You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@orc.apache.org by do...@apache.org on 2022/10/19 16:03:34 UTC
[orc] branch branch-1.8 updated: ORC-1292: Add paragraph in java documentation
This is an automated email from the ASF dual-hosted git repository.
dongjoon pushed a commit to branch branch-1.8
in repository https://gitbox.apache.org/repos/asf/orc.git
The following commit(s) were added to refs/heads/branch-1.8 by this push:
new 11d142280 ORC-1292: Add paragraph in java documentation
11d142280 is described below
commit 11d142280a4d3127a717147ecd845ce1114c37e9
Author: deshanxiao <de...@microsoft.com>
AuthorDate: Wed Oct 19 09:03:17 2022 -0700
ORC-1292: Add paragraph in java documentation
### What changes were proposed in this pull request?
This PR is aimed to add paragraph in java documentation.
### Why are the changes needed?
In java doc, blank line will be ignored. We need to add "\<p\>" to display it. #1278
### How was this patch tested?
UT
Closes #1285 from deshanxiao/deshan/fix-doc.
Authored-by: deshanxiao <de...@microsoft.com>
Signed-off-by: Dongjoon Hyun <do...@apache.org>
(cherry picked from commit ce6588dd084e57d67af6ced2150acc5e490b0ddc)
Signed-off-by: Dongjoon Hyun <do...@apache.org>
---
java/core/src/java/org/apache/orc/DataMask.java | 2 +-
java/core/src/java/org/apache/orc/EncryptionVariant.java | 2 +-
java/core/src/java/org/apache/orc/InMemoryKeystore.java | 6 +++---
java/core/src/java/org/apache/orc/MemoryManager.java | 2 +-
java/core/src/java/org/apache/orc/OrcUtils.java | 2 +-
java/core/src/java/org/apache/orc/PhysicalWriter.java | 2 +-
java/core/src/java/org/apache/orc/Reader.java | 2 +-
java/core/src/java/org/apache/orc/impl/DateUtils.java | 4 ++--
java/core/src/java/org/apache/orc/impl/DynamicIntArray.java | 6 +++---
java/core/src/java/org/apache/orc/impl/MemoryManagerImpl.java | 2 +-
java/core/src/java/org/apache/orc/impl/StreamName.java | 2 +-
.../src/java/org/apache/orc/impl/StringHashTableDictionary.java | 2 +-
java/core/src/java/org/apache/orc/impl/WriterImpl.java | 6 +++---
java/core/src/java/org/apache/orc/impl/filter/VectorFilter.java | 2 +-
java/core/src/java/org/apache/orc/impl/mask/RedactMaskFactory.java | 6 +++---
java/core/src/java/org/apache/orc/impl/reader/StripePlanner.java | 2 +-
java/core/src/java/org/apache/orc/impl/writer/WriterImplV2.java | 6 +++---
java/core/src/java/org/apache/orc/util/BloomFilter.java | 4 ++--
java/core/src/java/org/apache/orc/util/CuckooSetBytes.java | 6 +++---
java/core/src/java/org/apache/orc/util/Murmur3.java | 4 ++--
java/mapreduce/src/java/org/apache/orc/mapred/OrcKey.java | 2 +-
java/mapreduce/src/java/org/apache/orc/mapred/OrcValue.java | 2 +-
java/shims/src/java/org/apache/orc/EncryptionAlgorithm.java | 2 +-
java/shims/src/java/org/apache/orc/impl/HadoopShimsPre2_6.java | 2 +-
java/shims/src/java/org/apache/orc/impl/HadoopShimsPre2_7.java | 2 +-
25 files changed, 40 insertions(+), 40 deletions(-)
diff --git a/java/core/src/java/org/apache/orc/DataMask.java b/java/core/src/java/org/apache/orc/DataMask.java
index 021d4f175..57701b4cd 100644
--- a/java/core/src/java/org/apache/orc/DataMask.java
+++ b/java/core/src/java/org/apache/orc/DataMask.java
@@ -24,7 +24,7 @@ import java.util.ServiceLoader;
/**
* The API for masking data during column encryption for ORC.
