[
https://issues.apache.org/jira/browse/HADOOP-17868?focusedWorklogId=642288&page=com.atlassian.jira.plugin.system.issuetabpanels:worklog-tabpanel#worklog-642288
]
ASF GitHub Bot logged work on HADOOP-17868:
-------------------------------------------
Author: ASF GitHub Bot
Created on: 26/Aug/21 11:56
Start Date: 26/Aug/21 11:56
Worklog Time Spent: 10m
Work Description: steveloughran commented on a change in pull request
#3336:
URL: https://github.com/apache/hadoop/pull/3336#discussion_r696555789
##########
File path:
hadoop-common-project/hadoop-common/src/test/java/org/apache/hadoop/io/compress/TestCodec.java
##########
@@ -725,6 +725,164 @@ public void testGzipCompatibility() throws IOException {
assertArrayEquals(b, dflchk);
}
+ @Test
+ public void testGzipCompatibilityWithCompressor() throws IOException {
+ // don't use native libs
+ ZlibFactory.setNativeZlibLoaded(false);
+ Configuration conf = new Configuration();
+ CompressionCodec codec = ReflectionUtils.newInstance(GzipCodec.class,
conf);
+
+ for (int i = 0; i < 100; i++){
+ Compressor compressor = codec.createCompressor();
+ assertEquals(BuiltInGzipCompressor.class, compressor.getClass());
+
+ Random r = new Random();
+ long seed = r.nextLong();
+ r.setSeed(seed);
+ LOG.info("seed: " + seed);
+
+ int inputSize = r.nextInt(256 * 1024 + 1);
+ byte[] b = new byte[inputSize];
+ r.nextBytes(b);
+
+ compressor.setInput(b,0, b.length);
+ compressor.finish();
+
+ byte[] output = new byte[inputSize + 1024];
+ int outputOff = 0;
+
+ while (!compressor.finished()) {
+ byte[] buf = new byte[r.nextInt(1024)];
+ int compressed = compressor.compress(buf, 0, buf.length);
+ System.arraycopy(buf, 0, output, outputOff, compressed);
+ outputOff += compressed;
+ }
+
+ DataInputBuffer gzbuf = new DataInputBuffer();
+ gzbuf.reset(output, outputOff);
+
+ Decompressor decom = codec.createDecompressor();
+ assertNotNull(decom);
+ assertEquals(BuiltInGzipDecompressor.class, decom.getClass());
+ InputStream gzin = codec.createInputStream(gzbuf, decom);
+
+ DataOutputBuffer dflbuf = new DataOutputBuffer();
+ dflbuf.reset();
+ IOUtils.copyBytes(gzin, dflbuf, 4096);
+ final byte[] dflchk = Arrays.copyOf(dflbuf.getData(),
dflbuf.getLength());
+ assertArrayEquals(b, dflchk);
+ }
+ }
+
+ @Test
+ public void testGzipCompatibilityWithCompressorAndGZIPOutputStream() throws
IOException {
+ // don't use native libs
+ ZlibFactory.setNativeZlibLoaded(false);
+ Configuration conf = new Configuration();
+ CompressionCodec codec = ReflectionUtils.newInstance(GzipCodec.class,
conf);
+
+ for (int i = 0; i < 100; i++){
+ Compressor compressor = codec.createCompressor();
+ assertEquals(BuiltInGzipCompressor.class, compressor.getClass());
+
+ Random r = new Random();
+ long seed = r.nextLong();
+ r.setSeed(seed);
+ LOG.info("seed: " + seed);
+
+ int inputSize = r.nextInt(256 * 1024 + 1);
+ byte[] b = new byte[inputSize];
+ r.nextBytes(b);
+
+ compressor.setInput(b,0, b.length);
+ compressor.finish();
+
+ byte[] output = new byte[inputSize + 1024];
+ int outputOff = 0;
+
+ while (!compressor.finished()) {
+ byte[] buf = new byte[r.nextInt(1024)];
+ int compressed = compressor.compress(buf, 0, buf.length);
+ System.arraycopy(buf, 0, output, outputOff, compressed);
+ outputOff += compressed;
