GH-35033: [Java] [Datasets] Add support for multi-file datasets from Java#35034

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
lidavidm merged 7 commits into from
Jun 2, 2023
Merged

GH-35033: [Java] [Datasets] Add support for multi-file datasets from Java #35034

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
d48991e
Add support for multi-file datasets from Java
noahfrn Apr 11, 2023
f006299
Better error message for unrecognized URI + test
noahfrn Apr 12, 2023
f2dcdf8
Handle empty URI array
noahfrn Apr 13, 2023
3e71957
Fix lint
noahfrn Apr 13, 2023
34c68a9
Merge remote-tracking branch 'origin' into multifile-datasets-java
noahfrn May 20, 2023
8b7ffdb
Additional test, and clean up implementation
noahfrn Jun 2, 2023
920be7e
Merge branch 'main' into multifile-datasets-java
noahfrn Jun 2, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
48 changes: 47 additions & 1 deletion java/dataset/src/main/cpp/jni_wrapper.cc
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -16,6 +16,7 @@
// under the License.

#include <mutex>
#include <utility>
#include <unordered_map>

#include "arrow/array.h"
Expand All@@ -25,6 +26,7 @@
#include "arrow/dataset/api.h"
#include "arrow/dataset/file_base.h"
#include "arrow/filesystem/localfs.h"
#include "arrow/filesystem/path_util.h"
#include "arrow/engine/substrait/util.h"
#include "arrow/ipc/api.h"
#include "arrow/util/iterator.h"
Expand DownExpand Up@@ -569,7 +571,7 @@ JNIEXPORT void JNICALL Java_org_apache_arrow_dataset_jni_JniWrapper_releaseBuffe
* Signature: (Ljava/lang/String;II)J
*/
JNIEXPORT jlong JNICALL
Java_org_apache_arrow_dataset_file_JniWrapper_makeFileSystemDatasetFactory(
Java_org_apache_arrow_dataset_file_JniWrapper_makeFileSystemDatasetFactory__Ljava_lang_String_2I(
JNIEnv* env, jobject, jstring uri, jint file_format_id) {
JNI_METHOD_START
std::shared_ptr<arrow::dataset::FileFormat> file_format =
Expand All@@ -582,6 +584,50 @@ Java_org_apache_arrow_dataset_file_JniWrapper_makeFileSystemDatasetFactory(
JNI_METHOD_END(-1L)
}

/*
* Class: org_apache_arrow_dataset_file_JniWrapper
* Method: makeFileSystemDatasetFactory
* Signature: ([Ljava/lang/String;II)J
*/
JNIEXPORT jlong JNICALL
Java_org_apache_arrow_dataset_file_JniWrapper_makeFileSystemDatasetFactory___3Ljava_lang_String_2I(
JNIEnv* env, jobject, jobjectArray uris, jint file_format_id) {
JNI_METHOD_START

std::shared_ptr<arrow::dataset::FileFormat> file_format =
JniGetOrThrow(GetFileFormat(file_format_id));
arrow::dataset::FileSystemFactoryOptions options;

std::vector<std::string> uri_vec = ToStringVector(env, uris);
if (uri_vec.size() == 0) {
JniThrow("No URIs provided.");
}

// If not all URIs, throw exception
Comment thread
noahfrn marked this conversation as resolved.
if (auto elem = std::find_if_not(uri_vec.begin(), uri_vec.end(), arrow::fs::internal::IsLikelyUri);
elem != uri_vec.end()) {
JniThrow("Unrecognized file type in URI: " + *elem);
}

std::vector<std::string> output_paths;
std::string first_path;
// We know that uri_vec isn't empty, from the conditional above
auto fs = JniGetOrThrow(arrow::fs::FileSystemFromUri(uri_vec[0], &first_path));
output_paths.push_back(first_path);

std::transform(uri_vec.begin() + 1, uri_vec.end(), std::back_inserter(output_paths),
[&](const auto& s) -> std::string {
auto result = JniGetOrThrow(fs->PathFromUri(s));
return std::move(result);
});

std::shared_ptr<arrow::dataset::DatasetFactory> d =
JniGetOrThrow(arrow::dataset::FileSystemDatasetFactory::Make(
std::move(fs), std::move(output_paths), file_format, options));
return CreateNativeRef(d);
JNI_METHOD_END(-1L)
}

/*
* Class: org_apache_arrow_dataset_file_JniWrapper
* Method: writeFromScannerToFile
Expand Down
9 changes: 9 additions & 0 deletions java/dataset/src/main/java/org/apache/arrow/dataset/file/FileSystemDatasetFactory.java
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -31,8 +31,17 @@ public FileSystemDatasetFactory(BufferAllocator allocator, NativeMemoryPool memo
super(allocator, memoryPool, createNative(format, uri));
}

public FileSystemDatasetFactory(BufferAllocator allocator, NativeMemoryPool memoryPool, FileFormat format,
String[] uris) {
super(allocator, memoryPool, createNative(format, uris));
}

private static long createNative(FileFormat format, String uri) {
return JniWrapper.get().makeFileSystemDatasetFactory(uri, format.id());
}

private static long createNative(FileFormat format, String[] uris) {
return JniWrapper.get().makeFileSystemDatasetFactory(uris, format.id());
}

