Beginning of adding allowed extension support.
This commit is contained in:
parent
ba8121a334
commit
10642548f9
|
@ -1,5 +1,14 @@
|
|||
# This file is automatically @generated by Cargo.
|
||||
# It is not intended for manual editing.
|
||||
[[package]]
|
||||
name = "aho-corasick"
|
||||
version = "0.7.13"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "043164d8ba5c4c3035fec9bbee8647c0261d788f3474306f93bb65901cae0e86"
|
||||
dependencies = [
|
||||
"memchr",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "arrayref"
|
||||
version = "0.3.6"
|
||||
|
@ -115,6 +124,7 @@ dependencies = [
|
|||
"blake3",
|
||||
"multimap",
|
||||
"rayon",
|
||||
"regex",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
|
@ -169,6 +179,12 @@ version = "2.0.0"
|
|||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "60302e4db3a61da70c0cb7991976248362f30319e88850c487b9b95bbf059e00"
|
||||
|
||||
[[package]]
|
||||
name = "memchr"
|
||||
version = "2.3.3"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "3728d817d99e5ac407411fa471ff9800a778d88a24685968b36824eaf4bee400"
|
||||
|
||||
[[package]]
|
||||
name = "memoffset"
|
||||
version = "0.5.5"
|
||||
|
@ -222,6 +238,24 @@ dependencies = [
|
|||
"num_cpus",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "regex"
|
||||
version = "1.3.9"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "9c3780fcf44b193bc4d09f36d2a3c87b251da4a046c87795a0d35f4f927ad8e6"
|
||||
dependencies = [
|
||||
"aho-corasick",
|
||||
"memchr",
|
||||
"regex-syntax",
|
||||
"thread_local",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "regex-syntax"
|
||||
version = "0.6.18"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "26412eb97c6b088a6997e05f69403a802a92d520de2f8e63c2b65f9e0f47c4e8"
|
||||
|
||||
[[package]]
|
||||
name = "scopeguard"
|
||||
version = "1.1.0"
|
||||
|
@ -240,6 +274,15 @@ version = "2.2.3"
|
|||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "502d53007c02d7605a05df1c1a73ee436952781653da5d0bf57ad608f66932c1"
|
||||
|
||||
[[package]]
|
||||
name = "thread_local"
|
||||
version = "1.0.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "d40c6d1b69745a6ec6fb1ca717914848da4b44ae29d9b3080cbee91d72a69b14"
|
||||
dependencies = [
|
||||
"lazy_static",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "typenum"
|
||||
version = "1.12.0"
|
||||
|
|
|
@ -7,4 +7,5 @@ edition = "2018"
|
|||
[dependencies]
|
||||
rayon = "1.4.0"
|
||||
blake3 = "0.3.6"
|
||||
multimap = "0.8.2"
|
||||
multimap = "0.8.2"
|
||||
regex = "1.3.9"
|
481
src/duplicate.rs
481
src/duplicate.rs
|
@ -1,204 +1,100 @@
|
|||
// Todo, należy upewnić się, że ma wystarczające uprawnienia do odczytu i usuwania
|
||||
use std::collections::HashMap;
|
||||
use std::collections::{BTreeMap, HashMap};
|
||||
use std::fs::{File, Metadata};
|
||||
use std::hash::Hash;
|
||||
use std::io::prelude::*;
|
||||
use std::path::Path;
|
||||
use std::time::SystemTime;
|
||||
use std::{fs, process};
|
||||
|
||||
const MIN_FILE_SIZE: u64 = 1000;
|
||||
|
||||
#[derive(PartialEq)]
|
||||
#[allow(dead_code)]
|
||||
pub enum CheckingMethod {
|
||||
SIZE,
|
||||
HASH,
|
||||
}
|
||||
|
||||
pub struct DuplicateFinder {
|
||||
number_of_checked_files: usize,
|
||||
number_of_ignored_files: usize,
|
||||
number_of_checked_folders: usize,
|
||||
number_of_ignored_things: usize,
|
||||
number_of_duplicated_files: usize,
|
||||
// files : Vec<HashMap<FileEntry, Vec<FileEntry>>>,
|
||||
files_size: HashMap<u64, Vec<FileEntry>>,
|
||||
// files_hashes: HashMap<[u8],Vec<FileEntry>>,
