本文整理汇总了Java中org.apache.orc.OrcFile.createReader方法的典型用法代码示例。如果您正苦于以下问题：Java OrcFile.createReader方法的具体用法？Java OrcFile.createReader怎么用？Java OrcFile.createReader使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类org.apache.orc.OrcFile的用法示例。
在下文中一共展示了OrcFile.createReader方法的4个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Java代码示例。
示例1: test
import org.apache.orc.OrcFile; //导入方法依赖的package包/类
@Test
public void test () throws IOException, Descriptors.DescriptorValidationException
{
Configuration conf = new Configuration();
System.setProperty("hadoop.home.dir", "/");
FileSystem fileSystem = FileSystem.get(URI.create("hdfs://presto00:9000"), conf);
Path hdfsDirPath = new Path("/rainbow2/orc_new_compress");
System.out.println(fileSystem.isFile(hdfsDirPath));
FileStatus[] fileStatuses = fileSystem.listStatus(hdfsDirPath);
System.out.println(fileStatuses.length);
for (FileStatus status : fileStatuses)
{
status.getPath();
System.out.println(status.getPath() + ", " + status.getLen());
}
Reader reader = OrcFile.createReader(fileStatuses[0].getPath(),
OrcFile.readerOptions(conf));
System.out.println("file length:" + reader.getFileTail().getFileLength());
List<String> columnNames = new ArrayList<>();
columnNames.add("samplepercent");
System.out.println(reader.getRawDataSizeOfColumns(columnNames));
System.out.println(reader.getFileTail().getFooter().getTypes(0).getFieldNames(0));
System.out.println(reader.getTypes().get(0).getSerializedSize());
List<Reader> readers = new ArrayList<>();
for (FileStatus fileStatus : fileStatuses)
{
Reader reader1 = OrcFile.createReader(fileStatus.getPath(),
OrcFile.readerOptions(conf));
readers.add(reader1);
System.out.println("content size: " + reader1.getContentLength() + ", raw size: "
+ reader1.getRawDataSize());
}
for (String columnName : reader.getSchema().getFieldNames())
{
System.out.println(columnName);
}
}
示例2: JsonORCFileReader
import org.apache.orc.OrcFile; //导入方法依赖的package包/类
@SuppressWarnings("deprecation")
public JsonORCFileReader(LogFilePath logFilePath, CompressionCodec codec)
throws IOException {
schema = schemaProvider.getSchema(logFilePath.getTopic(),
logFilePath);
Path path = new Path(logFilePath.getLogFilePath());
Reader reader = OrcFile.createReader(path,
OrcFile.readerOptions(new Configuration(true)));
offset = logFilePath.getOffset();
rows = reader.rows();
batch = reader.getSchema().createRowBatch();
rows.nextBatch(batch);
}
示例3: open
import org.apache.orc.OrcFile; //导入方法依赖的package包/类
public void open(Configuration conf) throws IOException{
this.reader = OrcFile.createReader(new Path(this.filePath), OrcFile.readerOptions(conf));
this.schema = this.reader.getSchema();
}
示例4: open
import org.apache.orc.OrcFile; //导入方法依赖的package包/类
@Override
public void open(FileInputSplit fileSplit) throws IOException {
LOG.debug("Opening ORC file {}", fileSplit.getPath());
// open ORC file and create reader
org.apache.hadoop.fs.Path hPath = new org.apache.hadoop.fs.Path(fileSplit.getPath().getPath());
Reader orcReader = OrcFile.createReader(hPath, OrcFile.readerOptions(conf));
// get offset and length for the stripes that start in the split
Tuple2<Long, Long> offsetAndLength = getOffsetAndLengthForSplit(fileSplit, getStripes(orcReader));
// create ORC row reader configuration
Reader.Options options = getOptions(orcReader)
.schema(schema)
.range(offsetAndLength.f0, offsetAndLength.f1)
.useZeroCopy(OrcConf.USE_ZEROCOPY.getBoolean(conf))
.skipCorruptRecords(OrcConf.SKIP_CORRUPT_DATA.getBoolean(conf))
.tolerateMissingSchema(OrcConf.TOLERATE_MISSING_SCHEMA.getBoolean(conf));
// configure filters
if (!conjunctPredicates.isEmpty()) {
SearchArgument.Builder b = SearchArgumentFactory.newBuilder();
b = b.startAnd();
for (Predicate predicate : conjunctPredicates) {
predicate.add(b);
}
b = b.end();
options.searchArgument(b.build(), new String[]{});
}
// configure selected fields
options.include(computeProjectionMask());
// create ORC row reader
this.orcRowsReader = orcReader.rows(options);
// assign ids
this.schema.getId();
// create row batch
this.rowBatch = schema.createRowBatch(batchSize);
rowsInBatch = 0;
nextRow = 0;
}