Re: [PR] Add parquet page stats for float{16, 32, 64} [datafusion]

[via GitHub]

alamb commented on code in PR #10982:
URL: https://github.com/apache/datafusion/pull/10982#discussion_r1645026007


##########
datafusion/core/tests/parquet/arrow_statistics.rs:
##########
@@ -614,6 +614,94 @@ async fn test_int_8() {
     .run();
 }
 
+#[tokio::test]

Review Comment:
   💯  very nice tests



##########
datafusion/core/src/datasource/physical_plan/parquet/statistics.rs:
##########
@@ -548,11 +549,66 @@ macro_rules! make_data_page_stats_iterator {
     };
 }
 
-make_data_page_stats_iterator!(MinInt32DataPageStatsIterator, min, 
Index::INT32, i32);
-make_data_page_stats_iterator!(MaxInt32DataPageStatsIterator, max, 
Index::INT32, i32);
-make_data_page_stats_iterator!(MinInt64DataPageStatsIterator, min, 
Index::INT64, i64);
-make_data_page_stats_iterator!(MaxInt64DataPageStatsIterator, max, 
Index::INT64, i64);
-
+make_data_page_stats_iterator!(
+    MinInt32DataPageStatsIterator,
+    |x: &PageIndex<i32>| { x.min },
+    Index::INT32,
+    i32
+);
+make_data_page_stats_iterator!(
+    MaxInt32DataPageStatsIterator,
+    |x: &PageIndex<i32>| { x.max },
+    Index::INT32,
+    i32
+);
+make_data_page_stats_iterator!(
+    MinInt64DataPageStatsIterator,
+    |x: &PageIndex<i64>| { x.min },
+    Index::INT64,
+    i64
+);
+make_data_page_stats_iterator!(
+    MaxInt64DataPageStatsIterator,
+    |x: &PageIndex<i64>| { x.max },
+    Index::INT64,
+    i64
+);
+make_data_page_stats_iterator!(
+    MinFloat16DataPageStatsIterator,
+    |x: &PageIndex<FixedLenByteArray>| { x.min.clone() },
+    Index::FIXED_LEN_BYTE_ARRAY,

Review Comment:
   cargo doc --document-private-items -p datafusion --open
   
   ![Screenshot 2024-06-18 at 4 32 10 
PM](https://github.com/apache/datafusion/assets/490673/6a92c384-84e6-466e-b593-2e9c5313f7f6)
   
   I see what is going on -- I think this makes sense for now
   
   Implies that the iterator is an iterator over Vec<FixedLengthItem



-- 
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: github-unsubscr...@datafusion.apache.org

For queries about this service, please contact Infrastructure at:
us...@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscr...@datafusion.apache.org
For additional commands, e-mail: github-h...@datafusion.apache.org