|
||||
// duplicated_entries // Same as files, but only with 2+ entries
|
||||
// files : Vec<Vec<FileEntry>>,
|
||||
files_with_identical_size: HashMap<u64, Vec<FileEntry>>,
|
||||
files_with_identical_hashes: BTreeMap<u64, Vec<Vec<FileEntry>>>,
|
||||
allowed_extensions: Vec<String>, // jpg, jpeg, mp4
|
||||
// excluded_items: Vec<String>,
|
||||
excluded_directories: Vec<String>,
|
||||
included_directories: Vec<String>,
|
||||
// ignored_extensions: Vec<String>,
|
||||
// allowed_extensions: Vec<String>,
|
||||
// ignored_file_names: Vec<String>, // TODO Regex Support
|
||||
// allowed_file_names: Vec<String>, // TODO Regex Support
|
||||
min_file_size: u64,
|
||||
}
|
||||
|
||||
impl DuplicateFinder {
|
||||
pub fn new() -> DuplicateFinder {
|
||||
DuplicateFinder {
|
||||
number_of_checked_files: 0,
|
||||
number_of_ignored_files: 0,
|
||||
number_of_checked_folders: 0,
|
||||
number_of_ignored_things: 0,
|
||||
number_of_duplicated_files: 0,
|
||||
files_size: Default::default(),
|
||||
// files_hashes: Default::default(),
|
||||
files_with_identical_size: Default::default(),
|
||||
files_with_identical_hashes: Default::default(),
|
||||
// excluded_items: vec![],
|
||||
excluded_directories: vec![],
|
||||
included_directories: vec![],
|
||||
// ignored_extensions: vec![],
|
||||
// allowed_extensions: vec![],
|
||||
// ignored_file_names: vec![],
|
||||
// allowed_file_names: vec![]
|
||||
min_file_size: 0,
|
||||
allowed_extensions: vec![],
|
||||
}
|
||||
}
|
||||
// TODO - Still isn't used but it will be probably required with GUI
|
||||
// pub fn clear(&mut self) {
|
||||
//
|
||||
// self.number_of_checked_files = 0;
|
||||
// self.number_of_checked_folders = 0;
|
||||
// self.number_of_ignored_things = 0;
|
||||
// self.number_of_files_which_has_duplicated_entries = 0;
|
||||
// self.number_of_duplicated_files = 0;
|
||||
// self.files_sizeclear();
|
||||
// self.excluded_directories.clear();
|
||||
// self.included_directories.clear();
|
||||
// }
|
||||
pub fn find_duplicates_by_size(&mut self) {
|
||||
// TODO add multithread checking for file hash
|
||||
//let mut path;
|
||||
let start_time: SystemTime = SystemTime::now();
|
||||
let mut folders_to_check: Vec<String> = Vec::with_capacity(1024 * 16); // This should be small enough too not see to big difference and big enough to store most of paths without needing to resize vector
|
||||
|
||||
// Add root folders for finding
|
||||
for id in &self.included_directories {
|
||||
folders_to_check.push(id.to_string());
|
||||
pub fn find_duplicates(mut self, check_method: CheckingMethod) {
|
||||
self.optimize_directories();
|
||||
self.debug_print();
|
||||
self.check_files_size();
|
||||
self.remove_files_with_unique_size();
|
||||
if check_method == CheckingMethod::HASH {
|
||||
self.check_files_hash();
|
||||
}
|
||||
// self.print_duplicated_entries(check_method);
|
||||
}
|
||||
|
||||
let mut current_folder: String;
|
||||
let mut next_folder: String;
|
||||
while !folders_to_check.is_empty() {
|
||||
current_folder = folders_to_check.pop().unwrap();
|
||||
pub fn set_min_file_size(&mut self, min_size: u64) {
|
||||
self.min_file_size = min_size;
|
||||
}
|
||||
|
||||
let read_dir = fs::read_dir(¤t_folder);
|
||||
let read_dir = match read_dir {
|
||||
Ok(t) => t,
|
||||
_ => continue,
|
||||
};
|
||||
for entry in read_dir {
|
||||
let entry_data = entry.unwrap();
|
||||
let metadata: Metadata = entry_data.metadata().unwrap();
|
||||
if metadata.is_dir() {
|
||||
