HartOMat/backend/app/domains/pipeline/tasks/export_glb.py

"""GLB/GLTF export tasks.

Covers:
- generate_gltf_geometry_task   — OCC STEP → geometry GLB (fast preview)
- generate_gltf_production_task — OCC STEP → production GLB (Blender PBR materials)
"""
import logging

from app.tasks.celery_app import celery_app
from app.core.task_logs import log_task_event
from app.core.pipeline_logger import PipelineLogger

logger = logging.getLogger(__name__)


@celery_app.task(bind=True, name="app.tasks.step_tasks.generate_gltf_geometry_task", queue="thumbnail_rendering", max_retries=1)
def generate_gltf_geometry_task(self, cad_file_id: str):
    """Export a geometry GLB directly from STEP via OCC (no STL intermediary).

    Pipeline:
      1. Reads STEP file directly (no STL needed)
      2. Builds color_map from product.cad_part_materials (hex colors)
      3. Runs export_step_to_gltf.py (Python/OCP): STEP → GLB with per-part colors
      4. Stores result as gltf_geometry MediaAsset (replaces any existing one)

    Output is in meters, Y-up (glTF convention).
    """
    import json as _json
    import os as _os
    import subprocess as _subprocess
    import sys as _sys
    from pathlib import Path as _Path
    from sqlalchemy import create_engine, select as _select
    from sqlalchemy.orm import Session
    from app.config import settings as app_settings
    from app.models.cad_file import CadFile

    from app.models.system_setting import SystemSetting as _SysSetting

    pl = PipelineLogger(task_id=self.request.id)
    pl.step_start("export_glb_geometry", {"cad_file_id": cad_file_id})

    sync_url = app_settings.database_url.replace("+asyncpg", "")
    eng = create_engine(sync_url)
    with Session(eng) as session:
        cad_file = session.get(CadFile, cad_file_id)
        if not cad_file or not cad_file.stored_path:
            logger.error("generate_gltf_geometry_task: no stored_path for %s", cad_file_id)
            return
        step_path_str = cad_file.stored_path

        # Build hex color_map from product.cad_part_materials
        from app.domains.products.models import Product
        product = session.execute(
            _select(Product).where(Product.cad_file_id == cad_file.id)
        ).scalar_one_or_none()

        color_map: dict[str, str] = {}
        product_id = str(product.id) if product else None
        if product and product.cad_part_materials:
            for entry in product.cad_part_materials:
                part_name = entry.get("part_name") or entry.get("name", "")
                hex_color = entry.get("hex_color") or entry.get("color", "")
                if part_name and hex_color:
                    color_map[part_name] = hex_color

        settings_rows = session.execute(_select(_SysSetting)).scalars().all()
        sys_settings = {s.key: s.value for s in settings_rows}
    eng.dispose()

    linear_deflection = float(sys_settings.get("gltf_preview_linear_deflection", "0.1"))
    angular_deflection = float(sys_settings.get("gltf_preview_angular_deflection", "0.1"))
    tessellation_engine = sys_settings.get("tessellation_engine", "occ")

    step = _Path(step_path_str)

    if not step.exists():
        log_task_event(self.request.id, f"Failed: STEP file not found: {step}", "error")
        raise RuntimeError(f"STEP file not found: {step}")

    output_path = step.parent / f"{step.stem}_geometry.glb"

    log_task_event(
        self.request.id,
        f"Starting OCC GLB export: {len(color_map)} part colors",
        "info",
    )

    # Run export_step_to_gltf.py as a subprocess so OCP imports don't pollute worker state
    scripts_dir = _Path(_os.environ.get("RENDER_SCRIPTS_DIR", "/render-scripts"))
    script_path = scripts_dir / "export_step_to_gltf.py"

    python_bin = _sys.executable
    cmd = [
        python_bin, str(script_path),
        "--step_path", str(step),
        "--output_path", str(output_path),
        "--color_map", _json.dumps(color_map),
        "--linear_deflection", str(linear_deflection),
        "--angular_deflection", str(angular_deflection),
        "--tessellation_engine", tessellation_engine,
    ]
    log_task_event(
        self.request.id,
        f"Tessellation ({tessellation_engine}): linear={linear_deflection}mm, angular={angular_deflection}rad",
        "info",
    )

