Merge pull request #47 from sreedevk/development

Version 0.1.5

Cargo.lock

@@ -324,7 +324,7 @@ dependencies = [
 
 [[package]]
 name = "deduplicator"
-version = "0.1.4"
+version = "0.1.5"
 dependencies = [
  "anyhow",
  "bytesize",

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "deduplicator"
-version = "0.1.4"
+version = "0.1.5"
 edition = "2021"
 description = "find,filter,delete Duplicates"
 license = "MIT"

README.md

@@ -7,15 +7,38 @@
 ## Usage
 
 ```bash
-Usage: deduplicator [OPTIONS]
+Usage: deduplicator [OPTIONS] [scan_dir_path]
+
+Arguments:
+  [scan_dir_path]  Run Deduplicator on dir different from pwd (e.g., ~/Pictures )
 
 Options:
-  -t, --types <TYPES>      Filetypes to deduplicate (default = all)
-      --dir <DIR>          Run Deduplicator on dir different from pwd
-  -i, --interactive        Delete files interactively
-  -m, --minsize <MINSIZE>  Minimum filesize of duplicates to scan (e.g., 100B/1K/2M/3G/4T). [default = 0]
-  -h, --help               Print help information
-  -V, --version            Print version information
+  -t, --types <TYPES>          Filetypes to deduplicate [default = all]
+  -i, --interactive            Delete files interactively
+  -s, --min-size <MIN_SIZE>    Minimum filesize of duplicates to scan (e.g., 100B/1K/2M/3G/4T) [default: 1b]
+  -d, --max-depth <MAX_DEPTH>  Max Depth to scan while looking for duplicates
+      --min-depth <MIN_DEPTH>  Min Depth to scan while looking for duplicates
+  -f, --follow-links           Follow links while scanning directories
+  -h, --help                   Print help information
+  -V, --version                Print version information
+```
+### Examples
+
+```bash
+# Scan for duplicates recursively from the current dir, only look for png, jpg & pdf file types & interactively delete files
+deduplicator -t pdf,jpg,png -i
+
+# Scan for duplicates recursively from the ~/Pictures dir, only look for png, jpeg, jpg & pdf file types & interactively delete files
+deduplicator ~/Pictures/ -t png,jpeg,jpg,pdf -i
+
+# Scan for duplicates in the ~/Pictures without recursing into subdirectories
+deduplicator ~/Pictures --max-depth 0
+
+# look for duplicates in the ~/.config directory while also recursing into symbolic link paths
+deduplicator ~/.config --follow-links
+
+# scan for duplicates that are greater than 100mb in the ~/Media directory
+deduplicator ~/Media --min-size 100mb
 ```
 
 ## Installation
@@ -75,7 +98,7 @@ Deduplicator uses size comparison and fxhash (a non non-cryptographic hashing al
 |:---|:---|---:|---:|---:|---:|
 | `deduplicator --dir ~/Data/tmp` | (~120G) | 27.5 ± 1.0 | 26.0 | 32.1 | 1.70 ± 0.09 |
 | `deduplicator --dir ~/Data/books` | (~8.6G) | 21.8 ± 0.7 | 20.5 | 24.4 | 1.35 ± 0.07 |
-| `deduplicator --dir ~/Data/books --minsize 10M` | (~8.6G) | 16.1 ± 0.6 | 14.9 | 18.8 | 1.00 |
+| `deduplicator --dir ~/Data/books --min-size 10M` | (~8.6G) | 16.1 ± 0.6 | 14.9 | 18.8 | 1.00 |
 | `deduplicator --dir ~/Data/ --types pdf,jpg,png,jpeg` | (~290G) | 1857.4 ± 24.5 | 1817.0 | 1895.5 | 115.07 ± 4.64 |
 
 * The last entry is lower because of the number of files deduplicator had to go through (~660895 Files). The average size of the files rarely affect the performance of deduplicator.

src/filters.rs

@@ -1,8 +1,8 @@
 use crate::file_manager::File;
 use crate::params::Params;
 
