Merge pull request #53 from sreedevk/v0.2.0

v0.2.0  Architecture Improvements

.github/workflows/release.yml

@@ -1,31 +1,136 @@
+# CI that:
+#
+# * checks for a Git Tag that looks like a release ("v1.2.0")
+# * creates a Github Release™️
+# * builds binaries/packages with cargo-dist
+# * uploads those packages to the Github Release™️
+#
+# Note that the Github Release™️ will be created before the packages,
+# so there will be a few minutes where the release has no packages
+# 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
 
-env:
-  PROJECT_NAME: deduplicator
-  PROJECT_DESC: "Filter, Sort & Delete Duplicate Files Recursively"
-  PROJECT_AUTH: "sreedevk"
+permissions:
+  contents: write
 
+# This task will run whenever you push a git tag that looks like
+# a version number. We just look for `v` followed by at least one number
+# and then whatever. so `v1`, `v1.0.0`, and `v1.0.0-prerelease` all work.
+#
+# If there's a prerelease-style suffix to the version then the Github Release™️
+# will be marked as a prerelease (handled by taiki-e/create-gh-release-action).
+#
+# Note that when generating links to uploaded artifacts, cargo-dist will currently
+# assume that your git tag is always v{VERSION} where VERSION is the version in
+# the published package's Cargo.toml (this is the default behaviour of cargo-release).
+# In the future this may be made more robust/configurable.
 on:
-  release:
-    types:
-      - created
+  push:
+    tags:
+      - v[0-9]+.*
+
+env:
+  ALL_CARGO_DIST_TARGET_ARGS: --target=x86_64-unknown-linux-gnu --target=x86_64-apple-darwin --target=x86_64-pc-windows-msvc 
+  ALL_CARGO_DIST_INSTALLER_ARGS: 
 
 jobs:
-  upload-assets:
-    strategy:
-      matrix:
-        os:
-          - ubuntu-latest
-          - macos-latest
-          - windows-latest
-    runs-on: ${{ matrix.os }}
+  # Create the Github Release™️ so the packages have something to be uploaded to
+  create-release:
+    runs-on: ubuntu-latest
+    outputs:
+      tag: ${{ steps.create-gh-release.outputs.computed-prefix }}${{ steps.create-gh-release.outputs.version }}
     steps:
       - uses: actions/checkout@v3
-      - uses: taiki-e/upload-rust-binary-action@v1
+      - id: create-gh-release
+        uses: taiki-e/create-gh-release-action@v1
         with:
-          bin: deduplicator
-          tar: unix
-          zip: windows
+          draft: true
+          # (required) GitHub token for creating GitHub Releases.
           token: ${{ secrets.GITHUB_TOKEN }}
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+
+  # Build and packages all the things
+  upload-artifacts:
+    needs: create-release
+    strategy:
+      matrix:
+        # For these target platforms
+        include:
+        - target: x86_64-unknown-linux-gnu
+          os: ubuntu-20.04
+          install-dist: curl --proto '=https' --tlsv1.2 -L -sSf https://github.com/axodotdev/cargo-dist/releases/download/v0.0.2/installer.sh | sh
+        - target: x86_64-apple-darwin
+          os: macos-11
+          install-dist: curl --proto '=https' --tlsv1.2 -L -sSf https://github.com/axodotdev/cargo-dist/releases/download/v0.0.2/installer.sh | sh
+        - target: x86_64-pc-windows-msvc
+          os: windows-2019
+          install-dist: irm 'https://github.com/axodotdev/cargo-dist/releases/download/v0.0.2/installer.ps1' | iex
+    runs-on: ${{ matrix.os }}
+    env:
+      GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+    steps:
+      - uses: actions/checkout@v3
+      - name: Install Rust
+        run: rustup update stable && rustup default stable
+      - 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 commmands.
+        run: |
+          # Actually do builds and make zips and whatnot
+          cargo dist --target=${{ matrix.target }} --output-format=json > dist-manifest.json
+          echo "dist ran successfully"
+          cat dist-manifest.json
+          # Parse out what we just built and upload it to the Github Release™️
+          cat dist-manifest.json | jq --raw-output ".releases[].artifacts[].path" > uploads.txt
+          echo "uploading..."
+          cat uploads.txt
+          gh release upload ${{ needs.create-release.outputs.tag }} $(cat uploads.txt)
+          echo "uploaded!"
+
+  # Compute and upload the manifest for everything
+  upload-manifest:
+    needs: create-release
+    runs-on: ubuntu-latest
+    env:
+      GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+    steps:
+      - uses: actions/checkout@v3
+      - name: Install Rust
+        run: rustup update stable && rustup default stable
+      - name: Install cargo-dist
+        run: curl --proto '=https' --tlsv1.2 -L -sSf https://github.com/axodotdev/cargo-dist/releases/download/v0.0.2/installer.sh | sh
+      - name: Run cargo-dist manifest
+        run: |
+          # Generate a manifest describing everything
+          cargo dist manifest --no-local-paths --output-format=json $ALL_CARGO_DIST_TARGET_ARGS $ALL_CARGO_DIST_INSTALLER_ARGS > dist-manifest.json
+          echo "dist manifest ran successfully"
+          cat dist-manifest.json
+          # Upload the manifest to the Github Release™️
+          gh release upload ${{ needs.create-release.outputs.tag }} dist-manifest.json
+          echo "uploaded manifest!"
+          # Edit the Github Release™️ title/body to match what cargo-dist thinks it should be
+          CHANGELOG_TITLE=$(cat dist-manifest.json | jq --raw-output ".releases[].changelog_title")
+          cat dist-manifest.json | jq --raw-output ".releases[].changelog_body" > new_dist_changelog.md
+          gh release edit ${{ needs.create-release.outputs.tag }} --title="$CHANGELOG_TITLE" --notes-file=new_dist_changelog.md
+          echo "updated release notes!"
+
+  # Mark the Github Release™️ as a non-draft now that everything has succeeded!
+  publish-release:
+    needs: [create-release, upload-artifacts, upload-manifest]
+    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 ${{ needs.create-release.outputs.tag }} --draft=false
+

