dajac commented on a change in pull request #11456:
URL: https://github.com/apache/kafka/pull/11456#discussion_r763055170
##########
File path: core/src/main/scala/kafka/tools/ConsoleProducer.scala
##########
@@ -264,38 +282,113 @@ object ConsoleProducer {
var reader: BufferedReader = null
var parseKey = false
var keySeparator = "\t"
+ var parseHeader = false
+ var headersDelimiter = "\t"
+ var headersSeparator = ","
+ var headerKeySeparator = ":"
var ignoreError = false
var lineNumber = 0
var printPrompt = System.console != null
+ var headerSeparatorPattern: Pattern = _
+ var headerKeySeparatorPattern: Pattern = _
override def init(inputStream: InputStream, props: Properties): Unit = {
topic = props.getProperty("topic")
if (props.containsKey("parse.key"))
parseKey = props.getProperty("parse.key").trim.equalsIgnoreCase("true")
if (props.containsKey("key.separator"))
keySeparator = props.getProperty("key.separator")
+ if (props.containsKey("parse.headers"))
+ parseHeader =
props.getProperty("parse.headers").trim.equalsIgnoreCase("true")
+ if (props.containsKey("headers.delimiter"))
+ headersDelimiter = props.getProperty("headers.delimiter")
+ if (props.containsKey("headers.separator"))
+ headersSeparator = props.getProperty("headers.separator")
+ headerSeparatorPattern = Pattern.compile(headersSeparator)
+ if (props.containsKey("headers.key.separator"))
+ headerKeySeparator = props.getProperty("headers.key.separator")
+ headerKeySeparatorPattern = Pattern.compile(headerKeySeparator)
if (props.containsKey("ignore.error"))
ignoreError =
props.getProperty("ignore.error").trim.equalsIgnoreCase("true")
reader = new BufferedReader(new InputStreamReader(inputStream,
StandardCharsets.UTF_8))
}
- override def readMessage() = {
+ override def readMessage(): ProducerRecord[Array[Byte],Array[Byte]] = {
lineNumber += 1
- if (printPrompt)
- print(">")
- (reader.readLine(), parseKey) match {
- case (null, _) => null
- case (line, true) =>
- line.indexOf(keySeparator) match {
- case -1 =>
- if (ignoreError) new ProducerRecord(topic,
line.getBytes(StandardCharsets.UTF_8))
- else throw new KafkaException(s"No key found on line
$lineNumber: $line")
- case n =>
- val value = (if (n + keySeparator.size > line.size) "" else
line.substring(n + keySeparator.size)).getBytes(StandardCharsets.UTF_8)
- new ProducerRecord(topic, line.substring(0,
n).getBytes(StandardCharsets.UTF_8), value)
- }
- case (line, false) =>
- new ProducerRecord(topic, line.getBytes(StandardCharsets.UTF_8))
+ if (printPrompt) print(">")
+ val line = reader.readLine()
+ try{
+ (line, parseKey, parseHeader) match {
+ case (null, _, _) => null
+ case (line, true, true) => parseHeaderKeyValue(line)
+ case (line, true, false) => parseKeyValue(line)
+ case (line, false, true) => parseHeaderValue(line)
+ case (line, false, false) => parseValue(line)
+ }
+ } catch {
+ case _: Throwable => onMatchError(line)
+ }
+ }
+
+ private def parseHeaderKeyValue(line: String):
ProducerRecord[Array[Byte],Array[Byte]] = {
+ val headerIndex = line.indexOf(headersDelimiter)
Review comment:
It seems that the whole parsing is less robust than it was before? What
would happen if the delimiter is not found? I think that `indexOf` returns `-1`
in this case. I suppose that an exception is thrown and caught in
`readMessage`. Am I getting this right?
I wonder if it would be better to be explicit instead. This would also give
use the opportunity to provide more precise errors to the user. What do you
think?
##########
File path: core/src/main/scala/kafka/tools/ConsoleProducer.scala
##########
@@ -264,38 +282,113 @@ object ConsoleProducer {
var reader: BufferedReader = null
var parseKey = false
var keySeparator = "\t"
+ var parseHeader = false
+ var headersDelimiter = "\t"
+ var headersSeparator = ","
+ var headerKeySeparator = ":"
var ignoreError = false
var lineNumber = 0
var printPrompt = System.console != null
+ var headerSeparatorPattern: Pattern = _
+ var headerKeySeparatorPattern: Pattern = _
override def init(inputStream: InputStream, props: Properties): Unit = {
topic = props.getProperty("topic")
if (props.containsKey("parse.key"))
parseKey = props.getProperty("parse.key").trim.equalsIgnoreCase("true")
if (props.containsKey("key.separator"))
keySeparator = props.getProperty("key.separator")
+ if (props.containsKey("parse.headers"))
+ parseHeader =
props.getProperty("parse.headers").trim.equalsIgnoreCase("true")
+ if (props.containsKey("headers.delimiter"))
+ headersDelimiter = props.getProperty("headers.delimiter")
+ if (props.containsKey("headers.separator"))
+ headersSeparator = props.getProperty("headers.separator")
+ headerSeparatorPattern = Pattern.compile(headersSeparator)
+ if (props.containsKey("headers.key.separator"))
+ headerKeySeparator = props.getProperty("headers.key.separator")
+ headerKeySeparatorPattern = Pattern.compile(headerKeySeparator)
if (props.containsKey("ignore.error"))
ignoreError =
props.getProperty("ignore.error").trim.equalsIgnoreCase("true")
reader = new BufferedReader(new InputStreamReader(inputStream,
StandardCharsets.UTF_8))
}
- override def readMessage() = {
+ override def readMessage(): ProducerRecord[Array[Byte],Array[Byte]] = {
lineNumber += 1
- if (printPrompt)
- print(">")
- (reader.readLine(), parseKey) match {
- case (null, _) => null
- case (line, true) =>
- line.indexOf(keySeparator) match {
- case -1 =>
- if (ignoreError) new ProducerRecord(topic,
line.getBytes(StandardCharsets.UTF_8))
- else throw new KafkaException(s"No key found on line
$lineNumber: $line")
- case n =>
- val value = (if (n + keySeparator.size > line.size) "" else
line.substring(n + keySeparator.size)).getBytes(StandardCharsets.UTF_8)
- new ProducerRecord(topic, line.substring(0,
n).getBytes(StandardCharsets.UTF_8), value)
- }
- case (line, false) =>
- new ProducerRecord(topic, line.getBytes(StandardCharsets.UTF_8))
+ if (printPrompt) print(">")
+ val line = reader.readLine()
+ try{
+ (line, parseKey, parseHeader) match {
+ case (null, _, _) => null
+ case (line, true, true) => parseHeaderKeyValue(line)
+ case (line, true, false) => parseKeyValue(line)
+ case (line, false, true) => parseHeaderValue(line)
+ case (line, false, false) => parseValue(line)
Review comment:
Instead of doing this, did you consider have one method? We know that we
always have the headers, then the key, and finally the value so we could just
skip some part based on the selected options.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: jira-unsubscr...@kafka.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
