From 2b78e63c82a7ab826bcc78229729704658314460 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bartosz=20R=C3=B3=C5=BCa=C5=84ski?= <bartek.roza@gmail.com>
Date: Tue, 20 Aug 2024 11:46:00 +0200
Subject: [PATCH] tests for unpacking

---
 Cargo.lock    | 319 +-------------------------------------------------
 Cargo.toml    |   5 +-
 src/main.rs   |  10 +-
 src/unpack.rs |  72 +++++++++++-
 4 files changed, 73 insertions(+), 333 deletions(-)

diff --git a/Cargo.lock b/Cargo.lock
index 0a0ec08..7c70e58 100644
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -17,23 +17,6 @@ version = "1.0.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f26201604c87b1e01bd3d98f8d5d9a8fcbb815e8cedb41ffccbeb4bf593a35fe"
 
-[[package]]
-name = "adler2"
-version = "2.0.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "512761e0bb2578dd7380c6baaa0f4ce03e84f95e960231d1dec8bf4d7d6e2627"
-
-[[package]]
-name = "aes"
-version = "0.8.4"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b169f7a6d4742236a0a00c541b845991d0ac43e546831af1249753ab4c3aa3a0"
-dependencies = [
- "cfg-if",
- "cipher",
- "cpufeatures",
-]
-
 [[package]]
 name = "ahash"
 version = "0.8.11"
@@ -156,7 +139,7 @@ dependencies = [
  "cc",
  "cfg-if",
  "libc",
- "miniz_oxide 0.7.4",
+ "miniz_oxide",
  "object",
  "rustc-demangle",
 ]
@@ -173,27 +156,12 @@ version = "2.6.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "b048fb63fd8b5923fc5aa7b340d8e156aec7ec02f0c78fa8a6ddc2613f6f71de"
 
-[[package]]
-name = "block-buffer"
-version = "0.10.4"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3078c7629b62d3f0439517fa394996acacc5cbc91c5a20d8c658e77abd503a71"
-dependencies = [
- "generic-array",
-]
-
 [[package]]
 name = "bumpalo"
 version = "3.16.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "79296716171880943b8470b5f8d03aa55eb2e645a4874bdbb28adb49162e012c"
 
-[[package]]
-name = "byteorder"
-version = "1.5.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1fd0f2584146f6f2ef48085050886acf353beff7305ebd1ae69500e27c67f64b"
-
 [[package]]
 name = "bytes"
 version = "1.7.1"
@@ -252,16 +220,6 @@ dependencies = [
  "windows-targets",
 ]
 
-[[package]]
-name = "cipher"
-version = "0.4.4"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "773f3b9af64447d2ce9850330c473515014aa235e6a783b02db81ff39e4a3dad"
-dependencies = [
- "crypto-common",
- "inout",
-]
-
 [[package]]
 name = "clap"
 version = "4.5.16"
@@ -308,12 +266,6 @@ version = "1.0.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "d3fd119d74b830634cea2a0f58bbd0d54540518a14397557951e79340abc28c0"
 
-[[package]]
-name = "constant_time_eq"
-version = "0.3.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f7144d30dcf0fafbce74250a3963025d8d52177934239851c917d29f1df280c2"
-
 [[package]]
 name = "core-foundation"
 version = "0.9.4"
@@ -330,30 +282,6 @@ version = "0.8.7"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "773648b94d0e5d620f64f280777445740e61fe701025087ec8b57f45c791888b"
 
-[[package]]
-name = "cpufeatures"
-version = "0.2.13"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "51e852e6dc9a5bed1fae92dd2375037bf2b768725bf3be87811edee3249d09ad"
-dependencies = [
- "libc",
-]
-
-[[package]]
-name = "crc"
-version = "3.2.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "69e6e4d7b33a94f0991c26729976b10ebde1d34c3ee82408fb536164fa10d636"
-dependencies = [
- "crc-catalog",
-]
-
-[[package]]
-name = "crc-catalog"
-version = "2.4.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "19d374276b40fb8bbdee95aef7c7fa6b5316ec764510eb64b8dd0e2ed0d7e7f5"
-
 [[package]]
 name = "crc32fast"
 version = "1.4.2"
@@ -369,31 +297,6 @@ version = "0.8.20"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "22ec99545bb0ed0ea7bb9b8e1e9122ea386ff8a48c0922e43f36d45ab09e0e80"
 
