Enhance the FIMbench query modules (#15)

* added new version distribution files

* updated the building footprint download with ArcGIS API

* updated PWB module with Hosted ArcGIS Feature Layer

* Release 0.1.58

Author: supathdhitalGEO

dist/fimeval-0.1.58-py3-none-any.whl

@@ -1,6 +1,6 @@
 [project]
 name = "fimeval"
-version = "0.1.57"
+version = "0.1.58"
 description = "A Framework for Automatic Evaluation of Flood Inundation Mapping Predictions Evaluation"
 readme = "README.md"
 requires-python = ">=3.10"

dist/fimeval-0.1.58.tar.gz

@@ -25,6 +25,7 @@
     _record_day,
     _record_hour_or_none,
     _pretty_date_for_print,
+    _ensure_local_gpkg,
 )
 
 # Preferred area CRSs for area calculations
@@ -300,15 +301,28 @@ def _aoi_context_str(
         end_date=end_date,
     )
 
+def _display_raster_name(rec: Dict[str, Any]) -> str:
+    tif_url = rec.get("tif_url")
+    if isinstance(tif_url, str) and tif_url.strip():
+        # drop querystring if any
+        tif_url = tif_url.split("?", 1)[0]
+        return os.path.basename(tif_url)
+
+    # fallback: last path token of id
+    rid = rec.get("id")
+    if isinstance(rid, str) and rid.strip():
+        return rid.strip().split("/")[-1] + ".tif"
+
+    return "NA"
 
 # Build a single printable block, optionally with overlap appended
 def _format_block_with_overlap(
     rec: Dict[str, Any], pct: Optional[float], km2: Optional[float]
 ) -> str:
-    tier = rec.get("tier") or rec.get("quality") or "Unknown"
+    tier = rec.get("tier") or rec.get("HWM") or rec.get("quality") or "Unknown"
     res = rec.get("resolution_m")
     res_txt = f"{res}m" if res is not None else "NA"
-    fname = rec.get("file_name") or "NA"
+    fname = _display_raster_name(rec)
 
     lines = [f"Data Tier: {tier}"]
 
@@ -404,20 +418,23 @@ def _gpkg_urls_from_record(rec: Dict[str, Any]) -> List[str]:
             out.append(u)
     return out
 
-
 def _read_benchmark_aoi_union_geom(rec: Dict[str, Any]) -> Optional[Polygon]:
-    # Read and union AOI geometries referenced by the record (kept permissive)
+    # Read and union AOI geometries referenced by the record
     urls = _gpkg_urls_from_record(rec)
     if not urls:
         return None
+
     geoms: List[Polygon] = []
     for uri in urls:
         try:
             storage_opts = _storage_options_for_uri(uri)
+
+            uri_to_read = _ensure_local_gpkg(uri)
+
             gdf = (
-                gpd.read_file(uri, storage_options=storage_opts)
+                gpd.read_file(uri_to_read, storage_options=storage_opts)
                 if storage_opts
-                else gpd.read_file(uri)
+                else gpd.read_file(uri_to_read)
             )
             if gdf.empty:
                 continue
@@ -429,8 +446,9 @@ def _read_benchmark_aoi_union_geom(rec: Dict[str, Any]) -> Optional[Polygon]:
             u = unary_union(gdf.geometry)
             if not u.is_empty:
                 geoms.append(u)
-        except Exception:
+        except Exception as e:
             continue
+
     if not geoms:
         return None
     uall = unary_union(geoms)

pyproject.toml

@@ -38,12 +38,72 @@ def s3_http_url(bucket: str, key: str) -> str:
 _YMDHMS_RE = re.compile(r"^\d{4}-\d{2}-\d{2}[ T]\d{2}:\d{2}(:\d{2})?$")
 
