Add listing and decompressing support for LZMA1 and Lzip

CHANGELOG.md

@@ -25,6 +25,8 @@ Categories Used:
 - Merge folders in decompression [\#798](https://github.com/ouch-org/ouch/pull/798) ([tommady](https://github.com/tommady))
 - Add `--no-smart-unpack` flag to decompression command to disable smart unpack [\#809](https://github.com/ouch-org/ouch/pull/809) ([talis-fb](https://github.com/talis-fb))
 - Provide Nushell completions (packages still need to install them) [\#827](https://github.com/ouch-org/ouch/pull/827) ([FrancescElies](https://github.com/FrancescElies))
+- Support `.lz` decompression [\#838](https://github.com/ouch-org/ouch/pull/838) ([zzzsyyy](https://github.com/zzzsyyy))
+- Support `.lzma` decompression (and fix `.lzma` being a wrong alias for `.xz`) [\#838](https://github.com/ouch-org/ouch/pull/838) ([zzzsyyy](https://github.com/zzzsyyy))
 
 ### Improvements
 

Cargo.toml

@@ -41,7 +41,7 @@ tar = "0.4.42"
 tempfile = "3.10.1"
 time = { version = "0.3.36", default-features = false }
 unrar = { version = "0.5.7", optional = true }
-xz2 = "0.1.7"
+liblzma = "0.4"
 zip = { version = "0.6.6", default-features = false, features = [
     "time",
     "aes-crypto",

README.md

@@ -111,9 +111,9 @@ Output:
 
 # Supported formats
 
-| Format    | `.tar` | `.zip` | `7z` | `.gz` | `.xz`, `.lzma` | `.bz`, `.bz2` | `.bz3` | `.lz4` | `.sz` (Snappy) | `.zst` | `.rar` | `.br` |
-|:---------:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|
-| Supported | ✓ | ✓¹ | ✓¹ | ✓² | ✓ | ✓ | ✓ | ✓ | ✓² | ✓² | ✓³ | ✓ |
+| Format    | `.tar` | `.zip` | `7z` | `.gz` | `.xz` | `.lzma` | `.lz` | `.bz`, `.bz2` | `.bz3` | `.lz4` | `.sz` (Snappy) | `.zst` | `.rar` | `.br` |
+|:---------:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|
+| Supported | ✓ | ✓¹ | ✓¹ | ✓² | ✓ | ✓⁴ | ✓⁴ | ✓ | ✓ | ✓ | ✓² | ✓² | ✓³ | ✓ |
 
 ✓: Supports compression and decompression.
 
@@ -122,10 +122,13 @@ Output:
 ✓²: Supported, and compression runs in parallel.
 
 ✓³: Due to RAR's restrictive license, only decompression and listing can be supported.
+
+✓⁴: Only decompression is supported, compression is not implemented yet.
+
 If you wish to exclude non-free code from your build, you can disable RAR support
 by building without the `unrar` feature.
 
-`tar` aliases are also supported: `tgz`, `tbz`, `tbz2`, `tlz4`, `txz`, `tlzma`, `tsz`, `tzst`.
+`tar` aliases are also supported: `tgz`, `tbz`, `tbz2`, `tlz4`, `txz`, `tlzma`, `tsz`, `tzst`, `tlz`.
 
 Formats can be chained:
 

src/cli/args.rs

@@ -5,7 +5,7 @@ use clap::{Parser, ValueHint};
 // Ouch command line options (docstrings below are part of --help)
 /// A command-line utility for easily compressing and decompressing files and directories.
 ///
-/// Supported formats: tar, zip, gz, 7z, xz/lzma, bz/bz2, bz3, lz4, sz (Snappy), zst, rar and br.
+/// Supported formats: tar, zip, gz, 7z, xz, lzma, lzip, bz/bz2, bz3, lz4, sz (Snappy), zst, rar and br.
 ///
 /// Repository: https://github.com/ouch-org/ouch
 #[derive(Parser, Debug, PartialEq)]

src/commands/compress.rs

@@ -68,10 +68,20 @@ pub fn compress_files(
                 )
             }
             Lz4 => Box::new(lz4_flex::frame::FrameEncoder::new(encoder).auto_finish()),
-            Lzma => Box::new(xz2::write::XzEncoder::new(
+            Lzma => {
+                return Err(crate::Error::UnsupportedFormat {
+                    reason: "LZMA1 compression is not supported in ouch, use .xz instead.".to_string(),
+                })
+            }
+            Xz => Box::new(liblzma::write::XzEncoder::new(
                 encoder,
                 level.map_or(6, |l| (l as u32).clamp(0, 9)),
             )),
+            Lzip => {
+                return Err(crate::Error::UnsupportedFormat {
+                    reason: "Lzip compression is not supported in ouch.".to_string(),
+                })
+            }
             Snappy => Box::new(
                 gzp::par::compress::ParCompress::<gzp::snap::Snap>::builder()
                     .compression_level(gzp::par::compress::Compression::new(
@@ -108,7 +118,7 @@ pub fn compress_files(
     }
 
