Java Code Examples for org.apache.flink.types.parser.StringParser

The following examples show how to use org.apache.flink.types.parser.StringParser. These examples are extracted from open source projects. You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may check out the related API usage on the sidebar.
Example 1
Source Project: Flink-CEPplus   Source File: CsvInputFormatTest.java    License: Apache License 2.0 6 votes vote down vote up
@Test
public void testParseStringErrors() throws Exception {
	StringParser stringParser = new StringParser();
	stringParser.enableQuotedStringParsing((byte) '"');

	Object[][] failures = {
			{"\"string\" trailing", FieldParser.ParseErrorState.UNQUOTED_CHARS_AFTER_QUOTED_STRING},
			{"\"unterminated ", FieldParser.ParseErrorState.UNTERMINATED_QUOTED_STRING}
	};

	for (Object[] failure : failures) {
		String input = (String) failure[0];

		int result = stringParser.parseField(input.getBytes(ConfigConstants.DEFAULT_CHARSET), 0,
			input.length(), new byte[]{'|'}, null);

		assertThat(result, is(-1));
		assertThat(stringParser.getErrorState(), is(failure[1]));
	}

}
 
Example 2
Source Project: Flink-CEPplus   Source File: RowCsvInputFormatTest.java    License: Apache License 2.0 6 votes vote down vote up
@Test
public void testParseStringErrors() throws Exception {
	StringParser stringParser = new StringParser();

	stringParser.enableQuotedStringParsing((byte) '"');

	Map<String, StringParser.ParseErrorState> failures = new HashMap<>();
	failures.put("\"string\" trailing", FieldParser.ParseErrorState.UNQUOTED_CHARS_AFTER_QUOTED_STRING);
	failures.put("\"unterminated ", FieldParser.ParseErrorState.UNTERMINATED_QUOTED_STRING);

	for (Map.Entry<String, StringParser.ParseErrorState> failure : failures.entrySet()) {
		int result = stringParser.parseField(
			failure.getKey().getBytes(ConfigConstants.DEFAULT_CHARSET),
			0,
			failure.getKey().length(),
			new byte[]{(byte) '|'},
			null);
		assertEquals(-1, result);
		assertEquals(failure.getValue(), stringParser.getErrorState());
	}
}
 
Example 3
Source Project: flink   Source File: CsvInputFormatTest.java    License: Apache License 2.0 6 votes vote down vote up
@Test
public void testParseStringErrors() throws Exception {
	StringParser stringParser = new StringParser();
	stringParser.enableQuotedStringParsing((byte) '"');

	Object[][] failures = {
			{"\"string\" trailing", FieldParser.ParseErrorState.UNQUOTED_CHARS_AFTER_QUOTED_STRING},
			{"\"unterminated ", FieldParser.ParseErrorState.UNTERMINATED_QUOTED_STRING}
	};

	for (Object[] failure : failures) {
		String input = (String) failure[0];

		int result = stringParser.parseField(input.getBytes(ConfigConstants.DEFAULT_CHARSET), 0,
			input.length(), new byte[]{'|'}, null);

		assertThat(result, is(-1));
		assertThat(stringParser.getErrorState(), is(failure[1]));
	}

}
 
Example 4
Source Project: flink   Source File: RowCsvInputFormatTest.java    License: Apache License 2.0 6 votes vote down vote up
@Test
public void testParseStringErrors() throws Exception {
	StringParser stringParser = new StringParser();

	stringParser.enableQuotedStringParsing((byte) '"');

	Map<String, StringParser.ParseErrorState> failures = new HashMap<>();
	failures.put("\"string\" trailing", FieldParser.ParseErrorState.UNQUOTED_CHARS_AFTER_QUOTED_STRING);
	failures.put("\"unterminated ", FieldParser.ParseErrorState.UNTERMINATED_QUOTED_STRING);

	for (Map.Entry<String, StringParser.ParseErrorState> failure : failures.entrySet()) {
		int result = stringParser.parseField(
			failure.getKey().getBytes(ConfigConstants.DEFAULT_CHARSET),
			0,
			failure.getKey().length(),
			new byte[]{(byte) '|'},
			null);
		assertEquals(-1, result);
		assertEquals(failure.getValue(), stringParser.getErrorState());
	}
}
 
Example 5
Source Project: flink   Source File: CsvInputFormatTest.java    License: Apache License 2.0 6 votes vote down vote up
@Test
public void testParseStringErrors() throws Exception {
	StringParser stringParser = new StringParser();
	stringParser.enableQuotedStringParsing((byte) '"');

	Object[][] failures = {
			{"\"string\" trailing", FieldParser.ParseErrorState.UNQUOTED_CHARS_AFTER_QUOTED_STRING},
			{"\"unterminated ", FieldParser.ParseErrorState.UNTERMINATED_QUOTED_STRING}
	};

	for (Object[] failure : failures) {
		String input = (String) failure[0];

		int result = stringParser.parseField(input.getBytes(ConfigConstants.DEFAULT_CHARSET), 0,
			input.length(), new byte[]{'|'}, null);

		assertThat(result, is(-1));
		assertThat(stringParser.getErrorState(), is(failure[1]));
	}

