From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <w.bumiller@proxmox.com>
Received: from firstgate.proxmox.com (firstgate.proxmox.com [212.224.123.68])
 (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits)
 key-exchange X25519 server-signature RSA-PSS (2048 bits))
 (No client certificate requested)
 by lists.proxmox.com (Postfix) with ESMTPS id 6C613BBE75
 for <pbs-devel@lists.proxmox.com>; Wed, 20 Dec 2023 14:20:42 +0100 (CET)
Received: from firstgate.proxmox.com (localhost [127.0.0.1])
 by firstgate.proxmox.com (Proxmox) with ESMTP id 457E6D393
 for <pbs-devel@lists.proxmox.com>; Wed, 20 Dec 2023 14:20:12 +0100 (CET)
Received: from proxmox-new.maurer-it.com (proxmox-new.maurer-it.com
 [94.136.29.106])
 (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits)
 key-exchange X25519 server-signature RSA-PSS (2048 bits))
 (No client certificate requested)
 by firstgate.proxmox.com (Proxmox) with ESMTPS
 for <pbs-devel@lists.proxmox.com>; Wed, 20 Dec 2023 14:20:11 +0100 (CET)
Received: from proxmox-new.maurer-it.com (localhost.localdomain [127.0.0.1])
 by proxmox-new.maurer-it.com (Proxmox) with ESMTP id 06A414876C
 for <pbs-devel@lists.proxmox.com>; Wed, 20 Dec 2023 14:20:11 +0100 (CET)
Date: Wed, 20 Dec 2023 14:20:10 +0100
From: Wolfgang Bumiller <w.bumiller@proxmox.com>
To: Filip Schauer <f.schauer@proxmox.com>
Cc: pbs-devel@lists.proxmox.com, Dominik Csapak <d.csapak@proxmox.com>
Message-ID: <ccc4uaslsrj67zrjeixmjwvofnqos4vuyp5e3a6niljmaovr4e@wl4dq2mjueiv>
References: <20231214144824.100616-1-f.schauer@proxmox.com>
 <20231214144824.100616-3-f.schauer@proxmox.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20231214144824.100616-3-f.schauer@proxmox.com>
X-SPAM-LEVEL: Spam detection results:  0
 AWL 0.095 Adjusted score from AWL reputation of From: address
 BAYES_00                 -1.9 Bayes spam probability is 0 to 1%
 DMARC_MISSING             0.1 Missing DMARC policy
 KAM_DMARC_STATUS 0.01 Test Rule for DKIM or SPF Failure with Strict Alignment
 SPF_HELO_NONE           0.001 SPF: HELO does not publish an SPF Record
 SPF_PASS               -0.001 SPF: sender matches SPF record
 T_SCC_BODY_TEXT_LINE    -0.01 -
Subject: Re: [pbs-devel] [PATCH v3 proxmox 2/3] compression: Add support for
 symlinks in zip files
X-BeenThere: pbs-devel@lists.proxmox.com
X-Mailman-Version: 2.1.29
Precedence: list
List-Id: Proxmox Backup Server development discussion
 <pbs-devel.lists.proxmox.com>
List-Unsubscribe: <https://lists.proxmox.com/cgi-bin/mailman/options/pbs-devel>, 
 <mailto:pbs-devel-request@lists.proxmox.com?subject=unsubscribe>
List-Archive: <http://lists.proxmox.com/pipermail/pbs-devel/>
List-Post: <mailto:pbs-devel@lists.proxmox.com>
List-Help: <mailto:pbs-devel-request@lists.proxmox.com?subject=help>
List-Subscribe: <https://lists.proxmox.com/cgi-bin/mailman/listinfo/pbs-devel>, 
 <mailto:pbs-devel-request@lists.proxmox.com?subject=subscribe>
X-List-Received-Date: Wed, 20 Dec 2023 13:20:42 -0000

With the link of a symlink being encoded in the contents, I wonder if we
should just do the same in the code. Not normally what I'd go for in
rust, but...

