This is an automated email from the ASF dual-hosted git repository.
ggregory pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/commons-compress.git
commit 1ede093532a13562f751837f27d2f84d57a40c37
Author: Gary D. Gregory <garydgreg...@gmail.com>
AuthorDate: Tue Aug 19 07:37:36 2025 -0400
Add org.apache.commons.compress.archivers.tar.TarArchiveInputStream.Builder
- Add
org.apache.commons.compress.archivers.tar.TarArchiveInputStream.builder()
---
src/changes/changes.xml | 2 +
.../archivers/tar/TarArchiveInputStream.java | 94 ++++++++++++++++++++++
.../archivers/tar/TarArchiveInputStreamTest.java | 60 +++++++++++++-
3 files changed, 152 insertions(+), 4 deletions(-)
diff --git a/src/changes/changes.xml b/src/changes/changes.xml
index b69ccf1c0..bae92e27a 100644
--- a/src/changes/changes.xml
+++ b/src/changes/changes.xml
@@ -113,6 +113,8 @@ The <action> type attribute can be add,update,fix,remove.
<action type="add" issue="COMPRESS-705" dev="ggregory" due-to="Gary
Gregory">Add
org.apache.commons.compress.compressors.gzip.GzipCompressorInputStream.Builder.setIgnoreExtraField(boolean).</action>
<action type="add" dev="ggregory" due-to="Gary Gregory">Add
org.apache.commons.compress.compressors.snappy.SnappyCompressorInputStream.getUncompressedSize()
and deprecate getSize().</action>
<action type="add" dev="ggregory" due-to="Gary Gregory">Add
org.apache.commons.compress.archivers.ArchiveInputStream.ArchiveInputStream(InputStream,
Charset) as a public constructor, it was private.</action>
+ <action type="add" dev="ggregory" due-to="Gary Gregory">Add
org.apache.commons.compress.archivers.tar.TarArchiveInputStream.builder().</action>
+ <action type="add" dev="ggregory" due-to="Gary Gregory">Add
org.apache.commons.compress.archivers.tar.TarArchiveInputStream.Builder.</action>
<!-- UPDATE -->
</release>
<release version="1.28.0" date="2025-07-26" description="This is a feature
and maintenance release. Java 8 or later is required.">
diff --git
a/src/main/java/org/apache/commons/compress/archivers/tar/TarArchiveInputStream.java
b/src/main/java/org/apache/commons/compress/archivers/tar/TarArchiveInputStream.java
index d0f7d471c..65d2fc71e 100644
---
a/src/main/java/org/apache/commons/compress/archivers/tar/TarArchiveInputStream.java
+++
b/src/main/java/org/apache/commons/compress/archivers/tar/TarArchiveInputStream.java
@@ -39,8 +39,10 @@
import org.apache.commons.compress.archivers.ArchiveInputStream;
import org.apache.commons.compress.archivers.zip.ZipEncoding;
import org.apache.commons.compress.archivers.zip.ZipEncodingHelper;
+import org.apache.commons.compress.compressors.gzip.GzipCompressorInputStream;
import org.apache.commons.compress.utils.ArchiveUtils;
import org.apache.commons.compress.utils.IOUtils;
+import org.apache.commons.io.build.AbstractStreamBuilder;
import org.apache.commons.io.input.BoundedInputStream;
/**
@@ -51,6 +53,79 @@
*/
public class TarArchiveInputStream extends ArchiveInputStream<TarArchiveEntry>
{
+ // @formatter:off
+ /**
+ * Builds a new {@link GzipCompressorInputStream}.
+ *
+ * <p>
+ * For example:
+ * </p>
+ * <pre>{@code
+ * TarArchiveInputStream s = TarArchiveInputStream.builder()
+ * .setPath(path)
+ * .setLenient(true)
+ * .setFileNameCharset(StandardCharsets.UTF_8)
+ * .get();}
+ * </pre>
+ *
+ * @see #get()
+ * @since 1.29.0
+ */
+ // @formatter:on
+ public static class Builder extends
AbstractStreamBuilder<TarArchiveInputStream, Builder> {
+
+ private int blockSize = TarConstants.DEFAULT_BLKSIZE;
+ private int recordSize = TarConstants.DEFAULT_RCDSIZE;
+ private boolean lenient;
+
+ /**
+ * Constructs a new instance.