+ }
+
+ DataOutputBuffer dflbuf = new DataOutputBuffer();
+ GZIPOutputStream gzout = new GZIPOutputStream(dflbuf);
+ gzout.write(b);
+ gzout.close();
+
+ final byte[] dflchk = Arrays.copyOf(dflbuf.getData(),
dflbuf.getLength());
+ LOG.info("output: " + outputOff);
+ LOG.info("dflchk: " + dflchk.length);
+
+ assertEquals(outputOff, dflchk.length);
+
+ uncompressGzipOutput(b, output, outputOff, codec);
+ uncompressGzipOutput(b, dflchk, dflchk.length, codec);
+ }
+ }
+
+ @Test
+ public void testGzipCompatibilityWithCompressorStreamAndGZIPOutputStream()
throws IOException {
+ // don't use native libs
+ ZlibFactory.setNativeZlibLoaded(false);
+ Configuration conf = new Configuration();
+ CompressionCodec codec = ReflectionUtils.newInstance(GzipCodec.class,
conf);
+
+ for (int i = 0; i < 100; i++){
+ Compressor compressor = codec.createCompressor();
+ DataOutputBuffer dflbuf = new DataOutputBuffer();
+ assertEquals(BuiltInGzipCompressor.class, compressor.getClass());
+ CompressionOutputStream compressionOutputStream =
codec.createOutputStream(dflbuf, compressor);
+
+ Random r = new Random();
+ long seed = r.nextLong();
+ r.setSeed(seed);
+ LOG.info("seed: " + seed);
Review comment:
nit, use `LOG.info("seed {}", seed)` here and the same elsewhere
##########
File path:
hadoop-common-project/hadoop-common/src/test/java/org/apache/hadoop/io/compress/TestCodec.java
##########
@@ -725,6 +725,164 @@ public void testGzipCompatibility() throws IOException {
assertArrayEquals(b, dflchk);
}
+ @Test
+ public void testGzipCompatibilityWithCompressor() throws IOException {
+ // don't use native libs
+ ZlibFactory.setNativeZlibLoaded(false);
+ Configuration conf = new Configuration();
+ CompressionCodec codec = ReflectionUtils.newInstance(GzipCodec.class,
conf);
+
+ for (int i = 0; i < 100; i++){
+ Compressor compressor = codec.createCompressor();
+ assertEquals(BuiltInGzipCompressor.class, compressor.getClass());
+
+ Random r = new Random();
+ long seed = r.nextLong();
+ r.setSeed(seed);
+ LOG.info("seed: " + seed);
+
+ int inputSize = r.nextInt(256 * 1024 + 1);
+ byte[] b = new byte[inputSize];
+ r.nextBytes(b);
+
+ compressor.setInput(b,0, b.length);
+ compressor.finish();
+
+ byte[] output = new byte[inputSize + 1024];
+ int outputOff = 0;
+
+ while (!compressor.finished()) {
+ byte[] buf = new byte[r.nextInt(1024)];
+ int compressed = compressor.compress(buf, 0, buf.length);
+ System.arraycopy(buf, 0, output, outputOff, compressed);
+ outputOff += compressed;
+ }
+
+ DataInputBuffer gzbuf = new DataInputBuffer();
+ gzbuf.reset(output, outputOff);
+
+ Decompressor decom = codec.createDecompressor();
+ assertNotNull(decom);
+ assertEquals(BuiltInGzipDecompressor.class, decom.getClass());
+ InputStream gzin = codec.createInputStream(gzbuf, decom);
+
+ DataOutputBuffer dflbuf = new DataOutputBuffer();
+ dflbuf.reset();
+ IOUtils.copyBytes(gzin, dflbuf, 4096);
+ final byte[] dflchk = Arrays.copyOf(dflbuf.getData(),
dflbuf.getLength());
+ assertArrayEquals(b, dflchk);
+ }
+ }
+
+ @Test
+ public void testGzipCompatibilityWithCompressorAndGZIPOutputStream() throws
IOException {
+ // don't use native libs
+ ZlibFactory.setNativeZlibLoaded(false);
+ Configuration conf = new Configuration();
+ CompressionCodec codec = ReflectionUtils.newInstance(GzipCodec.class,
