mirror of
https://github.com/sreedevk/deduplicator.git
synced 2026-08-26 02:04:39 +00:00
v0.2.0
This commit is contained in:
3
.gitignore
vendored
3
.gitignore
vendored
@@ -1,3 +1,2 @@
|
||||
/target
|
||||
/test_data
|
||||
.envrc
|
||||
/Cargo.lock
|
||||
|
||||
663
Cargo.lock
generated
663
Cargo.lock
generated
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
||||
[package]
|
||||
name = "deduplicator"
|
||||
version = "0.1.6"
|
||||
version = "0.2.0"
|
||||
edition = "2021"
|
||||
description = "find,filter,delete Duplicates"
|
||||
license = "MIT"
|
||||
@@ -24,6 +24,7 @@ globwalk = "0.8.1"
|
||||
indicatif = { version = "0.17.2", features = ["rayon"] }
|
||||
itertools = "0.10.5"
|
||||
memmap2 = "0.5.8"
|
||||
pathdiff = "0.2.1"
|
||||
prettytable-rs = "0.10.0"
|
||||
rayon = "1.6.1"
|
||||
unicode-segmentation = "1.10.0"
|
||||
@@ -33,4 +34,3 @@ unicode-segmentation = "1.10.0"
|
||||
inherits = "release"
|
||||
debug = true
|
||||
split-debuginfo = "packed"
|
||||
|
||||
|
||||
20
examples/scanner.rs
Normal file
20
examples/scanner.rs
Normal file
@@ -0,0 +1,20 @@
|
||||
use std::path::PathBuf;
|
||||
|
||||
use anyhow::Result;
|
||||
use deduplicator_core::processor::Processor;
|
||||
use deduplicator_core::scanner::Scanner;
|
||||
|
||||
fn main() -> Result<()> {
|
||||
let scan_results: Vec<_> = Scanner::new()
|
||||
.directory(PathBuf::from("/home/sreedev/Data/books/"))
|
||||
.ignore_links().scan(None)?;
|
||||
|
||||
let processor = Processor::new(scan_results);
|
||||
let final_processor = processor.sizewise()?.hashwise()?;
|
||||
let display_vec = final_processor.files.into_iter().map(|file| file.path ).collect::<Vec<PathBuf>>();
|
||||
|
||||
dbg!(display_vec);
|
||||
|
||||
|
||||
Ok(())
|
||||
}
|
||||
18
src/app.rs
18
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(())
|
||||
}
|
||||
}
|
||||
@@ -1,21 +0,0 @@
|
||||
use anyhow::Result;
|
||||
use colored::Colorize;
|
||||
use std::path::PathBuf;
|
||||
|
||||
#[derive(Debug, Clone)]
|
||||
pub struct File {
|
||||
pub path: PathBuf,
|
||||
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.display()),
|
||||
Err(_) => println!("{}: {}", "FAILED".red(), file.path.display())
|
||||
}
|
||||
});
|
||||
|
||||
Ok(())
|
||||
}
|
||||
41
src/fileinfo.rs
Normal file
41
src/fileinfo.rs
Normal file
@@ -0,0 +1,41 @@
|
||||
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)
|
||||
.into_iter()
|
||||
.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(),
|
||||
})
|
||||
}
|
||||
}
|
||||
@@ -1,12 +0,0 @@
|
||||
use crate::file_manager::File;
|
||||
use crate::params::Params;
|
||||
|
||||
pub fn is_file_gt_min_size(app_opts: &Params, file: &File) -> bool {
|
||||
match app_opts.get_min_size() {
|
||||
Some(msize) => match file.size {
|
||||
Some(fsize) => fsize >= msize,
|
||||
None => true,
|
||||
},
|
||||
None => true,
|
||||
}
|
||||
}
|
||||
111
src/formatter.rs
Normal file
111
src/formatter.rs
Normal file
@@ -0,0 +1,111 @@
|
||||
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::{ProgressIterator, ParallelProgressIterator, ProgressBar, ProgressFinish, 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 {
|
||||
fn human_path(file: &FileInfo, app_args: &Params, min_path_length: usize) -> Result<String> {
|
||||
let base_directory: PathBuf = app_args.get_directory()?.to_path_buf();
|
||||
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)
|
||||
}
|
||||
|
||||
fn human_filesize(file: &FileInfo) -> Result<String> {
|
||||
Ok(format!("{:>12}", bytesize::ByteSize::b(file.size)))
|
||||
}
|
||||
|
||||
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 = max_filepath_length - basepath_length;
|
||||
|
||||
