Preserve rootfs hardlink facts in manifests

1 files changed, 19 insertions, 4 deletions

diff --git a/src/manifest.rs b/src/manifest.rs
index 307913e..6168706 100644
--- a/src/manifest.rs
+++ b/src/manifest.rs
@@ -1,6 +1,7 @@
-use std::collections::HashSet;
+use std::collections::{BTreeMap, HashSet};
 use std::fs;
 use std::io::Read;
+use std::os::unix::fs::MetadataExt;
 use std::path::{Path, PathBuf};
 
 use anyhow::{bail, Context, Result};
@@ -154,8 +155,15 @@ impl ArtifactManifest {
 
 fn collect_files(rootfs: &Path) -> Result<Vec<FileRecord>> {
     let mut files = Vec::new();
-    for entry in WalkDir::new(rootfs).follow_links(false).min_depth(1) {
-        let entry = entry.with_context(|| format!("walk rootfs {}", rootfs.display()))?;
+    let mut entries = WalkDir::new(rootfs)
+        .follow_links(false)
+        .min_depth(1)
+        .into_iter()
+        .collect::<std::result::Result<Vec<_>, _>>()
+        .with_context(|| format!("walk rootfs {}", rootfs.display()))?;
+    entries.sort_by_key(|entry| entry.path().to_path_buf());
+    let mut hardlink_targets: BTreeMap<(u64, u64), String> = BTreeMap::new();
+    for entry in entries {
         let relative = entry.path().strip_prefix(rootfs).expect("walk entry is below rootfs");
         if is_internal_metadata_path(&portable_path(relative)?) {
             continue;
@@ -163,7 +171,14 @@ fn collect_files(rootfs: &Path) -> Result<Vec<FileRecord>> {
         let path = portable_path(relative)?;
         let file_type = entry.file_type();
         if file_type.is_file() {
-            files.push(FileRecord::file(path, sha256_file(entry.path())?));
+            let metadata = entry.metadata().with_context(|| format!("inspect rootfs file {}", entry.path().display()))?;
+            let key = (metadata.dev(), metadata.ino());
+            if let Some(target) = hardlink_targets.get(&key) {
+                files.push(FileRecord::hardlink(path, target.clone()));
+            } else {
+                hardlink_targets.insert(key, path.clone());
+                files.push(FileRecord::file(path, sha256_file(entry.path())?));
+            }
         } else if file_type.is_symlink() {
             let target = fs::read_link(entry.path())
                 .with_context(|| format!("read rootfs symlink {}", entry.path().display()))?;