public static void registerFilters(Configuration conf) { String[] filters = conf.getStrings(THRIFT_FILTERS); Splitter splitter = Splitter.on(':'); if(filters != null) { for(String filterClass: filters) { List<String> filterPart = splitter.splitToList(filterClass); if(filterPart.size() != 2) { LOG.warn("Invalid filter specification " + filterClass + " - skipping"); } else { ParseFilter.registerFilter(filterPart.get(0), filterPart.get(1)); } } } }
Splitter.on(',').trimResults().split(columnsSpecification));
@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))); }
@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))); }
Set<String> families = Sets.newHashSet(); if (cf != null) { Iterables.addAll(families, Splitter.on(",").split(cf));
@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))); }
/** * Returns a splitter that uses the given single-character separator. For example, * {@code Splitter.on(',').split("foo,,bar")} returns an iterable containing * {@code ["foo", "", "bar"]}. * * @param separator the character to recognize as a separator * @return a splitter, with default settings, that recognizes that separator */ public static Splitter on(char separator) { return on(CharMatcher.is(separator)); }
public static void registerFilters(Configuration conf) { String[] filters = conf.getStrings("hbase.thrift.filters"); Splitter splitter = Splitter.on(':'); if(filters != null) { for(String filterClass: filters) { List<String> filterPart = splitter.splitToList(filterClass); if(filterPart.size() != 2) { LOG.warn("Invalid filter specification " + filterClass + " - skipping"); } else { ParseFilter.registerFilter(filterPart.get(0), filterPart.get(1)); } } } }
/** * Returns a {@code MapSplitter} which splits entries based on this splitter, and splits entries * into keys and values using the specified separator. * * @since 10.0 */ @Beta public MapSplitter withKeyValueSeparator(String separator) { return withKeyValueSeparator(on(separator)); }
/** * Returns a {@code MapSplitter} which splits entries based on this splitter, and splits entries * into keys and values using the specified separator. * * @since 14.0 */ @Beta public MapSplitter withKeyValueSeparator(char separator) { return withKeyValueSeparator(on(separator)); }
/** * Returns a splitter that considers any subsequence matching {@code pattern} to be a separator. * For example, {@code Splitter.on(Pattern.compile("\r?\n")).split(entireFile)} splits a string * into lines whether it uses DOS-style or UNIX-style line terminators. * * @param separatorPattern the pattern that determines whether a subsequence is a separator. This * pattern may not match the empty string. * @return a splitter, with default settings, that uses this pattern * @throws IllegalArgumentException if {@code separatorPattern} matches the empty string */ @GwtIncompatible // java.util.regex public static Splitter on(Pattern separatorPattern) { return on(new JdkPattern(separatorPattern)); }
/** * Returns a splitter that considers any subsequence matching a given pattern (regular expression) * to be a separator. For example, {@code Splitter.onPattern("\r?\n").split(entireFile)} splits a * string into lines whether it uses DOS-style or UNIX-style line terminators. This is equivalent * to {@code Splitter.on(Pattern.compile(pattern))}. * * @param separatorPattern the pattern that determines whether a subsequence is a separator. This * pattern may not match the empty string. * @return a splitter, with default settings, that uses this pattern * @throws IllegalArgumentException if {@code separatorPattern} matches the empty string or is a * malformed expression */ @GwtIncompatible // java.util.regex public static Splitter onPattern(String separatorPattern) { return on(Platform.compilePattern(separatorPattern)); }
checkArgument(separator.length() != 0, "The separator may not be the empty string."); if (separator.length() == 1) { return Splitter.on(separator.charAt(0));
/** * Converts a field mask from a Proto3 JSON string, that is splitting the paths along commas and * converting from camel case to snake case. */ public static FieldMask fromJsonString(String value) { Iterable<String> paths = Splitter.on(FIELD_PATH_SEPARATOR).split(value); FieldMask.Builder builder = FieldMask.newBuilder(); for (String path : paths) { if (path.isEmpty()) { continue; } builder.addPaths(CaseFormat.LOWER_CAMEL.to(CaseFormat.LOWER_UNDERSCORE, path)); } return builder.build(); }
@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))); }
@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))); }
@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))); }
@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))); }
@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))); }
@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))); }