This is an automated email from the ASF dual-hosted git repository.
github-bot pushed a change to branch dependabot/maven/protobuf.version-4.26.0
in repository https://gitbox.apache.org/repos/asf/parquet-java.git
discard a3c631747 Bump protobuf.version from 3.25.3 to 4.26.0
add d1c29755e Bump org.apache.arrow:arrow-vector from 15.0.0 to 15.0.2
(#1306)
add f2aa9d8ff Bump com.google.guava:guava from 33.0.0-jre to 33.1.0-jre
(#1307)
add 1b1961376 PARQUET-2453: Add build-helper-maven-plugin for some modules
(#1305)
add 67fc368c9 PARQUET-2456: Avoid type name conflicts on fixed type (#1304)
add a1f8591b3 PARQUET-2457: Add missing maven-scala-plugin version (#1312)
add 90436a8fd Bump commons-io:commons-io from 2.15.1 to 2.16.0 (#1313)
add e6ad25a75 Bump org.cyclonedx:cyclonedx-maven-plugin from 2.7.11 to
2.8.0 (#1315)
add d8c658216 Bump com.google.truth.extensions:truth-proto-extension
(#1316)
add 1781b810d Bump commons-io:commons-io from 2.16.0 to 2.16.1 (#1318)
add 0f1f1660d Bump commons-logging:commons-logging from 1.3.0 to 1.3.1
(#1319)
add f51ed41de Bump org.codehaus.mojo:exec-maven-plugin from 3.1.1 to 3.2.0
(#1320)
add 4bf606905 PARQUET-2461: Upgrade ZSTD-JNI to 1.5.6-2 (#1326)
add 460988a03 PARQUET-2459. parquet-hadoop tests to work with hadoop 3.4.0
(#1321)
add 87e99d129 PARQUET-2454: Invoking flush before closing the output
stream (#1309)
add 65ef1f1ea Bump org.apache.commons:commons-text from 1.11.0 to 1.12.0
(#1324)
add a89083caf PARQUET-2429: Reduce direct input buffer churn (#1270)
add 2116ae3f6 Bump com.google.api.grpc:proto-google-common-protos (#1323)
add adb3e27c8 Bump org.apache.arrow:arrow-vector from 15.0.2 to 16.0.0
(#1325)
add c8aee7f20 PARQUET-2171: Support Hadoop vectored IO (#1139)
add 202251b13 PARQUET-2458: Use --release 8 with java compiler (#1311)
add 1ae7da362 PARQUET-2398: Make static variables final (#1221)
add 09445b513 PARQUET-2451: Add BYTE_STREAM_SPLIT support for
FIXED_LEN_BYTE_ARRAY, INT32 and INT64 (#1291)
add 23c788d0c PARQUET-2463: Bump japicmp to 0.21.0 (#1329)
add cc22b5674 Bump net.alchim31.maven:scala-maven-plugin from 4.8.1 to
4.9.0 (#1331)
add ce0243130 Bump org.apache.maven.plugins:maven-shade-plugin from 3.5.2
to 3.5.3 (#1332)
add 337d0825d PARQUET-2171: (followup) add read metrics and hadoop conf
integration for vector io reader (#1330)
add cde9a6348 Update release note for 1.14.0 (#1336)
add 240ab0daa Prepare for 1.15.0 development
add 5cb50fb69 PARQUET-2462: Bump to Thrift 0.20.0 (#1327)
add 68609198c Bump org.apache:apache from 31 to 32 (#1333)
add 408c18b38 PARQUET-2465: Fall back to HadoopConfig (#1339)
add c241170d9 Update changes for the `master` branch (#1348)
add 3912bd259 PARQUET-2466: Simplify logic when calling `ParquetWriter`
(#1338)
add 8f2413277 Bump com.google.api.grpc:proto-google-common-protos (#1346)
add 4b6b808e0 Bump com.google.guava:guava from 33.1.0-jre to 33.2.0-jre
(#1345)
add b7005f55f PARQUET-2476: Remove the `maven-compiler` override (#1341)
add 77fa24eb2 Bump com.fasterxml.jackson.core:jackson-databind from 2.17.0
to 2.17.1 (#1344)
add f12229add PARQUET-2472: Close in finally block in
ParquetFileWriter#end (#1350)
add 6809a1859 PARQUET-2478: Update README with link to parquet website
(#1355)
add 9b11410f1 Update readme to point to 1.14.0 release (#1356)
add dd9014f3d PARQUET-2468: ParquetMetadata must convert to json (#1349)
add 3d3237a18 Bump org.codehaus.mojo:exec-maven-plugin from 3.2.0 to 3.3.0
(#1359)
add 7cd3e7abc Bump net.alchim31.maven:scala-maven-plugin from 4.9.0 to
4.9.1 (#1352)
add c9bbe78fd Bump org.apache.arrow:arrow-vector from 16.0.0 to 16.1.0
(#1354)
add 8b91d6c4d PARQUET-2487: Bump io.airlift:aircompressor from 0.26 to
0.27 (#1363)
add dab5aae88 PARQUET-34: Add #contains FilterPredicate for Array columns
(#1328)
add 1922a7499 Update NOTICE of parquet-avro (#1371)
add fd1514196 PARQUET-2494: Mark png files as binary in gitattributes
(#1372)
add bc603e994 PARQUET-2483: Update references to parquet-mr in Readmes
add 26268c941 PARQUET-2498: Vector IO to handle empty range list (#1374)
add 9275d594c PARQUET-34: Extend Contains support to all
ColumnFilterPredicate types (#1370)
add 7df7c75d1 MINOR: update CHANGES for 1.14.1 release
add fbe13d89a Bump commons-logging:commons-logging from 1.3.1 to 1.3.2
(#1366)
add 9d04cf3c4 Bump com.google.guava:guava from 33.2.0-jre to 33.2.1-jre
(#1367)
add 8fb542139 PARQUET-2499: Update NOTICE to Apache Parquet Java (#1375)
