Class TestScanData

java/tools/src/test/org/apache/orc/tools/TestScanData.java:40–89

import static org.junit.jupiter.api.Assertions.assertTrue;

public class TestScanData implements TestConf {
  private Path workDir = new Path(System.getProperty("test.tmp.dir"));
  private FileSystem fs;
  private Path testFilePath;

  @BeforeEach
  public void openFileSystem() throws Exception {
    fs = FileSystem.getLocal(conf);
    testFilePath = new Path(workDir + File.separator + "TestScanData.testScan.orc");
    fs.delete(testFilePath, false);
  }

  @Test
  public void testScan() throws Exception {
    TypeDescription schema = TypeDescription.fromString("struct<x:int,y:string>");
    Writer writer = OrcFile.createWriter(testFilePath,
        OrcFile.writerOptions(conf)
            .setSchema(schema));
    VectorizedRowBatch batch = schema.createRowBatch();
    LongColumnVector x = (LongColumnVector) batch.cols[0];
    BytesColumnVector y = (BytesColumnVector) batch.cols[1];
    for (int r = 0; r < 10000; ++r) {
      int row = batch.size++;
      x.vector[row] = r;
      byte[] buffer = ("byte-" + r).getBytes();
      y.setRef(row, buffer, 0, buffer.length);
      if (batch.size == batch.getMaxSize()) {
        writer.addRowBatch(batch);
        batch.reset();
      }
    }
    if (batch.size != 0) {
      writer.addRowBatch(batch);
    }
    writer.close();

    PrintStream origOut = System.out;
    ByteArrayOutputStream myOut = new ByteArrayOutputStream();
    // replace stdout and run command
    System.setOut(new PrintStream(myOut, false, StandardCharsets.UTF_8));
    ScanData.main(conf, new String[]{"--schema", testFilePath.toString()});
    System.out.flush();
    System.setOut(origOut);
    String output = myOut.toString(StandardCharsets.UTF_8);
    assertTrue(output.contains("{\"category\": \"struct\", \"id\": 0, \"max\": 2, \"fields\": [\n" +
        "{  \"x\": {\"category\": \"int\", \"id\": 1, \"max\": 1}},\n" +
        "{  \"y\": {\"category\": \"string\", \"id\": 2, \"max\": 2}}]}"));
    assertTrue(output.contains("TestScanData.testScan.orc, bad batches: 0, rows: 10000/10000"));
  }
}