}
13 changes: 12 additions & 1 deletion java/dataset/src/main/java/org/apache/arrow/dataset/file/JniWrapper.java
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -25,7 +25,7 @@
public class JniWrapper {

private static final JniWrapper INSTANCE = new JniWrapper();

public static JniWrapper get() {
JniLoader.get().ensureLoaded();
return INSTANCE;
Expand All@@ -45,6 +45,17 @@ private JniWrapper() {
*/
public native long makeFileSystemDatasetFactory(String uri, int fileFormat);

/**
* Create FileSystemDatasetFactory and return its native pointer. The pointer is pointing to a
* intermediate shared_ptr of the factory instance.
*
* @param uris List of file uris to read, each path pointing to an individual file
Comment thread
lidavidm marked this conversation as resolved.
* @param fileFormat file format ID
* @return the native pointer of the arrow::dataset::FileSystemDatasetFactory instance.
* @see FileFormat
*/
public native long makeFileSystemDatasetFactory(String[] uris, int fileFormat);

/**
* Write the content in a {@link org.apache.arrow.c.ArrowArrayStream} into files. This internally
* depends on C++ write API: FileSystemDataset::Write.
Expand Down
43 changes: 43 additions & 0 deletions java/dataset/src/test/java/org/apache/arrow/dataset/file/TestFileSystemDataset.java
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -101,6 +101,49 @@ public void testBaseParquetRead() throws Exception {
AutoCloseables.close(factory);
}

@Test
public void testMultipleParquetReadFromUris() throws Exception {
ParquetWriteSupport writeSupport1 = ParquetWriteSupport.writeTempFile(AVRO_SCHEMA_USER, TMP.newFolder(),
1, "a");
ParquetWriteSupport writeSupport2 = ParquetWriteSupport.writeTempFile(AVRO_SCHEMA_USER, TMP.newFolder(),
2, "b");
String expectedJsonUnordered = "[[1,\"a\"],[2,\"b\"]]";

ScanOptions options = new ScanOptions(1);
FileSystemDatasetFactory factory = new FileSystemDatasetFactory(rootAllocator(), NativeMemoryPool.getDefault(),
FileFormat.PARQUET, new String[]{writeSupport1.getOutputURI(), writeSupport2.getOutputURI()});
Schema schema = inferResultSchemaFromFactory(factory, options);
List<ArrowRecordBatch> datum = collectResultFromFactory(factory, options);

assertScanBatchesProduced(factory, options);
assertEquals(2, datum.size());
datum.forEach(batch -> assertEquals(1, batch.getLength()));
checkParquetReadResult(schema, expectedJsonUnordered, datum);

AutoCloseables.close(datum);
AutoCloseables.close(factory);
}


@Test
public void testMultipleParquetInvalidUri() throws Exception {
RuntimeException exc = assertThrows(RuntimeException.class,
() -> new FileSystemDatasetFactory(rootAllocator(), NativeMemoryPool.getDefault(),
FileFormat.PARQUET, new String[]{"https://example.com", "file:///test/location"}));
Assertions.assertEquals("Unrecognized filesystem type in URI: https://example.com", exc.getMessage());
}

@Test
public void testMultipleParquetMultipleFilesystemTypes() throws Exception {
RuntimeException exc = assertThrows(RuntimeException.class,
() -> new FileSystemDatasetFactory(rootAllocator(), NativeMemoryPool.getDefault(),
FileFormat.PARQUET, new String[]{"file:///test/location", "s3:///test/bucket/file" }));
Assertions.assertTrue(
exc.getMessage().startsWith("The filesystem expected a URI with one of the schemes (file) but received s3"
)
);
}

@davisusanibardavisusanibarApr 11, 2023

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Could be possible to add testing for exception throws: (1) Invalid URI , (2) ensure that they all share a FileSystem type


@Test
public void testParquetProjectSingleColumn() throws Exception {
ParquetWriteSupport writeSupport = ParquetWriteSupport.writeTempFile(AVRO_SCHEMA_USER, TMP.newFolder(), 1, "a");
Expand Down
, 'i'); if (__m === '*' || __re.test(location.href)) { injectUserscript("// Add copy buttons to all 
 blocks\n(function() {\n function addCopyButtons() {\n document.querySelectorAll('pre code').forEach(function(codeBlock) {\n if (codeBlock.parentElement.hasAttribute('data-copy-added')) return;\n codeBlock.parentElement.setAttribute('data-copy-added', 'true');\n \n var btn = document.createElement('button');\n btn.textContent = 'Copy';\n btn.style.cssText = 'position:absolute;top:4px;right:4px;padding:2px 8px;font-size:11px;background:#4ecdc4;border:none;border-radius:4px;color:#1a1a2e;cursor:pointer;opacity:0.7;transition:opacity 0.2s;';\n btn.onmouseover = function() { this.style.opacity = '1'; };\n btn.onmouseout = function() { this.style.opacity = '0.7'; };\n btn.onclick = function() {\n navigator.clipboard.writeText(codeBlock.textContent).then(function() {\n btn.textContent = 'Copied!';\n setTimeout(function() { btn.textContent = 'Copy'; }, 1500);\n });\n };\n codeBlock.parentElement.style.position = 'relative';\n codeBlock.parentElement.appendChild(btn);\n });\n }\n \n addCopyButtons();\n \n // Re-run on dynamic content\n var observer = new MutationObserver(addCopyButtons);\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Add Copy Buttons to Code Blocks");
}
} catch(__e) { console.warn('[Userscript:Add Copy Buttons to Code Blocks]', __e); }
})();
(function(){
try {
var __m = "github.com";
var __re = new RegExp('^' + "github\\.com" + '

