davisusanibar commented on a change in pull request #136: URL: https://github.com/apache/arrow-cookbook/pull/136#discussion_r808069658
########## File path: java/source/io.rst ########## @@ -0,0 +1,610 @@ +.. _arrow-io: + +======================== +Reading and writing data +======================== + +The `Arrow IPC format <https://arrow.apache.org/docs/java/ipc.html>`_ defines two types of binary formats +for serializing Arrow data: the streaming format and the file format (or random access format). Such files can +be directly memory-mapped when read. + +.. contents:: + +Writing +======= + +Both writing file and streaming formats use the same API. + +Writing Random Access Files +*************************** + +Write - Out to File +------------------- + +.. testcode:: + + import org.apache.arrow.memory.RootAllocator; + import org.apache.arrow.vector.VarCharVector; + import org.apache.arrow.vector.IntVector; + import org.apache.arrow.vector.types.pojo.Field; + import org.apache.arrow.vector.types.pojo.FieldType; + import org.apache.arrow.vector.types.pojo.ArrowType; + import org.apache.arrow.vector.types.pojo.Schema; + import org.apache.arrow.vector.VectorSchemaRoot; + import static java.util.Arrays.asList; + import org.apache.arrow.vector.ipc.ArrowFileWriter; + import java.io.File; + import java.io.FileNotFoundException; + import java.io.FileOutputStream; + import java.io.IOException; + + // Create and populate data: + Field name = new Field("name", FieldType.nullable(new ArrowType.Utf8()), null); + Field age = new Field("age", FieldType.nullable(new ArrowType.Int(32, true)), null); + Schema schemaPerson = new Schema(asList(name, age)); + RootAllocator rootAllocator = new RootAllocator(Long.MAX_VALUE); + VectorSchemaRoot vectorSchemaRoot = VectorSchemaRoot.create(schemaPerson, rootAllocator); + VarCharVector nameVector = (VarCharVector) vectorSchemaRoot.getVector("name"); + nameVector.allocateNew(3); + nameVector.set(0, "David".getBytes()); + nameVector.set(1, "Gladis".getBytes()); + nameVector.set(2, "Juan".getBytes()); + IntVector ageVector = (IntVector) vectorSchemaRoot.getVector("age"); + ageVector.allocateNew(3); + ageVector.set(0, 10); + ageVector.set(1, 20); + ageVector.set(2, 30); + vectorSchemaRoot.setRowCount(3); + File file = new File("randon_access_to_file.arrow"); + try (FileOutputStream fileOutputStream = new FileOutputStream(file); + ArrowFileWriter writer = new ArrowFileWriter(vectorSchemaRoot, null, fileOutputStream.getChannel()) + ){ + writer.start(); + for (int i=0; i<10; i++){ + // Generate data or modify the root or use a VectorLoader to get fresh data from somewhere else + writer.writeBatch(); + } + System.out.println("Record batches written: " + writer.getRecordBlocks().size()); + } catch (FileNotFoundException e) { + e.printStackTrace(); + } catch (IOException e) { + e.printStackTrace(); + } + +.. testoutput:: + + Record batches written: 10 + +Write - Out to Buffer +--------------------- + +.. testcode:: + + import org.apache.arrow.memory.RootAllocator; + import org.apache.arrow.vector.VarCharVector; + import org.apache.arrow.vector.IntVector; + import org.apache.arrow.vector.types.pojo.Field; + import org.apache.arrow.vector.types.pojo.FieldType; + import org.apache.arrow.vector.types.pojo.ArrowType; + import org.apache.arrow.vector.types.pojo.Schema; + import org.apache.arrow.vector.VectorSchemaRoot; + import static java.util.Arrays.asList; + import org.apache.arrow.vector.ipc.ArrowFileWriter; + + import java.io.ByteArrayOutputStream; + import java.io.FileNotFoundException; + import java.io.IOException; + import java.nio.channels.Channels; + + // Create and populate data: + Field name = new Field("name", FieldType.nullable(new ArrowType.Utf8()), null); + Field age = new Field("age", FieldType.nullable(new ArrowType.Int(32, true)), null); + Schema schemaPerson = new