/*
 * Licensed to the Apache Software Foundation (ASF) under one
 * or more contributor license agreements.  See the NOTICE file
 * distributed with this work for additional information
 * regarding copyright ownership.  The ASF licenses this file
 * to you under the Apache License, Version 2.0 (the
 * "License"); you may not use this file except in compliance
 * with the License.  You may obtain a copy of the License at
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */
package org.apache.hadoop.hbase.mapred;

import static org.junit.jupiter.api.Assertions.assertEquals;
import static org.junit.jupiter.api.Assertions.assertFalse;
import static org.junit.jupiter.api.Assertions.assertThrows;
import static org.junit.jupiter.api.Assertions.assertTrue;
import static org.mockito.ArgumentMatchers.any;
import static org.mockito.Mockito.doAnswer;
import static org.mockito.Mockito.doReturn;
import static org.mockito.Mockito.doThrow;
import static org.mockito.Mockito.mock;
import static org.mockito.Mockito.spy;

import java.io.IOException;
import java.util.Arrays;
import java.util.Map;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.Cell;
import org.apache.hadoop.hbase.CompareOperator;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.HBaseTestingUtil;
import org.apache.hadoop.hbase.NotServingRegionException;
import org.apache.hadoop.hbase.TableName;
import org.apache.hadoop.hbase.client.Connection;
import org.apache.hadoop.hbase.client.ConnectionFactory;
import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.client.Result;
import org.apache.hadoop.hbase.client.ResultScanner;
import org.apache.hadoop.hbase.client.Scan;
import org.apache.hadoop.hbase.client.Table;
import org.apache.hadoop.hbase.filter.Filter;
import org.apache.hadoop.hbase.filter.RegexStringComparator;
import org.apache.hadoop.hbase.filter.RowFilter;
import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
import org.apache.hadoop.hbase.testclassification.LargeTests;
import org.apache.hadoop.hbase.testclassification.MapReduceTests;
import org.apache.hadoop.hbase.util.Bytes;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.mapred.InputFormat;
import org.apache.hadoop.mapred.JobClient;
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapred.JobConfigurable;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reporter;
import org.apache.hadoop.mapred.RunningJob;
import org.apache.hadoop.mapred.lib.NullOutputFormat;
import org.junit.jupiter.api.AfterAll;
import org.junit.jupiter.api.BeforeAll;
import org.junit.jupiter.api.BeforeEach;
import org.junit.jupiter.api.Tag;
import org.junit.jupiter.api.Test;
import org.mockito.invocation.InvocationOnMock;
import org.mockito.stubbing.Answer;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;

/**
 * This tests the TableInputFormat and its recovery semantics
 */
@Tag(MapReduceTests.TAG)
@Tag(LargeTests.TAG)
public class TestTableInputFormat {

  private static final Logger LOG = LoggerFactory.getLogger(TestTableInputFormat.class);

  private final static HBaseTestingUtil UTIL = new HBaseTestingUtil();

  static final byte[] FAMILY = Bytes.toBytes("family");

  private static final byte[][] columns = new byte[][] { FAMILY };

  @BeforeAll
  public static void beforeClass() throws Exception {
    UTIL.startMiniCluster();
  }

  @AfterAll
  public static void afterClass() throws Exception {
    UTIL.shutdownMiniCluster();
  }

  @BeforeEach
  public void before() throws IOException {
    LOG.info("before");
    UTIL.ensureSomeRegionServersAvailable(1);
    LOG.info("before done");
  }

  /**
   * Setup a table with two rows and values.
   * @param tableName the name of the table to create
   * @return A Table instance for the created table.
   */
  public static Table createTable(byte[] tableName) throws IOException {
    return createTable(tableName, new byte[][] { FAMILY });
  }

