Search in sources :

Example 1 with ParsedLine

use of org.apache.hadoop.hbase.mapreduce.ImportTsv.TsvParser.ParsedLine in project hbase by apache.

the class TestImportTsvParser method testTsvParseAttributesKey.

@Test
public void testTsvParseAttributesKey() throws BadTsvLineException {
    TsvParser parser = new TsvParser("HBASE_ROW_KEY,col_a,HBASE_TS_KEY,HBASE_ATTRIBUTES_KEY", "\t");
    assertEquals(0, parser.getRowKeyColumnIndex());
    byte[] line = Bytes.toBytes("rowkey\tval_a\t1234\tkey=>value");
    ParsedLine parse = parser.parse(line, line.length);
    assertEquals(18, parse.getAttributeKeyOffset());
    assertEquals(3, parser.getAttributesKeyColumnIndex());
    String[] attributes = parse.getIndividualAttributes();
    assertEquals(attributes[0], "key=>value");
    try {
        line = Bytes.toBytes("rowkey\tval_a\t1234");
        parser.parse(line, line.length);
        fail("Should get BadTsvLineException on empty rowkey.");
    } catch (BadTsvLineException b) {
    }
    parser = new TsvParser("HBASE_ATTRIBUTES_KEY,col_a,HBASE_ROW_KEY,HBASE_TS_KEY", "\t");
    assertEquals(2, parser.getRowKeyColumnIndex());
    line = Bytes.toBytes("key=>value\tval_a\trowkey\t1234");
    parse = parser.parse(line, line.length);
    assertEquals(0, parse.getAttributeKeyOffset());
    assertEquals(0, parser.getAttributesKeyColumnIndex());
    attributes = parse.getIndividualAttributes();
    assertEquals(attributes[0], "key=>value");
    try {
        line = Bytes.toBytes("val_a");
        ParsedLine parse2 = parser.parse(line, line.length);
        fail("Should get BadTsvLineException when number of columns less than rowkey position.");
    } catch (BadTsvLineException b) {
    }
    parser = new TsvParser("col_a,HBASE_ATTRIBUTES_KEY,HBASE_TS_KEY,HBASE_ROW_KEY", "\t");
    assertEquals(3, parser.getRowKeyColumnIndex());
    line = Bytes.toBytes("val_a\tkey0=>value0,key1=>value1,key2=>value2\t1234\trowkey");
    parse = parser.parse(line, line.length);
    assertEquals(1, parser.getAttributesKeyColumnIndex());
    assertEquals(6, parse.getAttributeKeyOffset());
    String[] attr = parse.getIndividualAttributes();
    int i = 0;
    for (String str : attr) {
        assertEquals(("key" + i + "=>" + "value" + i), str);
        i++;
    }
}
Also used : BadTsvLineException(org.apache.hadoop.hbase.mapreduce.ImportTsv.TsvParser.BadTsvLineException) ParsedLine(org.apache.hadoop.hbase.mapreduce.ImportTsv.TsvParser.ParsedLine) TsvParser(org.apache.hadoop.hbase.mapreduce.ImportTsv.TsvParser) Test(org.junit.Test)

Example 2 with ParsedLine

use of org.apache.hadoop.hbase.mapreduce.ImportTsv.TsvParser.ParsedLine in project hbase by apache.

the class TestImportTsvParser method testTsvParserWithCellVisibilityCol.

@Test
public void testTsvParserWithCellVisibilityCol() throws BadTsvLineException {
    TsvParser parser = new TsvParser("HBASE_ROW_KEY,col_a,HBASE_TS_KEY,HBASE_ATTRIBUTES_KEY,HBASE_CELL_VISIBILITY", "\t");
    assertEquals(0, parser.getRowKeyColumnIndex());
    assertEquals(4, parser.getCellVisibilityColumnIndex());
    byte[] line = Bytes.toBytes("rowkey\tval_a\t1234\tkey=>value\tPRIVATE&SECRET");
    ParsedLine parse = parser.parse(line, line.length);
    assertEquals(18, parse.getAttributeKeyOffset());
    assertEquals(3, parser.getAttributesKeyColumnIndex());
    String[] attributes = parse.getIndividualAttributes();
    assertEquals(attributes[0], "key=>value");
    assertEquals(29, parse.getCellVisibilityColumnOffset());
}
Also used : ParsedLine(org.apache.hadoop.hbase.mapreduce.ImportTsv.TsvParser.ParsedLine) TsvParser(org.apache.hadoop.hbase.mapreduce.ImportTsv.TsvParser) Test(org.junit.Test)

Example 3 with ParsedLine

use of org.apache.hadoop.hbase.mapreduce.ImportTsv.TsvParser.ParsedLine in project hbase by apache.

the class TestImportTsvParser method testTsvParserInvalidTimestamp.