Schema(asList(name, age)); + RootAllocator rootAllocator = new RootAllocator(Long.MAX_VALUE); + VectorSchemaRoot vectorSchemaRoot = VectorSchemaRoot.create(schemaPerson, rootAllocator); + VarCharVector nameVector = (VarCharVector) vectorSchemaRoot.getVector("name"); + nameVector.allocateNew(3); + nameVector.set(0, "David".getBytes()); + nameVector.set(1, "Gladis".getBytes()); + nameVector.set(2, "Juan".getBytes()); + IntVector ageVector = (IntVector) vectorSchemaRoot.getVector("age"); + ageVector.allocateNew(3); + ageVector.set(0, 10); + ageVector.set(1, 20); + ageVector.set(2, 30); + vectorSchemaRoot.setRowCount(3); + try (ByteArrayOutputStream out = new ByteArrayOutputStream(); + ArrowFileWriter writer = new ArrowFileWriter(vectorSchemaRoot, null, /*WritableByteChannel out*/Channels.newChannel(out))) + { + writer.start(); + for (int i=0; i<10; i++){ + // Generate data or modify the root or use a VectorLoader to get fresh data from somewhere else + writer.writeBatch(); + } + System.out.println(writer.getRecordBlocks().size()); + } catch (FileNotFoundException e) { + e.printStackTrace(); + } catch (IOException e) { + e.printStackTrace(); + } + +.. testoutput:: + + 10 + +Writing Streaming Format +************************ + +Write - Out to File +------------------- + +.. testcode:: + + import org.apache.arrow.memory.RootAllocator; + import org.apache.arrow.vector.VarCharVector; + import org.apache.arrow.vector.IntVector; + import org.apache.arrow.vector.types.pojo.Field; + import org.apache.arrow.vector.types.pojo.FieldType; + import org.apache.arrow.vector.types.pojo.ArrowType; + import org.apache.arrow.vector.types.pojo.Schema; + import org.apache.arrow.vector.VectorSchemaRoot; + import static java.util.Arrays.asList; + import org.apache.arrow.vector.ipc.ArrowStreamWriter; + import java.io.File; + import java.io.FileNotFoundException; + import java.io.FileOutputStream; + import java.io.IOException; + + // Create and populate data: + Field name = new Field("name", FieldType.nullable(new ArrowType.Utf8()), null); + Field age = new Field("age", FieldType.nullable(new ArrowType.Int(32, true)), null); + Schema schemaPerson = new Schema(asList(name, age)); + RootAllocator rootAllocator = new RootAllocator(Long.MAX_VALUE); + VectorSchemaRoot vectorSchemaRoot = VectorSchemaRoot.create(schemaPerson, rootAllocator); + VarCharVector nameVector = (VarCharVector) vectorSchemaRoot.getVector("name"); + nameVector.allocateNew(3); + nameVector.set(0, "David".getBytes()); + nameVector.set(1, "Gladis".getBytes()); + nameVector.set(2, "Juan".getBytes()); + IntVector ageVector = (IntVector) vectorSchemaRoot.getVector("age"); + ageVector.allocateNew(3); + ageVector.set(0, 10); + ageVector.set(1, 20); + ageVector.set(2, 30); + vectorSchemaRoot.setRowCount(3); + File file = new File("streaming_to_file.arrow"); + try (FileOutputStream fileOutputStream = new FileOutputStream(file); + ArrowStreamWriter writer = new ArrowStreamWriter(vectorSchemaRoot, null, /*WritableByteChannel out*/fileOutputStream.getChannel()) + ){ + writer.start(); + for (int i=0; i<10; i++){ + // Generate data or modify the root or use a VectorLoader to get fresh data from somewhere else + writer.writeBatch(); + } + System.out.println(writer.bytesWritten()); + } catch (FileNotFoundException e) { + e.printStackTrace(); + } catch (IOException e) { + e.printStackTrace(); + } + +.. testoutput:: + + 2928 + +Write - Out to Buffer +--------------------- + +.. testcode:: + + import org.apache.arrow.memory.RootAllocator; + import org.apache.arrow.vector.VarCharVector; + import org.apache.arrow.vector.IntVector; + import org.apache.arrow.vector.ipc.ArrowStreamWriter; + import org.apache.arrow.vector.types.pojo.Field; + import org.apache.arrow.vector.types.pojo.FieldType; + import org.apache.arrow.vector.types.pojo.ArrowType; + import org.apache.arrow.vector.types.pojo.Schema; + import