fix: file-size-threshold

pacman82 · Nov 1, 2023 · d5c79bc · d5c79bc
1 parent 927ebf3
commit d5c79bc
Show file tree

Hide file tree

Showing 2 changed files with 3 additions and 0 deletions.
diff --git a/Changelog.md b/Changelog.md
@@ -3,6 +3,7 @@
 ## 3.0.0 (next)
 
 * Zero sized columns are now treated as an error. Before `odbc2parquet` issued a warning and ignored them.
+* Fix: `--file-size-threshold` had an issue with not resetting the current file size after starting a new file. This caused only the first file to have the desired size. All subsequent files would contain only one row group each.
 
 ## 2.0.4
 

diff --git a/src/query/parquet_writer.rs b/src/query/parquet_writer.rs
@@ -122,6 +122,8 @@ impl ParquetWriter {
             .should_start_new_file(num_batch, self.current_file_size)
         {
             self.num_file += 1;
+            // Reset current file size, so the next file will not be considered too large immediatly
+            self.current_file_size = ByteSize::b(0);
             let file: Box<dyn Write + Send> = Box::new(create_output_file(
                 self.path.as_deref().unwrap(),
                 Some((self.num_file, self.suffix_length)),