initial commit

2025-10-16 16:49:46 +03:00
commit cb51d16e0f
7 changed files with 589 additions and 0 deletions
--- a/.gitignore
+++ b/.gitignore
@@ -0,0 +1,3 @@
+.idea/
+target/
+test/
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -0,0 +1,336 @@
+# This file is automatically @generated by Cargo.
+# It is not intended for manual editing.
+version = 4
+
+[[package]]
+name = "async-compression"
+version = "0.4.32"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5a89bce6054c720275ac2432fbba080a66a2106a44a1b804553930ca6909f4e0"
+dependencies = [
+ "compression-codecs",
+ "compression-core",
+ "futures-core",
+ "pin-project-lite",
+]
+
+[[package]]
+name = "cc"
+version = "1.2.41"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ac9fe6cdbb24b6ade63616c0a0688e45bb56732262c158df3c0c4bea4ca47cb7"
+dependencies = [
+ "find-msvc-tools",
+ "jobserver",
+ "libc",
+ "shlex",
+]
+
+[[package]]
+name = "cfg-if"
+version = "1.0.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9330f8b2ff13f34540b44e946ef35111825727b38d33286ef986142615121801"
+
+[[package]]
+name = "compression-codecs"
+version = "0.4.31"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ef8a506ec4b81c460798f572caead636d57d3d7e940f998160f52bd254bf2d23"
+dependencies = [
+ "compression-core",
+ "zstd",
+ "zstd-safe",
+]
+
+[[package]]
+name = "compression-core"
+version = "0.4.29"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e47641d3deaf41fb1538ac1f54735925e275eaf3bf4d55c81b137fba797e5cbb"
+
+[[package]]
+name = "find-msvc-tools"
+version = "0.1.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "52051878f80a721bb68ebfbc930e07b65ba72f2da88968ea5c06fd6ca3d3a127"
+
+[[package]]
+name = "futures-core"
+version = "0.3.31"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "05f29059c0c2090612e8d742178b0580d2dc940c837851ad723096f87af6663e"
+
+[[package]]
+name = "getrandom"
+version = "0.3.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "899def5c37c4fd7b2664648c28120ecec138e4d395b459e5ca34f9cce2dd77fd"
+dependencies = [
+ "cfg-if",
+ "libc",
+ "r-efi",
+ "wasip2",
+]
+
+[[package]]
+name = "itoa"
+version = "1.0.15"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4a5f13b858c8d314ee3e8f639011f7ccefe71f97f96e50151fb991f267928e2c"
+
+[[package]]
+name = "jobserver"
+version = "0.1.34"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9afb3de4395d6b3e67a780b6de64b51c978ecf11cb9a462c66be7d4ca9039d33"
+dependencies = [
+ "getrandom",
+ "libc",
+]
+
+[[package]]
+name = "libc"
+version = "0.2.177"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2874a2af47a2325c2001a6e6fad9b16a53b802102b528163885171cf92b15976"
+
+[[package]]
+name = "md5"
+version = "0.8.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ae960838283323069879657ca3de837e9f7bbb4c7bf6ea7f1b290d5e9476d2e0"
+
+[[package]]
+name = "memchr"
+version = "2.7.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f52b00d39961fc5b2736ea853c9cc86238e165017a493d1d5c8eac6bdc4cc273"
+
+[[package]]
+name = "pin-project-lite"
+version = "0.2.16"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3b3cff922bd51709b605d9ead9aa71031d81447142d828eb4a6eba76fe619f9b"
+
+[[package]]
+name = "pkg-config"
+version = "0.3.32"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7edddbd0b52d732b21ad9a5fab5c704c14cd949e5e9a1ec5929a24fded1b904c"
+
+[[package]]
+name = "proc-macro2"
+version = "1.0.101"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "89ae43fd86e4158d6db51ad8e2b80f313af9cc74f5c0e03ccb87de09998732de"