On Thu, Dec 14, 2023 at 03:48:21PM +0100, Filip Schauer wrote:
> Add support for symlinks to ZipEntry. A symlink is encoded by or-ing its
> attributes with S_IFLNK as seen in the kernel in
> include/uapi/linux/stat.h
> 
> Signed-off-by: Filip Schauer <f.schauer@proxmox.com>
> ---
>  proxmox-compression/src/zip.rs | 32 +++++++++++++++++++++++++-------
>  1 file changed, 25 insertions(+), 7 deletions(-)
> 
> diff --git a/proxmox-compression/src/zip.rs b/proxmox-compression/src/zip.rs
> index 069e8bc..a3b2346 100644
> --- a/proxmox-compression/src/zip.rs
> +++ b/proxmox-compression/src/zip.rs
> @@ -74,6 +74,7 @@ fn epoch_to_dos(epoch: i64) -> (u16, u16) {
>  pub enum FileType {
>      Directory,
>      Regular,
> +    Symlink(OsString),

... then this enum could be #[repr(u32)] using the values from the hunk
below as discriminants here directly.
And without the OsString in there this could be all of `Clone + Copy +
Eq + PartialEq`, turning all the `matches!()` in this series into
comparisons with `==`.

>  }
>  
>  #[derive(Endian)]
> @@ -350,6 +351,7 @@ impl ZipEntry {


(maybe include a comment that these are the same as the S_IF* constants,
since Dominik had asked about more documentation in the previous
version ;-) )

>          let file_type_attr = match self.file_type {
>              FileType::Regular => 0o100000,
>              FileType::Directory => 0o040000,
> +            FileType::Symlink(_) => 0o120000,
>          };
>  
>          write_struct(
> @@ -497,22 +499,28 @@ impl<W: AsyncWrite + Unpin> ZipEncoder<W> {
>              .ok_or_else(|| format_err!("had no target during add entry"))?;
>          entry.offset = self.byte_count.try_into()?;
>          self.byte_count += entry.write_local_header(&mut target).await?;
> -        if let Some(content) = content {
> -            let mut reader = HashWrapper::new(content);
> +
> +        if content.is_some() || matches!(entry.file_type, FileType::Symlink(_)) {
>              let mut enc = DeflateEncoder::with_quality(target, Level::Fastest);
>  
> -            enc.compress(&mut reader).await?;
> +            if let Some(content) = content {
> +                let mut reader = HashWrapper::new(content);
> +                enc.compress(&mut reader).await?;
> +                entry.crc32 = reader.finish().0;
> +            } else if let FileType::Symlink(symlink_target) = &entry.file_type {
> +                let cursor = std::io::Cursor::new(symlink_target.as_bytes());
> +                let mut reader = HashWrapper::new(cursor);
> +                enc.compress(&mut reader).await?;
> +                entry.crc32 = reader.finish().0;

^ and AFAICT this entire hunk would simply disappear?

> +            }
> +
>              let total_in = enc.total_in();
>              let total_out = enc.total_out();
>              target = enc.into_inner();
>  
> -            let (crc32, _reader) = reader.finish();
> -
>              self.byte_count += total_out as usize;
>              entry.compressed_size = total_out;
>              entry.uncompressed_size = total_in;
> -
> -            entry.crc32 = crc32;
>          }
>  
>          self.byte_count += entry.write_data_descriptor(&mut target).await?;
> @@ -676,6 +684,16 @@ where
>                  let ze = ZipEntry::new(entry_path_no_base, mtime, mode, FileType::Directory);
>                  let content: Option<tokio::fs::File> = None;
>                  Ok(Some((ze, content)))
> +            } else if entry.file_type().is_symlink() {
> +                let target = std::fs::read_link(entry.path())?;
> +                let ze = ZipEntry::new(
> +                    entry_path_no_base,
> +                    mtime,
> +                    mode,
> +                    FileType::Symlink(target.into()),
> +                );
> +                let content: Option<tokio::fs::File> = None;
> +                Ok(Some((ze, content)))
>              } else {
>                  // ignore other file types
>                  Ok::<_, Error>(None)
> -- 
> 2.39.2