From 2cfb298468ca91036ce1dd3a72bcc9be619902b9 Mon Sep 17 00:00:00 2001
From: sreedev <sreedevpadmakumar@gmail.com>
Date: Fri, 30 Dec 2022 00:25:07 -0500
Subject: [PATCH] faster hashing algorithm

---
 Cargo.lock      | 16 ++++++++++++++++
 Cargo.toml      |  2 +-
 src/database.rs |  1 +
 src/output.rs   |  2 +-
 src/scanner.rs  |  2 +-
 5 files changed, 20 insertions(+), 3 deletions(-)

diff --git a/Cargo.lock b/Cargo.lock
index d84c0e6..4574b86 100644
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -46,6 +46,12 @@ version = "3.11.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "572f695136211188308f16ad2ca5c851a712c464060ae6974944458eb83880ba"
 
+[[package]]
+name = "byteorder"
+version = "1.4.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "14c189c53d098945499cdfa7ecc63567cf3886b3332b312a5b4585d8d3a6a610"
+
 [[package]]
 name = "bytes"
 version = "1.3.0"
@@ -238,6 +244,7 @@ dependencies = [
  "chrono",
  "clap",
  "colored",
+ "fxhash",
  "glob",
  "humansize",
  "itertools",
@@ -275,6 +282,15 @@ dependencies = [
  "libc",
 ]
 
+[[package]]
+name = "fxhash"
+version = "0.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c31b6d751ae2c7f11320402d34e41349dd1016f8d5d45e48c4312bc8625af50c"
+dependencies = [
+ "byteorder",
+]
+
 [[package]]
 name = "glob"
 version = "0.3.0"
diff --git a/Cargo.toml b/Cargo.toml
index d047305..87cad63 100644
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -10,6 +10,7 @@ anyhow = "1.0.68"
 chrono = "0.4.23"
 clap = { version = "4.0.32", features = ["derive"] }
 colored = "2.0.0"
+fxhash = "0.2.1"
 glob = "0.3.0"
 humansize = "2.1.2"
 itertools = "0.10.5"
@@ -17,4 +18,3 @@ rayon = "1.6.1"
 sqlite = "0.30.3"
 thiserror = "1.0.38"
 tokio = { version = "1.23.0", features = ["full"] }
-xxhash-rust = { version = "0.8.6", features = ["xxh3"] }
diff --git a/src/database.rs b/src/database.rs
index 147d997..2ecd934 100644
--- a/src/database.rs
+++ b/src/database.rs
@@ -67,6 +67,7 @@ pub fn duplicate_hashes(connection: &sqlite::Connection, path: &String) -> Resul
             ORDER BY a.file_identifier
         ", path
     );
+
     let result: Vec<File> = connection
         .prepare(query)?
         .into_iter()
diff --git a/src/output.rs b/src/output.rs
index 4cd267a..3e933bf 100644
--- a/src/output.rs
+++ b/src/output.rs
@@ -48,7 +48,7 @@ pub fn print(duplicates: Vec<File>) {
         group.into_iter().for_each(|file| {
             println!(
                 "| {0: <16} | {1: <35} | {2: <16} | {3: <32} |",
-                &file.hash[0..16].red(),
+                file.hash.red(),
                 format_path(&file.path).yellow(),
                 file_size(&file.path).blue(),
                 modified_time(&file.path).blue()
diff --git a/src/scanner.rs b/src/scanner.rs
index 977b302..d77dfeb 100644
--- a/src/scanner.rs
+++ b/src/scanner.rs
@@ -6,7 +6,7 @@ use itertools::Itertools;
 use rayon::prelude::*;
 use std::fs;
 use std::path::PathBuf;
-use xxhash_rust::xxh3::xxh3_64 as hasher;
+use fxhash::hash32 as hasher;
 
 pub fn duplicates(app_opts: &App, connection: &sqlite::Connection) -> Result<Vec<File>> {
     let scan_results = scan(app_opts, connection)?;