  /**
   * Setup a table with two rows and values per column family.
   * @return A Table instance for the created table.
   */
  public static Table createTable(byte[] tableName, byte[][] families) throws IOException {
    Table table = UTIL.createTable(TableName.valueOf(tableName), families);
    Put p = new Put(Bytes.toBytes("aaa"));
    for (byte[] family : families) {
      p.addColumn(family, null, Bytes.toBytes("value aaa"));
    }
    table.put(p);
    p = new Put(Bytes.toBytes("bbb"));
    for (byte[] family : families) {
      p.addColumn(family, null, Bytes.toBytes("value bbb"));
    }
    table.put(p);
    return table;
  }

  /**
   * Verify that the result and key have expected values.
   * @param r             single row result
   * @param key           the row key
   * @param expectedKey   the expected key
   * @param expectedValue the expected value
   * @return true if the result contains the expected key and value, false otherwise.
   */
  static boolean checkResult(Result r, ImmutableBytesWritable key, byte[] expectedKey,
    byte[] expectedValue) {
    assertEquals(0, key.compareTo(expectedKey));
    Map<byte[], byte[]> vals = r.getFamilyMap(FAMILY);
    byte[] value = vals.values().iterator().next();
    assertTrue(Arrays.equals(value, expectedValue));
    return true; // if succeed
  }

  /**
   * Create table data and run tests on specified htable using the o.a.h.hbase.mapred API.
   */
  static void runTestMapred(Table table) throws IOException {
    org.apache.hadoop.hbase.mapred.TableRecordReader trr =
      new org.apache.hadoop.hbase.mapred.TableRecordReader();
    trr.setStartRow(Bytes.toBytes("aaa"));
    trr.setEndRow(Bytes.toBytes("zzz"));
    trr.setHTable(table);
    trr.setInputColumns(columns);

    trr.init();
    Result r = new Result();
    ImmutableBytesWritable key = new ImmutableBytesWritable();

    boolean more = trr.next(key, r);
    assertTrue(more);
    checkResult(r, key, Bytes.toBytes("aaa"), Bytes.toBytes("value aaa"));

    more = trr.next(key, r);
    assertTrue(more);
    checkResult(r, key, Bytes.toBytes("bbb"), Bytes.toBytes("value bbb"));

    // no more data
    more = trr.next(key, r);
    assertFalse(more);
  }

  /**
   * Create a table that IOE's on first scanner next call
   */
  static Table createIOEScannerTable(byte[] name, final int failCnt) throws IOException {
    // build up a mock scanner stuff to fail the first time
    Answer<ResultScanner> a = new Answer<ResultScanner>() {
      int cnt = 0;

      @Override
      public ResultScanner answer(InvocationOnMock invocation) throws Throwable {
        // first invocation return the busted mock scanner
        if (cnt++ < failCnt) {
          // create mock ResultScanner that always fails.
          Scan scan = mock(Scan.class);
          doReturn(Bytes.toBytes("bogus")).when(scan).getStartRow(); // avoid npe
          ResultScanner scanner = mock(ResultScanner.class);
          // simulate TimeoutException / IOException
          doThrow(new IOException("Injected exception")).when(scanner).next();
          return scanner;
        }

        // otherwise return the real scanner.
        return (ResultScanner) invocation.callRealMethod();
      }
    };

    Table htable = spy(createTable(name));
    doAnswer(a).when(htable).getScanner(any(Scan.class));
    return htable;
  }

  /**
   * Create a table that throws a DoNoRetryIOException on first scanner next call
   */
  static Table createDNRIOEScannerTable(byte[] name, final int failCnt) throws IOException {
    // build up a mock scanner stuff to fail the first time
    Answer<ResultScanner> a = new Answer<ResultScanner>() {
      int cnt = 0;

      @Override
      public ResultScanner answer(InvocationOnMock invocation) throws Throwable {
        // first invocation return the busted mock scanner
        if (cnt++ < failCnt) {
          // create mock ResultScanner that always fails.
          Scan scan = mock(Scan.class);
          doReturn(Bytes.toBytes("bogus")).when(scan).getStartRow(); // avoid npe
          ResultScanner scanner = mock(ResultScanner.class);

          invocation.callRealMethod(); // simulate NotServingRegionException
          doThrow(new NotServingRegionException("Injected simulated TimeoutException"))
            .when(scanner).next();
          return scanner;
        }