-[[package]]
-name = "crypto-common"
-version = "0.1.6"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1bfb12502f3fc46cca1bb51ac28df9d618d813cdc3d2f25b9fe775a34af26bb3"
-dependencies = [
- "generic-array",
- "typenum",
-]
-
-[[package]]
-name = "deflate64"
-version = "0.1.9"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "da692b8d1080ea3045efaab14434d40468c3d8657e42abddfffca87b428f4c1b"
-
-[[package]]
-name = "deranged"
-version = "0.3.11"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b42b6fa04a440b495c8b04d0e71b707c585f83cb9cb28cf8cd0d976c315e31b4"
-dependencies = [
- "powerfmt",
-]
-
 [[package]]
 name = "derive_arbitrary"
 version = "1.3.2"
@@ -405,17 +308,6 @@ dependencies = [
  "syn",
 ]
 
-[[package]]
-name = "digest"
-version = "0.10.7"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9ed9a281f7bc9b7576e61468ba615a66a5c8cfdff42420a70aa82701a3b1e292"
-dependencies = [
- "block-buffer",
- "crypto-common",
- "subtle",
-]
-
 [[package]]
 name = "displaydoc"
 version = "0.2.5"
@@ -476,16 +368,6 @@ version = "2.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9fc0510504f03c51ada170672ac806f1f105a88aa97a5281117e1ddc3368e51a"
 
-[[package]]
-name = "flate2"
-version = "1.0.32"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9c0596c1eac1f9e04ed902702e9878208b336edc9d6fddc8a48387349bab3666"
-dependencies = [
- "crc32fast",
- "miniz_oxide 0.8.0",
-]
-
 [[package]]
 name = "fnv"
 version = "1.0.7"
@@ -578,16 +460,6 @@ dependencies = [
  "slab",
 ]
 
-[[package]]
-name = "generic-array"
-version = "0.14.7"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "85649ca51fd72272d7821adaf274ad91c288277713d9c18820d8499a7ff69e9a"
-dependencies = [
- "typenum",
- "version_check",
-]
-
 [[package]]
 name = "getrandom"
 version = "0.2.15"
@@ -654,15 +526,6 @@ version = "0.3.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "d231dfb89cfffdbc30e7fc41579ed6066ad03abda9e567ccafae602b97ec5024"
 
-[[package]]
-name = "hmac"
-version = "0.12.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6c49c37c09c17a53d937dfbb742eb3a961d65a994e6bcdcf37e7399d0cc8ab5e"
-dependencies = [
- "digest",
-]
-
 [[package]]
 name = "http"
 version = "1.1.0"
@@ -819,15 +682,6 @@ dependencies = [
  "hashbrown",
 ]
 
-[[package]]
-name = "inout"
-version = "0.1.3"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a0c10553d664a4d0bcff9f4215d0aac67a639cc68ef660840afe309b807bc9f5"
-dependencies = [
- "generic-array",
-]
-
 [[package]]
 name = "ipnet"
 version = "2.9.0"
@@ -887,28 +741,12 @@ version = "0.4.14"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "78b3ae25bc7c8c38cec158d1f2757ee79e9b3740fbc7ccf0e59e4b08d793fa89"
 
-[[package]]
-name = "lockfree-object-pool"
-version = "0.1.6"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9374ef4228402d4b7e403e5838cb880d9ee663314b0a900d5a6aabf0c213552e"
-
 [[package]]
 name = "log"
 version = "0.4.22"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "a7a70ba024b9dc04c27ea2f0c0548feb474ec5c54bba33a7f72f873a39d07b24"
 
-[[package]]
-name = "lzma-rs"
-version = "0.3.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "297e814c836ae64db86b36cf2a557ba54368d03f6afcd7d947c266692f71115e"
-dependencies = [
- "byteorder",
- "crc",
-]
-
 [[package]]
 name = "md5"
 version = "0.7.0"
@@ -936,15 +774,6 @@ dependencies = [
  "adler",
 ]
 
