davisusanibar commented on a change in pull request #136: URL: https://github.com/apache/arrow-cookbook/pull/136#discussion_r800876970
########## File path: java/source/io.rst ########## @@ -0,0 +1,578 @@ +.. _arrow-io: + +======================== +Reading and writing data +======================== + +Recipes related to reading and writing data from disk using Apache Arrow. + +Arrow defines two types of binary formats for serializing record batches `IPC <https://arrow.apache.org/docs/java/ipc.html>`_: Streaming format / File or Random Access format + +Arrow vectors can be serialized to disk as the Arrow IPC format. Such files can be directly memory-mapped when read. + +.. contents:: + +Writing +======= + +Both libraries writing random access file and streaming format offer 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()); + nameVector.setValueCount(3); + IntVector ageVector = (IntVector) vectorSchemaRoot.getVector("age"); + ageVector.allocateNew(3); + ageVector.set(0, 10); + ageVector.set(1, 20); + ageVector.set(2, 30); + ageVector.setValueCount(3); + vectorSchemaRoot.setRowCount(3); Review comment: Changed -- 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]