.gitignore

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

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "deduplicator"
-version = "0.1.4"
+version = "0.2.0"
 edition = "2021"
 description = "find,filter,delete Duplicates"
 license = "MIT"
@@ -21,11 +21,16 @@ colored = "2.0.0"
 dashmap = { version = "5.4.0", features = ["rayon"] }
 fxhash = "0.2.1"
 globwalk = "0.8.1"
-indicatif = { version = "0.17.2", features = ["rayon", "tokio"] }
+indicatif = { version = "0.17.2", features = ["rayon"] }
 itertools = "0.10.5"
 memmap2 = "0.5.8"
+pathdiff = "0.2.1"
 prettytable-rs = "0.10.0"
 rayon = "1.6.1"
-thiserror = "1.0.38"
-tokio = { version = "1.23.1", features = ["full"] }
 unicode-segmentation = "1.10.0"
+
+# generated by 'cargo dist init'
+[profile.dist]
+inherits = "release"
+debug = true
+split-debuginfo = "packed"

README.md

@@ -7,15 +7,38 @@
 ## Usage
 
 ```bash
-Usage: deduplicator [OPTIONS]
+Usage: deduplicator [OPTIONS] [scan_dir_path]
+
+Arguments:
+  [scan_dir_path]  Run Deduplicator on dir different from pwd (e.g., ~/Pictures )
 
 Options:
-  -t, --types <TYPES>      Filetypes to deduplicate (default = all)
-      --dir <DIR>          Run Deduplicator on dir different from pwd
-  -i, --interactive        Delete files interactively
-  -m, --minsize <MINSIZE>  Minimum filesize of duplicates to scan (e.g., 100B/1K/2M/3G/4T). [default = 0]
-  -h, --help               Print help information
-  -V, --version            Print version information
+  -t, --types <TYPES>          Filetypes to deduplicate [default = all]
+  -i, --interactive            Delete files interactively
+  -s, --min-size <MIN_SIZE>    Minimum filesize of duplicates to scan (e.g., 100B/1K/2M/3G/4T) [default: 1b]
+  -d, --max-depth <MAX_DEPTH>  Max Depth to scan while looking for duplicates
+      --min-depth <MIN_DEPTH>  Min Depth to scan while looking for duplicates
+  -f, --follow-links           Follow links while scanning directories
+  -h, --help                   Print help information
+  -V, --version                Print version information
+```
+### Examples
+
+```bash
+# Scan for duplicates recursively from the current dir, only look for png, jpg & pdf file types & interactively delete files
+deduplicator -t pdf,jpg,png -i
+
+# Scan for duplicates recursively from the ~/Pictures dir, only look for png, jpeg, jpg & pdf file types & interactively delete files
+deduplicator ~/Pictures/ -t png,jpeg,jpg,pdf -i
+
+# Scan for duplicates in the ~/Pictures without recursing into subdirectories
+deduplicator ~/Pictures --max-depth 0
+
+# look for duplicates in the ~/.config directory while also recursing into symbolic link paths
+deduplicator ~/.config --follow-links
+
+# scan for duplicates that are greater than 100mb in the ~/Media directory
+deduplicator ~/Media --min-size 100mb
 ```
 
