2020-10-10 22:15:20 +13:00
use crossbeam_channel ::Receiver ;
2020-08-31 00:00:22 +12:00
use humansize ::{ file_size_opts as options , FileSize } ;
2021-05-09 04:29:52 +12:00
use std ::collections ::BTreeMap ;
2021-02-21 00:28:06 +13:00
#[ cfg(target_family = " unix " ) ]
use std ::collections ::HashSet ;
2021-01-15 00:17:15 +13:00
use std ::fs ::{ File , Metadata , OpenOptions } ;
2020-08-29 06:30:22 +12:00
use std ::io ::prelude ::* ;
2021-02-22 22:52:21 +13:00
use std ::io ::{ self , Error , ErrorKind } ;
2021-02-21 00:28:06 +13:00
#[ cfg(target_family = " unix " ) ]
use std ::os ::unix ::fs ::MetadataExt ;
2021-01-15 00:17:15 +13:00
use std ::path ::{ Path , PathBuf } ;
2020-12-02 22:25:27 +13:00
use std ::time ::{ Duration , SystemTime , UNIX_EPOCH } ;
2021-03-05 00:09:53 +13:00
use std ::{ fs , mem , thread } ;
2020-08-27 06:50:07 +12:00
2020-09-27 03:52:13 +13:00
use crate ::common ::Common ;
use crate ::common_directory ::Directories ;
use crate ::common_extensions ::Extensions ;
use crate ::common_items ::ExcludedItems ;
use crate ::common_messages ::Messages ;
use crate ::common_traits ::* ;
2021-01-15 00:17:15 +13:00
use directories_next ::ProjectDirs ;
2020-11-09 04:19:40 +13:00
use rayon ::prelude ::* ;
2021-02-04 07:59:06 +13:00
use std ::hash ::Hasher ;
2021-01-15 00:17:15 +13:00
use std ::io ::{ BufReader , BufWriter } ;
2020-12-02 22:25:27 +13:00
use std ::sync ::atomic ::{ AtomicBool , AtomicUsize , Ordering } ;
use std ::sync ::Arc ;
use std ::thread ::sleep ;
2020-09-01 05:37:30 +12:00
2020-09-27 07:46:35 +13:00
const HASH_MB_LIMIT_BYTES : u64 = 1024 * 1024 ; // 1MB
2021-01-15 00:17:15 +13:00
const CACHE_FILE_NAME : & str = " cache_duplicates.txt " ;
2020-12-02 22:25:27 +13:00
#[ derive(Debug) ]
pub struct ProgressData {
pub checking_method : CheckingMethod ,
pub current_stage : u8 ,
pub max_stage : u8 ,
pub files_checked : usize ,
pub files_to_check : usize ,
}
2020-09-26 23:48:53 +12:00
#[ derive(PartialEq, Eq, Clone, Debug) ]
2020-08-30 02:12:20 +12:00
pub enum CheckingMethod {
2020-09-25 08:25:24 +12:00
None ,
2020-10-25 07:44:21 +13:00
Name ,
2020-09-25 08:25:24 +12:00
Size ,
Hash ,
2021-03-28 01:14:02 +13:00
HashMb ,
2020-08-30 02:12:20 +12:00
}
2021-02-22 22:52:21 +13:00
impl MyHasher for blake3 ::Hasher {
fn update ( & mut self , bytes : & [ u8 ] ) {
self . update ( bytes ) ;
}
fn finalize ( & self ) -> String {
self . finalize ( ) . to_hex ( ) . to_string ( )
}
}
impl MyHasher for crc32fast ::Hasher {
fn update ( & mut self , bytes : & [ u8 ] ) {
self . write ( bytes ) ;
}
fn finalize ( & self ) -> String {
self . finish ( ) . to_string ( )
}
}
impl MyHasher for xxhash_rust ::xxh3 ::Xxh3 {
fn update ( & mut self , bytes : & [ u8 ] ) {
self . write ( bytes ) ;
}
fn finalize ( & self ) -> String {
self . finish ( ) . to_string ( )
}
}
2021-01-15 00:17:15 +13:00
#[ derive(PartialEq, Eq, Clone, Debug, Copy) ]
2020-10-25 07:44:21 +13:00
pub enum HashType {
Blake3 ,
2021-03-28 01:14:02 +13:00
Crc32 ,
Xxh3 ,
2020-10-25 07:44:21 +13:00
}
2021-02-22 22:52:21 +13:00
impl HashType {
fn hasher ( self : & HashType ) -> Box < dyn MyHasher > {
match self {
HashType ::Blake3 = > Box ::new ( blake3 ::Hasher ::new ( ) ) ,
2021-03-28 01:14:02 +13:00
HashType ::Crc32 = > Box ::new ( crc32fast ::Hasher ::new ( ) ) ,
HashType ::Xxh3 = > Box ::new ( xxhash_rust ::xxh3 ::Xxh3 ::new ( ) ) ,
2021-02-22 22:52:21 +13:00
}
}
}
2020-09-26 23:48:53 +12:00
#[ derive(Eq, PartialEq, Clone, Debug) ]
2020-09-01 02:15:56 +12:00
pub enum DeleteMethod {
None ,
2020-08-31 03:18:04 +12:00
AllExceptNewest ,
AllExceptOldest ,
OneOldest ,
OneNewest ,
2021-02-06 05:59:34 +13:00
HardLink ,
2020-09-01 02:15:56 +12:00
}
2021-02-21 00:28:06 +13:00
#[ derive(Clone, Debug, PartialEq, Default) ]
2020-09-20 21:32:55 +12:00
pub struct FileEntry {
2020-10-15 05:41:37 +13:00
pub path : PathBuf ,
2020-09-01 02:15:56 +12:00
pub size : u64 ,
2020-10-01 17:53:10 +13:00
pub modified_date : u64 ,
2021-01-15 00:17:15 +13:00
pub hash : String ,
2020-08-31 03:18:04 +12:00
}
2020-08-31 00:00:22 +12:00
2020-09-12 01:52:06 +12:00
/// Info struck with helpful information's about results
2020-10-10 09:32:08 +13:00
#[ derive(Default) ]
2020-09-10 22:42:44 +12:00
pub struct Info {
2020-09-16 05:17:13 +12:00
pub number_of_groups_by_size : usize ,
pub number_of_duplicated_files_by_size : usize ,
pub number_of_groups_by_hash : usize ,
pub number_of_duplicated_files_by_hash : usize ,
2020-10-25 07:44:21 +13:00
pub number_of_groups_by_name : usize ,
pub number_of_duplicated_files_by_name : usize ,
2020-09-16 05:17:13 +12:00
pub lost_space_by_size : u64 ,
pub lost_space_by_hash : u64 ,
2020-09-19 18:31:32 +12:00
pub bytes_read_when_hashing : u64 ,
2020-09-12 01:52:06 +12:00
pub number_of_removed_files : usize ,
pub number_of_failed_to_remove_files : usize ,
pub gained_space : u64 ,
2020-09-10 22:42:44 +12:00
}
2020-10-10 09:32:08 +13:00
impl Info {
pub fn new ( ) -> Self {
Default ::default ( )
2020-09-10 22:42:44 +12:00
}
}
2020-09-17 22:07:58 +12:00
/// Struct with required information's to work
pub struct DuplicateFinder {
2020-09-18 20:23:49 +12:00
text_messages : Messages ,
2020-09-18 17:32:37 +12:00
information : Info ,
2020-10-25 07:44:21 +13:00
files_with_identical_names : BTreeMap < String , Vec < FileEntry > > , // File Size, File Entry
2020-09-27 06:51:28 +13:00
files_with_identical_size : BTreeMap < u64 , Vec < FileEntry > > , // File Size, File Entry
files_with_identical_hashes : BTreeMap < u64 , Vec < Vec < FileEntry > > > , // File Size, File Entry
2020-09-27 03:52:13 +13:00
directories : Directories ,
allowed_extensions : Extensions ,
excluded_items : ExcludedItems ,
2020-09-17 22:07:58 +12:00
recursive_search : bool ,
2020-10-03 20:51:02 +13:00
minimal_file_size : u64 ,
2020-09-17 22:07:58 +12:00
check_method : CheckingMethod ,
delete_method : DeleteMethod ,
2020-10-25 07:44:21 +13:00
hash_type : HashType ,
2021-02-23 08:14:33 +13:00
ignore_hard_links : bool ,
2021-03-02 00:23:43 +13:00
dryrun : bool ,
2020-10-10 22:15:20 +13:00
stopped_search : bool ,
2021-03-05 00:09:53 +13:00
use_cache : bool ,
2021-05-07 07:54:44 +12:00
minimal_cache_file_size : u64 ,
2020-09-17 22:07:58 +12:00
}
2020-09-10 22:42:44 +12:00
impl DuplicateFinder {
2020-10-10 09:32:08 +13:00
pub fn new ( ) -> Self {
Self {
2020-09-27 03:52:13 +13:00
text_messages : Messages ::new ( ) ,
2020-09-18 17:32:37 +12:00
information : Info ::new ( ) ,
2020-10-25 07:44:21 +13:00
files_with_identical_names : Default ::default ( ) ,
2020-08-30 02:12:20 +12:00
files_with_identical_size : Default ::default ( ) ,
files_with_identical_hashes : Default ::default ( ) ,
2020-09-12 23:25:23 +12:00
recursive_search : true ,
2020-09-27 03:52:13 +13:00
allowed_extensions : Extensions ::new ( ) ,
2020-09-25 08:25:24 +12:00
check_method : CheckingMethod ::None ,
2020-09-17 22:07:58 +12:00
delete_method : DeleteMethod ::None ,
2020-10-03 20:51:02 +13:00
minimal_file_size : 1024 ,
2020-09-27 03:52:13 +13:00
directories : Directories ::new ( ) ,
excluded_items : ExcludedItems ::new ( ) ,
2020-10-10 22:15:20 +13:00
stopped_search : false ,
2021-02-23 08:14:33 +13:00
ignore_hard_links : true ,
2020-10-25 07:44:21 +13:00
hash_type : HashType ::Blake3 ,
2021-03-02 00:23:43 +13:00
dryrun : false ,
2021-03-05 00:09:53 +13:00
use_cache : true ,
2021-05-07 07:54:44 +12:00
minimal_cache_file_size : 2 * 1024 * 1024 , // By default cache only >= 1MB files
2020-08-30 02:12:20 +12:00
}
}
2020-09-18 17:32:37 +12:00
2021-04-14 18:23:59 +12:00
pub fn find_duplicates ( & mut self , stop_receiver : Option < & Receiver < ( ) > > , progress_sender : Option < & futures ::channel ::mpsc ::UnboundedSender < ProgressData > > ) {
2020-09-27 03:52:13 +13:00
self . directories . optimize_directories ( self . recursive_search , & mut self . text_messages ) ;
2020-10-25 07:44:21 +13:00
match self . check_method {
CheckingMethod ::Name = > {
2020-12-02 22:25:27 +13:00
if ! self . check_files_name ( stop_receiver , progress_sender ) {
2020-10-25 07:44:21 +13:00
self . stopped_search = true ;
return ;
}
}
CheckingMethod ::Size = > {
2020-12-02 22:25:27 +13:00
if ! self . check_files_size ( stop_receiver , progress_sender ) {
