From d51c69789ba70d69dc14c95372a82dc058850a90 Mon Sep 17 00:00:00 2001 From: Andrew Lamb Date: Thu, 8 Aug 2024 14:35:29 -0400 Subject: [PATCH] Document how to write bloom filters --- parquet/src/file/metadata/writer.rs | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/parquet/src/file/metadata/writer.rs b/parquet/src/file/metadata/writer.rs index 484520252d4b..d7eaebdfbd62 100644 --- a/parquet/src/file/metadata/writer.rs +++ b/parquet/src/file/metadata/writer.rs @@ -207,6 +207,11 @@ impl<'a, W: Write> ThriftMetadataWriter<'a, W> { /// BloomFilters stored in separate structures whose locations are stored as /// offsets from the beginning of the file. /// +/// Note: this writer does not directly write BloomFilters. In order to write +/// BloomFilters, write the bloom filters into the buffer before creating the +/// metadata writer. Then set the corresponding `bloom_filter_offset` and +/// `bloom_filter_length` on [`ColumnChunkMetaData`] passed to this writer. +/// /// # Output Format /// /// The format of the metadata is as follows: @@ -218,6 +223,7 @@ impl<'a, W: Write> ThriftMetadataWriter<'a, W> { /// 5. Parquet Magic Bytes (4 bytes) /// /// [`FileMetaData`]: crate::format::FileMetaData +/// [`ColumnChunkMetaData`]: crate::file::metadata::ColumnChunkMetaData /// /// ```text /// ┌──────────────────────┐