stevenzwu commented on code in PR #6934:
URL: https://github.com/apache/iceberg/pull/6934#discussion_r1117533850
##########
core/src/main/java/org/apache/iceberg/BaseContentScanTask.java:
##########
@@ -52,12 +53,24 @@ public F file() {
return file;
}
+ protected Schema schema() {
Review Comment:
exposed as `protected` so that `BaseFileScanTask` can use it to implement
the `FileScanTask#schema()` method
##########
core/src/main/java/org/apache/iceberg/DataFiles.java:
##########
@@ -134,6 +134,8 @@ public static class Builder {
private Map<Integer, ByteBuffer> upperBounds = null;
private ByteBuffer keyMetadata = null;
private List<Long> splitOffsets = null;
+ private List<Integer> equalityFieldIds = null;
+ private Integer sortOrderId = SortOrder.unsorted().orderId();
Review Comment:
relocated the line here to follow the same order of definition
##########
core/src/main/java/org/apache/iceberg/DataFiles.java:
##########
@@ -134,6 +134,8 @@ public static class Builder {
private Map<Integer, ByteBuffer> upperBounds = null;
private ByteBuffer keyMetadata = null;
private List<Long> splitOffsets = null;
+ private List<Integer> equalityFieldIds = null;
Review Comment:
add a setter for `equalityFieldIds` so that the parser unit test can cover
this field too.
##########
core/src/main/java/org/apache/iceberg/ContentFileParser.java:
##########
@@ -0,0 +1,286 @@
+/*
+ * 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.iceberg;
+
+import com.fasterxml.jackson.core.JsonGenerator;
+import com.fasterxml.jackson.databind.JsonNode;
+import java.io.IOException;
+import java.nio.ByteBuffer;
+import java.util.List;
+import java.util.Map;
+import org.apache.iceberg.relocated.com.google.common.base.Preconditions;
+import org.apache.iceberg.util.ArrayUtil;
+import org.apache.iceberg.util.JsonUtil;
+
+class ContentFileParser {
Review Comment:
since DataFile and DeleteFile has the same structure, calling this
`ContentFileParser` without any generic type.
##########
core/src/main/java/org/apache/iceberg/ContentFileParser.java:
##########
@@ -0,0 +1,286 @@
+/*
+ * 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.iceberg;
+
+import com.fasterxml.jackson.core.JsonGenerator;
+import com.fasterxml.jackson.databind.JsonNode;
+import java.io.IOException;
+import java.nio.ByteBuffer;
+import java.util.List;
+import java.util.Map;
+import org.apache.iceberg.relocated.com.google.common.base.Preconditions;
+import org.apache.iceberg.util.ArrayUtil;
+import org.apache.iceberg.util.JsonUtil;
+
+class ContentFileParser {
+ private static final String SPEC_ID = "spec-id";
+ private static final String CONTENT = "content";
+ private static final String FILE_PATH = "file-path";
+ private static final String FILE_FORMAT = "file-format";
+ private static final String PARTITION = "partition";
+ private static final String RECORD_COUNT = "record-count";
+ private static final String FILE_SIZE = "file-size-in-bytes";
+ private static final String COLUMN_SIZES = "column-sizes";
+ private static final String VALUE_COUNTS = "value-counts";
+ private static final String NULL_VALUE_COUNTS = "null-value-counts";
+ private static final String NAN_VALUE_COUNTS = "nan-value-counts";
+ private static final String LOWER_BOUNDS = "lower-bounds";
+ private static final String UPPER_BOUNDS = "upper-bounds";
+ private static final String KEY_METADATA = "key-metadata";
+ private static final String SPLIT_OFFSETS = "split-offsets";
+ private static final String EQUALITY_IDS = "equality-ids";
+ private static final String SORT_ORDER_ID = "sort-order-id";
+
+ private final PartitionSpec spec;
+
+ ContentFileParser(PartitionSpec spec) {
Review Comment:
Unlike other JSON parser with a static singleton pattern,
`ContentFileParser` depends on the partition spec. Hence this is a regular
class and constructor.
##########
core/src/main/java/org/apache/iceberg/FileScanTaskParser.java:
##########
@@ -0,0 +1,141 @@
+/*
+ * 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.iceberg;
+
+import com.fasterxml.jackson.core.JsonGenerator;
+import com.fasterxml.jackson.databind.JsonNode;
+import com.github.benmanes.caffeine.cache.Caffeine;
+import com.github.benmanes.caffeine.cache.LoadingCache;
+import java.io.IOException;
+import java.io.StringWriter;
+import java.io.UncheckedIOException;
+import org.apache.iceberg.expressions.Expression;
+import org.apache.iceberg.expressions.ExpressionParser;
+import org.apache.iceberg.expressions.Expressions;
+import org.apache.iceberg.expressions.ResidualEvaluator;
+import org.apache.iceberg.relocated.com.google.common.base.Preconditions;
+import org.apache.iceberg.relocated.com.google.common.collect.ImmutableList;
+import org.apache.iceberg.util.JsonUtil;
+
+public class FileScanTaskParser {
+ private static final String SCHEMA = "schema";
+ private static final String SPEC = "spec";
+ private static final String DATA_FILE = "data-file";
+ private static final String DELETE_FILES = "delete-files";
+ private static final String RESIDUAL = "residual-filter";
+
+ private final boolean caseSensitive;
+ private final LoadingCache<PartitionSpec, ContentFileParser>
contentFileParsersBySpec;
+
+ public FileScanTaskParser(boolean caseSensitive) {
Review Comment:
`caseSensitive` is needed to construct residual evaluator object below.
--
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]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
