Smaller fixes (#795)

* Improve a little documentation, add missing bad extension

* Allow to find the smallest files from CLo

* Show error when all directories are reference folders

* 2 more testing objects

* Add missing original preset

Author: qarmin

.github/workflows/mac.yml

@@ -44,7 +44,6 @@ jobs:
         run: cargo build --release --features heif
         env:
           CARGO_INCREMENTAL: 0
-          RUSTFLAGS: "-C debuginfo=0 -D warnings"
         if: ${{ matrix.type == 'release'}}
 
       - name: Store MacOS CLI

Changelog.md

@@ -1,3 +1,10 @@
+## Version 5.0.1 - .08.2022r
+- Fixed problem with removing ending slash with empty disk window path
+- Added to CLI bad extensions mode
+- Fixed default sorting method in CLI where finding biggest files 
+- Added tests to CI
+- Show error message when all directories are set as reference folders
+
 ## Version 5.0.0 - 28.07.2022r
 - GUI ported to use GTK 4 - [#466](https://github.com/qarmin/czkawka/pull/466)
 - Use multithreading and improved algorithm to compare image hashes - [#762](https://github.com/qarmin/czkawka/pull/762)

README.md

@@ -27,6 +27,13 @@
 
 ![Czkawka](https://user-images.githubusercontent.com/41945903/145280350-506f7e94-4db0-4de7-a68d-6e7c26bbd2bf.gif)
 
+## Supported OS
+Linux - Ubuntu 22.04+, Fedora 36+, Alpine Linux 3.16+, Debian 12+ and a lot of more   
+Windows - 7, 8.1, 10, 11  
+MacOS - 10.15+
+
+If you are looking for older version that use GTK 3 and have support for more OS(like e.g. Ubuntu 20.04), look at [4.1.0](https://github.com/qarmin/czkawka/releases/tag/4.1.0) or older versions.
+
 ## How do I use it?
 You can find the instructions on how to use Czkawka [**here**](instructions/Instruction.md).
 
@@ -140,6 +147,7 @@ You can help by creating:
   If the change is bigger, then it's a good idea to open a new issue to discuss changes, but issues with label `PR welcome` are already checked and accepted.
 - Documentation - There is an [instruction](instructions/Instruction.md) which you can improve.
 - Translations - Instruction how to translate files is available [here](instructions/Translations.md)
+- External contributions - App use big number of external libraries like [lofty](https://github.com/Serial-ATA/lofty-rs), [image-rs](https://github.com/image-rs/image) or [symphonia](https://github.com/pdeljanov/Symphonia) so improving this libraries will automatically improve Czkawka
 
 You can also help by doing other things:
 - Creating text articles - [LinuxUprising](https://www.linuxuprising.com/2021/03/find-and-remove-duplicate-files-similar.html) or [Ubunlog](https://ubunlog.com/en/czkawka-finds-and-removes-empty-and-broken-duplicate-files/)