@Test(expected = BadTsvLineException.class)
public void testTsvParserInvalidTimestamp() throws BadTsvLineException {
    TsvParser parser = new TsvParser("HBASE_ROW_KEY,HBASE_TS_KEY,col_a,", "\t");
    assertEquals(1, parser.getTimestampKeyColumnIndex());
    byte[] line = Bytes.toBytes("rowkey\ttimestamp\tval_a");
    ParsedLine parsed = parser.parse(line, line.length);
    assertEquals(-1, parsed.getTimestamp(-1));
    checkParsing(parsed, Splitter.on("\t").split(Bytes.toString(line)));
}
Also used : ParsedLine(org.apache.hadoop.hbase.mapreduce.ImportTsv.TsvParser.ParsedLine) TsvParser(org.apache.hadoop.hbase.mapreduce.ImportTsv.TsvParser) Test(org.junit.Test)

Example 4 with ParsedLine

use of org.apache.hadoop.hbase.mapreduce.ImportTsv.TsvParser.ParsedLine in project hbase by apache.

the class TestImportTsvParser method testTsvParser.

@Test
public void testTsvParser() throws BadTsvLineException {
    TsvParser parser = new TsvParser("col_a,col_b:qual,HBASE_ROW_KEY,col_d", "\t");
    assertBytesEquals(Bytes.toBytes("col_a"), parser.getFamily(0));
    assertBytesEquals(HConstants.EMPTY_BYTE_ARRAY, parser.getQualifier(0));
    assertBytesEquals(Bytes.toBytes("col_b"), parser.getFamily(1));
    assertBytesEquals(Bytes.toBytes("qual"), parser.getQualifier(1));
    assertNull(parser.getFamily(2));
    assertNull(parser.getQualifier(2));
    assertEquals(2, parser.getRowKeyColumnIndex());
    assertEquals(TsvParser.DEFAULT_TIMESTAMP_COLUMN_INDEX, parser.getTimestampKeyColumnIndex());
    byte[] line = Bytes.toBytes("val_a\tval_b\tval_c\tval_d");
    ParsedLine parsed = parser.parse(line, line.length);
    checkParsing(parsed, Splitter.on("\t").split(Bytes.toString(line)));
}
Also used : ParsedLine(org.apache.hadoop.hbase.mapreduce.ImportTsv.TsvParser.ParsedLine) TsvParser(org.apache.hadoop.hbase.mapreduce.ImportTsv.TsvParser) Test(org.junit.Test)

Example 5 with ParsedLine

use of org.apache.hadoop.hbase.mapreduce.ImportTsv.TsvParser.ParsedLine in project hbase by apache.

the class TestImportTsvParser method testTsvParserWithTimestamp.

@Test
public void testTsvParserWithTimestamp() throws BadTsvLineException {
    TsvParser parser = new TsvParser("HBASE_ROW_KEY,HBASE_TS_KEY,col_a,", "\t");
    assertNull(parser.getFamily(0));
    assertNull(parser.getQualifier(0));
    assertNull(parser.getFamily(1));
    assertNull(parser.getQualifier(1));
    assertBytesEquals(Bytes.toBytes("col_a"), parser.getFamily(2));
    assertBytesEquals(HConstants.EMPTY_BYTE_ARRAY, parser.getQualifier(2));
    assertEquals(0, parser.getRowKeyColumnIndex());
    assertEquals(1, parser.getTimestampKeyColumnIndex());
    byte[] line = Bytes.toBytes("rowkey\t1234\tval_a");
    ParsedLine parsed = parser.parse(line, line.length);
    assertEquals(1234l, parsed.getTimestamp(-1));
    checkParsing(parsed, Splitter.on("\t").split(Bytes.toString(line)));
}
Also used : ParsedLine(org.apache.hadoop.hbase.mapreduce.ImportTsv.TsvParser.ParsedLine) TsvParser(org.apache.hadoop.hbase.mapreduce.ImportTsv.TsvParser) Test(org.junit.Test)

Aggregations

TsvParser (org.apache.hadoop.hbase.mapreduce.ImportTsv.TsvParser)5 ParsedLine (org.apache.hadoop.hbase.mapreduce.ImportTsv.TsvParser.ParsedLine)5 Test (org.junit.Test)5 BadTsvLineException (org.apache.hadoop.hbase.mapreduce.ImportTsv.TsvParser.BadTsvLineException)1