+dependencies = [
+ "unicode-ident",
+]
+
+[[package]]
+name = "quote"
+version = "1.0.41"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ce25767e7b499d1b604768e7cde645d14cc8584231ea6b295e9c9eb22c02e1d1"
+dependencies = [
+ "proc-macro2",
+]
+
+[[package]]
+name = "r-efi"
+version = "5.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "69cdb34c158ceb288df11e18b4bd39de994f6657d83847bdffdbd7f346754b0f"
+
+[[package]]
+name = "ryu"
+version = "1.0.20"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "28d3b2b1366ec20994f1fd18c3c594f05c5dd4bc44d8bb0c1c632c8d6829481f"
+
+[[package]]
+name = "same-file"
+version = "1.0.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "93fc1dc3aaa9bfed95e02e6eadabb4baf7e3078b0bd1b4d7b6b0b68378900502"
+dependencies = [
+ "winapi-util",
+]
+
+[[package]]
+name = "serde"
+version = "1.0.228"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9a8e94ea7f378bd32cbbd37198a4a91436180c5bb472411e48b5ec2e2124ae9e"
+dependencies = [
+ "serde_core",
+ "serde_derive",
+]
+
+[[package]]
+name = "serde_core"
+version = "1.0.228"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "41d385c7d4ca58e59fc732af25c3983b67ac852c1a25000afe1175de458b67ad"
+dependencies = [
+ "serde_derive",
+]
+
+[[package]]
+name = "serde_derive"
+version = "1.0.228"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d540f220d3187173da220f885ab66608367b6574e925011a9353e4badda91d79"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "serde_json"
+version = "1.0.145"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "402a6f66d8c709116cf22f558eab210f5a50187f702eb4d7e5ef38d9a7f1c79c"
+dependencies = [
+ "itoa",
+ "memchr",
+ "ryu",
+ "serde",
+ "serde_core",
+]
+
+[[package]]
+name = "shlex"
+version = "1.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0fda2ff0d084019ba4d7c6f371c95d8fd75ce3524c3cb8fb653a3023f6323e64"
+
+[[package]]
+name = "syn"
+version = "2.0.106"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ede7c438028d4436d71104916910f5bb611972c5cfd7f89b8300a8186e6fada6"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "unicode-ident",
+]
+
+[[package]]
+name = "tokio"
+version = "1.48.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ff360e02eab121e0bc37a2d3b4d4dc622e6eda3a8e5253d5435ecf5bd4c68408"
+dependencies = [
+ "pin-project-lite",
+ "tokio-macros",
+]
+
+[[package]]
+name = "tokio-macros"
+version = "2.6.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "af407857209536a95c8e56f8231ef2c2e2aff839b22e07a1ffcbc617e9db9fa5"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "unicode-ident"
+version = "1.0.19"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f63a545481291138910575129486daeaf8ac54aee4387fe7906919f7830c7d9d"
+
+[[package]]
+name = "walkdir"
+version = "2.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "29790946404f91d9c5d06f9874efddea1dc06c5efe94541a7d6863108e3a5e4b"
+dependencies = [
+ "same-file",
+ "winapi-util",
+]
+
+[[package]]
+name = "wasip2"
+version = "1.0.1+wasi-0.2.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0562428422c63773dad2c345a1882263bbf4d65cf3f42e90921f787ef5ad58e7"
+dependencies = [
+ "wit-bindgen",
+]
+
+[[package]]
+name = "winapi-util"
+version = "0.1.11"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c2a7b1c03c876122aa43f3020e6c3c3ee5c05081c9a00739faf7503aeba10d22"
+dependencies = [
+ "windows-sys",
+]
+
+[[package]]