-pub fn is_file_gt_minsize(app_opts: &Params, file: &File) -> bool {
-    match app_opts.get_minsize() {
+pub fn is_file_gt_min_size(app_opts: &Params, file: &File) -> bool {
+    match app_opts.get_min_size() {
         Some(msize) => match file.size {
             Some(fsize) => fsize >= msize,
             None => true,

src/params.rs

@@ -7,23 +7,32 @@ use globwalk::{GlobWalker, GlobWalkerBuilder};
 #[derive(Parser, Debug)]
 #[command(author, version, about, long_about = None)]
 pub struct Params {
-    /// Filetypes to deduplicate (default = all)
+    /// Filetypes to deduplicate [default = all]
     #[arg(short, long)]
     pub types: Option<String>,
-    /// Run Deduplicator on dir different from pwd
-    #[arg(long, value_hint = ValueHint::DirPath)]
+    /// Run Deduplicator on dir different from pwd (e.g., ~/Pictures )
+    #[arg(value_hint = ValueHint::DirPath, value_name = "scan_dir_path")]
     pub dir: Option<PathBuf>,
     /// Delete files interactively
     #[arg(long, short)]
     pub interactive: bool,
-    /// Minimum filesize of duplicates to scan (e.g., 100B/1K/2M/3G/4T). [default = 0]
+    /// Minimum filesize of duplicates to scan (e.g., 100B/1K/2M/3G/4T).
+    #[arg(long, short = 's', default_value = "1b")]
+    pub min_size: Option<String>,
+    /// Max Depth to scan while looking for duplicates
+    #[arg(long, short = 'd')]
+    pub max_depth: Option<usize>,
+    /// Min Depth to scan while looking for duplicates
+    #[arg(long)]
+    pub min_depth: Option<usize>,
+    /// Follow links while scanning directories
     #[arg(long, short)]
-    pub minsize: Option<String>,
+    pub follow_links: bool,
 }
 
 impl Params {
-    pub fn get_minsize(&self) -> Option<u64> {
-        match &self.minsize {
+    pub fn get_min_size(&self) -> Option<u64> {
+        match &self.min_size {
             Some(msize) => match msize.parse::<bytesize::ByteSize>() {
                 Ok(units) => Some(units.0),
                 Err(_) => None,
@@ -39,14 +48,41 @@ impl Params {
         Ok(dir)
     }
 
+    fn add_glob_min_depth(&self, builder: GlobWalkerBuilder) -> Result<GlobWalkerBuilder> {
+        match self.min_depth {
+            Some(mindepth) => Ok(builder.min_depth(mindepth)),
+            None => Ok(builder),
+        }
+    }
+
+    fn add_glob_max_depth(&self, builder: GlobWalkerBuilder) -> Result<GlobWalkerBuilder> {
+        match self.max_depth {
+            Some(maxdepth) => Ok(builder.max_depth(maxdepth)),
+            None => Ok(builder),
+        }
+    }
+
+    fn add_glob_follow_links(&self, builder: GlobWalkerBuilder) -> Result<GlobWalkerBuilder> {
+        match self.follow_links {
+            true => Ok(builder.follow_links(true)),
+            false => Ok(builder.follow_links(false)),
+        }
+    }
+
     pub fn get_glob_walker(&self) -> Result<GlobWalker> {
         let pattern: String = match self.types.as_ref() {
             Some(filetypes) => format!("**/*{{{filetypes}}}"),
             None => "**/*".to_string(),
         };
-        // TODO: add params for maximum depth and following symlinks, then pass them to this builder
-        GlobWalkerBuilder::from_patterns(self.get_directory()?, &[pattern])
-            .build()
-            .map_err(|e| anyhow!(e))
+
+        let glob_walker_builder = self
+            .add_glob_min_depth(GlobWalkerBuilder::from_patterns(
+                self.get_directory()?,
+                &[pattern],
+            ))
+            .and_then(|builder| self.add_glob_max_depth(builder))
+            .and_then(|builder| self.add_glob_follow_links(builder))?;
+
+        glob_walker_builder.build().map_err(|e| anyhow!(e))
     }
 }

src/scanner.rs

@@ -63,7 +63,7 @@ fn scan(app_opts: &Params) -> Result<Vec<File>> {
             hash: None,
             size: Some(fs::metadata(fpath).unwrap().len()),
         })
-        .filter(|file| filters::is_file_gt_minsize(app_opts, file))
+        .filter(|file| filters::is_file_gt_min_size(app_opts, file))
         .collect();
 
     Ok(files)