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.clone()
|
||||
.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<()> {
|
||||
let output_table = Self::generate_table(raw, app_args)?;
|
||||
output_table.printstd();
|
||||
|
||||
Ok(())
|
||||
}
|
||||
}
|
||||
85
src/interative.rs
Normal file
85
src/interative.rs
Normal file
@@ -0,0 +1,85 @@
|
||||
use anyhow::Result;
|
||||
use colored::Colorize;
|
||||
use crate::fileinfo::FileInfo;
|
||||
use prettytable::Table;
|
||||
use std::io::{self, Write};
|
||||
|
||||
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 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()),
|
||||
}
|
||||
}
|
||||
23
src/main.rs
23
src/main.rs
@@ -1,14 +1,23 @@
|
||||
mod app;
|
||||
mod file_manager;
|
||||
mod output;
|
||||
mod params;
|
||||
mod fileinfo;
|
||||
mod processor;
|
||||
mod scanner;
|
||||
mod filters;
|
||||
mod params;
|
||||
mod formatter;
|
||||
mod interative;
|
||||
|
||||
use anyhow::Result;
|
||||
use app::App;
|
||||
use params::Params;
|
||||
use scanner::Scanner;
|
||||
use processor::Processor;
|
||||
use clap::Parser;
|
||||
use formatter::Formatter;
|
||||
|
||||
fn main() -> Result<()> {
|
||||
App::init(¶ms::Params::parse())
|
||||
let app_args = Params::parse();
|
||||
let scan_results = Scanner::build(&app_args)?.scan()?;
|
||||
let processor = Processor::new(scan_results);
|
||||
let results = processor.sizewise()?.hashwise()?;
|
||||
|
||||
Formatter::print(results.files, &app_args)?;
|
||||
Ok(())
|
||||
}
|
||||
|
||||
217
src/output.rs
217
src/output.rs
@@ -1,217 +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::path::Path;
|
||||
use std::time::Duration;
|
||||
use std::{fs, io};
|
||||
use unicode_segmentation::UnicodeSegmentation;
|
||||
|
||||
fn format_path(path: &Path, opts: &Params) -> Result<String> {
|
||||
let display_path = path
|
||||
.to_string_lossy()
|
||||
.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: &Path) -> 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<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 => {
|
||||
file_manager::delete_files(files_to_delete.collect::<Vec<File>>()).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);
|
||||
progress_bar.enable_steady_tick(Duration::from_millis(50));
|
||||
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();
|
||||
}
|
||||
|
||||
#[allow(unused)]
|
||||
pub fn raw(duplicates: DashMap<String, Vec<File>>, opts: &Params) -> Result<()> {
|
||||
if duplicates.is_empty() {
|
||||
println!(
|
||||
"\n{}",
|
||||
"No duplicates found matching your search criteria.".green()
|
||||
);
|
||||
return Ok(());
|
||||
}
|
||||
|
||||
duplicates
|
||||
.into_iter()
|
||||
.sorted_unstable_by_key(|(_, f)| f.first().and_then(|ff| ff.size).unwrap_or_default())
|
||||
.for_each(|(_hash, group)| {
|
||||
group.iter().for_each(|file| {
|
||||
println!(
|
||||
"{}\t{}\t{}",
|
||||
format_path(&file.path, opts).unwrap_or_default().blue(),
|
||||
file_size(file).unwrap_or_default().red(),
|
||||
modified_time(&file.path).unwrap_or_default().yellow()
|
||||
)
|
||||
});
|
||||
|
||||
println!("---");
|
||||
});
|
||||
|
||||
Ok(())
|
||||
}
|
||||
@@ -1,10 +1,9 @@
|
||||
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]
|
||||
@@ -47,42 +46,4 @@ impl Params {
|
||||
let dir = fs::canonicalize(dir_path)?;
|
||||
Ok(dir)
|
||||
}
|
||||
|
||||
fn add_glob_min_depth(&self, builder: GlobWalkerBuilder) -> Result<GlobWalkerBuilder> {
|
||||
match self.min_depth {
|
||||
Some(mindepth) => Ok(builder.min_depth(mindepth)),
|
||||
None => Ok(builder),
|
||||
}
|
||||
}
|
||||
|
||||
fn add_glob_max_depth(&self, builder: GlobWalkerBuilder) -> Result<GlobWalkerBuilder> {
|
||||
match self.max_depth {