 ## Installation
@@ -71,12 +94,12 @@ Deduplicator uses size comparison and fxhash (a non non-cryptographic hashing al
 
 ## benchmarks
 
-| Command | Dirsize | Mean [ms] | Min [ms] | Max [ms] | Relative |
-|:---|:---|---:|---:|---:|---:|
-| `deduplicator --dir ~/Data/tmp` | (~120G) | 27.5 ± 1.0 | 26.0 | 32.1 | 1.70 ± 0.09 |
-| `deduplicator --dir ~/Data/books` | (~8.6G) | 21.8 ± 0.7 | 20.5 | 24.4 | 1.35 ± 0.07 |
-| `deduplicator --dir ~/Data/books --minsize 10M` | (~8.6G) | 16.1 ± 0.6 | 14.9 | 18.8 | 1.00 |
-| `deduplicator --dir ~/Data/ --types pdf,jpg,png,jpeg` | (~290G) | 1857.4 ± 24.5 | 1817.0 | 1895.5 | 115.07 ± 4.64 |
+| 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.
 

src/app.rs

@@ -1,18 +0,0 @@
-use crate::output;
-use crate::params::Params;
-use crate::scanner;
-use anyhow::Result;
-
-pub struct App;
-
-impl App {
-    pub fn init(app_args: &Params) -> Result<()> {
-        let duplicates = scanner::duplicates(app_args)?;
-        match app_args.interactive {
-            true => output::interactive(duplicates, app_args),
-            false => output::print(duplicates, app_args),
-        }
-
-        Ok(())
-    }
-}

src/file_manager.rs

@@ -1,20 +0,0 @@
-use anyhow::Result;
-use colored::Colorize;
-
-#[derive(Debug, Clone)]
-pub struct File {
-    pub path: String,
-    pub size: Option<u64>,
-    pub hash: Option<String>,
-}
-
-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(_) => println!("{}: {}", "FAILED".red(), file.path)
-        }
-    });
-
-    Ok(())
-}

src/fileinfo.rs

@@ -0,0 +1,40 @@
+use anyhow::Result;
+use memmap2::Mmap;
+use std::fs;
+use std::hash::Hasher;
+use std::{fs::Metadata, path::PathBuf};
+
+#[derive(Debug, Clone)]
+pub struct FileInfo {
+    pub path: PathBuf,
+    pub filemeta: Metadata,
+    pub hash: Option<String>,
+    pub size: u64,
+}
+
+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 = fxhash::FxHasher::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/filters.rs

@@ -1,12 +0,0 @@
-use crate::file_manager::File;
-use crate::params::Params;
-
-pub fn is_file_gt_minsize(app_opts: &Params, file: &File) -> bool {
-    match app_opts.get_minsize() {
-        Some(msize) => match file.size {
-            Some(fsize) => fsize >= msize,
-            None => true,
-        },
-        None => true,
-    }
-}

src/formatter.rs

@@ -0,0 +1,129 @@
+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(());
+        }
+
+        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

