[CAMEL-10053] Bindy does not seem to support Cp922 character encoding

• Type: Bug
• Status: Closed
• Priority: Major
• Resolution: Not A Bug
• Affects Version/s: 2.16.2
• Component/s: camel-bindy
• Estimated Complexity: Unknown
• Assignee: Unassigned
• Reporter: David Cornforth
• Created: 13/Jun/16 17:05
• Updated: 16/Jun/16 07:29
• Resolved: 15/Jun/16 20:46

Description

If I use the charset option when consuming from a non UTF8 encoded file and then unmarshal the result using a bindy object the result is either an exception or incorrect data. Below are some unit tests that illustrate the issue. The UTF8 ones work, but all of the Cp922 ones fail for a variety of reasons, both using BindyFixedLengthDataFormat and BindyCsvDataFormat. I have only tested this with Cp922, but it may be the case that other non-standard encodings also exhibit the same behaviour.

import org.apache.camel.EndpointInject;
import org.apache.camel.builder.RouteBuilder;
import org.apache.camel.component.mock.MockEndpoint;
import org.apache.camel.dataformat.bindy.annotation.CsvRecord;
import org.apache.camel.dataformat.bindy.annotation.DataField;
import org.apache.camel.dataformat.bindy.annotation.FixedLengthRecord;
import org.apache.camel.dataformat.bindy.csv.BindyCsvDataFormat;
import org.apache.camel.dataformat.bindy.fixed.BindyFixedLengthDataFormat;
import org.apache.camel.test.junit4.CamelTestSupport;
import org.junit.After;
import org.junit.Test;

import java.io.IOException;
import java.nio.file.Files;
import java.nio.file.Paths;
import java.util.List;

public class BindyEncodingTest extends CamelTestSupport {

    private static final String RESULT_FIXED_LENGTH_UTF8 = "mock:result_fixed_length_utf8";
    private static final String RESULT_FIXED_LENGTH_CP922 = "mock:result_fixed_length_cp922";
    private static final String RESULT_CSV_UTF8 = "mock:result_csv_utf8";
    private static final String RESULT_CSV_CP922 = "mock:result_csv_cp922";

    private static final String TMP = "C:/tmp";
    private static final String FIXED_LENGTH_UTF8 = "BindyEncodingTest.FixedLength.utf8.txt";
    private static final String FIXED_LENGTH_CP922 = "BindyEncodingTest.FixedLength.cp922.txt";
    private static final String CSV_UTF8 = "BindyEncodingTest.csv.utf8.txt";
    private static final String CSV_CP922 = "BindyEncodingTest.csv.cp922.txt";

    @EndpointInject(uri = RESULT_FIXED_LENGTH_UTF8)
    protected MockEndpoint resultEndpointFixedLengthUtf8;

    @EndpointInject(uri = RESULT_FIXED_LENGTH_CP922)
    protected MockEndpoint resultEndpointFixedLengthCp922;

    @EndpointInject(uri = RESULT_CSV_UTF8)
    protected MockEndpoint resultEndpointCsvUtf8;

    @EndpointInject(uri = RESULT_CSV_CP922)
    protected MockEndpoint resultEndpointCsvCp922;

    @Override
    protected RouteBuilder createRouteBuilder() throws Exception {
        return new RouteBuilder() {
            @Override
            public void configure() throws Exception {
                from("file://"+TMP+"?fileName="+ FIXED_LENGTH_UTF8 +"&charset=UTF8")
                        .unmarshal(new BindyFixedLengthDataFormat(FixedLengthBindy.class))
                        .to(RESULT_FIXED_LENGTH_UTF8);

                from("file://"+TMP+"?fileName="+ FIXED_LENGTH_CP922 +"&charset=Cp922")
                        .unmarshal(new BindyFixedLengthDataFormat(FixedLengthBindy.class))
                        .to(RESULT_FIXED_LENGTH_CP922);

                from("file://"+TMP+"?fileName="+ CSV_UTF8 +"&charset=UTF8")
                        .unmarshal(new BindyCsvDataFormat(CsvBindy.class))
                        .to(RESULT_CSV_UTF8);

                from("file://"+TMP+"?fileName="+ CSV_CP922 +"&charset=Cp922")
                        .unmarshal(new BindyCsvDataFormat(CsvBindy.class))
                        .to(RESULT_CSV_CP922);
            }
        };
    }

    @After
    public void after() throws InterruptedException {
        assertMockEndpointsSatisfied();
    }

    /* works */
    @Test
    public void fixedLengthUtf8() throws IOException, InterruptedException {
        byte[] input = new byte[]{
                (byte)0xC3,(byte)0x85, // Å
                (byte)0xC3,(byte)0x98, // Ø
                (byte)0xC3,(byte)0x86, // Æ
                (byte)0x33,(byte)0x34,(byte)0x35,(byte)0x36,(byte)0x37,(byte)0x38,(byte)0x39 // 3456789
        };

        writeFile(TMP+"/"+ FIXED_LENGTH_UTF8, input);
        resultEndpointFixedLengthUtf8.expectedMessageCount(1);
        Thread.sleep(5000);