2020-10-25 07:44:21 +13:00
self . stopped_search = true ;
return ;
}
}
2021-03-28 01:14:02 +13:00
CheckingMethod ::HashMb | CheckingMethod ::Hash = > {
2020-12-02 22:25:27 +13:00
if ! self . check_files_size ( stop_receiver , progress_sender ) {
2020-10-25 07:44:21 +13:00
self . stopped_search = true ;
return ;
}
2020-12-02 22:25:27 +13:00
if ! self . check_files_hash ( stop_receiver , progress_sender ) {
2020-10-25 07:44:21 +13:00
self . stopped_search = true ;
return ;
}
}
CheckingMethod ::None = > {
panic! ( ) ;
2020-10-10 22:15:20 +13:00
}
2020-09-27 03:52:13 +13:00
}
self . delete_files ( ) ;
self . debug_print ( ) ;
}
2020-10-10 09:32:08 +13:00
pub const fn get_check_method ( & self ) -> & CheckingMethod {
2020-10-08 09:22:39 +13:00
& self . check_method
}
2020-10-10 22:15:20 +13:00
pub fn get_stopped_search ( & self ) -> bool {
self . stopped_search
}
2021-05-07 07:54:44 +12:00
pub fn set_minimal_cache_file_size ( & mut self , minimal_cache_file_size : u64 ) {
self . minimal_cache_file_size = minimal_cache_file_size ;
}
2020-10-25 07:44:21 +13:00
pub const fn get_files_sorted_by_names ( & self ) -> & BTreeMap < String , Vec < FileEntry > > {
& self . files_with_identical_names
}
2021-03-05 00:09:53 +13:00
pub fn set_use_cache ( & mut self , use_cache : bool ) {
self . use_cache = use_cache ;
}
2020-10-10 09:32:08 +13:00
pub const fn get_files_sorted_by_size ( & self ) -> & BTreeMap < u64 , Vec < FileEntry > > {
2020-09-20 21:32:55 +12:00
& self . files_with_identical_size
}
2020-10-10 09:32:08 +13:00
pub const fn get_files_sorted_by_hash ( & self ) -> & BTreeMap < u64 , Vec < Vec < FileEntry > > > {
2020-09-20 21:32:55 +12:00
& self . files_with_identical_hashes
}
2020-10-10 09:32:08 +13:00
pub const fn get_text_messages ( & self ) -> & Messages {
2020-09-18 20:23:49 +12:00
& self . text_messages
2020-09-18 17:32:37 +12:00
}
2020-09-25 08:25:24 +12:00
2020-10-10 09:32:08 +13:00
pub const fn get_information ( & self ) -> & Info {
2020-09-18 17:32:37 +12:00
& self . information
2020-09-12 01:52:06 +12:00
}
2020-08-30 02:12:20 +12:00
2021-02-04 07:59:06 +13:00
pub fn set_hash_type ( & mut self , hash_type : HashType ) {
self . hash_type = hash_type ;
}
2021-02-23 08:14:33 +13:00
pub fn set_ignore_hard_links ( & mut self , ignore_hard_links : bool ) {
self . ignore_hard_links = ignore_hard_links ;
}
2021-03-02 00:23:43 +13:00
pub fn set_dryrun ( & mut self , dryrun : bool ) {
self . dryrun = dryrun ;
}
2020-09-17 22:07:58 +12:00
pub fn set_check_method ( & mut self , check_method : CheckingMethod ) {
self . check_method = check_method ;
}
pub fn set_delete_method ( & mut self , delete_method : DeleteMethod ) {
self . delete_method = delete_method ;
}
2020-10-03 20:51:02 +13:00
pub fn set_minimal_file_size ( & mut self , minimal_file_size : u64 ) {
self . minimal_file_size = match minimal_file_size {
0 = > 1 ,
t = > t ,
} ;
2020-08-30 02:12:20 +12:00
}
2020-09-16 05:17:13 +12:00
pub fn set_recursive_search ( & mut self , recursive_search : bool ) {
self . recursive_search = recursive_search ;
2020-09-12 23:25:23 +12:00
}
2020-09-25 08:25:24 +12:00
2021-01-11 08:44:10 +13:00
pub fn set_included_directory ( & mut self , included_directory : Vec < PathBuf > ) -> bool {
2020-09-27 03:52:13 +13:00
self . directories . set_included_directory ( included_directory , & mut self . text_messages )
2020-09-25 08:25:24 +12:00
}
2021-01-11 08:44:10 +13:00
pub fn set_excluded_directory ( & mut self , excluded_directory : Vec < PathBuf > ) {
2020-09-27 03:52:13 +13:00
self . directories . set_excluded_directory ( excluded_directory , & mut self . text_messages ) ;
2020-08-30 02:12:20 +12:00
}
2020-09-27 03:52:13 +13:00
pub fn set_allowed_extensions ( & mut self , allowed_extensions : String ) {
self . allowed_extensions . set_allowed_extensions ( allowed_extensions , & mut self . text_messages ) ;
2020-08-30 02:12:20 +12:00
}
2021-01-11 08:44:10 +13:00
pub fn set_excluded_items ( & mut self , excluded_items : Vec < String > ) {
2020-09-27 03:52:13 +13:00
self . excluded_items . set_excluded_items ( excluded_items , & mut self . text_messages ) ;
2020-08-27 06:50:07 +12:00
}
2020-08-30 02:12:20 +12:00
2021-04-14 18:23:59 +12:00
fn check_files_name ( & mut self , stop_receiver : Option < & Receiver < ( ) > > , progress_sender : Option < & futures ::channel ::mpsc ::UnboundedSender < ProgressData > > ) -> bool {
2020-10-25 07:44:21 +13:00
let start_time : SystemTime = SystemTime ::now ( ) ;
let mut folders_to_check : Vec < PathBuf > = 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 . directories . included_directories {
folders_to_check . push ( id . clone ( ) ) ;
}
2020-12-02 22:25:27 +13:00
//// PROGRESS THREAD START
const LOOP_DURATION : u32 = 200 ; //in ms
let progress_thread_run = Arc ::new ( AtomicBool ::new ( true ) ) ;
let atomic_file_counter = Arc ::new ( AtomicUsize ::new ( 0 ) ) ;
let progress_thread_handle ;
if let Some ( progress_sender ) = progress_sender {
2021-04-14 18:23:59 +12:00
let progress_send = progress_sender . clone ( ) ;
2020-12-02 22:25:27 +13:00
let progress_thread_run = progress_thread_run . clone ( ) ;
let atomic_file_counter = atomic_file_counter . clone ( ) ;
progress_thread_handle = thread ::spawn ( move | | loop {
progress_send
2021-04-14 18:23:59 +12:00
. unbounded_send ( ProgressData {
2020-12-02 22:25:27 +13:00
checking_method : CheckingMethod ::Name ,
current_stage : 0 ,
max_stage : 0 ,
files_checked : atomic_file_counter . load ( Ordering ::Relaxed ) as usize ,
files_to_check : 0 ,
} )
. unwrap ( ) ;
if ! progress_thread_run . load ( Ordering ::Relaxed ) {
break ;
}
sleep ( Duration ::from_millis ( LOOP_DURATION as u64 ) ) ;
} ) ;
} else {
progress_thread_handle = thread ::spawn ( | | { } ) ;
}
//// PROGRESS THREAD END
2020-10-25 07:44:21 +13:00
while ! folders_to_check . is_empty ( ) {
2020-11-05 06:15:06 +13:00
if stop_receiver . is_some ( ) & & stop_receiver . unwrap ( ) . try_recv ( ) . is_ok ( ) {
2020-12-02 22:25:27 +13:00
// End thread which send info to gui
progress_thread_run . store ( false , Ordering ::Relaxed ) ;
progress_thread_handle . join ( ) . unwrap ( ) ;
2020-10-25 07:44:21 +13:00
return false ;
}
2020-12-02 22:25:27 +13:00
2020-10-25 07:44:21 +13:00
let current_folder = folders_to_check . pop ( ) . unwrap ( ) ;
// Read current dir, if permission are denied just go to next
let read_dir = match fs ::read_dir ( & current_folder ) {
Ok ( t ) = > t ,
Err ( _ ) = > {
self . text_messages . warnings . push ( format! ( " Cannot open dir {} " , current_folder . display ( ) ) ) ;
continue ;
} // Permissions denied
} ;
// Check every sub folder/file/link etc.
' dir : for entry in read_dir {
let entry_data = match entry {
Ok ( t ) = > t ,
Err ( _ ) = > {
self . text_messages . warnings . push ( format! ( " Cannot read entry in dir {} " , current_folder . display ( ) ) ) ;
continue 'dir ;
} //Permissions denied
} ;
let metadata : Metadata = match entry_data . metadata ( ) {
Ok ( t ) = > t ,
Err ( _ ) = > {
self . text_messages . warnings . push ( format! ( " Cannot read metadata in dir {} " , current_folder . display ( ) ) ) ;
continue 'dir ;
} //Permissions denied
} ;
if metadata . is_dir ( ) {
if ! self . recursive_search {
continue 'dir ;
}
let next_folder = current_folder . join ( entry_data . file_name ( ) ) ;
if self . directories . is_excluded ( & next_folder ) {
continue 'dir ;
}
if self . excluded_items . is_excluded ( & next_folder ) {
continue 'dir ;
}
folders_to_check . push ( next_folder ) ;
} else if metadata . is_file ( ) {
2020-12-02 22:25:27 +13:00
atomic_file_counter . fetch_add ( 1 , Ordering ::Relaxed ) ;
2020-10-25 07:44:21 +13:00
// let mut have_valid_extension: bool;
let file_name_lowercase : String = match entry_data . file_name ( ) . into_string ( ) {
Ok ( t ) = > t ,
Err ( _ ) = > continue 'dir ,
}
. to_lowercase ( ) ;
// Checking allowed extensions
if ! self . allowed_extensions . file_extensions . is_empty ( ) {
let allowed = self . allowed_extensions . file_extensions . iter ( ) . any ( | e | file_name_lowercase . ends_with ( ( " . " . to_string ( ) + e . to_lowercase ( ) . as_str ( ) ) . as_str ( ) ) ) ;
if ! allowed {
// Not an allowed extension, ignore it.