|
||||
Some(maxdepth) => Ok(builder.max_depth(maxdepth)),
|
||||
None => Ok(builder),
|
||||
}
|
||||
}
|
||||
|
||||
fn add_glob_follow_links(&self, builder: GlobWalkerBuilder) -> Result<GlobWalkerBuilder> {
|
||||
match self.follow_links {
|
||||
true => Ok(builder.follow_links(true)),
|
||||
false => Ok(builder.follow_links(false)),
|
||||
}
|
||||
}
|
||||
|
||||
pub fn get_glob_walker(&self) -> Result<GlobWalker> {
|
||||
let pattern: String = match self.types.as_ref() {
|
||||
Some(filetypes) => format!("**/*{{{filetypes}}}"),
|
||||
None => "**/*".to_string(),
|
||||
};
|
||||
|
||||
let glob_walker_builder = self
|
||||
.add_glob_min_depth(GlobWalkerBuilder::from_patterns(
|
||||
self.get_directory()?,
|
||||
&[pattern],
|
||||
))
|
||||
.and_then(|builder| self.add_glob_max_depth(builder))
|
||||
.and_then(|builder| self.add_glob_follow_links(builder))?;
|
||||
|
||||
glob_walker_builder.build().map_err(|e| anyhow!(e))
|
||||
}
|
||||
}
|
||||
|
||||
107
src/processor.rs
Normal file
107
src/processor.rs
Normal file
@@ -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,
|
||||
})
|
||||
}
|
||||
}
|
||||
278
src/scanner.rs
278
src/scanner.rs
@@ -1,151 +1,169 @@
|
||||
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::{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(50));
|
||||
|
||||
let files = walker
|
||||
.progress_with(progress)
|
||||
.filter_map(Result::ok)
|
||||
.map(|file| file.into_path())
|
||||
.filter(|fpath| fpath.is_file())
|
||||
.collect::<Vec<PathBuf>>();
|
||||
|
||||
let scan_progress = ProgressBar::new(files.len() as u64);
|
||||
let scan_progress_style = ProgressStyle::with_template(
|
||||
"{spinner:.green} [processing mapped paths] [{wide_bar:.cyan/blue}] {pos}/{len} files",
|
||||
)?;
|
||||
scan_progress.set_style(scan_progress_style);
|
||||
scan_progress.enable_steady_tick(Duration::from_millis(50));
|
||||
|
||||
let scan_results = files
|
||||
.into_par_iter()
|
||||
.progress_with(scan_progress)
|
||||
.map(|fpath| File {
|
||||
path: fpath.clone(),
|
||||
hash: None,
|
||||
size: Some(
|
||||
fs::metadata(fpath)
|
||||
.map(|metadata| metadata.len())
|
||||
.unwrap_or_default(),
|
||||
),
|
||||
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.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,
|
||||
})
|
||||
.filter(|file| filters::is_file_gt_min_size(app_opts, file))
|
||||
.collect();
|
||||
|
||||
Ok(scan_results)
|
||||
}
|
||||
|
||||
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_or_default())
|
||||
.and_modify(|fileset| fileset.push(file.clone()))
|
||||
.or_insert_with(|| vec![file]);
|
||||
|
||||
pub fn min_size(&self, min_size: u64) -> Self {
|
||||
Self {
|
||||
min_size: Some(min_size),
|
||||
..self.clone()
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
fn index_files(
|
||||
files: Vec<File>,
|
||||
index_criteria: IndexCritera,
|
||||
) -> Result<DashMap<String, Vec<File>>> {
|
||||
let store: DashMap<String, Vec<File>> = DashMap::new();
|
||||
let index_progress = ProgressBar::new(files.len() as u64);
|
||||
let index_progress_style = ProgressStyle::with_template(
|
||||
"{spinner:.green} [indexing files] [{wide_bar:.cyan/blue}] {pos}/{len} files",
|
||||
)?;
|
||||
index_progress.set_style(index_progress_style);
|
||||
index_progress.enable_steady_tick(Duration::from_millis(50));
|
||||
pub fn min_depth(&self, min_depth: usize) -> Self {
|
||||
Self {
|
||||
min_depth: Some(min_depth),
|
||||
..self.clone()
|
||||
}
|
||||
}
|
||||
|
||||
files
|
||||
.into_par_iter()
|
||||
.progress_with(index_progress)
|
||||
.for_each(|file| process_file_index(file, &store, index_criteria));
|
||||
pub fn max_depth(&self, max_depth: usize) -> Self {