- *
+ * <p>
* They apply to an individual column (via ColumnVector) instead of a
* VectorRowBatch.
*
diff --git a/java/core/src/java/org/apache/orc/EncryptionVariant.java b/java/core/src/java/org/apache/orc/EncryptionVariant.java
index 4eb2e8ba5..41f1066bb 100644
--- a/java/core/src/java/org/apache/orc/EncryptionVariant.java
+++ b/java/core/src/java/org/apache/orc/EncryptionVariant.java
@@ -23,7 +23,7 @@ import java.security.Key;
/**
* Information about a column encryption variant.
- *
+ * <p>
* Column encryption is done by encoding multiple variants of the same column.
* Each encrypted column ends up in two variants:
* <ul>
diff --git a/java/core/src/java/org/apache/orc/InMemoryKeystore.java b/java/core/src/java/org/apache/orc/InMemoryKeystore.java
index 743e3052b..e691e887f 100644
--- a/java/core/src/java/org/apache/orc/InMemoryKeystore.java
+++ b/java/core/src/java/org/apache/orc/InMemoryKeystore.java
@@ -42,15 +42,15 @@ import java.util.TreeMap;
/**
* This is an in-memory implementation of {@link KeyProvider}.
- *
+ * <p>
* The primary use of this class is for when the user doesn't have a
* Hadoop KMS running and wishes to use encryption. It is also useful for
* testing.
- *
+ * <p>
* The local keys for this class are encrypted/decrypted using the cipher
* in CBC/NoPadding mode and a constant IV. Since the key is random, the
* constant IV is not a problem.
- *
+ * <p>
* This class is not thread safe.
*/
public class InMemoryKeystore implements KeyProvider {
diff --git a/java/core/src/java/org/apache/orc/MemoryManager.java b/java/core/src/java/org/apache/orc/MemoryManager.java
index a187c1d9e..40eb19cbc 100644
--- a/java/core/src/java/org/apache/orc/MemoryManager.java
+++ b/java/core/src/java/org/apache/orc/MemoryManager.java
@@ -28,7 +28,7 @@ import java.io.IOException;
* dynamic partitions, it is easy to end up with many writers in the same task.
* By managing the size of each allocation, we try to cut down the size of each
* allocation and keep the task from running out of memory.
- *
+ * <p>
* This class is not thread safe, but is re-entrant - ensure creation and all
* invocations are triggered from the same thread.
*/
diff --git a/java/core/src/java/org/apache/orc/OrcUtils.java b/java/core/src/java/org/apache/orc/OrcUtils.java
index 358407fc9..48eceb037 100644
--- a/java/core/src/java/org/apache/orc/OrcUtils.java
+++ b/java/core/src/java/org/apache/orc/OrcUtils.java
@@ -44,7 +44,7 @@ public class OrcUtils {
* Index 0 is the root element of the struct which is set to false by default, index 1,2
* corresponds to columns a and b. Index 3,4 correspond to column c which is list<string> and
* index 5 correspond to column d. After flattening list<string> gets 2 columns.
- *
+ * <p>
* Column names that aren't found are ignored.
* @param selectedColumns - comma separated list of selected column names
* @param schema - object schema
diff --git a/java/core/src/java/org/apache/orc/PhysicalWriter.java b/java/core/src/java/org/apache/orc/PhysicalWriter.java
index 0c6fe68b6..3c40fb36a 100644
--- a/java/core/src/java/org/apache/orc/PhysicalWriter.java
+++ b/java/core/src/java/org/apache/orc/PhysicalWriter.java
@@ -28,7 +28,7 @@ import java.nio.ByteBuffer;
/**
* This interface separates the physical layout of ORC files from the higher
* level details.
- *
+ * <p>
* This API is limited to being used by LLAP.
*/
public interface PhysicalWriter {
diff --git a/java/core/src/java/org/apache/orc/Reader.java b/java/core/src/java/org/apache/orc/Reader.java
index 56b14393a..8ff1e74da 100644
--- a/java/core/src/java/org/apache/orc/Reader.java
+++ b/java/core/src/java/org/apache/orc/Reader.java
@@ -29,7 +29,7 @@ import java.util.function.Consumer;
/**
* The interface for reading ORC files.
- *
+ * <p>
* One Reader can support multiple concurrent RecordReader.
* @since 1.1.0
*/
diff --git a/java/core/src/java/org/apache/orc/impl/DateUtils.java b/java/core/src/java/org/apache/orc/impl/DateUtils.java
index 9a31c5d43..184b00d1d 100644
--- a/java/core/src/java/org/apache/orc/impl/DateUtils.java
+++ b/java/core/src/java/org/apache/orc/impl/DateUtils.java
@@ -31,11 +31,11 @@ import java.util.concurrent.TimeUnit;
/**
* Conversion utilities from the hybrid Julian/Gregorian calendar to/from the
* proleptic Gregorian.
- *
+ * <p>
* The semantics here are to hold the string representation constant and change
* the epoch offset rather than holding the instant in time constant and change
* the string representation.
- *
+ * <p>
* These utilities will be fast for the common case (> 1582 AD), but slow
* for old dates.
*/
diff --git a/java/core/src/java/org/apache/orc/impl/DynamicIntArray.java b/java/core/src/java/org/apache/orc/impl/DynamicIntArray.java
index fb531ce2d..632a54b08 100644
--- a/java/core/src/java/org/apache/orc/impl/DynamicIntArray.java
+++ b/java/core/src/java/org/apache/orc/impl/DynamicIntArray.java
@@ -20,14 +20,14 @@ package org.apache.orc.impl;
/**
* Dynamic int array that uses primitive types and chunks to avoid copying
* large number of integers when it resizes.
- *
+ * <p>
* The motivation for this class is memory optimization, i.e. space efficient
* storage of potentially huge arrays without good a-priori size guesses.
- *
+ * <p>
* The API of this class is between a primitive array and a AbstractList. It's
* not a Collection implementation because it handles primitive types, but the
* API could be extended to support iterators and the like.
- *
+ * <p>
* NOTE: Like standard Collection implementations/arrays, this class is not
* synchronized.
*/
diff --git a/java/core/src/java/org/apache/orc/impl/MemoryManagerImpl.java b/java/core/src/java/org/apache/orc/impl/MemoryManagerImpl.java
index 0930ac185..0a1f8efae 100644
--- a/java/core/src/java/org/apache/orc/impl/MemoryManagerImpl.java
+++ b/java/core/src/java/org/apache/orc/impl/MemoryManagerImpl.java
@@ -35,7 +35,7 @@ import java.util.concurrent.atomic.AtomicLong;
* dynamic partitions, it is easy to end up with many writers in the same task.
* By managing the size of each allocation, we try to cut down the size of each
* allocation and keep the task from running out of memory.
- *
+ * <p>
* This class is not thread safe, but is re-entrant - ensure creation and all
* invocations are triggered from the same thread.
*/
diff --git a/java/core/src/java/org/apache/orc/impl/StreamName.java b/java/core/src/java/org/apache/orc/impl/StreamName.java
index 5c629166f..fe80cd4a7 100644
--- a/java/core/src/java/org/apache/orc/impl/StreamName.java
+++ b/java/core/src/java/org/apache/orc/impl/StreamName.java
@@ -24,7 +24,7 @@ import org.jetbrains.annotations.NotNull;
/**
* The name of a stream within a stripe.
- *
+ * <p>
* Sorted by area, encryption, column, and then kind.
*/
public class StreamName implements Comparable<StreamName> {
diff --git a/java/core/src/java/org/apache/orc/impl/StringHashTableDictionary.java b/java/core/src/java/org/apache/orc/impl/StringHashTableDictionary.java
index 6cbf14795..e6cbb9483 100644
--- a/java/core/src/java/org/apache/orc/impl/StringHashTableDictionary.java
+++ b/java/core/src/java/org/apache/orc/impl/StringHashTableDictionary.java
@@ -27,7 +27,7 @@ import java.nio.ByteBuffer;
/**
* Using HashTable to represent a dictionary. The strings are stored as UTF-8 bytes
* and an offset for each entry. It is using chaining for collision resolution.
- *
+ * <p>
* This implementation is not thread-safe.
*/
public class StringHashTableDictionary implements Dictionary {
diff --git a/java/core/src/java/org/apache/orc/impl/WriterImpl.java b/java/core/src/java/org/apache/orc/impl/WriterImpl.java
index 734b94061..2e191be6c 100644
--- a/java/core/src/java/org/apache/orc/impl/WriterImpl.java
+++ b/java/core/src/java/org/apache/orc/impl/WriterImpl.java
@@ -69,13 +69,13 @@ import java.util.TreeMap;
* type of column. TreeWriters may have children TreeWriters that handle the
* sub-types. Each of the TreeWriters writes the column's data as a set of
* streams.
- *
+ * <p>
* This class is unsynchronized like most Stream objects, so from the creation
* of an OrcFile and all access to a single instance has to be from a single
* thread.
- *
+ * <p>
* There are no known cases where these happen between different threads today.
- *
+ * <p>
* Caveat: the MemoryManager is created during WriterOptions create, that has
* to be confined to a single thread as well.
*
diff --git a/java/core/src/java/org/apache/orc/impl/filter/VectorFilter.java b/java/core/src/java/org/apache/orc/impl/filter/VectorFilter.java
index cbf188c82..90c35133f 100644
--- a/java/core/src/java/org/apache/orc/impl/filter/VectorFilter.java
+++ b/java/core/src/java/org/apache/orc/impl/filter/VectorFilter.java
@@ -23,7 +23,7 @@ import org.apache.orc.OrcFilterContext;
/**
* A filter that operates on the supplied
* {@link org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch} and updates the selections.
- *
+ * <p>
* This is the interface that is the basis of both the leaf filters such as Equals, In and logical
* filters such as And, Or and Not
*/
diff --git a/java/core/src/java/org/apache/orc/impl/mask/RedactMaskFactory.java b/java/core/src/java/org/apache/orc/impl/mask/RedactMaskFactory.java
index e929d6d58..c6d314738 100644
--- a/java/core/src/java/org/apache/orc/impl/mask/RedactMaskFactory.java
+++ b/java/core/src/java/org/apache/orc/impl/mask/RedactMaskFactory.java
@@ -42,7 +42,7 @@ import java.util.concurrent.TimeUnit;
/**
* Masking strategy that hides most string and numeric values based on unicode
* character categories.
- *
+ * <p>
* Masking Parameters:
* character replacements: string of 10 characters one per group below
* letter, upper case (default X)
@@ -55,7 +55,7 @@ import java.util.concurrent.TimeUnit;
* mark (default ः)
* number, other (default ²)
* other (default )
- *
+ * <p>
* time replacements: string of 6 numbers or _ one per field below
* year (0 to 4000, default no masking)
* month (1 to 12, default 1)
@@ -63,7 +63,7 @@ import java.util.concurrent.TimeUnit;
* hour (0 to 23, default 0)
* minute (0 to 59, default 0)
* second (0 to 59, default 0)
- *
+ * <p>
* Parameters use "_" for preserve original.
*/
public class RedactMaskFactory extends MaskFactory {
diff --git a/java/core/src/java/org/apache/orc/impl/reader/StripePlanner.java b/java/core/src/java/org/apache/orc/impl/reader/StripePlanner.java
index 06364548d..e35302c76 100644
--- a/java/core/src/java/org/apache/orc/impl/reader/StripePlanner.java
+++ b/java/core/src/java/org/apache/orc/impl/reader/StripePlanner.java
@@ -52,7 +52,7 @@ import java.util.Set;
/**
* This class handles parsing the stripe information and handling the necessary
* filtering and selection.
- *
+ * <p>
* It supports:
* <ul>
* <li>column projection</li>
diff --git a/java/core/src/java/org/apache/orc/impl/writer/WriterImplV2.java b/java/core/src/java/org/apache/orc/impl/writer/WriterImplV2.java
index 80528cdcb..41465960c 100644
--- a/java/core/src/java/org/apache/orc/impl/writer/WriterImplV2.java
+++ b/java/core/src/java/org/apache/orc/impl/writer/WriterImplV2.java
@@ -35,13 +35,13 @@ import java.io.IOException;
* type of column. TreeWriters may have children TreeWriters that handle the
* sub-types. Each of the TreeWriters writes the column's data as a set of
* streams.
- *
+ * <p>
* This class is unsynchronized like most Stream objects, so from the creation
* of an OrcFile and all access to a single instance has to be from a single
* thread.
- *
+ * <p>
* There are no known cases where these happen between different threads today.
- *
+ * <p>
* Caveat: the MemoryManager is created during WriterOptions create, that has
* to be confined to a single thread as well.
*
diff --git a/java/core/src/java/org/apache/orc/util/BloomFilter.java b/java/core/src/java/org/apache/orc/util/BloomFilter.java
index 3aa12ec28..3292af687 100644
--- a/java/core/src/java/org/apache/orc/util/BloomFilter.java
+++ b/java/core/src/java/org/apache/orc/util/BloomFilter.java
@@ -33,12 +33,12 @@ import java.util.Arrays;
* During the creation of bloom filter expected number of entries must be specified. If the number
* of insertions exceed the specified initial number of entries then false positive probability will
* increase accordingly.
- *
+ * <p>
* Internally, this implementation of bloom filter uses Murmur3 fast non-cryptographic hash
* algorithm. Although Murmur2 is slightly faster than Murmur3 in Java, it suffers from hash
* collisions for specific sequence of repeating bytes. Check the following link for more info
* https://code.google.com/p/smhasher/wiki/MurmurHash2Flaw
- *
+ * <p>
* Note that this class is here for backwards compatibility, because it uses
* the JVM default character set for strings. All new users should
* BloomFilterUtf8, which always uses UTF8 for the encoding.
diff --git a/java/core/src/java/org/apache/orc/util/CuckooSetBytes.java b/java/core/src/java/org/apache/orc/util/CuckooSetBytes.java
index c213d29f7..567f387ca 100644
--- a/java/core/src/java/org/apache/orc/util/CuckooSetBytes.java
+++ b/java/core/src/java/org/apache/orc/util/CuckooSetBytes.java
@@ -25,12 +25,12 @@ import java.util.Random;
/**
* A high-performance set implementation used to support fast set membership testing,
* using Cuckoo hashing. This is used to support fast tests of the form
- *
+ * <p>
* column IN ( list-of-values )
- *
+ * <p>
* For details on the algorithm, see R. Pagh and F. F. Rodler, "Cuckoo Hashing,"
* Elsevier Science preprint, Dec. 2003. http://www.itu.dk/people/pagh/papers/cuckoo-jour.pdf.
- *
+ * <p>
* Copied from CuckooSetBytes@Apache Hive project for convenience
*/
public class CuckooSetBytes {
diff --git a/java/core/src/java/org/apache/orc/util/Murmur3.java b/java/core/src/java/org/apache/orc/util/Murmur3.java
index a78aa12b9..c01855bb8 100644
--- a/java/core/src/java/org/apache/orc/util/Murmur3.java
+++ b/java/core/src/java/org/apache/orc/util/Murmur3.java
@@ -20,11 +20,11 @@ package org.apache.orc.util;
/**
* Murmur3 is successor to Murmur2 fast non-crytographic hash algorithms.