let mut is_excluded_dir = false;
|
||||
next_folder = "".to_owned() + ¤t_folder + &entry_data.file_name().into_string().unwrap() + "/";
|
||||
for ed in &self.excluded_directories {
|
||||
if next_folder == ed.to_string() {
|
||||
is_excluded_dir = true;
|
||||
break;
|
||||
}
|
||||
}
|
||||
if !is_excluded_dir {
|
||||
folders_to_check.push(next_folder);
|
||||
}
|
||||
self.number_of_checked_folders += 1;
|
||||
pub fn set_excluded_items(&mut self, _excluded_items: String) {
|
||||
// TODO Still don't know how to exactly parse this
|
||||
// Things like /.git/ should be by default hidden with help of this *.git*
|
||||
}
|
||||
pub fn set_allowed_extensions(&mut self, mut allowed_extensions: String) {
|
||||
if allowed_extensions.is_empty() {
|
||||
println!("No allowed extension was provided, so all are allowed");
|
||||
}
|
||||
allowed_extensions = allowed_extensions.replace("IMAGE","jpg,kra,gif,png,bmp,tiff,webp,hdr,svg");
|
||||
allowed_extensions = allowed_extensions.replace("VIDEO","mp4,flv,mkv,webm,vob,ogv,gifv,avi,mov,wmv,mpg,m4v,m4p,mpeg,3gp");
|
||||
allowed_extensions = allowed_extensions.replace("MUSIC", "mp3,flac,ogg,tta,wma,webm");
|
||||
|
||||
//println!("Directory\t - {:?}", next_folder); // DEBUG
|
||||
} else if metadata.is_file() {
|
||||
let current_file_name = "".to_owned() + ¤t_folder + &entry_data.file_name().into_string().unwrap();
|
||||
// println!("File\t\t - {:?}", current_file_name); // DEBUG
|
||||
//file_to_check
|
||||
let fe: FileEntry = FileEntry {
|
||||
path: current_file_name,
|
||||
size: metadata.len(),
|
||||
created_date: metadata.created().unwrap(),
|
||||
modified_date: metadata.modified().unwrap(),
|
||||
};
|
||||
if !self.files_size.contains_key(&metadata.len()) {
|
||||
self.files_size.insert(metadata.len(), Vec::new());
|
||||
}
|
||||
self.files_size.get_mut(&metadata.len()).unwrap().push(fe);
|
||||
|
||||
self.number_of_checked_files += 1;
|
||||
} else {
|
||||
// Probably this is symbolic links so we are free to ignore this
|
||||
// println!("Found another type of file {} {:?}","".to_owned() + ¤t_folder + &entry_data.file_name().into_string().unwrap(), metadata) //DEBUG
|
||||
self.number_of_ignored_things += 1;
|
||||
let extensions: Vec<String> = allowed_extensions.split(',').map(String::from).collect();
|
||||
for mut extension in extensions{
|
||||
if extension.contains('.'){
|
||||
if !extension.starts_with('.'){
|
||||
println!("{} is not valid extension(valid extension doesn't have dot inside)",extension);
|
||||
}
|
||||
extension = extension.replace('.',"");
|
||||
}
|
||||
}
|
||||
self.debug_print();
|
||||
DuplicateFinder::print_time(start_time, SystemTime::now(), "find_duplicates".to_string());
|
||||
//println!("Duration of finding duplicates {:?}", end_time.duration_since(start_time).expect("a"));
|
||||
}
|
||||
// pub fn save_to_file(&self) {}
|
||||
|
||||
/// Remove files which have unique size
|
||||
pub fn remove_files_with_unique_size(&mut self) {
|
||||
let start_time: SystemTime = SystemTime::now();
|
||||
self.debug_print();
|
||||
let mut new_hashmap: HashMap<u64, Vec<FileEntry>> = Default::default();
|
||||
|
||||
self.number_of_duplicated_files = 0;
|
||||
|
||||
for entry in &self.files_size {
|
||||
if entry.1.len() > 1 {
|
||||
self.number_of_duplicated_files += entry.1.len() - 1;
|
||||
new_hashmap.insert(*entry.0, entry.1.clone());
|
||||
}
|
||||
self.allowed_extensions.push(extension.trim().to_string());
|
||||
}
|
||||
|
||||
self.files_size = new_hashmap;
|
||||
|
||||
self.debug_print();