czkawka_cli/src/commands.rs

@@ -36,6 +36,8 @@ pub enum Commands {
         file_to_save: FileToSave,
         #[clap(flatten)]
         not_recursive: NotRecursive,
+        #[clap(flatten)]
+        case_sensitive_name_comparison: CaseSensitiveNameComparison,
         #[cfg(target_family = "unix")]
         #[clap(flatten)]
         exclude_other_filesystems: ExcludeOtherFilesystems,
@@ -60,7 +62,7 @@ pub enum Commands {
         #[clap(flatten)]
         exclude_other_filesystems: ExcludeOtherFilesystems,
     },
-    #[clap(name = "big", about = "Finds big files", help_message = HELP_MESSAGE, after_help = "EXAMPLE:\n    czkawka big -d /home/rafal/ /home/piszczal -e /home/rafal/Roman -n 25 -x VIDEO -f results.txt")]
+    #[clap(name = "big", about = "Finds big files", help_message = HELP_MESSAGE, after_help = "EXAMPLE:\n    czkawka big -d /home/rafal/ /home/piszczal -e /home/rafal/Roman -n 25 -J -x VIDEO -f results.txt")]
     BiggestFiles {
         #[clap(flatten)]
         directories: Directories,
@@ -78,6 +80,8 @@ pub enum Commands {
         file_to_save: FileToSave,
         #[clap(flatten)]
         not_recursive: NotRecursive,
+        #[clap(short = 'J', long, help = "Finds the smallest files instead the biggest")]
+        smallest_mode: bool,
         #[cfg(target_family = "unix")]
         #[clap(flatten)]
         exclude_other_filesystems: ExcludeOtherFilesystems,
@@ -130,7 +134,7 @@ pub enum Commands {
         minimal_file_size: u64,
         #[clap(short = 'i', long, parse(try_from_str = parse_maximal_file_size), default_value = "18446744073709551615", help = "Maximum size in bytes", long_help = "Maximum size of checked files in bytes, assigning lower value may speed up searching")]
         maximal_file_size: u64,
-        #[clap(short, long, default_value = "High", parse(try_from_str = parse_similar_images_similarity), help = "Similairty level (Minimal, VerySmall, Small, Medium, High, VeryHigh)", long_help = "Methods to choose similarity level of images which will be considered as duplicated.")]
+        #[clap(short, long, default_value = "High", parse(try_from_str = parse_similar_images_similarity), help = "Similairty level (Minimal, VerySmall, Small, Medium, High, VeryHigh, Original)", long_help = "Methods to choose similarity level of images which will be considered as duplicated.")]
         similarity_preset: SimilarityPreset,
         #[clap(flatten)]
         excluded_items: ExcludedItems,
@@ -143,7 +147,7 @@ pub enum Commands {
         exclude_other_filesystems: ExcludeOtherFilesystems,
         #[clap(short = 'g', long, default_value = "Gradient", parse(try_from_str = parse_similar_hash_algorithm), help = "Hash algorithm (allowed: Mean, Gradient, Blockhash, VertGradient, DoubleGradient)")]
         hash_alg: HashAlg,
-        #[clap(short = 'z', long, default_value = "Lanczos3", parse(try_from_str = parse_similar_image_filter), help = "Hash algorithm (allowed: Lanczos3, Nearest, Triangle, Faussian, Catmullrom)")]
+        #[clap(short = 'z', long, default_value = "Nearest", parse(try_from_str = parse_similar_image_filter), help = "Hash algorithm (allowed: Lanczos3, Nearest, Triangle, Faussian, Catmullrom)")]
         image_filter: FilterType,
         #[clap(short = 'c', long, default_value = "16", parse(try_from_str = parse_image_hash_size), help = "Hash size (allowed: 8, 16, 32, 64)")]
         hash_size: u8,
@@ -238,11 +242,26 @@ pub enum Commands {
         #[clap(short = 't', long, parse(try_from_str = parse_tolerance), default_value = "10", help = "Video maximium difference (allowed values <0,20>)", long_help = "Maximum difference between video frames, bigger value means that videos can looks more and more different (allowed values <0,20>)")]
         tolerance: i32,
     },
-    #[clap(name = "tester", about = "Contains various test", help_message = HELP_MESSAGE, after_help = "EXAMPLE:\n    czkawka tests -i")]
-    Tester {
-        #[clap(short = 'i', long = "test_image", help = "Test speed of hashing provided test.jpg image with different filters and methods.")]
-        test_image: bool,
+    #[clap(name = "ext", about = "Finds files with invalid extensions", help_message = HELP_MESSAGE, after_help = "EXAMPLE:\n    czkawka broken -d /home/czokolada/ -f results.txt")]
+    BadExtensions {
+        #[clap(flatten)]
+        directories: Directories,
+        #[clap(flatten)]
+        excluded_directories: ExcludedDirectories,
+        #[clap(flatten)]
+        excluded_items: ExcludedItems,
+        #[clap(flatten)]
+        allowed_extensions: AllowedExtensions,
+        #[clap(flatten)]
+        file_to_save: FileToSave,
+        #[clap(flatten)]
+        not_recursive: NotRecursive,
+        #[cfg(target_family = "unix")]
+        #[clap(flatten)]
+        exclude_other_filesystems: ExcludeOtherFilesystems,
     },
+    #[clap(name = "tester", about = "Small utility to test supported speed of ", help_message = HELP_MESSAGE, after_help = "EXAMPLE:\n    czkawka tester")]
+    Tester {},
 }
 
