rashdf 0.4.0__tar.gz → 0.5.0__tar.gz

{rashdf-0.4.0 → rashdf-0.5.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: rashdf
-Version: 0.4.0
+Version: 0.5.0
 Summary: Read data from HEC-RAS HDF files.
 Project-URL: repository, https://github.com/fema-ffrd/rashdf
 Classifier: Development Status :: 4 - Beta
@@ -14,7 +14,7 @@ Classifier: Programming Language :: Python :: 3.12
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: h5py
-Requires-Dist: geopandas<0.15,>=0.14
+Requires-Dist: geopandas<2.0,>=1.0
 Requires-Dist: pyarrow
 Requires-Dist: xarray
 Provides-Extra: dev
@@ -22,6 +22,7 @@ Requires-Dist: pre-commit; extra == "dev"
 Requires-Dist: ruff; extra == "dev"
 Requires-Dist: pytest; extra == "dev"
 Requires-Dist: pytest-cov; extra == "dev"
+Requires-Dist: fiona; extra == "dev"
 Provides-Extra: docs
 Requires-Dist: sphinx; extra == "docs"
 Requires-Dist: numpydoc; extra == "docs"
@@ -76,8 +77,8 @@ Also, methods to extract certain HDF group attributes as dictionaries:
 ```python
 >>> from rashdf import RasPlanHdf
 >>> with RasPlanHdf("path/to/rasmodel/Muncie.p04.hdf") as plan_hdf:
->>> results_unsteady_summary = plan_hdf.get_results_unsteady_summary()
->>> results_unsteady_summary
+>>> results_unsteady_summary_attrs = plan_hdf.get_results_unsteady_summary_attrs()
+>>> results_unsteady_summary_attrs
 {'Computation Time DSS': datetime.timedelta(0),
 'Computation Time Total': datetime.timedelta(seconds=23),
 'Maximum WSEL Error': 0.0099277812987566,
@@ -101,9 +102,9 @@ CLI help:
 $ rashdf --help
 ```
 
-Print the output formats supported by Fiona:
+Print the output formats supported by pyorgio:
 ```
-$ rashdf --fiona-drivers
+$ rashdf --pyogrio-drivers
 ```
 
 Help for a specific subcommand:

{rashdf-0.4.0 → rashdf-0.5.0}/README.md

@@ -47,8 +47,8 @@ Also, methods to extract certain HDF group attributes as dictionaries:
 ```python
 >>> from rashdf import RasPlanHdf
 >>> with RasPlanHdf("path/to/rasmodel/Muncie.p04.hdf") as plan_hdf:
->>> results_unsteady_summary = plan_hdf.get_results_unsteady_summary()
->>> results_unsteady_summary
+>>> results_unsteady_summary_attrs = plan_hdf.get_results_unsteady_summary_attrs()
+>>> results_unsteady_summary_attrs
 {'Computation Time DSS': datetime.timedelta(0),
 'Computation Time Total': datetime.timedelta(seconds=23),
 'Maximum WSEL Error': 0.0099277812987566,
@@ -72,9 +72,9 @@ CLI help:
 $ rashdf --help
 ```
 
-Print the output formats supported by Fiona:
+Print the output formats supported by pyorgio:
 ```
-$ rashdf --fiona-drivers
+$ rashdf --pyogrio-drivers
 ```
 
 Help for a specific subcommand:

{rashdf-0.4.0 → rashdf-0.5.0}/pyproject.toml

@@ -12,11 +12,11 @@ classifiers = [
     "Programming Language :: Python :: 3.11",
     "Programming Language :: Python :: 3.12",
 ]
-version = "0.4.0"
-dependencies = ["h5py", "geopandas>=0.14,<0.15", "pyarrow", "xarray"]
+version = "0.5.0"
+dependencies = ["h5py", "geopandas>=1.0,<2.0", "pyarrow", "xarray"]
 
 [project.optional-dependencies]
-dev = ["pre-commit", "ruff", "pytest", "pytest-cov"]
+dev = ["pre-commit", "ruff", "pytest", "pytest-cov", "fiona"]
 docs = ["sphinx", "numpydoc", "sphinx_rtd_theme"]
 
 [project.urls]

{rashdf-0.4.0 → rashdf-0.5.0}/src/cli.py

@@ -3,7 +3,6 @@
 from rashdf import RasGeomHdf, RasPlanHdf
 from rashdf.utils import df_datetimes_to_str
 
-import fiona
 from geopandas import GeoDataFrame
 
 import argparse
@@ -23,6 +22,8 @@ COMMANDS = [
     "refinement_regions",
     "bc_lines",
     "breaklines",
+    "reference_lines",
+    "reference_points",
     "structures",
 ]
 
@@ -50,6 +51,20 @@ def docstring_to_help(docstring: Optional[str]) -> str:
     return help_text
 
 
+def pyogrio_supported_drivers() -> List[str]:
+    """Return a list of drivers supported by pyogrio for writing output files.
+
+    Returns
+    -------
+    list
+        A list of drivers supported by pyogrio for writing output files.
+    """
+    import pyogrio
+
+    drivers = pyogrio.list_drivers(write=True)
+    return sorted(drivers)
+
+
 def fiona_supported_drivers() -> List[str]:
     """Return a list of drivers supported by Fiona for writing output files.
 