@@ -1,15 +1,27 @@
-mod app;
-mod file_manager;
-mod output;
+mod fileinfo;
+mod formatter;
+mod interactive;
 mod params;
+mod processor;
 mod scanner;
-mod filters;
 
 use anyhow::Result;
-use app::App;
 use clap::Parser;
+use formatter::Formatter;
+use params::Params;
+use processor::Processor;
+use scanner::Scanner;
 
-#[tokio::main]
-async fn main() -> Result<()> {
-    App::init(&params::Params::parse())
+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)?; }
+    }
+
+    Ok(())
 }

src/output.rs

@@ -1,183 +0,0 @@
-use crate::file_manager::{self, File};
-use crate::params::Params;
-use anyhow::Result;
-use chrono::offset::Utc;
-use chrono::DateTime;
-use colored::Colorize;
-use dashmap::DashMap;
-use indicatif::{ProgressBar, ProgressIterator, ProgressStyle};
-use itertools::Itertools;
-use prettytable::{format, row, Table};
-use std::io::Write;
-use std::{fs, io};
-use unicode_segmentation::UnicodeSegmentation;
-
-fn format_path(path: &str, opts: &Params) -> Result<String> {
-    let display_path = path.replace(opts.get_directory()?.to_string_lossy().as_ref(), "");
-    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
-    };
-
-    Ok(format!("...{display_range:<32}"))
-}
-
-fn file_size(file: &File) -> Result<String> {
-    Ok(format!("{:>12}", bytesize::ByteSize::b(file.size.unwrap())))
-}
-
-fn modified_time(path: &String) -> Result<String> {
-    let mdata = fs::metadata(path)?;
-    let modified_time: DateTime<Utc> = mdata.modified()?.into();
-
-    Ok(modified_time.format("%Y-%m-%d %H:%M:%S").to_string())
-}
-
-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()).ok();
-        }
-        false => println!("{}", "\nCancelled Delete Operation.".red()),
-    }
-}
-
-pub fn interactive(duplicates: DashMap<String, Vec<File>>, opts: &Params) {
-    if duplicates.is_empty() {
-        println!(
-            "\n{}",
-            "No duplicates found matching your search criteria.".green()
-        );
-        return;
-    }
-
-    duplicates
-        .clone()
-        .into_iter()
-        .sorted_unstable_by_key(|(_, f)| {
-            -(f.first().and_then(|ff| ff.size).unwrap_or_default() as i64)
-        }) // sort by descending file size in interactive mode
-        .enumerate()
-        .for_each(|(gindex, (_, group))| {
-            let mut itable = Table::new();
-            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).unwrap_or_default().red(),
-                    modified_time(&file.path).unwrap_or_default().yellow()
-                ]);
-            });
-
-            process_group_action(&group, gindex, duplicates.len(), itable);
-        });
-}
-
-pub fn print(duplicates: DashMap<String, Vec<File>>, opts: &Params) {
-    if duplicates.is_empty() {
-        println!(
-            "\n{}",
-            "No duplicates found matching your search criteria.".green()
-        );
-        return;
-    }
-
-    let mut output_table = Table::new();
-    let progress_bar = ProgressBar::new(duplicates.len() as u64);
-    let progress_style = ProgressStyle::default_bar()
-        .template("{spinner:.green} [generating output] [{wide_bar:.cyan/blue}] {pos}/{len} files")
-        .unwrap();
-
-    progress_bar.set_style(progress_style);
-    output_table.set_titles(row!["hash", "duplicates"]);
-
-    duplicates
-        .into_iter()
-        .sorted_unstable_by_key(|(_, f)| f.first().and_then(|ff| ff.size).unwrap_or_default())
-        .progress_with(progress_bar)
-        .for_each(|(hash, group)| {
-            let mut inner_table = Table::new();
-            inner_table.set_format(*format::consts::FORMAT_NO_BORDER_LINE_SEPARATOR);
-            group.iter().for_each(|file| {
-                inner_table.add_row(row![
-                    format_path(&file.path, opts).unwrap_or_default().blue(),
-                    file_size(file).unwrap_or_default().red(),
-                    modified_time(&file.path).unwrap_or_default().yellow()
-                ]);
-            });
-            output_table.add_row(row![hash.green(), inner_table]);
-        });
-
-    output_table.printstd();
-}

src/params.rs

@@ -1,29 +1,37 @@
 use std::{fs, path::PathBuf};
 
