etseidl commented on code in PR #8602:
URL: https://github.com/apache/arrow-rs/pull/8602#discussion_r2441427434


##########
parquet/src/file/serialized_reader.rs:
##########
@@ -1139,6 +1142,35 @@ mod tests {
 
     use super::*;
 
+    #[test]
+    fn test_decode_page_invalid_offset() {
+        use crate::file::metadata::thrift_gen::DataPageHeaderV2;
+
+        let mut page_header = PageHeader::default();
+        page_header.r#type = PageType::DATA_PAGE_V2;
+        page_header.uncompressed_page_size = 10;
+        page_header.compressed_page_size = 10;
+        let mut data_page_header_v2 = DataPageHeaderV2::default();
+        data_page_header_v2.definition_levels_byte_length = 11; // offset > 
uncompressed_page_size
+        page_header.data_page_header_v2 = Some(data_page_header_v2);
+
+        let buffer = Bytes::new();
+        let err = decode_page(page_header, buffer, Type::INT32, 
None).unwrap_err();
+        assert_eq!(err.to_string(), "Parquet error: Invalid page header");

Review Comment:
   We don't implement `Default` for the thrift structs nor `Debug` for `Page`. 
Instead you'll have to explicitly instantiate the page header. Something like
   
   ```rust
       let page_header = PageHeader {
           r#type: PageType::DATA_PAGE_V2,
           uncompressed_page_size: 10,
           compressed_page_size: 10,
           data_page_header: None,
           index_page_header: None,
           dictionary_page_header: None,
           crc: None,
           data_page_header_v2: Some(DataPageHeaderV2 {
               num_nulls: 0,
               num_rows: 0,
               num_values: 0,
               encoding: Encoding::PLAIN,
               definition_levels_byte_length: 11,
               repetition_levels_byte_length: 0,
               is_compressed: None,
               statistics: None,
           }),
       };
   
       let buffer = Bytes::new();
       match decode_page(page_header, buffer, Type::INT32, None) {
           Err(e) => assert_eq!(e.to_string(), "Parquet error: Invalid page 
header"),
           _ => panic!("should have failed"),
       }
   ```



-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: [email protected]

For queries about this service, please contact Infrastructure at:
[email protected]

Reply via email to