        // otherwise return the real scanner.
        return (ResultScanner) invocation.callRealMethod();
      }
    };

    Table htable = spy(createTable(name));
    doAnswer(a).when(htable).getScanner(any(Scan.class));
    return htable;
  }

  /**
   * Run test assuming no errors using mapred api.
   */
  @Test
  public void testTableRecordReader() throws IOException {
    Table table = createTable(Bytes.toBytes("table1"));
    runTestMapred(table);
  }

  /**
   * Run test assuming Scanner IOException failure using mapred api,
   */
  @Test
  public void testTableRecordReaderScannerFail() throws IOException {
    Table htable = createIOEScannerTable(Bytes.toBytes("table2"), 1);
    runTestMapred(htable);
  }

  /**
   * Run test assuming Scanner IOException failure using mapred api,
   */
  @Test
  public void testTableRecordReaderScannerFailTwice() throws IOException {
    Table htable = createIOEScannerTable(Bytes.toBytes("table3"), 2);
    assertThrows(IOException.class, () -> runTestMapred(htable));
  }

  /**
   * Run test assuming NotServingRegionException using mapred api.
   * @throws org.apache.hadoop.hbase.DoNotRetryIOException
   */
  @Test
  public void testTableRecordReaderScannerTimeout() throws IOException {
    Table htable = createDNRIOEScannerTable(Bytes.toBytes("table4"), 1);
    runTestMapred(htable);
  }

  /**
   * Run test assuming NotServingRegionException using mapred api.
   * @throws org.apache.hadoop.hbase.DoNotRetryIOException
   */
  @Test
  public void testTableRecordReaderScannerTimeoutTwice() throws IOException {
    Table htable = createDNRIOEScannerTable(Bytes.toBytes("table5"), 2);
    assertThrows(org.apache.hadoop.hbase.NotServingRegionException.class,
      () -> runTestMapred(htable));
  }

  /**
   * Verify the example we present in javadocs on TableInputFormatBase
   */
  @Test
  public void testExtensionOfTableInputFormatBase() throws IOException {
    LOG.info("testing use of an InputFormat taht extends InputFormatBase");
    final Table table = createTable(Bytes.toBytes("exampleTable"),
      new byte[][] { Bytes.toBytes("columnA"), Bytes.toBytes("columnB") });
    testInputFormat(ExampleTIF.class);
  }

  @Test
  public void testDeprecatedExtensionOfTableInputFormatBase() throws IOException {
    LOG.info(
      "testing use of an InputFormat taht extends InputFormatBase, " + "as it was given in 0.98.");
    final Table table = createTable(Bytes.toBytes("exampleDeprecatedTable"),
      new byte[][] { Bytes.toBytes("columnA"), Bytes.toBytes("columnB") });
    testInputFormat(ExampleDeprecatedTIF.class);
  }

  @Test
  public void testJobConfigurableExtensionOfTableInputFormatBase() throws IOException {
    LOG.info(
      "testing use of an InputFormat taht extends InputFormatBase, " + "using JobConfigurable.");
    final Table table = createTable(Bytes.toBytes("exampleJobConfigurableTable"),
      new byte[][] { Bytes.toBytes("columnA"), Bytes.toBytes("columnB") });
    testInputFormat(ExampleJobConfigurableTIF.class);
  }