 #[derive(Debug, clap::StructOpt)]
@@ -317,6 +336,12 @@ pub struct AllowHardLinks {
     pub allow_hard_links: bool,
 }
 
+#[derive(Debug, clap::StructOpt)]
+pub struct CaseSensitiveNameComparison {
+    #[clap(short = 'l', long, help = "Use case sensitive name comparison")]
+    pub case_sensitive_name_comparison: bool,
+}
+
 #[derive(Debug, clap::StructOpt)]
 pub struct DryRun {
     #[clap(long, help = "Do nothing and print the operation that would happen.")]

czkawka_cli/src/main.rs

@@ -5,17 +5,18 @@ use std::process;
 use clap::Parser;
 
 use commands::Commands;
+use czkawka_core::big_file::SearchMode;
 #[allow(unused_imports)] // It is used in release for print_results().
 use czkawka_core::common_traits::*;
 use czkawka_core::similar_images::test_image_conversion_speed;
 use czkawka_core::{
+    bad_extensions::BadExtensions,
     big_file::{self, BigFile},
     broken_files::{self, BrokenFiles},
     duplicate::DuplicateFinder,
     empty_files::{self, EmptyFiles},
     empty_folder::EmptyFolder,
-    invalid_symlinks,
-    invalid_symlinks::InvalidSymlinks,
+    invalid_symlinks::{self, InvalidSymlinks},
     same_music::SameMusic,
     similar_images::{return_similarity_from_similarity_preset, SimilarImages},
     similar_videos::SimilarVideos,
@@ -49,6 +50,7 @@ fn main() {
             exclude_other_filesystems,
             allow_hard_links,
             dryrun,
+            case_sensitive_name_comparison,
         } => {
             let mut df = DuplicateFinder::new();
 
@@ -67,6 +69,7 @@ fn main() {
             df.set_exclude_other_filesystems(exclude_other_filesystems.exclude_other_filesystems);
             df.set_ignore_hard_links(!allow_hard_links.allow_hard_links);
             df.set_dryrun(dryrun.dryrun);
+            df.set_case_sensitive_name_comparison(case_sensitive_name_comparison.case_sensitive_name_comparison);
 
             df.find_duplicates(None, None);
 
@@ -123,6 +126,7 @@ fn main() {
             #[cfg(target_family = "unix")]
             exclude_other_filesystems,
             delete_files,
+            smallest_mode,
         } => {
             let mut bf = BigFile::new();
 
@@ -137,6 +141,9 @@ fn main() {
             if delete_files {
                 bf.set_delete_method(big_file::DeleteMethod::Delete);
             }
+            if smallest_mode {
+                bf.set_search_mode(SearchMode::SmallestFiles);
+            }
 
             bf.find_big_files(None, None);
 
@@ -425,12 +432,41 @@ fn main() {
             vr.print_results();
             vr.get_text_messages().print_messages();
         }
-        Commands::Tester { test_image } => {
-            if test_image {
-                test_image_conversion_speed();
-            } else {
-                println!("At least one test should be choosen!");
+        Commands::BadExtensions {
+            directories,
+            excluded_directories,
+            excluded_items,
+            file_to_save,
+            not_recursive,
+            #[cfg(target_family = "unix")]
+            exclude_other_filesystems,
+            allowed_extensions,
+        } => {
+            let mut be = BadExtensions::new();
+
+            be.set_included_directory(directories.directories);
+            be.set_excluded_directory(excluded_directories.excluded_directories);
+            be.set_excluded_items(excluded_items.excluded_items);
+            be.set_allowed_extensions(allowed_extensions.allowed_extensions.join(","));
+            be.set_recursive_search(!not_recursive.not_recursive);
+            #[cfg(target_family = "unix")]
+            be.set_exclude_other_filesystems(exclude_other_filesystems.exclude_other_filesystems);
+
+            if let Some(file_name) = file_to_save.file_name() {
+                if !be.save_results_to_file(file_name) {
+                    be.get_text_messages().print_messages();
+                    process::exit(1);
+                }
             }
+
+            be.find_bad_extensions_files(None, None);
+
+            #[cfg(not(debug_assertions))] // This will show too much probably unnecessary data to debug, comment line only if needed
+            be.print_results();
+            be.get_text_messages().print_messages();
+        }
+        Commands::Tester {} => {
+            test_image_conversion_speed();
         }
     }
 }