@@ -58,18 +73,34 @@ def fiona_supported_drivers() -> List[str]:
     list
         A list of drivers supported by Fiona for writing output files.
     """
+    import fiona
+
     drivers = [d for d, s in fiona.supported_drivers.items() if "w" in s]
-    return drivers
+    return sorted(drivers)
 
 
 def parse_args(args: str) -> argparse.Namespace:
     """Parse command-line arguments."""
     parser = argparse.ArgumentParser(description="Extract data from HEC-RAS HDF files.")
     parser.add_argument(
-        "--fiona-drivers",
+        "--pyogrio-drivers",
         action="store_true",
-        help="List the drivers supported by Fiona for writing output files.",
+        help="List the drivers supported by pyogrio for writing output files.",
     )
+    fiona_installed = False
+    engines = ["pyogrio"]
+    try:
+        import fiona
+
+        fiona_installed = True
+        engines.append("fiona")
+        parser.add_argument(
+            "--fiona-drivers",
+            action="store_true",
+            help="List the drivers supported by Fiona for writing output files.",
+        )
+    except ImportError:
+        pass
     subparsers = parser.add_subparsers(help="Sub-command help")
     for command in COMMANDS:
         f = getattr(RasGeomHdf, command)
@@ -91,6 +122,13 @@ def parse_args(args: str) -> argparse.Namespace:
         output_group.add_argument(
             "--feather", action="store_true", help="Output as Feather."
         )
+        output_group.add_argument(
+            "--engine",
+            type=str,
+            choices=engines,
+            default="pyogrio",
+            help="Engine for writing output data.",
+        )
         subparser.add_argument(
             "--kwargs",
             type=str,
@@ -105,7 +143,11 @@ def parse_args(args: str) -> argparse.Namespace:
 
 def export(args: argparse.Namespace) -> Optional[str]:
     """Act on parsed arguments to extract data from HEC-RAS HDF files."""
-    if args.fiona_drivers:
+    if args.pyogrio_drivers:
+        for driver in pyogrio_supported_drivers():
+            print(driver)
+        return
+    if hasattr(args, "fiona_drivers") and args.fiona_drivers:
         for driver in fiona_supported_drivers():
             print(driver)
         return
@@ -138,6 +180,7 @@ def export(args: argparse.Namespace) -> Optional[str]:
                 ),
             )
             result = gdf.to_json(**kwargs)
+        print("No output file!")
         print(result)
         return result
     elif args.parquet:
@@ -153,7 +196,7 @@ def export(args: argparse.Namespace) -> Optional[str]:
         # convert any datetime columns to string.
         # TODO: besides Geopackage, which of the standard Fiona drivers allow datetime?
         gdf = df_datetimes_to_str(gdf)
-    gdf.to_file(args.output_file, **kwargs)
+    gdf.to_file(args.output_file, engine=args.engine, **kwargs)
 
 
 def main():

{rashdf-0.4.0 → rashdf-0.5.0}/src/rashdf/geom.py

@@ -1,12 +1,13 @@
 """HEC-RAS Geometry HDF class."""
 
-from typing import Dict, List, Optional
-
 import numpy as np
 import pandas as pd
 from geopandas import GeoDataFrame
 from pyproj import CRS
 from shapely import (
+    Geometry,
+    Polygon,
+    Point,
     LineString,
     MultiLineString,
     MultiPolygon,
@@ -15,6 +16,9 @@ from shapely import (
     polygonize_full,
 )
 
+from typing import Dict, List, Optional, Union
+
+
 from .base import RasHdf
 from .utils import (
     convert_ras_hdf_string,
@@ -24,12 +28,24 @@ from .utils import (
 )
 
 
+class RasGeomHdfError(Exception):
+    """HEC-RAS Plan HDF error class."""
+
+    pass
+
+
 class RasGeomHdf(RasHdf):
     """HEC-RAS Geometry HDF class."""
 
     GEOM_PATH = "Geometry"
     GEOM_STRUCTURES_PATH = f"{GEOM_PATH}/Structures"
     FLOW_AREA_2D_PATH = f"{GEOM_PATH}/2D Flow Areas"
+    BC_LINES_PATH = f"{GEOM_PATH}/Boundary Condition Lines"
+    BREAKLINES_PATH = f"{GEOM_PATH}/2D Flow Area Break Lines"
+    REFERENCE_LINES_PATH = f"{GEOM_PATH}/Reference Lines"
+    REFERENCE_POINTS_PATH = f"{GEOM_PATH}/Reference Points"
+    CROSS_SECTIONS = f"{GEOM_PATH}/Cross Sections"
+    RIVER_CENTERLINES = f"{GEOM_PATH}/River Centerlines"
 
     def __init__(self, name: str, **kwargs):
         """Open a HEC-RAS Geometry HDF file.
@@ -262,6 +278,38 @@ class RasGeomHdf(RasHdf):
 
         return d2_flow_area_attrs
 
+    def _get_polylines(
+        self,
+        path: str,
+        info_name: str = "Polyline Info",
+        parts_name: str = "Polyline Parts",
+        points_name: str = "Polyline Points",
+    ) -> List[Geometry]:
+        polyline_info_path = f"{path}/{info_name}"
+        polyline_parts_path = f"{path}/{parts_name}"
+        polyline_points_path = f"{path}/{points_name}"
+
+        polyline_info = self[polyline_info_path][()]
+        polyline_parts = self[polyline_parts_path][()]
+        polyline_points = self[polyline_points_path][()]
+
+        geoms = []
+        for pnt_start, pnt_cnt, part_start, part_cnt in polyline_info:
+            points = polyline_points[pnt_start : pnt_start + pnt_cnt]
+            if part_cnt == 1:
+                geoms.append(LineString(points))
+            else:
+                parts = polyline_parts[part_start : part_start + part_cnt]
+                geoms.append(
+                    MultiLineString(
+                        list(
+                            points[part_pnt_start : part_pnt_start + part_pnt_cnt]
+                            for part_pnt_start, part_pnt_cnt in parts
+                        )
+                    )
+                )
+        return geoms
+
     def bc_lines(self) -> GeoDataFrame:
         """Return 2D mesh area boundary condition lines.
 
@@ -270,35 +318,15 @@ class RasGeomHdf(RasHdf):
         GeoDataFrame
             A GeoDataFrame containing the 2D mesh area boundary condition lines if they exist.
         """
-        if "/Geometry/Boundary Condition Lines" not in self:
+        if self.BC_LINES_PATH not in self:
             return GeoDataFrame()
-        bc_line_data = self["/Geometry/Boundary Condition Lines"]
+        bc_line_data = self[self.BC_LINES_PATH]
         bc_line_ids = range(bc_line_data["Attributes"][()].shape[0])
         v_conv_str = np.vectorize(convert_ras_hdf_string)
         names = v_conv_str(bc_line_data["Attributes"][()]["Name"])
         mesh_names = v_conv_str(bc_line_data["Attributes"][()]["SA-2D"])
         types = v_conv_str(bc_line_data["Attributes"][()]["Type"])
-        geoms = list()
-        for pnt_start, pnt_cnt, part_start, part_cnt in bc_line_data["Polyline Info"][
-            ()
-        ]:
-            points = bc_line_data["Polyline Points"][()][
-                pnt_start : pnt_start + pnt_cnt
-            ]
-            if part_cnt == 1:
-                geoms.append(LineString(points))
-            else:
-                parts = bc_line_data["Polyline Parts"][()][
-                    part_start : part_start + part_cnt
-                ]
-                geoms.append(
-                    MultiLineString(
-                        list(
-                            points[part_pnt_start : part_pnt_start + part_pnt_cnt]
-                            for part_pnt_start, part_pnt_cnt in parts
-                        )
-                    )
-                )
+        geoms = self._get_polylines(self.BC_LINES_PATH)
         return GeoDataFrame(
             {
                 "bc_line_id": bc_line_ids,
@@ -319,34 +347,14 @@ class RasGeomHdf(RasHdf):
         GeoDataFrame
             A GeoDataFrame containing the 2D mesh area breaklines if they exist.
         """
-        if "/Geometry/2D Flow Area Break Lines" not in self:
+        if self.BREAKLINES_PATH not in self:
             return GeoDataFrame()
-        bl_line_data = self["/Geometry/2D Flow Area Break Lines"]
+        bl_line_data = self[self.BREAKLINES_PATH]
         bl_line_ids = range(bl_line_data["Attributes"][()].shape[0])
         names = np.vectorize(convert_ras_hdf_string)(
             bl_line_data["Attributes"][()]["Name"]
         )
-        geoms = list()
-        for pnt_start, pnt_cnt, part_start, part_cnt in bl_line_data["Polyline Info"][
-            ()
-        ]:
-            points = bl_line_data["Polyline Points"][()][
-                pnt_start : pnt_start + pnt_cnt
-            ]
-            if part_cnt == 1:
-                geoms.append(LineString(points))
-            else:
-                parts = bl_line_data["Polyline Parts"][()][
-                    part_start : part_start + part_cnt
-                ]
-                geoms.append(
-                    MultiLineString(
-                        list(
-                            points[part_pnt_start : part_pnt_start + part_pnt_cnt]
-                            for part_pnt_start, part_pnt_cnt in parts
-                        )
-                    )
-                )
+        geoms = self._get_polylines(self.BREAKLINES_PATH)
         return GeoDataFrame(
             {"bl_id": bl_line_ids, "name": names, "geometry": geoms},
             geometry="geometry",
@@ -400,36 +408,21 @@ class RasGeomHdf(RasHdf):
         GeoDataFrame
             A GeoDataFrame containing the model structures if they exist.
         """
-        if "/Geometry/Structures" not in self:
+        if self.GEOM_STRUCTURES_PATH not in self:
             return GeoDataFrame()
-        struct_data = self["/Geometry/Structures"]
+        struct_data = self[self.GEOM_STRUCTURES_PATH]
         v_conv_val = np.vectorize(convert_ras_hdf_value)
         sd_attrs = struct_data["Attributes"][()]
         struct_dict = {"struct_id": range(sd_attrs.shape[0])}
         struct_dict.update(
             {name: v_conv_val(sd_attrs[name]) for name in sd_attrs.dtype.names}
         )
-        geoms = list()
-        for pnt_start, pnt_cnt, part_start, part_cnt in struct_data["Centerline Info"][
-            ()
-        ]:
-            points = struct_data["Centerline Points"][()][
-                pnt_start : pnt_start + pnt_cnt
-            ]
-            if part_cnt == 1:
-                geoms.append(LineString(points))
-            else:
-                parts = struct_data["Centerline Parts"][()][
-                    part_start : part_start + part_cnt
-                ]
-                geoms.append(
-                    MultiLineString(
-                        list(
-                            points[part_pnt_start : part_pnt_start + part_pnt_cnt]
-                            for part_pnt_start, part_pnt_cnt in parts
-                        )
-                    )
-                )
+        geoms = self._get_polylines(
+            self.GEOM_STRUCTURES_PATH,
+            info_name="Centerline Info",
+            parts_name="Centerline Parts",
+            points_name="Centerline Points",
+        )
         struct_gdf = GeoDataFrame(
             struct_dict,
             geometry=geoms,
@@ -447,11 +440,153 @@ class RasGeomHdf(RasHdf):
     def ic_points(self) -> GeoDataFrame:  # noqa D102
         raise NotImplementedError
 
-    def reference_lines(self) -> GeoDataFrame:  # noqa D102
-        raise NotImplementedError
+    def _reference_lines_points_names(
+        self, reftype: str = "lines", mesh_name: Optional[str] = None
+    ) -> Union[Dict[str, List[str]], List[str]]:
+        """Return reference line names.
 
