huaxingao commented on code in PR #9841:
URL: https://github.com/apache/iceberg/pull/9841#discussion_r1602698512
##
spark/v3.4/spark/src/main/java/org/apache/iceberg/spark/BatchReadConf.java:
##
@@ -0,0 +1,47 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
aokolnychyi commented on code in PR #9841:
URL: https://github.com/apache/iceberg/pull/9841#discussion_r1594829408
##
spark/v3.4/spark/src/main/java/org/apache/iceberg/spark/BatchReadConf.java:
##
@@ -0,0 +1,47 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under
huaxingao commented on code in PR #9841:
URL: https://github.com/apache/iceberg/pull/9841#discussion_r1589730054
##
spark/v3.4/spark/src/main/java/org/apache/iceberg/spark/data/vectorized/CometColumnReader.java:
##
@@ -0,0 +1,164 @@
+/*
+ * Licensed to the Apache Software
aokolnychyi commented on code in PR #9841:
URL: https://github.com/apache/iceberg/pull/9841#discussion_r1589715889
##
spark/v3.4/spark/src/main/java/org/apache/iceberg/spark/SparkReadConf.java:
##
@@ -184,7 +185,7 @@ public boolean orcVectorizationEnabled() {
.parse();
aokolnychyi commented on code in PR #9841:
URL: https://github.com/apache/iceberg/pull/9841#discussion_r1589703297
##
spark/v3.4/spark/src/main/java/org/apache/iceberg/spark/SparkSQLProperties.java:
##
@@ -27,6 +27,10 @@ private SparkSQLProperties() {}
// Controls whether
huaxingao commented on code in PR #9841:
URL: https://github.com/apache/iceberg/pull/9841#discussion_r1585770312
##
spark/v3.4/spark/src/main/java/org/apache/iceberg/spark/source/SparkColumnarReaderFactory.java:
##
@@ -28,10 +29,12 @@
class SparkColumnarReaderFactory
huaxingao commented on code in PR #9841:
URL: https://github.com/apache/iceberg/pull/9841#discussion_r1585769857
##
spark/v3.4/spark/src/main/java/org/apache/iceberg/spark/source/SparkBatch.java:
##
@@ -115,11 +115,11 @@ private String[][] computePreferredLocations() {
huaxingao commented on code in PR #9841:
URL: https://github.com/apache/iceberg/pull/9841#discussion_r1585769554
##
spark/v3.4/spark/src/main/java/org/apache/iceberg/spark/source/BaseBatchReader.java:
##
@@ -32,23 +32,27 @@
import org.apache.iceberg.orc.ORC;
import
huaxingao commented on code in PR #9841:
URL: https://github.com/apache/iceberg/pull/9841#discussion_r1585769266
##
spark/v3.4/spark/src/main/java/org/apache/iceberg/spark/data/vectorized/comet/CometColumnReader.java:
##
@@ -0,0 +1,163 @@
+/*
+ * Licensed to the Apache Software
huaxingao commented on code in PR #9841:
URL: https://github.com/apache/iceberg/pull/9841#discussion_r1585767596
##
spark/v3.4/spark/src/main/java/org/apache/iceberg/spark/data/vectorized/ColumnarBatchReader.java:
##
@@ -74,48 +71,23 @@ public final ColumnarBatch
huaxingao commented on code in PR #9841:
URL: https://github.com/apache/iceberg/pull/9841#discussion_r1585767204
##
spark/v3.4/spark/src/main/java/org/apache/iceberg/spark/ParquetReaderType.java:
##
@@ -0,0 +1,24 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under
aokolnychyi commented on code in PR #9841:
URL: https://github.com/apache/iceberg/pull/9841#discussion_r1585438330
##
spark/v3.4/spark/src/main/java/org/apache/iceberg/spark/source/BaseBatchReader.java:
##
@@ -32,23 +32,27 @@
import org.apache.iceberg.orc.ORC;
import
aokolnychyi commented on code in PR #9841:
URL: https://github.com/apache/iceberg/pull/9841#discussion_r1585438330
##
spark/v3.4/spark/src/main/java/org/apache/iceberg/spark/source/BaseBatchReader.java:
##
@@ -32,23 +32,27 @@
import org.apache.iceberg.orc.ORC;
import
aokolnychyi commented on code in PR #9841:
URL: https://github.com/apache/iceberg/pull/9841#discussion_r1585438330
##
spark/v3.4/spark/src/main/java/org/apache/iceberg/spark/source/BaseBatchReader.java:
##
@@ -32,23 +32,27 @@
import org.apache.iceberg.orc.ORC;
import
aokolnychyi commented on PR #9841:
URL: https://github.com/apache/iceberg/pull/9841#issuecomment-2086131659
Will check today.
