the-other-tim-brown commented on code in PR #767:
URL: https://github.com/apache/incubator-xtable/pull/767#discussion_r2682963470


##########
xtable-core/src/main/java/org/apache/xtable/paimon/PaimonStatsExtractor.java:
##########
@@ -0,0 +1,187 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements.  See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership.  The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License.  You may obtain a copy of the License at
+ *
+ *      http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+ 
+package org.apache.xtable.paimon;
+
+import java.util.ArrayList;
+import java.util.List;
+import java.util.Map;
+import java.util.stream.Collectors;
+
+import lombok.AccessLevel;
+import lombok.NoArgsConstructor;
+import lombok.extern.log4j.Log4j2;
+
+import org.apache.paimon.data.BinaryArray;
+import org.apache.paimon.data.BinaryRow;
+import org.apache.paimon.data.Timestamp;
+import org.apache.paimon.io.DataFileMeta;
+import org.apache.paimon.stats.SimpleStats;
+import org.apache.paimon.types.TimestampType;
+
+import org.apache.xtable.exception.ReadException;
+import org.apache.xtable.model.schema.InternalField;
+import org.apache.xtable.model.schema.InternalSchema;
+import org.apache.xtable.model.schema.InternalType;
+import org.apache.xtable.model.stat.ColumnStat;
+import org.apache.xtable.model.stat.Range;
+
+@Log4j2
+@NoArgsConstructor(access = AccessLevel.PRIVATE)
+public class PaimonStatsExtractor {
+  private static final PaimonStatsExtractor INSTANCE = new 
PaimonStatsExtractor();
+
+  public static PaimonStatsExtractor getInstance() {
+    return INSTANCE;
+  }
+
+  public List<ColumnStat> extractColumnStats(DataFileMeta file, InternalSchema 
internalSchema) {
+    List<ColumnStat> columnStats = new ArrayList<>();
+    Map<String, InternalField> fieldMap =
+        internalSchema.getAllFields().stream()
+            .collect(Collectors.toMap(InternalField::getPath, f -> f));
+
+    // stats for all columns are present in valueStats, we can safely ignore 
file.keyStats()
+    SimpleStats valueStats = file.valueStats();
+    if (valueStats != null) {
+      List<String> colNames = file.valueStatsCols();
+      if (colNames == null) {
+        // if column names are not present, then stats are being collected for 
all columns
+        colNames =
+            internalSchema.getAllFields().stream()
+                .map(InternalField::getPath)
+                .collect(Collectors.toList());
+      }
+
+      if (colNames.size() != valueStats.minValues().getFieldCount()) {
+        // paranoia check - this should never happen, but if the code reaches 
here, then there is a
+        // bug! Please file a bug report
+        throw new ReadException(
+            String.format(
+                "Mismatch between column stats names and values arity: 
names=%d, values=%d",
+                colNames.size(), valueStats.minValues().getFieldCount()));
+      }
+
+      collectColumnStats(columnStats, valueStats, colNames, fieldMap, 
file.rowCount());
+    }
+
+    return columnStats;
+  }
+
+  private void collectColumnStats(
+      List<ColumnStat> columnStats,
+      SimpleStats stats,
+      List<String> colNames,
+      Map<String, InternalField> fieldMap,
+      long rowCount) {
+
+    BinaryRow minValues = stats.minValues();
+    BinaryRow maxValues = stats.maxValues();
+    BinaryArray nullCounts = stats.nullCounts();
+
+    for (int i = 0; i < colNames.size(); i++) {
+      String colName = colNames.get(i);
+      InternalField field = fieldMap.get(colName);
+      if (field == null) {
+        continue;
+      }
+
+      // Check if we already have stats for this field
+      boolean alreadyExists =
+          columnStats.stream().anyMatch(cs -> 
cs.getField().getPath().equals(colName));
+      if (alreadyExists) {
+        continue;
+      }
+
+      InternalType type = field.getSchema().getDataType();
+      Object min = getValue(minValues, i, type, field.getSchema());
+      Object max = getValue(maxValues, i, type, field.getSchema());

Review Comment:
   If the `getValue` returns `null`, should we set the range value to `null` as 
well?



-- 
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