add 5ac50884e Add github section in asf.yaml to enable issues (#1362)
add fb9c17458 GH-2932: Adjust PR template to reference GitHub issue
tracker (#2933)
add 807bd5320 Bump org.apache.maven.plugins:maven-shade-plugin from 3.5.3
to 3.6.0 (#2922)
add 77ed3aa38 Bump org.easymock:easymock from 5.2.0 to 5.3.0 (#2924)
add e6d772826 GH-2930: Add issue templates (#2931)
add 087667971 GH-2939: Update PULL_REQUEST_TEMPLATE (#2940)
add 515ed4c14 MINOR: Make ColumnPath immutable (#1380)
add b92c0a899 Bump com.google.truth.extensions:truth-proto-extension
(#2936)
add cfaa0ba38 Update readme to 1.14.1 release (#2947)
add 74648366b Bump com.google.api.grpc:proto-google-common-protos (#2937)
add 1edaf0bf5 Bump commons-logging:commons-logging from 1.3.2 to 1.3.3
(#2954)
add 1de2af8b8 GH-2948: Fix NPE when using the AvroParquetReader.Builder
with LocalInputFile (#2949)
add b714b79ab PARQUET-2139: set metadata offset to 0 since it is not
written at all (#1369)
add 20651b8dd Bump org.codehaus.mojo:build-helper-maven-plugin from 3.5.0
to 3.6.0 (#1365)
add 824b7d009 GH-2935: Avoid double close of ParquetFileWriter (#2951)
add c928c4bfc GH-2959: Optimize the test case of parquet rewriter. (#2960)
add e8bbfbbd4 GH-2956: Use avro SchemaBuilder API to convert record (#2957)
add 7be98076f PARQUET-1126: Write unencrypted Parquet files without Hadoop
(#1376)
add ea3d2734a PARQUET-34: implement not() for Contains predicate (#2941)
add be6bf4b66 Bump com.h2database:h2 from 2.2.224 to 2.3.230 (#2963)
add 1ea4506e8 Bump zstd-jni.version from 1.5.6-2 to 1.5.6-3 (#2968)
add 1c76796da GH-2921: Remove Jackson JDK8 module (#1378)
add 5f956066d Bump com.fasterxml.jackson.core:jackson-databind from 2.17.1
to 2.17.2 (#2973)
add 26febded5 Bump jackson.version from 2.17.1 to 2.17.2 (#2964)
add fd829959d GH-2976: Parquet CLI compression commands should accept
lowercase compression name (#2977)
add 06c37b2f8 Bump org.apache.commons:commons-lang3 from 3.14.0 to 3.15.0
(#2979)
add d4384d3f2 Bump org.easymock:easymock from 5.3.0 to 5.4.0 (#2978)
add 312a15f53 GH-2992: Gate LocalTimestamp references in
AvroSchemaConverter (#2993)
add bc4e5b416 GH-2952: Add maven wrapper (#2953)
add 3ac860e11 GH-2994: Optimize string to binary conversion in
AvroWriteSupport (#2995)
add 3b5fb4b15 GH-2988: Supports disabling statistics for specific columns
(#2989)
add fafd9b033 GH-2986: Fails the file writing when footer size exceeds int
max value (#2987)
add aec7bc64d MINOR: ParquetRewriter must close opened reader/stream
(#3002)
add 08a4e7e62 PARQUET-2430: Add parquet joiner v2 (#1335)
add 2b36e99ba GH-3009: Bump zstd-jni.version from 1.5.6-3 to 1.5.6-6
(#3010)
add ac6a5a005 GH-2962: Set dictionary_page_offset even when encoding_stats
are missing (#3012)
add fcfd427a1 GH-3007: Ensure version specific Jackson classes are shaded
(#3017)
add 0c8b757a8 GH-3016: Do not use dependency-reduced pom for attached
shaded artifact (#3015)
add 9d33db2f6 MINOR: Don't run all the tests on a release (#2999)
add 9b4a95b23 Bump org.tukaani:xz from 1.9 to 1.10 (#2985)
add 96de3f4c3 GH-3013: Fix potential ClassCastException at reading
DELTA_BYTE_ARRAY encoding (#3019)
add d3f621bde Bump com.google.protobuf:protobuf-java in /parquet-protobuf
(#3018)
add eed26b4ea GH-3021: Upgrade Avro dependency (#3022)
add 5baa9036e GH-3026: Add a fix to ParquetRewriter when you try to
nullify and encrypt 2 separate columns (#3027)
add 42cf31c0f Bump io.airlift:aircompressor from 0.27 to 2.0.2 (#3023)
add 73a4430af PARQUET-3031: Support to transfer input stream when building
ParquetFileReader (#3030)
add d2128afda GH-3029: Fix EncryptionPropertiesHelper not to use
java.nio.file.Path (#3038)
add 72520d2b9 Bump net.openhft:zero-allocation-hashing from 0.16 to
0.26ea0 (#3024)
add bdc93464c Bump org.apache.arrow:arrow-vector from 16.1.0 to 17.0.0
(#2980)
add 2e765cc04 GH-3040: DictionaryFilter.canDrop may return false positive
result when dict size exceeds 8k (#3041)
add 985c34d26 MINOR: Throw exception in BytesInput (#3042)
add 042547a8d MINOR: Update version in `README.md` (#3045)
add 356dd3bb7 MINOR: Update `issueManagement` in `pom.xml` (#3046)
add bc90dd5d1 MINOR: Bump Maven parent pom (#3048)
add a86959937 MINOR: Bump Thrift to 0.21.0 (#3049)
add 4fb75181e Support int value for `timeOfDay` in `ProtoTimeConverter`
(#3034)
add 40972b33c MINOR: Redirect to releases (#3058)
add 54335a6f1 MINOR: Bump latest version to 1.14.4 (#3057)
add 34359c95d GH-3055: Disable column statistics for all columns by
