WIP checkpoint: US-1: Asset Import Pipeline — glTF upload endpoint with metadata extraction

backend/app/routers/assets.py

@@ -1,5 +1,6 @@
 """Asset management router."""
 
+import json
 import os
 from pathlib import Path
 from typing import Optional
@@ -13,6 +14,7 @@ from app.database import get_db
 from app.dependencies import CurrentUser
 from app.models.asset import Asset, AssetType
 from app.models.world import World
+from app.services import gltf as gltf_service
 from pydantic import BaseModel, Field
 
 router = APIRouter()
@@ -64,6 +66,14 @@ def _sanitize_filename(filename: str) -> str:
     return safe or "file"
 
 
+def _detect_asset_type(filename: Optional[str], content: bytes) -> AssetType:
+    """Detect the asset type from filename and content."""
+    if filename and gltf_service.looks_like_gltf(content, filename):
+        return AssetType.MODEL_3D
+    # Fallback: let the caller decide based on mime_type or default.
+    return AssetType.OTHER
+
+
 # --- Endpoints ---
 
 @router.post("/", response_model=AssetResponse, status_code=201)
@@ -183,10 +193,16 @@ async def upload_asset_file(
     # Sanitize filename to prevent path traversal.
     safe_filename = _sanitize_filename(file.filename or f"asset_{asset_id}")
 
-    # Validate file size against configured maximum.
+    # Read the file content.
-    max_bytes = settings.MAX_UPLOAD_SIZE_MB * 1024 * 1024
     content = await file.read()
     file_size = len(content)
+
+    # Determine which size limit to apply.
+    if gltf_service.looks_like_gltf(content, file.filename):
+        max_bytes = settings.GLTF_MAX_FILE_SIZE_MB * 1024 * 1024
+    else:
+        max_bytes = settings.MAX_UPLOAD_SIZE_MB * 1024 * 1024
+
     if file_size > max_bytes:
         raise HTTPException(
             status_code=413,
@@ -200,10 +216,28 @@ async def upload_asset_file(
     file_path = upload_dir / stored_name
     file_path.write_bytes(content)
 
+    # Detect asset type from content/filename.
+    detected_type = _detect_asset_type(file.filename, content)
+
+    # Update asset record.
     asset.file_path = str(file_path)
     asset.mime_type = file.content_type
     asset.file_size = file_size
 
+    # If this is a glTF file, extract and store metadata.
+    if detected_type == AssetType.MODEL_3D:
+        try:
+            metadata = gltf_service.extract_gltf_metadata(content)
+            asset.metadata_json = json.dumps(metadata)
+            # Also set the asset type to model_3d if it was auto-detected.
+            if asset.asset_type == AssetType.OTHER:
+                asset.asset_type = AssetType.MODEL_3D
+        except ValueError as exc:
+            raise HTTPException(
+                status_code=400,
+                detail=f"Invalid glTF file: {exc}",
+            )
+
     await db.commit()
     await db.refresh(asset)
     return asset