conf);
+
+ for (int i = 0; i < 100; i++){
+ Compressor compressor = codec.createCompressor();
+ assertEquals(BuiltInGzipCompressor.class, compressor.getClass());
+
+ Random r = new Random();
+ long seed = r.nextLong();
+ r.setSeed(seed);
+ LOG.info("seed: " + seed);
+
+ int inputSize = r.nextInt(256 * 1024 + 1);
+ byte[] b = new byte[inputSize];
+ r.nextBytes(b);
+
+ compressor.setInput(b,0, b.length);
+ compressor.finish();
+
+ byte[] output = new byte[inputSize + 1024];
+ int outputOff = 0;
+
+ while (!compressor.finished()) {
+ byte[] buf = new byte[r.nextInt(1024)];
+ int compressed = compressor.compress(buf, 0, buf.length);
+ System.arraycopy(buf, 0, output, outputOff, compressed);
+ outputOff += compressed;
+ }
+
+ DataOutputBuffer dflbuf = new DataOutputBuffer();
+ GZIPOutputStream gzout = new GZIPOutputStream(dflbuf);
+ gzout.write(b);
+ gzout.close();
+
+ final byte[] dflchk = Arrays.copyOf(dflbuf.getData(),
dflbuf.getLength());
+ LOG.info("output: " + outputOff);
+ LOG.info("dflchk: " + dflchk.length);
+
+ assertEquals(outputOff, dflchk.length);
Review comment:
nit: add an error string in the assert
##########
File path:
hadoop-common-project/hadoop-common/src/test/java/org/apache/hadoop/io/compress/TestCodec.java
##########
@@ -725,6 +725,164 @@ public void testGzipCompatibility() throws IOException {
assertArrayEquals(b, dflchk);
}
+ @Test
+ public void testGzipCompatibilityWithCompressor() throws IOException {
+ // don't use native libs
+ ZlibFactory.setNativeZlibLoaded(false);
+ Configuration conf = new Configuration();
+ CompressionCodec codec = ReflectionUtils.newInstance(GzipCodec.class,
conf);
+
+ for (int i = 0; i < 100; i++){
+ Compressor compressor = codec.createCompressor();
+ assertEquals(BuiltInGzipCompressor.class, compressor.getClass());
+
+ Random r = new Random();
+ long seed = r.nextLong();
+ r.setSeed(seed);
+ LOG.info("seed: " + seed);
+
+ int inputSize = r.nextInt(256 * 1024 + 1);
+ byte[] b = new byte[inputSize];
+ r.nextBytes(b);
+
+ compressor.setInput(b,0, b.length);
+ compressor.finish();
+
+ byte[] output = new byte[inputSize + 1024];
+ int outputOff = 0;
+
+ while (!compressor.finished()) {
+ byte[] buf = new byte[r.nextInt(1024)];
+ int compressed = compressor.compress(buf, 0, buf.length);
+ System.arraycopy(buf, 0, output, outputOff, compressed);
+ outputOff += compressed;
+ }
+
+ DataInputBuffer gzbuf = new DataInputBuffer();
+ gzbuf.reset(output, outputOff);
+
+ Decompressor decom = codec.createDecompressor();
+ assertNotNull(decom);
+ assertEquals(BuiltInGzipDecompressor.class, decom.getClass());
+ InputStream gzin = codec.createInputStream(gzbuf, decom);
+
+ DataOutputBuffer dflbuf = new DataOutputBuffer();
+ dflbuf.reset();
+ IOUtils.copyBytes(gzin, dflbuf, 4096);
+ final byte[] dflchk = Arrays.copyOf(dflbuf.getData(),
dflbuf.getLength());
+ assertArrayEquals(b, dflchk);
+ }
+ }
+
+ @Test
+ public void testGzipCompatibilityWithCompressorAndGZIPOutputStream() throws
IOException {
+ // don't use native libs
+ ZlibFactory.setNativeZlibLoaded(false);
+ Configuration conf = new Configuration();
+ CompressionCodec codec = ReflectionUtils.newInstance(GzipCodec.class,
conf);
+
+ for (int i = 0; i < 100; i++){
+ Compressor compressor = codec.createCompressor();
