Feature/issue 186 Optional NRT label in the filenames

CHANGELOG.md

@@ -4,6 +4,12 @@ All notable changes to this project will be documented in this file.
 The format is based on [Common Changelog](https://common-changelog.org/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## Unreleased
+
+### Changed
+
+- update regex for filename pattern to recognize optional NRT label in TEMPO NRT collections ([#187](https://github.com/nasa/batchee/pull/187))([**@ank1m**](https://github.com/ank1m))
+
 ## [1.4.0] - 2025-08-20
 
 ### Changed

batchee/tempo_filename_parser.py

@@ -39,6 +39,7 @@
     r"(?P<product_type>[1-9A-Z]+)"
     r"(?P<proxy>(?:-PROXY)*)_"
     r"(?P<processing_level>L[0-9])_"
+    r"(?P<nrt>NRT_)?"
     r"(?P<version_id>V[0-9]+)_"
     r"(?P<day_in_granule>[0-9]{8})T"
     r"(?P<time_in_granule>[0-9]{6})Z_"

tests/test_filename_grouping.py

@@ -16,6 +16,18 @@
     "TEMPO_NO2_L2_V03_20240801T234630Z_S016G03.nc",
 ]
 
+example_nrt_filenames = [
+    "TEMPO_NO2_L2_NRT_V02_20250711T183227Z_S010G04.nc",
+    "TEMPO_NO2_L2_NRT_V02_20250711T183904Z_S010G05.nc",
+    "TEMPO_NO2_L2_NRT_V02_20250711T184541Z_S010G06.nc",
+    "TEMPO_NO2_L2_NRT_V02_20250711T185856Z_S010G08.nc",
+    "TEMPO_NO2_L2_NRT_V02_20250712T000606Z_S016G03.nc",
+    "TEMPO_NO2_L2_NRT_V02_20250712T001927Z_S016G05.nc",
+    "TEMPO_NO2_L2_NRT_V02_20250712T161248Z_S008G01.nc",
+    "TEMPO_NO2_L2_NRT_V02_20250712T162608Z_S008G03.nc",
+    "TEMPO_NO2_L2_NRT_V02_20250712T170552Z_S008G09.nc",
+]
+
 
 def test_timezone_conversion():
     utcdates = [filename.split("_")[4] for filename in example_filenames]
@@ -39,6 +51,12 @@ def test_grouping():
     assert results == [0, 0, 0, 1, 1, 1, 2, 2, 2]
 
 
+def test_nrt_grouping():
+    results = get_batch_indices(example_nrt_filenames)
+
+    assert results == [0, 0, 0, 0, 1, 1, 2, 2, 2]
+
+
 def test_main_cli():
     test_args = [batchee.tempo_filename_parser.__file__, "-v"]
     test_args.extend(example_filenames)