@vespermcp/mcp-server 1.2.4 → 1.2.5

package/src/python/vesper/core/download_recipe.py

@@ -0,0 +1,104 @@
+from __future__ import annotations
+
+import json
+import re
+from dataclasses import dataclass, asdict
+from pathlib import Path
+from typing import Any, Dict, Optional
+
+
+DEFAULT_RECIPES_DIR = Path.home() / ".vesper" / "recipes"
+
+
+@dataclass
+class DownloadRecipe:
+    dataset_id: str
+    source: str
+    repo_id: str
+    image_column: Optional[str]
+    download_method: str
+    requires_auth: bool
+    estimated_asset_size_gb: float
+    total_images: int
+    fallback_strategy: list[str]
+
+
+def _safe_name(value: str) -> str:
+    return re.sub(r"[^a-zA-Z0-9._-]+", "_", value).strip("_") or "dataset"
+
+
+def build_download_recipe(dataset_info: Dict[str, Any]) -> Dict[str, Any]:
+    dataset_id = str(dataset_info.get("dataset_id") or dataset_info.get("id") or "")
+    source = str(dataset_info.get("source") or "unknown").lower()
+    repo_id = str(dataset_info.get("repo_id") or dataset_info.get("id") or dataset_id)
+
+    image_column = dataset_info.get("image_column")
+    if not image_column:
+        features = dataset_info.get("features") or {}
+        if isinstance(features, dict):
+            for key in features.keys():
+                lower = str(key).lower()
+                if lower in {"image", "images", "img", "img_path", "image_url", "url"}:
+                    image_column = key
+                    break
+
+    download_method = "url_list"
+    if source == "huggingface":
+        download_method = "hf_dataset_image_feature"
+    elif source == "kaggle":
+        download_method = "kaggle_archive"
+    elif source in {"dataworld", "openml"}:
+        download_method = "direct_file_scan"
+
+    requires_auth = bool(dataset_info.get("requires_auth", source in {"kaggle", "dataworld"}))
+
+    total_images = int(dataset_info.get("total_images") or dataset_info.get("total_examples") or 0)
+    if total_images <= 0:
+        total_images = 1000
+
+    estimated_asset_size_gb = round(float(dataset_info.get("estimated_asset_size_gb") or (total_images * 0.0004)), 3)
+
+    fallback_strategy = dataset_info.get("fallback_strategy") or [
+        "scan_archive_for_images",
+        "extract_url_column_and_download",
+        "export_metadata_only_with_actionable_error",
+    ]
+
+    recipe = DownloadRecipe(
+        dataset_id=dataset_id or repo_id,
+        source=source,
+        repo_id=repo_id,
+        image_column=image_column,
+        download_method=download_method,
+        requires_auth=requires_auth,
+        estimated_asset_size_gb=estimated_asset_size_gb,
+        total_images=total_images,
+        fallback_strategy=list(fallback_strategy),
+    )
+
+    return asdict(recipe)
+
+
+def save_recipe(recipe: Dict[str, Any], recipes_dir: Optional[str] = None) -> str:
+    root = Path(recipes_dir) if recipes_dir else DEFAULT_RECIPES_DIR
+    root.mkdir(parents=True, exist_ok=True)
+
+    dataset_id = str(recipe.get("dataset_id") or recipe.get("repo_id") or "dataset")
+    recipe_dir = root / _safe_name(dataset_id)
+    recipe_dir.mkdir(parents=True, exist_ok=True)
+
+    out_path = recipe_dir / "download_recipe.json"
+    out_path.write_text(json.dumps(recipe, indent=2, ensure_ascii=False), encoding="utf-8")
+    return str(out_path)
+
+
+def get_download_recipe(dataset_id: str, recipes_dir: Optional[str] = None) -> Optional[Dict[str, Any]]:
+    root = Path(recipes_dir) if recipes_dir else DEFAULT_RECIPES_DIR
+    path = root / _safe_name(dataset_id) / "download_recipe.json"
+    if not path.exists():
+        return None
+
+    try:
+        return json.loads(path.read_text(encoding="utf-8"))
+    except Exception:
+        return None