czkawka_core/src/bad_extensions.rs

@@ -469,7 +469,7 @@ impl BadExtensions {
 
         self.information.number_of_files_with_bad_extension = self.bad_extensions_files.len();
 
-        Common::print_time(system_time, SystemTime::now(), "sort_images - reading data from files in parallel".to_string());
+        Common::print_time(system_time, SystemTime::now(), "bad extension finding".to_string());
 
         // Clean unused data
         self.files_to_check = Default::default();
@@ -539,7 +539,7 @@ impl SaveResults for BadExtensions {
         if !self.bad_extensions_files.is_empty() {
             writeln!(writer, "Found {} files with invalid extension.", self.information.number_of_files_with_bad_extension).unwrap();
             for file_entry in self.bad_extensions_files.iter() {
-                writeln!(writer, "{}", file_entry.path.display()).unwrap();
+                writeln!(writer, "{} ----- {}", file_entry.path.display(), file_entry.proper_extensions).unwrap();
             }
         } else {
             write!(writer, "Not found any files with invalid extension.").unwrap();
@@ -556,7 +556,7 @@ impl PrintResults for BadExtensions {
         let start_time: SystemTime = SystemTime::now();
         println!("Found {} files with invalid extension.\n", self.information.number_of_files_with_bad_extension);
         for file_entry in self.bad_extensions_files.iter() {
-            println!("{}", file_entry.path.display());
+            println!("{} ----- {}", file_entry.path.display(), file_entry.proper_extensions);
         }
 
         Common::print_time(start_time, SystemTime::now(), "print_entries".to_string());

czkawka_core/src/big_file.rs

@@ -464,9 +464,12 @@ impl SaveResults for BigFile {
         }
 
         if self.information.number_of_real_files != 0 {
-            write!(writer, "{} the biggest files.\n\n", self.information.number_of_real_files).unwrap();
-
-            for (size, file_entry) in self.big_files.iter().rev() {
+            if self.search_mode == SearchMode::BiggestFiles {
+                write!(writer, "{} the biggest files.\n\n", self.information.number_of_real_files).unwrap();
+            } else {
+                write!(writer, "{} the smallest files.\n\n", self.information.number_of_real_files).unwrap();
+            }
+            for (size, file_entry) in self.big_files.iter() {
                 writeln!(writer, "{} ({}) - {}", size.file_size(options::BINARY).unwrap(), size, file_entry.path.display()).unwrap();
             }
         } else {
@@ -480,9 +483,13 @@ impl SaveResults for BigFile {
 impl PrintResults for BigFile {
     fn print_results(&self) {
         let start_time: SystemTime = SystemTime::now();
-        for (size, file_entry) in self.big_files.iter().rev() {
-            // TODO Align all to same width
-            println!("{} ({} bytes) - {}", size.file_size(options::BINARY).unwrap(), size, file_entry.path.display());
+        if self.search_mode == SearchMode::BiggestFiles {
+            println!("{} the biggest files.\n\n", self.information.number_of_real_files);
+        } else {
+            println!("{} the smallest files.\n\n", self.information.number_of_real_files);
+        }
+        for (size, file_entry) in self.big_files.iter() {
+            println!("{} ({}) - {}", size.file_size(options::BINARY).unwrap(), size, file_entry.path.display());
         }
         Common::print_time(start_time, SystemTime::now(), "print_entries".to_string());
     }

czkawka_core/src/similar_images.rs

@@ -32,7 +32,7 @@ use crate::flc;
 use crate::localizer_core::generate_translation_hashmap;
 