|
||||
DuplicateFinder::print_time(start_time, SystemTime::now(), "optimize_files".to_string());
|
||||
}
|
||||
|
||||
/// Should be slower than checking in different ways, but still needs to be checked
|
||||
pub fn find_duplicates_by_hashing(mut self) {
|
||||
let start_time: SystemTime = SystemTime::now();
|
||||
let mut file_handler: File;
|
||||
|
||||
for entry in self.files_size {
|
||||
let mut hashes: Vec<String> = Vec::new();
|
||||
if entry.1.len() > 5 {
|
||||
println!("{}", entry.1.len());
|
||||
}
|
||||
|
||||
for file_entry in entry.1.iter().enumerate() {
|
||||
file_handler = match File::open(&file_entry.1.path) {
|
||||
Ok(T) => T,
|
||||
Err(_) => {
|
||||
// Removing File may happens,so we should handle this
|
||||
hashes.push("".to_owned());
|
||||
continue;
|
||||
}
|
||||
};
|
||||
|
||||
let mut hasher: blake3::Hasher = blake3::Hasher::new();
|
||||
let mut buffer = [0u8; 16384];
|
||||
loop {
|
||||
let n = file_handler.read(&mut buffer).unwrap();
|
||||
if n == 0 {
|
||||
break;
|
||||
}
|
||||
hasher.update(&buffer[..n]);
|
||||
}
|
||||
//println!("{}", hasher.finalize().to_hex().to_string());
|
||||
}
|
||||
if self.allowed_extensions.len() == 0{
|
||||
println!("No valid extensions were provided, so allowing all extensions by default.");
|
||||
}
|
||||
|
||||
DuplicateFinder::print_time(start_time, SystemTime::now(), "find_duplicates_by_hashing".to_string());
|
||||
}
|
||||
// /// I'mm not sure about performance, so maybe I
|
||||
// pub fn find_small_duplicates_by_hashing(mut self){
|
||||
// let start_time: SystemTime = SystemTime::now();
|
||||
// let size_limit_for_small_files u64 = // 16 MB
|
||||
// let mut new_hashmap
|
||||
//
|
||||
// DuplicateFinder::print_time(start_time, SystemTime::now(), "find_duplicates_by_comparting_begin_bytes_of_file".to_string());
|
||||
// }
|
||||
|
||||
pub fn print_time(start_time: SystemTime, end_time: SystemTime, function_name: String) {
|
||||
println!(
|
||||
"Execution of function \"{}\" took {:?}",
|
||||
function_name,
|
||||
end_time.duration_since(start_time).expect("Time cannot go reverse.")
|
||||
);
|
||||
}
|
||||
|
||||
/// Setting include directories, panics when there is not directories available
|
||||
pub fn set_include_directory(&mut self, mut include_directory: String) {
|
||||
let start_time: SystemTime = SystemTime::now();
|
||||
// let start_time: SystemTime = SystemTime::now();
|
||||
|
||||
if include_directory.is_empty() {
|
||||
println!("At least one directory must be provided")
|
||||
|
@ -225,7 +121,7 @@ impl DuplicateFinder {
|
|||
process::exit(1);
|
||||
}
|
||||
if !Path::new(&directory).exists() {
|
||||
println!("Include Directory ERROR: Path {} doens't exists.", directory);
|
||||
println!("Include Directory ERROR: Path {} doesn't exists.", directory);
|
||||
process::exit(1);
|
||||
}
|
||||
if !Path::new(&directory).exists() {
|
||||
|
@ -235,9 +131,9 @@ impl DuplicateFinder {
|
|||
|
||||
// directory must end with /, due to possiblity of incorrect assumption, that e.g. /home/rafal is top folder to /home/rafalinho
|
||||
if !directory.ends_with('/') {
|
||||
checked_directories.push(directory + "/");
|
||||
checked_directories.push(directory.trim().to_string() + "/");
|
||||
} else {
|
||||
checked_directories.push(directory);
|
||||
checked_directories.push(directory.trim().to_string());
|
||||
}
|
||||
}
|
||||
|
||||
|
@ -248,11 +144,11 @@ impl DuplicateFinder {
|
|||
|
||||
self.included_directories = checked_directories;
|
||||
|
||||