+name = "windows-link"
+version = "0.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f0805222e57f7521d6a62e36fa9163bc891acd422f971defe97d64e70d0a4fe5"
+
+[[package]]
+name = "windows-sys"
+version = "0.61.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ae137229bcbd6cdf0f7b80a31df61766145077ddf49416a728b02cb3921ff3fc"
+dependencies = [
+ "windows-link",
+]
+
+[[package]]
+name = "wit-bindgen"
+version = "0.46.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f17a85883d4e6d00e8a97c586de764dabcc06133f7f1d55dce5cdc070ad7fe59"
+
+[[package]]
+name = "zdiff"
+version = "0.1.0"
+dependencies = [
+ "async-compression",
+ "md5",
+ "serde",
+ "serde_json",
+ "tokio",
+ "walkdir",
+ "zstd",
+]
+
+[[package]]
+name = "zstd"
+version = "0.13.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e91ee311a569c327171651566e07972200e76fcfe2242a4fa446149a3881c08a"
+dependencies = [
+ "zstd-safe",
+]
+
+[[package]]
+name = "zstd-safe"
+version = "7.2.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8f49c4d5f0abb602a93fb8736af2a4f4dd9512e36f7f570d66e65ff867ed3b9d"
+dependencies = [
+ "zstd-sys",
+]
+
+[[package]]
+name = "zstd-sys"
+version = "2.0.16+zstd.1.5.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "91e19ebc2adc8f83e43039e79776e3fda8ca919132d68a1fed6a5faca2683748"
+dependencies = [
+ "cc",
+ "pkg-config",
+]
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -0,0 +1,13 @@
+[package]
+name = "zdiff"
+version = "0.1.0"
+edition = "2024"
+
+[dependencies]
+zstd = { version = "0.13" }
+async-compression = { version = "0.4", features = ["zstd"] }
+tokio = { version = "1.48.0", features = ["rt", "rt-multi-thread", "macros"] }
+md5 = "0.8"
+serde = { version = "1.0", features = ["derive"] }
+serde_json = "1.0"
+walkdir = "2.5"
--- a/src/main.rs
+++ b/src/main.rs
@@ -0,0 +1,53 @@
+mod utils;
+mod zdiff;
+mod zpatch;
+
+use std::fs;
+use std::fs::read;
+use std::io;
+use std::path::Path;
+
+async fn zdiff(filename: &str, old: &str, new: &str) -> Result<(), io::Error> {
+    let output_filename = &format!("{}.zdiff", filename);
+    let old_hashes = zdiff::walk_dir(old.to_string()).await;
+    let new_hashes = zdiff::walk_dir(new.to_string()).await;
+    let compare_hashes = zdiff::compare_hashes(old_hashes, new_hashes).await;
+    let parts = compare_hashes.to_vec().await;
+    utils::compress_parts(parts, fs::File::create(output_filename)?, 11).await;
+    Ok(())
+}
+
+async fn zpatch(filename: &str, dest_dir: &str) -> Result<(), io::Error> {
+    let filename = &format!("{}.zdiff", filename);
+    let parts = utils::decompress_parts(read(filename)?).await?;
+    let zdiff = zdiff::Zdiff::from_vec(parts).await?;
+    let tmp_dir_name = zpatch::extract_files(&zdiff, filename).await?;
+    for name in zdiff.content.keys().collect::<Vec<&String>>() {
+        let from_path = Path::new(&tmp_dir_name).join(name);
+        let to_path = Path::new(&dest_dir).join(name);
+        // println!("{:?} {:?}", from_path, to_path);
+        fs::create_dir_all(to_path.parent().unwrap())?;
+        fs::copy(from_path, to_path)?;
+    }
+    for file in zdiff.metadata.remove_files {
+        let path = Path::new(&dest_dir).join(file);
+        fs::remove_file(path)?;
+    }
+
+    for (k, hash) in zdiff.metadata.hashes {
+        let path = Path::new(&dest_dir).join(k);
+        println!("path: {:?}", path);
+        let content = read(path)?;
+        let fs_hash = zdiff::get_hash(&content).await;
