Skip to content

Commit f3baf57

Browse files
As Glue limits comments to 255 characters, we may need to truncate them.
1 parent fd8cab8 commit f3baf57

File tree

1 file changed

+9
-2
lines changed

1 file changed

+9
-2
lines changed

utilities/Hive_metastore_migration/src/hive_metastore_migration.py

Lines changed: 9 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -414,6 +414,14 @@ def transform_ms_bucketing_cols(self, ms_bucketing_cols):
414414
payload_func=lambda row: row['BUCKET_COL_NAME'])
415415

416416
def transform_ms_columns(self, ms_columns):
417+
def extract_row(row):
418+
def truncate(x):
419+
return x[:255] if hasattr(x,"__getitem__") else x
420+
return (
421+
row['COLUMN_NAME'],
422+
row['TYPE_NAME'],
423+
truncate(row['COMMENT'])
424+
)
417425
return self.transform_df_with_idx(df=ms_columns,
418426
id_col='CD_ID',
419427
idx='INTEGER_IDX',
@@ -422,8 +430,7 @@ def transform_ms_columns(self, ms_columns):
422430
StructField(name='name', dataType=StringType()),
423431
StructField(name='type', dataType=StringType()),
424432
StructField(name='comment', dataType=StringType())]),
425-
payload_func=lambda row: (
426-
row['COLUMN_NAME'], row['TYPE_NAME'], row['COMMENT']))
433+
payload_func=extract_row)
427434

428435
def transform_ms_skewed_col_names(self, ms_skewed_col_names):
429436
return self.transform_df_with_idx(df=ms_skewed_col_names,

0 commit comments

Comments
 (0)