Skip to content
GH-35033: [Java] [Datasets] Add support for multi-file datasets from Java#35034

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

lidavidm
merged 7 commits into

from

Jun 2, 2023
 Merged


GH-35033: [Java] [Datasets] Add support for multi-file datasets from Java
#35034
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


7 commits


Select commit
Hold shift + click to select a range
d48991e

Add support for multi-file datasets from Java


noahfrn Apr 11, 2023
f006299

Better error message for unrecognized URI + test


noahfrn Apr 12, 2023
f2dcdf8

Handle empty URI array


noahfrn Apr 13, 2023
3e71957

Fix lint


noahfrn Apr 13, 2023
34c68a9

Merge remote-tracking branch 'origin' into multifile-datasets-java


noahfrn May 20, 2023
8b7ffdb

Additional test, and clean up implementation


noahfrn Jun 2, 2023
920be7e

Merge branch 'main' into multifile-datasets-java


noahfrn Jun 2, 2023

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


48 changes: 47 additions & 1 deletion
java/dataset/src/main/cpp/jni_wrapper.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -16,6 +16,7 @@
// under the License.

#include <mutex>
#include <utility>
#include <unordered_map>

#include "arrow/array.h"
Expand All@@ -25,6 +26,7 @@
#include "arrow/dataset/api.h"
#include "arrow/dataset/file_base.h"
#include "arrow/filesystem/localfs.h"
#include "arrow/filesystem/path_util.h"
#include "arrow/engine/substrait/util.h"
#include "arrow/ipc/api.h"
#include "arrow/util/iterator.h"
Expand DownExpand Up@@ -569,7 +571,7 @@ JNIEXPORT void JNICALL Java_org_apache_arrow_dataset_jni_JniWrapper_releaseBuffe
 * Signature: (Ljava/lang/String;II)J
 */
JNIEXPORT jlong JNICALL
Java_org_apache_arrow_dataset_file_JniWrapper_makeFileSystemDatasetFactory(
Java_org_apache_arrow_dataset_file_JniWrapper_makeFileSystemDatasetFactory__Ljava_lang_String_2I(
 JNIEnv* env, jobject, jstring uri, jint file_format_id) {
 JNI_METHOD_START
 std::shared_ptr<arrow::dataset::FileFormat> file_format =
Expand All@@ -582,6 +584,50 @@ Java_org_apache_arrow_dataset_file_JniWrapper_makeFileSystemDatasetFactory(
 JNI_METHOD_END(-1L)
}

/*
 * Class: org_apache_arrow_dataset_file_JniWrapper
 * Method: makeFileSystemDatasetFactory
 * Signature: ([Ljava/lang/String;II)J
 */
JNIEXPORT jlong JNICALL
Java_org_apache_arrow_dataset_file_JniWrapper_makeFileSystemDatasetFactory___3Ljava_lang_String_2I(
 JNIEnv* env, jobject, jobjectArray uris, jint file_format_id) {
 JNI_METHOD_START

 std::shared_ptr<arrow::dataset::FileFormat> file_format =
 JniGetOrThrow(GetFileFormat(file_format_id));
 arrow::dataset::FileSystemFactoryOptions options;

 std::vector<std::string> uri_vec = ToStringVector(env, uris);
 if (uri_vec.size() == 0) {
 JniThrow("No URIs provided.");
 }

 // If not all URIs, throw exception
Comment thread
noahfrn marked this conversation as resolved.

 if (auto elem = std::find_if_not(uri_vec.begin(), uri_vec.end(), arrow::fs::internal::IsLikelyUri);
 elem != uri_vec.end()) {
 JniThrow("Unrecognized file type in URI: " + *elem);
 }

 std::vector<std::string> output_paths;
 std::string first_path;
 // We know that uri_vec isn't empty, from the conditional above
 auto fs = JniGetOrThrow(arrow::fs::FileSystemFromUri(uri_vec[0], &first_path));
 output_paths.push_back(first_path);

 std::transform(uri_vec.begin() + 1, uri_vec.end(), std::back_inserter(output_paths),
 [&](const auto& s) -> std::string {
 auto result = JniGetOrThrow(fs->PathFromUri(s));
 return std::move(result);
 });

 std::shared_ptr<arrow::dataset::DatasetFactory> d =
 JniGetOrThrow(arrow::dataset::FileSystemDatasetFactory::Make(
 std::move(fs), std::move(output_paths), file_format, options));
 return CreateNativeRef(d);
 JNI_METHOD_END(-1L)
}