    try:
        result = _subprocess.run(cmd, capture_output=True, text=True, timeout=120)
        for line in result.stdout.splitlines():
            logger.info("[occ-gltf] %s", line)
        for line in result.stderr.splitlines():
            logger.warning("[occ-gltf stderr] %s", line)

        if result.returncode != 0 or not output_path.exists() or output_path.stat().st_size == 0:
            raise RuntimeError(
                f"export_step_to_gltf.py failed (exit {result.returncode}).\n"
                f"STDERR: {result.stderr[-1000:]}"
            )
    except Exception as exc:
        log_task_event(self.request.id, f"Failed: {exc}", "error")
        pl.step_error("export_glb_geometry", str(exc), exc)
        logger.error("generate_gltf_geometry_task OCC export failed: %s", exc)
        raise self.retry(exc=exc, countdown=15)

    log_task_event(self.request.id, f"OCC GLB export completed: {output_path.name}", "done")

    # --- Store MediaAsset (upsert: update existing to keep stable ID/URL) ---
    import uuid as _uuid
    from sqlalchemy import create_engine as _ce, select as _sel2
    from sqlalchemy.orm import Session as _Session
    from app.domains.media.models import MediaAsset, MediaAssetType

    _sync_url = app_settings.database_url.replace("+asyncpg", "")
    _eng2 = _ce(_sync_url)
    with _Session(_eng2) as _sess:
        _key = str(output_path)
        _prefix = str(app_settings.upload_dir).rstrip("/") + "/"
        if _key.startswith(_prefix):
            _key = _key[len(_prefix):]
        _file_size = output_path.stat().st_size if output_path.exists() else None

        existing = _sess.execute(
            _sel2(MediaAsset).where(
                MediaAsset.cad_file_id == _uuid.UUID(cad_file_id),
                MediaAsset.asset_type == MediaAssetType.gltf_geometry,
            )
        ).scalars().first()

        if existing:
            existing.storage_key = _key
            existing.mime_type = "model/gltf-binary"
            existing.file_size_bytes = _file_size
            if product_id:
                existing.product_id = _uuid.UUID(product_id)
            _sess.commit()
            asset_id = str(existing.id)
        else:
            asset = MediaAsset(
                cad_file_id=_uuid.UUID(cad_file_id),
                product_id=_uuid.UUID(product_id) if product_id else None,
                asset_type=MediaAssetType.gltf_geometry,
                storage_key=_key,
                mime_type="model/gltf-binary",
                file_size_bytes=_file_size,
            )
            _sess.add(asset)
            _sess.commit()
            asset_id = str(asset.id)
    _eng2.dispose()

    pl.step_done("export_glb_geometry", result={"glb_path": str(output_path), "asset_id": asset_id})
    logger.info("generate_gltf_geometry_task: MediaAsset %s created for cad %s", asset_id, cad_file_id)
    return {"glb_path": str(output_path), "asset_id": asset_id}


@celery_app.task(
    bind=True,
    name="app.tasks.step_tasks.generate_gltf_production_task",
    queue="thumbnail_rendering",
    max_retries=2,
)
def generate_gltf_production_task(self, cad_file_id: str, product_id: str | None = None) -> dict:
    """Generate a production GLB (Blender + PBR materials) from a geometry GLB via export_gltf.py.

    1. Ensures a gltf_geometry MediaAsset exists (runs OCC export inline if not).
    2. Resolves SCHAEFFLER material map for the CadFile's product.
    3. Runs Blender headless with export_gltf.py → production GLB.
    4. Stores result as gltf_production MediaAsset.
    """
    import json as _json
    import os as _os
    import subprocess as _subprocess
    import sys as _sys
    import uuid as _uuid
    from pathlib import Path as _Path

    from sqlalchemy import create_engine as _ce, delete as _del, select as _sel, update as _upd
    from sqlalchemy.orm import Session as _Session

    from app.config import settings as app_settings
    from app.domains.media.models import MediaAsset, MediaAssetType
    from app.services.render_blender import find_blender, is_blender_available

    pl = PipelineLogger(task_id=self.request.id)
    pl.step_start("export_glb_production", {"cad_file_id": cad_file_id})
    log_task_event(self.request.id, f"generate_gltf_production_task started for cad {cad_file_id}", "info")