 pub const SIMILAR_VALUES: [[u32; 6]; 4] = [
-    [0, 2, 5, 7, 14, 20],    // 8
+    [1, 2, 5, 7, 14, 20],    // 8
     [2, 5, 15, 30, 40, 40],  // 16
     [4, 10, 20, 40, 40, 40], // 32
     [6, 20, 40, 40, 40, 40], // 64
@@ -59,6 +59,7 @@ pub struct FileEntry {
 /// Used by CLI tool when we cannot use directly values
 #[derive(Clone, Debug)]
 pub enum SimilarityPreset {
+    Original,
     VeryHigh,
     High,
     Medium,
@@ -1283,6 +1284,7 @@ pub fn return_similarity_from_similarity_preset(similarity_preset: &SimilarityPr
         _ => panic!(),
     };
     match similarity_preset {
+        SimilarityPreset::Original => 0,
         SimilarityPreset::VeryHigh => SIMILAR_VALUES[index_preset][0],
         SimilarityPreset::High => SIMILAR_VALUES[index_preset][1],
         SimilarityPreset::Medium => SIMILAR_VALUES[index_preset][2],

czkawka_gui/i18n/en/czkawka_gui.ftl

@@ -463,6 +463,7 @@ invalid_symlink_infinite_recursion = Infinite recursion
 invalid_symlink_non_existent_destination = Non-existent destination file
 
 # Other
+selected_all_reference_folders = Cannot start search, when all directories are set as reference folders
 searching_for_data = Searching data, it may take a while, please wait...
 text_view_messages = MESSAGES
 text_view_warnings = WARNINGS

czkawka_gui/src/connect_things/connect_button_search.rs

@@ -117,6 +117,13 @@ pub fn connect_button_search(
     let check_button_settings_save_also_json = gui_data.settings.check_button_settings_save_also_json.clone();
 
     buttons_search_clone.connect_clicked(move |_| {
+        // Check if user selected all referenced folders
+        let list_store_included_directories = get_list_store(&tree_view_included_directories);
+        if check_if_list_store_column_have_all_same_values(&list_store_included_directories, ColumnsIncludedDirectory::ReferenceButton as i32, true) {
+            entry_info.set_text(&flg!("selected_all_reference_folders"));
+            return;
+        }
+
         let included_directories = get_path_buf_from_vector_of_strings(get_string_from_list_store(&tree_view_included_directories, ColumnsIncludedDirectory::Path as i32, None));
         let excluded_directories = get_path_buf_from_vector_of_strings(get_string_from_list_store(&tree_view_excluded_directories, ColumnsExcludedDirectory::Path as i32, None));
         let reference_directories = get_path_buf_from_vector_of_strings(get_string_from_list_store(

czkawka_gui/src/connect_things/connect_selection_of_directories.rs

@@ -184,6 +184,7 @@ fn add_manually_directories(window_main: &Window, tree_view: &TreeView, excluded
         dialog.close();
     });
 }
+
 fn remove_ending_slashes(original_string: &mut String) {
     let mut windows_disk_path: bool = false;
     let mut chars = original_string.chars();
@@ -202,6 +203,7 @@ fn remove_ending_slashes(original_string: &mut String) {
         original_string.pop();
     }
 }
+
 #[test]
 pub fn test_remove_ending_slashes() {
     let mut original = "/home/rafal".to_string();
@@ -248,6 +250,14 @@ pub fn test_remove_ending_slashes() {
     remove_ending_slashes(&mut original);
     assert_eq!(&original, "C:/");
 
+    let mut original = "C:/roman/function/".to_string();
+    remove_ending_slashes(&mut original);
+    assert_eq!(&original, "C:/roman/function");
+
+    let mut original = "C:/staszek/without".to_string();
+    remove_ending_slashes(&mut original);
+    assert_eq!(&original, "C:/staszek/without");
+
     let mut original = "C:\\\\\\\\\\".to_string();
     remove_ending_slashes(&mut original);
     assert_eq!(&original, "C:\\");