-use anyhow::{anyhow, Result};
+use anyhow::Result;
 use clap::{Parser, ValueHint};
-use globwalk::{GlobWalker, GlobWalkerBuilder};
 
-#[derive(Parser, Debug)]
+#[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, value_hint = ValueHint::DirPath)]
+    /// Run Deduplicator on dir different from pwd (e.g., ~/Pictures )
+    #[arg(value_hint = ValueHint::DirPath, value_name = "scan_dir_path")]
     pub dir: Option<PathBuf>,
     /// Delete files interactively
     #[arg(long, short)]
     pub interactive: bool,
-    /// Minimum filesize of duplicates to scan (e.g., 100B/1K/2M/3G/4T). [default = 0]
+    /// Minimum filesize of duplicates to scan (e.g., 100B/1K/2M/3G/4T).
+    #[arg(long, short = 's', default_value = "1b")]
+    pub min_size: Option<String>,
+    /// Max Depth to scan while looking for duplicates
+    #[arg(long, short = 'd')]
+    pub max_depth: Option<usize>,
+    /// Min Depth to scan while looking for duplicates
+    #[arg(long)]
+    pub min_depth: Option<usize>,
+    /// Follow links while scanning directories
     #[arg(long, short)]
-    pub minsize: Option<String>,
+    pub follow_links: bool,
 }
 
 impl Params {
-    pub fn get_minsize(&self) -> Option<u64> {
-        match &self.minsize {
+    pub fn get_min_size(&self) -> Option<u64> {
+        match &self.min_size {
             Some(msize) => match msize.parse::<bytesize::ByteSize>() {
                 Ok(units) => Some(units.0),
                 Err(_) => None,
@@ -39,14 +47,7 @@ impl Params {
         Ok(dir)
     }
 
-    pub fn get_glob_walker(&self) -> Result<GlobWalker> {
-        let pattern: String = match self.types.as_ref() {
-            Some(filetypes) => format!("**/*{{{filetypes}}}"),
-            None => "**/*".to_string(),
-        };
-        // TODO: add params for maximum depth and following symlinks, then pass them to this builder
-        GlobWalkerBuilder::from_patterns(self.get_directory()?, &[pattern])
-            .build()
-            .map_err(|e| anyhow!(e))
+    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

@@ -1,133 +1,173 @@
-use crate::{file_manager::File, filters, params::Params};
+#![allow(unused)]
+use crate::{fileinfo::FileInfo, params::Params};
 use anyhow::Result;
-use dashmap::DashMap;
-use fxhash::hash64 as hasher;
-use indicatif::{ParallelProgressIterator, ProgressBar, ProgressIterator, ProgressStyle};
-use memmap2::Mmap;
-use rayon::prelude::*;
-use std::hash::Hasher;
-use std::time::Duration;
-use std::{fs, path::PathBuf};
+use indicatif::{ProgressBar, ProgressStyle};
+use std::{fs, path::PathBuf, time::Duration};
 
-#[derive(Clone, Copy)]
-enum IndexCritera {
-    Size,
-    Hash,
+use globwalk::{GlobWalker, GlobWalkerBuilder};
+
+#[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,
 }
 
-pub fn duplicates(app_opts: &Params) -> Result<DashMap<String, Vec<File>>> {
-    let scan_results = scan(app_opts)?;
-    let size_index_store = index_files(scan_results, IndexCritera::Size)?;
-
-    let sizewize_duplicate_files = size_index_store
-        .into_par_iter()
-        .filter(|(_, files)| files.len() > 1)
-        .map(|(_, files)| files)
-        .flatten()
-        .collect::<Vec<File>>();
-
-    if sizewize_duplicate_files.len() > 1 {
-        let hash_index_store = index_files(sizewize_duplicate_files, IndexCritera::Hash)?;
-        let duplicate_files = hash_index_store
-            .into_par_iter()
-            .filter(|(_, files)| files.len() > 1)
-            .collect();
-
-        Ok(duplicate_files)
-    } else {
-        Ok(DashMap::new())
+impl Scanner {
+    pub fn new() -> Self {
+        Self {
+            directory: None,
+            filetypes: None,
+            min_depth: None,
+            max_depth: None,
+            min_size: None,
+            follow_links: true,
+        }
     }
-}
 