+        println!("{:?} {:?}", hash, fs_hash);
+    }
+    Ok(())
+}
+
+#[tokio::main]
+async fn main() -> io::Result<()> {
+    let filename = "test";
+    zdiff(filename, "test/old", "test/new").await?;
+    zpatch(filename, "old").await?;
+    Ok(())
+}
--- a/src/utils.rs
+++ b/src/utils.rs
@@ -0,0 +1,33 @@
+use std::{fs, io};
+use zstd::{Decoder, Encoder};
+
+pub async fn compress_parts(input: Vec<Vec<u8>>, output: fs::File, level: i32) {
+    let mut encoder = Encoder::new(output, level).unwrap();
+    for part in input.iter() {
+        io::copy(&mut &part[..], &mut encoder).unwrap();
+    }
+    encoder.finish().unwrap();
+}
+
+pub async fn decompress_parts(input: Vec<u8>) -> Result<Vec<Vec<u8>>, io::Error> {
+    let mut decoder = Decoder::new(&input[..])?;
+    let mut buf = Vec::new();
+
+    io::copy(&mut decoder, &mut buf)?;
+    let mut index = 0;
+    let mut parts: Vec<Vec<u8>> = Vec::new();
+
+    while index < buf.len() {
+        let filename_size = u32::from_be_bytes(buf[index..index + 4].try_into().unwrap()) as usize;
+        let filename = buf[index..index + filename_size + 4].to_vec();
+        index += 4 + filename_size;
+
+        let content_size = u32::from_be_bytes(buf[index..index + 4].try_into().unwrap()) as usize;
+        let content = buf[index..index + content_size + 4].to_vec();
+        index += content_size + 4;
+
+        let part = vec![filename, content].concat();
+        parts.push(part);
+    }
+    Ok(parts)
+}
--- a/src/zdiff.rs
+++ b/src/zdiff.rs
@@ -0,0 +1,127 @@
+use serde::{Deserialize, Serialize};
+use std::collections::HashMap;
+use std::fs;
+use walkdir::WalkDir;
+
+#[derive(Debug)]
+pub struct Zdiff {
+    pub content: HashMap<String, Vec<u8>>,
+    pub metadata: Metadata,
+}
+
+impl Zdiff {
+    pub async fn from_vec(_data: Vec<Vec<u8>>) -> Result<Self, std::io::Error> {
+        let mut content = HashMap::new();
+        for part in _data {
+            let filename_size = u32::from_be_bytes(part[0..4].try_into().unwrap()) as usize;
+            let filename = String::from_utf8(part[4..filename_size + 4].to_vec()).unwrap();
+            let cont = part[filename_size + 8..].to_vec();
+            content.insert(filename, cont);
+        }
+        let meta = content.get("metadata.json").unwrap();
+        let metadata: Metadata = serde_json::from_slice(meta.as_slice())?;
+        content.remove("metadata.json");
+
+        Ok(Zdiff { content, metadata })
+    }
+
+    pub async fn to_vec(&self) -> Vec<Vec<u8>> {
+        let mut parts: Vec<Vec<u8>> = Vec::new();
+        for (filename, content) in &self.content {
+            let filename_size: [u8; 4] = (filename.len() as u32).to_be_bytes();
+            let filename_encoded = vec![filename_size.as_slice(), filename.as_bytes()].concat();
+
+            let content_size: [u8; 4] = (content.len() as u32).to_be_bytes();
+            let content_encoded = vec![content_size.as_slice(), content.as_slice()].concat();
+            parts.push(vec![filename_encoded, content_encoded].concat())
+        }
+
+        let meta = serde_json::to_vec(&self.metadata).unwrap();
+        let meta_filename = "metadata.json";
+        let meta_filename_size = (meta_filename.len() as u32).to_be_bytes();
+        let meta_filename_encoded =
+            vec![meta_filename_size.as_slice(), meta_filename.as_bytes()].concat();
+
+        let meta_size = (meta.len() as u32).to_be_bytes();
