fix: stats is optional in add action

crates/core/src/kernel/snapshot/parse.rs

@@ -83,7 +83,7 @@ pub(super) fn read_adds(array: &dyn ProvidesColumnByName) -> DeltaResult<Vec<Add
         let size = ex::extract_and_cast::<Int64Array>(arr, "size")?;
         let modification_time = ex::extract_and_cast::<Int64Array>(arr, "modificationTime")?;
         let data_change = ex::extract_and_cast::<BooleanArray>(arr, "dataChange")?;
-        let stats = ex::extract_and_cast::<StringArray>(arr, "stats")?;
+        let stats = ex::extract_and_cast_opt::<StringArray>(arr, "stats");
         let tags = ex::extract_and_cast_opt::<MapArray>(arr, "tags");
         let dv = ex::extract_and_cast_opt::<StructArray>(arr, "deletionVector");
 
@@ -126,7 +126,8 @@ pub(super) fn read_adds(array: &dyn ProvidesColumnByName) -> DeltaResult<Vec<Add
                     size: ex::read_primitive(size, i)?,
                     modification_time: ex::read_primitive(modification_time, i)?,
                     data_change: ex::read_bool(data_change, i)?,
-                    stats: ex::read_str_opt(stats, i).map(|s| s.to_string()),
+                    stats: stats
+                        .and_then(|stats| ex::read_str_opt(stats, i).map(|s| s.to_string())),
                     partition_values: pvs
                         .and_then(|pv| collect_map(&pv.value(i)).map(|m| m.collect()))
                         .unwrap_or_default(),

crates/core/src/protocol/mod.rs

@@ -1221,6 +1221,15 @@ mod tests {
             assert_eq!(&expected_null_count, null_count_column);
         }
 
+        #[tokio::test]
+        async fn test_table_checkpoint_not_always_with_stats() {
+            let path = "../test/tests/data/delta-checkpoint-stats-optional";
+            let mut table = crate::open_table(path).await.unwrap();
+            table.load().await.unwrap();
+
+            assert_eq!(2, table.snapshot().unwrap().file_actions().unwrap().len());
+        }
+
         #[tokio::test]
         async fn test_only_struct_stats() {
             // test table with no json stats

crates/test/tests/data/delta-checkpoint-stats-optional/_delta_log/00000000000000000000.json

@@ -0,0 +1,3 @@
+{"commitInfo":{"timestamp":1666652369577,"userId":"6114986638742036","userName":"dummy_username","operation":"CREATE OR REPLACE TABLE","operationParameters":{"isManaged":"false","description":null,"partitionBy":"[]","properties":"{\"delta.checkpoint.writeStatsAsJson\":\"false\",\"delta.checkpoint.writeStatsAsStruct\":\"true\"}"},"notebook":{"notebookId":"1829280694121074"},"clusterId":"1007-161845-fa2h8e50","isolationLevel":"WriteSerializable","isBlindAppend":true,"operationMetrics":{},"engineInfo":"Databricks-Runtime/10.4.x-scala2.12","txnId":"a8510a45-92dc-4e9f-9f7a-42bbcc9b752d"}}
+{"protocol":{"minReaderVersion":1,"minWriterVersion":2}}
+{"metaData":{"id":"8d3d2b8a-f091-4d7d-8a37-432a9beaf17b","format":{"provider":"parquet","options":{}},"schemaString":"{\"type\":\"struct\",\"fields\":[{\"name\":\"integer\",\"type\":\"integer\",\"nullable\":false,\"metadata\":{}}]}","partitionColumns":[],"configuration":{"delta.checkpoint.writeStatsAsJson":"false","delta.checkpoint.writeStatsAsStruct":"true"},"createdTime":1666652369483}}

crates/test/tests/data/delta-checkpoint-stats-optional/_delta_log/00000000000000000001.json