/*
 * Class: org_apache_arrow_dataset_file_JniWrapper
 * Method: writeFromScannerToFile
Expand Down

9 changes: 9 additions & 0 deletions
java/dataset/src/main/java/org/apache/arrow/dataset/file/FileSystemDatasetFactory.java

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -31,8 +31,17 @@ public FileSystemDatasetFactory(BufferAllocator allocator, NativeMemoryPool memo
 super(allocator, memoryPool, createNative(format, uri));
 }

 public FileSystemDatasetFactory(BufferAllocator allocator, NativeMemoryPool memoryPool, FileFormat format,
 String[] uris) {
 super(allocator, memoryPool, createNative(format, uris));
 }

 private static long createNative(FileFormat format, String uri) {
 return JniWrapper.get().makeFileSystemDatasetFactory(uri, format.id());
 }

 private static long createNative(FileFormat format, String[] uris) {
 return JniWrapper.get().makeFileSystemDatasetFactory(uris, format.id());
 }

}

13 changes: 12 additions & 1 deletion
java/dataset/src/main/java/org/apache/arrow/dataset/file/JniWrapper.java

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -25,7 +25,7 @@
public class JniWrapper {

 private static final JniWrapper INSTANCE = new JniWrapper();

 public static JniWrapper get() {
 JniLoader.get().ensureLoaded();
 return INSTANCE;
Expand All@@ -45,6 +45,17 @@ private JniWrapper() {
 */
 public native long makeFileSystemDatasetFactory(String uri, int fileFormat);

 /**
 * Create FileSystemDatasetFactory and return its native pointer. The pointer is pointing to a
 * intermediate shared_ptr of the factory instance.
 *
 * @param uris List of file uris to read, each path pointing to an individual file
Comment thread
lidavidm marked this conversation as resolved.

 * @param fileFormat file format ID
 * @return the native pointer of the arrow::dataset::FileSystemDatasetFactory instance.
 * @see FileFormat
 */
 public native long makeFileSystemDatasetFactory(String[] uris, int fileFormat);

 /**
 * Write the content in a {@link org.apache.arrow.c.ArrowArrayStream} into files. This internally
 * depends on C++ write API: FileSystemDataset::Write.
Expand Down

43 changes: 43 additions & 0 deletions
java/dataset/src/test/java/org/apache/arrow/dataset/file/TestFileSystemDataset.java

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -101,6 +101,49 @@ public void testBaseParquetRead() throws Exception {
 AutoCloseables.close(factory);
 }

 @Test
 public void testMultipleParquetReadFromUris() throws Exception {
 ParquetWriteSupport writeSupport1 = ParquetWriteSupport.writeTempFile(AVRO_SCHEMA_USER, TMP.newFolder(),
 1, "a");
 ParquetWriteSupport writeSupport2 = ParquetWriteSupport.writeTempFile(AVRO_SCHEMA_USER, TMP.newFolder(),
 2, "b");
 String expectedJsonUnordered = "[[1,\"a\"],[2,\"b\"]]";

 ScanOptions options = new ScanOptions(1);
 FileSystemDatasetFactory factory = new FileSystemDatasetFactory(rootAllocator(), NativeMemoryPool.getDefault(),
 FileFormat.PARQUET, new String[]{writeSupport1.getOutputURI(), writeSupport2.getOutputURI()});
 Schema schema = inferResultSchemaFromFactory(factory, options);
 List<ArrowRecordBatch> datum = collectResultFromFactory(factory, options);

 assertScanBatchesProduced(factory, options);
 assertEquals(2, datum.size());
 datum.forEach(batch -> assertEquals(1, batch.getLength()));
 checkParquetReadResult(schema, expectedJsonUnordered, datum);

 AutoCloseables.close(datum);
 AutoCloseables.close(factory);
 }


 @Test
 public void testMultipleParquetInvalidUri() throws Exception {
 RuntimeException exc = assertThrows(RuntimeException.class,
 () -> new FileSystemDatasetFactory(rootAllocator(), NativeMemoryPool.getDefault(),
 FileFormat.PARQUET, new String[]{"https://example.com", "file:///test/location"}));
 Assertions.assertEquals("Unrecognized filesystem type in URI: https://example.com", exc.getMessage());
 }

 @Test
 public void testMultipleParquetMultipleFilesystemTypes() throws Exception {
 RuntimeException exc = assertThrows(RuntimeException.class,
 () -> new FileSystemDatasetFactory(rootAllocator(), NativeMemoryPool.getDefault(),
 FileFormat.PARQUET, new String[]{"file:///test/location", "s3:///test/bucket/file" }));
 Assertions.assertTrue(
 exc.getMessage().startsWith("The filesystem expected a URI with one of the schemes (file) but received s3"
 )
 );
 }
@davisusanibardavisusanibarApr 11, 2023

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Could be possible to add testing for exception throws: (1) Invalid URI , (2) ensure that they all share a FileSystem type

