utc> = mdata.modified()?.into();
 
-    modified_time.format("%Y-%m-%d %H:%M:%S").to_string()
+    Ok(modified_time.format("%Y-%m-%d %H:%M:%S").to_string())
 }
 
-fn print_divider() {
+fn group_duplicates(duplicates: Vec<File>) -> HashMap<String, Vec<File>> {
-    println!("-------------------+-------------------------------------+------------------+----------------------------------+");
+    let mut duplicate_mapper: HashMap<String, Vec<File>> = HashMap::new();
+    duplicates.into_iter().for_each(|file| {
+        duplicate_mapper
+            .entry(file.hash.clone())
+            .and_modify(|value| value.push(file.clone()))
+            .or_insert_with(|| vec![file]);
+    });
+
+    duplicate_mapper
+}
+
+fn print_meta_info(duplicates: &Vec<File>, opts: &Params) {
+    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.");
+    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)
+}
+
+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)
+    }
+}
+
+fn process_group_action(duplicates: &Vec<File>, 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();
+
+    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);
+    });
+    
+    match scan_group_confirmation().unwrap() {
+        true => { file_manager::delete_files(files_to_delete.collect_vec()); },
+        false => println!("{}", "\nCancelled Delete Operation.".red())
+    }
+}
+
+pub fn interactive(duplicates: Vec<File>, opts: &Params) {
+    print_meta_info(&duplicates, opts);
+    let grouped_duplicates = group_duplicates(duplicates);
+
+    grouped_duplicates.iter().enumerate().for_each(|(gindex, (hash, 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,
+                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()
+            ]);
+        });
+
+        process_group_action(group, gindex, grouped_duplicates.len(), itable);
+    });
 }
 
 pub fn print(duplicates: Vec<File>, opts: &Params) {
-    print_divider();
+    print_meta_info(&duplicates, opts);
-    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();
+    let mut output_table = Table::new();
+    let grouped_duplicates: HashMap<String, Vec<File>> = group_duplicates(duplicates);
 
-    duplicates.into_iter().for_each(|file| {
+    output_table.set_titles(row!["hash", "duplicates"]);
-        dup_index
+    grouped_duplicates.iter().for_each(|(hash, group)| {
-            .entry(file.hash.clone())
+        let mut inner_table = Table::new();
-            .and_modify(|value| value.push(file.clone()))
+        inner_table.set_format(*format::consts::FORMAT_NO_BORDER_LINE_SEPARATOR);
-            .or_insert(vec![file]);
+        group.iter().for_each(|file| {
-    });
+            inner_table.add_row(row![
-
+                format_path(&file.path, opts).unwrap_or_default().blue(),
-    dup_index.into_iter().for_each(|(_, group)| {
+                file_size(&file.path).unwrap_or_default().red(),
-        group.into_iter().for_each(|file| {
+                modified_time(&file.path).unwrap_or_default().yellow()
-            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();
+        output_table.add_row(row![hash.green(), inner_table]);
     });
+
+    output_table.printstd();
 }

src/params.rs

@@ -1,7 +1,7 @@
-use std::path::PathBuf;
+use std::{fs, path::PathBuf};
+
+use anyhow::{anyhow, Result};
 use clap::Parser;
-use anyhow::Result;
-use std::fs;
 
 #[derive(Parser, Debug)]
 #[command(author, version, about, long_about = None)]
@@ -12,27 +12,27 @@ pub struct Params {
     /// Run Deduplicator on dir different from pwd
     #[arg(long)]
     pub dir: Option<PathBuf>,
-    /// Don't use cache for indexing files (default = true)
+    /// Don't use cache for indexing files (default = false)
     #[arg(long, short)]
     pub nocache: bool,
+    /// Delete files interactively
+    #[arg(long, short)]
+    pub interactive: bool
 }
 
 impl Params {
     pub fn get_directory(&self) -> Result<String> {
-        let dir_string: String = self
+        let dir_pathbuf: PathBuf = self
             .dir
             .clone()
             .unwrap_or(std::env::current_dir()?)
             .as_os_str()
-            .to_str()
+            .into();
-            .unwrap()
-            .to_string();
 