@@ -0,0 +1,3 @@
+{"commitInfo":{"timestamp":1666652373383,"userId":"6114986638742036","userName":"dummy_username","operation":"WRITE","operationParameters":{"mode":"Append","partitionBy":"[]"},"notebook":{"notebookId":"1829280694121074"},"clusterId":"1007-161845-fa2h8e50","readVersion":0,"isolationLevel":"WriteSerializable","isBlindAppend":true,"operationMetrics":{"numFiles":"1","numOutputRows":"1","numOutputBytes":"5489"},"engineInfo":"Databricks-Runtime/10.4.x-scala2.12","txnId":"35e88c76-9cfb-4e0e-bce8-2317f3c49c75"}}
+{"metaData":{"id":"8d3d2b8a-f091-4d7d-8a37-432a9beaf17b","format":{"provider":"parquet","options":{}},"schemaString":"{\"type\":\"struct\",\"fields\":[{\"name\":\"integer\",\"type\":\"integer\",\"nullable\":false,\"metadata\":{}},{\"name\":\"null\",\"type\":\"boolean\",\"nullable\":true,\"metadata\":{}},{\"name\":\"boolean\",\"type\":\"boolean\",\"nullable\":true,\"metadata\":{}},{\"name\":\"double\",\"type\":\"double\",\"nullable\":true,\"metadata\":{}},{\"name\":\"decimal\",\"type\":\"decimal(8,5)\",\"nullable\":true,\"metadata\":{}},{\"name\":\"string\",\"type\":\"string\",\"nullable\":true,\"metadata\":{}},{\"name\":\"binary\",\"type\":\"binary\",\"nullable\":true,\"metadata\":{}},{\"name\":\"date\",\"type\":\"date\",\"nullable\":true,\"metadata\":{}},{\"name\":\"timestamp\",\"type\":\"timestamp\",\"nullable\":true,\"metadata\":{}},{\"name\":\"struct\",\"type\":{\"type\":\"struct\",\"fields\":[{\"name\":\"struct_element\",\"type\":\"string\",\"nullable\":true,\"metadata\":{}}]},\"nullable\":true,\"metadata\":{}},{\"name\":\"map\",\"type\":{\"type\":\"map\",\"keyType\":\"string\",\"valueType\":\"string\",\"valueContainsNull\":true},\"nullable\":true,\"metadata\":{}},{\"name\":\"array\",\"type\":{\"type\":\"array\",\"elementType\":\"string\",\"containsNull\":true},\"nullable\":true,\"metadata\":{}},{\"name\":\"nested_struct\",\"type\":{\"type\":\"struct\",\"fields\":[{\"name\":\"struct_element\",\"type\":{\"type\":\"struct\",\"fields\":[{\"name\":\"nested_struct_element\",\"type\":\"string\",\"nullable\":true,\"metadata\":{}}]},\"nullable\":true,\"metadata\":{}}]},\"nullable\":true,\"metadata\":{}},{\"name\":\"struct_of_array_of_map\",\"type\":{\"type\":\"struct\",\"fields\":[{\"name\":\"struct_element\",\"type\":{\"type\":\"array\",\"elementType\":{\"type\":\"map\",\"keyType\":\"string\",\"valueType\":\"string\",\"valueContainsNull\":true},\"containsNull\":true},\"nullable\":true,\"metadata\":{}}]},\"nullable\":true,\"metadata\":{}}]}","partitionColumns":[],"configuration":{"delta.checkpoint.writeStatsAsJson":"false","delta.checkpoint.writeStatsAsStruct":"true"},"createdTime":1666652369483}}
+{"add":{"path":"part-00000-7a509247-4f58-4453-9202-51d75dee59af-c000.snappy.parquet","partitionValues":{},"size":5489,"modificationTime":1666652373000,"dataChange":true,"stats":"{\"numRecords\":1,\"minValues\":{\"integer\":0,\"double\":1.234,\"decimal\":-5.67800,\"string\":\"string\",\"date\":\"2022-10-24\",\"timestamp\":\"2022-10-24T22:59:32.846Z\",\"struct\":{\"struct_element\":\"struct_value\"},\"nested_struct\":{\"struct_element\":{\"nested_struct_element\":\"nested_struct_value\"}}},\"maxValues\":{\"integer\":0,\"double\":1.234,\"decimal\":-5.67800,\"string\":\"string\",\"date\":\"2022-10-24\",\"timestamp\":\"2022-10-24T22:59:32.846Z\",\"struct\":{\"struct_element\":\"struct_value\"},\"nested_struct\":{\"struct_element\":{\"nested_struct_element\":\"nested_struct_value\"}}},\"nullCount\":{\"integer\":0,\"null\":1,\"boolean\":0,\"double\":0,\"decimal\":0,\"string\":0,\"binary\":0,\"date\":0,\"timestamp\":0,\"struct\":{\"struct_element\":0},\"map\":0,\"array\":0,\"nested_struct\":{\"struct_element\":{\"nested_struct_element\":0}},\"struct_of_array_of_map\":{\"struct_element\":0}}}","tags":{"INSERTION_TIME":"1666652373000000","OPTIMIZE_TARGET_SIZE":"268435456"}}}

crates/test/tests/data/delta-checkpoint-stats-optional/_delta_log/00000000000000000002.json

@@ -0,0 +1,2 @@
+{"commitInfo":{"timestamp":1666652374424,"userId":"6114986638742036","userName":"dummy_username","operation":"WRITE","operationParameters":{"mode":"Append","partitionBy":"[]"},"notebook":{"notebookId":"1829280694121074"},"clusterId":"1007-161845-fa2h8e50","readVersion":1,"isolationLevel":"WriteSerializable","isBlindAppend":true,"operationMetrics":{"numFiles":"1","numOutputRows":"1","numOutputBytes":"5489"},"engineInfo":"Databricks-Runtime/10.4.x-scala2.12","txnId":"efe25f5f-e03a-458d-8fbe-34ed2111b3c1"}}
+{"add":{"path":"part-00000-28925d3a-bdf2-411e-bca9-b067444cbcb0-c000.snappy.parquet","partitionValues":{},"size":5489,"modificationTime":1666652374000,"dataChange":true,"stats_parsed":null,"tags":{"INSERTION_TIME":"1666652374000000","OPTIMIZE_TARGET_SIZE":"268435456"}}}

crates/test/tests/data/delta-checkpoint-stats-optional/_delta_log/_last_checkpoint

@@ -0,0 +1 @@
+{"size":4,"size_in_bytes":41898,"version":2}