}
 
Example 6
Source Project: flink   Source File: RowCsvInputFormatTest.java    License: Apache License 2.0 6 votes vote down vote up
@Test
public void testParseStringErrors() throws Exception {
	StringParser stringParser = new StringParser();

	stringParser.enableQuotedStringParsing((byte) '"');

	Map<String, StringParser.ParseErrorState> failures = new HashMap<>();
	failures.put("\"string\" trailing", FieldParser.ParseErrorState.UNQUOTED_CHARS_AFTER_QUOTED_STRING);
	failures.put("\"unterminated ", FieldParser.ParseErrorState.UNTERMINATED_QUOTED_STRING);

	for (Map.Entry<String, StringParser.ParseErrorState> failure : failures.entrySet()) {
		int result = stringParser.parseField(
			failure.getKey().getBytes(ConfigConstants.DEFAULT_CHARSET),
			0,
			failure.getKey().length(),
			new byte[]{(byte) '|'},
			null);
		assertEquals(-1, result);
		assertEquals(failure.getValue(), stringParser.getErrorState());
	}
}
 
Example 7
Source Project: Flink-CEPplus   Source File: GenericCsvInputFormat.java    License: Apache License 2.0 5 votes vote down vote up
@Override
public void open(FileInputSplit split) throws IOException {
	super.open(split);

	// instantiate the parsers
	FieldParser<?>[] parsers = new FieldParser<?>[fieldTypes.length];
	
	for (int i = 0; i < fieldTypes.length; i++) {
		if (fieldTypes[i] != null) {
			Class<? extends FieldParser<?>> parserType = FieldParser.getParserForType(fieldTypes[i]);
			if (parserType == null) {
				throw new RuntimeException("No parser available for type '" + fieldTypes[i].getName() + "'.");
			}

			FieldParser<?> p = InstantiationUtil.instantiate(parserType, FieldParser.class);

			p.setCharset(getCharset());
			if (this.quotedStringParsing) {
				if (p instanceof StringParser) {
					((StringParser)p).enableQuotedStringParsing(this.quoteCharacter);
				} else if (p instanceof StringValueParser) {
					((StringValueParser)p).enableQuotedStringParsing(this.quoteCharacter);
				}
			}

			parsers[i] = p;
		}
	}
	this.fieldParsers = parsers;
	
	// skip the first line, if we are at the beginning of a file and have the option set
	if (this.skipFirstLineAsHeader && this.splitStart == 0) {
		readLine(); // read and ignore
	}
}
 
Example 8
Source Project: flink   Source File: GenericCsvInputFormat.java    License: Apache License 2.0 5 votes vote down vote up
@Override
public void open(FileInputSplit split) throws IOException {
	super.open(split);

	// instantiate the parsers
	FieldParser<?>[] parsers = new FieldParser<?>[fieldTypes.length];
	
	for (int i = 0; i < fieldTypes.length; i++) {
		if (fieldTypes[i] != null) {
			Class<? extends FieldParser<?>> parserType = FieldParser.getParserForType(fieldTypes[i]);
			if (parserType == null) {
				throw new RuntimeException("No parser available for type '" + fieldTypes[i].getName() + "'.");
			}

			FieldParser<?> p = InstantiationUtil.instantiate(parserType, FieldParser.class);

			p.setCharset(getCharset());
			if (this.quotedStringParsing) {
				if (p instanceof StringParser) {
					((StringParser)p).enableQuotedStringParsing(this.quoteCharacter);
				} else if (p instanceof StringValueParser) {
					((StringValueParser)p).enableQuotedStringParsing(this.quoteCharacter);
				}
			}

			parsers[i] = p;
		}
	}
	this.fieldParsers = parsers;
	
	// skip the first line, if we are at the beginning of a file and have the option set
	if (this.skipFirstLineAsHeader && this.splitStart == 0) {
		readLine(); // read and ignore
	}
}
 
Example 9
Source Project: flink   Source File: GenericCsvInputFormat.java    License: Apache License 2.0 5 votes vote down vote up
@Override
public void open(FileInputSplit split) throws IOException {
	super.open(split);

	// instantiate the parsers
	FieldParser<?>[] parsers = new FieldParser<?>[fieldTypes.length];
	
	for (int i = 0; i < fieldTypes.length; i++) {
		if (fieldTypes[i] != null) {
			Class<? extends FieldParser<?>> parserType = FieldParser.getParserForType(fieldTypes[i]);
			if (parserType == null) {
				throw new RuntimeException("No parser available for type '" + fieldTypes[i].getName() + "'.");
			}

			FieldParser<?> p = InstantiationUtil.instantiate(parserType, FieldParser.class);

			p.setCharset(getCharset());
			if (this.quotedStringParsing) {
				if (p instanceof StringParser) {
					((StringParser)p).enableQuotedStringParsing(this.quoteCharacter);
				} else if (p instanceof StringValueParser) {
					((StringValueParser)p).enableQuotedStringParsing(this.quoteCharacter);
				}
			}

			parsers[i] = p;
		}
	}
	this.fieldParsers = parsers;
	
	// skip the first line, if we are at the beginning of a file and have the option set
	if (this.skipFirstLineAsHeader && this.splitStart == 0) {
		readLine(); // read and ignore
	}
}