Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fix CSV parsing to handle nested comma delimiter inside quotes by using Apache Commons CSV. #200

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Fix CSV parsing to handle nested comma delimiter inside quotes by using Apache Commons CSV. #200

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 7 additions & 2 deletions pom.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -65,18 +65,23 @@
<dependency>
<groupId>com.fasterxml.jackson.core</groupId>
<artifactId>jackson-annotations</artifactId>
<version>2.8.11</version>
<version>2.9.10</version>
</dependency>
<dependency>
<groupId>com.fasterxml.jackson.core</groupId>
<artifactId>jackson-core</artifactId>
<version>2.8.11</version>
<version>2.9.10</version>
</dependency>
<dependency>
<groupId>com.fasterxml.jackson.core</groupId>
<artifactId>jackson-databind</artifactId>
<version>2.9.10.3</version>
</dependency>
<dependency>
<groupId>org.apache.commons</groupId>
<artifactId>commons-csv</artifactId>
<version>1.8</version>
</dependency>
<dependency>
<groupId>com.google.code.findbugs</groupId>
<artifactId>jsr305</artifactId>
Expand Down
41 changes: 28 additions & 13 deletions src/com/amazon/kinesis/streaming/agent/processing/processors/CSVToJSONDataConverter.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,12 +13,17 @@
*/
package com.amazon.kinesis.streaming.agent.processing.processors;

import java.io.IOException;
import java.io.StringReader;
import java.nio.ByteBuffer;
import java.nio.charset.StandardCharsets;
import java.util.LinkedHashMap;
import java.util.List;
import java.util.Map;

import org.apache.commons.csv.CSVFormat;
import org.apache.commons.csv.CSVParser;
import org.apache.commons.csv.CSVRecord;
import org.slf4j.LoggerFactory;

import com.amazon.kinesis.streaming.agent.ByteBuffers;
Expand Down Expand Up @@ -69,19 +74,29 @@ public ByteBuffer convert(ByteBuffer data) throws DataConversionException {
dataStr = dataStr.substring(0, (dataStr.length() - NEW_LINE.length()));
}

String[] columns = dataStr.split(delimiter);

for (int i = 0; i < fieldNames.size(); i++) {
try {
recordMap.put(fieldNames.get(i), columns[i]);
} catch (ArrayIndexOutOfBoundsException e) {
LoggerFactory.getLogger(getClass()).debug("Null field in CSV detected");
recordMap.put(fieldNames.get(i), null);
} catch (Exception e) {
throw new DataConversionException("Unable to create the column map", e);
}
}

CSVParser csvParser = null;
try {
if (delimiter.equals(",")) {
csvParser = CSVFormat.RFC4180.parse(new StringReader(dataStr));
} else {
csvParser = CSVFormat.TDF.withIgnoreSurroundingSpaces(false).parse(new StringReader(dataStr));
Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

delimiter is ignored in this case

}
CSVRecord csvRecord = csvParser.getRecords().get(0);

for (int i = 0; i < fieldNames.size(); i++) {
try {
recordMap.put(fieldNames.get(i), csvRecord.get(i));
} catch (ArrayIndexOutOfBoundsException e) {
LoggerFactory.getLogger(getClass()).debug("Null field in CSV detected");
recordMap.put(fieldNames.get(i), null);
} catch (Exception e) {
throw new DataConversionException("Unable to create the column map", e);
}
}
} catch (IOException e) {
throw new DataConversionException("Unable to parse the CSV records.", e);
}

String dataJson = jsonProducer.writeAsString(recordMap) + NEW_LINE;

return ByteBuffer.wrap(dataJson.getBytes(StandardCharsets.UTF_8));
Expand Down
8 changes: 6 additions & 2 deletions tst/com/amazon/kinesis/streaming/agent/processing/processors/DataConverterTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -54,7 +54,7 @@ public void testCSVToJSONDataConverter() throws Exception {
put("customFieldNames", Arrays.asList("column1", "column2", "column3", "column4"));
}});
final IDataConverter converter = new CSVToJSONDataConverter(config);
final String dataStr = "value1, value2,valu\ne3, value4\n";
final String dataStr = "value1, value2,\"valu\ne3\", value4\n";
final String expectedStr = "{\"column1\":\"value1\",\"column2\":\" value2\",\"column3\":\"valu\\ne3\",\"column4\":\" value4\"}\n";
verifyDataConversion(converter, dataStr.getBytes(), expectedStr.getBytes());

Expand All @@ -64,7 +64,11 @@ public void testCSVToJSONDataConverter() throws Exception {

final String dataStrMoreThanColumns = "value1,value2,value3,value4,value5\n";
final String expectedStrMoreThanColumns = "{\"column1\":\"value1\",\"column2\":\"value2\",\"column3\":\"value3\",\"column4\":\"value4\"}\n";
verifyDataConversion(converter, dataStrMoreThanColumns.getBytes(), expectedStrMoreThanColumns.getBytes());
verifyDataConversion(converter, dataStrMoreThanColumns.getBytes(), expectedStrMoreThanColumns.getBytes());

final String dataStrEmbeddedComma = "value1,\"val,ue2\",value3,value4\n";
final String expectedStrEmbeddedComma = "{\"column1\":\"value1\",\"column2\":\"val,ue2\",\"column3\":\"value3\",\"column4\":\"value4\"}\n";
verifyDataConversion(converter, dataStrEmbeddedComma.getBytes(), expectedStrEmbeddedComma.getBytes());
}

@SuppressWarnings("serial")
Expand Down