DuplicateFinder::print_time(start_time, SystemTime::now(), "set_include_directory".to_string());
|
||||
//DuplicateFinder::print_time(start_time, SystemTime::now(), "set_include_directory".to_string());
|
||||
}
|
||||
|
||||
pub fn set_exclude_directory(&mut self, mut exclude_directory: String) {
|
||||
let start_time: SystemTime = SystemTime::now();
|
||||
//let start_time: SystemTime = SystemTime::now();
|
||||
if exclude_directory.is_empty() {
|
||||
return;
|
||||
}
|
||||
|
@ -278,7 +174,7 @@ impl DuplicateFinder {
|
|||
process::exit(1);
|
||||
}
|
||||
if !Path::new(&directory).exists() {
|
||||
println!("Exclude Directory ERROR: Path {} doens't exists.", directory);
|
||||
println!("Exclude Directory ERROR: Path {} doesn't exists.", directory);
|
||||
process::exit(1);
|
||||
}
|
||||
if !Path::new(&directory).exists() {
|
||||
|
@ -288,33 +184,258 @@ impl DuplicateFinder {
|
|||
|
||||
// directory must end with /, due to possiblity of incorrect assumption, that e.g. /home/rafal is top folder to /home/rafalinho
|
||||
if !directory.ends_with('/') {
|
||||
checked_directories.push(directory + "/");
|
||||
checked_directories.push(directory.trim().to_string() + "/");
|
||||
} else {
|
||||
checked_directories.push(directory);
|
||||
checked_directories.push(directory.trim().to_string());
|
||||
}
|
||||
}
|
||||
println!("{:?}", checked_directories);
|
||||
self.excluded_directories = checked_directories;
|
||||
|
||||
//DuplicateFinder::print_time(start_time, SystemTime::now(), "set_exclude_directory".to_string());
|
||||
}
|
||||
|
||||
// TODO - Still isn't used but it will be probably required with GUI
|
||||
// pub fn clear(&mut self) {
|
||||
//
|
||||
// self.number_of_checked_files = 0;
|
||||
// self.number_of_checked_folders = 0;
|
||||
// self.number_of_ignored_things = 0;
|
||||
// self.number_of_files_which_has_duplicated_entries = 0;
|
||||
// self.number_of_duplicated_files = 0;
|
||||
// self.files_sizeclear();
|
||||
// self.excluded_directories.clear();
|
||||
// self.included_directories.clear();
|
||||
// }
|
||||
fn check_files_size(&mut self) {
|
||||
// TODO maybe add multithread checking for file hash
|
||||
let start_time: SystemTime = SystemTime::now();
|
||||
let mut folders_to_check: Vec<String> = Vec::with_capacity(1024 * 2); // This should be small enough too not see to big difference and
|
||||
// big enough to store most of paths without needing to resize vector
|
||||
|
||||
// Add root folders for finding
|
||||
for id in &self.included_directories {
|
||||
folders_to_check.push(id.to_string());
|
||||
}
|
||||
|
||||
let mut current_folder: String;
|
||||
let mut next_folder: String;
|
||||
while !folders_to_check.is_empty() {
|
||||
current_folder = folders_to_check.pop().unwrap();
|
||||
|
||||
let read_dir = fs::read_dir(¤t_folder);
|
||||
let read_dir = match read_dir {
|
||||
Ok(t) => t,
|
||||
_ => continue,
|
||||
};
|
||||
for entry in read_dir {
|
||||
let entry_data = entry.unwrap();
|
||||
let metadata: Metadata = entry_data.metadata().unwrap();
|
||||
if metadata.is_dir() {
|
||||
let mut is_excluded_dir = false;
|
||||
next_folder = "".to_owned() + ¤t_folder + &entry_data.file_name().into_string().unwrap() + "/";
|
||||
for ed in &self.excluded_directories {
|
||||
if next_folder == *ed {
|
||||
is_excluded_dir = true;
|
||||
break;
|
||||
}
|
||||
}
|
||||
if !is_excluded_dir {
|
||||
folders_to_check.push(next_folder);
|
||||
}
|
||||
self.number_of_checked_folders += 1;
|
||||
|
||||