--
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
huaxingao commented on PR #9841:
URL: https://github.com/apache/iceberg/pull/9841#issuecomment-2083223651
@aokolnychyi I have addressed the comments. Could you please take one more
look when you have a moment? Thanks a lot!
--
This is an automated message from the Apache Git Service.
To
huaxingao commented on code in PR #9841:
URL: https://github.com/apache/iceberg/pull/9841#discussion_r1580539378
##
spark/v3.4/spark/src/main/java/org/apache/iceberg/spark/source/SparkColumnarReaderFactory.java:
##
@@ -49,7 +52,9 @@ public PartitionReader
huaxingao commented on code in PR #9841:
URL: https://github.com/apache/iceberg/pull/9841#discussion_r1580538817
##
spark/v3.4/spark/src/main/java/org/apache/iceberg/spark/data/vectorized/VectorizedSparkParquetReaders.java:
##
@@ -51,22 +53,37 @@ public class
huaxingao commented on code in PR #9841:
URL: https://github.com/apache/iceberg/pull/9841#discussion_r1580538480
##
spark/v3.4/spark/src/main/java/org/apache/iceberg/spark/SparkReadConf.java:
##
@@ -353,4 +354,12 @@ private boolean executorCacheLocalityEnabledInternal() {
huaxingao commented on code in PR #9841:
URL: https://github.com/apache/iceberg/pull/9841#discussion_r1580538348
##
gradle.properties:
##
@@ -20,8 +20,8 @@ systemProp.defaultFlinkVersions=1.18
systemProp.knownFlinkVersions=1.16,1.17,1.18
systemProp.defaultHiveVersions=2
huaxingao commented on code in PR #9841:
URL: https://github.com/apache/iceberg/pull/9841#discussion_r1580538128
##
api/src/main/java/org/apache/iceberg/ReaderType.java:
##
@@ -0,0 +1,24 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more
aokolnychyi commented on code in PR #9841:
URL: https://github.com/apache/iceberg/pull/9841#discussion_r1575419871
##
gradle.properties:
##
@@ -20,8 +20,8 @@ systemProp.defaultFlinkVersions=1.18
systemProp.knownFlinkVersions=1.16,1.17,1.18
systemProp.defaultHiveVersions=2
aokolnychyi commented on code in PR #9841:
URL: https://github.com/apache/iceberg/pull/9841#discussion_r1575416837
##
api/src/main/java/org/apache/iceberg/ReaderType.java:
##
@@ -0,0 +1,24 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more
aokolnychyi commented on code in PR #9841:
URL: https://github.com/apache/iceberg/pull/9841#discussion_r1575528604
##
spark/v3.4/spark/src/main/java/org/apache/iceberg/spark/SparkConfParser.java:
##
@@ -196,6 +201,33 @@ private Duration toDuration(String time) {
}
}
+
aokolnychyi commented on code in PR #9841:
URL: https://github.com/apache/iceberg/pull/9841#discussion_r1575528604
##
spark/v3.4/spark/src/main/java/org/apache/iceberg/spark/SparkConfParser.java:
##
@@ -196,6 +201,33 @@ private Duration toDuration(String time) {
}
}
+
huaxingao commented on code in PR #9841:
URL: https://github.com/apache/iceberg/pull/9841#discussion_r1573865006
##
spark/v3.4/spark/src/main/java/org/apache/iceberg/spark/data/vectorized/BaseColumnBatchLoader.java:
##
@@ -0,0 +1,199 @@
+/*
+ * Licensed to the Apache Software
huaxingao commented on code in PR #9841:
URL: https://github.com/apache/iceberg/pull/9841#discussion_r1573864929
##
spark/v3.4/build.gradle:
##
@@ -70,8 +70,11 @@
project(":iceberg-spark:iceberg-spark-${sparkMajorVersion}_${scalaVersion}") {
exclude group: 'io.netty',
RussellSpitzer commented on code in PR #9841:
URL: https://github.com/apache/iceberg/pull/9841#discussion_r1571301509
##
spark/v3.4/spark/src/main/java/org/apache/iceberg/spark/data/vectorized/comet/CometColumnReader.java:
##
@@ -0,0 +1,165 @@
+/*
+ * Licensed to the Apache
RussellSpitzer commented on code in PR #9841:
URL: https://github.com/apache/iceberg/pull/9841#discussion_r1571295057
##
spark/v3.4/spark/src/main/java/org/apache/iceberg/spark/data/vectorized/BaseColumnBatchLoader.java:
##
@@ -0,0 +1,199 @@
+/*
+ * Licensed to the Apache