-    def reference_points(self) -> GeoDataFrame:  # noqa D102
-        raise NotImplementedError
+        If a mesh name is provided, return a list of the reference line names for that mesh area.
+        If no mesh name is provided, return a dictionary of mesh names and their reference line names.
+
+        Parameters
+        ----------
+        mesh_name : str, optional
+            The name of the mesh area for which to return reference line names.
+
+        Returns
+        -------
+        Union[Dict[str, List[str]], List[str]]
+            A dictionary of mesh names and their reference line names if mesh_name is None.
+            A list of reference line names for the specified mesh area if mesh_name is not None.
+        """
+        if reftype == "lines":
+            path = self.REFERENCE_LINES_PATH
+            sa_2d_field = "SA-2D"
+        elif reftype == "points":
+            path = self.REFERENCE_POINTS_PATH
+            sa_2d_field = "SA/2D"
+        else:
+            raise RasGeomHdfError(
+                f"Invalid reference type: {reftype} -- must be 'lines' or 'points'."
+            )
+        attributes_path = f"{path}/Attributes"
+        if mesh_name is None and attributes_path not in self:
+            return {m: [] for m in self.mesh_area_names()}
+        if mesh_name is not None and attributes_path not in self:
+            return []
+        attributes = self[attributes_path][()]
+        v_conv_str = np.vectorize(convert_ras_hdf_string)
+        names = np.vectorize(convert_ras_hdf_string)(attributes["Name"])
+        if mesh_name is not None:
+            return names[v_conv_str(attributes[sa_2d_field]) == mesh_name].tolist()
+        mesh_names = np.vectorize(convert_ras_hdf_string)(attributes[sa_2d_field])
+        return {m: names[mesh_names == m].tolist() for m in np.unique(mesh_names)}
+
+    def reference_lines_names(
+        self, mesh_name: Optional[str] = None
+    ) -> Union[Dict[str, List[str]], List[str]]:
+        """Return reference line names.
+
+        If a mesh name is provided, return a list of the reference line names for that mesh area.
+        If no mesh name is provided, return a dictionary of mesh names and their reference line names.
+
+        Parameters
+        ----------
+        mesh_name : str, optional
+            The name of the mesh area for which to return reference line names.
+
+        Returns
+        -------
+        Union[Dict[str, List[str]], List[str]]
+            A dictionary of mesh names and their reference line names if mesh_name is None.
+            A list of reference line names for the specified mesh area if mesh_name is not None.
+        """
+        return self._reference_lines_points_names("lines", mesh_name)
+
+    def reference_points_names(
+        self, mesh_name: Optional[str] = None
+    ) -> Union[Dict[str, List[str]], List[str]]:
+        """Return reference point names.
+
+        If a mesh name is provided, return a list of the reference point names for that mesh area.
+        If no mesh name is provided, return a dictionary of mesh names and their reference point names.
+
+        Parameters
+        ----------
+        mesh_name : str, optional
+            The name of the mesh area for which to return reference point names.
+
+        Returns
+        -------
+        Union[Dict[str, List[str]], List[str]]
+            A dictionary of mesh names and their reference point names if mesh_name is None.
+            A list of reference point names for the specified mesh area if mesh_name is not None.
+        """
+        return self._reference_lines_points_names("points", mesh_name)
+
+    def reference_lines(self) -> GeoDataFrame:
+        """Return the reference lines geometry and attributes.
+
+        Returns
+        -------
+        GeoDataFrame
+            A GeoDataFrame containing the reference lines if they exist.
+        """
+        attributes_path = f"{self.REFERENCE_LINES_PATH}/Attributes"
+        if attributes_path not in self:
+            return GeoDataFrame()
+        attributes = self[attributes_path][()]
+        refline_ids = range(attributes.shape[0])
+        v_conv_str = np.vectorize(convert_ras_hdf_string)
+        names = v_conv_str(attributes["Name"])
+        mesh_names = v_conv_str(attributes["SA-2D"])
+        try:
+            types = v_conv_str(attributes["Type"])
+        except ValueError:
+            # "Type" field doesn't exist -- observed in some RAS HDF files
+            types = np.array([""] * attributes.shape[0])
+        geoms = self._get_polylines(self.REFERENCE_LINES_PATH)
+        return GeoDataFrame(
+            {
+                "refln_id": refline_ids,
+                "refln_name": names,
+                "mesh_name": mesh_names,
+                "type": types,
+                "geometry": geoms,
+            },
+            geometry="geometry",
+            crs=self.projection(),
+        )
+
+    def reference_points(self) -> GeoDataFrame:
+        """Return the reference points geometry and attributes.
+
+        Returns
+        -------
+        GeoDataFrame
+            A GeoDataFrame containing the reference points if they exist.
+        """
+        attributes_path = f"{self.REFERENCE_POINTS_PATH}/Attributes"
+        if attributes_path not in self:
+            return GeoDataFrame()
+        ref_points_group = self[self.REFERENCE_POINTS_PATH]
+        attributes = ref_points_group["Attributes"][:]
+        v_conv_str = np.vectorize(convert_ras_hdf_string)
+        names = v_conv_str(attributes["Name"])
+        mesh_names = v_conv_str(attributes["SA/2D"])
+        cell_id = attributes["Cell Index"]
+        points = ref_points_group["Points"][()]
+        return GeoDataFrame(
+            {
+                "refpt_id": range(attributes.shape[0]),
+                "refpt_name": names,
+                "mesh_name": mesh_names,
+                "cell_id": cell_id,
+                "geometry": list(map(Point, points)),
+            },
+            geometry="geometry",
+            crs=self.projection(),
+        )
 
     def pump_stations(self) -> GeoDataFrame:  # noqa D102
         raise NotImplementedError
@@ -473,33 +608,17 @@ class RasGeomHdf(RasHdf):
         GeoDataFrame
             A GeoDataFrame containing the model 1D cross sections if they exist.
         """
-        if "/Geometry/Cross Sections" not in self:
+        if self.CROSS_SECTIONS not in self:
             return GeoDataFrame()
 
-        xs_data = self["/Geometry/Cross Sections"]
+        xs_data = self[self.CROSS_SECTIONS]
         v_conv_val = np.vectorize(convert_ras_hdf_value)
         xs_attrs = xs_data["Attributes"][()]
         xs_dict = {"xs_id": range(xs_attrs.shape[0])}
         xs_dict.update(
             {name: v_conv_val(xs_attrs[name]) for name in xs_attrs.dtype.names}
         )
-        geoms = list()
-        for pnt_start, pnt_cnt, part_start, part_cnt in xs_data["Polyline Info"][()]:
-            points = xs_data["Polyline Points"][()][pnt_start : pnt_start + pnt_cnt]
-            if part_cnt == 1:
-                geoms.append(LineString(points))
-            else:
-                parts = xs_data["Polyline Parts"][()][
-                    part_start : part_start + part_cnt
-                ]
-                geoms.append(
-                    MultiLineString(
-                        list(
-                            points[part_pnt_start : part_pnt_start + part_pnt_cnt]
-                            for part_pnt_start, part_pnt_cnt in parts
-                        )
-                    )
-                )
+        geoms = self._get_polylines(self.CROSS_SECTIONS)
         xs_gdf = GeoDataFrame(
             xs_dict,
             geometry=geoms,
@@ -519,10 +638,10 @@ class RasGeomHdf(RasHdf):
         GeoDataFrame
             A GeoDataFrame containing the model 1D river reach lines if they exist.
         """
-        if "/Geometry/River Centerlines" not in self:
+        if self.RIVER_CENTERLINES not in self:
             return GeoDataFrame()
 
