From 1d6ece8e4f34a1c92677c98470d7621930be80c8 Mon Sep 17 00:00:00 2001 From: Chris Johns <95475146+cjohns-scottlogic@users.noreply.github.com> Date: Wed, 4 Dec 2024 11:55:48 +0000 Subject: [PATCH] Revert "Extended 'max_line_length' when reading in csv file in DuckDB (#293)" This reverts commit d884867c5b5a049b4f9d7f764bda6e47339b3966. --- digital_land/package/datasetparquet.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/digital_land/package/datasetparquet.py b/digital_land/package/datasetparquet.py index e9d7fa84..a306da47 100644 --- a/digital_land/package/datasetparquet.py +++ b/digital_land/package/datasetparquet.py @@ -193,7 +193,7 @@ def load_entities(self): SELECT {fields_str} FROM ( SELECT {fields_str}, CASE WHEN resource_csv."end-date" IS NULL THEN '2999-12-31' ELSE resource_csv."end-date" END AS resource_end_date FROM temp_table - LEFT JOIN read_csv_auto('{self.resource_path}', max_line_size=40000000) resource_csv + LEFT JOIN read_csv_auto('{self.resource_path}') resource_csv ON temp_table.resource = resource_csv.resource QUALIFY ROW_NUMBER() OVER ( PARTITION BY entity, field @@ -232,7 +232,7 @@ def load_entities(self): # define organisation query org_csv = organisation_path org_query = f""" - SELECT * FROM read_csv_auto('{org_csv}', max_line_size=40000000) + SELECT * FROM read_csv_auto('{org_csv}') """ sql = f"""