13 Commits
0.0.3 ... 0.0.4

Author SHA1 Message Date
sreedev
e158a8267a added authors & updated version 2023-01-08 17:16:46 -05:00
Sreedev Kodichath
e6f93ce3d6 Merge pull request #9 from beeb/scanner
Refactor scanner
2023-01-08 17:11:36 -05:00
Sreedev Kodichath
011da05c59 Merge pull request #10 from beeb/output
Refactor output.rs
2023-01-08 17:11:04 -05:00
beeb
6087abe960 refactor: no need for into_iter 2023-01-08 13:24:08 +01:00
beeb
5eba7cdc30 fix: still print items even if file size or modified time cannot be retrieved 2023-01-08 13:21:47 +01:00
beeb
5a65550e58 refactor: output.rs 2023-01-08 13:20:15 +01:00
beeb
0b5effd06e refactor: no need to consume pathbuf iterator 2023-01-08 13:09:43 +01:00
beeb
cc243f413a refactor: no need to consume iterator items 2023-01-08 13:08:27 +01:00
beeb
ad467d70a8 style: combine use statements for std 2023-01-08 12:20:27 +01:00
beeb
4490ea4c69 style: combine use statements for database 2023-01-08 12:19:56 +01:00
beeb
8ed0b13ff0 style: order imports 2023-01-08 12:19:25 +01:00
beeb
be7e8d38ae refactor: avoid unwraps 2023-01-08 11:48:49 +01:00
beeb
c9694dea09 fix: clippy warnings 2023-01-08 11:22:43 +01:00
4 changed files with 60 additions and 48 deletions

2
Cargo.lock generated
View File

@@ -269,7 +269,7 @@ dependencies = [
[[package]]
name = "deduplicator"
version = "0.0.3"
version = "0.0.4"
dependencies = [
"anyhow",
"chrono",

View File

@@ -1,9 +1,10 @@
[package]
name = "deduplicator"
version = "0.0.3"
version = "0.0.4"
edition = "2021"
description = "find,filter,delete Duplicates"
license = "MIT"
authors = ["Sreedev Kodichath <sreedevpadmakumar@gmail.com>", "Valentin Bersier <vbersier@gmail.com>"]
# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html

View File

@@ -1,35 +1,40 @@
use crate::database::File;
use std::{collections::HashMap, fs};
use anyhow::Result;
use chrono::offset::Utc;
use chrono::DateTime;
use colored::Colorize;
use humansize::{format_size, DECIMAL};
use std::{collections::HashMap, fs};
use crate::database::File;
use crate::params::Params;
fn format_path(path: &String, opts: &Params) -> String {
let display_path = path.replace(&opts.get_directory().unwrap(), "");
fn format_path(path: &str, opts: &Params) -> Result<String> {
let display_path = path.replace(&opts.get_directory()?, "");
let text_vec = display_path.chars().collect::<Vec<_>>();
let display_range = if text_vec.len() > 32 {
text_vec[(display_path.len() - 32)..].into_iter().collect::<String>()
text_vec[(display_path.len() - 32)..]
.iter()
.collect::<String>()
} else {
display_path
};
format!("...{}", display_range)
Ok(format!("...{}", display_range))
}
fn file_size(path: &String) -> String {
let mdata = fs::metadata(path).unwrap();
fn file_size(path: &String) -> Result<String> {
let mdata = fs::metadata(path)?;
let formatted_size = format_size(mdata.len(), DECIMAL);
format!("{}", formatted_size)
Ok(formatted_size)
}
fn modified_time(path: &String) -> String {
let mdata = fs::metadata(path).unwrap();
let modified_time: DateTime<Utc> = mdata.modified().unwrap().into();
fn modified_time(path: &String) -> Result<String> {
let mdata = fs::metadata(path)?;
let modified_time: DateTime<Utc> = mdata.modified()?.into();
modified_time.format("%Y-%m-%d %H:%M:%S").to_string()
Ok(modified_time.format("%Y-%m-%d %H:%M:%S").to_string())
}
fn print_divider() {
@@ -50,17 +55,17 @@ pub fn print(duplicates: Vec<File>, opts: &Params) {
dup_index
.entry(file.hash.clone())
.and_modify(|value| value.push(file.clone()))
.or_insert(vec![file]);
.or_insert_with(|| vec![file]);
});
dup_index.into_iter().for_each(|(_, group)| {
group.into_iter().for_each(|file| {
dup_index.iter().for_each(|(_, group)| {
group.iter().for_each(|file| {
println!(
"| {0: <16} | {1: <35} | {2: <16} | {3: <32} |",
file.hash.red(),
format_path(&file.path, opts).yellow(),
file_size(&file.path).blue(),
modified_time(&file.path).blue()
format_path(&file.path, opts).unwrap_or_default().yellow(),
file_size(&file.path).unwrap_or_default().blue(),
modified_time(&file.path).unwrap_or_default().blue()
);
});
print_divider();

View File

@@ -1,55 +1,61 @@
use crate::database;
use crate::{params::Params, database::File};
use std::{fs, path::PathBuf};
use anyhow::Result;
use fxhash::hash32 as hasher;
use glob::glob;
use itertools::Itertools;
use rayon::prelude::*;
use std::fs;
use std::path::PathBuf;
use fxhash::hash32 as hasher;
use crate::{
database::{self, File},
params::Params,
};
pub fn duplicates(app_opts: &Params, connection: &sqlite::Connection) -> Result<Vec<File>> {
let scan_results = scan(app_opts, connection)?;
let base_path = app_opts.get_directory()?;
index_files(scan_results, connection);
index_files(scan_results, connection)?;
database::duplicate_hashes(connection, &base_path)
}
fn get_glob_patterns(opts: &Params, directory: &String) -> Vec<PathBuf> {
fn get_glob_patterns(opts: &Params, directory: &str) -> Vec<PathBuf> {
opts.types
.clone()
.unwrap_or(String::from("*"))
.split(",")
.unwrap_or_else(|| String::from("*"))
.split(',')
.map(|filetype| format!("*.{}", filetype))
.map(|filetype| {
vec![directory.clone(), String::from("**"), filetype]
vec![directory.to_owned(), String::from("**"), filetype]
.iter()
.collect()
})
.collect()
}
fn is_indexed_file(path: &String, indexed: &Vec<File>) -> bool {
fn is_indexed_file(path: impl Into<String>, indexed: &[File]) -> bool {
indexed
.into_iter()
.iter()
.map(|file| file.path.clone())
.contains(path)
.contains(&path.into())
}
fn scan(app_opts: &Params, connection: &sqlite::Connection) -> Result<Vec<String>> {
let directory = app_opts.get_directory()?;
let glob_patterns: Vec<PathBuf> = get_glob_patterns(&app_opts, &directory);
let glob_patterns: Vec<PathBuf> = get_glob_patterns(app_opts, &directory);
let indexed_paths = database::indexed_paths(connection)?;
let files: Vec<String> = glob_patterns
.into_par_iter()
.map(|glob_pattern| glob(&glob_pattern.as_os_str().to_str().unwrap()))
.map(|glob_result| glob_result.unwrap())
.par_iter()
.filter_map(|glob_pattern| glob(glob_pattern.as_os_str().to_str()?).ok())
.flat_map(|file_vec| {
file_vec
.map(|x| x.unwrap().as_os_str().to_str().unwrap().to_string())
.filter_map(|x| Some(x.ok()?.as_os_str().to_str()?.to_string()))
.filter(|fpath| !is_indexed_file(fpath, &indexed_paths))
.filter(|glob_result| fs::metadata(glob_result).unwrap().is_file())
.filter(|glob_result| {
fs::metadata(glob_result)
.map(|f| f.is_file())
.unwrap_or(false)
})
.collect::<Vec<String>>()
})
.collect();
@@ -57,18 +63,18 @@ fn scan(app_opts: &Params, connection: &sqlite::Connection) -> Result<Vec<String
Ok(files)
}
fn index_files(files: Vec<String>, connection: &sqlite::Connection) {
fn index_files(files: Vec<String>, connection: &sqlite::Connection) -> Result<()> {
let hashed: Vec<File> = files
.into_par_iter()
.map(|file| {
let hash = hash_file(&file).unwrap();
database::File { path: file, hash }
.filter_map(|file| {
let hash = hash_file(&file).ok()?;
Some(database::File { path: file, hash })
})
.collect();
hashed.into_iter().for_each(|file| {
database::put(&file, connection).unwrap();
});
hashed
.iter()
.try_for_each(|file| database::put(file, connection))
}
pub fn hash_file(filepath: &str) -> Result<String> {