configuration (#3056)
add 686f07147 GH-3035: ParquetRewriter: Add a column renaming feature
(#3036)
add e51bcb359 Bump org.xerial.snappy:snappy-java from 1.1.10.5 to 1.1.10.7
(#3053)
add efda65e87 Bump org.codehaus.mojo:buildnumber-maven-plugin from 3.2.0
to 3.2.1 (#3054)
add 331aea026 Bump jackson.version from 2.17.2 to 2.18.1 (#3052)
add ccac04f84 GH-3059: Add configuration to disable size statistics (#3060)
add 1e04ec740 GH-3068: Remove `parquet-scala` (#3063)
add 54f219871 Bump org.apache.maven.plugins:maven-dependency-plugin (#3064)
add 410f5e1f9 Bump org.apache.commons:commons-lang3 from 3.15.0 to 3.17.0
(#3065)
add e24d8d457 Bump commons-io:commons-io from 2.16.1 to 2.18.0 (#3071)
add 84ba54a3a [maven-release-plugin] prepare release
apache-parquet-1.15.0-rc1
add 78a3b76f4 [maven-release-plugin] prepare for next development iteration
add 77c80f52b Revert "[maven-release-plugin] prepare release
apache-parquet-1.15.0-rc1"
add e32ed7410 Revert "[maven-release-plugin] prepare for next development
iteration"
add 586a35442 GH-2943: Remove hadoop-2 support (#3061)
add 8fa70320a MINOR: Use `exec-maven-plugin.version` property (#3047)
add 7b599eded Revert "Revert "[maven-release-plugin] prepare for next
development iteration""
add 7180c47a3 MINOR: Add shading for JDK22 specific classes (#3081)
add 7644e2771 MINOR: Revert `buildnumber-maven-plugin` to 3.2.0 (#3082)
add bcf5abcbc GH-3086: Allow for empty beans (#3087)
add 0ddffb272 GH-3089: Add missing license header to pom.xml (#3090)
add f4a3e8b65 GH-3078: Use Hadoop FileSystem.openFile() to open files
(#3079)
add 4aeba6cb7 MINOR: bump version to 1.16.0-SNAPSHOT (#3097)
add f362765b2 Bump org.codehaus.mojo:exec-maven-plugin from 3.3.0 to 3.5.0
(#3092)
add 1c9ead4f9 Bump commons-logging:commons-logging from 1.3.3 to 1.3.4
(#3094)
add a3bfbcddd Bump net.openhft:zero-allocation-hashing from 0.26ea0 to
0.27ea0 (#3093)
add 498531825 Bump com.google.api.grpc:proto-google-common-protos (#3109)
add e0e778536 Bump jackson.version from 2.18.1 to 2.18.2 (#3108)
add 7f7790833 MINOR: Remove `scala` properties from `pom.xml` (#3104)
add d6c80d7dd GH-3114: Fix LogicalType conversions for nested records on
Avro <= 1.8 (#3111)
add 10d27330a Bump com.google.truth.extensions:truth-proto-extension
(#3107)
add 9aadcf565 Bump org.cyclonedx:cyclonedx-maven-plugin from 2.8.0 to
2.9.1 (#3120)
add 7a99d86d5 Bump org.apache.commons:commons-text from 1.12.0 to 1.13.0
(#3119)
add b65934204 MINOR: Remove Joda as a direct dependency (#3132)
add a4aa781da Bump org.easymock:easymock from 5.4.0 to 5.5.0 (#3131)
add b7058f5e6 GH-3099 add libthrift to parquet-cli shaded jar (#3100)
add 8127cc3fe GH-3127: Enabled `parquet.hadoop.vectored.io.enabled` by
default (#3128)
add ec537c7da GH-3123: Omit level histogram for some max levels (#3124)
add d5f86d7c0 GH-3133: Fix SizeStatistics to handle omitted histogram
(#3134)
add be5ada2e9 GH-3125: Add CLI for SizeStatistics (#3126)
add bb4f867c4 GH-3115: Fix int96 read issue in complex type (#3118)
add bcd161ca5 MINOR: Remove `parquet-tools` from `NOTICE` (#3140)
add 7bac7a96d Bump com.google.guava:guava from 33.2.1-jre to 33.4.0-jre
(#3137)
add 3306fd605 Bump protobuf.version from 3.25.5 to 3.25.6 (#3138)
add fb6f0be03 Improve exception message in InternalFileDecryptor. (#3143)
add 43226d34c Bump com.google.api.grpc:proto-google-common-protos (#3151)
add 92354f6be MINOR: Remove release script (#3144)
add 6797280d2 Deprecate Apache Pig Integration (#3153)
add 78c9c5cb9 Bump com.h2database:h2 from 2.3.230 to 2.3.232 (#3158)
add 05dc53841 Bump commons-logging:commons-logging from 1.3.4 to 1.3.5
(#3159)
add 37a29d98f Add logical type annotation for `UnknownType` (#3154)
add 5468116c1 GH-3156: Enable vectored IO by default (#3155)
add 3174442f5 Bump it.unimi.dsi:fastutil from 8.5.13 to 8.5.15 (#3162)
add 41e294c7f GH-3122: Correct V2 page header compression fields for
zero-size data pages (#3148)
add 976e2d23b GH-3163: Reduce memory and time overhead of
ParquetRewriterTests (#3164)
add d639b064c MINOR: Reader fails fast when footer size is larger than
INT_MAX (#3136)
add 680edfa71 GH-3168: Restrict trusted packages in the parquet-avro
module (#3169)
add b6d54cccc GH-3172: Do not drop blocks with some null values if
`DictionaryFilter` is applied for `UserDefinedPredicate` which keeps null
values (#3173)
add 868bcebd7 Bump protobuf.version from 3.25.3 to 4.26.0
This update added new revisions after undoing existing revisions.
