You are viewing a plain text version of this content. The canonical link for it is here.
Posted to common-issues@hadoop.apache.org by GitBox <gi...@apache.org> on 2021/08/30 18:19:14 UTC
[GitHub] [hadoop] sunchao commented on a change in pull request #3336: HADOOP-17868. Add more tests for BuiltInGzipCompressor
sunchao commented on a change in pull request #3336:
URL: https://github.com/apache/hadoop/pull/3336#discussion_r698693663
##########
File path: hadoop-common-project/hadoop-common/src/test/java/org/apache/hadoop/io/compress/TestCodec.java
##########
@@ -725,6 +726,173 @@ 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();
+ assertThat(compressor).withFailMessage("should be BuiltInGzipCompressor")
+ .isInstanceOf(BuiltInGzipCompressor.class);
+
+ 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();
+ assertThat(decom).as("decompressor should not be null").isNotNull();
+ assertThat(decom).withFailMessage("should be BuiltInGzipDecompressor")
+ .isInstanceOf(BuiltInGzipDecompressor.class);
+ try (InputStream gzin = codec.createInputStream(gzbuf, decom);) {
Review comment:
nit: extra `;` at the end
##########
File path: hadoop-common-project/hadoop-common/src/test/java/org/apache/hadoop/io/compress/TestCodec.java
##########
@@ -725,6 +726,173 @@ 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();
+ assertThat(compressor).withFailMessage("should be BuiltInGzipCompressor")
+ .isInstanceOf(BuiltInGzipCompressor.class);
+
+ 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();
+ assertThat(decom).as("decompressor should not be null").isNotNull();
+ assertThat(decom).withFailMessage("should be BuiltInGzipDecompressor")
+ .isInstanceOf(BuiltInGzipDecompressor.class);
+ try (InputStream gzin = codec.createInputStream(gzbuf, decom);) {
+
Review comment:
nit: remove extra line
##########
File path: hadoop-common-project/hadoop-common/src/test/java/org/apache/hadoop/io/compress/TestCodec.java
##########
@@ -725,6 +726,173 @@ 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();
+ assertThat(compressor).withFailMessage("should be BuiltInGzipCompressor")
+ .isInstanceOf(BuiltInGzipCompressor.class);
+
+ 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);
Review comment:
nit: spaces
##########
File path: hadoop-common-project/hadoop-common/src/test/java/org/apache/hadoop/io/compress/TestCodec.java
##########
@@ -725,6 +726,173 @@ 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();
+ assertThat(compressor).withFailMessage("should be BuiltInGzipCompressor")
+ .isInstanceOf(BuiltInGzipCompressor.class);
+
+ 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();
+ assertThat(decom).as("decompressor should not be null").isNotNull();
+ assertThat(decom).withFailMessage("should be BuiltInGzipDecompressor")
+ .isInstanceOf(BuiltInGzipDecompressor.class);
+ try (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());
+ assertThat(b).as("check decompressed output").isEqualTo(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();
+ assertThat(compressor).withFailMessage("should be BuiltInGzipCompressor")
+ .isInstanceOf(BuiltInGzipCompressor.class);
+
+ 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;
+ }
+
+ try (DataOutputBuffer dflbuf = new DataOutputBuffer();
+ GZIPOutputStream gzout = new GZIPOutputStream(dflbuf);) {
Review comment:
nit: extra `;` at the end
##########
File path: hadoop-common-project/hadoop-common/src/test/java/org/apache/hadoop/io/compress/TestCodec.java
##########
@@ -725,6 +726,173 @@ 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();
+ assertThat(compressor).withFailMessage("should be BuiltInGzipCompressor")
+ .isInstanceOf(BuiltInGzipCompressor.class);
+
+ 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();
+ assertThat(decom).as("decompressor should not be null").isNotNull();
+ assertThat(decom).withFailMessage("should be BuiltInGzipDecompressor")
+ .isInstanceOf(BuiltInGzipDecompressor.class);
+ try (InputStream gzin = codec.createInputStream(gzbuf, decom);) {
+
+ DataOutputBuffer dflbuf = new DataOutputBuffer();
Review comment:
nit: put this into the try block too? since it is also a resource that should be closed with a finally block
##########
File path: hadoop-common-project/hadoop-common/src/test/java/org/apache/hadoop/io/compress/TestCodec.java
##########
@@ -725,6 +726,173 @@ 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();
+ assertThat(compressor).withFailMessage("should be BuiltInGzipCompressor")
+ .isInstanceOf(BuiltInGzipCompressor.class);
+
+ 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();
+ assertThat(decom).as("decompressor should not be null").isNotNull();
+ assertThat(decom).withFailMessage("should be BuiltInGzipDecompressor")
+ .isInstanceOf(BuiltInGzipDecompressor.class);
+ try (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());
+ assertThat(b).as("check decompressed output").isEqualTo(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++){
Review comment:
can we share this code across the 3 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: common-issues-unsubscribe@hadoop.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: common-issues-unsubscribe@hadoop.apache.org
For additional commands, e-mail: common-issues-help@hadoop.apache.org