 
+#Support functions to ensute the geopackage file is local
+def _s3_bucket_key_from_http_url(url: str) -> Optional[tuple[str, str]]:
+    try:
+        u = urllib.parse.urlparse(url)
+        host = (u.netloc or "").lower()
+        path = (u.path or "").lstrip("/")
+        if not host or not path:
+            return None
+
+        if ".s3." in host or host.endswith(".s3.amazonaws.com"):
+            bucket = host.split(".s3", 1)[0]
+            key = path
+            return bucket, key
+
+        return None
+    except Exception:
+        return None
+
+
+def _ensure_local_gpkg(uri: str) -> str:
+    """
+    Ensure we can read a GPKG even when uri is an https S3 URL by caching locally.
+    Returns a path usable by geopandas.read_file().
+    """
+    if not isinstance(uri, str) or not uri.strip():
+        return uri
+
+    u = uri.strip()
+    if os.path.exists(u):
+        return u
+
+    # Cache https S3 gpkg locally
+    if u.lower().startswith("http") and ".amazonaws.com/" in u.lower() and u.lower().endswith(".gpkg"):
+        parsed = _s3_bucket_key_from_http_url(u.split("?", 1)[0])
+        if not parsed:
+            return u
+
+        bucket, key = parsed
+        cache_dir = os.path.join(os.path.expanduser("~"), ".fimeval_cache", "aoi_gpkg")
+        os.makedirs(cache_dir, exist_ok=True)
+
+        local = os.path.join(cache_dir, os.path.basename(key))
+        if not os.path.exists(local):
+            _download(bucket, key, local)
+        return local
+    return u
+
 def _normalize_user_dt(s: str) -> str:
     s = s.strip()
     s = s.replace("/", "-")
     s = re.sub(r"\s+", " ", s)
     return s
 
+def _display_raster_name(rec: Dict[str, Any]) -> str:
+    tif_url = rec.get("tif_url")
+    if isinstance(tif_url, str) and tif_url.strip():
+        # drop querystring if any
+        tif_url = tif_url.split("?", 1)[0]
+        return os.path.basename(tif_url)
+
+    # fallback: last path token of id
+    rid = rec.get("id")
+    if isinstance(rid, str) and rid.strip():
+        return rid.strip().split("/")[-1] + ".tif"
+
+    return "NA"
 
 def _to_date(s: str) -> dt.date:
     s = _normalize_user_dt(s)
@@ -186,7 +246,7 @@ def _return_period_text_local(r: Dict[str, Any]) -> str:
         tier = r.get("tier") or r.get("quality") or "Unknown"
         res = r.get("resolution_m")
         res_txt = f"{res}m" if res is not None else "NA"
-        fname = r.get("file_name") or "NA"
+        fname = _display_raster_name(r)
 
         # Build lines with Tier-aware event text
         lines = [f"Data Tier: {tier}"]

src/fimeval/BenchFIMQuery/access_benchfim.py

@@ -1,8 +1,8 @@
 import fimeval as fe
 
 # For testing boundary/raster inputs
-raster_path = "/Users/supath/Downloads/MSResearch/FIMpef/CodeUsage/SM_prediction/HUC11110203_AR/hf_RS_HUC11110203_AR_binary_BM.tif"  # ./paths/to/your/model_predicted_fim"
-boundary_path = "./paths/to/your/boundaryfile"
+# raster_path = "/Users/supath/Downloads/MSResearch/FIMpef/CodeUsage/SM_prediction/HUC11110203_AR/hf_RS_HUC11110203_AR_binary_BM.tif"  # ./paths/to/your/model_predicted_fim"
+boundary_path = "/Users/Supath/Downloads/HWM_10_0m_20250704_991013W300036N_BM.gpkg"
 
 
 # Benchmark FIM querying
@@ -39,15 +39,15 @@
 
 def test_benchmark_fimquery():
     response = fe.benchFIMquery(
-        raster_path=raster_path,
-        boundary_path=None,
-        huc8=None,  # Example HUC8 ID: "03020202"
+        # raster_path=raster_path,
+        boundary_path=boundary_path,
+        # huc8=None,  # Example HUC8 ID: "03020202"
         # event_date = "2017-05-01",
         # start_date = "2017-04-01",
         # end_date = "2017-05-01",
         # file_name = None,
         area=True,  # Default is false; if True, returns overlap stats
-        # download = False,
+        # download = True,
         # out_dir = None,
     )
     print(response)