That is to say, some revisions that were in the old version of the
branch are not in the new version. This situation occurs
when a user --force pushes a change and generates a repository
containing something like this:
* -- * -- B -- O -- O -- O (a3c631747)
\
N -- N -- N refs/heads/dependabot/maven/protobuf.version-4.26.0
(868bcebd7)
You should already have received notification emails for all of the O
revisions, and so the following emails describe only the N revisions
from the common base, B.
Any revisions marked "omit" are not gone; other references still
refer to them. Any revisions marked "discard" are gone forever.
No new revisions were added by this update.
Summary of changes:
.asf.yaml | 18 +
.gitattributes | 1 +
.../ISSUE_TEMPLATE/bug_report.yaml | 32 +-
.../bundle => .github/ISSUE_TEMPLATE/config.yaml | 4 +-
.../ISSUE_TEMPLATE/feature_request.yaml | 39 +-
.github/ISSUE_TEMPLATE/usage_question.yaml | 69 ++
.github/PULL_REQUEST_TEMPLATE.md | 45 +-
.github/workflows/ci-hadoop2.yml | 56 --
.github/workflows/ci-hadoop3.yml | 8 +-
.github/workflows/vector-plugins.yml | 8 +-
.../wrapper/maven-wrapper.properties | 5 +-
CHANGES.md | 163 +++++
LICENSE | 10 -
NOTICE | 21 +-
README.md | 99 ++-
dev/README.md | 93 ---
dev/ci-before_install.sh | 2 +-
dev/finalize-release | 8 +-
dev/merge_parquet_pr.py | 393 -----------
dev/prepare-release.sh | 10 +-
mvnw | 259 +++++++
mvnw.cmd | 149 ++++
parquet-arrow/pom.xml | 4 +-
.../parquet/arrow/schema/SchemaConverter.java | 30 +
parquet-avro/pom.xml | 4 +-
.../org/apache/parquet/avro/AvroConverters.java | 39 ++
.../org/apache/parquet/avro/AvroParquetReader.java | 4 +-
.../org/apache/parquet/avro/AvroReadSupport.java | 5 +-
.../apache/parquet/avro/AvroRecordConverter.java | 10 +-
.../apache/parquet/avro/AvroSchemaConverter.java | 65 +-
.../org/apache/parquet/avro/AvroWriteSupport.java | 4 +-
parquet-avro/src/main/resources/META-INF/NOTICE | 4 +-
.../apache/parquet/UntrustedStringableClass.java} | 14 +-
.../parquet/avro/TestArrayCompatibility.java | 20 +
.../parquet/avro/TestAvroRecordConverter.java | 37 +-
.../parquet/avro/TestAvroSchemaConverter.java | 200 ++++--
.../org/apache/parquet/avro/TestReadWrite.java | 22 +
.../apache/parquet/avro/TestReflectReadWrite.java | 35 +
parquet-benchmarks/README.md | 10 +-
parquet-benchmarks/pom.xml | 2 +-
parquet-benchmarks/run.sh | 2 +-
.../parquet/benchmarks/FilteringBenchmarks.java | 4 +-
.../benchmarks/NestedNullWritingBenchmarks.java | 2 +-
parquet-cli/README.md | 6 +-
parquet-cli/pom.xml | 13 +-
.../java/org/apache/parquet/cli/BaseCommand.java | 6 +-
.../src/main/java/org/apache/parquet/cli/Main.java | 2 +
.../parquet/cli/commands/RewriteCommand.java | 3 +-
.../cli/commands/ShowSizeStatisticsCommand.java | 116 ++++
.../cli/commands/TransCompressionCommand.java | 3 +-
parquet-cli/src/main/resources/META-INF/NOTICE | 4 +-
.../parquet/cli/commands/RewriteCommandTest.java | 28 +
...est.java => ShowSizeStatisticsCommandTest.java} | 6 +-
.../cli/commands/TransCompressionCommandTest.java | 19 +-
parquet-column/pom.xml | 26 +-
.../java/org/apache/parquet/column/Encoding.java | 9 +
.../apache/parquet/column/ParquetProperties.java | 173 ++++-
.../parquet/column/impl/ColumnReaderBase.java | 1 -
.../parquet/column/impl/ColumnValueCollector.java | 15 +-
.../parquet/column/statistics/NoopStatistics.java | 130 ++++
.../parquet/column/statistics/SizeStatistics.java | 93 ++-
.../parquet/column/statistics/Statistics.java | 9 +
.../ByteStreamSplitValuesReader.java | 47 +-
.../ByteStreamSplitValuesReaderForDouble.java | 9 +-
...ava => ByteStreamSplitValuesReaderForFLBA.java} | 18 +-
.../ByteStreamSplitValuesReaderForFloat.java | 9 +-
.../ByteStreamSplitValuesReaderForInteger.java | 13 +-
.../ByteStreamSplitValuesReaderForLong.java | 13 +-
.../ByteStreamSplitValuesWriter.java | 58 +-
.../values/deltastrings/DeltaByteArrayReader.java | 2 +-
.../factory/DefaultV1ValuesWriterFactory.java | 54 +-
.../factory/DefaultV2ValuesWriterFactory.java | 56 +-
.../parquet/example/data/simple/SimpleGroup.java | 28 +-
.../parquet/filter2/compat/FilterCompat.java | 8 +-
...lInverseRewriter.java => ContainsRewriter.java} | 101 ++-
