fix: remove duplicated collection id prefix

mdps_ds_lib/stage_in_out/upload_arbitrary_files_as_granules.py

@@ -42,8 +42,10 @@ def generate_sample_stac(self, filepath: str):
         file_checksum = FileUtils.get_checksum(filepath, True)
         # https://github.com/stac-extensions/file
         # https://github.com/stac-extensions/file/blob/main/examples/item.json
+        granule_id = os.path.splitext(filename)[0]
+        granule_id = granule_id if granule_id.startswith(self.__collection_id) else f'{self.__collection_id}:{granule_id}'
         sample_stac_item = Item(
-                         id=f'{self.__collection_id}:{os.path.splitext(filename)[0]}',
+                         id=granule_id,
                          stac_extensions=["https://stac-extensions.github.io/file/v2.1.0/schema.json"],
                          geometry={
                              "type": "Point",
@@ -78,7 +80,8 @@ def execute_job(self, job_obj, lock) -> bool:
         updating_assets = {}
         try:
             LOGGER.audit(f'uploading auxiliary file: {job_obj}')
-            s3_url = self.__s3.upload(job_obj, self.__staging_bucket, f'{self.__collection_id}/{self.__collection_id}:{sample_stac_item.id}', self.__delete_files)
+            # NOTE: sample_stac_item.id is guaranteed to start with colleciton id.
+            s3_url = self.__s3.upload(job_obj, self.__staging_bucket, f'{self.__collection_id}/{sample_stac_item.id}', self.__delete_files)
             updating_assets[os.path.basename(s3_url)] = s3_url
             uploading_current_granule_stac = f'{s3_url}.stac.json'
             self.__s3.set_s3_url(uploading_current_granule_stac)

tests/integration_tests/test_docker_stage_out.py

@@ -1454,7 +1454,7 @@ def test_03_03_upload_auxiliary_files(self):
             self.assertTrue(result_key.startswith('test_file'), f'worng asset key: {result_key}')
             self.assertTrue(f'{result_key}.stac.json' in upload_result['assets'], f'missing assets#metadata asset: test_file_0.json')
             self.assertTrue('href' in upload_result['assets'][f'{result_key}.stac.json'], 'missing assets#metadata__cas#href')
-            self.assertTrue(upload_result['assets'][f'{result_key}.stac.json']['href'].startswith(f's3://{os.environ["STAGING_BUCKET"]}/{os.environ["COLLECTION_ID"]}/'), f"wrong HREF (no S3?): upload_result['assets'][f'{result_key}.stac.json']['href']")
+            self.assertTrue(upload_result['assets'][f'{result_key}.stac.json']['href'].startswith(f's3://{os.environ["STAGING_BUCKET"]}/{os.environ["COLLECTION_ID"]}/{os.environ["COLLECTION_ID"]}:test_file_'), f"wrong HREF (no S3?): upload_result['assets'][f'{result_key}.stac.json']['href']")
             """
             Example output: 
             {
@@ -1479,9 +1479,7 @@ def test_03_03_upload_auxiliary_files(self):
                     'collection': 'NEW_COLLECTION_EXAMPLE_L1B___9'}]}
             """
             s3 = AwsS3()
-            s3_keys = [k for k in s3.get_child_s3_files(os.environ['STAGING_BUCKET'],
-                                  f"stage_out/successful_features_{starting_time}",
-                                  )]
+            s3_keys = [k for k in s3.get_child_s3_files(os.environ['STAGING_BUCKET'], f"stage_out/successful_features_{starting_time}")]
             s3_keys = sorted(s3_keys)
             print(f's3_keys: {s3_keys}')
             self.assertTrue(len(s3_keys) > 0, f'empty files in S3')