-        river_data = self["/Geometry/River Centerlines"]
+        river_data = self[self.RIVER_CENTERLINES]
         v_conv_val = np.vectorize(convert_ras_hdf_value)
         river_attrs = river_data["Attributes"][()]
         river_dict = {"river_id": range(river_attrs.shape[0])}
@@ -530,22 +649,7 @@ class RasGeomHdf(RasHdf):
             {name: v_conv_val(river_attrs[name]) for name in river_attrs.dtype.names}
         )
         geoms = list()
-        for pnt_start, pnt_cnt, part_start, part_cnt in river_data["Polyline Info"][()]:
-            points = river_data["Polyline Points"][()][pnt_start : pnt_start + pnt_cnt]
-            if part_cnt == 1:
-                geoms.append(LineString(points))
-            else:
-                parts = river_data["Polyline Parts"][()][
-                    part_start : part_start + part_cnt
-                ]
-                geoms.append(
-                    MultiLineString(
-                        list(
-                            points[part_pnt_start : part_pnt_start + part_pnt_cnt]
-                            for part_pnt_start, part_pnt_cnt in parts
-                        )
-                    )
-                )
+        geoms = self._get_polylines(self.RIVER_CENTERLINES)
         river_gdf = GeoDataFrame(
             river_dict,
             geometry=geoms,

{rashdf-0.4.0 → rashdf-0.5.0}/src/rashdf/plan.py

@@ -163,6 +163,8 @@ class RasPlanHdf(RasGeomHdf):
         f"{BASE_OUTPUT_PATH}/Summary Output/2D Flow Areas"
     )
     UNSTEADY_TIME_SERIES_PATH = f"{BASE_OUTPUT_PATH}/Unsteady Time Series"
+    REFERENCE_LINES_OUTPUT_PATH = f"{UNSTEADY_TIME_SERIES_PATH}/Reference Lines"
+    REFERENCE_POINTS_OUTPUT_PATH = f"{UNSTEADY_TIME_SERIES_PATH}/Reference Points"
 
     RESULTS_STEADY_PATH = "Results/Steady"
     BASE_STEADY_PATH = f"{RESULTS_STEADY_PATH}/Output/Output Blocks/Base Output"
@@ -921,6 +923,214 @@ class RasPlanHdf(RasGeomHdf):
         ds = self._mesh_timeseries_outputs(mesh_name, TIME_SERIES_OUTPUT_VARS_FACES)
         return ds
 