        Object body = resultEndpointFixedLengthUtf8.getExchanges().get(0).getIn().getBody();
        assertTrue("The message body is null", body != null);
        assertTrue(body instanceof FixedLengthBindy);
        FixedLengthBindy fixedLengthBindy = (FixedLengthBindy) body;
        assertEquals("First is incorrect","Å",fixedLengthBindy.getFirst());
        assertEquals("Second is incorrect","ØÆ",fixedLengthBindy.getSecond());
        assertEquals("Third is incorrect","345678",fixedLengthBindy.getThird());
        assertEquals("Fourth is incorrect","9",fixedLengthBindy.getFourth());
        System.out.println(body);
    }

    /* fails with java.lang.StringIndexOutOfBoundsException */
    @Test
    public void fixedLengthCp922() throws IOException, InterruptedException {
        // ftp://ftp.software.ibm.com/software/globalization/gcoc/attachments/CP00922.pdf
        byte[] input = new byte[]{
                (byte)0xC5, // Å
                (byte)0xD8, // Ø
                (byte)0xC6, // Æ
                (byte)0x33,(byte)0x34,(byte)0x35,(byte)0x36,(byte)0x37,(byte)0x38,(byte)0x39 // 3456789
        };

        writeFile(TMP + "/" + FIXED_LENGTH_CP922, input);
        resultEndpointFixedLengthCp922.expectedMessageCount(1);
        Thread.sleep(5000);

        Object body = resultEndpointFixedLengthCp922.getExchanges().get(0).getIn().getBody();
        assertTrue("The message body is null", body != null);
        assertTrue(body instanceof FixedLengthBindy);
        FixedLengthBindy fixedLengthBindy = (FixedLengthBindy) body;
        assertEquals("First is incorrect","Å",fixedLengthBindy.getFirst());
        assertEquals("Second is incorrect","ØÆ",fixedLengthBindy.getSecond());
        assertEquals("Third is incorrect","345678",fixedLengthBindy.getThird());
        assertEquals("Fourth is incorrect","9",fixedLengthBindy.getFourth());
        System.out.println(body);
    }

    /* fails as Third is incorrect */
    @Test
    public void fixedLengthCp922a() throws IOException, InterruptedException {
        // ftp://ftp.software.ibm.com/software/globalization/gcoc/attachments/CP00922.pdf
        byte[] input = new byte[]{
                (byte)0x31,(byte)0x32,(byte)0x33,(byte)0x34,(byte)0x35,(byte)0x36,(byte)0x37, // 1234567
                (byte)0xD8, // Ø
                (byte)0xC6, // Æ
                (byte)0xC5 // Å
        };

        writeFile(TMP + "/" + FIXED_LENGTH_CP922, input);
        resultEndpointFixedLengthCp922.expectedMessageCount(1);
        Thread.sleep(5000);

        Object body = resultEndpointFixedLengthCp922.getExchanges().get(0).getIn().getBody();
        assertTrue("The message body is null", body != null);
        assertTrue(body instanceof FixedLengthBindy);
        FixedLengthBindy fixedLengthBindy = (FixedLengthBindy) body;
        assertEquals("First is incorrect","1",fixedLengthBindy.getFirst());
        assertEquals("Second is incorrect","23",fixedLengthBindy.getSecond());
        assertEquals("Third is incorrect","4567ØÆ",fixedLengthBindy.getThird());
        assertEquals("Fourth is incorrect","Å",fixedLengthBindy.getFourth());
        System.out.println(body);
    }

    /* works */
    @Test
    public void csvUtf8() throws IOException, InterruptedException {
        byte[] input = new byte[]{
                (byte)0xC3,(byte)0x85, // Å
                (byte)0x2C, // ,
                (byte)0xC3,(byte)0x98, // Ø
                (byte)0xC3,(byte)0x86, // Æ
                (byte)0x2C, // ,
                (byte)0x33,(byte)0x34,(byte)0x35,(byte)0x36,(byte)0x37,(byte)0x38,
                (byte)0x2C, // ,
                (byte)0x39 // 3456789
        };

        writeFile(TMP+"/"+ CSV_UTF8, input);
        resultEndpointCsvUtf8.expectedMessageCount(1);
        Thread.sleep(5000);

        Object body = resultEndpointCsvUtf8.getExchanges().get(0).getIn().getBody();
        assertTrue("The message body is null", body != null);
        assertTrue(body instanceof CsvBindy);
        CsvBindy csvBindy = (CsvBindy) body;
        assertEquals("First is incorrect","Å",csvBindy.getFirst());
        assertEquals("First is incorrect","ØÆ",csvBindy.getSecond());
        assertEquals("First is incorrect","345678",csvBindy.getThird());
        assertEquals("First is incorrect","9",csvBindy.getFourth());
        System.out.println(body);
    }