     match first_format {
-        Gzip | Bzip | Bzip3 | Lz4 | Lzma | Snappy | Zstd | Brotli => {
+        Gzip | Bzip | Bzip3 | Lz4 | Lzma | Xz | Lzip | Snappy | Zstd | Brotli => {
             writer = chain_writer_encoder(&first_format, writer)?;
             let mut reader = fs::File::open(&files[0])?;
 

src/commands/decompress.rs

@@ -128,7 +128,15 @@ pub fn decompress_file(options: DecompressOptions) -> crate::Result<()> {
                 Box::new(bzip3::read::Bz3Decoder::new(decoder)?)
             }
             Lz4 => Box::new(lz4_flex::frame::FrameDecoder::new(decoder)),
-            Lzma => Box::new(xz2::read::XzDecoder::new(decoder)),
+            Lzma => Box::new(liblzma::read::XzDecoder::new_stream(
+                decoder,
+                liblzma::stream::Stream::new_lzma_decoder(u64::MAX).unwrap(),
+            )),
+            Xz => Box::new(liblzma::read::XzDecoder::new(decoder)),
+            Lzip => Box::new(liblzma::read::XzDecoder::new_stream(
+                decoder,
+                liblzma::stream::Stream::new_lzip_decoder(u64::MAX, 0).unwrap(),
+            )),
             Snappy => Box::new(snap::read::FrameDecoder::new(decoder)),
             Zstd => Box::new(zstd::stream::Decoder::new(decoder)?),
             Brotli => Box::new(brotli::Decompressor::new(decoder, BUFFER_CAPACITY)),
@@ -144,7 +152,7 @@ pub fn decompress_file(options: DecompressOptions) -> crate::Result<()> {
     }
 
     let files_unpacked = match first_extension {
-        Gzip | Bzip | Bzip3 | Lz4 | Lzma | Snappy | Zstd | Brotli => {
+        Gzip | Bzip | Bzip3 | Lz4 | Lzma | Xz | Lzip | Snappy | Zstd | Brotli => {
             reader = chain_reader_decoder(&first_extension, reader)?;
 
             let mut writer = match utils::ask_to_create_file(

src/commands/list.rs

@@ -57,7 +57,15 @@ pub fn list_archive_contents(
                     Box::new(bzip3::read::Bz3Decoder::new(decoder).unwrap())
                 }
                 Lz4 => Box::new(lz4_flex::frame::FrameDecoder::new(decoder)),
-                Lzma => Box::new(xz2::read::XzDecoder::new(decoder)),
+                Lzma => Box::new(liblzma::read::XzDecoder::new_stream(
+                    decoder,
+                    liblzma::stream::Stream::new_lzma_decoder(u64::MAX).unwrap(),
+                )),
+                Xz => Box::new(liblzma::read::XzDecoder::new(decoder)),
+                Lzip => Box::new(liblzma::read::XzDecoder::new_stream(
+                    decoder,
+                    liblzma::stream::Stream::new_lzip_decoder(u64::MAX, 0).unwrap(),
+                )),
                 Snappy => Box::new(snap::read::FrameDecoder::new(decoder)),
                 Zstd => Box::new(zstd::stream::Decoder::new(decoder)?),
                 Brotli => Box::new(brotli::Decompressor::new(decoder, BUFFER_CAPACITY)),
@@ -127,7 +135,7 @@ pub fn list_archive_contents(
 
             Box::new(archive::sevenz::list_archive(io::Cursor::new(vec), password)?)
         }
-        Gzip | Bzip | Bzip3 | Lz4 | Lzma | Snappy | Zstd | Brotli => {
+        Gzip | Bzip | Bzip3 | Lz4 | Lzma | Xz | Lzip | Snappy | Zstd | Brotli => {
             unreachable!("Not an archive, should be validated before calling this function.");
         }
     };