//println!("Directory\t - {:?}", next_folder); // DEBUG
|
||||
} else if metadata.is_file() {
|
||||
if metadata.len() >= MIN_FILE_SIZE {
|
||||
let current_file_name = "".to_owned() + ¤t_folder + &entry_data.file_name().into_string().unwrap();
|
||||
// println!("File\t\t - {:?}", current_file_name); // DEBUG
|
||||
//file_to_check
|
||||
let fe: FileEntry = FileEntry {
|
||||
path: current_file_name,
|
||||
size: metadata.len(),
|
||||
created_date: metadata.created().unwrap(),
|
||||
modified_date: metadata.modified().unwrap(),
|
||||
};
|
||||
// // self.files_with_identical_size.entry from below should be faster according to clippy
|
||||
// if !self.files_with_identical_size.contains_key(&metadata.len()) {
|
||||
// self.files_with_identical_size.insert(metadata.len(), Vec::new());
|
||||
// }
|
||||
self.files_with_identical_size.entry(metadata.len()).or_insert_with(Vec::new);
|
||||
|
||||
self.files_with_identical_size.get_mut(&metadata.len()).unwrap().push(fe);
|
||||
|
||||
self.number_of_checked_files += 1;
|
||||
} else {
|
||||
self.number_of_ignored_files += 1;
|
||||
}
|
||||
} else {
|
||||
// Probably this is symbolic links so we are free to ignore this
|
||||
// println!("Found another type of file {} {:?}","".to_owned() + ¤t_folder + &entry_data.file_name().into_string().unwrap(), metadata) //DEBUG
|
||||
self.number_of_ignored_things += 1;
|
||||
}
|
||||
}
|
||||
}
|
||||
self.debug_print();
|
||||
DuplicateFinder::print_time(start_time, SystemTime::now(), "check_files_size".to_string());
|
||||
//println!("Duration of finding duplicates {:?}", end_time.duration_since(start_time).expect("a"));
|
||||
}
|
||||
// pub fn save_results_to_file(&self) {}
|
||||
|
||||
/// Remove files which have unique size
|
||||
fn remove_files_with_unique_size(&mut self) {
|
||||
let start_time: SystemTime = SystemTime::now();
|
||||
self.debug_print();
|
||||
let mut new_hashmap: HashMap<u64, Vec<FileEntry>> = Default::default();
|
||||
|
||||
self.number_of_duplicated_files = 0;
|
||||
|
||||
for entry in &self.files_with_identical_size {
|
||||
if entry.1.len() > 1 {
|
||||
self.number_of_duplicated_files += entry.1.len() - 1;
|
||||
new_hashmap.insert(*entry.0, entry.1.clone());
|
||||
}
|
||||
}
|
||||
|
||||
self.excluded_directories = checked_directories;
|
||||
self.files_with_identical_size = new_hashmap;
|
||||
|
||||
DuplicateFinder::print_time(start_time, SystemTime::now(), "set_exclude_directory".to_string());
|
||||
self.debug_print();
|
||||
DuplicateFinder::print_time(start_time, SystemTime::now(), "remove_files_with_unique_size".to_string());
|
||||
}
|
||||
|
||||
pub fn debug_print(&self) {
|
||||
println!("---------------DEBUG PRINT---------------");
|
||||
println!("Number of all checked files - {}", self.number_of_checked_files);
|
||||
println!("Number of all checked folders - {}", self.number_of_checked_folders);
|
||||
println!("Number of all ignored things - {}", self.number_of_ignored_things);
|
||||
println!("Number of duplicated files - {}", self.number_of_duplicated_files);
|
||||
println!("Files list - {}", self.files_size.len());
|
||||
println!("Excluded directories - {:?}", self.excluded_directories);
|
||||
println!("Included directories - {:?}", self.included_directories);
|
||||
println!("-----------------------------------------");
|
||||
/// Should be slower than checking in different ways, but still needs to be checked
|
||||
fn check_files_hash(&mut self) {
|
||||
let start_time: SystemTime = SystemTime::now();
|
||||
let mut file_handler: File;