continue 'dir ;
}
}
// Checking files
if metadata . len ( ) > = self . minimal_file_size {
let current_file_name = current_folder . join ( entry_data . file_name ( ) ) ;
if self . excluded_items . is_excluded ( & current_file_name ) {
continue 'dir ;
}
// Creating new file entry
let fe : FileEntry = FileEntry {
path : current_file_name . clone ( ) ,
size : metadata . len ( ) ,
modified_date : match metadata . modified ( ) {
Ok ( t ) = > match t . duration_since ( UNIX_EPOCH ) {
Ok ( d ) = > d . as_secs ( ) ,
Err ( _ ) = > {
self . text_messages . warnings . push ( format! ( " File {} seems to be modified before Unix Epoch. " , current_file_name . display ( ) ) ) ;
0
}
} ,
Err ( _ ) = > {
self . text_messages . warnings . push ( format! ( " Unable to get modification date from file {} " , current_file_name . display ( ) ) ) ;
continue 'dir ;
} // Permissions Denied
} ,
2021-01-15 00:17:15 +13:00
hash : " " . to_string ( ) ,
2020-10-25 07:44:21 +13:00
} ;
// Adding files to BTreeMap
self . files_with_identical_names . entry ( entry_data . file_name ( ) . to_string_lossy ( ) . to_string ( ) ) . or_insert_with ( Vec ::new ) ;
self . files_with_identical_names . get_mut ( & entry_data . file_name ( ) . to_string_lossy ( ) . to_string ( ) ) . unwrap ( ) . push ( fe ) ;
}
}
}
}
2020-12-02 22:25:27 +13:00
// End thread which send info to gui
progress_thread_run . store ( false , Ordering ::Relaxed ) ;
progress_thread_handle . join ( ) . unwrap ( ) ;
2020-10-25 07:44:21 +13:00
// Create new BTreeMap without single size entries(files have not duplicates)
let mut new_map : BTreeMap < String , Vec < FileEntry > > = Default ::default ( ) ;
for ( name , vector ) in & self . files_with_identical_names {
if vector . len ( ) > 1 {
self . information . number_of_duplicated_files_by_name + = vector . len ( ) - 1 ;
self . information . number_of_groups_by_name + = 1 ;
new_map . insert ( name . clone ( ) , vector . clone ( ) ) ;
}
}
self . files_with_identical_names = new_map ;
Common ::print_time ( start_time , SystemTime ::now ( ) , " check_files_name " . to_string ( ) ) ;
true
}
2020-09-25 08:25:24 +12:00
/// Read file length and puts it to different boxes(each for different lengths)
/// If in box is only 1 result, then it is removed
2021-04-14 18:23:59 +12:00
fn check_files_size ( & mut self , stop_receiver : Option < & Receiver < ( ) > > , progress_sender : Option < & futures ::channel ::mpsc ::UnboundedSender < ProgressData > > ) -> bool {
2020-08-28 04:57:56 +12:00
let start_time : SystemTime = SystemTime ::now ( ) ;
2020-10-15 05:41:37 +13:00
let mut folders_to_check : Vec < PathBuf > = 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
2020-08-28 04:57:56 +12:00
// Add root folders for finding
2020-09-27 03:52:13 +13:00
for id in & self . directories . included_directories {
2020-10-15 05:41:37 +13:00
folders_to_check . push ( id . clone ( ) ) ;
2020-08-28 04:57:56 +12:00
}
2020-12-02 22:25:27 +13:00
//// PROGRESS THREAD START
const LOOP_DURATION : u32 = 200 ; //in ms
let progress_thread_run = Arc ::new ( AtomicBool ::new ( true ) ) ;
let atomic_file_counter = Arc ::new ( AtomicUsize ::new ( 0 ) ) ;
let progress_thread_handle ;
if let Some ( progress_sender ) = progress_sender {
2021-04-14 18:23:59 +12:00
let progress_send = progress_sender . clone ( ) ;
2020-12-02 22:25:27 +13:00
let progress_thread_run = progress_thread_run . clone ( ) ;
let atomic_file_counter = atomic_file_counter . clone ( ) ;
let checking_method = self . check_method . clone ( ) ;
let max_stage = match self . check_method {
CheckingMethod ::Size = > 0 ,
2021-03-28 01:14:02 +13:00
CheckingMethod ::HashMb | CheckingMethod ::Hash = > 2 ,
2020-12-02 22:25:27 +13:00
_ = > 255 ,
} ;
progress_thread_handle = thread ::spawn ( move | | loop {
progress_send
2021-04-14 18:23:59 +12:00
. unbounded_send ( ProgressData {
2020-12-02 22:25:27 +13:00
checking_method : checking_method . clone ( ) ,
current_stage : 0 ,
max_stage ,
files_checked : atomic_file_counter . load ( Ordering ::Relaxed ) as usize ,
files_to_check : 0 ,
} )
. unwrap ( ) ;
if ! progress_thread_run . load ( Ordering ::Relaxed ) {
break ;
}
sleep ( Duration ::from_millis ( LOOP_DURATION as u64 ) ) ;
} ) ;
} else {
progress_thread_handle = thread ::spawn ( | | { } ) ;
}
//// PROGRESS THREAD END
2020-08-28 04:57:56 +12:00
while ! folders_to_check . is_empty ( ) {
2020-11-05 06:15:06 +13:00
if stop_receiver . is_some ( ) & & stop_receiver . unwrap ( ) . try_recv ( ) . is_ok ( ) {
2020-12-02 22:25:27 +13:00
// End thread which send info to gui
progress_thread_run . store ( false , Ordering ::Relaxed ) ;
progress_thread_handle . join ( ) . unwrap ( ) ;
2020-10-10 22:15:20 +13:00
return false ;
}
2020-12-02 22:25:27 +13:00
2020-10-15 05:41:37 +13:00
let current_folder = folders_to_check . pop ( ) . unwrap ( ) ;
2020-08-28 04:57:56 +12:00
2020-09-27 06:51:28 +13:00
// Read current dir, if permission are denied just go to next
2020-09-01 09:03:10 +12:00
let read_dir = match fs ::read_dir ( & current_folder ) {
2020-08-28 04:57:56 +12:00
Ok ( t ) = > t ,
2020-09-12 01:52:06 +12:00
Err ( _ ) = > {
2020-10-15 05:41:37 +13:00
self . text_messages . warnings . push ( format! ( " Cannot open dir {} " , current_folder . display ( ) ) ) ;
2020-09-12 01:52:06 +12:00
continue ;
} // Permissions denied
2020-08-28 04:57:56 +12:00
} ;
2020-09-27 06:51:28 +13:00
// Check every sub folder/file/link etc.
2020-10-10 09:32:08 +13:00
' dir : for entry in read_dir {
2020-09-10 07:32:23 +12:00
let entry_data = match entry {
2020-09-08 03:39:16 +12:00
Ok ( t ) = > t ,
2020-09-12 01:52:06 +12:00
Err ( _ ) = > {
2020-10-15 05:41:37 +13:00
self . text_messages . warnings . push ( format! ( " Cannot read entry in dir {} " , current_folder . display ( ) ) ) ;
2020-10-24 17:56:39 +13:00
continue 'dir ;
2020-09-12 01:52:06 +12:00
} //Permissions denied
2020-09-08 03:39:16 +12:00
} ;
2020-09-07 19:06:12 +12:00
let metadata : Metadata = match entry_data . metadata ( ) {
Ok ( t ) = > t ,
2020-09-12 01:52:06 +12:00
Err ( _ ) = > {
2020-10-15 05:41:37 +13:00
self . text_messages . warnings . push ( format! ( " Cannot read metadata in dir {} " , current_folder . display ( ) ) ) ;
2020-10-24 17:56:39 +13:00
continue 'dir ;
2020-09-12 01:52:06 +12:00
} //Permissions denied
2020-09-07 19:06:12 +12:00
} ;
2020-08-28 04:57:56 +12:00
if metadata . is_dir ( ) {
2020-09-16 05:17:13 +12:00
if ! self . recursive_search {
2020-10-24 17:56:39 +13:00
continue 'dir ;
2020-09-12 23:25:23 +12:00
}
2020-10-15 05:41:37 +13:00
let next_folder = current_folder . join ( entry_data . file_name ( ) ) ;
if self . directories . is_excluded ( & next_folder ) {
continue 'dir ;
2020-08-28 04:57:56 +12:00
}
2020-10-15 05:41:37 +13:00
if self . excluded_items . is_excluded ( & next_folder ) {
continue 'dir ;
2020-08-28 04:57:56 +12:00
}
2020-10-15 05:41:37 +13:00
2020-10-10 09:32:08 +13:00
folders_to_check . push ( next_folder ) ;
2020-08-28 04:57:56 +12:00
} else if metadata . is_file ( ) {
2020-12-02 22:25:27 +13:00
atomic_file_counter . fetch_add ( 1 , Ordering ::Relaxed ) ;
2020-10-10 09:32:08 +13:00
// let mut have_valid_extension: bool;
2020-10-07 04:10:34 +13:00
let file_name_lowercase : String = match entry_data . file_name ( ) . into_string ( ) {
Ok ( t ) = > t ,
2020-10-24 17:56:39 +13:00
Err ( _ ) = > continue 'dir ,
2020-10-07 04:10:34 +13:00
}
. to_lowercase ( ) ;
2020-08-30 05:11:55 +12:00
2020-09-12 08:32:17 +12:00
// Checking allowed extensions
2020-10-10 22:15:20 +13:00
if ! self . allowed_extensions . file_extensions . is_empty ( ) {
let allowed = self . allowed_extensions . file_extensions . iter ( ) . any ( | e | file_name_lowercase . ends_with ( ( " . " . to_string ( ) + e . to_lowercase ( ) . as_str ( ) ) . as_str ( ) ) ) ;
if ! allowed {
// Not an allowed extension, ignore it.