.../parquet/filter2/predicate/FilterApi.java | 6 +
.../parquet/filter2/predicate/FilterPredicate.java | 5 +
.../filter2/predicate/LogicalInverseRewriter.java | 6 +
.../parquet/filter2/predicate/LogicalInverter.java | 6 +
.../parquet/filter2/predicate/Operators.java | 194 +++++-
.../predicate/SchemaCompatibilityValidator.java | 21 +-
.../IncrementallyUpdatedFilterPredicate.java | 80 ++-
.../column/columnindex/ColumnIndexBuilder.java | 45 +-
.../internal/column/columnindex/IndexIterator.java | 113 +++
.../column/columnindex/OffsetIndexBuilder.java | 11 +-
.../filter2/columnindex/ColumnIndexFilter.java | 6 +
.../java/org/apache/parquet/io/api/Binary.java | 4 +-
.../parquet/schema/LogicalTypeAnnotation.java | 41 ++
.../parquet/schema/PrimitiveStringifier.java | 7 +
.../main/java/org/apache/parquet/schema/Types.java | 6 +
.../column/impl/TestCorruptDeltaByteArrays.java | 44 +-
.../column/statistics/TestSizeStatistics.java | 19 +-
.../parquet/column/statistics/TestStatistics.java | 27 +
.../ByteStreamSplitValuesEndToEndTest.java | 116 +++-
.../ByteStreamSplitValuesReaderTest.java | 209 ++++--
.../ByteStreamSplitValuesWriterTest.java | 99 ++-
.../factory/DefaultValuesWriterFactoryTest.java | 404 +++++++++--
...erseRewriter.java => TestContainsRewriter.java} | 58 +-
.../filter2/predicate/TestFilterApiMethods.java | 41 ++
.../TestSchemaCompatibilityValidator.java | 26 +-
.../column/columnindex/TestColumnIndexBuilder.java | 57 ++
.../column/columnindex/TestIndexIterator.java | 91 +++
.../filter2/columnindex/TestColumnIndexFilter.java | 70 +-
parquet-common/pom.xml | 24 +-
.../parquet/ParquetSizeOverflowException.java | 15 +-
.../java/org/apache/parquet/bytes/BytesInput.java | 14 +-
.../bytes/LittleEndianDataOutputStream.java | 11 +-
.../apache/parquet/hadoop/metadata/ColumnPath.java | 10 +-
.../parquet/io/DelegatingPositionOutputStream.java | 6 +-
.../org/apache/parquet/io/LocalOutputFile.java | 7 +-
.../org/apache/parquet/io/ParquetFileRange.java | 71 ++
.../org/apache/parquet/io/SeekableInputStream.java | 27 +
.../java/org/apache/parquet/util/DynMethods.java | 14 +-
.../bytes/AvailableAgnosticInputStream.java | 19 +-
.../org/apache/parquet/bytes/TestBytesInput.java | 14 +
parquet-encoding/pom.xml | 24 +-
parquet-format-structures/pom.xml | 4 +-
parquet-generator/pom.xml | 2 +-
...crementallyUpdatedFilterPredicateGenerator.java | 313 ++++++++-
parquet-hadoop-bundle/pom.xml | 2 +-
parquet-hadoop/README.md | 41 ++
parquet-hadoop/pom.xml | 41 +-
.../java/org/apache/parquet/HadoopReadOptions.java | 3 +
.../org/apache/parquet/ParquetReadOptions.java | 20 +
.../org/apache/parquet/crypto/AesCtrDecryptor.java | 4 +-
.../org/apache/parquet/crypto/AesGcmDecryptor.java | 4 +-
.../crypto/EncryptionPropertiesFactory.java | 17 +-
.../crypto/InternalColumnEncryptionSetup.java | 3 +-
.../parquet/crypto/InternalFileDecryptor.java | 8 +-
.../filter2/bloomfilterlevel/BloomFilterImpl.java | 5 +
.../filter2/dictionarylevel/DictionaryFilter.java | 10 +
.../filter2/statisticslevel/StatisticsFilter.java | 6 +
.../format/converter/ParquetMetadataConverter.java | 173 ++++-
.../org/apache/parquet/hadoop/CodecFactory.java | 21 +-
.../parquet/hadoop/ColumnChunkPageWriteStore.java | 55 +-
.../apache/parquet/hadoop/DirectCodecFactory.java | 4 +-
.../parquet/hadoop/EncryptionPropertiesHelper.java | 52 ++
.../apache/parquet/hadoop/ParquetFileReader.java | 201 +++++-
.../apache/parquet/hadoop/ParquetFileWriter.java | 236 ++++++-
.../apache/parquet/hadoop/ParquetInputFormat.java | 11 +
.../apache/parquet/hadoop/ParquetInputSplit.java | 19 +-
.../apache/parquet/hadoop/ParquetOutputFormat.java | 52 +-
.../org/apache/parquet/hadoop/ParquetReader.java | 38 +-
.../apache/parquet/hadoop/ParquetRecordWriter.java | 57 ++
.../org/apache/parquet/hadoop/ParquetWriter.java | 100 ++-
.../org/apache/parquet/hadoop/api/InitContext.java | 2 +
.../org/apache/parquet/hadoop/api/ReadSupport.java | 11 +-
.../apache/parquet/hadoop/api/WriteSupport.java | 5 +-
.../parquet/hadoop/codec/NonBlockedCompressor.java | 19 +-
.../hadoop/codec/NonBlockedDecompressor.java | 19 +-
.../parquet/hadoop/codec/ZstdCompressorStream.java | 4 +-
.../hadoop/metadata/ColumnChunkMetaData.java | 4 +