+ assertEquals(BuiltInGzipCompressor.class, compressor.getClass());
+
+ Random r = new Random();
+ long seed = r.nextLong();
+ r.setSeed(seed);
+ LOG.info("seed: " + seed);
+
+ int inputSize = r.nextInt(256 * 1024 + 1);
+ byte[] b = new byte[inputSize];
+ r.nextBytes(b);
+
+ compressor.setInput(b,0, b.length);
+ compressor.finish();
+
+ byte[] output = new byte[inputSize + 1024];
+ int outputOff = 0;
+
+ while (!compressor.finished()) {
+ byte[] buf = new byte[r.nextInt(1024)];
+ int compressed = compressor.compress(buf, 0, buf.length);
+ System.arraycopy(buf, 0, output, outputOff, compressed);
+ outputOff += compressed;
+ }
+
+ DataOutputBuffer dflbuf = new DataOutputBuffer();
+ GZIPOutputStream gzout = new GZIPOutputStream(dflbuf);
Review comment:
nit: use try-with-resources so the streams are automatically/always
closed
##########
File path:
hadoop-common-project/hadoop-common/src/test/java/org/apache/hadoop/io/compress/TestCodec.java
##########
@@ -725,6 +725,164 @@ public void testGzipCompatibility() throws IOException {
assertArrayEquals(b, dflchk);
}
+ @Test
+ public void testGzipCompatibilityWithCompressor() throws IOException {
+ // don't use native libs
+ ZlibFactory.setNativeZlibLoaded(false);
+ Configuration conf = new Configuration();
+ CompressionCodec codec = ReflectionUtils.newInstance(GzipCodec.class,
conf);
+
+ for (int i = 0; i < 100; i++){
+ Compressor compressor = codec.createCompressor();
+ assertEquals(BuiltInGzipCompressor.class, compressor.getClass());
+
+ Random r = new Random();
+ long seed = r.nextLong();
+ r.setSeed(seed);
+ LOG.info("seed: " + seed);
+
+ int inputSize = r.nextInt(256 * 1024 + 1);
+ byte[] b = new byte[inputSize];
+ r.nextBytes(b);
+
+ compressor.setInput(b,0, b.length);
+ compressor.finish();
+
+ byte[] output = new byte[inputSize + 1024];
+ int outputOff = 0;
+
+ while (!compressor.finished()) {
+ byte[] buf = new byte[r.nextInt(1024)];
+ int compressed = compressor.compress(buf, 0, buf.length);
+ System.arraycopy(buf, 0, output, outputOff, compressed);
+ outputOff += compressed;
+ }
+
+ DataInputBuffer gzbuf = new DataInputBuffer();
+ gzbuf.reset(output, outputOff);
+
+ Decompressor decom = codec.createDecompressor();
+ assertNotNull(decom);
+ assertEquals(BuiltInGzipDecompressor.class, decom.getClass());
+ InputStream gzin = codec.createInputStream(gzbuf, decom);
+
+ DataOutputBuffer dflbuf = new DataOutputBuffer();
+ dflbuf.reset();
+ IOUtils.copyBytes(gzin, dflbuf, 4096);
+ final byte[] dflchk = Arrays.copyOf(dflbuf.getData(),
dflbuf.getLength());
+ assertArrayEquals(b, dflchk);
+ }
+ }
+
+ @Test
+ public void testGzipCompatibilityWithCompressorAndGZIPOutputStream() throws
IOException {
+ // don't use native libs
+ ZlibFactory.setNativeZlibLoaded(false);
+ Configuration conf = new Configuration();
+ CompressionCodec codec = ReflectionUtils.newInstance(GzipCodec.class,
conf);
+
+ for (int i = 0; i < 100; i++){
+ Compressor compressor = codec.createCompressor();
+ assertEquals(BuiltInGzipCompressor.class, compressor.getClass());
+
+ Random r = new Random();
+ long seed = r.nextLong();
+ r.setSeed(seed);
+ LOG.info("seed: " + seed);
+
+ int inputSize = r.nextInt(256 * 1024 + 1);
+ byte[] b = new byte[inputSize];
+ r.nextBytes(b);
