From a113b7bd62e564b973d4c5ce784aa11b65d2a1e0 Mon Sep 17 00:00:00 2001
From: Logan <logan@ljones.me>
Date: Wed, 26 Aug 2026 06:35:04 -0400
Subject: [PATCH] fix(riff): grow a chunk buffer with what arrives

Parse sized its buffer from the chunk header, which is four bytes read
off the file, so a truncated or malformed WAV declaring a 4 GB data
chunk in a 2 kB file got 4 GB from the allocator before the read
discovered there was nothing to put in it. The error was always right;
the allocation happened first.

io.CopyN into a bytes.Buffer is what ID3Chunk beside it has done since
#104, and needs nothing new: the reader stays an io.Reader and the
buffer grows with what actually arrives.

The regression test measures rather than asserts the error, because the
error is identical on a build that allocates the gigabyte. Measured on
the pre-fix build: 1,073,750,920 bytes of TotalAlloc for a 42-byte
container whose data chunk claimed 1 GiB.

Closes #216
---
 backend/riff/riff.go      |  9 +++++---
 backend/riff/riff_test.go | 43 +++++++++++++++++++++++++++++++++++++++
 2 files changed, 49 insertions(+), 3 deletions(-)

diff --git a/backend/riff/riff.go b/backend/riff/riff.go
index e60d265..60e2b79 100644
--- a/backend/riff/riff.go
+++ b/backend/riff/riff.go
@@ -63,12 +63,15 @@ func Parse(r io.Reader) ([]Chunk, error) {
 			return nil, err
 		}
 
-		data := make([]byte, size)
-		if _, err := io.ReadFull(r, data); err != nil {
+		// Copied rather than allocated up front, as ID3Chunk does: the
+		// size is four bytes off the file, so a truncated one is free to
+		// declare a chunk larger than the whole of itself.
+		var data bytes.Buffer
+		if _, err := io.CopyN(&data, r, int64(size)); err != nil {
 			return nil, fmt.Errorf("read chunk data for %q: %w", id, err)
 		}
 
-		chunks = append(chunks, Chunk{ID: id, Data: data})
+		chunks = append(chunks, Chunk{ID: id, Data: data.Bytes()})
 
 		// Odd-length chunks have a padding byte.  Lenient: if the
 		// read fails (e.g. EOF), just break rather than error.
diff --git a/backend/riff/riff_test.go b/backend/riff/riff_test.go
index 19295ff..3c9da6a 100644
--- a/backend/riff/riff_test.go
+++ b/backend/riff/riff_test.go
@@ -4,6 +4,7 @@ import (
 	"bytes"
 	"encoding/binary"
 	"errors"
+	"runtime"
 	"testing"
 
 	"yellowjacket/backend/riff"
@@ -209,3 +210,45 @@ func TestParse_ReadsEveryChunkInOrder(t *testing.T) {
 		t.Errorf("odd chunk data: got %q, want %q", chunks[1].Data, "INFOodd")
 	}
 }
+
+// A chunk size is four bytes read off the file, so a truncated or
+// malformed WAV is free to declare a chunk larger than the whole of
+// itself.  Parse must grow with what arrives rather than with what was
+// claimed.
+//
+// This measures the allocation instead of the error because the error
+// is the same either way: a build sizing its buffer from the header
+// reports the truncation correctly, having asked the allocator for a
+// gigabyte on the way.  Deliberately not parallel — TotalAlloc is
+// process-wide, and a test paused beside another one is measuring it
+// too.
+func TestParse_DoesNotAllocateWhatAChunkClaims(t *testing.T) {
+	// Large enough that a header-sized buffer is unmistakable, in a
+	// container of a few dozen bytes.
+	const declared = 1 << 30
+
+	var raw bytes.Buffer
+
+	raw.WriteString("RIFF")
+	_ = binary.Write(&raw, binary.LittleEndian, uint32(declared+12))
+	raw.WriteString("WAVE")
+	raw.WriteString("data")
+	_ = binary.Write(&raw, binary.LittleEndian, uint32(declared))
+	raw.WriteString("and then the file ends")
+
+	var before, after runtime.MemStats
+
+	runtime.GC()
+	runtime.ReadMemStats(&before)
+
+	if _, err := riff.Parse(bytes.NewReader(raw.Bytes())); err == nil {
+		t.Fatal("Parse: got nil error for a chunk larger than the file holding it")
+	}
+
+	runtime.ReadMemStats(&after)
+
+	if grew := after.TotalAlloc - before.TotalAlloc; grew > 1<<20 {
+		t.Errorf("Parse allocated %d bytes reading a %d-byte file whose chunk header claimed %d",
+			grew, raw.Len(), declared)
+	}
+}
-- 
2.54.0