-        let dir_pathbuf = PathBuf::from(&dir_string);
+        let dir = fs::canonicalize(dir_pathbuf)?
-        let dir = fs::canonicalize(&dir_pathbuf)?
             .as_os_str()
             .to_str()
-            .unwrap()
+            .ok_or_else(|| anyhow!("Invalid directory"))?
             .to_string();
 
         Ok(dir)

src/scanner.rs

@@ -1,55 +1,62 @@
-use crate::database;
+use std::{fs, path::PathBuf};
-use crate::{params::Params, database::File};
+use indicatif::{HumanDuration, MultiProgress, ProgressBar, ProgressStyle, ParallelProgressIterator};
 use anyhow::Result;
+use fxhash::hash32 as hasher;
 use glob::glob;
 use itertools::Itertools;
 use rayon::prelude::*;
-use std::fs;
+
-use std::path::PathBuf;
+use crate::{
-use fxhash::hash32 as hasher;
+    database::{self, File},
+    params::Params,
+};
 
 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()?;
 
-    index_files(scan_results, connection);
+    index_files(scan_results, connection)?;
     database::duplicate_hashes(connection, &base_path)
 }
 
-fn get_glob_patterns(opts: &Params, directory: &String) -> Vec<PathBuf> {
+fn get_glob_patterns(opts: &Params, directory: &str) -> Vec<PathBuf> {
     opts.types
         .clone()
-        .unwrap_or(String::from("*"))
+        .unwrap_or_else(|| String::from("*"))
-        .split(",")
+        .split(',')
         .map(|filetype| format!("*.{}", filetype))
         .map(|filetype| {
-            vec![directory.clone(), String::from("**"), filetype]
+            vec![directory.to_owned(), String::from("**"), filetype]
                 .iter()
                 .collect()
         })
         .collect()
 }
 
-fn is_indexed_file(path: &String, indexed: &Vec<File>) -> bool {
+fn is_indexed_file(path: impl Into<String>, indexed: &[File]) -> bool {
     indexed
-        .into_iter()
+        .iter()
         .map(|file| file.path.clone())
-        .contains(path)
+        .contains(&path.into())
 }
 
 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 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()
+        .par_iter()
-        .map(|glob_pattern| glob(&glob_pattern.as_os_str().to_str().unwrap()))
+        .progress_with_style(ProgressStyle::with_template("{spinner:.green} [scanning files] [{wide_bar:.cyan/blue}] {pos}/{len} files").unwrap())
-        .map(|glob_result| glob_result.unwrap())
+        .filter_map(|glob_pattern| glob(glob_pattern.as_os_str().to_str()?).ok())
         .flat_map(|file_vec| {
             file_vec
-                .map(|x| x.unwrap().as_os_str().to_str().unwrap().to_string())
+                .filter_map(|x| Some(x.ok()?.as_os_str().to_str()?.to_string()))
                 .filter(|fpath| !is_indexed_file(fpath, &indexed_paths))
-                .filter(|glob_result| fs::metadata(glob_result).unwrap().is_file())
+                .filter(|glob_result| {
+                    fs::metadata(glob_result)
+                        .map(|f| f.is_file())
+                        .unwrap_or(false)
+                })
                 .collect::<Vec<String>>()
         })
         .collect();
@@ -57,18 +64,19 @@ fn scan(app_opts: &Params, connection: &sqlite::Connection) -> Result<Vec<String
     Ok(files)
 }
 
-fn index_files(files: Vec<String>, connection: &sqlite::Connection) {
+fn index_files(files: Vec<String>, connection: &sqlite::Connection) -> Result<()> {
     let hashed: Vec<File> = files
         .into_par_iter()
-        .map(|file| {
+        .progress_with_style(ProgressStyle::with_template("{spinner:.green} [indexing files] [{wide_bar:.cyan/blue}] {pos}/{len} files").unwrap())
-            let hash = hash_file(&file).unwrap();
+        .filter_map(|file| {
-            database::File { path: file, hash }
+            let hash = hash_file(&file).ok()?;
+            Some(database::File { path: file, hash })
         })
         .collect();
 
-    hashed.into_iter().for_each(|file| {
+    hashed
-        database::put(&file, connection).unwrap();
+        .iter()
-    });
+        .try_for_each(|file| database::put(file, connection))
 }
 
 pub fn hash_file(filepath: &str) -> Result<String> {