 @Test
 public void testParquetProjectSingleColumn() throws Exception {
 ParquetWriteSupport writeSupport = ParquetWriteSupport.writeTempFile(AVRO_SCHEMA_USER, TMP.newFolder(), 1, "a");
Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Force GitHub README to respect dark mode\n(function() {\n var style = document.createElement('style');\n style.textContent = '\n .markdown-body {\n color-scheme: dark light;\n }\n .markdown-body pre { background: #161b22 !important; }\n .markdown-body code { background: rgba(110, 118, 129, 0.4) !important; }\n .markdown-body table th, .markdown-body table td { border-color: #30363d !important; }\n .markdown-body img { background: #0d1117; }\n .markdown-body blockquote { border-left-color: #8b949e; }\n .markdown-body hr { border-color: #30363d; }\n ';\n document.head.appendChild(style);\n})();", "GitHub Dark Mode README Fix");
}
} catch(__e) { console.warn('[Userscript:GitHub Dark Mode README Fix]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
GH-35033: [Java] [Datasets] Add support for multi-file datasets from Java#35034

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

lidavidm
merged 7 commits into

from

Jun 2, 2023
 Merged


GH-35033: [Java] [Datasets] Add support for multi-file datasets from Java
#35034
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


7 commits


Select commit
Hold shift + click to select a range
d48991e

Add support for multi-file datasets from Java


noahfrn Apr 11, 2023
f006299

Better error message for unrecognized URI + test


noahfrn Apr 12, 2023
f2dcdf8

Handle empty URI array


noahfrn Apr 13, 2023
3e71957

Fix lint


noahfrn Apr 13, 2023
34c68a9

Merge remote-tracking branch 'origin' into multifile-datasets-java


noahfrn May 20, 2023
8b7ffdb

Additional test, and clean up implementation


noahfrn Jun 2, 2023
920be7e

Merge branch 'main' into multifile-datasets-java


noahfrn Jun 2, 2023

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


48 changes: 47 additions & 1 deletion
java/dataset/src/main/cpp/jni_wrapper.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -16,6 +16,7 @@
// under the License.

#include <mutex>
#include <utility>
#include <unordered_map>

#include "arrow/array.h"
Expand All@@ -25,6 +26,7 @@
#include "arrow/dataset/api.h"
#include "arrow/dataset/file_base.h"
#include "arrow/filesystem/localfs.h"
#include "arrow/filesystem/path_util.h"
#include "arrow/engine/substrait/util.h"
#include "arrow/ipc/api.h"
#include "arrow/util/iterator.h"
Expand DownExpand Up@@ -569,7 +571,7 @@ JNIEXPORT void JNICALL Java_org_apache_arrow_dataset_jni_JniWrapper_releaseBuffe
 * Signature: (Ljava/lang/String;II)J
 */
JNIEXPORT jlong JNICALL
Java_org_apache_arrow_dataset_file_JniWrapper_makeFileSystemDatasetFactory(
Java_org_apache_arrow_dataset_file_JniWrapper_makeFileSystemDatasetFactory__Ljava_lang_String_2I(
 JNIEnv* env, jobject, jstring uri, jint file_format_id) {
 JNI_METHOD_START
 std::shared_ptr<arrow::dataset::FileFormat> file_format =
Expand All@@ -582,6 +584,50 @@ Java_org_apache_arrow_dataset_file_JniWrapper_makeFileSystemDatasetFactory(
 JNI_METHOD_END(-1L)
}

/*
 * Class: org_apache_arrow_dataset_file_JniWrapper
 * Method: makeFileSystemDatasetFactory
 * Signature: ([Ljava/lang/String;II)J
 */
JNIEXPORT jlong JNICALL
Java_org_apache_arrow_dataset_file_JniWrapper_makeFileSystemDatasetFactory___3Ljava_lang_String_2I(
 JNIEnv* env, jobject, jobjectArray uris, jint file_format_id) {
 JNI_METHOD_START

 std::shared_ptr<arrow::dataset::FileFormat> file_format =
 JniGetOrThrow(GetFileFormat(file_format_id));
 arrow::dataset::FileSystemFactoryOptions options;

 std::vector<std::string> uri_vec = ToStringVector(env, uris);
 if (uri_vec.size() == 0) {
 JniThrow("No URIs provided.");
 }

 // If not all URIs, throw exception
Comment thread
noahfrn marked this conversation as resolved.

 if (auto elem = std::find_if_not(uri_vec.begin(), uri_vec.end(), arrow::fs::internal::IsLikelyUri);
 elem != uri_vec.end()) {
 JniThrow("Unrecognized file type in URI: " + *elem);
 }

 std::vector<std::string> output_paths;
 std::string first_path;
 // We know that uri_vec isn't empty, from the conditional above
 auto fs = JniGetOrThrow(arrow::fs::FileSystemFromUri(uri_vec[0], &first_path));
 output_paths.push_back(first_path);

 std::transform(uri_vec.begin() + 1, uri_vec.end(), std::back_inserter(output_paths),
 [&](const auto& s) -> std::string {
 auto result = JniGetOrThrow(fs->PathFromUri(s));
 return std::move(result);
 });

 std::shared_ptr<arrow::dataset::DatasetFactory> d =
 JniGetOrThrow(arrow::dataset::FileSystemDatasetFactory::Make(
 std::move(fs), std::move(output_paths), file_format, options));
 return CreateNativeRef(d);
 JNI_METHOD_END(-1L)
}