+    def reference_timeseries_output(self, reftype: str = "lines") -> xr.Dataset:
+        """Return timeseries output data for reference lines or points from a HEC-RAS HDF plan file.
+
+        Parameters
+        ----------
+        reftype : str, optional
+            The type of reference data to retrieve. Must be either "lines" or "points".
+            (default: "lines")
+
+        Returns
+        -------
+        xr.Dataset
+            An xarray Dataset with reference line timeseries data.
+        """
+        if reftype == "lines":
+            output_path = self.REFERENCE_LINES_OUTPUT_PATH
+            abbrev = "refln"
+        elif reftype == "points":
+            output_path = self.REFERENCE_POINTS_OUTPUT_PATH
+            abbrev = "refpt"
+        else:
+            raise ValueError('reftype must be either "lines" or "points".')
+        reference_group = self.get(output_path)
+        if reference_group is None:
+            raise RasPlanHdfError(
+                f"Could not find HDF group at path '{output_path}'."
+                f" Does the Plan HDF file contain reference {reftype[:-1]} output data?"
+            )
+        reference_names = reference_group["Name"][:]
+        names = []
+        mesh_areas = []
+        for s in reference_names:
+            name, mesh_area = s.decode("utf-8").split("|")
+            names.append(name)
+            mesh_areas.append(mesh_area)
+
+        times = self.unsteady_datetimes()
+
+        das = {}
+        for var in ["Flow", "Velocity", "Water Surface"]:
+            group = reference_group.get(var)
+            if group is None:
+                continue
+            try:
+                import dask.array as da
+
+                # TODO: user-specified chunks?
+                values = da.from_array(group, chunks=group.chunks)
+            except ImportError:
+                values = group[:]
+            units = group.attrs["Units"].decode("utf-8")
+            da = xr.DataArray(
+                values,
+                name=var,
+                dims=["time", f"{abbrev}_id"],
+                coords={
+                    "time": times,
+                    f"{abbrev}_id": range(values.shape[1]),
+                    f"{abbrev}_name": (f"{abbrev}_id", names),
+                    "mesh_name": (f"{abbrev}_id", mesh_areas),
+                },
+                attrs={"Units": units},
+            )
+            das[var] = da
+        return xr.Dataset(das)
+
+    def reference_lines_timeseries_output(self) -> xr.Dataset:
+        """Return timeseries output data for reference lines from a HEC-RAS HDF plan file.
+
+        Returns
+        -------
+        xr.Dataset
+            An xarray Dataset with timeseries output data for reference lines.
+        """
+        return self.reference_timeseries_output(reftype="lines")
+
+    def reference_points_timeseries_output(self) -> xr.Dataset:
+        """Return timeseries output data for reference points from a HEC-RAS HDF plan file.
+
+        Returns
+        -------
+        xr.Dataset
+            An xarray Dataset with timeseries output data for reference points.
+        """
+        return self.reference_timeseries_output(reftype="points")
+
+    def reference_summary_output(self, reftype: str = "lines") -> DataFrame:
+        """Return summary output data for reference lines or points from a HEC-RAS HDF plan file.
+
+        Returns
+        -------
+        DataFrame
+            A DataFrame with reference line summary output data.
+        """
+        if reftype == "lines":
+            abbrev = "refln"
+        elif reftype == "points":
+            abbrev = "refpt"
+        else:
+            raise ValueError('reftype must be either "lines" or "points".')
+        ds = self.reference_timeseries_output(reftype=reftype)
+        result = {
+            f"{abbrev}_id": ds[f"{abbrev}_id"],
+            f"{abbrev}_name": ds[f"{abbrev}_name"],
+            "mesh_name": ds.mesh_name,
+        }
+        vars = {
+            "Flow": "q",
+            "Water Surface": "ws",
+            "Velocity": "v",
+        }
+        for var, abbrev in vars.items():
+            if var not in ds:
+                continue
+            max_var = ds[var].max(dim="time")
+            max_time = ds[var].time[ds[var].argmax(dim="time")]
+            min_var = ds[var].min(dim="time")
+            min_time = ds[var].time[ds[var].argmin(dim="time")]
+            result[f"max_{abbrev}"] = max_var
+            result[f"max_{abbrev}_time"] = max_time
+            result[f"min_{abbrev}"] = min_var
+            result[f"min_{abbrev}_time"] = min_time
+        return DataFrame(result)
+
+    def _reference_lines_points(
+        self,
+        reftype: str = "lines",
+        include_output: bool = True,
+        datetime_to_str: bool = False,
+    ) -> GeoDataFrame:
+        if reftype == "lines":
+            abbrev = "refln"
+            gdf = super().reference_lines()
+        elif reftype == "points":
+            abbrev = "refpt"
+            gdf = super().reference_points()
+        else:
+            raise ValueError('reftype must be either "lines" or "points".')
+        if include_output is False:
+            return gdf
+        summary_output = self.reference_summary_output(reftype=reftype)
+        gdf = gdf.merge(
+            summary_output,
+            on=[f"{abbrev}_id", f"{abbrev}_name", "mesh_name"],
+            how="left",
+        )
+        if datetime_to_str:
+            gdf = df_datetimes_to_str(gdf)
+        return gdf
+
+    def reference_lines(
+        self, include_output: bool = True, datetime_to_str: bool = False
+    ) -> GeoDataFrame:
+        """Return the reference lines from a HEC-RAS HDF plan file.
+
+        Includes summary output data for each reference line:
+        - Maximum flow & time (max_q, max_q_time)
+        - Minimum flow & time (min_q, min_q_time)
+        - Maximum water surface elevation & time (max_ws, max_ws_time)
+        - Minimum water surface elevation & time (min_ws, min_ws_time)
+
+        Parameters
+        ----------
+        include_output : bool, optional
+            If True, include summary output data in the GeoDataFrame. (default: True)
+        datetime_to_str : bool, optional
+            If True, convert datetime columns to strings. (default: False)
+
+        Returns
+        -------
+        GeoDataFrame
+            A GeoDataFrame with reference line geometry and summary output data.
+        """
+        return self._reference_lines_points(
+            reftype="lines",
+            include_output=include_output,
+            datetime_to_str=datetime_to_str,
+        )
+
+    def reference_points(
+        self, include_output: bool = True, datetime_to_str: bool = False
+    ) -> GeoDataFrame:
+        """Return the reference points from a HEC-RAS HDF plan file.
+
+        Parameters
+        ----------
+        include_output : bool, optional
+            If True, include summary output data in the GeoDataFrame. (default: True)
+        datetime_to_str : bool, optional
+            If True, convert datetime columns to strings. (default: False)
+
+        Includes summary output data for each reference point:
+        - Maximum flow & time (max_q, max_q_time)
+        - Minimum flow & time (min_q, min_q_time)
+        - Maximum water surface elevation & time (max_ws, max_ws_time)
+        - Minimum water surface elevation & time (min_ws, min_ws_time)
+
+        Returns
+        -------
+        GeoDataFrame
+            A GeoDataFrame with reference point geometry and summary output data.
+        """
+        return self._reference_lines_points(
+            reftype="points",
+            include_output=include_output,
+            datetime_to_str=datetime_to_str,
+        )
+
     def get_plan_info_attrs(self) -> Dict:
         """Return plan information attributes from a HEC-RAS HDF plan file.
 

{rashdf-0.4.0 → rashdf-0.5.0}/src/rashdf.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: rashdf
-Version: 0.4.0
+Version: 0.5.0
 Summary: Read data from HEC-RAS HDF files.
 Project-URL: repository, https://github.com/fema-ffrd/rashdf
 Classifier: Development Status :: 4 - Beta
@@ -14,7 +14,7 @@ Classifier: Programming Language :: Python :: 3.12
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: h5py
-Requires-Dist: geopandas<0.15,>=0.14
+Requires-Dist: geopandas<2.0,>=1.0
 Requires-Dist: pyarrow
 Requires-Dist: xarray
 Provides-Extra: dev
@@ -22,6 +22,7 @@ Requires-Dist: pre-commit; extra == "dev"
 Requires-Dist: ruff; extra == "dev"
 Requires-Dist: pytest; extra == "dev"
 Requires-Dist: pytest-cov; extra == "dev"
+Requires-Dist: fiona; extra == "dev"
 Provides-Extra: docs
 Requires-Dist: sphinx; extra == "docs"
 Requires-Dist: numpydoc; extra == "docs"
@@ -76,8 +77,8 @@ Also, methods to extract certain HDF group attributes as dictionaries:
 ```python
 >>> from rashdf import RasPlanHdf
 >>> with RasPlanHdf("path/to/rasmodel/Muncie.p04.hdf") as plan_hdf:
->>> results_unsteady_summary = plan_hdf.get_results_unsteady_summary()
->>> results_unsteady_summary
+>>> results_unsteady_summary_attrs = plan_hdf.get_results_unsteady_summary_attrs()
+>>> results_unsteady_summary_attrs
 {'Computation Time DSS': datetime.timedelta(0),
 'Computation Time Total': datetime.timedelta(seconds=23),
 'Maximum WSEL Error': 0.0099277812987566,
@@ -101,9 +102,9 @@ CLI help:
 $ rashdf --help
 ```
 
