Merge branch 'main' of github.com:Altinity/clickhouse-regression

Author: alsugiliazova

parquet/requirements/requirements.md

@@ -480,19 +480,6 @@ Parquet:
         IfCorrupted:
             - Only that row group is lost
       ColumnChunk:
-        Metadata2:
-            - name
-            - path
-            - total_compressed_size
-            - total_uncompressed_size
-            - have_statistics
-            - statistics
-            - statistics:
-                - num_values
-                - null_count
-                - distinct_count
-                - min - the minimum value of the column chunk
-                - max - the maximum column of the column chunk
         Metadata:
           - file_path
           - file_offset
@@ -529,7 +516,15 @@ Parquet:
         IfCorrupted:
           - The remaining pages in that chunk are lost.
           - If the data within a page is corrupt, that page is lost
-    
+      FormatLevelFeatures:
+        - xxxHash-based bloom filters
+        - Bloom filter length
+        - Statistics min_value, max_value
+        - Page index
+        - Page CRC32 checksum
+        - Modular encryption
+        - Size statistics 
+
     ClickHouseRead:
         functions:
           - file()

parquet/requirements/requirements.py

@@ -6374,19 +6374,6 @@
         IfCorrupted:
             - Only that row group is lost
       ColumnChunk:
-        Metadata2:
-            - name
-            - path
-            - total_compressed_size
-            - total_uncompressed_size
-            - have_statistics
-            - statistics
-            - statistics:
-                - num_values
-                - null_count
-                - distinct_count
-                - min - the minimum value of the column chunk
-                - max - the maximum column of the column chunk
         Metadata:
           - file_path
           - file_offset
@@ -6423,7 +6410,15 @@
         IfCorrupted:
           - The remaining pages in that chunk are lost.
           - If the data within a page is corrupt, that page is lost
-    
+      FormatLevelFeatures:
+        - xxxHash-based bloom filters
+        - Bloom filter length
+        - Statistics min_value, max_value
+        - Page index
+        - Page CRC32 checksum
+        - Modular encryption
+        - Size statistics 
+
     ClickHouseRead:
         functions:
           - file()