2021-01-08 11:20:51 +13:00
2020-10-10 22:15:20 +13:00
continue 'dir ;
}
2020-08-30 05:11:55 +12:00
}
2020-09-12 08:32:17 +12:00
// Checking files
2020-10-10 09:32:08 +13:00
if metadata . len ( ) > = self . minimal_file_size {
2020-10-15 05:41:37 +13:00
let current_file_name = current_folder . join ( entry_data . file_name ( ) ) ;
if self . excluded_items . is_excluded ( & current_file_name ) {
continue 'dir ;
2020-10-11 02:18:04 +13:00
}
2020-09-12 08:32:17 +12:00
// Creating new file entry
2020-08-30 02:12:20 +12:00
let fe : FileEntry = FileEntry {
2020-09-12 01:52:06 +12:00
path : current_file_name . clone ( ) ,
2020-08-30 02:12:20 +12:00
size : metadata . len ( ) ,
2020-09-07 19:06:12 +12:00
modified_date : match metadata . modified ( ) {
2020-10-03 04:59:46 +13:00
Ok ( t ) = > match t . duration_since ( UNIX_EPOCH ) {
Ok ( d ) = > d . as_secs ( ) ,
Err ( _ ) = > {
2020-10-15 05:41:37 +13:00
self . text_messages . warnings . push ( format! ( " File {} seems to be modified before Unix Epoch. " , current_file_name . display ( ) ) ) ;
2020-10-03 04:59:46 +13:00
0
}
} ,
2020-09-12 01:52:06 +12:00
Err ( _ ) = > {
2020-10-15 05:41:37 +13:00
self . text_messages . warnings . push ( format! ( " Unable to get modification date from file {} " , current_file_name . display ( ) ) ) ;
2020-10-24 17:56:39 +13:00
continue 'dir ;
2020-09-12 01:52:06 +12:00
} // Permissions Denied
2020-09-07 19:06:12 +12:00
} ,
2021-01-15 00:17:15 +13:00
hash : " " . to_string ( ) ,
2020-08-30 02:12:20 +12:00
} ;
2020-09-27 06:51:28 +13:00
// Adding files to BTreeMap
2020-09-12 01:52:06 +12:00
self . files_with_identical_size . entry ( metadata . len ( ) ) . or_insert_with ( Vec ::new ) ;
2020-08-30 02:12:20 +12:00
self . files_with_identical_size . get_mut ( & metadata . len ( ) ) . unwrap ( ) . push ( fe ) ;
2020-08-29 06:30:22 +12:00
}
2020-08-28 04:57:56 +12:00
}
}
}
2020-12-02 22:25:27 +13:00
// End thread which send info to gui
progress_thread_run . store ( false , Ordering ::Relaxed ) ;
progress_thread_handle . join ( ) . unwrap ( ) ;
2020-09-18 00:01:14 +12:00
2020-09-27 06:51:28 +13:00
// Create new BTreeMap without single size entries(files have not duplicates)
2020-09-18 00:01:14 +12:00
let mut new_map : BTreeMap < u64 , Vec < FileEntry > > = Default ::default ( ) ;
2021-02-21 00:28:06 +13:00
for ( size , vec ) in & self . files_with_identical_size {
if vec . len ( ) < = 1 {
continue ;
}
2021-02-23 08:14:33 +13:00
let vector ;
if self . ignore_hard_links {
vector = filter_hard_links ( vec ) ;
} else {
vector = vec . clone ( ) ;
}
2020-09-18 00:01:14 +12:00
if vector . len ( ) > 1 {
2020-09-18 17:32:37 +12:00
self . information . number_of_duplicated_files_by_size + = vector . len ( ) - 1 ;
self . information . number_of_groups_by_size + = 1 ;
self . information . lost_space_by_size + = ( vector . len ( ) as u64 - 1 ) * size ;
2021-02-21 00:28:06 +13:00
new_map . insert ( * size , vector ) ;
2020-09-18 00:01:14 +12:00
}
}
self . files_with_identical_size = new_map ;
2020-09-01 05:37:30 +12:00
Common ::print_time ( start_time , SystemTime ::now ( ) , " check_files_size " . to_string ( ) ) ;
2020-10-10 22:15:20 +13:00
true
2020-08-28 04:57:56 +12:00
}
2020-09-25 08:25:24 +12:00
/// The slowest checking type, which must be applied after checking for size
2021-04-14 18:23:59 +12:00
fn check_files_hash ( & mut self , stop_receiver : Option < & Receiver < ( ) > > , progress_sender : Option < & futures ::channel ::mpsc ::UnboundedSender < ProgressData > > ) -> bool {
2021-02-04 06:11:04 +13:00
let check_type = Arc ::new ( self . hash_type ) ;
2020-08-29 06:30:22 +12:00
let start_time : SystemTime = SystemTime ::now ( ) ;
2020-12-02 22:25:27 +13:00
let check_was_breaked = AtomicBool ::new ( false ) ; // Used for breaking from GUI and ending check thread
2020-10-24 17:56:39 +13:00
let mut pre_checked_map : BTreeMap < u64 , Vec < FileEntry > > = Default ::default ( ) ;
2020-08-29 06:30:22 +12:00
2020-12-02 22:25:27 +13:00
//// PROGRESS THREAD START
const LOOP_DURATION : u32 = 200 ; //in ms
let progress_thread_run = Arc ::new ( AtomicBool ::new ( true ) ) ;
let atomic_file_counter = Arc ::new ( AtomicUsize ::new ( 0 ) ) ;
let progress_thread_handle ;
if let Some ( progress_sender ) = progress_sender {
2021-04-14 18:23:59 +12:00
let progress_send = progress_sender . clone ( ) ;
2020-12-02 22:25:27 +13:00
let progress_thread_run = progress_thread_run . clone ( ) ;
let atomic_file_counter = atomic_file_counter . clone ( ) ;
let files_to_check = self . files_with_identical_size . iter ( ) . map ( | e | e . 1. len ( ) ) . sum ( ) ;
let checking_method = self . check_method . clone ( ) ;
progress_thread_handle = thread ::spawn ( move | | loop {
progress_send
2021-04-14 18:23:59 +12:00
. unbounded_send ( ProgressData {
2020-12-02 22:25:27 +13:00
checking_method : checking_method . clone ( ) ,
current_stage : 1 ,
max_stage : 2 ,
files_checked : atomic_file_counter . load ( Ordering ::Relaxed ) as usize ,
files_to_check ,
} )
. unwrap ( ) ;
if ! progress_thread_run . load ( Ordering ::Relaxed ) {
break ;
}
sleep ( Duration ::from_millis ( LOOP_DURATION as u64 ) ) ;
} ) ;
} else {
progress_thread_handle = thread ::spawn ( | | { } ) ;
}
//// PROGRESS THREAD END
2020-11-09 04:19:40 +13:00
#[ allow(clippy::type_complexity) ]
2021-05-09 04:29:52 +12:00
let pre_hash_results : Vec < ( u64 , BTreeMap < String , Vec < FileEntry > > , Vec < String > , u64 ) > = self
2020-11-09 04:19:40 +13:00
. files_with_identical_size
. par_iter ( )
. map ( | ( size , vec_file_entry ) | {
2021-05-09 04:29:52 +12:00
let mut hashmap_with_hash : BTreeMap < String , Vec < FileEntry > > = Default ::default ( ) ;
2020-11-09 04:19:40 +13:00
let mut errors : Vec < String > = Vec ::new ( ) ;
let mut bytes_read : u64 = 0 ;
2021-02-04 06:11:04 +13:00
let mut buffer = [ 0 u8 ; 1024 * 2 ] ;
2020-12-02 22:25:27 +13:00
atomic_file_counter . fetch_add ( vec_file_entry . len ( ) , Ordering ::Relaxed ) ;
2021-02-22 22:52:21 +13:00
for file_entry in vec_file_entry {
2020-11-09 04:19:40 +13:00
if stop_receiver . is_some ( ) & & stop_receiver . unwrap ( ) . try_recv ( ) . is_ok ( ) {
check_was_breaked . store ( true , Ordering ::Relaxed ) ;
return None ;
2020-10-24 17:56:39 +13:00
}
2021-02-22 22:52:21 +13:00
match hash_calculation ( & mut buffer , & file_entry , & check_type , 0 ) {
Ok ( ( hash_string , bytes ) ) = > {
bytes_read + = bytes ;
hashmap_with_hash . entry ( hash_string . clone ( ) ) . or_insert_with ( Vec ::new ) ;
hashmap_with_hash . get_mut ( hash_string . as_str ( ) ) . unwrap ( ) . push ( file_entry . clone ( ) ) ;
2020-11-09 04:19:40 +13:00
}
2021-02-22 22:52:21 +13:00
Err ( s ) = > errors . push ( s ) ,
}
2020-10-24 17:56:39 +13:00
}
2020-11-09 04:19:40 +13:00
Some ( ( * size , hashmap_with_hash , errors , bytes_read ) )
} )
. while_some ( )
. collect ( ) ;
2020-12-02 22:25:27 +13:00
// End thread which send info to gui
progress_thread_run . store ( false , Ordering ::Relaxed ) ;
progress_thread_handle . join ( ) . unwrap ( ) ;
2020-11-09 04:19:40 +13:00
// Check if user aborted search(only from GUI)
if check_was_breaked . load ( Ordering ::Relaxed ) {
return false ;
2020-10-24 17:56:39 +13:00
}
2020-11-09 04:19:40 +13:00
// Check results
for ( size , hash_map , mut errors , bytes_read ) in pre_hash_results {
self . information . bytes_read_when_hashing + = bytes_read ;
self . text_messages . warnings . append ( & mut errors ) ;
for ( _hash , mut vec_file_entry ) in hash_map {
if vec_file_entry . len ( ) > 1 {
pre_checked_map . entry ( size ) . or_insert_with ( Vec ::new ) ;
pre_checked_map . get_mut ( & size ) . unwrap ( ) . append ( & mut vec_file_entry ) ;
2020-10-10 22:15:20 +13:00
}
2020-11-09 04:19:40 +13:00
}
}
2020-08-29 06:30:22 +12:00
2020-11-09 04:19:40 +13:00
Common ::print_time ( start_time , SystemTime ::now ( ) , " check_files_hash - prehash " . to_string ( ) ) ;
let start_time : SystemTime = SystemTime ::now ( ) ;
2020-09-07 19:06:12 +12:00
2020-11-09 04:19:40 +13:00
/////////////////////////
2020-12-02 22:25:27 +13:00
//// PROGRESS THREAD START
// const LOOP_DURATION: u32 = 200; //in ms
let progress_thread_run = Arc ::new ( AtomicBool ::new ( true ) ) ;
let atomic_file_counter = Arc ::new ( AtomicUsize ::new ( 0 ) ) ;
let progress_thread_handle ;
if let Some ( progress_sender ) = progress_sender {
2021-04-14 18:23:59 +12:00
let progress_send = progress_sender . clone ( ) ;
2020-12-02 22:25:27 +13:00
let progress_thread_run = progress_thread_run . clone ( ) ;
let atomic_file_counter = atomic_file_counter . clone ( ) ;
let files_to_check = pre_checked_map . iter ( ) . map ( | e | e . 1. len ( ) ) . sum ( ) ;
let checking_method = self . check_method . clone ( ) ;
progress_thread_handle = thread ::spawn ( move | | loop {
progress_send
2021-04-14 18:23:59 +12:00
. unbounded_send ( ProgressData {
2020-12-02 22:25:27 +13:00
checking_method : checking_method . clone ( ) ,
current_stage : 2 ,
max_stage : 2 ,
files_checked : atomic_file_counter . load ( Ordering ::Relaxed ) as usize ,
files_to_check ,
} )
. unwrap ( ) ;
if ! progress_thread_run . load ( Ordering ::Relaxed ) {
break ;
}
sleep ( Duration ::from_millis ( LOOP_DURATION as u64 ) ) ;
} ) ;
} else {
progress_thread_handle = thread ::spawn ( | | { } ) ;
}
//// PROGRESS THREAD END
2020-11-09 04:19:40 +13:00
#[ allow(clippy::type_complexity) ]
2021-05-09 04:29:52 +12:00
let mut full_hash_results : Vec < ( u64 , BTreeMap < String , Vec < FileEntry > > , Vec < String > , u64 ) > ;
2021-01-15 00:17:15 +13:00
match self . check_method {
2021-03-28 01:14:02 +13:00
CheckingMethod ::HashMb = > {
2021-01-15 00:17:15 +13:00
full_hash_results = pre_checked_map
. par_iter ( )
. map ( | ( size , vec_file_entry ) | {
2021-05-09 04:29:52 +12:00
let mut hashmap_with_hash : BTreeMap < String , Vec < FileEntry > > = Default ::default ( ) ;
2021-01-15 00:17:15 +13:00
let mut errors : Vec < String > = Vec ::new ( ) ;
let mut bytes_read : u64 = 0 ;
2021-02-04 06:11:04 +13:00
let mut buffer = [ 0 u8 ; 1024 * 128 ] ;
2021-01-15 00:17:15 +13:00
atomic_file_counter . fetch_add ( vec_file_entry . len ( ) , Ordering ::Relaxed ) ;
2021-02-22 22:52:21 +13:00
for file_entry in vec_file_entry {
