pitrou commented on code in PR #48201:
URL: https://github.com/apache/arrow/pull/48201#discussion_r2560603114


##########
python/pyarrow/tests/parquet/test_metadata.py:
##########
@@ -814,3 +816,31 @@ def msg(c):
 
     with pytest.raises(TypeError, match=msg("FileMetaData")):
         pq.FileMetaData()
+
+
+def test_column_metadata_with_bloom_filter(parquet_test_datadir):
+    metadata = pq.read_metadata(parquet_test_datadir /
+                                
'data_index_bloom_encoding_with_length.parquet')
+    assert metadata.row_group(0).column(0).has_dictionary_page is True
+    assert metadata.row_group(0).column(0).dictionary_page_offset == 4
+    assert metadata.row_group(0).column(0).has_index_page is False
+    assert metadata.row_group(0).column(0).index_page_offset is None
+    assert metadata.row_group(0).column(0).has_bloom_filter is True
+    assert metadata.row_group(0).column(0).has_column_index is True
+    assert metadata.row_group(0).column(0).has_offset_index is True
+    assert metadata.row_group(0).column(0).bloom_filter_offset == 253
+    assert metadata.row_group(0).column(0).bloom_filter_length == 2064
+
+
+def test_column_metadata_with_index_page(parquet_test_datadir):
+    metadata = pq.read_metadata(parquet_test_datadir /
+                                'nan_in_stats.parquet')
+    assert metadata.row_group(0).column(0).has_dictionary_page is True
+    assert metadata.row_group(0).column(0).dictionary_page_offset == 4
+    assert metadata.row_group(0).column(0).has_index_page is True
+    assert metadata.row_group(0).column(0).index_page_offset == 0

Review Comment:
   Index pages don't actually exist, so it seems a bit confusing to expose this.



-- 
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