.../hadoop/metadata/ColumnChunkProperties.java | 2 +
.../parquet/hadoop/metadata/FileMetaData.java | 2 +
.../parquet/hadoop/metadata/ParquetMetadata.java | 33 +-
.../parquet/hadoop/rewrite/ParquetRewriter.java | 594 +++++++++++-----
.../parquet/hadoop/rewrite/RewriteOptions.java | 281 +++++++-
.../parquet/hadoop/util/H1SeekableInputStream.java | 19 +
.../parquet/hadoop/util/H2SeekableInputStream.java | 18 +
.../parquet/hadoop/util/HadoopInputFile.java | 61 +-
.../hadoop/util/HadoopPositionOutputStream.java | 4 +-
.../hadoop/util/wrapped/io/BindingUtils.java | 94 +++
.../hadoop/util/wrapped/io/FileRangeBridge.java | 280 ++++++++
.../parquet/hadoop/util/wrapped/io/FutureIO.java | 140 ++++
.../hadoop/util/wrapped/io/VectorIoBridge.java | 423 ++++++++++++
.../hadoop/util/wrapped/io/package-info.java | 25 +
.../org/apache/hadoop/fs/FileSystemTestBinder.java | 77 +++
.../crypto/EncryptionPropertiesFactoryTest.java | 23 +
.../dictionarylevel/DictionaryFilterTest.java | 74 +-
.../filter2/recordlevel/PhoneBookWriter.java | 56 +-
.../recordlevel/TestRecordLevelFilters.java | 235 ++++++-
.../statisticslevel/TestStatisticsFilter.java | 34 +
.../converter/TestParquetMetadataConverter.java | 74 +-
.../apache/parquet/hadoop/TestBloomFiltering.java | 57 +-
.../hadoop/TestInputFormatColumnProjection.java | 30 +-
.../hadoop/TestInterOpReadByteStreamSplit.java | 39 +-
.../parquet/hadoop/TestParquetFileWriter.java | 91 ++-
.../apache/parquet/hadoop/TestParquetWriter.java | 183 ++++-
.../parquet/hadoop/TestParquetWriterError.java | 9 +-
.../hadoop/example/TestInputOutputFormat.java | 29 +-
.../hadoop/metadata/TestParquetMetadata.java | 113 +++
.../hadoop/rewrite/ParquetRewriterTest.java | 764 +++++++++++++++------
.../parquet/hadoop/util/TestFileBuilder.java | 28 +-
.../parquet/hadoop/util/TestHadoopOpenFile.java | 283 ++++++++
.../util/wrapped/io/TestFileRangeBridge.java | 103 +++
.../hadoop/util/wrapped/io/TestVectorIoBridge.java | 586 ++++++++++++++++
.../parquet/statistics/DataGenerationContext.java | 79 ++-
.../statistics/TestSizeStatisticsRoundTrip.java | 66 +-
.../apache/parquet/statistics/TestStatistics.java | 171 ++++-
.../resources/test-expected-parquet-metadata.json | 500 ++++++++++++++
parquet-jackson/README.md | 6 +-
parquet-jackson/pom.xml | 38 +-
parquet-pig-bundle/pom.xml | 95 ---
.../src/main/resources/META-INF/LICENSE | 248 -------
parquet-pig/REVIEWERS.md | 25 -
parquet-pig/pom.xml | 146 ----
.../java/org/apache/parquet/pig/ParquetLoader.java | 595 ----------------
.../java/org/apache/parquet/pig/ParquetStorer.java | 143 ----
.../java/org/apache/parquet/pig/PigMetaData.java | 89 ---
.../org/apache/parquet/pig/PigSchemaConverter.java | 563 ---------------
.../parquet/pig/SchemaConversionException.java | 42 --
.../parquet/pig/TupleConversionException.java | 41 --
.../org/apache/parquet/pig/TupleReadSupport.java | 221 ------
.../org/apache/parquet/pig/TupleWriteSupport.java | 223 ------
.../apache/parquet/pig/convert/DecimalUtils.java | 65 --
.../apache/parquet/pig/convert/MapConverter.java | 210 ------
.../parquet/pig/convert/ParentValueContainer.java | 32 -
.../apache/parquet/pig/convert/TupleConverter.java | 609 ----------------
.../pig/convert/TupleRecordMaterializer.java | 49 --
.../apache/parquet/pig/summary/BagSummaryData.java | 71 --
.../org/apache/parquet/pig/summary/EnumStat.java | 115 ----
.../parquet/pig/summary/FieldSummaryData.java | 176 -----
.../apache/parquet/pig/summary/MapSummaryData.java | 83 ---
.../parquet/pig/summary/NumberSummaryData.java | 46 --
.../parquet/pig/summary/StringSummaryData.java | 78 ---
.../org/apache/parquet/pig/summary/Summary.java | 220 ------
.../apache/parquet/pig/summary/SummaryData.java | 133 ----
.../parquet/pig/summary/TupleSummaryData.java | 93 ---
.../org/apache/parquet/pig/summary/ValueStat.java | 62 --
.../test/java/org/apache/parquet/pig/PerfTest.java | 104 ---
.../java/org/apache/parquet/pig/PerfTest2.java | 185 -----
.../apache/parquet/pig/PerfTestReadAllCols.java | 44 --
.../org/apache/parquet/pig/TestDecimalUtils.java | 76 --
.../org/apache/parquet/pig/TestParquetLoader.java | 380 ----------
.../org/apache/parquet/pig/TestParquetStorer.java | 273 --------