backend/tests/test_gltf_metadata.py

@@ -0,0 +1,220 @@
+"""Tests for the lightweight glTF metadata extraction service."""
+
+import json
+import struct
+import pytest
+
+from app.services.gltf import (
+    extract_gltf_metadata,
+    looks_like_gltf,
+    _parse_glb,
+    _parse_gltf_json,
+)
+
+
+# ---------------------------------------------------------------------------
+# Test data helpers
+# ---------------------------------------------------------------------------
+
+def _make_gltf_json(
+    meshes: int = 1,
+    vertices_per_mesh: int = 24,
+    has_animations: bool = False,
+    images: list[dict] | None = None,
+) -> dict:
+    """Build a minimal glTF JSON structure."""
+    accessors = []
+    meshes_data = []
+    for i in range(meshes):
+        acc_index = len(accessors)
+        accessors.append({
+            "bufferView": 0,
+            "componentType": 5126,  # FLOAT
+            "count": vertices_per_mesh,
+            "type": "VEC3",
+            "max": [1.0, 1.0, 1.0],
+            "min": [-1.0, -1.0, -1.0],
+        })
+        meshes_data.append({
+            "primitives": [{
+                "attributes": {"POSITION": acc_index},
+            }],
+        })
+    gltf = {
+        "asset": {"version": "2.0"},
+        "accessors": accessors,
+        "meshes": meshes_data,
+    }
+    if has_animations:
+        gltf["animations"] = [{"name": "anim1", "channels": [], "samplers": []}]
+    if images:
+        gltf["images"] = images
+    return gltf
+
+
+def _make_glb(gltf_json: dict) -> bytes:
+    """Wrap *gltf_json* in a minimal GLB binary container."""
+    json_bytes = json.dumps(gltf_json).encode("utf-8")
+    json_length = len(json_bytes)
+    # Pad JSON chunk to 4-byte boundary.
+    json_padding = (4 - json_length % 4) % 4
+    json_chunk = json_bytes + b"\x00" * json_padding
+    json_chunk_type = 0x4E4F534A  # "JSON"
+    # No BIN chunk.
+    bin_length = 0
+    bin_chunk_type = 0x004E4942
+    total_length = 12 + 8 + len(json_chunk) + 8 + bin_length
+    header = struct.pack("<III", 0x46546C67, 2, total_length)  # magic, version, length
+    json_header = struct.pack("<II", len(json_chunk), json_chunk_type)
+    if bin_length > 0:
+        bin_header = struct.pack("<II", bin_length, bin_chunk_type)
+    else:
+        bin_header = b""
+    return header + json_header + json_chunk + bin_header
+
+
+# ---------------------------------------------------------------------------
+# looks_like_gltf
+# ---------------------------------------------------------------------------
+
+class TestLooksLikeGltf:
+    def test_glb_magic(self):
+        assert looks_like_gltf(b"glTF\x00\x00\x00\x00") is True
+
+    def test_gltf_extension(self):
+        assert looks_like_gltf(b'{"asset":{"version":"2.0"}}', "model.gltf") is True
+
+    def test_glb_extension(self):
+        assert looks_like_gltf(b"some binary", "model.glb") is True
+
+    def test_json_with_asset_version(self):
+        payload = json.dumps({"asset": {"version": "2.0"}}).encode()
+        assert looks_like_gltf(payload) is True
+
+    def test_plain_json_no_asset(self):
+        payload = json.dumps({"foo": "bar"}).encode()
+        assert looks_like_gltf(payload) is False
+
+    def test_non_json_bytes(self):
+        assert looks_like_gltf(b"\x89PNG\r\n\x1a\n") is False
+
+
+# ---------------------------------------------------------------------------
+# _parse_glb
+# ---------------------------------------------------------------------------
+
+class TestParseGlb:
+    def test_parses_valid_glb(self):
+        gltf_json = _make_gltf_json()
+        glb = _make_glb(gltf_json)
+        result = _parse_glb(glb)
+        assert result["asset"]["version"] == "2.0"
+        assert len(result["meshes"]) == 1
+
+    def test_rejects_too_short(self):
+        with pytest.raises(ValueError, match="too short"):
+            _parse_glb(b"glTF\x00\x00")
+
+    def test_rejects_invalid_magic(self):
+        with pytest.raises(ValueError, match="invalid GLB magic"):
+            _parse_glb(b"NOTglTF\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00")
+
+
+# ---------------------------------------------------------------------------
+# _parse_gltf_json
+# ---------------------------------------------------------------------------
+
+class TestParseGltfJson:
+    def test_parses_valid_gltf(self):
+        gltf_json = _make_gltf_json()
+        result = _parse_gltf_json(json.dumps(gltf_json).encode())
+        assert result["asset"]["version"] == "2.0"
+
+    def test_rejects_non_object(self):
+        with pytest.raises(ValueError, match="root must be an object"):
+            _parse_gltf_json(b"[1, 2, 3]")
+
+
+# ---------------------------------------------------------------------------
+# extract_gltf_metadata  (GLB path)
+# ---------------------------------------------------------------------------
+
+class TestExtractGltfMetadataGlb:
+    def test_basic_glb(self):
+        gltf_json = _make_gltf_json(meshes=1, vertices_per_mesh=24)
+        glb = _make_glb(gltf_json)
+        meta = extract_gltf_metadata(glb)
+        assert meta["mesh_count"] == 1
+        assert meta["vertex_count"] == 24
+        assert meta["has_animation"] is False
+        assert meta["bounding_box_min"] == [-1.0, -1.0, -1.0]
+        assert meta["bounding_box_max"] == [1.0, 1.0, 1.0]
+        assert meta["texture_refs"] == []
+
+    def test_multiple_meshes(self):
+        gltf_json = _make_gltf_json(meshes=3, vertices_per_mesh=12)
+        glb = _make_glb(gltf_json)
+        meta = extract_gltf_metadata(glb)
+        assert meta["mesh_count"] == 3
+        assert meta["vertex_count"] == 36
+
+    def test_with_animation(self):
+        gltf_json = _make_gltf_json(has_animations=True)
+        glb = _make_glb(gltf_json)
+        meta = extract_gltf_metadata(glb)
+        assert meta["has_animation"] is True
+
+    def test_with_external_texture(self):
+        gltf_json = _make_gltf_json(images=[{"uri": "textures/rock.png"}])
+        glb = _make_glb(gltf_json)
+        meta = extract_gltf_metadata(glb)
+        assert meta["texture_refs"] == ["textures/rock.png"]
+
+    def test_with_named_texture(self):
+        gltf_json = _make_gltf_json(images=[{"name": "my_texture"}])
+        glb = _make_glb(gltf_json)
+        meta = extract_gltf_metadata(glb)
+        assert meta["texture_refs"] == ["my_texture"]
+
+    def test_empty_meshes(self):
+        gltf_json = _make_gltf_json(meshes=0)
+        glb = _make_glb(gltf_json)
+        meta = extract_gltf_metadata(glb)
+        assert meta["mesh_count"] == 0
+        assert meta["vertex_count"] == 0
+        assert meta["bounding_box_min"] == [0.0, 0.0, 0.0]
+        assert meta["bounding_box_max"] == [0.0, 0.0, 0.0]
+
+
+# ---------------------------------------------------------------------------
+# extract_gltf_metadata  (plain .gltf JSON path)
+# ---------------------------------------------------------------------------
+
+class TestExtractGltfMetadataGltfJson:
+    def test_plain_gltf(self):
+        gltf_json = _make_gltf_json(meshes=2, vertices_per_mesh=8)
+        raw = json.dumps(gltf_json).encode()
+        meta = extract_gltf_metadata(raw)
+        assert meta["mesh_count"] == 2
+        assert meta["vertex_count"] == 16
+        assert meta["has_animation"] is False
+
+    def test_plain_gltf_with_animation(self):
+        gltf_json = _make_gltf_json(has_animations=True)
+        raw = json.dumps(gltf_json).encode()
+        meta = extract_gltf_metadata(raw)
+        assert meta["has_animation"] is True
+
+
+# ---------------------------------------------------------------------------
+# Error handling
+# ---------------------------------------------------------------------------
+
+class TestExtractGltfMetadataErrors:
+    def test_invalid_glb(self):
+        with pytest.raises(ValueError):
+            extract_gltf_metadata(b"not a glb")
+
+    def test_invalid_gltf_json(self):
+        with pytest.raises(ValueError):
+            extract_gltf_json(b"[1, 2, 3]")