+        let meta_encoded = vec![meta_size.as_slice(), meta.as_slice()].concat();
+        parts.push(vec![meta_filename_encoded, meta_encoded].concat());
+
+        parts
+    }
+}
+
+#[derive(Serialize, Deserialize, Debug)]
+pub struct Metadata {
+    diff_files: Vec<String>,
+    pub hashes: HashMap<String, String>,
+    pub remove_files: Vec<String>,
+}
+
+#[derive(Debug)]
+pub struct FileInfo {
+    path: String,
+    relative_path: String, // Without dir prefix
+    hash: String,
+}
+
+pub async fn get_hash(data: &Vec<u8>) -> String {
+    let hash = md5::compute(&data[..]);
+    format!("{:x}", hash)
+}
+
+pub async fn walk_dir(dir: String) -> HashMap<String, FileInfo> {
+    let mut hash_list: HashMap<String, FileInfo> = HashMap::new();
+    for e in WalkDir::new(&dir) {
+        let e = e.unwrap();
+        let path = e.path();
+        if path.is_dir() {
+            continue;
+        }
+        let content = fs::read(path).unwrap();
+        let hash = get_hash(&content).await;
+        // let filename = path.file_name().unwrap().to_str().unwrap().to_string();
+        let path_str = path.display().to_string();
+        let file_info = FileInfo {
+            relative_path: path_str[dir.len() + 1..].to_string(),
+            path: path_str,
+            hash: hash.clone(),
+        };
+        hash_list.insert(hash, file_info);
+    }
+    hash_list
+}
+
+pub async fn compare_hashes(
+    old: HashMap<String, FileInfo>,
+    new: HashMap<String, FileInfo>,
+) -> Zdiff {
+    let mut diff_files: HashMap<String, Vec<u8>> = HashMap::new();
+    let mut remove_files: Vec<String> = vec![];
+    let mut hashes: HashMap<String, String> = HashMap::new();
+    for (_, info) in &old {
+        remove_files.push(info.relative_path.clone());
+    }
+
+    for (new_hash, new_fileinfo) in &new {
+        let old_fileinfo = old.get(new_hash);
+        remove_files.retain(|filename| !filename.eq(&new_fileinfo.relative_path));
+
+        if old_fileinfo.is_none() {
+            let path = new_fileinfo.relative_path.clone();
+            diff_files.insert(path.clone(), fs::read(new_fileinfo.path.clone()).unwrap());
+            hashes.insert(
+                new_fileinfo.relative_path.clone(),
+                new_fileinfo.hash.clone(),
+            );
+        }
+    }
+
+    Zdiff {
+        content: diff_files.clone(),
+        metadata: Metadata {
+            diff_files: diff_files.keys().cloned().collect(),
+            hashes,
+            remove_files,
+        },
+    }
+}
--- a/src/zpatch.rs
+++ b/src/zpatch.rs
@@ -0,0 +1,24 @@
+use crate::zdiff::Zdiff;
+use crate::zpatch;
+use std::fs;
+use std::io::Write;
+use std::path::Path;
+
+pub async fn create_tmp_dir(dir_name: String) -> Result<String, std::io::Error> {
+    let name = format!("{}.tmp", dir_name);
+    fs::remove_dir_all(name.clone()).map_err(|_| std::io::ErrorKind::NotFound)?;
+    fs::DirBuilder::new().create(name.clone())?;
+    Ok(name)
+}
+
+pub async fn extract_files(zdiff: &Zdiff, filename: &String) -> Result<String, std::io::Error> {
+    let tmp_dir_name = create_tmp_dir(filename.to_string()).await?;
+    let path = Path::new(&tmp_dir_name);
+    fs::remove_dir_all(path)?;
+    for (f, c) in zdiff.content.iter() {
+        let filepath = path.join(f);
+        fs::create_dir_all(filepath.parent().unwrap())?;
+        fs::File::create(&filepath)?.write_all(c)?;
+    }
+    Ok(tmp_dir_name)
+}