+
+ compressor.setInput(b,0, b.length);
+ compressor.finish();
+
+ byte[] output = new byte[inputSize + 1024];
+ int outputOff = 0;
+
+ while (!compressor.finished()) {
+ byte[] buf = new byte[r.nextInt(1024)];
+ int compressed = compressor.compress(buf, 0, buf.length);
+ System.arraycopy(buf, 0, output, outputOff, compressed);
+ outputOff += compressed;
+ }
+
+ DataOutputBuffer dflbuf = new DataOutputBuffer();
+ GZIPOutputStream gzout = new GZIPOutputStream(dflbuf);
+ gzout.write(b);
+ gzout.close();
+
+ final byte[] dflchk = Arrays.copyOf(dflbuf.getData(),
dflbuf.getLength());
+ LOG.info("output: " + outputOff);
+ LOG.info("dflchk: " + dflchk.length);
+
+ assertEquals(outputOff, dflchk.length);
+
+ uncompressGzipOutput(b, output, outputOff, codec);
+ uncompressGzipOutput(b, dflchk, dflchk.length, codec);
+ }
+ }
+
+ @Test
+ public void testGzipCompatibilityWithCompressorStreamAndGZIPOutputStream()
throws IOException {
+ // don't use native libs
+ ZlibFactory.setNativeZlibLoaded(false);
+ Configuration conf = new Configuration();
+ CompressionCodec codec = ReflectionUtils.newInstance(GzipCodec.class,
conf);
+
+ for (int i = 0; i < 100; i++){
+ Compressor compressor = codec.createCompressor();
+ DataOutputBuffer dflbuf = new DataOutputBuffer();
+ assertEquals(BuiltInGzipCompressor.class, compressor.getClass());
+ CompressionOutputStream compressionOutputStream =
codec.createOutputStream(dflbuf, compressor);
+
+ Random r = new Random();
+ long seed = r.nextLong();
+ r.setSeed(seed);
+ LOG.info("seed: " + seed);
+
+ int inputSize = r.nextInt(256 * 1024 + 1);
+ byte[] b = new byte[inputSize];
+ r.nextBytes(b);
+
+ compressionOutputStream.write(b);
+ compressionOutputStream.close();
+
+ final byte[] output = Arrays.copyOf(dflbuf.getData(),
dflbuf.getLength());
+ dflbuf.reset();
+
+ GZIPOutputStream gzout = new GZIPOutputStream(dflbuf);
+ gzout.write(b);
+ gzout.close();
+
+ final byte[] dflchk = Arrays.copyOf(dflbuf.getData(),
dflbuf.getLength());
+ LOG.info("output: " + output.length);
+ LOG.info("dflchk: " + dflchk.length);
+
+ assertEquals(output.length, dflchk.length);
+
+ uncompressGzipOutput(b, output, output.length, codec);
+ uncompressGzipOutput(b, dflchk, dflchk.length, codec);
+ }
+ }
+
+ private void uncompressGzipOutput(
+ byte[] origin, byte[] output, int outputLen, CompressionCodec codec)
throws IOException {
+ DataInputBuffer gzbuf = new DataInputBuffer();
+ gzbuf.reset(output, outputLen);
+
+ Decompressor decom = codec.createDecompressor();
+ assertNotNull(decom);
Review comment:
+exception text here and below. Ideally, use AssertJ assertions for new
tests
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
Issue Time Tracking
-------------------
Worklog Id: (was: 642288)
Time Spent: 40m (was: 0.5h)
> Add more test for the BuiltInGzipCompressor
> -------------------------------------------
>
> Key: HADOOP-17868
> URL: https://issues.apache.org/jira/browse/HADOOP-17868
> Project: Hadoop Common
> Issue Type: Test
> Reporter: L. C. Hsieh
> Priority: Major
> Labels: pull-request-available
> Time Spent: 40m
> Remaining Estimate: 0h
>
> We added BuiltInGzipCompressor recently. It is better to add more
> compatibility tests for the compressor.
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