-Print the output formats supported by Fiona:
+Print the output formats supported by pyorgio:
 ```
-$ rashdf --fiona-drivers
+$ rashdf --pyogrio-drivers
 ```
 
 Help for a specific subcommand:

{rashdf-0.4.0 → rashdf-0.5.0}/src/rashdf.egg-info/requires.txt

@@ -1,5 +1,5 @@
 h5py
-geopandas<0.15,>=0.14
+geopandas<2.0,>=1.0
 pyarrow
 xarray
 
@@ -8,6 +8,7 @@ pre-commit
 ruff
 pytest
 pytest-cov
+fiona
 
 [docs]
 sphinx

{rashdf-0.4.0 → rashdf-0.5.0}/tests/test_cli.py

@@ -1,8 +1,16 @@
-from src.cli import parse_args, export, docstring_to_help, fiona_supported_drivers
+from src.cli import (
+    parse_args,
+    export,
+    docstring_to_help,
+    fiona_supported_drivers,
+    pyogrio_supported_drivers,
+)
 
 import geopandas as gpd
 from pyproj import CRS
+import pytest
 
+import builtins
 import json
 from pathlib import Path
 
@@ -30,6 +38,15 @@ def test_fiona_supported_drivers():
     assert "ESRI Shapefile" in drivers
     assert "GeoJSON" in drivers
     assert "GPKG" in drivers
+    assert "MBTiles" not in drivers
+
+
+def test_pyogrio_supported_drivers():
+    drivers = pyogrio_supported_drivers()
+    assert "ESRI Shapefile" in drivers
+    assert "GeoJSON" in drivers
+    assert "GPKG" in drivers
+    assert "MBTiles" in drivers
 
 
 def test_parse_args():
@@ -114,3 +131,40 @@ def test_export_plan_hdf():
     exported = json.loads(export(args))
     gdf = gpd.GeoDataFrame.from_features(exported)
     assert len(gdf) == 4425
+
+
+def test_fiona_missing(monkeypatch):
+    # Test behavior when fiona isn't installed
+
+    def mock_import(name, globals=None, locals=None, fromlist=(), level=0):
+        if name == "fiona":
+            raise ImportError("No module named 'fiona'")
+        return real_import(name, globals, locals, fromlist, level)
+
+    real_import = builtins.__import__
+
+    # Replace the built-in __import__ function with our mock
+    monkeypatch.setattr(builtins, "__import__", mock_import)
+
+    # Verify that the --fiona-drivers argument is not available
+    # when fiona is not installed
+    args = parse_args(["structures", "fake_file.hdf"])
+    assert not hasattr(args, "fiona_drivers")
+
+
+def test_print_pyogrio_supported_drivers(capfd):
+    export(parse_args(["--pyogrio-drivers"]))
+    captured = capfd.readouterr()
+    assert "ESRI Shapefile" in captured.out
+    assert "GeoJSON" in captured.out
+    assert "GPKG" in captured.out
+    assert "MBTiles" in captured.out
+
+
+def test_print_fiona_supported_drivers(capfd):
+    export(parse_args(["--fiona-drivers"]))
+    captured = capfd.readouterr()
+    assert "ESRI Shapefile" in captured.out
+    assert "GeoJSON" in captured.out
+    assert "GPKG" in captured.out
+    assert "MBTiles" not in captured.out

{rashdf-0.4.0 → rashdf-0.5.0}/tests/test_geom.py

@@ -10,6 +10,7 @@ MUNCIE_G05 = TEST_DATA / "ras/Muncie.g05.hdf"
 COAL_G01 = TEST_DATA / "ras/Coal.g01.hdf"
 BAXTER_P01 = TEST_DATA / "ras_1d/Baxter.p01.hdf"
 TEST_JSON = TEST_DATA / "json"
+BALD_EAGLE_P18_REF = TEST_DATA / "ras/BaldEagleDamBrk.reflines-refpts.p18.hdf"
 
 TEST_ATTRS = {"test_attribute1": "test_str1", "test_attribute2": 500}
 
@@ -119,6 +120,35 @@ def test_structs():
         assert _gdf_matches_json(ghdf.structures(datetime_to_str=True), structs_json)
 
 
+def test_reference_lines_names():
+    with RasGeomHdf(BALD_EAGLE_P18_REF) as geom_hdf:
+        assert geom_hdf.reference_lines_names() == {
+            "BaldEagleCr": [
+                "Reference Line 1",
+                "Reference Line 2",
+                "Reference Line 3",
+                "Reference Line 4",
+            ]
+        }
+        assert geom_hdf.reference_lines_names("Upper 2D Area") == []
+
+
+def test_reference_points_names():
+    with RasGeomHdf(BALD_EAGLE_P18_REF) as geom_hdf:
+        assert geom_hdf.reference_points_names() == {
+            "Upper 2D Area": [
+                "Reference Point 1",
+            ],
+            "BaldEagleCr": [
+                "Reference Point 2",
+                "Reference Point 3",
+            ],
+        }
+        assert geom_hdf.reference_points_names("Upper 2D Area") == [
+            "Reference Point 1",
+        ]
+
+
 def test_structs_not_found():
     with RasGeomHdf(COAL_G01) as ghdf:
         assert (ghdf.structures(), None)