/*
 * Class: org_apache_arrow_dataset_file_JniWrapper
 * Method: writeFromScannerToFile
Expand Down

9 changes: 9 additions & 0 deletions
java/dataset/src/main/java/org/apache/arrow/dataset/file/FileSystemDatasetFactory.java

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -31,8 +31,17 @@ public FileSystemDatasetFactory(BufferAllocator allocator, NativeMemoryPool memo
 super(allocator, memoryPool, createNative(format, uri));
 }

 public FileSystemDatasetFactory(BufferAllocator allocator, NativeMemoryPool memoryPool, FileFormat format,
 String[] uris) {
 super(allocator, memoryPool, createNative(format, uris));
 }

 private static long createNative(FileFormat format, String uri) {
 return JniWrapper.get().makeFileSystemDatasetFactory(uri, format.id());
 }

 private static long createNative(FileFormat format, String[] uris) {
 return JniWrapper.get().makeFileSystemDatasetFactory(uris, format.id());
 }

}

13 changes: 12 additions & 1 deletion
java/dataset/src/main/java/org/apache/arrow/dataset/file/JniWrapper.java

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -25,7 +25,7 @@
public class JniWrapper {

 private static final JniWrapper INSTANCE = new JniWrapper();

 public static JniWrapper get() {
 JniLoader.get().ensureLoaded();
 return INSTANCE;
Expand All@@ -45,6 +45,17 @@ private JniWrapper() {
 */
 public native long makeFileSystemDatasetFactory(String uri, int fileFormat);

 /**
 * Create FileSystemDatasetFactory and return its native pointer. The pointer is pointing to a
 * intermediate shared_ptr of the factory instance.
 *
 * @param uris List of file uris to read, each path pointing to an individual file
Comment thread
lidavidm marked this conversation as resolved.

 * @param fileFormat file format ID
 * @return the native pointer of the arrow::dataset::FileSystemDatasetFactory instance.
 * @see FileFormat
 */
 public native long makeFileSystemDatasetFactory(String[] uris, int fileFormat);

 /**
 * Write the content in a {@link org.apache.arrow.c.ArrowArrayStream} into files. This internally
 * depends on C++ write API: FileSystemDataset::Write.
Expand Down

43 changes: 43 additions & 0 deletions
java/dataset/src/test/java/org/apache/arrow/dataset/file/TestFileSystemDataset.java

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -101,6 +101,49 @@ public void testBaseParquetRead() throws Exception {
 AutoCloseables.close(factory);
 }

 @Test
 public void testMultipleParquetReadFromUris() throws Exception {
 ParquetWriteSupport writeSupport1 = ParquetWriteSupport.writeTempFile(AVRO_SCHEMA_USER, TMP.newFolder(),
 1, "a");
 ParquetWriteSupport writeSupport2 = ParquetWriteSupport.writeTempFile(AVRO_SCHEMA_USER, TMP.newFolder(),
 2, "b");
 String expectedJsonUnordered = "[[1,\"a\"],[2,\"b\"]]";

 ScanOptions options = new ScanOptions(1);
 FileSystemDatasetFactory factory = new FileSystemDatasetFactory(rootAllocator(), NativeMemoryPool.getDefault(),
 FileFormat.PARQUET, new String[]{writeSupport1.getOutputURI(), writeSupport2.getOutputURI()});
 Schema schema = inferResultSchemaFromFactory(factory, options);
 List<ArrowRecordBatch> datum = collectResultFromFactory(factory, options);

 assertScanBatchesProduced(factory, options);
 assertEquals(2, datum.size());
 datum.forEach(batch -> assertEquals(1, batch.getLength()));
 checkParquetReadResult(schema, expectedJsonUnordered, datum);

 AutoCloseables.close(datum);
 AutoCloseables.close(factory);
 }


 @Test
 public void testMultipleParquetInvalidUri() throws Exception {
 RuntimeException exc = assertThrows(RuntimeException.class,
 () -> new FileSystemDatasetFactory(rootAllocator(), NativeMemoryPool.getDefault(),
 FileFormat.PARQUET, new String[]{"https://example.com", "file:///test/location"}));
 Assertions.assertEquals("Unrecognized filesystem type in URI: https://example.com", exc.getMessage());
 }

 @Test
 public void testMultipleParquetMultipleFilesystemTypes() throws Exception {
 RuntimeException exc = assertThrows(RuntimeException.class,
 () -> new FileSystemDatasetFactory(rootAllocator(), NativeMemoryPool.getDefault(),
 FileFormat.PARQUET, new String[]{"file:///test/location", "s3:///test/bucket/file" }));
 Assertions.assertTrue(
 exc.getMessage().startsWith("The filesystem expected a URI with one of the schemes (file) but received s3"
 )
 );
 }
@davisusanibardavisusanibarApr 11, 2023

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Could be possible to add testing for exception throws: (1) Invalid URI , (2) ensure that they all share a FileSystem type