-fn scan(app_opts: &Params) -> Result<Vec<File>> {
-    let walker = app_opts.get_glob_walker()?;
-    let progress = ProgressBar::new_spinner();
-    let progress_style =
-        ProgressStyle::with_template("{spinner:.green} [mapping paths] {pos} paths")?;
-    progress.set_style(progress_style);
-    progress.enable_steady_tick(Duration::from_millis(100));
+    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,
+            })
+    }
 
-    let files = walker
-        .progress_with(progress)
-        .filter_map(Result::ok)
-        .map(|file| file.into_path())
-        .filter(|fpath| fpath.is_file())
-        .collect::<Vec<PathBuf>>()
-        .into_par_iter()
-        .progress_with_style(ProgressStyle::with_template(
-            "{spinner:.green} [processing mapped paths] [{wide_bar:.cyan/blue}] {pos}/{len} files",
-        )?)
-        .map(|fpath| fpath.display().to_string())
-        .map(|fpath| File {
-            path: fpath.clone(),
-            hash: None,
-            size: Some(fs::metadata(fpath).unwrap().len()),
+    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(),
         })
-        .filter(|file| filters::is_file_gt_minsize(app_opts, file))
-        .collect();
+    }
 
-    Ok(files)
-}
+    fn scan_dir(&self) -> Result<PathBuf> {
+        let scan_dir = match self.directory.clone() {
+            Some(path) => path,
+            None => std::env::current_dir()?,
+        };
 
-fn process_file_index(
-    mut file: File,
-    store: &DashMap<String, Vec<File>>,
-    index_criteria: IndexCritera,
-) {
-    match index_criteria {
-        IndexCritera::Size => {
-            store
-                .entry(file.size.unwrap_or_default().to_string())
-                .and_modify(|fileset| fileset.push(file.clone()))
-                .or_insert_with(|| vec![file]);
-        }
-        IndexCritera::Hash => {
-            file.hash = Some(hash_file(&file.path).unwrap_or_default());
-            store
-                .entry(file.clone().hash.unwrap())
-                .and_modify(|fileset| fileset.push(file.clone()))
-                .or_insert_with(|| vec![file]);
+        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 index_files(
-    files: Vec<File>,
-    index_criteria: IndexCritera,
-) -> Result<DashMap<String, Vec<File>>> {
-    let store: DashMap<String, Vec<File>> = DashMap::new();
-    files
-        .into_par_iter()
-        .progress_with_style(ProgressStyle::with_template(
-            "{spinner:.green} [indexing files] [{wide_bar:.cyan/blue}] {pos}/{len} files",
-        )?)
-        .for_each(|file| process_file_index(file, &store, index_criteria));
+    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(store)
-}
+        Ok(walker.build()?)
+    }
 
-fn incremental_hashing(filepath: &str) -> Result<String> {
-    let file = fs::File::open(filepath)?;
-    let fmap = unsafe { Mmap::map(&file)? };
-    let mut inchasher = fxhash::FxHasher::default();
+    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();
 
-    fmap.chunks(1_000_000)
-        .for_each(|mega| inchasher.write(mega));
+        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>>();
 
-    Ok(format!("{}", inchasher.finish()))
-}
+        progress_bar.finish_with_message("paths mapped");
 
-fn standard_hashing(filepath: &str) -> Result<String> {
-    let file = fs::read(filepath)?;
-    Ok(hasher(&*file).to_string())
-}
-
-fn hash_file(filepath: &str) -> Result<String> {
-    let filemeta = fs::metadata(filepath)?;
-
-    // NOTE: USE INCREMENTAL HASHING ONLY FOR FILES > 100MB
-    match filemeta.len() < 100_000_000 {
-        true => standard_hashing(filepath),
-        false => incremental_hashing(filepath),
+        Ok(results)
     }
 }