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

@@ -161,6 +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"
@@ -303,7 +316,7 @@ dependencies = [
 
 [[package]]
 name = "deduplicator"
-version = "0.0.6"
+version = "0.0.9"
 dependencies = [
  "anyhow",
  "chrono",
@@ -313,6 +326,7 @@ dependencies = [
  "fxhash",
  "glob",
  "humansize",
+ "indicatif",
  "itertools",
  "prettytable-rs",
  "rayon",
@@ -320,6 +334,7 @@ dependencies = [
  "thiserror",
  "tokio",
  "tui",
+ "unicode-segmentation",
 ]
 
 [[package]]
@@ -349,6 +364,12 @@ 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"
@@ -459,6 +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"
@@ -613,6 +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"
@@ -660,6 +701,12 @@ 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"
@@ -667,7 +714,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "eea25e07510aa6ab6547308ebe3c036016d162b8da920dbb079e3ba8acf3d95a"
 dependencies = [
  "csv",
- "encode_unicode",
+ "encode_unicode 1.0.0",
  "is-terminal",
  "lazy_static",
  "term",

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "deduplicator"
-version = "0.0.6"
+version = "0.0.9"
 edition = "2021"
 description = "find,filter,delete Duplicates"
 license = "MIT"
@@ -17,6 +17,7 @@ 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"
@@ -24,3 +25,4 @@ 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/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

@@ -1,7 +1,10 @@
+#![allow(unused)]
+
 mod event_handler;
 mod events;
 mod formatter;
 mod ui;
+pub mod file_manager;
 
 use std::{io, thread, time::Duration};
 
@@ -32,7 +35,11 @@ impl App {
         // 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(())
     }
 

src/output.rs

@@ -1,23 +1,31 @@
-use std::{collections::HashMap, fs};
+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 itertools::Itertools;
 
+use crate::app::file_manager;
 use crate::database::File;
 use crate::params::Params;
-use prettytable::{row, Cell, Row, format, Table};
+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 text_vec = display_path.chars().collect::<Vec<_>>();
 
-    let display_range = if text_vec.len() > 32 {
+    let display_range = if display_path.chars().count() > 32 {
-        text_vec[(display_path.len() - 32)..]
+        display_path
-            .iter()
+            .graphemes(true)
-            .collect::<String>()
+            .collect::<Vec<&str>>()
+            .into_iter()
+            .rev()
+            .take(32)
+            .rev()
+            .collect()
     } else {
         display_path
     };
@@ -50,16 +58,104 @@ fn group_duplicates(duplicates: Vec<File>) -> HashMap<String, 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_meta_info(&duplicates, opts);
+
     let mut output_table = Table::new();
     let grouped_duplicates: HashMap<String, Vec<File>> = group_duplicates(duplicates);
 
     output_table.set_titles(row!["hash", "duplicates"]);
     grouped_duplicates.iter().for_each(|(hash, group)| {
         let mut inner_table = Table::new();
-        // inner_table.set_format(inner_table_format);
         inner_table.set_format(*format::consts::FORMAT_NO_BORDER_LINE_SEPARATOR);
-        //inner_table.set_titles(row!["filename", "size", "updated_at"]);
         group.iter().for_each(|file| {
             inner_table.add_row(row![
                 format_path(&file.path, opts).unwrap_or_default().blue(),

src/params.rs

@@ -12,9 +12,12 @@ 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 {

src/scanner.rs

@@ -1,5 +1,5 @@
 use std::{fs, path::PathBuf};
-
+use indicatif::{HumanDuration, MultiProgress, ProgressBar, ProgressStyle, ParallelProgressIterator};
 use anyhow::Result;
 use fxhash::hash32 as hasher;
 use glob::glob;
@@ -46,6 +46,7 @@ fn scan(app_opts: &Params, connection: &sqlite::Connection) -> Result<Vec<String
     let indexed_paths = database::indexed_paths(connection)?;
     let files: Vec<String> = glob_patterns
         .par_iter()
+        .progress_with_style(ProgressStyle::with_template("{spinner:.green} [scanning files] [{wide_bar:.cyan/blue}] {pos}/{len} files").unwrap())
         .filter_map(|glob_pattern| glob(glob_pattern.as_os_str().to_str()?).ok())
         .flat_map(|file_vec| {
             file_vec
@@ -66,6 +67,7 @@ fn scan(app_opts: &Params, connection: &sqlite::Connection) -> Result<Vec<String
 fn index_files(files: Vec<String>, connection: &sqlite::Connection) -> Result<()> {
     let hashed: Vec<File> = files
         .into_par_iter()
+        .progress_with_style(ProgressStyle::with_template("{spinner:.green} [indexing files] [{wide_bar:.cyan/blue}] {pos}/{len} files").unwrap())
         .filter_map(|file| {
             let hash = hash_file(&file).ok()?;
             Some(database::File { path: file, hash })