From f6d99307c1e43a8a59da44cdd6add42d170e8b03 Mon Sep 17 00:00:00 2001
From: Neil Macneale IV <neil@dolthub.com>
Date: Mon, 15 Sep 2025 18:08:05 +0000
Subject: [PATCH] Add the --object-id flag to inspect an object

---
 go/cmd/dolt/commands/admin/archive_inspect.go | 41 +++++++++++++
 go/store/nbs/archive_inspect.go               | 61 +++++++++++++++++++
 2 files changed, 102 insertions(+)

diff --git a/go/cmd/dolt/commands/admin/archive_inspect.go b/go/cmd/dolt/commands/admin/archive_inspect.go
index b6a5218681..ad1be585a4 100644
--- a/go/cmd/dolt/commands/admin/archive_inspect.go
+++ b/go/cmd/dolt/commands/admin/archive_inspect.go
@@ -24,6 +24,7 @@ import (
 	"github.com/dolthub/dolt/go/cmd/dolt/cli"
 	"github.com/dolthub/dolt/go/libraries/doltcore/env"
 	"github.com/dolthub/dolt/go/libraries/utils/argparser"
+	"github.com/dolthub/dolt/go/store/hash"
 	"github.com/dolthub/dolt/go/store/nbs"
 )
 
@@ -50,6 +51,7 @@ func (cmd ArchiveInspectCmd) ArgParser() *argparser.ArgParser {
 	ap := argparser.NewArgParserWithMaxArgs(cmd.Name(), 1)
 	ap.SupportsString("archive-path", "", "archive_path", "Full path to the archive file (.darc) to inspect")
 	ap.SupportsFlag("mmap", "", "Enable memory-mapped index reading for better performance")
+	ap.SupportsString("object-id", "", "object_id", "Base32-encoded 20-byte object ID to inspect within the archive")
 	return ap
 }
 
@@ -134,5 +136,44 @@ func (cmd ArchiveInspectCmd) Exec(ctx context.Context, commandStr string, args [
 		}
 	}
 
+	// Handle object-id inspection if provided
+	if objectIdStr, ok := apr.GetValue("object-id"); ok {
+		cli.Println()
+		cli.Println("Object inspection:")
+		
+		// Parse the hash
+		objectHash, hashOk := hash.MaybeParse(objectIdStr)
+		if !hashOk {
+			cli.PrintErrln("Error: Invalid object ID format. Expected 32-character base32 encoded hash.")
+			return 1
+		}
+		
+		// Look up the object in the archive
+		chunkInfo, err := inspector.GetChunkInfo(ctx, objectHash)
+		if err != nil {
+			cli.PrintErrln("Error inspecting object:", err.Error())
+			return 1
+		}
+		
+		if chunkInfo == nil {
+			cli.Printf("Object %s not found in archive\n", objectIdStr)
+		} else {
+			cli.Printf("Object ID: %s\n", objectIdStr)
+			cli.Printf("Compression type: %s\n", chunkInfo.CompressionType)
+			cli.Printf("Dictionary byte span ID: %d\n", chunkInfo.DictionaryID)
+			cli.Printf("Data byte span ID: %d\n", chunkInfo.DataID)
+			
+			if chunkInfo.DictionaryByteSpan.Length > 0 {
+				cli.Printf("Dictionary byte span: offset=%d, length=%d\n", 
+					chunkInfo.DictionaryByteSpan.Offset, chunkInfo.DictionaryByteSpan.Length)
+			} else {
+				cli.Println("Dictionary byte span: none (empty)")
+			}
+			
+			cli.Printf("Data byte span: offset=%d, length=%d\n", 
+				chunkInfo.DataByteSpan.Offset, chunkInfo.DataByteSpan.Length)
+		}
+	}
+
 	return 0
 }
\ No newline at end of file
diff --git a/go/store/nbs/archive_inspect.go b/go/store/nbs/archive_inspect.go
index 580abc3c4f..ffbbd7856e 100644
--- a/go/store/nbs/archive_inspect.go
+++ b/go/store/nbs/archive_inspect.go
@@ -20,6 +20,21 @@ import (
 	"github.com/dolthub/dolt/go/store/hash"
 )
 
+// ByteSpanInfo provides information about a byte span in the archive
+type ByteSpanInfo struct {
+	Offset uint64
+	Length uint64
+}
+
+// ChunkInfo contains information about a chunk within the archive
+type ChunkInfo struct {
+	CompressionType      string
+	DictionaryID         uint32
+	DataID               uint32
+	DictionaryByteSpan   ByteSpanInfo
+	DataByteSpan         ByteSpanInfo
+}
+
 // ArchiveInspector provides a way to inspect archive files from outside the nbs package
 type ArchiveInspector struct {
 	reader archiveReader
@@ -94,4 +109,50 @@ func (ai *ArchiveInspector) ByteSpanCount() uint32 {
 func (ai *ArchiveInspector) GetMetadata(ctx context.Context) ([]byte, error) {
 	stats := &Stats{}
 	return ai.reader.getMetadata(ctx, stats)
+}
+
+// GetChunkInfo looks up information about a specific chunk in the archive
+func (ai *ArchiveInspector) GetChunkInfo(ctx context.Context, h hash.Hash) (*ChunkInfo, error) {
+	// Search for the chunk
+	idx := ai.reader.search(h)
+	if idx < 0 {
+		return nil, nil // Chunk not found
+	}
+	
+	// Get the chunk reference (dictionary ID and data ID)
+	dictID, dataID := ai.reader.getChunkRef(idx)
+	
+	// Get the byte span information
+	dictByteSpan := ai.reader.getByteSpanByID(dictID)
+	dataByteSpan := ai.reader.getByteSpanByID(dataID)
+	
+	// Determine compression type based on dictionary ID and archive version
+	compressionType := "unknown"
+	formatVersion := ai.reader.footer.formatVersion
+	
+	if dictID == 0 {
+		// Dictionary ID 0 means no dictionary
+		if formatVersion == 1 {
+			compressionType = "zstd (no dictionary)"
+		} else if formatVersion >= 2 {
+			compressionType = "snappy"
+		}
+	} else {
+		// Dictionary ID > 0 means zstd with dictionary
+		compressionType = "zstd (with dictionary)"
+	}
+	
+	return &ChunkInfo{
+		CompressionType: compressionType,
+		DictionaryID:    dictID,
+		DataID:          dataID,
+		DictionaryByteSpan: ByteSpanInfo{
+			Offset: dictByteSpan.offset,
+			Length: dictByteSpan.length,
+		},
+		DataByteSpan: ByteSpanInfo{
+			Offset: dataByteSpan.offset,
+			Length: dataByteSpan.length,
+		},
+	}, nil
 }
\ No newline at end of file