Github user olegz commented on a diff in the pull request:
https://github.com/apache/nifi/pull/1214#discussion_r102830048
--- Diff:
nifi-commons/nifi-utils/src/main/java/org/apache/nifi/stream/io/util/AbstractDemarcator.java
---
@@ -0,0 +1,138 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.nifi.stream.io.util;
+
+import java.io.Closeable;
+import java.io.IOException;
+import java.io.InputStream;
+
+import org.apache.nifi.stream.io.exception.TokenTooLargeException;
+
+/**
+ * Base class for implementing streaming demarcators.
+ * <p>
+ * NOTE: Not intended for multi-thread usage hence not Thread-safe.
+ * </p>
+ */
+abstract class AbstractDemarcator implements Closeable {
+
+ final static int INIT_BUFFER_SIZE = 8192;
+
+ private final InputStream is;
+
+ private final int initialBufferSize;
+
+ private final int maxDataSize;
+
+ byte[] buffer;
+
+ int index;
+
+ int mark;
+
+ long offset;
+
+ int bufferLength;
+
+ /**
+ * Constructs an instance of demarcator with provided {@link
InputStream}
+ * and max buffer size. Each demarcated token must fit within max
buffer
+ * size, otherwise the exception will be raised.
+ */
+ AbstractDemarcator(InputStream is, int maxDataSize) {
+ this(is, maxDataSize, INIT_BUFFER_SIZE);
+ }
+
+ /**
+ * Constructs an instance of demarcator with provided {@link
InputStream}
+ * and max buffer size and initial buffer size. Each demarcated token
must
+ * fit within max buffer size, otherwise the exception will be raised.
+ */
+ AbstractDemarcator(InputStream is, int maxDataSize, int
initialBufferSize) {
+ this.validate(is, maxDataSize, initialBufferSize);
+ this.is = is;
+ this.initialBufferSize = initialBufferSize;
+ this.buffer = new byte[initialBufferSize];
+ this.maxDataSize = maxDataSize;
+ }
+
+ @Override
+ public void close() throws IOException {
+ // noop
+ }
+
+ /**
+ * Will fill the current buffer from current 'index' position,
expanding it
+ * and or shuffling it if necessary. If buffer exceeds max buffer size
a
+ * {@link TokenTooLargeException} will be thrown.
+ *
+ * @throws IOException
+ * if unable to read from the stream
+ */
+ void fill() throws IOException {
+ if (this.index >= this.buffer.length) {
+ if (this.mark == 0) { // expand
+ byte[] newBuff = new byte[this.buffer.length +
this.initialBufferSize];
+ System.arraycopy(this.buffer, 0, newBuff, 0,
this.buffer.length);
+ this.buffer = newBuff;
+ } else { // shuffle
+ int length = this.index - this.mark;
+ System.arraycopy(this.buffer, this.mark, this.buffer, 0,
length);
+ this.index = length;
+ this.mark = 0;
+ }
+ }
+
+ int bytesRead;
+ do {
+ bytesRead = this.is.read(this.buffer, this.index,
this.buffer.length - this.index);
--- End diff --
Good point @mosermw . Mark and I did discuss it earlier and the I kept the
code as is for exactly that reason. I did add an inline comment to explain the
do/while loop.
---
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.
---