.../apache/parquet/pig/TestPigSchemaConverter.java | 280 --------
.../parquet/pig/TestTupleRecordConsumer.java | 223 ------
.../apache/parquet/pig/TupleConsumerPerfTest.java | 213 ------
.../apache/parquet/pig/summary/TestSummary.java | 172 -----
parquet-pig/src/test/resources/log4j.properties | 23 -
parquet-plugins/parquet-encoding-vector/pom.xml | 36 +-
parquet-plugins/parquet-plugins-benchmarks/pom.xml | 4 +-
parquet-protobuf/pom.xml | 8 +-
.../parquet/proto/ProtoMessageConverter.java | 5 +
.../src/main/resources/META-INF/NOTICE | 4 +-
parquet-scala/pom.xml | 97 ---
.../scala/org/apache/parquet/filter2/dsl/Dsl.scala | 112 ---
.../org/apache/parquet/filter2/dsl/DslTest.scala | 87 ---
parquet-thrift/pom.xml | 12 +-
.../parquet/thrift/pig/ParquetThriftStorer.java | 3 +
.../thrift/pig/TupleToThriftWriteSupport.java | 3 +
.../apache/parquet/thrift/struct/ThriftType.java | 8 +-
pom.xml | 138 ++--
243 files changed, 10676 insertions(+), 8732 deletions(-)
copy parquet-generator/src/main/resources/parquet-version.properties =>
.github/ISSUE_TEMPLATE/bug_report.yaml (55%)
copy parquet-pig-bundle/src/main/resources/org/apache/parquet/bundle =>
.github/ISSUE_TEMPLATE/config.yaml (96%)
copy parquet-benchmarks/src/main/resources/log4j.properties =>
.github/ISSUE_TEMPLATE/feature_request.yaml (52%)
create mode 100644 .github/ISSUE_TEMPLATE/usage_question.yaml
delete mode 100644 .github/workflows/ci-hadoop2.yml
rename parquet-pig-bundle/src/main/resources/org/apache/parquet/bundle =>
.mvn/wrapper/maven-wrapper.properties (82%)
delete mode 100644 dev/README.md
delete mode 100755 dev/merge_parquet_pr.py
create mode 100755 mvnw
create mode 100644 mvnw.cmd
copy
parquet-avro/src/{main/java/org/apache/parquet/avro/GenericDataSupplier.java =>
test/java/org/apache/parquet/UntrustedStringableClass.java} (78%)
create mode 100644
parquet-cli/src/main/java/org/apache/parquet/cli/commands/ShowSizeStatisticsCommand.java
copy
parquet-cli/src/test/java/org/apache/parquet/cli/commands/{ShowPagesCommandTest.java
=> ShowSizeStatisticsCommandTest.java} (84%)
create mode 100644
parquet-column/src/main/java/org/apache/parquet/column/statistics/NoopStatistics.java
copy
parquet-column/src/main/java/org/apache/parquet/column/values/bytestreamsplit/{ByteStreamSplitValuesReaderForFloat.java
=> ByteStreamSplitValuesReaderForFLBA.java} (66%)
copy
parquet-avro/src/main/java/org/apache/parquet/avro/SpecificDataSupplier.java =>
parquet-column/src/main/java/org/apache/parquet/column/values/bytestreamsplit/ByteStreamSplitValuesReaderForInteger.java
(72%)
copy
parquet-avro/src/main/java/org/apache/parquet/avro/SpecificDataSupplier.java =>
parquet-column/src/main/java/org/apache/parquet/column/values/bytestreamsplit/ByteStreamSplitValuesReaderForLong.java
(73%)
copy
parquet-column/src/main/java/org/apache/parquet/filter2/predicate/{LogicalInverseRewriter.java
=> ContainsRewriter.java} (50%)
copy
parquet-column/src/test/java/org/apache/parquet/filter2/predicate/{TestLogicalInverseRewriter.java
=> TestContainsRewriter.java} (58%)
copy
parquet-column/src/main/java/org/apache/parquet/io/InvalidFileOffsetException.java
=>
parquet-common/src/main/java/org/apache/parquet/ParquetSizeOverflowException.java
(76%)
create mode 100644
parquet-common/src/main/java/org/apache/parquet/io/ParquetFileRange.java
copy parquet-cli/src/main/java/org/apache/parquet/cli/util/GetClassLoader.java
=>
parquet-common/src/test/java/org/apache/parquet/bytes/AvailableAgnosticInputStream.java
(65%)
create mode 100644
parquet-hadoop/src/main/java/org/apache/parquet/hadoop/EncryptionPropertiesHelper.java
create mode 100644
parquet-hadoop/src/main/java/org/apache/parquet/hadoop/util/wrapped/io/BindingUtils.java
create mode 100644
parquet-hadoop/src/main/java/org/apache/parquet/hadoop/util/wrapped/io/FileRangeBridge.java
create mode 100644
parquet-hadoop/src/main/java/org/apache/parquet/hadoop/util/wrapped/io/FutureIO.java
create mode 100644
parquet-hadoop/src/main/java/org/apache/parquet/hadoop/util/wrapped/io/VectorIoBridge.java
create mode 100644
parquet-hadoop/src/main/java/org/apache/parquet/hadoop/util/wrapped/io/package-info.java
create mode 100644