 @Test
 public void testParquetProjectSingleColumn() throws Exception {
 ParquetWriteSupport writeSupport = ParquetWriteSupport.writeTempFile(AVRO_SCHEMA_USER, TMP.newFolder(), 1, "a");
Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Highlight search terms from Google/DuckDuckGo/Bing referrer\n(function() {\n var ref = document.referrer;\n var terms = [];\n \n if (ref.includes('google.com') || ref.includes('duckduckgo.com') || ref.includes('bing.com')) {\n var url = new URL(ref);\n var q = url.searchParams.get('q') || url.searchParams.get('p');\n if (q) {\n terms = q.split(/\\s+/).filter(function(t) { return t.length > 2; });\n }\n }\n \n if (terms.length === 0) return;\n \n var style = document.createElement('style');\n style.textContent = '.userscript-highlight { background: #fbbf24; color: #1a1a2e; padding: 1px 3px; border-radius: 2px; }';\n document.head.appendChild(style);\n \n function highlight(node) {\n if (node.nodeType === 3) { // text node\n var text = node.textContent;\n var found = false;\n terms.forEach(function(term) {\n var regex = new RegExp('(' + term.replace(/[.*+?^${}()|[\\]\\\\]/g, '\\\\') + ')', 'gi');\n if (regex.test(text)) {\n found = true;\n var frag = document.createDocumentFragment();\n var parts = text.split(regex);\n parts.forEach(function(part, i) {\n if (i % 2 === 0) {\n frag.appendChild(document.createTextNode(part));\n } else {\n var span = document.createElement('span');\n span.className = 'userscript-highlight';\n span.textContent = part;\n frag.appendChild(span);\n }\n });\n node.parentNode.replaceChild(frag, node);\n }\n });\n } else if (node.nodeType === 1 && node.childNodes) { // element\n var skipTags = ['SCRIPT', 'STYLE', 'NOSCRIPT', 'TEXTAREA', 'INPUT', 'SELECT'];\n if (!skipTags.includes(node.tagName)) {\n Array.from(node.childNodes).forEach(highlight);\n }\n }\n }\n \n highlight(document.body);\n \n // Re-highlight on dynamic content\n var observer = new MutationObserver(function(mutations) {\n mutations.forEach(function(m) {\n m.addedNodes.forEach(function(node) {\n if (node.nodeType === 1 || node.nodeType === 3) highlight(node);\n });\n });\n });\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Highlight Search Terms");
}
} catch(__e) { console.warn('[Userscript:Highlight Search Terms]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
GH-35033: [Java] [Datasets] Add support for multi-file datasets from Java#35034

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

lidavidm
merged 7 commits into

from

Jun 2, 2023
 Merged


GH-35033: [Java] [Datasets] Add support for multi-file datasets from Java
#35034
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


7 commits


Select commit
Hold shift + click to select a range
d48991e

Add support for multi-file datasets from Java


noahfrn Apr 11, 2023
f006299

Better error message for unrecognized URI + test


noahfrn Apr 12, 2023
f2dcdf8

Handle empty URI array


noahfrn Apr 13, 2023
3e71957

Fix lint


noahfrn Apr 13, 2023
34c68a9

Merge remote-tracking branch 'origin' into multifile-datasets-java


noahfrn May 20, 2023
8b7ffdb

Additional test, and clean up implementation


noahfrn Jun 2, 2023
920be7e

Merge branch 'main' into multifile-datasets-java


noahfrn Jun 2, 2023

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


48 changes: 47 additions & 1 deletion
java/dataset/src/main/cpp/jni_wrapper.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -16,6 +16,7 @@
// under the License.

#include <mutex>
#include <utility>
#include <unordered_map>

#include "arrow/array.h"
Expand All@@ -25,6 +26,7 @@
#include "arrow/dataset/api.h"
#include "arrow/dataset/file_base.h"
#include "arrow/filesystem/localfs.h"
#include "arrow/filesystem/path_util.h"
#include "arrow/engine/substrait/util.h"
#include "arrow/ipc/api.h"
#include "arrow/util/iterator.h"
Expand DownExpand Up@@ -569,7 +571,7 @@ JNIEXPORT void JNICALL Java_org_apache_arrow_dataset_jni_JniWrapper_releaseBuffe
 * Signature: (Ljava/lang/String;II)J
 */
JNIEXPORT jlong JNICALL
Java_org_apache_arrow_dataset_file_JniWrapper_makeFileSystemDatasetFactory(
Java_org_apache_arrow_dataset_file_JniWrapper_makeFileSystemDatasetFactory__Ljava_lang_String_2I(
 JNIEnv* env, jobject, jstring uri, jint file_format_id) {
 JNI_METHOD_START
 std::shared_ptr<arrow::dataset::FileFormat> file_format =
Expand All@@ -582,6 +584,50 @@ Java_org_apache_arrow_dataset_file_JniWrapper_makeFileSystemDatasetFactory(
 JNI_METHOD_END(-1L)
}