org.apache.arrow.vector.VectorSchemaRoot; + import static java.util.Arrays.asList; + + import java.io.ByteArrayOutputStream; + import java.io.FileNotFoundException; + import java.io.IOException; + import java.nio.channels.Channels; + + // Create and populate data: + Field name = new Field("name", FieldType.nullable(new ArrowType.Utf8()), null); + Field age = new Field("age", FieldType.nullable(new ArrowType.Int(32, true)), null); + Schema schemaPerson = new Schema(asList(name, age)); + RootAllocator rootAllocator = new RootAllocator(Long.MAX_VALUE); + VectorSchemaRoot vectorSchemaRoot = VectorSchemaRoot.create(schemaPerson, rootAllocator); + VarCharVector nameVector = (VarCharVector) vectorSchemaRoot.getVector("name"); + nameVector.allocateNew(3); + nameVector.set(0, "David".getBytes()); + nameVector.set(1, "Gladis".getBytes()); + nameVector.set(2, "Juan".getBytes()); + IntVector ageVector = (IntVector) vectorSchemaRoot.getVector("age"); + ageVector.allocateNew(3); + ageVector.set(0, 10); + ageVector.set(1, 20); + ageVector.set(2, 30); + vectorSchemaRoot.setRowCount(3); + try (ByteArrayOutputStream out = new ByteArrayOutputStream(); + ArrowStreamWriter writer = new ArrowStreamWriter(vectorSchemaRoot, null, /*WritableByteChannel out*/Channels.newChannel(out)) + ){ + writer.start(); + for (int i=0; i<10; i++){ + // Generate data or modify the root or use a VectorLoader to get fresh data from somewhere else + writer.writeBatch(); + } + System.out.println(writer.bytesWritten()); + } catch (FileNotFoundException e) { + e.printStackTrace(); + } catch (IOException e) { + e.printStackTrace(); + } + +.. testoutput:: + + 2928 + +Reading +======= + +Reading the random access format and streaming format both offer the same API, +with the difference that random access files also offer access to any record batch by index. + +Reading Random Access Files +*************************** + +Read - From File +---------------- + +.. testcode:: + + import org.apache.arrow.memory.RootAllocator; + import org.apache.arrow.vector.VarCharVector; + import org.apache.arrow.vector.IntVector; + import org.apache.arrow.vector.ipc.message.ArrowBlock; + import org.apache.arrow.vector.types.pojo.Field; + import org.apache.arrow.vector.types.pojo.FieldType; + import org.apache.arrow.vector.types.pojo.ArrowType; + import org.apache.arrow.vector.types.pojo.Schema; + import org.apache.arrow.vector.VectorSchemaRoot; + import static java.util.Arrays.asList; + import org.apache.arrow.vector.ipc.ArrowFileWriter; + import java.io.File; + import java.io.FileInputStream; + import java.io.FileNotFoundException; + import java.io.FileOutputStream; + import java.io.IOException; + import org.apache.arrow.vector.ipc.ArrowFileReader; + + // Create and populate data + Field name = new Field("name", FieldType.nullable(new ArrowType.Utf8()), null); + Field age = new Field("age", FieldType.nullable(new ArrowType.Int(32, true)), null); + Schema schemaPerson = new Schema(asList(name, age)); + RootAllocator rootAllocator = new RootAllocator(Long.MAX_VALUE); + VectorSchemaRoot vectorSchemaRoot = VectorSchemaRoot.create(schemaPerson, rootAllocator); + VarCharVector nameVector = (VarCharVector) vectorSchemaRoot.getVector("name"); + nameVector.allocateNew(3); + nameVector.set(0, "David".getBytes()); + nameVector.set(1, "Gladis".getBytes()); + nameVector.set(2, "Juan".getBytes()); + IntVector ageVector = (IntVector) vectorSchemaRoot.getVector("age"); + ageVector.allocateNew(3); + ageVector.set(0, 10); + ageVector.set(1, 20); + ageVector.set(2, 30); + vectorSchemaRoot.setRowCount(3); + File file = new File("randon_access_to_file.arrow"); + try (FileOutputStream fileOutputStream = new FileOutputStream(file); Review comment: Added a arrow file to resources to only consider read recipe on the code -- 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]