2021-01-15 00:17:15 +13:00
if stop_receiver . is_some ( ) & & stop_receiver . unwrap ( ) . try_recv ( ) . is_ok ( ) {
check_was_breaked . store ( true , Ordering ::Relaxed ) ;
return None ;
}
2021-02-22 22:52:21 +13:00
match hash_calculation ( & mut buffer , & file_entry , & check_type , HASH_MB_LIMIT_BYTES ) {
Ok ( ( hash_string , bytes ) ) = > {
bytes_read + = bytes ;
hashmap_with_hash . entry ( hash_string . to_string ( ) ) . or_insert_with ( Vec ::new ) ;
hashmap_with_hash . get_mut ( hash_string . as_str ( ) ) . unwrap ( ) . push ( file_entry . to_owned ( ) ) ;
}
Err ( s ) = > errors . push ( s ) ,
}
2020-09-07 19:06:12 +12:00
}
2021-01-15 00:17:15 +13:00
Some ( ( * size , hashmap_with_hash , errors , bytes_read ) )
} )
. while_some ( )
. collect ( ) ;
}
CheckingMethod ::Hash = > {
2021-03-05 00:09:53 +13:00
let loaded_hash_map ;
2020-09-27 07:46:35 +13:00
2021-03-05 00:09:53 +13:00
let mut records_already_cached : BTreeMap < u64 , Vec < FileEntry > > = Default ::default ( ) ;
let mut non_cached_files_to_check : BTreeMap < u64 , Vec < FileEntry > > = Default ::default ( ) ;
2021-01-15 00:17:15 +13:00
2021-03-05 00:09:53 +13:00
if self . use_cache {
loaded_hash_map = match load_hashes_from_file ( & mut self . text_messages , & self . hash_type ) {
Some ( t ) = > t ,
None = > Default ::default ( ) ,
} ;
for ( size , vec_file_entry ) in pre_checked_map {
#[ allow(clippy::collapsible_if) ]
if ! loaded_hash_map . contains_key ( & size ) {
// If loaded data doesn't contains current info
non_cached_files_to_check . insert ( size , vec_file_entry ) ;
} else {
let loaded_vec_file_entry = loaded_hash_map . get ( & size ) . unwrap ( ) ;
for file_entry in vec_file_entry {
let mut found : bool = false ;
for loaded_file_entry in loaded_vec_file_entry {
if file_entry . path = = loaded_file_entry . path & & file_entry . modified_date = = loaded_file_entry . modified_date {
records_already_cached . entry ( file_entry . size ) . or_insert_with ( Vec ::new ) ;
records_already_cached . get_mut ( & file_entry . size ) . unwrap ( ) . push ( loaded_file_entry . clone ( ) ) ;
found = true ;
break ;
}
2021-01-15 00:17:15 +13:00
}
2021-03-05 00:09:53 +13:00
if ! found {
non_cached_files_to_check . entry ( file_entry . size ) . or_insert_with ( Vec ::new ) ;
non_cached_files_to_check . get_mut ( & file_entry . size ) . unwrap ( ) . push ( file_entry ) ;
}
2020-11-09 04:19:40 +13:00
}
}
2021-01-15 00:17:15 +13:00
}
2021-03-05 00:09:53 +13:00
} else {
loaded_hash_map = Default ::default ( ) ;
mem ::swap ( & mut pre_checked_map , & mut non_cached_files_to_check ) ;
2021-01-15 00:17:15 +13:00
}
full_hash_results = non_cached_files_to_check
. par_iter ( )
. map ( | ( size , vec_file_entry ) | {
2021-05-09 04:29:52 +12:00
let mut hashmap_with_hash : BTreeMap < String , Vec < FileEntry > > = Default ::default ( ) ;
2021-01-15 00:17:15 +13:00
let mut errors : Vec < String > = Vec ::new ( ) ;
let mut bytes_read : u64 = 0 ;
2021-02-04 06:11:04 +13:00
let mut buffer = [ 0 u8 ; 1024 * 128 ] ;
2021-01-15 00:17:15 +13:00
atomic_file_counter . fetch_add ( vec_file_entry . len ( ) , Ordering ::Relaxed ) ;
2021-02-22 22:52:21 +13:00
for file_entry in vec_file_entry {
2021-01-15 00:17:15 +13:00
if stop_receiver . is_some ( ) & & stop_receiver . unwrap ( ) . try_recv ( ) . is_ok ( ) {
check_was_breaked . store ( true , Ordering ::Relaxed ) ;
return None ;
}
2021-02-22 22:52:21 +13:00
match hash_calculation ( & mut buffer , & file_entry , & check_type , u64 ::MAX ) {
Ok ( ( hash_string , bytes ) ) = > {
bytes_read + = bytes ;
let mut file_entry = file_entry . clone ( ) ;
file_entry . hash = hash_string . clone ( ) ;
hashmap_with_hash . entry ( hash_string . clone ( ) ) . or_insert_with ( Vec ::new ) ;
hashmap_with_hash . get_mut ( hash_string . as_str ( ) ) . unwrap ( ) . push ( file_entry ) ;
}
Err ( s ) = > errors . push ( s ) ,
}
2020-11-09 04:19:40 +13:00
}
2021-01-15 00:17:15 +13:00
Some ( ( * size , hashmap_with_hash , errors , bytes_read ) )
} )
. while_some ( )
. collect ( ) ;
2021-03-05 00:09:53 +13:00
if self . use_cache {
' main : for ( size , vec_file_entry ) in records_already_cached {
// Check if size already exists, if exists we must to change it outside because cannot have mut and non mut reference to full_hash_results
for ( full_size , full_hashmap , _errors , _bytes_read ) in & mut full_hash_results {
if size = = * full_size {
for file_entry in vec_file_entry {
full_hashmap . entry ( file_entry . hash . clone ( ) ) . or_insert_with ( Vec ::new ) ;
full_hashmap . get_mut ( & file_entry . hash ) . unwrap ( ) . push ( file_entry ) ;
}
continue 'main ;
2021-01-15 00:17:15 +13:00
}
}
2021-03-05 00:09:53 +13:00
// Size doesn't exists add results to files
2021-05-09 04:29:52 +12:00
let mut temp_hashmap : BTreeMap < String , Vec < FileEntry > > = Default ::default ( ) ;
2021-03-05 00:09:53 +13:00
for file_entry in vec_file_entry {
temp_hashmap . entry ( file_entry . hash . clone ( ) ) . or_insert_with ( Vec ::new ) ;
temp_hashmap . get_mut ( & file_entry . hash ) . unwrap ( ) . push ( file_entry ) ;
}
full_hash_results . push ( ( size , temp_hashmap , Vec ::new ( ) , 0 ) ) ;
2021-01-15 00:17:15 +13:00
}
2020-11-09 04:19:40 +13:00
2021-03-05 00:09:53 +13:00
// Must save all results to file, old loaded from file with all currently counted results
2021-05-09 04:29:52 +12:00
let mut all_results : BTreeMap < String , FileEntry > = Default ::default ( ) ;
2021-03-05 00:09:53 +13:00
for ( _size , vec_file_entry ) in loaded_hash_map {
2021-01-15 00:17:15 +13:00
for file_entry in vec_file_entry {
2021-03-05 00:09:53 +13:00
all_results . insert ( file_entry . path . to_string_lossy ( ) . to_string ( ) , file_entry ) ;
}
}
for ( _size , hashmap , _errors , _bytes_read ) in & full_hash_results {
for vec_file_entry in hashmap . values ( ) {
for file_entry in vec_file_entry {
all_results . insert ( file_entry . path . to_string_lossy ( ) . to_string ( ) , file_entry . clone ( ) ) ;
}
2021-01-15 00:17:15 +13:00
}
}
2021-05-07 07:54:44 +12:00
save_hashes_to_file ( & all_results , & mut self . text_messages , & self . hash_type , self . minimal_cache_file_size ) ;
2021-01-15 00:17:15 +13:00
}
}
_ = > panic! ( " What " ) ,
}
2020-11-09 04:19:40 +13:00
2020-12-02 22:25:27 +13:00
// End thread which send info to gui
progress_thread_run . store ( false , Ordering ::Relaxed ) ;
progress_thread_handle . join ( ) . unwrap ( ) ;
2020-11-09 04:19:40 +13:00
// Check if user aborted search(only from GUI)
if check_was_breaked . load ( Ordering ::Relaxed ) {
return false ;
}
for ( size , hash_map , mut errors , bytes_read ) in full_hash_results {
self . information . bytes_read_when_hashing + = bytes_read ;
self . text_messages . warnings . append ( & mut errors ) ;
for ( _hash , vec_file_entry ) in hash_map {
if vec_file_entry . len ( ) > 1 {
self . files_with_identical_hashes . entry ( size ) . or_insert_with ( Vec ::new ) ;
self . files_with_identical_hashes . get_mut ( & size ) . unwrap ( ) . push ( vec_file_entry ) ;
2020-08-30 02:12:20 +12:00
}
2020-08-29 06:30:22 +12:00
}
}
2020-09-16 05:17:13 +12:00
2020-11-09 04:19:40 +13:00
/////////////////////////
2020-09-27 06:51:28 +13:00
for ( size , vector_vectors ) in & self . files_with_identical_hashes {
for vector in vector_vectors {
self . information . number_of_duplicated_files_by_hash + = vector . len ( ) - 1 ;
2020-09-18 17:32:37 +12:00
self . information . number_of_groups_by_hash + = 1 ;
2020-09-27 06:51:28 +13:00
self . information . lost_space_by_hash + = ( vector . len ( ) as u64 - 1 ) * size ;
2020-09-16 05:17:13 +12:00
}
}
2020-11-09 04:19:40 +13:00
Common ::print_time ( start_time , SystemTime ::now ( ) , " check_files_hash - full hash " . to_string ( ) ) ;
2021-01-16 00:41:45 +13:00
// Clean unused data
self . files_with_identical_size = Default ::default ( ) ;
2020-10-10 22:15:20 +13:00
true
2020-08-29 06:30:22 +12:00
}
2020-09-27 03:52:13 +13:00
/// Function to delete files, from filed before BTreeMap
/// Using another function to delete files to avoid duplicates data
fn delete_files ( & mut self ) {
let start_time : SystemTime = SystemTime ::now ( ) ;
2020-10-25 07:44:21 +13:00
if self . delete_method = = DeleteMethod ::None {
return ;
}
2020-09-27 03:52:13 +13:00
match self . check_method {
2020-10-25 07:44:21 +13:00
CheckingMethod ::Name = > {
for vector in self . files_with_identical_names . values ( ) {
2021-03-02 00:23:43 +13:00
let tuple : ( u64 , usize , usize ) = delete_files ( vector , & self . delete_method , & mut self . text_messages , self . dryrun ) ;
2020-10-25 07:44:21 +13:00
self . information . gained_space + = tuple . 0 ;
self . information . number_of_removed_files + = tuple . 1 ;
self . information . number_of_failed_to_remove_files + = tuple . 2 ;
}
}
2021-03-28 01:14:02 +13:00
CheckingMethod ::Hash | CheckingMethod ::HashMb = > {
2020-09-27 07:46:35 +13:00
for vector_vectors in self . files_with_identical_hashes . values ( ) {
2020-09-27 06:51:28 +13:00
for vector in vector_vectors . iter ( ) {
2021-03-02 00:23:43 +13:00
let tuple : ( u64 , usize , usize ) = delete_files ( vector , & self . delete_method , & mut self . text_messages , self . dryrun ) ;
2020-09-27 03:52:13 +13:00
self . information . gained_space + = tuple . 0 ;
self . information . number_of_removed_files + = tuple . 1 ;
self . information . number_of_failed_to_remove_files + = tuple . 2 ;
}
}
}
CheckingMethod ::Size = > {
2020-09-27 07:46:35 +13:00
for vector in self . files_with_identical_size . values ( ) {
2021-03-02 00:23:43 +13:00
let tuple : ( u64 , usize , usize ) = delete_files ( vector , & self . delete_method , & mut self . text_messages , self . dryrun ) ;
2020-09-27 03:52:13 +13:00
self . information . gained_space + = tuple . 0 ;
self . information . number_of_removed_files + = tuple . 1 ;
self . information . number_of_failed_to_remove_files + = tuple . 2 ;
}
}
CheckingMethod ::None = > {
//Just do nothing
panic! ( " Checking method should never be none. " ) ;
}
}
Common ::print_time ( start_time , SystemTime ::now ( ) , " delete_files " . to_string ( ) ) ;
}
}
impl Default for DuplicateFinder {
fn default ( ) -> Self {