parquet-hadoop/src/test/java/org/apache/hadoop/fs/FileSystemTestBinder.java
create mode 100644
parquet-hadoop/src/test/java/org/apache/parquet/hadoop/metadata/TestParquetMetadata.java
create mode 100644
parquet-hadoop/src/test/java/org/apache/parquet/hadoop/util/TestHadoopOpenFile.java
create mode 100644
parquet-hadoop/src/test/java/org/apache/parquet/hadoop/util/wrapped/io/TestFileRangeBridge.java
create mode 100644
parquet-hadoop/src/test/java/org/apache/parquet/hadoop/util/wrapped/io/TestVectorIoBridge.java
create mode 100644
parquet-hadoop/src/test/resources/test-expected-parquet-metadata.json
delete mode 100644 parquet-pig-bundle/pom.xml
delete mode 100644 parquet-pig-bundle/src/main/resources/META-INF/LICENSE
delete mode 100644 parquet-pig/REVIEWERS.md
delete mode 100644 parquet-pig/pom.xml
delete mode 100644
parquet-pig/src/main/java/org/apache/parquet/pig/ParquetLoader.java
delete mode 100644
parquet-pig/src/main/java/org/apache/parquet/pig/ParquetStorer.java
delete mode 100644
parquet-pig/src/main/java/org/apache/parquet/pig/PigMetaData.java
delete mode 100644
parquet-pig/src/main/java/org/apache/parquet/pig/PigSchemaConverter.java
delete mode 100644
parquet-pig/src/main/java/org/apache/parquet/pig/SchemaConversionException.java
delete mode 100644
parquet-pig/src/main/java/org/apache/parquet/pig/TupleConversionException.java
delete mode 100644
parquet-pig/src/main/java/org/apache/parquet/pig/TupleReadSupport.java
delete mode 100644
parquet-pig/src/main/java/org/apache/parquet/pig/TupleWriteSupport.java
delete mode 100644
parquet-pig/src/main/java/org/apache/parquet/pig/convert/DecimalUtils.java
delete mode 100644
parquet-pig/src/main/java/org/apache/parquet/pig/convert/MapConverter.java
delete mode 100644
parquet-pig/src/main/java/org/apache/parquet/pig/convert/ParentValueContainer.java
delete mode 100644
parquet-pig/src/main/java/org/apache/parquet/pig/convert/TupleConverter.java
delete mode 100644
parquet-pig/src/main/java/org/apache/parquet/pig/convert/TupleRecordMaterializer.java
delete mode 100644
parquet-pig/src/main/java/org/apache/parquet/pig/summary/BagSummaryData.java
delete mode 100644
parquet-pig/src/main/java/org/apache/parquet/pig/summary/EnumStat.java
delete mode 100644
parquet-pig/src/main/java/org/apache/parquet/pig/summary/FieldSummaryData.java
delete mode 100644
parquet-pig/src/main/java/org/apache/parquet/pig/summary/MapSummaryData.java
delete mode 100644
parquet-pig/src/main/java/org/apache/parquet/pig/summary/NumberSummaryData.java
delete mode 100644
parquet-pig/src/main/java/org/apache/parquet/pig/summary/StringSummaryData.java
delete mode 100644
parquet-pig/src/main/java/org/apache/parquet/pig/summary/Summary.java
delete mode 100644
parquet-pig/src/main/java/org/apache/parquet/pig/summary/SummaryData.java
delete mode 100644
parquet-pig/src/main/java/org/apache/parquet/pig/summary/TupleSummaryData.java
delete mode 100644
parquet-pig/src/main/java/org/apache/parquet/pig/summary/ValueStat.java
delete mode 100644
parquet-pig/src/test/java/org/apache/parquet/pig/PerfTest.java
delete mode 100644
parquet-pig/src/test/java/org/apache/parquet/pig/PerfTest2.java
delete mode 100644
parquet-pig/src/test/java/org/apache/parquet/pig/PerfTestReadAllCols.java
delete mode 100644
parquet-pig/src/test/java/org/apache/parquet/pig/TestDecimalUtils.java
delete mode 100644
parquet-pig/src/test/java/org/apache/parquet/pig/TestParquetLoader.java
delete mode 100644
parquet-pig/src/test/java/org/apache/parquet/pig/TestParquetStorer.java
delete mode 100644
parquet-pig/src/test/java/org/apache/parquet/pig/TestPigSchemaConverter.java
delete mode 100644
parquet-pig/src/test/java/org/apache/parquet/pig/TestTupleRecordConsumer.java
delete mode 100644
parquet-pig/src/test/java/org/apache/parquet/pig/TupleConsumerPerfTest.java
delete mode 100644
parquet-pig/src/test/java/org/apache/parquet/pig/summary/TestSummary.java
delete mode 100644 parquet-pig/src/test/resources/log4j.properties
delete mode 100644 parquet-scala/pom.xml
delete mode 100644
parquet-scala/src/main/scala/org/apache/parquet/filter2/dsl/Dsl.scala
delete mode 100644
parquet-scala/src/test/scala/org/apache/parquet/filter2/dsl/DslTest.scala