Guarantee output column ordering

.gitignore

@@ -158,3 +158,40 @@ dmypy.json
 .ionide
 
 # End of https://www.toptal.com/developers/gitignore/api/visualstudiocode
+
+# Created by https://www.toptal.com/developers/gitignore/api/macos
+# Edit at https://www.toptal.com/developers/gitignore?templates=macos
+
+### macOS ###
+# General
+.DS_Store
+.AppleDouble
+.LSOverride
+
+# Icon must end with two \r
+Icon
+
+# Thumbnails
+._*
+
+# Files that might appear in the root of a volume
+.DocumentRevisions-V100
+.fseventsd
+.Spotlight-V100
+.TemporaryItems
+.Trashes
+.VolumeIcon.icns
+.com.apple.timemachine.donotpresent
+
+# Directories potentially created on remote AFP share
+.AppleDB
+.AppleDesktop
+Network Trash Folder
+Temporary Items
+.apdisk
+
+### macOS Patch ###
+# iCloud generated files
+*.icloud
+
+# End of https://www.toptal.com/developers/gitignore/api/macos

CHANGELOG.md

@@ -7,14 +7,26 @@ The format is based on [Keep a Changelog], and this project adheres to
 
 ## [Unreleased]
 
+### Fixed
+
+- Columns in the output file are now guaranteed to be in the same order as given
+  by the `columns` input value.
+  ([#100](https://github.com/MAAP-Project/gedi-subsetter/issues/100))
+
 ### Changed
 
-- Valid values for the `output` option have changed such that a file extension
-  is required, whereas previously this was optional since `.gpkg` was the only
-  supported output format.  However, in addition to `.gpkg`, it is now possible
-  to specify the extensions `.parquet` for (Geo)Parquet format, and `.fgb` for
-  FlatGeobuf format.
-  (([#97](https://github.com/MAAP-Project/gedi-subsetter/issues/97))
+- Valid values for the `output` option have changed such that **a file extension
+  is required**, whereas previously this was optional since `.gpkg` was the only
+  supported output format.
+  ([#97](https://github.com/MAAP-Project/gedi-subsetter/issues/97))
+
+### Added
+
+- It is now possible to specify alternative file formats for the `output` value:
+  in addition to the file extension `.gpkg` for GeoPackage format, it is now
+  possible to specify the extensions `.parquet` for (Geo)Parquet format, or
+  `.fgb` for FlatGeobuf format.
+  ([#97](https://github.com/MAAP-Project/gedi-subsetter/issues/97))
 
 ## [0.9.0] (2024-10-09)
 

pyproject.toml

@@ -37,6 +37,7 @@ module = [
 ignore_missing_imports = true
 
 [tool.pytest.ini_options]
+addopts = ["--doctest-modules"]
 filterwarnings = ["ignore::DeprecationWarning", "ignore::UserWarning"]
 # Uncomment next line to enable live logging during tests
 # log_cli = true

src/gedi_subset/gedi_utils.py

@@ -392,8 +392,8 @@ def subset_hdf5(
     ...     # `filename` column (which refers to the memory location of the
     ...     # ``io.BytesIO``, not a filename).
     ...     gdf.drop(columns=["filename"])
-       BEAM      agbd  sensitivity                   geometry
-    0  0000  1.116093         0.99  POINT (12.06707 -1.82471)
+           agbd  sensitivity                   geometry
+    0  1.116093         0.99  POINT (12.06707 -1.82471)
 
     Note that the resulting ``geopandas.GeoDataFrame`` contains only the specified
     coverage `BEAM`s, specified columns (`agbd` and `sensitivity`), and only the
@@ -414,7 +414,7 @@ def subset_beam(beam: h5py.Group) -> gpd.GeoDataFrame:
         # Grab the coordinates for the geometry, before dropping columns
         geometry = gpd.points_from_xy(df[lon_col], df[lat_col])
         # Select only the user-specified columns
-        gdf = gpd.GeoDataFrame(df[[*set(columns)]], geometry=geometry, crs=aoi.crs)
+        gdf = gpd.GeoDataFrame(df[columns], geometry=geometry, crs=aoi.crs)
 
         return cast(gpd.GeoDataFrame, gdf.clip(aoi))