Github user markobean commented on a diff in the pull request:
https://github.com/apache/nifi/pull/444#discussion_r65467195
--- Diff:
nifi-nar-bundles/nifi-standard-bundle/nifi-standard-processors/src/main/java/org/apache/nifi/processors/standard/SplitText.java
---
@@ -147,138 +193,200 @@ protected void init(final
ProcessorInitializationContext context) {
return properties;
}
- private int readLines(final InputStream in, final int maxNumLines,
final OutputStream out, final boolean keepAllNewLines, final byte[]
leadingNewLineBytes) throws IOException {
+ private int readLines(final InputStream in, final int maxNumLines,
final long maxByteCount, final OutputStream out,
+ final boolean includeLineDelimiter, final byte[]
leadingNewLineBytes) throws IOException {
final EndOfLineBuffer eolBuffer = new EndOfLineBuffer();
- int numLines = 0;
byte[] leadingBytes = leadingNewLineBytes;
+ int numLines = 0;
+ long totalBytes = 0L;
for (int i = 0; i < maxNumLines; i++) {
- final EndOfLineMarker eolMarker = locateEndOfLine(in, out,
false, eolBuffer, leadingBytes);
+ final EndOfLineMarker eolMarker = countBytesToSplitPoint(in,
out, totalBytes, maxByteCount, includeLineDelimiter, eolBuffer, leadingBytes);
+ final long bytes = eolMarker.getBytesConsumed();
leadingBytes = eolMarker.getLeadingNewLineBytes();
- if (keepAllNewLines && out != null) {
+ if (includeLineDelimiter && out != null) {
if (leadingBytes != null) {
out.write(leadingBytes);
leadingBytes = null;
}
-
eolBuffer.drainTo(out);
}
-
- if (eolBuffer.length() > 0 || eolMarker.getBytesConsumed() >
0L) {
- numLines++;
+ totalBytes += bytes;
+ if (bytes <= 0) {
+ return numLines;
}
-
- if (eolMarker.isStreamEnded()) {
+ numLines++;
+ if (totalBytes >= maxByteCount) {
break;
}
}
-
return numLines;
}
- private EndOfLineMarker locateEndOfLine(final InputStream in, final
OutputStream out, final boolean includeLineDelimiter,
- final EndOfLineBuffer eolBuffer, final byte[] leadingNewLineBytes)
throws IOException {
-
+ private EndOfLineMarker countBytesToSplitPoint(final InputStream in,
final OutputStream out, final long bytesReadSoFar, final long maxSize,
+ final boolean
includeLineDelimiter, final EndOfLineBuffer eolBuffer, final byte[]
leadingNewLineBytes) throws IOException {
int lastByte = -1;
--- End diff --
removed lastByte variable
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