src/error.rs

@@ -135,8 +135,8 @@ impl FinalError {
     ///
     /// This is what it looks like:
     /// ```
-    /// hint: Supported extensions are: tar, zip, bz, bz2, gz, lz4, xz, lzma, sz, zst
-    /// hint: Supported aliases are: tgz, tbz, tlz4, txz, tzlma, tsz, tzst
+    /// hint: Supported extensions are: tar, zip, bz, bz2, gz, lz4, xz, lzma, lz, sz, zst
+    /// hint: Supported aliases are: tgz, tbz, tlz4, txz, tlzma, tsz, tzst, tlz
     /// ```
     pub fn hint_all_supported_formats(self) -> Self {
         self.hint(format!("Supported extensions are: {PRETTY_SUPPORTED_EXTENSIONS}"))

src/extension.rs

@@ -19,6 +19,7 @@ pub const SUPPORTED_EXTENSIONS: &[&str] = &[
     "lz4",
     "xz",
     "lzma",
+    "lz",
     "sz",
     "zst",
     #[cfg(feature = "unrar")]
@@ -27,14 +28,14 @@ pub const SUPPORTED_EXTENSIONS: &[&str] = &[
     "br",
 ];
 
-pub const SUPPORTED_ALIASES: &[&str] = &["tgz", "tbz", "tlz4", "txz", "tzlma", "tsz", "tzst"];
+pub const SUPPORTED_ALIASES: &[&str] = &["tgz", "tbz", "tlz4", "txz", "tlzma", "tsz", "tzst", "tlz"];
 
 #[cfg(not(feature = "unrar"))]
-pub const PRETTY_SUPPORTED_EXTENSIONS: &str = "tar, zip, bz, bz2, bz3, gz, lz4, xz, lzma, sz, zst, 7z";
+pub const PRETTY_SUPPORTED_EXTENSIONS: &str = "tar, zip, bz, bz2, bz3, gz, lz4, xz, lzma, lz, sz, zst, 7z";
 #[cfg(feature = "unrar")]
-pub const PRETTY_SUPPORTED_EXTENSIONS: &str = "tar, zip, bz, bz2, bz3, gz, lz4, xz, lzma, sz, zst, rar, 7z";
+pub const PRETTY_SUPPORTED_EXTENSIONS: &str = "tar, zip, bz, bz2, bz3, gz, lz4, xz, lzma, lz, sz, zst, rar, 7z";
 
-pub const PRETTY_SUPPORTED_ALIASES: &str = "tgz, tbz, tlz4, txz, tzlma, tsz, tzst";
+pub const PRETTY_SUPPORTED_ALIASES: &str = "tgz, tbz, tlz4, txz, tlzma, tsz, tzst, tlz";
 
 /// A wrapper around `CompressionFormat` that allows combinations like `tgz`
 #[derive(Debug, Clone)]
@@ -85,8 +86,12 @@ pub enum CompressionFormat {
     Bzip3,
     /// .lz4
     Lz4,
-    /// .xz .lzma
+    /// .xz
+    Xz,
+    /// .lzma
     Lzma,
+    /// .lzip
+    Lzip,
     /// .sz
     Snappy,
     /// tar, tgz, tbz, tbz2, tbz3, txz, tlz4, tlzma, tsz, tzst
@@ -95,7 +100,6 @@ pub enum CompressionFormat {
     Zstd,
     /// .zip
     Zip,
-    // even if built without RAR support, we still want to recognise the format
     /// .rar
     Rar,
     /// .7z
@@ -105,19 +109,11 @@ pub enum CompressionFormat {
 }
 
 impl CompressionFormat {
-    /// Currently supported archive formats are .tar (and aliases to it) and .zip
     pub fn archive_format(&self) -> bool {
-        // Keep this match like that without a wildcard `_` so we don't forget to update it
+        // Keep this match without a wildcard `_` so we never forget to update it
         match self {
             Tar | Zip | Rar | SevenZip => true,
-            Gzip => false,
-            Bzip => false,
-            Bzip3 => false,
-            Lz4 => false,
-            Lzma => false,
-            Snappy => false,
-            Zstd => false,
-            Brotli => false,
+            Bzip | Bzip3 | Lz4 | Lzma | Xz | Lzip | Snappy | Zstd | Brotli | Gzip => false,
         }
     }
 }
@@ -130,15 +126,19 @@ fn to_extension(ext: &[u8]) -> Option<Extension> {
             b"tbz" | b"tbz2" => &[Tar, Bzip],
             b"tbz3" => &[Tar, Bzip3],
             b"tlz4" => &[Tar, Lz4],
-            b"txz" | b"tlzma" => &[Tar, Lzma],
+            b"txz" => &[Tar, Xz],
+            b"tlzma" => &[Tar, Lzma],
+            b"tlz" => &[Tar, Lzip],
             b"tsz" => &[Tar, Snappy],
             b"tzst" => &[Tar, Zstd],
             b"zip" => &[Zip],
             b"bz" | b"bz2" => &[Bzip],
             b"bz3" => &[Bzip3],
             b"gz" => &[Gzip],
             b"lz4" => &[Lz4],
-            b"xz" | b"lzma" => &[Lzma],
+            b"xz" => &[Xz],
+            b"lzma" => &[Lzma],
+            b"lz" => &[Lzip],
             b"sz" => &[Snappy],
             b"zst" => &[Zstd],
             b"rar" => &[Rar],