Self ::new ( )
}
}
impl DebugPrint for DuplicateFinder {
2020-09-10 22:42:44 +12:00
#[ allow(dead_code) ]
2020-09-17 22:07:58 +12:00
#[ allow(unreachable_code) ]
2020-09-25 08:25:24 +12:00
/// Debugging printing - only available on debug build
2020-08-30 02:12:20 +12:00
fn debug_print ( & self ) {
2020-09-17 22:07:58 +12:00
#[ cfg(not(debug_assertions)) ]
{
return ;
}
2020-09-08 19:41:22 +12:00
println! ( " ---------------DEBUG PRINT--------------- " ) ;
2020-09-18 17:32:37 +12:00
println! ( " ### Information's " ) ;
2020-09-18 20:23:49 +12:00
println! ( " Errors size - {} " , self . text_messages . errors . len ( ) ) ;
println! ( " Warnings size - {} " , self . text_messages . warnings . len ( ) ) ;
println! ( " Messages size - {} " , self . text_messages . messages . len ( ) ) ;
println! (
" Number of duplicated files by size(in groups) - {} ({}) " ,
self . information . number_of_duplicated_files_by_size , self . information . number_of_groups_by_size
) ;
println! (
" Number of duplicated files by hash(in groups) - {} ({}) " ,
self . information . number_of_duplicated_files_by_hash , self . information . number_of_groups_by_hash
) ;
2020-10-25 07:44:21 +13:00
println! (
" Number of duplicated files by name(in groups) - {} ({}) " ,
self . information . number_of_duplicated_files_by_name , self . information . number_of_groups_by_name
) ;
2020-09-18 17:32:37 +12:00
println! ( " Lost space by size - {} ( {} bytes) " , self . information . lost_space_by_size . file_size ( options ::BINARY ) . unwrap ( ) , self . information . lost_space_by_size ) ;
println! ( " Lost space by hash - {} ( {} bytes) " , self . information . lost_space_by_hash . file_size ( options ::BINARY ) . unwrap ( ) , self . information . lost_space_by_hash ) ;
2020-09-18 20:23:49 +12:00
println! (
" Gained space by removing duplicated entries - {} ({} bytes) " ,
self . information . gained_space . file_size ( options ::BINARY ) . unwrap ( ) ,
self . information . gained_space
) ;
2020-09-19 18:31:32 +12:00
println! (
" Bytes read when hashing - {} ({} bytes) " ,
self . information . bytes_read_when_hashing . file_size ( options ::BINARY ) . unwrap ( ) ,
self . information . bytes_read_when_hashing
) ;
2020-09-18 17:32:37 +12:00
println! ( " Number of removed files - {} " , self . information . number_of_removed_files ) ;
println! ( " Number of failed to remove files - {} " , self . information . number_of_failed_to_remove_files ) ;
2020-09-16 05:17:13 +12:00
println! ( " ### Other " ) ;
println! ( " Files list size - {} " , self . files_with_identical_size . len ( ) ) ;
println! ( " Hashed Files list size - {} " , self . files_with_identical_hashes . len ( ) ) ;
2020-09-27 03:52:13 +13:00
println! ( " Allowed extensions - {:?} " , self . allowed_extensions . file_extensions ) ;
println! ( " Excluded items - {:?} " , self . excluded_items . items ) ;
println! ( " Included directories - {:?} " , self . directories . included_directories ) ;
println! ( " Excluded directories - {:?} " , self . directories . excluded_directories ) ;
2020-09-16 05:17:13 +12:00
println! ( " Recursive search - {} " , self . recursive_search . to_string ( ) ) ;
2020-10-03 20:51:02 +13:00
println! ( " Minimum file size - {:?} " , self . minimal_file_size ) ;
2020-09-26 23:48:53 +12:00
println! ( " Checking Method - {:?} " , self . check_method ) ;
println! ( " Delete Method - {:?} " , self . delete_method ) ;
2020-09-08 19:41:22 +12:00
println! ( " ----------------------------------------- " ) ;
2020-08-27 06:50:07 +12:00
}
2020-09-27 03:52:13 +13:00
}
impl SaveResults for DuplicateFinder {
fn save_results_to_file ( & mut self , file_name : & str ) -> bool {
let start_time : SystemTime = SystemTime ::now ( ) ;
let file_name : String = match file_name {
" " = > " results.txt " . to_string ( ) ,
k = > k . to_string ( ) ,
} ;
2021-01-09 23:52:43 +13:00
let file_handler = match File ::create ( & file_name ) {
2020-09-27 03:52:13 +13:00
Ok ( t ) = > t ,
Err ( _ ) = > {
2020-09-27 06:51:28 +13:00
self . text_messages . errors . push ( format! ( " Failed to create file {} " , file_name ) ) ;
2020-09-27 03:52:13 +13:00
return false ;
}
} ;
2021-01-09 23:52:43 +13:00
let mut writer = BufWriter ::new ( file_handler ) ;
2020-09-27 03:52:13 +13:00
2020-10-15 05:41:37 +13:00
if writeln! (
2021-01-09 23:52:43 +13:00
writer ,
2020-10-15 05:41:37 +13:00
" Results of searching {:?} with excluded directories {:?} and excluded items {:?} " ,
self . directories . included_directories , self . directories . excluded_directories , self . excluded_items . items
)
. is_err ( )
{
self . text_messages . errors . push ( format! ( " Failed to save results to file {} " , file_name ) ) ;
return false ;
2020-09-27 03:52:13 +13:00
}
2020-10-25 07:44:21 +13:00
match self . check_method {
CheckingMethod ::Name = > {
2021-04-01 22:37:16 +13:00
if ! self . files_with_identical_names . is_empty ( ) {
2021-01-09 23:52:43 +13:00
writeln! ( writer , " -------------------------------------------------Files with same names------------------------------------------------- " ) . unwrap ( ) ;
2020-10-25 07:44:21 +13:00
writeln! (
2021-01-09 23:52:43 +13:00
writer ,
2020-10-25 07:44:21 +13:00
" Found {} files in {} groups with same name(may have different content) " ,
self . information . number_of_duplicated_files_by_name , self . information . number_of_groups_by_name ,
)
. unwrap ( ) ;
for ( name , vector ) in self . files_with_identical_names . iter ( ) . rev ( ) {
2021-01-09 23:52:43 +13:00
writeln! ( writer , " Name - {} - {} files " , name , vector . len ( ) ) . unwrap ( ) ;
2020-10-25 07:44:21 +13:00
for j in vector {
2021-01-09 23:52:43 +13:00
writeln! ( writer , " {} " , j . path . display ( ) ) . unwrap ( ) ;
2020-10-25 07:44:21 +13:00
}
2021-01-09 23:52:43 +13:00
writeln! ( writer ) . unwrap ( ) ;
2020-10-25 07:44:21 +13:00
}
} else {
2021-01-09 23:52:43 +13:00
write! ( writer , " Not found any files with same names. " ) . unwrap ( ) ;
2020-09-27 03:52:13 +13:00
}
}
2020-10-25 07:44:21 +13:00
CheckingMethod ::Size = > {
if ! self . files_with_identical_size . is_empty ( ) {
2021-01-09 23:52:43 +13:00
writeln! ( writer , " -------------------------------------------------Files with same size------------------------------------------------- " ) . unwrap ( ) ;
2020-10-25 07:44:21 +13:00
writeln! (
2021-01-09 23:52:43 +13:00
writer ,
2020-10-25 07:44:21 +13:00
" Found {} duplicated files which in {} groups which takes {}. " ,
self . information . number_of_duplicated_files_by_size ,
self . information . number_of_groups_by_size ,
self . information . lost_space_by_size . file_size ( options ::BINARY ) . unwrap ( )
)
. unwrap ( ) ;
for ( size , vector ) in self . files_with_identical_size . iter ( ) . rev ( ) {
2021-01-09 23:52:43 +13:00
write! ( writer , " \n ---- Size {} ({}) - {} files \n " , size . file_size ( options ::BINARY ) . unwrap ( ) , size , vector . len ( ) ) . unwrap ( ) ;
2020-09-27 03:52:13 +13:00
for file_entry in vector {
2021-01-09 23:52:43 +13:00
writeln! ( writer , " {} " , file_entry . path . display ( ) ) . unwrap ( ) ;
2020-09-27 03:52:13 +13:00
}
}
2020-10-25 07:44:21 +13:00
} else {
2021-01-09 23:52:43 +13:00
write! ( writer , " Not found any duplicates. " ) . unwrap ( ) ;
2020-10-25 07:44:21 +13:00
}
}
2021-03-28 01:14:02 +13:00
CheckingMethod ::Hash | CheckingMethod ::HashMb = > {
2020-10-25 07:44:21 +13:00
if ! self . files_with_identical_hashes . is_empty ( ) {
2021-01-09 23:52:43 +13:00
writeln! ( writer , " -------------------------------------------------Files with same hashes------------------------------------------------- " ) . unwrap ( ) ;
2020-10-25 07:44:21 +13:00
writeln! (
2021-01-09 23:52:43 +13:00
writer ,
2020-10-25 07:44:21 +13:00
" Found {} duplicated files which in {} groups which takes {}. " ,
self . information . number_of_duplicated_files_by_hash ,
self . information . number_of_groups_by_hash ,
self . information . lost_space_by_hash . file_size ( options ::BINARY ) . unwrap ( )
)
. unwrap ( ) ;
for ( size , vectors_vector ) in self . files_with_identical_hashes . iter ( ) . rev ( ) {
for vector in vectors_vector {
2021-01-09 23:52:43 +13:00
writeln! ( writer , " \n ---- Size {} ({}) - {} files " , size . file_size ( options ::BINARY ) . unwrap ( ) , size , vector . len ( ) ) . unwrap ( ) ;
2020-10-25 07:44:21 +13:00
for file_entry in vector {
2021-01-09 23:52:43 +13:00
writeln! ( writer , " {} " , file_entry . path . display ( ) ) . unwrap ( ) ;
2020-10-25 07:44:21 +13:00
}
}
}
} else {
2021-01-09 23:52:43 +13:00
write! ( writer , " Not found any duplicates. " ) . unwrap ( ) ;
2020-09-27 03:52:13 +13:00
}
}
2020-10-25 07:44:21 +13:00
CheckingMethod ::None = > {
panic! ( ) ;
}
2020-09-27 03:52:13 +13:00
}
Common ::print_time ( start_time , SystemTime ::now ( ) , " save_results_to_file " . to_string ( ) ) ;
true
}
}
impl PrintResults for DuplicateFinder {
2020-09-18 17:32:37 +12:00
/// Print information's about duplicated entries
2020-09-25 08:25:24 +12:00
/// Only needed for CLI
2020-09-27 03:52:13 +13:00
fn print_results ( & self ) {
2020-08-29 06:30:22 +12:00
let start_time : SystemTime = SystemTime ::now ( ) ;
2020-08-30 02:12:20 +12:00
let mut number_of_files : u64 = 0 ;
let mut number_of_groups : u64 = 0 ;
2020-09-17 23:35:11 +12:00
match self . check_method {
2020-10-25 07:44:21 +13:00
CheckingMethod ::Name = > {
for i in & self . files_with_identical_names {
number_of_files + = i . 1. len ( ) as u64 ;
number_of_groups + = 1 ;
}
println! ( " Found {} files in {} groups with same name(may have different content) " , number_of_files , number_of_groups , ) ;
for ( name , vector ) in & self . files_with_identical_names {
println! ( " Name - {} - {} files " , name , vector . len ( ) ) ;
for j in vector {
println! ( " {} " , j . path . display ( ) ) ;
}
println! ( ) ;
}
}
2021-03-28 01:14:02 +13:00
CheckingMethod ::Hash | CheckingMethod ::HashMb = > {
2020-09-10 22:42:44 +12:00
for ( _size , vector ) in self . files_with_identical_hashes . iter ( ) {
for j in vector {
2020-08-30 02:12:20 +12:00
number_of_files + = j . len ( ) as u64 ;
number_of_groups + = 1 ;
}
}
2020-08-31 00:00:22 +12:00
println! (
