[pbs-devel] [PATCH v2 proxmox-backup 4/7] client: add helper to dump catalog from metadata archive

[Christian Ebner]

Implements the methods to dump the contents of a metadata pxar
archive using the same output format as used by the catalog dump.

The helper function has been split into 2 for async recursion to
work.

Signed-off-by: Christian Ebner <c.ebner at proxmox.com>
---
changes since version 1:
- use attribute mapping helper
- get rid of unneeded `pxar_metadata_catalog_dump` and use
  `pxar_metadata_catalog_dump_dir` directly
- factor out `pxar_metadata_read_dir` helper, as that will be used by
  the catalog shell as well

 pbs-client/src/tools/mod.rs | 64 +++++++++++++++++++++++++++++++++++--
 1 file changed, 62 insertions(+), 2 deletions(-)

diff --git a/pbs-client/src/tools/mod.rs b/pbs-client/src/tools/mod.rs
index 97f71f3f1..10a368fd2 100644
--- a/pbs-client/src/tools/mod.rs
+++ b/pbs-client/src/tools/mod.rs
@@ -4,11 +4,13 @@ use std::collections::HashMap;
 use std::env::VarError::{NotPresent, NotUnicode};
 use std::ffi::OsStr;
 use std::fs::File;
+use std::future::Future;
 use std::io::{BufRead, BufReader};
 use std::os::unix::ffi::OsStrExt;
 use std::os::unix::fs::OpenOptionsExt;
 use std::os::unix::io::FromRawFd;
 use std::path::PathBuf;
+use std::pin::Pin;
 use std::process::Command;
 use std::sync::{Arc, OnceLock};
 
@@ -22,12 +24,12 @@ use proxmox_schema::*;
 use proxmox_sys::fs::file_get_json;
 
 use pbs_api_types::{Authid, BackupNamespace, RateLimitConfig, UserWithTokens, BACKUP_REPO_URL};
-use pbs_datastore::catalog::{ArchiveEntry, DirEntryAttribute};
+use pbs_datastore::catalog::{ArchiveEntry, CatalogEntryType, DirEntryAttribute};
 use pbs_datastore::dynamic_index::{BufferedDynamicReader, LocalDynamicReadAt};
 use pbs_datastore::index::IndexFile;
 use pbs_datastore::BackupManifest;
 use pbs_tools::crypt_config::CryptConfig;
-use pxar::accessor::aio::Accessor;
+use pxar::accessor::aio::{Accessor, Directory};
 use pxar::accessor::ReadAt;
 use pxar::format::SignedDuration;
 use pxar::{mode, EntryKind};
@@ -806,3 +808,61 @@ pub(crate) fn map_to_dir_entry_attr<T: Clone + ReadAt>(
     };
     Ok(Some(attr))
 }
+
+/// Read a sorted list of pxar archive entries from given parent entry via the pxar accessor.
+pub(crate) async fn pxar_metadata_read_dir<T: Clone + Send + Sync + ReadAt>(
+    parent_dir: Directory<T>,
+) -> Result<Vec<FileEntry<T>>, Error> {
+    let mut entries_iter = parent_dir.read_dir();
+    let mut entries = Vec::new();
+    while let Some(entry) = entries_iter.next().await {
+        let entry = entry?.decode_entry().await?;
+        entries.push(entry);
+    }
+    entries.sort_unstable_by(|a, b| a.path().cmp(b.path()));
+    Ok(entries)
+}
+
+/// Dump pxar archive entry by using the same format used to dump entries from a catalog.
+fn pxar_metadata_catalog_dump_entry<'future, T: Clone + Send + Sync + ReadAt + 'future>(
+    entry: FileEntry<T>,
+    path_prefix: &'future str,
+) -> Pin<Box<dyn Future<Output = Result<(), Error>> + Send + 'future>> {
+    let entry_path = entry_path_with_prefix(&entry, path_prefix);
+
+    Box::pin(async move {
+        if let Some(attr) = map_to_dir_entry_attr(&entry)? {
+            let etype = CatalogEntryType::from(&attr);
+            match attr {
+                DirEntryAttribute::File { size, mtime } => {
+                    let mut mtime_string = mtime.to_string();
+                    if let Ok(s) = proxmox_time::strftime_local("%FT%TZ", mtime) {
+                        mtime_string = s;
+                    }
+                    log::info!("{etype} {entry_path:?} {size} {mtime_string}");
+                }
+                DirEntryAttribute::Directory { .. } => {
+                    log::info!("{etype} {entry_path:?}");
+                    let dir = entry.enter_directory().await?;
+                    pxar_metadata_catalog_dump_dir(dir, path_prefix).await?;
+                }
+                _ => log::info!("{etype} {entry_path:?}"),
+            }
+        }
+
+        Ok(())
+    })
+}
+
+/// Recursively iterate over pxar archive entries and dump them using the same format used to dump
+/// entries from a catalog.
+pub async fn pxar_metadata_catalog_dump_dir<T: Clone + Send + Sync + ReadAt>(
+    parent_dir: Directory<T>,
+    path_prefix: &str,
+) -> Result<(), Error> {
+    let entries = pxar_metadata_read_dir(parent_dir).await?;
+    for entry in entries {
+        pxar_metadata_catalog_dump_entry(entry, path_prefix).await?;
+    }
+    Ok(())
+}
-- 
2.39.2