    /* fails as First is incorrect */
    @Test
    public void csvCp922() throws IOException, InterruptedException {
        // ftp://ftp.software.ibm.com/software/globalization/gcoc/attachments/CP00922.pdf
        byte[] input = new byte[]{
                (byte)0xC5, // Å
                (byte)0x2C, // ,
                (byte)0xD8, // Ø
                (byte)0xC6, // Æ
                (byte)0x2C, // ,
                (byte)0x33,(byte)0x34,(byte)0x35,(byte)0x36,(byte)0x37,(byte)0x38, // 345678
                (byte)0x2C, // ,
                (byte)0x39  // 9
        };

        writeFile(TMP+"/"+ CSV_CP922, input);
        resultEndpointCsvCp922.expectedMessageCount(1);
        Thread.sleep(5000);

        Object body = resultEndpointCsvCp922.getExchanges().get(0).getIn().getBody();
        assertTrue("The message body is null", body != null);
        assertTrue("body is not List it is "+body.getClass(), body instanceof List);
        List<?> list = (List<?>)body;
        assertEquals("incorrect list size", 2, list.size());
        CsvBindy csvBindy = (CsvBindy) list.get(0);
        assertEquals("First is incorrect","Å",csvBindy.getFirst());
        assertEquals("First is incorrect","ØÆ",csvBindy.getSecond());
        assertEquals("First is incorrect","345678",csvBindy.getThird());
        assertEquals("First is incorrect","9",csvBindy.getFourth());
        System.out.println(body);
    }

    private void writeFile(String path, byte[] content) throws IOException {
        Files.write(Paths.get(path),content);
    }

    @FixedLengthRecord(ignoreTrailingChars = true)
    public static class FixedLengthBindy {
        @DataField(pos = 1, length = 1) // 1
        private String first;

        @DataField(pos = 2, length = 2) // 2 - 3
        private String second;

        @DataField(pos = 3, length = 6) // 4 - 9
        private String third;

        @DataField(pos = 4, length = 1) // 10
        private String fourth;

        public String getFirst() {
            return first;
        }

        public void setFirst(String first) {
            this.first = first;
        }

        public String getSecond() {
            return second;
        }

        public void setSecond(String second) {
            this.second = second;
        }

        public String getThird() {
            return third;
        }

        public void setThird(String third) {
            this.third = third;
        }

        public String getFourth() {
            return fourth;
        }

        public void setFourth(String fourth) {
            this.fourth = fourth;
        }

        @Override
        public String toString() {
            return "FixedLengthBindy{" +
                    "first='" + first + '\'' +
                    ", second='" + second + '\'' +
                    ", third='" + third + '\'' +
                    ", fourth='" + fourth + '\'' +
                    '}';
        }
    }

    @CsvRecord(separator = ",", skipFirstLine = false)
    public static class CsvBindy{
        @DataField(pos = 1)
        private String first;
        @DataField(pos = 2)
        private String second;
        @DataField(pos = 3)
        private String third;
        @DataField(pos = 4)
        private String fourth;

        public String getFirst() {
            return first;
        }

        public void setFirst(String first) {
            this.first = first;
        }

        public String getSecond() {
            return second;
        }

        public void setSecond(String second) {
            this.second = second;
        }

        public String getThird() {
            return third;
        }

        public void setThird(String third) {
            this.third = third;
        }

        public String getFourth() {
            return fourth;
        }

        public void setFourth(String fourth) {
            this.fourth = fourth;
        }

        @Override
        public String toString() {
            return "CsvBindy{" +
                    "first='" + first + '\'' +
                    ", second='" + second + '\'' +
                    ", third='" + third + '\'' +
                    ", fourth='" + fourth + '\'' +
                    '}';
        }
    }
}

The relevant parts of the pom:

    <properties>
        <camel.version>2.16.2</camel.version>
    </properties>
    ...
    <build>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <version>2.5.1</version>
                <configuration>
                    <source>1.7</source>
                    <target>1.7</target>
                </configuration>
            </plugin>
        </plugins>
    </build>

    <dependencies>
        <dependency>
            <groupId>org.apache.camel</groupId>
            <artifactId>camel-core</artifactId>
            <version>${camel.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.camel</groupId>
            <artifactId>camel-bindy</artifactId>
            <version>${camel.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.camel</groupId>
            <artifactId>camel-jackson</artifactId>
            <version>${camel.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.camel</groupId>
            <artifactId>camel-test</artifactId>
            <version>${camel.version}</version>
            <scope>test</scope>
        </dependency>
        <dependency>
            <groupId>commons-lang</groupId>
            <artifactId>commons-lang</artifactId>
            <version>2.6</version>
        </dependency>
        <dependency>
            <groupId>commons-io</groupId>
            <artifactId>commons-io</artifactId>
            <version>2.4</version>
        </dependency>
        <dependency>
            <groupId>org.slf4j</groupId>
            <artifactId>slf4j-jdk14</artifactId>
            <version>1.7.21</version>
        </dependency>
    </dependencies>

Note that the tests write to the filesystem, defaulting to C:/tmp.

Issue Links

• links to: GitHub Pull Request #1038