2020-09-02 03:10:54 +12:00
" Found {} duplicated files in {} groups with same content which took {}: " ,
2020-08-31 00:00:22 +12:00
number_of_files ,
number_of_groups ,
2020-09-18 17:32:37 +12:00
self . information . lost_space_by_size . file_size ( options ::BINARY ) . unwrap ( )
2020-08-31 00:00:22 +12:00
) ;
2020-09-17 23:35:11 +12:00
for ( size , vector ) in self . files_with_identical_hashes . iter ( ) . rev ( ) {
2020-09-10 22:42:44 +12:00
for j in vector {
2020-09-17 23:35:11 +12:00
println! ( " Size - {} ( {} ) - {} files " , size . file_size ( options ::BINARY ) . unwrap ( ) , size , j . len ( ) ) ;
2020-08-30 02:12:20 +12:00
for k in j {
2020-10-15 05:41:37 +13:00
println! ( " {} " , k . path . display ( ) ) ;
2020-08-30 02:12:20 +12:00
}
println! ( " ---- " ) ;
}
println! ( ) ;
}
2020-08-28 04:57:56 +12:00
}
2020-09-25 08:25:24 +12:00
CheckingMethod ::Size = > {
2020-08-30 02:12:20 +12:00
for i in & self . files_with_identical_size {
number_of_files + = i . 1. len ( ) as u64 ;
number_of_groups + = 1 ;
}
2020-08-31 00:00:22 +12:00
println! (
" Found {} files in {} groups with same size(may have different content) which took {}: " ,
number_of_files ,
number_of_groups ,
2020-09-18 17:32:37 +12:00
self . information . lost_space_by_size . file_size ( options ::BINARY ) . unwrap ( )
2020-08-31 00:00:22 +12:00
) ;
2020-09-17 23:35:11 +12:00
for ( size , vector ) in & self . files_with_identical_size {
println! ( " Size - {} ( {} ) - {} files " , size . file_size ( options ::BINARY ) . unwrap ( ) , size , vector . len ( ) ) ;
for j in vector {
2020-10-15 05:41:37 +13:00
println! ( " {} " , j . path . display ( ) ) ;
2020-08-31 03:18:04 +12:00
}
println! ( ) ;
}
2020-08-27 19:42:37 +12:00
}
2020-09-25 08:25:24 +12:00
CheckingMethod ::None = > {
panic! ( " Checking Method shouldn't be ever set to None " ) ;
2020-09-17 22:07:58 +12:00
}
2020-08-27 06:50:07 +12:00
}
2020-09-27 08:50:16 +13:00
Common ::print_time ( start_time , SystemTime ::now ( ) , " print_entries " . to_string ( ) ) ;
2020-08-27 08:24:02 +12:00
}
2020-09-07 19:06:12 +12:00
}
2020-09-25 08:25:24 +12:00
/// Functions to remove slice(vector) of files with provided method
/// Returns size of removed elements, number of deleted and failed to delete files and modified warning list
2021-03-02 00:23:43 +13:00
fn delete_files ( vector : & [ FileEntry ] , delete_method : & DeleteMethod , text_messages : & mut Messages , dryrun : bool ) -> ( u64 , usize , usize ) {
2020-09-01 02:15:56 +12:00
assert! ( vector . len ( ) > 1 , " Vector length must be bigger than 1(This should be done in previous steps). " ) ;
2020-09-12 01:52:06 +12:00
let mut gained_space : u64 = 0 ;
let mut removed_files : usize = 0 ;
let mut failed_to_remove_files : usize = 0 ;
2021-02-27 21:00:59 +13:00
let mut values = vector . iter ( ) . enumerate ( ) ;
let q_index = match delete_method {
DeleteMethod ::OneOldest | DeleteMethod ::AllExceptNewest = > values . max_by ( | ( _ , l ) , ( _ , r ) | l . modified_date . cmp ( & r . modified_date ) ) ,
DeleteMethod ::OneNewest | DeleteMethod ::AllExceptOldest | DeleteMethod ::HardLink = > values . min_by ( | ( _ , l ) , ( _ , r ) | l . modified_date . cmp ( & r . modified_date ) ) ,
DeleteMethod ::None = > values . next ( ) ,
} ;
let q_index = q_index . map ( | t | t . 0 ) . unwrap_or ( 0 ) ;
let n = match delete_method {
DeleteMethod ::OneNewest | DeleteMethod ::OneOldest = > 1 ,
DeleteMethod ::AllExceptNewest | DeleteMethod ::AllExceptOldest | DeleteMethod ::None | DeleteMethod ::HardLink = > usize ::MAX ,
} ;
for ( index , file ) in vector . iter ( ) . enumerate ( ) {
if q_index = = index {
continue ;
} else if removed_files + failed_to_remove_files > = n {
break ;
2021-02-06 05:59:34 +13:00
}
2021-03-02 00:23:43 +13:00
2021-02-27 21:00:59 +13:00
let r = match delete_method {
2021-03-02 00:23:43 +13:00
DeleteMethod ::OneOldest | DeleteMethod ::OneNewest | DeleteMethod ::AllExceptOldest | DeleteMethod ::AllExceptNewest = > {
if dryrun {
Ok ( Some ( format! ( " Delete {} " , file . path . display ( ) ) ) )
} else {
fs ::remove_file ( & file . path ) . map ( | _ | None )
}
}
DeleteMethod ::HardLink = > {
let src = & vector [ q_index ] . path ;
if dryrun {
Ok ( Some ( format! ( " Replace file {} with hard link to {} " , file . path . display ( ) , src . display ( ) ) ) )
} else {
make_hard_link ( & src , & file . path ) . map ( | _ | None )
}
}
DeleteMethod ::None = > Ok ( None ) ,
2021-02-27 21:00:59 +13:00
} ;
2021-03-02 00:23:43 +13:00
match r {
Err ( e ) = > {
failed_to_remove_files + = 1 ;
text_messages . warnings . push ( format! ( " Failed to remove {} ( {} ) " , file . path . display ( ) , e ) ) ;
}
Ok ( Some ( msg ) ) = > {
text_messages . messages . push ( msg ) ;
removed_files + = 1 ;
gained_space + = file . size ;
}
Ok ( None ) = > {
removed_files + = 1 ;
gained_space + = file . size ;
}
2020-09-01 02:15:56 +12:00
}
2021-02-27 21:00:59 +13:00
}
2020-09-12 01:52:06 +12:00
( gained_space , removed_files , failed_to_remove_files )
2020-08-27 06:50:07 +12:00
}
2021-01-15 00:17:15 +13:00
2021-02-21 00:28:06 +13:00
#[ cfg(target_family = " windows " ) ]
fn filter_hard_links ( vec_file_entry : & [ FileEntry ] ) -> Vec < FileEntry > {
vec_file_entry . to_vec ( )
}
#[ cfg(target_family = " unix " ) ]
fn filter_hard_links ( vec_file_entry : & [ FileEntry ] ) -> Vec < FileEntry > {
let mut inodes : HashSet < u64 > = HashSet ::with_capacity ( vec_file_entry . len ( ) ) ;
let mut identical : Vec < FileEntry > = Vec ::with_capacity ( vec_file_entry . len ( ) ) ;
for f in vec_file_entry {
if let Ok ( meta ) = fs ::metadata ( & f . path ) {
if ! inodes . insert ( meta . ino ( ) ) {
continue ;
}
}
identical . push ( f . clone ( ) ) ;
}
identical
}
2021-03-28 01:14:02 +13:00
pub fn make_hard_link ( src : & Path , dst : & Path ) -> io ::Result < ( ) > {
2021-02-12 07:04:23 +13:00
let dst_dir = dst . parent ( ) . ok_or_else ( | | Error ::new ( ErrorKind ::Other , " No parent " ) ) ? ;
let temp = tempfile ::Builder ::new ( ) . tempfile_in ( dst_dir ) ? ;
fs ::rename ( dst , temp . path ( ) ) ? ;
let result = fs ::hard_link ( src , dst ) ;
if result . is_err ( ) {
fs ::rename ( temp . path ( ) , dst ) ? ;
}
result
}
2021-05-09 04:29:52 +12:00
fn save_hashes_to_file ( hashmap : & BTreeMap < String , FileEntry > , text_messages : & mut Messages , type_of_hash : & HashType , minimal_cache_file_size : u64 ) {
2021-01-15 00:17:15 +13:00
if let Some ( proj_dirs ) = ProjectDirs ::from ( " pl " , " Qarmin " , " Czkawka " ) {
let cache_dir = PathBuf ::from ( proj_dirs . cache_dir ( ) ) ;
if cache_dir . exists ( ) {
if ! cache_dir . is_dir ( ) {
text_messages . messages . push ( format! ( " Config dir {} is a file! " , cache_dir . display ( ) ) ) ;
return ;
}
} else if fs ::create_dir_all ( & cache_dir ) . is_err ( ) {
text_messages . messages . push ( format! ( " Cannot create config dir {} " , cache_dir . display ( ) ) ) ;
return ;
}
let cache_file = cache_dir . join ( CACHE_FILE_NAME . replace ( " . " , format! ( " _ {:?} . " , type_of_hash ) . as_str ( ) ) ) ;
let file_handler = match OpenOptions ::new ( ) . truncate ( true ) . write ( true ) . create ( true ) . open ( & cache_file ) {
Ok ( t ) = > t ,
Err ( _ ) = > {
text_messages . messages . push ( format! ( " Cannot create or open cache file {} " , cache_file . display ( ) ) ) ;
return ;
}
} ;
let mut writer = BufWriter ::new ( file_handler ) ;
for file_entry in hashmap . values ( ) {
// Only cache bigger than 5MB files
2021-05-07 07:54:44 +12:00
if file_entry . size > = minimal_cache_file_size {
2021-01-15 00:17:15 +13:00
let string : String = format! ( " {} // {} // {} // {} " , file_entry . path . display ( ) , file_entry . size , file_entry . modified_date , file_entry . hash ) ;
if writeln! ( writer , " {} " , string ) . is_err ( ) {
text_messages . messages . push ( format! ( " Failed to save some data to cache file {} " , cache_file . display ( ) ) ) ;
return ;
} ;
}
}
}
}
2021-02-22 22:52:21 +13:00
pub trait MyHasher {
fn update ( & mut self , bytes : & [ u8 ] ) ;
fn finalize ( & self ) -> String ;
2021-02-04 06:11:04 +13:00
}
2021-02-22 22:52:21 +13:00
fn hash_calculation ( buffer : & mut [ u8 ] , file_entry : & FileEntry , hash_type : & HashType , limit : u64 ) -> Result < ( String , u64 ) , String > {
let mut file_handler = match File ::open ( & file_entry . path ) {
Ok ( t ) = > t ,
Err ( _ ) = > return Err ( format! ( " Unable to check hash of file {} " , file_entry . path . display ( ) ) ) ,
} ;
let hasher = & mut * hash_type . hasher ( ) ;
let mut current_file_read_bytes : u64 = 0 ;
loop {
let n = match file_handler . read ( buffer ) {
Ok ( 0 ) = > break ,
Ok ( t ) = > t ,
Err ( _ ) = > return Err ( format! ( " Error happened when checking hash of file {} " , file_entry . path . display ( ) ) ) ,
} ;
2021-02-04 07:59:06 +13:00
2021-02-22 22:52:21 +13:00
current_file_read_bytes + = n as u64 ;
hasher . update ( & buffer [ .. n ] ) ;
2021-02-04 07:59:06 +13:00
2021-02-22 22:52:21 +13:00
if current_file_read_bytes > = limit {
break ;
2021-02-04 07:59:06 +13:00
}
2021-02-04 06:11:04 +13:00
}
2021-02-22 22:52:21 +13:00
Ok ( ( hasher . finalize ( ) , current_file_read_bytes ) )
2021-02-04 06:11:04 +13:00
}
2021-01-15 00:17:15 +13:00
fn load_hashes_from_file ( text_messages : & mut Messages , type_of_hash : & HashType ) -> Option < BTreeMap < u64 , Vec < FileEntry > > > {
if let Some ( proj_dirs ) = ProjectDirs ::from ( " pl " , " Qarmin " , " Czkawka " ) {
let cache_dir = PathBuf ::from ( proj_dirs . cache_dir ( ) ) ;
let cache_file = cache_dir . join ( CACHE_FILE_NAME . replace ( " . " , format! ( " _ {:?} . " , type_of_hash ) . as_str ( ) ) ) ;
let file_handler = match OpenOptions ::new ( ) . read ( true ) . open ( & cache_file ) {
Ok ( t ) = > t ,
Err ( _ ) = > {
// text_messages.messages.push(format!("Cannot find or open cache file {}", cache_file.display())); // This shouldn't be write to output
return None ;
}
} ;
let reader = BufReader ::new ( file_handler ) ;
let mut hashmap_loaded_entries : BTreeMap < u64 , Vec < FileEntry > > = Default ::default ( ) ;
// Read the file line by line using the lines() iterator from std::io::BufRead.