    _sync_url = app_settings.database_url.replace("+asyncpg", "")
    _eng = _ce(_sync_url)

    # --- 1. Resolve STEP file path and system settings ---
    from app.models.cad_file import CadFile as _CF
    from app.models.system_setting import SystemSetting

    with _Session(_eng) as _sess:
        _cad = _sess.execute(
            _sel(_CF).where(_CF.id == _uuid.UUID(cad_file_id))
        ).scalar_one_or_none()
        step_path_str = _cad.stored_path if _cad else None
        cad_mesh_attributes: dict = (_cad.mesh_attributes or {}) if _cad else {}

        settings_rows = _sess.execute(_sel(SystemSetting)).scalars().all()
        sys_settings = {s.key: s.value for s in settings_rows}

    if not step_path_str:
        raise RuntimeError(f"CadFile {cad_file_id} not found in DB")
    step_path = _Path(step_path_str)
    if not step_path.exists():
        raise RuntimeError(f"STEP file not found: {step_path}")

    smooth_angle = float(sys_settings.get("blender_smooth_angle", "30"))
    prod_linear = float(sys_settings.get("gltf_production_linear_deflection", "0.03"))
    prod_angular = float(sys_settings.get("gltf_production_angular_deflection", "0.05"))
    tessellation_engine = sys_settings.get("tessellation_engine", "occ")

    scripts_dir = _Path(_os.environ.get("RENDER_SCRIPTS_DIR", "/render-scripts"))
    occ_script = scripts_dir / "export_step_to_gltf.py"
    if not occ_script.exists():
        raise RuntimeError(f"export_step_to_gltf.py not found at {occ_script}")

    prod_geom_glb = step_path.parent / f"{step_path.stem}_production_geom.glb"
    python_bin = _sys.executable
    sharp_threshold = float(sys_settings.get("sharp_edge_threshold", "20.0"))
    occ_cmd = [
        python_bin, str(occ_script),
        "--step_path", str(step_path),
        "--output_path", str(prod_geom_glb),
        "--linear_deflection", str(prod_linear),
        "--angular_deflection", str(prod_angular),
        "--sharp_threshold", str(sharp_threshold),
        "--tessellation_engine", tessellation_engine,
    ]
    log_task_event(
        self.request.id,
        f"Re-exporting STEP at production quality (linear={prod_linear}mm, angular={prod_angular}rad)",
        "info",
    )
    try:
        occ_result = _subprocess.run(occ_cmd, capture_output=True, text=True, timeout=180)
        for line in occ_result.stdout.splitlines():
            logger.info("[occ-prod] %s", line)
        if occ_result.returncode != 0 or not prod_geom_glb.exists() or prod_geom_glb.stat().st_size == 0:
            raise RuntimeError(
                f"OCC export failed (exit {occ_result.returncode}): {occ_result.stderr[-500:]}"
            )
    except Exception as exc:
        log_task_event(self.request.id, f"OCC re-export failed: {exc}", "error")
        pl.step_error("export_glb_production", f"OCC re-export failed: {exc}", exc)
        raise self.retry(exc=exc, countdown=30)

    geom_glb_path = prod_geom_glb

    # --- 2. Resolve material map from Product.cad_part_materials (SCHAEFFLER library names) ---
    # cad_part_materials lives on Product (list[dict]), NOT on CadFile.
    # We look up the Product that owns this CadFile (prefer product_id arg if given).
    from app.services.material_service import resolve_material_map
    from app.domains.products.models import Product as _Product

    with _Session(_eng) as _sess:
        _prod_query = _sel(_Product).where(_Product.cad_file_id == _uuid.UUID(cad_file_id))
        if product_id:
            _prod_query = _prod_query.where(_Product.id == _uuid.UUID(product_id))
        _product = _sess.execute(_prod_query).scalars().first()
        raw_materials: list[dict] = _product.cad_part_materials if _product else []

    # Convert list[{"part_name": X, "material": Y}] → dict[str, str] for resolve_material_map
    raw_mat_map: dict[str, str] = {
        m["part_name"]: m["material"]
        for m in raw_materials
        if m.get("part_name") and m.get("material")
    }
    mat_map = resolve_material_map(raw_mat_map)
    logger.info(
        "generate_gltf_production_task: resolved %d material(s) for cad %s (product: %s)",
        len(mat_map), cad_file_id, _product.id if _product else "none",
    )