|
||||
let mut hashmap_with_hash: HashMap<String, Vec<FileEntry>>;
|
||||
|
||||
for entry in &self.files_with_identical_size {
|
||||
hashmap_with_hash = Default::default();
|
||||
|
||||
for file_entry in entry.1.iter().enumerate() {
|
||||
file_handler = match File::open(&file_entry.1.path) {
|
||||
Ok(t) => t,
|
||||
Err(_) => {
|
||||
continue;
|
||||
}
|
||||
};
|
||||
|
||||
let mut hasher: blake3::Hasher = blake3::Hasher::new();
|
||||
let mut buffer = [0u8; 16384];
|
||||
loop {
|
||||
let n = file_handler.read(&mut buffer).unwrap();
|
||||
if n == 0 {
|
||||
break;
|
||||
}
|
||||
hasher.update(&buffer[..n]);
|
||||
}
|
||||
let hash_string: String = hasher.finalize().to_hex().to_string();
|
||||
hashmap_with_hash.entry(hash_string.to_string()).or_insert_with(Vec::new);
|
||||
hashmap_with_hash.get_mut(&*hash_string).unwrap().push(file_entry.1.to_owned());
|
||||
}
|
||||
for hash_entry in hashmap_with_hash {
|
||||
if hash_entry.1.len() > 1 {
|
||||
self.files_with_identical_hashes.entry(*entry.0).or_insert_with(Vec::new);
|
||||
self.files_with_identical_hashes.get_mut(entry.0).unwrap().push(hash_entry.1);
|
||||
// self.files_with_identical_hashes.insert(*entry.0,hash_entry.1);
|
||||
}
|
||||
}
|
||||
}
|
||||
self.debug_print();
|
||||
DuplicateFinder::print_time(start_time, SystemTime::now(), "check_files_hash".to_string());
|
||||
}
|
||||
// /// I'mm not sure about performance, so maybe I
|
||||
// pub fn find_small_duplicates_by_hashing(mut self){
|
||||
// let start_time: SystemTime = SystemTime::now();
|
||||
// let size_limit_for_small_files u64 = // 16 MB
|
||||
// let mut new_hashmap
|
||||
//
|
||||
// DuplicateFinder::print_time(start_time, SystemTime::now(), "find_duplicates_by_comparting_begin_bytes_of_file".to_string());
|
||||
// }
|
||||
|
||||
fn print_time(start_time: SystemTime, end_time: SystemTime, function_name: String) {
|
||||
println!(
|
||||
"Execution of function \"{}\" took {:?}",
|
||||
function_name,
|
||||
end_time.duration_since(start_time).expect("Time cannot go reverse.")
|
||||
);
|
||||
}
|
||||
|
||||
/// Setting include directories, panics when there is not directories available
|
||||
|
||||
|
||||
fn debug_print(&self) {
|
||||
// println!("---------------DEBUG PRINT---------------");
|
||||
// println!("Number of all checked files - {}", self.number_of_checked_files);
|
||||
// println!("Number of all ignored files - {}", self.number_of_ignored_files);
|
||||
// println!("Number of all checked folders - {}", self.number_of_checked_folders);
|
||||
// println!("Number of all ignored things - {}", self.number_of_ignored_things);
|
||||
// println!("Number of duplicated files - {}", self.number_of_duplicated_files);
|
||||
// let mut file_size : u64 = 0;
|
||||
// for i in &self.files_with_identical_size{
|
||||
// file_size += i.1.len() as u64;
|
||||
// }
|
||||
// println!("Files list size - {} ({})", self.files_with_identical_size.len(), file_size);
|
||||
// let mut hashed_file_size : u64 = 0;
|
||||
// for i in &self.files_with_identical_hashes{
|
||||
// for j in i.1{
|
||||
// hashed_file_size += j.len() as u64;
|
||||
// }
|
||||
// }
|
||||
// println!("Hashed Files list size - {} ({})", self.files_with_identical_hashes.len(), hashed_file_size);
|
||||
// println!("Excluded directories - {:?}", self.excluded_directories);
|
||||
// println!("Included directories - {:?}", self.included_directories);
|
||||
// println!("-----------------------------------------");
|
||||
}
|
||||
|
||||
