Merge pull request #17 from nasa/add-harmony-filename-generator

Added use of harmony filename generator for CASPER created files

Author: kecunning

casper/convert_to_csv.py

@@ -3,8 +3,10 @@
 import sys
 import zipfile
 from logging import Logger
+from pathlib import Path
 
 import xarray as xr
+from harmony_service_lib.util import generate_output_filename
 
 from casper.file_ops import (
     valid_input_file,
@@ -120,7 +122,7 @@ def convert_to_csv(fname: str, zip_file: str, logger: Logger = default_logger) -
                     schemas[dims] = []
                 schemas[dims].append(varname)
 
-        input_filename = fname.split("/")[-1]
+        input_filename = Path(fname).name
         vals = list(schemas.items())
 
         # Create the zip file object in write mode
@@ -131,7 +133,9 @@ def convert_to_csv(fname: str, zip_file: str, logger: Logger = default_logger) -
 
             for idx in range(len(vals)):
                 dims, vvs = vals[idx]
+                # Use Harmony generated filename
                 op_file = f"{input_filename}-{idx}.csv"
+                op_file = generate_output_filename(op_file, ext="csv", is_reformatted=True)
                 with zf.open(op_file, "w", force_zip64=True) as csv_file:
                     ds = xr.combine_by_coords([data[vv].rename(vv) for vv in vvs])
                     # Order columns: dimensions, non-dimensional coordinates, rest of variables

casper/harmony/service_adapter.py

@@ -32,7 +32,7 @@
 from uuid import uuid4
 
 from harmony_service_lib.adapter import BaseHarmonyAdapter
-from harmony_service_lib.util import stage
+from harmony_service_lib.util import generate_output_filename, stage
 from pystac import Catalog, Item
 from pystac.item import Asset
 
@@ -98,7 +98,6 @@ def process_file(self, catalog: Catalog) -> list[Catalog]:
             netcdf_url = _get_item_url(items[0])
             if netcdf_url is None:
                 raise ValueError("No URL found for item")
-            filename = Path(netcdf_url).stem
 
             with TemporaryDirectory() as temp_dir:
                 # Download file
@@ -107,24 +106,25 @@ def process_file(self, catalog: Catalog) -> list[Catalog]:
                 )
 
                 # Zip filename is the input filename without the file extension
-                zip_file_name = input_file.split("/")[-1].split(".")[0]
+                zip_file_name = Path(input_file).stem
 
                 # Create the subdirectory
                 self.logger.info("Running Casper.")
 
+                # Use Harmony generated filename
+                zip_file = generate_output_filename(zip_file_name, ext="zip", is_reformatted=True)
+                zip_file = Path(temp_dir) / zip_file
+
                 # --- Run Casper ---
-                zip_file = f"{temp_dir}/{zip_file_name}.zip"
                 convert_to_csv(
                     input_file,
                     zip_file,
                     logger=self.logger,
                 )
 
-                self.logger.info(
-                    f"Casper conversion completed. Zip file created {zip_file_name}.zip"
-                )
-                staged_url = self._stage(zip_file, f"{zip_file_name}.zip", "application/zip")
+                self.logger.info(f"Casper conversion completed. Zip file created {zip_file}")
 
+                staged_url = self._stage(zip_file, zip_file.name, "application/zip")
             # -- Output to STAC catalog --
             result.clear_items()
             properties = {
@@ -138,11 +138,10 @@ def process_file(self, catalog: Catalog) -> list[Catalog]:
                 None,
                 properties,
             )
-            filename = f"{zip_file_name}.zip"
 
             asset = Asset(
                 staged_url,
-                title=filename,
+                title=zip_file.name,
                 media_type="application/zip",
                 roles=["data"],
             )

tests/data/unit-test-data/Readme.json

@@ -1,13 +1,13 @@
 {
     "Notice": "The Readme.md file includes the same information",
-    "TEMPO_HCHO_L3_V04_20250912T210435Z_S012_subsetted.nc4-0.csv": {
+    "TEMPO_HCHO_L3_V04_20250912T210435Z_S012_subsetted.nc4-0_reformatted.csv": {
         "dimensions": "latitude,longitude",
         "non-dimensional coordinates": "",
         "variables": [
             "/weight"
         ]
     },
-    "TEMPO_HCHO_L3_V04_20250912T210435Z_S012_subsetted.nc4-1.csv": {
+    "TEMPO_HCHO_L3_V04_20250912T210435Z_S012_subsetted.nc4-1_reformatted.csv": {
         "dimensions": "time,latitude,longitude",
         "non-dimensional coordinates": "",
         "variables": [

tests/data/unit-test-data/Readme.md

@@ -1,13 +1,13 @@
 # 2 CSV files created for TEMPO_HCHO_L3_V04_20250912T210435Z_S012_subsetted.nc4 based on dimensional schemas
 
 
-## TEMPO_HCHO_L3_V04_20250912T210435Z_S012_subsetted.nc4-0.csv
+## TEMPO_HCHO_L3_V04_20250912T210435Z_S012_subsetted.nc4-0_reformatted.csv
 	dimensions:  latitude, longitude
 	non-dimension coordinates:
 	1 variables:
 		/weight
 
-## TEMPO_HCHO_L3_V04_20250912T210435Z_S012_subsetted.nc4-1.csv
+## TEMPO_HCHO_L3_V04_20250912T210435Z_S012_subsetted.nc4-1_reformatted.csv
 	dimensions:  time, latitude, longitude
 	non-dimension coordinates:
 	20 variables: