From ee0aa2952a813d233ab10ee74272d1975d1b2fd9 Mon Sep 17 00:00:00 2001
From: david dali susanibar arce <davi.sarces@gmail.com>
Date: Fri, 30 Dec 2022 17:20:46 -0500
Subject: [PATCH] doc: adding java read compression files with LZ4 codec

---
 java/source/demo/pom.xml                 |   5 ++
 java/source/io.rst                       |  59 +++++++++++++++++++++++
 java/thirdpartydeps/arrowfiles/lz4.arrow | Bin 0 -> 1122 bytes
 3 files changed, 64 insertions(+)
 create mode 100644 java/thirdpartydeps/arrowfiles/lz4.arrow

diff --git a/java/source/demo/pom.xml b/java/source/demo/pom.xml
index bd4036f6..3546852a 100644
--- a/java/source/demo/pom.xml
+++ b/java/source/demo/pom.xml
@@ -82,6 +82,11 @@
             <artifactId>arrow-avro</artifactId>
             <version>${arrow.version}</version>
         </dependency>
+        <dependency>
+            <groupId>org.apache.arrow</groupId>
+            <artifactId>arrow-compression</artifactId>
+            <version>${arrow.version}</version>
+        </dependency>
         <dependency>
             <groupId>com.h2database</groupId>
             <artifactId>h2</artifactId>
diff --git a/java/source/io.rst b/java/source/io.rst
index 74f74d15..89709fea 100644
--- a/java/source/io.rst
+++ b/java/source/io.rst
@@ -320,6 +320,65 @@ We are providing a path with auto generated arrow files for testing purposes, ch
    Jhon    29
    Thomy    33
 
+Read - From Compressed File
+---------------------------
+
+We are providing a path with auto generated arrow files for testing purposes, change that at your convenience.
+
+Compressed file generated through this code example:
+
+.. code:: python
+
+   import pandas as pd
+   import pyarrow as pa
+
+   pd.DataFrame({'key': range(4)}).to_feather('lz4.arrow', compression='lz4')
+   pd.DataFrame({'key': range(4)}).to_feather('zstd.arrow', compression='zstd')
+
+.. note::
+
+   Java Vector module offer read files without compression codec, in case reading
+   compressed files is required consider to also add Java Compression module
+   dependency.
+
+.. testcode::
+
+   import org.apache.arrow.compression.CommonsCompressionFactory;
+   import org.apache.arrow.memory.BufferAllocator;
+   import org.apache.arrow.memory.RootAllocator;
+   import org.apache.arrow.vector.ipc.ArrowFileReader;
+   import org.apache.arrow.vector.ipc.message.ArrowBlock;
+   import org.apache.arrow.vector.VectorSchemaRoot;
+   import java.io.File;
+   import java.io.FileInputStream;
+   import java.io.IOException;
+
+   File file = new File("./thirdpartydeps/arrowfiles/lz4.arrow");
+   try(
+       BufferAllocator rootAllocator = new RootAllocator();
+       FileInputStream fileInputStream = new FileInputStream(file);
+       ArrowFileReader reader = new ArrowFileReader(fileInputStream.getChannel(),
+           rootAllocator, CommonsCompressionFactory.INSTANCE)
+   ){
+       System.out.println("Record batches in file: " + reader.getRecordBlocks().size());
+       for (ArrowBlock arrowBlock : reader.getRecordBlocks()) {
+           reader.loadRecordBatch(arrowBlock);
+           VectorSchemaRoot vectorSchemaRootRecover = reader.getVectorSchemaRoot();
+           System.out.print(vectorSchemaRootRecover.contentToTSVString());
+       }
+   } catch (IOException e) {
+       e.printStackTrace();
+   }
+
+.. testoutput::
+
+   Record batches in file: 1
+   key
+   0
+   1
+   2
+   3
+
 Read - From Buffer
 ------------------
 
diff --git a/java/thirdpartydeps/arrowfiles/lz4.arrow b/java/thirdpartydeps/arrowfiles/lz4.arrow
new file mode 100644
index 0000000000000000000000000000000000000000..dbaad3c9eb50541160695511676402ea995b46de
GIT binary patch
literal 1122
zcmeHH!AiqG5S_L$h7u&u3O)2t_S8cOEffV$_2xx{UOb4z)kFv;n~<hzC<XB=JoXd(
z6o17p&^MbXq2k$#Q)aXCW_D)h&C=uf{Oo)}^a0s4h#X>R(;k_$Ll$<BhVhNtFpUZy
zBHmy(lyM6y`z-7kWZye<B|_x~kKRoZEn~G1M}v#Y(Lj`@r+vW|s?C*9G7b<f?t((#
z#BCTvzPAOYQu%V><wdGPLzN#)Ian>@wD<|fK`wonOQcoHC|c{AWP!|+4A4qM;dLgn
zf~%&5%(CQxlidf|B1{ychwj)Ni#5Qia?Lk!r|v|o(X$CH{UtwL*ba5UjY+$jEvMqN
z(PYm1Q09xJ1x3f2PYcnSPo$Xv=Q+LL%lTMr>Q$4nbyjK_I@h>#S22Cm;>naTCqTI#
z=lH70frkDOHQD$@Mm3!0UO&&S0WT0koc69}&->VR@D@4^i#kn<p18NVa6fD_2R3eG
s>RUQxFUURvK7?`|uJ_6dWTRK2dY=`9Pg|e=f2V)<PTw%6WBuRq3GLLrz5oCK

literal 0
HcmV?d00001