{rashdf-0.4.0 → rashdf-0.5.0}/tests/test_plan.py

@@ -25,6 +25,7 @@ TEST_CSV = TEST_DATA / "csv"
 TEST_ATTRS = {"test_attribute1": "test_str1", "test_attribute2": 500}
 BALD_EAGLE_P18 = TEST_DATA / "ras/BaldEagleDamBrk.p18.hdf"
 BALD_EAGLE_P18_TIMESERIES = TEST_DATA / "ras/BaldEagleDamBrk.p18.timeseries.hdf"
+BALD_EAGLE_P18_REF = TEST_DATA / "ras/BaldEagleDamBrk.reflines-refpts.p18.hdf"
 MUNCIE_G05 = TEST_DATA / "ras/Muncie.g05.hdf"
 COAL_G01 = TEST_DATA / "ras/Coal.g01.hdf"
 BAXTER_P01 = TEST_DATA / "ras_1d/Baxter.p01.hdf"
@@ -143,7 +144,7 @@ def test_mesh_cell_points_with_output(tmp_path):
     )
     temp_points = tmp_path / "temp-bald-eagle-mesh-cell-points.geojson"
     gdf = gdf.to_crs(4326)
-    gdf.to_file(temp_points)
+    gdf.to_file(temp_points, engine="fiona")
     valid = get_sha1_hash(TEST_JSON / "bald-eagle-mesh-cell-points.geojson")
     test = get_sha1_hash(temp_points)
     assert valid == test
@@ -160,7 +161,7 @@ def test_mesh_cell_polygons_with_output(tmp_path):
         ],
     )
     temp_polygons = tmp_path / "temp-bald-eagle-mesh-cell-polygons.geojson"
-    gdf.to_crs(4326).to_file(temp_polygons)
+    gdf.to_crs(4326).to_file(temp_polygons, engine="fiona")
     valid = get_sha1_hash(TEST_JSON / "bald-eagle-mesh-cell-polygons.geojson")
     test = get_sha1_hash(temp_polygons)
     assert valid == test
@@ -176,7 +177,7 @@ def test_mesh_cell_faces_with_output(tmp_path):
         ],
     )
     temp_faces = tmp_path / "temp-bald-eagle-mesh-cell-faces.geojson"
-    gdf.to_crs(4326).to_file(temp_faces)
+    gdf.to_crs(4326).to_file(temp_faces, engine="fiona")
     valid = get_sha1_hash(TEST_JSON / "bald-eagle-mesh-cell-faces.geojson")
     test = get_sha1_hash(temp_faces)
     assert valid == test
@@ -266,6 +267,84 @@ def test_mesh_timeseries_output_faces():
         assert_frame_equal(df, valid_df)
 
 
+def test_reference_lines(tmp_path: Path):
+    plan_hdf = RasPlanHdf(BALD_EAGLE_P18_REF)
+    gdf = plan_hdf.reference_lines(datetime_to_str=True)
+    temp_lines = tmp_path / "temp-bald-eagle-reference-lines.geojson"
+    gdf.to_crs(4326).to_file(temp_lines, engine="fiona")
+    with open(TEST_JSON / "bald-eagle-reflines.geojson") as f:
+        valid_lines = f.read()
+        with open(temp_lines) as f:
+            test_lines = f.read()
+            assert valid_lines == test_lines
+
+
+def test_reference_lines_timeseries(tmp_path: Path):
+    plan_hdf = RasPlanHdf(BALD_EAGLE_P18_REF)
+    ds = plan_hdf.reference_lines_timeseries_output()
+    assert "time" in ds.coords
+    assert "refln_id" in ds.coords
+    assert "refln_name" in ds.coords
+    assert "mesh_name" in ds.coords
+    assert "Water Surface" in ds.variables
+    assert "Flow" in ds.variables
+
+    ws = ds["Water Surface"]
+    assert ws.shape == (37, 4)
+    assert ws.attrs["Units"] == "ft"
+    q = ds["Flow"]
+    assert q.shape == (37, 4)
+    assert q.attrs["Units"] == "cfs"
+
+    df = ds.sel(refln_id=2).to_dataframe()
+    valid_df = pd.read_csv(
+        TEST_CSV / "BaldEagleDamBrk.reflines.2.csv",
+        index_col="time",
+        parse_dates=True,
+        dtype={"Water Surface": np.float32, "Flow": np.float32},
+    )
+    assert_frame_equal(df, valid_df)
+
+
+def test_reference_points(tmp_path: Path):
+    plan_hdf = RasPlanHdf(BALD_EAGLE_P18_REF)
+    gdf = plan_hdf.reference_points(datetime_to_str=True)
+    temp_lines = tmp_path / "temp-bald-eagle-reference-points.geojson"
+    gdf.to_crs(4326).to_file(temp_lines, engine="fiona")
+    with open(TEST_JSON / "bald-eagle-refpoints.geojson") as f:
+        valid_points = f.read()
+        with open(temp_lines) as f:
+            test_points = f.read()
+            assert valid_points == test_points
+
+
+def test_reference_points_timeseries():
+    plan_hdf = RasPlanHdf(BALD_EAGLE_P18_REF)
+    ds = plan_hdf.reference_points_timeseries_output()
+    assert "time" in ds.coords
+    assert "refpt_id" in ds.coords
+    assert "refpt_name" in ds.coords
+    assert "mesh_name" in ds.coords
+    assert "Water Surface" in ds.variables
+    assert "Velocity" in ds.variables
+
+    ws = ds["Water Surface"]
+    assert ws.shape == (37, 3)
+    assert ws.attrs["Units"] == "ft"
+    v = ds["Velocity"]
+    assert v.attrs["Units"] == "ft/s"
+    assert v.shape == (37, 3)
+
+    df = ds.sel(refpt_id=1).to_dataframe()
+    valid_df = pd.read_csv(
+        TEST_CSV / "BaldEagleDamBrk.refpoints.1.csv",
+        index_col="time",
+        parse_dates=True,
+        dtype={"Water Surface": np.float32, "Velocity": np.float32},
+    )
+    assert_frame_equal(df, valid_df)
+
+
 def test_cross_sections_additional_velocity_total():
     xs_velocity_json = TEST_JSON / "xs_velocity.json"
     with RasPlanHdf(BAXTER_P01) as phdf: