fix: parse field names correctly

Author: tskir

src/batch/eqtl_catalogue.py

@@ -9,7 +9,7 @@
 from spark_prep import SparkPrep
 
 EQTL_CATALOGUE_IMPORTED_PATH = "https://raw.githubusercontent.com/eQTL-Catalogue/eQTL-Catalogue-resources/master/tabix/tabix_ftp_paths_imported.tsv"
-EQTL_CATALOGUE_OUPUT_BASE = (
+EQTL_CATALOGUE_OUTPUT_BASE = (
     "gs://genetics_etl_python_playground/1-smart-mirror/summary_stats"
 )
 
@@ -30,7 +30,7 @@
             source_id="eQTL_Catalogue",
             project_id="GTEx_V8",
             study_id=record["qtl_group"],
-            output_base_path=EQTL_CATALOGUE_OUPUT_BASE,
+            output_base_path=EQTL_CATALOGUE_OUTPUT_BASE,
         )
         worker.process()
     else:

src/batch/spark_prep.py

@@ -177,7 +177,7 @@ def cast_to_bytes(x: Any) -> typing.IO[bytes]:
         gzip_stream = cast_to_bytes(ResilientFetch(self.input_uri))
         bytes_stream = cast_to_bytes(gzip.GzipFile(fileobj=gzip_stream))
         self.text_stream = io.TextIOWrapper(bytes_stream)
-        self.field_names = self.text_stream.readline().split("\t")
+        self.field_names = self.text_stream.readline().rstrip().split("\t")
 
     def _p1_fetch_data(self, q_out: Queue[str | None]) -> None:
         """Fetch data from the URI in blocks.