-[[package]]
-name = "miniz_oxide"
-version = "0.8.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e2d80299ef12ff69b16a84bb182e3b9df68b5a91574d3d4fa6e41b65deec4df1"
-dependencies = [
- "adler2",
-]
-
 [[package]]
 name = "mio"
 version = "1.0.2"
@@ -974,12 +803,6 @@ dependencies = [
  "tempfile",
 ]
 
-[[package]]
-name = "num-conv"
-version = "0.1.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "51d515d32fb182ee37cda2ccdcb92950d6a3c2893aa280e540671c2cd0f3b1d9"
-
 [[package]]
 name = "num-traits"
 version = "0.2.19"
@@ -1048,16 +871,6 @@ dependencies = [
  "vcpkg",
 ]
 
-[[package]]
-name = "pbkdf2"
-version = "0.12.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f8ed6a7761f76e3b9f92dfb0a60a6a6477c61024b775147ff0973a02653abaf2"
-dependencies = [
- "digest",
- "hmac",
-]
-
 [[package]]
 name = "percent-encoding"
 version = "2.3.1"
@@ -1102,21 +915,6 @@ version = "0.3.30"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "d231b230927b5e4ad203db57bbcbee2802f6bce620b1e4a9024a07d94e2907ec"
 
-[[package]]
-name = "powerfmt"
-version = "0.2.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "439ee305def115ba05938db6eb1644ff94165c5ab5e9420d1c1bcedbba909391"
-
-[[package]]
-name = "ppv-lite86"
-version = "0.2.20"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "77957b295656769bb8ad2b6a6b09d897d94f05c41b069aede1fcdaa675eaea04"
-dependencies = [
- "zerocopy",
-]
-
 [[package]]
 name = "proc-macro2"
 version = "1.0.86"
@@ -1140,6 +938,7 @@ dependencies = [
  "rusqlite",
  "serde",
  "serde_json",
+ "tempfile",
  "url",
  "zip",
  "zstd",
@@ -1154,36 +953,6 @@ dependencies = [
  "proc-macro2",
 ]
 
-[[package]]
-name = "rand"
-version = "0.8.5"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "34af8d1a0e25924bc5b7c43c079c942339d8f0a8b57c39049bef581b46327404"
-dependencies = [
- "libc",
- "rand_chacha",
- "rand_core",
-]
-
-[[package]]
-name = "rand_chacha"
-version = "0.3.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e6c10a63a0fa32252be49d21e7709d4d4baf8d231c2dbce1eaa8141b9b127d88"
-dependencies = [
- "ppv-lite86",
- "rand_core",
-]
-
-[[package]]
-name = "rand_core"
-version = "0.6.4"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ec0be4795e2f6a28069bec0b5ff3e2ac9bafc99e6a9a7dc3547996c5c816922c"
-dependencies = [
- "getrandom",
-]
-
 [[package]]
 name = "regex"
 version = "1.10.6"
@@ -1429,29 +1198,12 @@ dependencies = [
  "serde",
 ]
 
-[[package]]
-name = "sha1"
-version = "0.10.6"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e3bf829a2d51ab4a5ddf1352d8470c140cadc8301b2ae1789db023f01cedd6ba"
-dependencies = [
- "cfg-if",
- "cpufeatures",
- "digest",
-]
-
 [[package]]
 name = "shlex"
 version = "1.3.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "0fda2ff0d084019ba4d7c6f371c95d8fd75ce3524c3cb8fb653a3023f6323e64"
 
-[[package]]
-name = "simd-adler32"
-version = "0.3.7"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d66dc143e6b11c1eddc06d5c423cfc97062865baf299914ab64caa38182078fe"
-
 [[package]]
 name = "slab"
 version = "0.4.9"
@@ -1569,25 +1321,6 @@ dependencies = [
  "syn",
 ]
 
-[[package]]
-name = "time"
-version = "0.3.36"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5dfd88e563464686c916c7e46e623e520ddc6d79fa6641390f2e3fa86e83e885"
-dependencies = [
- "deranged",
- "num-conv",
- "powerfmt",
- "serde",
- "time-core",
-]
-
-[[package]]
-name = "time-core"
-version = "0.1.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ef927ca75afb808a4d64dd374f00a2adf8d0fcff8e7b184af886c3c87ec4a3f3"
-
 [[package]]
 name = "tinyvec"
 version = "1.8.0"
@@ -1704,12 +1437,6 @@ version = "0.2.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "e421abadd41a4225275504ea4d6566923418b7f05506fbc9c0fe86ba7396114b"
 
-[[package]]
-name = "typenum"
-version = "1.17.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "42ff0bf0c66b8238c6f3b578df37d0b7848e55df8577b3f74f92a69acceeb825"
-
 [[package]]
 name = "unicode-bidi"
 version = "0.3.15"
@@ -1998,7 +1725,6 @@ version = "0.7.35"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "1b9b4fd18abc82b8136838da5d50bae7bdea537c574d8dc1a34ed098d6c166f0"
 dependencies = [
- "byteorder",
  "zerocopy-derive",
 ]
 
@@ -2018,20 +1744,6 @@ name = "zeroize"
 version = "1.8.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "ced3678a2879b30306d323f4542626697a464a97c0a07c9aebf7ebca65cd4dde"
-dependencies = [
- "zeroize_derive",
-]
-
-[[package]]
-name = "zeroize_derive"
-version = "1.4.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ce36e65b0d2999d2aafac989fb249189a141aee1f53c612c1f37d72631959f69"
-dependencies = [
- "proc-macro2",
- "quote",
- "syn",
-]
 
 [[package]]
 name = "zip"
@@ -2039,41 +1751,14 @@ version = "2.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "dc5e4288ea4057ae23afc69a4472434a87a2495cafce6632fd1c4ec9f5cf3494"
 dependencies = [
- "aes",
  "arbitrary",
  "bzip2",
- "constant_time_eq",
  "crc32fast",
  "crossbeam-utils",
- "deflate64",
  "displaydoc",
- "flate2",
- "hmac",
  "indexmap",
- "lzma-rs",
  "memchr",
- "pbkdf2",
- "rand",
- "sha1",
  "thiserror",
- "time",
- "zeroize",
- "zopfli",
- "zstd",
-]
-
-[[package]]
-name = "zopfli"
-version = "0.8.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e5019f391bac5cf252e93bbcc53d039ffd62c7bfb7c150414d61369afe57e946"
-dependencies = [
- "bumpalo",
- "crc32fast",
- "lockfree-object-pool",
- "log",
- "once_cell",
- "simd-adler32",
 ]
 
 [[package]]
diff --git a/Cargo.toml b/Cargo.toml
index 91803ec..673b706 100644
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -17,5 +17,8 @@ rusqlite = { version = "0.32.1", features = ["bundled"] }
 serde = { version = "1.0.197", features = ["derive"] }
 serde_json = "1.0.114"
 url = "2.5.0"
-zip = "2.2.0"
+zip = { version = "2.2.0", default-features = false, features = ["bzip2"] }
 zstd = "0.13.0"
+
+[dev-dependencies]
+tempfile = "3.12.0"
diff --git a/src/main.rs b/src/main.rs
index 1f922ff..4f54256 100644
--- a/src/main.rs
+++ b/src/main.rs
@@ -22,7 +22,6 @@ use download::download_with_retries;
 use go_spacemesh::get_version;
 use parsers::*;
 use sql::get_last_layer_from_db;
-use unpack::{unpack_zip, unpack_zstd};
 use utils::*;
 
 #[derive(Parser, Debug)]
@@ -245,14 +244,7 @@ fn main() -> anyhow::Result<()> {
         println!("Download URL is not found: skip archive checksum verification");
       }
 
-      let unpack = if archive_file_path.ends_with(".zip") {
-        unpack_zip
-      } else {
-        unpack_zstd
-      };
-
-      // Unzip
-      match unpack(&archive_file_path, &unpacked_file_path) {
+      match unpack::unpack(&archive_file_path, &unpacked_file_path) {
         Ok(_) => {
           println!("Archive unpacked successfully");
         }
diff --git a/src/unpack.rs b/src/unpack.rs
index 91d5fb3..8b8291c 100644
--- a/src/unpack.rs
+++ b/src/unpack.rs
@@ -9,6 +9,8 @@ use zstd::stream::read::Decoder;
 use crate::reader_with_bytes::ReaderWithBytes;
 use crate::reader_with_progress::ReaderWithProgress;
 
+const DB_FILENAME: &str = "state.sql";
+
 fn find_file_in_archive<'a>(
   archive: &'a mut ZipArchive<File>,
   file_name: &str,
@@ -31,7 +33,7 @@ fn find_file_in_archive<'a>(
   ))
 }
 
-pub fn unpack_zstd(archive_path: &Path, output_path: &Path) -> Result<()> {
+fn unpack_zstd(archive_path: &Path, outpath: &Path) -> Result<()> {
   let file = File::open(archive_path).context(format!(
     "Failed to open archive at path: {:?}",
     archive_path
@@ -40,7 +42,6 @@ pub fn unpack_zstd(archive_path: &Path, output_path: &Path) -> Result<()> {
   let mut decoder = Decoder::new(reader)?;
 
   decoder.window_log_max(31)?;
-  let outpath = Path::new(output_path);
   if let Some(p) = outpath.parent() {
     std::fs::create_dir_all(p).context(format!("Failed to create directory at path: {:?}", p))?;
   }
@@ -58,12 +59,11 @@ pub fn unpack_zstd(archive_path: &Path, output_path: &Path) -> Result<()> {
   Ok(())
 }
 
-pub fn unpack_zip(archive_path: &Path, output_path: &Path) -> Result<()> {
+fn unpack_zip(archive_path: &Path, outpath: &Path) -> Result<()> {
   let file = File::open(archive_path)?;
   let mut zip = ZipArchive::new(file)?;
 
-  let state_sql: ZipFile = find_file_in_archive(&mut zip, "state.sql")?;
-  let outpath = Path::new(output_path);
+  let state_sql: ZipFile = find_file_in_archive(&mut zip, DB_FILENAME)?;
 
   if let Some(p) = outpath.parent() {
     std::fs::create_dir_all(p)?;
@@ -75,7 +75,67 @@ pub fn unpack_zip(archive_path: &Path, output_path: &Path) -> Result<()> {
     ReaderWithProgress::new(BufReader::with_capacity(1024 * 1024, state_sql), total_size);
 
   std::io::copy(&mut reader, &mut outfile)?;
-  println!("Unzipping... 100%");
 
   Ok(())
 }
+
+pub(crate) fn unpack(archive_path: &Path, output_path: &Path) -> Result<()> {
+  match archive_path.extension() {
+    Some(ext) if ext == "zst" => unpack_zstd(archive_path, output_path),
+    Some(ext) if ext == "zip" => unpack_zip(archive_path, output_path),
+    _ => Err(anyhow::anyhow!("Unsupported archive format")),
+  }
+}
+
+#[cfg(test)]
+mod tests {
+  use std::fs::File;
+  use std::io::{Read, Write};
+
+  use zip::write::SimpleFileOptions;
+  use zip::CompressionMethod;
+
+  use super::{unpack, DB_FILENAME};
+
+  fn test_unpack(ext: &str) {
+    let tempdir = tempfile::tempdir().unwrap();
+    let archive_path = tempdir.path().join(format!("database.{}", ext));
+    let archive = File::create(&archive_path).unwrap();
+
+    match ext {
+      "zip" => {
+        let mut zip = zip::ZipWriter::new(&archive);
+        let options = SimpleFileOptions::default().compression_method(CompressionMethod::Bzip2);
+        zip.start_file(DB_FILENAME, options).unwrap();
+        zip.write_all(b"Hello, World!\n").unwrap();
+        zip.finish().unwrap();
+      }
+      "zst" => {
+        let mut encoder = zstd::stream::write::Encoder::new(archive, 0).unwrap();
+        encoder.write_all(b"Hello, World!\n").unwrap();
+        encoder.finish().unwrap();
+      }
+      _ => panic!("Unsupported archive format"),
+    }
+
+    // unpack the archive
+    let output_filepath = tempdir.path().join(DB_FILENAME);
+    unpack(&archive_path, &output_filepath).unwrap();
+
+    // check the output
+    let mut output_file = File::open(&output_filepath).unwrap();
+    let mut output = String::new();
+    output_file.read_to_string(&mut output).unwrap();
+    assert_eq!(output, "Hello, World!\n");
+  }
+
+  #[test]
+  fn unpack_zst() {
+    test_unpack("zst");
+  }
+
+  #[test]
+  fn unpack_zip() {
+    test_unpack("zip");
+  }
+}