for ( index , line ) in reader . lines ( ) . enumerate ( ) {
let line = match line {
Ok ( t ) = > t ,
Err ( _ ) = > {
text_messages . warnings . push ( format! ( " Failed to load line number {} from cache file {} " , index + 1 , cache_file . display ( ) ) ) ;
return None ;
}
} ;
let uuu = line . split ( " // " ) . collect ::< Vec < & str > > ( ) ;
if uuu . len ( ) ! = 4 {
text_messages
. warnings
. push ( format! ( " Found invalid data(too much or too low amount of data) in line {} - ( {} ) in cache file {} " , index + 1 , line , cache_file . display ( ) ) ) ;
continue ;
}
// Don't load cache data if destination file not exists
if Path ::new ( uuu [ 0 ] ) . exists ( ) {
let file_entry = FileEntry {
path : PathBuf ::from ( uuu [ 0 ] ) ,
size : match uuu [ 1 ] . parse ::< u64 > ( ) {
Ok ( t ) = > t ,
Err ( _ ) = > {
text_messages . warnings . push ( format! ( " Found invalid size value in line {} - ( {} ) in cache file {} " , index + 1 , line , cache_file . display ( ) ) ) ;
continue ;
}
} ,
modified_date : match uuu [ 2 ] . parse ::< u64 > ( ) {
Ok ( t ) = > t ,
Err ( _ ) = > {
text_messages . warnings . push ( format! ( " Found invalid modified date value in line {} - ( {} ) in cache file {} " , index + 1 , line , cache_file . display ( ) ) ) ;
continue ;
}
} ,
hash : uuu [ 3 ] . to_string ( ) ,
} ;
hashmap_loaded_entries . entry ( file_entry . size ) . or_insert_with ( Vec ::new ) ;
hashmap_loaded_entries . get_mut ( & file_entry . size ) . unwrap ( ) . push ( file_entry ) ;
}
}
return Some ( hashmap_loaded_entries ) ;
}
text_messages . messages . push ( " Cannot find or open system config dir to save cache file " . to_string ( ) ) ;
None
}
2021-02-12 07:04:23 +13:00
#[ cfg(test) ]
mod tests {
use super ::* ;
use std ::fs ::{ read_dir , File } ;
2021-02-22 22:52:21 +13:00
use std ::io ;
2021-02-12 07:04:23 +13:00
#[ cfg(target_family = " windows " ) ]
use std ::os ::fs ::MetadataExt ;
#[ cfg(target_family = " unix " ) ]
use std ::os ::unix ::fs ::MetadataExt ;
#[ cfg(target_family = " unix " ) ]
fn assert_inode ( before : & Metadata , after : & Metadata ) {
assert_eq! ( before . ino ( ) , after . ino ( ) ) ;
}
#[ cfg(target_family = " windows " ) ]
fn assert_inode ( _ : & Metadata , _ : & Metadata ) { }
#[ test ]
2021-02-22 22:52:21 +13:00
fn test_make_hard_link ( ) -> io ::Result < ( ) > {
2021-02-12 07:04:23 +13:00
let dir = tempfile ::Builder ::new ( ) . tempdir ( ) ? ;
let ( src , dst ) = ( dir . path ( ) . join ( " a " ) , dir . path ( ) . join ( " b " ) ) ;
File ::create ( & src ) ? ;
let metadata = fs ::metadata ( & src ) ? ;
File ::create ( & dst ) ? ;
make_hard_link ( & src , & dst ) ? ;
assert_inode ( & metadata , & fs ::metadata ( & dst ) ? ) ;
assert_eq! ( metadata . permissions ( ) , fs ::metadata ( & dst ) ? . permissions ( ) ) ;
assert_eq! ( metadata . modified ( ) ? , fs ::metadata ( & dst ) ? . modified ( ) ? ) ;
assert_inode ( & metadata , & fs ::metadata ( & src ) ? ) ;
assert_eq! ( metadata . permissions ( ) , fs ::metadata ( & src ) ? . permissions ( ) ) ;
assert_eq! ( metadata . modified ( ) ? , fs ::metadata ( & src ) ? . modified ( ) ? ) ;
let mut actual = read_dir ( & dir ) ? . map ( | e | e . unwrap ( ) . path ( ) ) . collect ::< Vec < PathBuf > > ( ) ;
actual . sort ( ) ;
assert_eq! ( vec! [ src , dst ] , actual ) ;
Ok ( ( ) )
}
#[ test ]
2021-02-22 22:52:21 +13:00
fn test_make_hard_link_fails ( ) -> io ::Result < ( ) > {
2021-02-12 07:04:23 +13:00
let dir = tempfile ::Builder ::new ( ) . tempdir ( ) ? ;
let ( src , dst ) = ( dir . path ( ) . join ( " a " ) , dir . path ( ) . join ( " b " ) ) ;
File ::create ( & dst ) ? ;
let metadata = fs ::metadata ( & dst ) ? ;
assert! ( make_hard_link ( & src , & dst ) . is_err ( ) ) ;
assert_inode ( & metadata , & fs ::metadata ( & dst ) ? ) ;
assert_eq! ( metadata . permissions ( ) , fs ::metadata ( & dst ) ? . permissions ( ) ) ;
assert_eq! ( metadata . modified ( ) ? , fs ::metadata ( & dst ) ? . modified ( ) ? ) ;
assert_eq! ( vec! [ dst ] , read_dir ( & dir ) ? . map ( | e | e . unwrap ( ) . path ( ) ) . collect ::< Vec < PathBuf > > ( ) ) ;
Ok ( ( ) )
}
2021-02-21 00:28:06 +13:00
#[ test ]
fn test_filter_hard_links_empty ( ) {
let expected : Vec < FileEntry > = Default ::default ( ) ;
assert_eq! ( expected , filter_hard_links ( & [ ] ) ) ;
}
#[ cfg(target_family = " unix " ) ]
#[ test ]
2021-02-22 22:52:21 +13:00
fn test_filter_hard_links ( ) -> io ::Result < ( ) > {
2021-02-21 00:28:06 +13:00
let dir = tempfile ::Builder ::new ( ) . tempdir ( ) ? ;
let ( src , dst ) = ( dir . path ( ) . join ( " a " ) , dir . path ( ) . join ( " b " ) ) ;
File ::create ( & src ) ? ;
fs ::hard_link ( src . clone ( ) , dst . clone ( ) ) ? ;
let e1 = FileEntry { path : src , .. Default ::default ( ) } ;
let e2 = FileEntry { path : dst , .. Default ::default ( ) } ;
let actual = filter_hard_links ( & [ e1 . clone ( ) , e2 ] ) ;
assert_eq! ( vec! [ e1 ] , actual ) ;
Ok ( ( ) )
}
#[ test ]
2021-02-22 22:52:21 +13:00
fn test_filter_hard_links_regular_files ( ) -> io ::Result < ( ) > {
2021-02-21 00:28:06 +13:00
let dir = tempfile ::Builder ::new ( ) . tempdir ( ) ? ;
let ( src , dst ) = ( dir . path ( ) . join ( " a " ) , dir . path ( ) . join ( " b " ) ) ;
File ::create ( & src ) ? ;
File ::create ( & dst ) ? ;
let e1 = FileEntry { path : src , .. Default ::default ( ) } ;
let e2 = FileEntry { path : dst , .. Default ::default ( ) } ;
let actual = filter_hard_links ( & [ e1 . clone ( ) , e2 . clone ( ) ] ) ;
assert_eq! ( vec! [ e1 , e2 ] , actual ) ;
Ok ( ( ) )
}
2021-02-22 22:52:21 +13:00
#[ test ]
fn test_hash_calculation ( ) -> io ::Result < ( ) > {
let dir = tempfile ::Builder ::new ( ) . tempdir ( ) ? ;
let mut buf = [ 0 u8 ; 1 < < 10 ] ;
let src = dir . path ( ) . join ( " a " ) ;
let mut file = File ::create ( & src ) ? ;
file . write_all ( b " aa " ) ? ;
let e = FileEntry { path : src , .. Default ::default ( ) } ;
let r = hash_calculation ( & mut buf , & e , & HashType ::Blake3 , 0 ) . unwrap ( ) ;
assert_eq! ( 2 , r . 1 ) ;
assert! ( ! r . 0. is_empty ( ) ) ;
Ok ( ( ) )
}
#[ test ]
fn test_hash_calculation_limit ( ) -> io ::Result < ( ) > {
let dir = tempfile ::Builder ::new ( ) . tempdir ( ) ? ;
let mut buf = [ 0 u8 ; 1 ] ;
let src = dir . path ( ) . join ( " a " ) ;
let mut file = File ::create ( & src ) ? ;
file . write_all ( b " aa " ) ? ;
let e = FileEntry { path : src , .. Default ::default ( ) } ;
let r1 = hash_calculation ( & mut buf , & e , & HashType ::Blake3 , 1 ) . unwrap ( ) ;
let r2 = hash_calculation ( & mut buf , & e , & HashType ::Blake3 , 2 ) . unwrap ( ) ;
let r3 = hash_calculation ( & mut buf , & e , & HashType ::Blake3 , u64 ::MAX ) . unwrap ( ) ;
assert_ne! ( r1 , r2 ) ;
assert_eq! ( r2 , r3 ) ;
Ok ( ( ) )
}
#[ test ]
fn test_hash_calculation_invalid_file ( ) -> io ::Result < ( ) > {
let dir = tempfile ::Builder ::new ( ) . tempdir ( ) ? ;
let mut buf = [ 0 u8 ; 1 < < 10 ] ;
let src = dir . path ( ) . join ( " a " ) ;
let e = FileEntry { path : src , .. Default ::default ( ) } ;
let r = hash_calculation ( & mut buf , & e , & HashType ::Blake3 , 0 ) . unwrap_err ( ) ;
assert! ( ! r . is_empty ( ) ) ;
Ok ( ( ) )
}
2021-02-12 07:04:23 +13:00
}