+ */
+ public Builder() {
+ // empty
+ }
+
+ @Override
+ public TarArchiveInputStream get() throws IOException {
+ return new TarArchiveInputStream(this);
+ }
+
+ /**
+ * Sets the block size.
+ *
+ * @param blockSize the block size.
+ * @return {@code this} instance.
+ */
+ public Builder setBlockSize(final int blockSize) {
+ this.blockSize = blockSize;
+ return this;
+ }
+
+ /**
+ * Set whether illegal values for group/userid, mode, device numbers
and timestamp will be ignored and the fields set to
+ * {@link TarArchiveEntry#UNKNOWN}. When set to false such illegal
fields cause an exception instead.
+ *
+ * @param lenient whether illegal values throw exceptions.
+ * @return {@code this} instance.
+ */
+ public Builder setLenient(final boolean lenient) {
+ this.lenient = lenient;
+ return this;
+ }
+
+ /**
+ * Sets the record size.
+ *
+ * @param recordSize the record size.
+ * @return {@code this} instance.
+ */
+ public Builder setRecordSize(final int recordSize) {
+ this.recordSize = recordSize;
+ return this;
+ }
+
+ }
+
/**
* IBM AIX <a
href=""https://www.ibm.com/docs/sv/aix/7.2.0?topic=files-tarh-file";>tar.h</a>:
"This field is terminated with a space only."
*/
@@ -58,6 +133,16 @@ public class TarArchiveInputStream extends
ArchiveInputStream<TarArchiveEntry> {
private static final int SMALL_BUFFER_SIZE = 256;
+ /**
+ * Creates a new builder.
+ *
+ * @return a new builder.
+ * @since 1.29.0
+ */
+ public static Builder builder() {
+ return new Builder();
+ }
+
/**
* Checks if the signature matches what is expected for a tar file.
*
@@ -129,6 +214,15 @@ public static boolean matches(final byte[] signature,
final int length) {
private final boolean lenient;
+ @SuppressWarnings("resource") // caller closes.
+ private TarArchiveInputStream(final Builder builder) throws IOException {
+ super(builder.getInputStream(), builder.getCharset());
+ this.zipEncoding =
ZipEncodingHelper.getZipEncoding(builder.getCharset());
+ this.recordBuffer = new byte[builder.recordSize];
+ this.blockSize = builder.blockSize;
+ this.lenient = builder.lenient;
+ }
+
/**
* Constructs a new instance.
*
diff --git
a/src/test/java/org/apache/commons/compress/archivers/tar/TarArchiveInputStreamTest.java
b/src/test/java/org/apache/commons/compress/archivers/tar/TarArchiveInputStreamTest.java
index 147356a9b..0dcaef850 100644
---
a/src/test/java/org/apache/commons/compress/archivers/tar/TarArchiveInputStreamTest.java
+++
b/src/test/java/org/apache/commons/compress/archivers/tar/TarArchiveInputStreamTest.java
@@ -63,6 +63,7 @@
import org.apache.commons.compress.archivers.ArchiveStreamFactory;
import org.apache.commons.io.IOUtils;
import org.apache.commons.io.function.IOConsumer;
+import org.junit.jupiter.api.Disabled;
import org.junit.jupiter.api.Test;
import org.junit.jupiter.params.ParameterizedTest;
import org.junit.jupiter.params.provider.ValueSource;
@@ -150,9 +151,13 @@ private void testCompress666(final int factor, final
boolean bufferInputStream,
final List<Future<?>> tasks = IntStream.range(0,
200).mapToObj(index -> executorService.submit(() -> {
TarArchiveEntry tarEntry = null;
try (InputStream inputStream =
getClass().getResourceAsStream(localPath);
- TarArchiveInputStream tarInputStream = new
TarArchiveInputStream(
- bufferInputStream ? new BufferedInputStream(new
GZIPInputStream(inputStream)) : new GZIPInputStream(inputStream),
- TarConstants.DEFAULT_RCDSIZE * factor,
TarConstants.DEFAULT_RCDSIZE)) {
+ // @formatter:off
+ TarArchiveInputStream tarInputStream =
TarArchiveInputStream.builder()
+ .setInputStream(bufferInputStream ? new
BufferedInputStream(new GZIPInputStream(inputStream)) : new
GZIPInputStream(inputStream))
+ .setBlockSize(TarConstants.DEFAULT_RCDSIZE *
factor)
+ .setRecordSize(TarConstants.DEFAULT_RCDSIZE)
+ .get()) {
+ // @formatter:on
while ((tarEntry = tarInputStream.getNextEntry()) != null)
{
assertNotNull(tarEntry);
}
@@ -277,7 +282,7 @@ void testGetAndSetOfPaxEntry() throws Exception {
* Depending on your setup, this test may need a small stack size {@code
-Xss256k}.