|
||||
Self {
|
||||
max_depth: Some(max_depth),
|
||||
..self.clone()
|
||||
}
|
||||
}
|
||||
|
||||
Ok(store)
|
||||
}
|
||||
pub fn directory(&self, dir: PathBuf) -> Self {
|
||||
Self {
|
||||
directory: Some(dir),
|
||||
..self.clone()
|
||||
}
|
||||
}
|
||||
|
||||
fn incremental_hashing(filepath: &Path) -> Result<String> {
|
||||
let file = fs::File::open(filepath)?;
|
||||
let fmap = unsafe { Mmap::map(&file)? };
|
||||
let mut inchasher = fxhash::FxHasher::default();
|
||||
pub fn filetypes(&self, patterns: String) -> Self {
|
||||
Self {
|
||||
filetypes: Some(patterns),
|
||||
..self.clone()
|
||||
}
|
||||
}
|
||||
|
||||
fmap.chunks(1_000_000)
|
||||
.for_each(|mega| inchasher.write(mega));
|
||||
pub fn ignore_links(&self) -> Self {
|
||||
Self {
|
||||
follow_links: false,
|
||||
..self.clone()
|
||||
}
|
||||
}
|
||||
|
||||
Ok(format!("{}", inchasher.finish()))
|
||||
}
|
||||
pub fn follow_links(&self) -> Self {
|
||||
Self {
|
||||
follow_links: true,
|
||||
..self.clone()
|
||||
}
|
||||
}
|
||||
|
||||
fn standard_hashing(filepath: &Path) -> Result<String> {
|
||||
let file = fs::read(filepath)?;
|
||||
Ok(hasher(&*file).to_string())
|
||||
}
|
||||
fn scan_patterns(&self) -> Result<String> {
|
||||
Ok(match self.filetypes.clone() {
|
||||
Some(ftypes) => format!("**/*{{{ftypes}}}"),
|
||||
None => "**/*".to_string(),
|
||||
})
|
||||
}
|
||||
|
||||
fn hash_file(filepath: &Path) -> Result<String> {
|
||||
let filemeta = fs::metadata(filepath)?;
|
||||
fn scan_dir(&self) -> Result<PathBuf> {
|
||||
let scan_dir = match self.directory.clone() {
|
||||
Some(path) => path,
|
||||
None => std::env::current_dir()?,
|
||||
};
|
||||
|
||||
// NOTE: USE INCREMENTAL HASHING ONLY FOR FILES > 100MB
|
||||
match filemeta.len() < 100_000_000 {
|
||||
true => standard_hashing(filepath),
|
||||
false => incremental_hashing(filepath),
|
||||
Ok(fs::canonicalize(scan_dir)?)
|
||||
}
|
||||
|
||||
fn attach_link_opts(&self, walker: GlobWalkerBuilder) -> Result<GlobWalkerBuilder> {
|
||||
Ok(walker.follow_links(self.follow_links))
|
||||
}
|
||||
|
||||
fn attach_walker_min_depth(&self, walker: GlobWalkerBuilder) -> Result<GlobWalkerBuilder> {
|
||||
match self.min_depth {
|
||||
Some(min_depth) => Ok(walker.min_depth(min_depth)),
|
||||
None => Ok(walker),
|
||||
}
|
||||
}
|
||||
|
||||
fn attach_walker_max_depth(&self, walker: GlobWalkerBuilder) -> Result<GlobWalkerBuilder> {
|
||||
match self.max_depth {
|
||||
Some(max_depth) => Ok(walker.max_depth(max_depth)),
|
||||
None => Ok(walker),
|
||||
}
|
||||
}
|
||||
|
||||
fn build_walker(&self) -> Result<GlobWalker> {
|
||||
let walker = Ok(GlobWalkerBuilder::from_patterns(
|
||||
self.scan_dir()?,
|
||||
&[self.scan_patterns()?],
|
||||
))
|
||||
.and_then(|walker| self.attach_walker_min_depth(walker))
|
||||
.and_then(|walker| self.attach_walker_max_depth(walker))
|
||||
.and_then(|walker| self.attach_link_opts(walker))?;
|
||||
|
||||
Ok(walker.build()?)
|
||||
}
|
||||
|
||||
pub fn scan(&self) -> Result<Vec<FileInfo>> {
|
||||
let progress_style =
|
||||
ProgressStyle::with_template("[{elapsed_precise}] {pos:>7} {msg}")?;
|
||||
let progress_bar = ProgressBar::new_spinner();
|
||||
progress_bar.set_style(progress_style);
|
||||
progress_bar.enable_steady_tick(Duration::from_millis(50));
|
||||
progress_bar.set_message("paths mapped");
|
||||
|
||||
let 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(|file| FileInfo::new(file))
|
||||
.filter_map(Result::ok)
|
||||
.collect::<Vec<FileInfo>>();
|
||||
|
||||
progress_bar.finish_with_message("paths mapped");
|
||||
|
||||
Ok(results)
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user