#[allow(dead_code)]
|
||||
fn print_duplicated_entries(&self, check_method: CheckingMethod) {
|
||||
let start_time: SystemTime = SystemTime::now();
|
||||
let mut number_of_files: u64 = 0;
|
||||
let mut number_of_groups: u64 = 0;
|
||||
|
||||
match check_method {
|
||||
CheckingMethod::HASH => {
|
||||
for i in &self.files_with_identical_hashes {
|
||||
for j in i.1 {
|
||||
number_of_files += j.len() as u64;
|
||||
number_of_groups += 1;
|
||||
}
|
||||
}
|
||||
println!("Found {} files in {} groups with same content:", number_of_files, number_of_groups);
|
||||
for i in &self.files_with_identical_hashes {
|
||||
println!("Size - {}", i.0);
|
||||
for j in i.1 {
|
||||
for k in j {
|
||||
println!("{}", k.path);
|
||||
}
|
||||
println!("----");
|
||||
}
|
||||
println!();
|
||||
}
|
||||
}
|
||||
CheckingMethod::SIZE => {
|
||||
for i in &self.files_with_identical_size {
|
||||
number_of_files += i.1.len() as u64;
|
||||
number_of_groups += 1;
|
||||
}
|
||||
println!("Found {} files in {} groups with same size(may have different content):", number_of_files, number_of_groups);
|
||||
for i in &self.files_with_identical_size {
|
||||
println!("Size - {}", i.0);
|
||||
for j in i.1 {
|
||||
println!("{}", j.path);
|
||||
}
|
||||
println!();
|
||||
}
|
||||
}
|
||||
}
|
||||
DuplicateFinder::print_time(start_time, SystemTime::now(), "print_duplicated_entries".to_string());
|
||||
}
|
||||
/// Remove unused entries when included or excluded overlaps with each other or are duplicated
|
||||
/// ```
|
||||
/// let df : DuplicateFinder = saf
|
||||
/// ```
|
||||
pub fn optimize_directories(&mut self) {
|
||||
fn optimize_directories(&mut self) {
|
||||
let start_time: SystemTime = SystemTime::now();
|
||||
|
||||
let mut optimized_included: Vec<String> = Vec::<String>::new();
|
||||
|
|
34
src/main.rs
34
src/main.rs
|
@ -18,20 +18,36 @@ fn main() {
|
|||
match arguments[1].as_ref() {
|
||||
"-d" | "-duplicate_finder" => {
|
||||
if arguments.len() != 4 {
|
||||
println!("Duplicate Finder must be executed with exactly 3 arguments");
|
||||
println!("FATAL ERROR: Duplicate Finder must be executed with exactly 3 arguments");
|
||||
process::exit(1);
|
||||
}
|
||||
|
||||
let mut df = duplicate::DuplicateFinder::new();
|
||||
df.set_exclude_directory(arguments[3].to_string());
|
||||
df.set_include_directory(arguments[2].to_string());
|
||||
df.optimize_directories();
|
||||
df.debug_print();
|
||||
df.find_duplicates_by_size();
|
||||
df.remove_files_with_unique_size();
|
||||
df.find_duplicates_by_hashing();
|
||||
df.set_include_directory(arguments[2].clone());
|
||||
|
||||
if arguments.len() > 3 {
|
||||
df.set_exclude_directory(arguments[3].clone());
|
||||
}
|
||||
if arguments.len() > 4 {
|
||||
let min_size = match arguments[4].parse::<u64>() {
|
||||
Ok(t) => t,
|
||||
Err(_) => {
|
||||
println!("FATAL ERROR: Cannot parse \"{}\" to u64", arguments[4]);
|
||||
process::exit(1);
|
||||
}
|
||||
};
|
||||
df.set_min_file_size(min_size);
|
||||
}
|
||||
if arguments.len() > 5 {
|
||||
df.set_allowed_extensions(arguments[5].clone());
|
||||
}
|
||||
if arguments.len() > 6 {
|
||||
df.set_excluded_items(arguments[6].clone());
|
||||
}
|
||||
|
||||
df.find_duplicates(duplicate::CheckingMethod::SIZE);
|
||||
}
|
||||
argum => println!("{} argument is not supported, check help for more info.", argum),
|
||||
argum => println!("\"{}\" argument is not supported, check help for more info.", argum),
|
||||
};
|
||||
}
|
||||
|
||||
|
|
Loading…
Reference in New Issue