  void testInputFormat(Class<? extends InputFormat> clazz) throws IOException {
    Configuration conf = UTIL.getConfiguration();
    final JobConf job = new JobConf(conf);
    job.setInputFormat(clazz);
    job.setOutputFormat(NullOutputFormat.class);
    job.setMapperClass(ExampleVerifier.class);
    job.setNumReduceTasks(0);
    LOG.debug("submitting job.");
    final RunningJob run = JobClient.runJob(job);
    assertTrue(run.isSuccessful(), "job failed!");
    assertEquals(2, run.getCounters()
      .findCounter(TestTableInputFormat.class.getName() + ":row", "aaa").getCounter(),
      "Saw the wrong number of instances of the filtered-for row.");
    assertEquals(0, run.getCounters()
      .findCounter(TestTableInputFormat.class.getName() + ":row", "bbb").getCounter(),
      "Saw any instances of the filtered out row.");
    assertEquals(1, run.getCounters()
      .findCounter(TestTableInputFormat.class.getName() + ":family", "columnA").getCounter(),
      "Saw the wrong number of instances of columnA.");
    assertEquals(1, run.getCounters()
      .findCounter(TestTableInputFormat.class.getName() + ":family", "columnB").getCounter(),
      "Saw the wrong number of instances of columnB.");
    assertEquals(2, run.getCounters()
      .findCounter(TestTableInputFormat.class.getName() + ":value", "value aaa").getCounter(),
      "Saw the wrong count of values for the filtered-for row.");
    assertEquals(0, run.getCounters()
      .findCounter(TestTableInputFormat.class.getName() + ":value", "value bbb").getCounter(),
      "Saw the wrong count of values for the filtered-out row.");
  }

  public static class ExampleVerifier implements TableMap<NullWritable, NullWritable> {

    @Override
    public void configure(JobConf conf) {
    }

    @Override
    public void map(ImmutableBytesWritable key, Result value,
      OutputCollector<NullWritable, NullWritable> output, Reporter reporter) throws IOException {
      for (Cell cell : value.listCells()) {
        reporter
          .getCounter(TestTableInputFormat.class.getName() + ":row",
            Bytes.toString(cell.getRowArray(), cell.getRowOffset(), cell.getRowLength()))
          .increment(1l);
        reporter
          .getCounter(TestTableInputFormat.class.getName() + ":family",
            Bytes.toString(cell.getFamilyArray(), cell.getFamilyOffset(), cell.getFamilyLength()))
          .increment(1l);
        reporter
          .getCounter(TestTableInputFormat.class.getName() + ":value",
            Bytes.toString(cell.getValueArray(), cell.getValueOffset(), cell.getValueLength()))
          .increment(1l);
      }
    }

    @Override
    public void close() {
    }

  }

  public static class ExampleDeprecatedTIF extends TableInputFormatBase implements JobConfigurable {

    @Override
    public void configure(JobConf job) {
      try {
        Connection connection = ConnectionFactory.createConnection(job);
        Table exampleTable = connection.getTable(TableName.valueOf("exampleDeprecatedTable"));
        // mandatory
        initializeTable(connection, exampleTable.getName());
        byte[][] inputColumns = new byte[][] { Bytes.toBytes("columnA"), Bytes.toBytes("columnB") };
        // mandatory
        setInputColumns(inputColumns);
        Filter exampleFilter =
          new RowFilter(CompareOperator.EQUAL, new RegexStringComparator("aa.*"));
        // optional
        setRowFilter(exampleFilter);
      } catch (IOException exception) {
        throw new RuntimeException("Failed to configure for job.", exception);
      }
    }

  }

  public static class ExampleJobConfigurableTIF extends ExampleTIF implements JobConfigurable {

    @Override
    public void configure(JobConf job) {
      try {
        initialize(job);
      } catch (IOException exception) {
        throw new RuntimeException("Failed to initialize.", exception);
      }
    }

    @Override
    protected void initialize(JobConf job) throws IOException {
      initialize(job, "exampleJobConfigurableTable");
    }
  }

  public static class ExampleTIF extends TableInputFormatBase {

    @Override
    protected void initialize(JobConf job) throws IOException {
      initialize(job, "exampleTable");
    }

    protected void initialize(JobConf job, String table) throws IOException {
      Connection connection = ConnectionFactory.createConnection(HBaseConfiguration.create(job));
      TableName tableName = TableName.valueOf(table);
      // mandatory
      initializeTable(connection, tableName);
      byte[][] inputColumns = new byte[][] { Bytes.toBytes("columnA"), Bytes.toBytes("columnB") };
      // mandatory
      setInputColumns(inputColumns);
      Filter exampleFilter =
        new RowFilter(CompareOperator.EQUAL, new RegexStringComparator("aa.*"));
      // optional
      setRowFilter(exampleFilter);
    }

  }

}