src/utils/fs.rs

@@ -135,9 +135,15 @@ pub fn try_infer_extension(path: &Path) -> Option<Extension> {
     fn is_bz3(buf: &[u8]) -> bool {
         buf.starts_with(b"BZ3v1")
     }
+    fn is_lzma(buf: &[u8]) -> bool {
+        buf.len() >= 14 && buf[0] == 0x5d && (buf[12] == 0x00 || buf[12] == 0xff) && buf[13] == 0x00
+    }
     fn is_xz(buf: &[u8]) -> bool {
         buf.starts_with(&[0xFD, 0x37, 0x7A, 0x58, 0x5A, 0x00])
     }
+    fn is_lzip(buf: &[u8]) -> bool {
+        buf.starts_with(&[0x4C, 0x5A, 0x49, 0x50])
+    }
     fn is_lz4(buf: &[u8]) -> bool {
         buf.starts_with(&[0x04, 0x22, 0x4D, 0x18])
     }
@@ -183,8 +189,12 @@ pub fn try_infer_extension(path: &Path) -> Option<Extension> {
         Some(Extension::new(&[Bzip], "bz2"))
     } else if is_bz3(&buf) {
         Some(Extension::new(&[Bzip3], "bz3"))
+    } else if is_lzma(&buf) {
+        Some(Extension::new(&[Lzma], "lzma"))
     } else if is_xz(&buf) {
-        Some(Extension::new(&[Lzma], "xz"))
+        Some(Extension::new(&[Xz], "xz"))
+    } else if is_lzip(&buf) {
+        Some(Extension::new(&[Lzip], "lzip"))
     } else if is_lz4(&buf) {
         Some(Extension::new(&[Lz4], "lz4"))
     } else if is_sz(&buf) {

tests/integration.rs

@@ -33,7 +33,6 @@ enum DirectoryExtension {
     Tbz3,
     Tgz,
     Tlz4,
-    Tlzma,
     Tsz,
     Txz,
     Tzst,
@@ -50,7 +49,6 @@ enum FileExtension {
     Bz3,
     Gz,
     Lz4,
-    Lzma,
     Sz,
     Xz,
     Zst,

tests/mime.rs

@@ -17,8 +17,7 @@ fn sanity_check_through_mime() {
     write_random_content(test_file, &mut SmallRng::from_entropy());
 
     let formats = [
-        "7z", "tar", "zip", "tar.gz", "tgz", "tbz", "tbz2", "txz", "tlzma", "tzst", "tar.bz", "tar.bz2", "tar.lzma",
-        "tar.xz", "tar.zst",
+        "7z", "tar", "zip", "tar.gz", "tgz", "tbz", "tbz2", "txz", "tzst", "tar.bz", "tar.bz2", "tar.xz", "tar.zst",
     ];
 
     let expected_mimes = [
@@ -30,12 +29,10 @@ fn sanity_check_through_mime() {
         "application/x-bzip2",
         "application/x-bzip2",
         "application/x-xz",
-        "application/x-xz",
         "application/zstd",
         "application/x-bzip2",
         "application/x-bzip2",
         "application/x-xz",
-        "application/x-xz",
         "application/zstd",
     ];
 

tests/snapshots/ui__ui_test_err_decompress_missing_extension_with_rar-1.snap

@@ -6,8 +6,8 @@ expression: "run_ouch(\"ouch decompress a\", dir)"
  - Files with missing extensions: <TMP_DIR>/a
  - Decompression formats are detected automatically from file extension
 
-hint: Supported extensions are: tar, zip, bz, bz2, bz3, gz, lz4, xz, lzma, sz, zst, rar, 7z
-hint: Supported aliases are: tgz, tbz, tlz4, txz, tzlma, tsz, tzst
+hint: Supported extensions are: tar, zip, bz, bz2, bz3, gz, lz4, xz, lzma, lz, sz, zst, rar, 7z
+hint: Supported aliases are: tgz, tbz, tlz4, txz, tlzma, tsz, tzst, tlz
 hint: 
 hint: Alternatively, you can pass an extension to the '--format' flag:
 hint:   ouch decompress <TMP_DIR>/a --format tar.gz