*/
@Test
- void testGetNextTarEntry() throws IOException {
+ void testGetNextEntry() throws IOException {
try (TarArchiveInputStream inputStream = new TarArchiveInputStream(
Files.newInputStream(Paths.get("src/test/resources/org/apache/commons/compress/tar/getNextTarEntry.bin"))))
{
final AtomicLong count = new AtomicLong();
@@ -311,6 +316,44 @@ void testGetNextTarEntry() throws IOException {
}
}
+ /**
+ * Depending on your setup, this test may need a small stack size {@code
-Xss256k}.
+ */
+ @Test
+ void testGetNextTarEntryDeprecated() throws IOException {
+ try (TarArchiveInputStream inputStream = new TarArchiveInputStream(
+
Files.newInputStream(Paths.get("src/test/resources/org/apache/commons/compress/tar/getNextTarEntry.bin"))))
{
+ final AtomicLong count = new AtomicLong();
+ final TarArchiveEntry entry = inputStream.getNextTarEntry();
+ assertNull(entry.getCreationTime());
+ assertNull(entry.getLastAccessTime());
+ assertEquals(new Date(0), entry.getLastModifiedDate());
+ assertEquals(FileTime.fromMillis(0), entry.getLastModifiedTime());
+ assertNull(entry.getStatusChangeTime());
+ assertEquals(-1, entry.getDataOffset());
+ assertEquals(0, entry.getDevMajor());
+ assertEquals(0, entry.getDevMinor());
+ assertEquals(0, entry.getDirectoryEntries().length);
+ assertEquals(0, entry.getExtraPaxHeaders().size());
+ assertEquals(0, entry.getOrderedSparseHeaders().size());
+ assertEquals(0, entry.getSparseHeaders().size());
+ assertNull(entry.getFile());
+ assertNull(entry.getPath());
+ assertEquals("", entry.getGroupName());
+ assertEquals(0x1ff, entry.getMode());
+ assertEquals("", entry.getName());
+ assertEquals(0, entry.getRealSize());
+ assertEquals(0, entry.getSize());
+ assertEquals("", entry.getUserName());
+ assertEquals("", entry.getLinkName());
+ assertEquals(0x30, entry.getLinkFlag());
+ assertEquals(0, entry.getLongGroupId());
+ assertEquals(0, entry.getLongUserId());
+ inputStream.forEach(e -> count.incrementAndGet());
+ assertEquals(0, count.get());
+ }
+ }
+
@Test
void testMultiByteReadConsistentlyReturnsMinusOneAtEof() throws Exception {
final byte[] buf = new byte[2];
@@ -347,6 +390,15 @@ void testParseTarWithNonNumberPaxHeaders() throws
IOException {
}
}
+ @Test
+ @Disabled
+ void testChecksum() throws IOException {
+ try (InputStream in =
newInputStream("org/apache/commons/compress/COMPRESS-707/COMPRESS-707.tar");
+ TarArchiveInputStream archive =
TarArchiveInputStream.builder().setInputStream(in).setLenient(true).get()) {
+ archive.getNextEntry();
+ }
+ }
+
@Test
void testParseTarWithSpecialPaxHeaders() throws IOException {
try (InputStream in = newInputStream("COMPRESS-530-fail.tar");
