Read files from captured Git commits

internal/git/source.go

@@ -1,12 +1,26 @@
 package git
 
 import (
+	"bytes"
 	"context"
 	"fmt"
 	"path"
+	"strconv"
 	"strings"
+
+	"gitea.maximumdirect.net/eric/ReleaseKit/internal/process"
 )
 
+// TreeEntry records one committed path and its Git object metadata.
+type TreeEntry struct {
+	Path     string
+	ObjectID string
+	Mode     string
+	Type     string
+	Size     int64
+	HasSize  bool
+}
+
 type TaggedSource struct {
 	Head          string
 	Status        string
@@ -74,3 +88,112 @@ func ReadCommitFile(ctx context.Context, repositoryDir, commit, name string) ([]
 	}
 	return []byte(content), nil
 }
+
+// ReadTree enumerates all entries in a commit and records blob sizes. Paths
+// are NUL-delimited by Git so whitespace in a filename is preserved.
+func ReadTree(ctx context.Context, repositoryDir, commit string) ([]TreeEntry, error) {
+	if !validObjectID(commit) {
+		return nil, fmt.Errorf("invalid commit object ID %q", commit)
+	}
+	output, err := run(ctx, repositoryDir, nil, "ls-tree", "-r", "-z", "--full-tree", commit)
+	if err != nil {
+		return nil, fmt.Errorf("enumerate committed tree %s: %w", commit, err)
+	}
+	entries, err := parseTreeEntries([]byte(output))
+	if err != nil {
+		return nil, fmt.Errorf("parse committed tree %s: %w", commit, err)
+	}
+	if err := populateBlobSizes(ctx, repositoryDir, entries); err != nil {
+		return nil, fmt.Errorf("read committed blob sizes for %s: %w", commit, err)
+	}
+	return entries, nil
+}
+
+// ReadBlob reads the bytes for a Git blob object ID without consulting the
+// worktree.
+func ReadBlob(ctx context.Context, repositoryDir, objectID string) ([]byte, error) {
+	if !validObjectID(objectID) {
+		return nil, fmt.Errorf("invalid blob object ID %q", objectID)
+	}
+	content, err := run(ctx, repositoryDir, nil, "cat-file", "blob", objectID)
+	if err != nil {
+		return nil, fmt.Errorf("read blob %s: %w", objectID, err)
+	}
+	return []byte(content), nil
+}
+
+func parseTreeEntries(output []byte) ([]TreeEntry, error) {
+	if len(output) == 0 {
+		return nil, nil
+	}
+	var entries []TreeEntry
+	for _, record := range bytes.Split(output, []byte{0}) {
+		if len(record) == 0 {
+			continue
+		}
+		tab := bytes.IndexByte(record, '\t')
+		if tab < 0 {
+			return nil, fmt.Errorf("tree record has no path separator")
+		}
+		fields := strings.Fields(string(record[:tab]))
+		if len(fields) != 3 || !validObjectID(fields[2]) {
+			return nil, fmt.Errorf("invalid tree record metadata %q", record[:tab])
+		}
+		entries = append(entries, TreeEntry{
+			Mode:     fields[0],
+			Type:     fields[1],
+			ObjectID: fields[2],
+			Path:     string(record[tab+1:]),
+		})
+	}
+	return entries, nil
+}
+
+func populateBlobSizes(ctx context.Context, repositoryDir string, entries []TreeEntry) error {
+	var blobIndexes []int
+	var input strings.Builder
+	for index := range entries {
+		if entries[index].Type != "blob" {
+			continue
+		}
+		blobIndexes = append(blobIndexes, index)
+		input.WriteString(entries[index].ObjectID)
+		input.WriteByte('\n')
+	}
+	if len(blobIndexes) == 0 {
+		return nil
+	}
+	var stdout, stderr bytes.Buffer
+	err := process.Run(ctx, process.Invocation{
+		Args:   []string{"git", "cat-file", "--batch-check=%(objectname) %(objecttype) %(objectsize)"},
+		Dir:    repositoryDir,
+		Stdin:  strings.NewReader(input.String()),
+		Stdout: &stdout,
+		Stderr: &stderr,
+	})
+	if err != nil {
+		message := strings.TrimSpace(stderr.String())
+		if message != "" {
+			return fmt.Errorf("git cat-file --batch-check: %s: %w", message, err)
+		}
+		return err
+	}
+	lines := strings.Split(strings.TrimSuffix(stdout.String(), "\n"), "\n")
+	if len(lines) != len(blobIndexes) {
+		return fmt.Errorf("git returned %d blob sizes for %d blobs", len(lines), len(blobIndexes))
+	}
+	for index, line := range lines {
+		fields := strings.Fields(line)
+		entry := &entries[blobIndexes[index]]
+		if len(fields) != 3 || fields[0] != entry.ObjectID || fields[1] != "blob" {
+			return fmt.Errorf("unexpected blob size record %q", line)
+		}
+		size, err := strconv.ParseInt(fields[2], 10, 64)
+		if err != nil || size < 0 {
+			return fmt.Errorf("invalid blob size in record %q", line)
+		}
+		entry.Size = size
+		entry.HasSize = true
+	}
+	return nil
+}