From 130a8f99ba4d45fe25cefbda58eeafd49b02e7a6 Mon Sep 17 00:00:00 2001
From: sreedevk <sreedev@icloud.com>
Date: Fri, 18 Jul 2025 11:25:37 +0000
Subject: [PATCH] partial hash page count increased

---
 Cargo.lock       |  2 +-
 README.md        |  2 ++
 src/fileinfo.rs  |  4 ++--
 src/processor.rs | 10 +++++-----
 4 files changed, 10 insertions(+), 8 deletions(-)

diff --git a/Cargo.lock b/Cargo.lock
index c7a2c07..6b1d6dd 100644
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -274,7 +274,7 @@ dependencies = [
 
 [[package]]
 name = "deduplicator"
-version = "0.3.0"
+version = "0.3.1"
 dependencies = [
  "anyhow",
  "bytesize",
diff --git a/README.md b/README.md
index 6e481b2..343848a 100644
--- a/README.md
+++ b/README.md
@@ -168,6 +168,8 @@ dust 'bench_artifacts'
 ## v0.3.1
 - [x] parallelization
     - [x] (scanning + processing sw + processing hw) & formatting & printing
+- [ ] remove formatting step and write directly to stdout (tree mode)
+- [x] Increase the number of pages hashed in partial hashing
 
 ## v0.3.0
 - [x] parallelization
diff --git a/src/fileinfo.rs b/src/fileinfo.rs
index d82fa9c..f13191f 100644
--- a/src/fileinfo.rs
+++ b/src/fileinfo.rs
@@ -33,9 +33,9 @@ impl FileInfo {
             .fold(0u128, |acc, chunk: &[u8]| acc ^ gxhash128(chunk, seed)))
     }
 
-    pub fn initpage_hash(&self, seed: i64) -> Result<u128> {
+    pub fn initpages_hash(&self, seed: i64) -> Result<u128> {
         let mut file = fs::File::open(&self.path)?;
-        let mut buffer = [0; 4096];
+        let mut buffer = [0; 16384];
         let bytes_read = file.read(&mut buffer)?;
 
         Ok(gxhash128(&buffer[..bytes_read], seed))
diff --git a/src/processor.rs b/src/processor.rs
index 88ac3f2..533cda8 100644
--- a/src/processor.rs
+++ b/src/processor.rs
@@ -59,7 +59,7 @@ impl Processor {
 
                             let fhash = match app_args.strict {
                                 true => file.hash(seed).expect("hashing file failed."),
-                                false => file.initpage_hash(seed).expect("hashing file failed."),
+                                false => file.initpages_hash(seed).expect("hashing file failed."),
                             };
 
                             Self::compare_and_update_max_path_len(
@@ -153,9 +153,9 @@ mod tests {
     }
 
     #[test]
-    fn hashwise_sorting_two_files_with_identical_init_page_only_strict_mode() -> Result<()> {
+    fn hashwise_sorting_two_files_with_identical_init_pages_only_strict_mode() -> Result<()> {
         let root = TempDir::new()?;
-        let content = generate_bytes(4096);
+        let content = generate_bytes(16384);
 
         let mut content_x = content.clone();
         let mut content_y = content.clone();
@@ -211,9 +211,9 @@ mod tests {
     }
 
     #[test]
-    fn hashwise_sorting_two_files_with_identical_init_page_only_fast_mode() -> Result<()> {
+    fn hashwise_sorting_two_files_with_identical_init_pages_only_fast_mode() -> Result<()> {
         let root = TempDir::new()?;
-        let content = generate_bytes(4096);
+        let content = generate_bytes(16384);
 
         let mut content_x = content.clone();
         let mut content_y = content.clone();