Skip to content

Commit

Permalink
Removed maximum size constraint when loading temp_table (#296)
Browse files Browse the repository at this point in the history
Co-authored-by: alexiglaser <[email protected]>
  • Loading branch information
alexglasertpx and alexiglaser authored Dec 3, 2024
1 parent 812d505 commit 6da0d25
Showing 1 changed file with 5 additions and 6 deletions.
11 changes: 5 additions & 6 deletions digital_land/package/datasetparquet.py
Original file line number Diff line number Diff line change
Expand Up @@ -68,8 +68,9 @@ def create_temp_table(self, input_paths):
# Initial max_line_size and increment step
max_size = 40000000
increment_step = 20000000
max_limit = 200000000 # Maximum allowable line size to attempt
# max_limit = 200000000 # Maximum allowable line size to attempt

increment = False
while True:
try:
query = f"""
Expand All @@ -84,15 +85,13 @@ def create_temp_table(self, input_paths):
)
"""
self.conn.execute(query)
if increment:
logging.info(f"Ended up needing a value of max_size = {max_size}")
break
except duckdb.Error as e: # Catch specific DuckDB error
if "Value with unterminated quote" in str(e):
increment = True
max_size += increment_step
if max_size > max_limit:
print(
f"Exceeded max_limit of {max_limit}. Could not resolve the issue."
)
raise
else:
raise

Expand Down

0 comments on commit 6da0d25

Please sign in to comment.