RussellSpitzer commented on code in PR #9841:
URL: https://github.com/apache/iceberg/pull/9841#discussion_r1571293170
##
spark/v3.4/spark/src/main/java/org/apache/iceberg/spark/data/vectorized/BaseColumnBatchLoader.java:
##
@@ -0,0 +1,199 @@
+/*
+ * Licensed to the Apache
RussellSpitzer commented on code in PR #9841:
URL: https://github.com/apache/iceberg/pull/9841#discussion_r1571286633
##
spark/v3.4/spark/src/main/java/org/apache/iceberg/spark/SparkConfParser.java:
##
@@ -196,6 +201,40 @@ private Duration toDuration(String time) {
}
}
RussellSpitzer commented on code in PR #9841:
URL: https://github.com/apache/iceberg/pull/9841#discussion_r1571283635
##
spark/v3.4/build.gradle:
##
@@ -70,8 +70,11 @@
project(":iceberg-spark:iceberg-spark-${sparkMajorVersion}_${scalaVersion}") {
exclude group:
aokolnychyi commented on code in PR #9841:
URL: https://github.com/apache/iceberg/pull/9841#discussion_r1568005309
##
spark/v3.4/spark/src/main/java/org/apache/iceberg/spark/data/vectorized/comet/CometIcebergColumnarBatchReader.java:
##
@@ -0,0 +1,303 @@
+/*
+ * Licensed to the
huaxingao commented on code in PR #9841:
URL: https://github.com/apache/iceberg/pull/9841#discussion_r1566753916
##
spark/v3.4/spark/src/main/java/org/apache/iceberg/spark/data/vectorized/VectorizedSparkParquetReaders.java:
##
@@ -51,22 +53,43 @@ public class
huaxingao commented on code in PR #9841:
URL: https://github.com/apache/iceberg/pull/9841#discussion_r1566753486
##
spark/v3.4/spark/src/main/java/org/apache/iceberg/spark/data/vectorized/comet/CometIcebergColumnarBatchReader.java:
##
@@ -0,0 +1,303 @@
+/*
+ * Licensed to the
huaxingao commented on code in PR #9841:
URL: https://github.com/apache/iceberg/pull/9841#discussion_r1566752772
##
spark/v3.4/spark/src/main/java/org/apache/iceberg/spark/data/vectorized/comet/CometIcebergColumnReader.java:
##
@@ -0,0 +1,164 @@
+/*
+ * Licensed to the Apache
huaxingao commented on code in PR #9841:
URL: https://github.com/apache/iceberg/pull/9841#discussion_r1566752634
##
spark/v3.4/spark/src/main/java/org/apache/iceberg/spark/data/vectorized/comet/CometIcebergColumnReader.java:
##
@@ -0,0 +1,164 @@
+/*
+ * Licensed to the Apache
huaxingao commented on code in PR #9841:
URL: https://github.com/apache/iceberg/pull/9841#discussion_r1566753162
##
spark/v3.4/spark/src/main/java/org/apache/iceberg/spark/data/vectorized/comet/CometIcebergColumnarBatchReader.java:
##
@@ -0,0 +1,303 @@
+/*
+ * Licensed to the
aokolnychyi commented on code in PR #9841:
URL: https://github.com/apache/iceberg/pull/9841#discussion_r1566673808
##
spark/v3.4/spark/src/main/java/org/apache/iceberg/spark/data/vectorized/comet/CometIcebergColumnReader.java:
##
@@ -0,0 +1,164 @@
+/*
+ * Licensed to the Apache
huaxingao commented on code in PR #9841:
URL: https://github.com/apache/iceberg/pull/9841#discussion_r1548708375
##
spark/v3.4/spark/src/main/java/org/apache/iceberg/spark/data/vectorized/comet/CometIcebergColumnReader.java:
##
@@ -0,0 +1,164 @@
+/*
+ * Licensed to the Apache
RussellSpitzer commented on code in PR #9841:
URL: https://github.com/apache/iceberg/pull/9841#discussion_r1548617271
##
spark/v3.4/spark/src/main/java/org/apache/iceberg/spark/data/vectorized/comet/CometIcebergColumnReader.java:
##
@@ -0,0 +1,164 @@
+/*
+ * Licensed to the
huaxingao commented on PR #9841:
URL: https://github.com/apache/iceberg/pull/9841#issuecomment-1972363257
cc @aokolnychyi @sunchao
--
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
huaxingao opened a new pull request, #9841:
URL: https://github.com/apache/iceberg/pull/9841
This PR shows how I will integrate
[Comet](https://github.com/apache/arrow-datafusion-comet) with iceberg. The PR
doesn't compile yet because we haven't released Comet yet. Also, Comet doesn't
43 matches
Mail list logo