    # --- 3. Run Blender: apply materials + smooth shading + export production GLB ---
    # Use get_material_library_path() which checks active AssetLibrary first,
    # then falls back to the legacy material_library_path system setting.
    from app.services.template_service import get_material_library_path
    asset_library_blend = get_material_library_path() or ""
    _eng.dispose()

    output_path = step_path.parent / f"{step_path.stem}_production.glb"

    export_script = scripts_dir / "export_gltf.py"
    if not is_blender_available():
        raise RuntimeError("Blender is not available — cannot generate production GLB")
    if not export_script.exists():
        raise RuntimeError(f"export_gltf.py not found at {export_script}")

    blender_bin = find_blender()
    cmd = [
        blender_bin, "--background",
        "--python", str(export_script),
        "--",
        "--glb_path", str(geom_glb_path),
        "--output_path", str(output_path),
        "--material_map", _json.dumps(mat_map),
        "--smooth_angle", str(smooth_angle),
        "--mesh_attributes", _json.dumps(cad_mesh_attributes),
    ]
    if asset_library_blend:
        cmd += ["--asset_library_blend", asset_library_blend]

    log_task_event(
        self.request.id,
        f"Running Blender export_gltf.py — {len(mat_map)} material(s), smooth={smooth_angle}°",
        "info",
    )
    try:
        result = _subprocess.run(cmd, capture_output=True, text=True, timeout=300)
        for line in result.stdout.splitlines():
            logger.info("[export-gltf] %s", line)
        if result.returncode != 0:
            raise RuntimeError(
                f"export_gltf.py exited {result.returncode}:\n{result.stderr[-500:]}"
            )
    except Exception as exc:
        log_task_event(self.request.id, f"Blender production GLB failed: {exc}", "error")
        pl.step_error("export_glb_production", f"Blender production GLB failed: {exc}", exc)
        logger.error("generate_gltf_production_task Blender failed for cad %s: %s", cad_file_id, exc)
        raise self.retry(exc=exc, countdown=30)
    finally:
        # Clean up the high-quality temp geometry GLB (not needed after Blender export)
        try:
            prod_geom_glb.unlink(missing_ok=True)
        except Exception:
            pass

    log_task_event(self.request.id, f"Production GLB exported: {output_path.name}", "done")

    # --- 4. Store MediaAsset (upsert: update existing record to keep stable ID/URL) ---
    # Updating in-place (not DELETE+INSERT) preserves the existing asset UUID so that
    # any frontend page holding a stale download_url continues to resolve correctly.
    _eng2 = _ce(_sync_url)
    with _Session(_eng2) as _sess:
        _key = str(output_path)
        _prefix = str(app_settings.upload_dir).rstrip("/") + "/"
        if _key.startswith(_prefix):
            _key = _key[len(_prefix):]
        _file_size = output_path.stat().st_size if output_path.exists() else None

        existing = _sess.execute(
            _sel(MediaAsset).where(
                MediaAsset.cad_file_id == _uuid.UUID(cad_file_id),
                MediaAsset.asset_type == MediaAssetType.gltf_production,
            )
        ).scalars().first()

        if existing:
            existing.storage_key = _key
            existing.mime_type = "model/gltf-binary"
            existing.file_size_bytes = _file_size
            if product_id:
                existing.product_id = _uuid.UUID(product_id)
            _sess.commit()
            asset_id = str(existing.id)
        else:
            asset = MediaAsset(
                cad_file_id=_uuid.UUID(cad_file_id),
                product_id=_uuid.UUID(product_id) if product_id else None,
                asset_type=MediaAssetType.gltf_production,
                storage_key=_key,
                mime_type="model/gltf-binary",
                file_size_bytes=_file_size,
            )
            _sess.add(asset)
            _sess.commit()
            asset_id = str(asset.id)
    _eng2.dispose()

    pl.step_done("export_glb_production", result={"glb_path": str(output_path), "asset_id": asset_id})
    logger.info("generate_gltf_production_task: MediaAsset %s created for cad %s", asset_id, cad_file_id)
    return {"glb_path": str(output_path), "asset_id": asset_id}