NGWPC-10077 - Update NHF Schema

app/streamlit/helpers.py

@@ -57,6 +57,9 @@
         },
     },
     "virtual_nexus": {"marker_styling": folium.Marker(icon=folium.Icon(color="green", icon="filter"))},
+    "lakes": {
+        "marker_styling": folium.Marker(icon=folium.Icon(color="darkblue", prefix="fa", icon="sailboat"))
+    },
     "ras_xs": {
         "styling": {
             "color": "black",
@@ -297,11 +300,14 @@ def post_transient_success_msg(msg, length_s=1.5):
 def load_hf_gpkg(path):
     """Helper to load the subsetted GPKG and return a dictionary of GeoDataFrames for each layer."""
     hf_dict = {}
-    for t in list(nhf_layers.keys()):
-        if t == "reference_flowpaths" or t == "hydrolocations":
-            hf_dict[t] = pl.from_pandas(gpd.read_file(path, layer=t))
-        else:
-            hf_dict[t] = pl.from_pandas(gpd.read_file(path, layer=t).to_wkt())
+    layers = gpd.list_layers(path)
+    for _index, row in layers.iterrows():
+        layer_name, has_geom = row["name"], row["geometry_type"] is not None
+        if layer_name in nhf_layers.keys():
+            if has_geom:
+                hf_dict[layer_name] = pl.from_pandas(gpd.read_file(path, layer=layer_name).to_wkt())
+            else:
+                hf_dict[layer_name] = pl.from_pandas(gpd.read_file(path, layer=layer_name))
     return hf_dict
 
 
@@ -315,7 +321,7 @@ def display_nhf_schemas():
     )
     with image_expander:
         st.image(
-            "app/streamlit/resources/hydrofabric_diagram.png",
+            "app/streamlit/resources/nhf_schema.png",
             width="content",
             caption="Entity Relationship Diagram (ERD) for the Iceberg NGWPC Hydrofabric Data Catalog.",
         )

src/icefabric/hydrofabric/subset_nhf.py

@@ -221,13 +221,15 @@ def generate_subset_from_ids(
             "gages": ex.submit(source.load_filtered, "gages", "fp_id", flowpath_ids),
             "ref_fp": ex.submit(source.load_filtered, "reference_flowpaths", "div_id", flowpath_ids),
             "lakes": ex.submit(source.load_filtered, "lakes", "fp_id", flowpath_ids),
+            "nhd": ex.submit(source.load_filtered, "nhd", "ref_id", flowpath_ids),
         }
         subset_fp = f["fp"].result()
         subset_div = f["div"].result()
         subset_wb = f["wb"].result()
         subset_gages = f["gages"].result()
         subset_ref_fp = f["ref_fp"].result()
         subset_lakes = f["lakes"].result()
+        subset_nhd = f["nhd"].result()
 
     # Derive dependent IDs
     all_nex_ids = set(
@@ -293,6 +295,7 @@ def generate_subset_from_ids(
         "lakes": pl_to_gdf(subset_lakes, crs=crs) if len(subset_lakes) > 0 else subset_lakes.to_pandas(),
         "reference_flowpaths": subset_ref_fp.to_pandas(),
         "hydrolocations": subset_hydrolocations.to_pandas(),
+        "nhd": subset_nhd.to_pandas(),
     }
 
     if subset_file is not None:
@@ -315,7 +318,7 @@ def generate_subset_from_ids(
             if isinstance(df, gpd.GeoDataFrame) and len(df) > 0:
                 pyogrio.write_dataframe(df, subset_file, layer=name)
 
-        nonspatial_layers = ["reference_flowpaths", "hydrolocations"]
+        nonspatial_layers = ["reference_flowpaths", "hydrolocations", "nhd"]
         conn = sqlite3.connect(subset_file)
         for name in nonspatial_layers:
             logger.debug(f"  {name}: {len(output[name])} rows")

src/icefabric/schemas/iceberg_tables/__init__.py

@@ -1,10 +1,11 @@
 from .hydrofabric_update import (
+    NHD,
     Divides,
     Flowpaths,
     Gages,
     Hydrolocations,
+    Lakes,
     Nexus,
-    NHFLakes,
     ReferenceFlowpaths,
     VirtualFlowpaths,
     VirtualNexus,
@@ -21,5 +22,6 @@
     "virtual_flowpaths": VirtualFlowpaths,
     "virtual_nexus": VirtualNexus,
     "hydrolocations": Hydrolocations,
-    "lakes": NHFLakes,
+    "lakes": Lakes,
+    "nhd": NHD,
 }