- *
+ * <p>
* Murmur3 32 and 128 bit variants.
* 32-bit Java port of https://code.google.com/p/smhasher/source/browse/trunk/MurmurHash3.cpp#94
* 128-bit Java port of https://code.google.com/p/smhasher/source/browse/trunk/MurmurHash3.cpp#255
- *
+ * <p>
* This is a public domain code with no copyrights.
* From homepage of MurmurHash (https://code.google.com/p/smhasher/),
* "All MurmurHash versions are public domain software, and the author disclaims all copyright
diff --git a/java/mapreduce/src/java/org/apache/orc/mapred/OrcKey.java b/java/mapreduce/src/java/org/apache/orc/mapred/OrcKey.java
index 07ed0d642..880dec769 100644
--- a/java/mapreduce/src/java/org/apache/orc/mapred/OrcKey.java
+++ b/java/mapreduce/src/java/org/apache/orc/mapred/OrcKey.java
@@ -30,7 +30,7 @@ import java.io.IOException;
/**
* This type provides a wrapper for OrcStruct so that it can be sent through
* the MapReduce shuffle as a key.
- *
+ * <p>
* The user should set the JobConf with orc.mapred.key.type with the type
* string of the type.
*/
diff --git a/java/mapreduce/src/java/org/apache/orc/mapred/OrcValue.java b/java/mapreduce/src/java/org/apache/orc/mapred/OrcValue.java
index 23f50b62e..3129d3ff4 100644
--- a/java/mapreduce/src/java/org/apache/orc/mapred/OrcValue.java
+++ b/java/mapreduce/src/java/org/apache/orc/mapred/OrcValue.java
@@ -31,7 +31,7 @@ import java.io.IOException;
/**
* This type provides a wrapper for OrcStruct so that it can be sent through
* the MapReduce shuffle as a value.
- *
+ * <p>
* The user should set the JobConf with orc.mapred.value.type with the type
* string of the type.
*/
diff --git a/java/shims/src/java/org/apache/orc/EncryptionAlgorithm.java b/java/shims/src/java/org/apache/orc/EncryptionAlgorithm.java
index 79a424d9c..a6b97cae6 100644
--- a/java/shims/src/java/org/apache/orc/EncryptionAlgorithm.java
+++ b/java/shims/src/java/org/apache/orc/EncryptionAlgorithm.java
@@ -24,7 +24,7 @@ import java.security.NoSuchAlgorithmException;
/**
* The encryption algorithms supported by ORC.
- *
+ * <p>
* This class can't reference any of the newer Hadoop classes.
*/
public enum EncryptionAlgorithm {
diff --git a/java/shims/src/java/org/apache/orc/impl/HadoopShimsPre2_6.java b/java/shims/src/java/org/apache/orc/impl/HadoopShimsPre2_6.java
index 1a44f197e..ae740f99c 100644
--- a/java/shims/src/java/org/apache/orc/impl/HadoopShimsPre2_6.java
+++ b/java/shims/src/java/org/apache/orc/impl/HadoopShimsPre2_6.java
@@ -27,7 +27,7 @@ import java.util.Random;
/**
* Shims for versions of Hadoop less than 2.6
- *
+ * <p>
* Adds support for:
* <ul>
* <li>Direct buffer decompression</li>
diff --git a/java/shims/src/java/org/apache/orc/impl/HadoopShimsPre2_7.java b/java/shims/src/java/org/apache/orc/impl/HadoopShimsPre2_7.java
index 00210046a..47f1066f7 100644
--- a/java/shims/src/java/org/apache/orc/impl/HadoopShimsPre2_7.java
+++ b/java/shims/src/java/org/apache/orc/impl/HadoopShimsPre2_7.java
@@ -29,7 +29,7 @@ import java.util.Random;
/**
* Shims for versions of Hadoop less than 2.7.
- *
+ * <p>
* Adds support for:
* <ul>
* <li>Crypto</li>