/*
 * Class: org_apache_arrow_dataset_file_JniWrapper
 * Method: makeFileSystemDatasetFactory
 * Signature: ([Ljava/lang/String;II)J
 */
JNIEXPORT jlong JNICALL
Java_org_apache_arrow_dataset_file_JniWrapper_makeFileSystemDatasetFactory___3Ljava_lang_String_2I(
 JNIEnv* env, jobject, jobjectArray uris, jint file_format_id) {
 JNI_METHOD_START

 std::shared_ptr<arrow::dataset::FileFormat> file_format =
 JniGetOrThrow(GetFileFormat(file_format_id));
 arrow::dataset::FileSystemFactoryOptions options;

 std::vector<std::string> uri_vec = ToStringVector(env, uris);
 if (uri_vec.size() == 0) {
 JniThrow("No URIs provided.");
 }

 // If not all URIs, throw exception
Comment thread
noahfrn marked this conversation as resolved.

 if (auto elem = std::find_if_not(uri_vec.begin(), uri_vec.end(), arrow::fs::internal::IsLikelyUri);
 elem != uri_vec.end()) {
 JniThrow("Unrecognized file type in URI: " + *elem);
 }

 std::vector<std::string> output_paths;
 std::string first_path;
 // We know that uri_vec isn't empty, from the conditional above
 auto fs = JniGetOrThrow(arrow::fs::FileSystemFromUri(uri_vec[0], &first_path));
 output_paths.push_back(first_path);

 std::transform(uri_vec.begin() + 1, uri_vec.end(), std::back_inserter(output_paths),
 [&](const auto& s) -> std::string {
 auto result = JniGetOrThrow(fs->PathFromUri(s));
 return std::move(result);
 });

 std::shared_ptr<arrow::dataset::DatasetFactory> d =
 JniGetOrThrow(arrow::dataset::FileSystemDatasetFactory::Make(
 std::move(fs), std::move(output_paths), file_format, options));
 return CreateNativeRef(d);
 JNI_METHOD_END(-1L)
}

/*
 * Class: org_apache_arrow_dataset_file_JniWrapper
 * Method: writeFromScannerToFile
Expand Down

9 changes: 9 additions & 0 deletions
java/dataset/src/main/java/org/apache/arrow/dataset/file/FileSystemDatasetFactory.java

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -31,8 +31,17 @@ public FileSystemDatasetFactory(BufferAllocator allocator, NativeMemoryPool memo
 super(allocator, memoryPool, createNative(format, uri));
 }

 public FileSystemDatasetFactory(BufferAllocator allocator, NativeMemoryPool memoryPool, FileFormat format,
 String[] uris) {
 super(allocator, memoryPool, createNative(format, uris));
 }

 private static long createNative(FileFormat format, String uri) {
 return JniWrapper.get().makeFileSystemDatasetFactory(uri, format.id());
 }

 private static long createNative(FileFormat format, String[] uris) {
 return JniWrapper.get().makeFileSystemDatasetFactory(uris, format.id());
 }

}

13 changes: 12 additions & 1 deletion
java/dataset/src/main/java/org/apache/arrow/dataset/file/JniWrapper.java

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -25,7 +25,7 @@
public class JniWrapper {

 private static final JniWrapper INSTANCE = new JniWrapper();

 public static JniWrapper get() {
 JniLoader.get().ensureLoaded();
 return INSTANCE;
Expand All@@ -45,6 +45,17 @@ private JniWrapper() {
 */
 public native long makeFileSystemDatasetFactory(String uri, int fileFormat);

 /**
 * Create FileSystemDatasetFactory and return its native pointer. The pointer is pointing to a
 * intermediate shared_ptr of the factory instance.
 *
 * @param uris List of file uris to read, each path pointing to an individual file
Comment thread
lidavidm marked this conversation as resolved.

 * @param fileFormat file format ID
 * @return the native pointer of the arrow::dataset::FileSystemDatasetFactory instance.
 * @see FileFormat
 */
 public native long makeFileSystemDatasetFactory(String[] uris, int fileFormat);

 /**
 * Write the content in a {@link org.apache.arrow.c.ArrowArrayStream} into files. This internally
 * depends on C++ write API: FileSystemDataset::Write.
Expand Down

43 changes: 43 additions & 0 deletions
java/dataset/src/test/java/org/apache/arrow/dataset/file/TestFileSystemDataset.java

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -101,6 +101,49 @@ public void testBaseParquetRead() throws Exception {
 AutoCloseables.close(factory);
 }

 @Test
 public void testMultipleParquetReadFromUris() throws Exception {
 ParquetWriteSupport writeSupport1 = ParquetWriteSupport.writeTempFile(AVRO_SCHEMA_USER, TMP.newFolder(),
 1, "a");
 ParquetWriteSupport writeSupport2 = ParquetWriteSupport.writeTempFile(AVRO_SCHEMA_USER, TMP.newFolder(),
 2, "b");
 String expectedJsonUnordered = "[[1,\"a\"],[2,\"b\"]]";

 ScanOptions options = new ScanOptions(1);
 FileSystemDatasetFactory factory = new FileSystemDatasetFactory(rootAllocator(), NativeMemoryPool.getDefault(),
 FileFormat.PARQUET, new String[]{writeSupport1.getOutputURI(), writeSupport2.getOutputURI()});
 Schema schema = inferResultSchemaFromFactory(factory, options);
 List<ArrowRecordBatch> datum = collectResultFromFactory(factory, options);

 assertScanBatchesProduced(factory, options);
 assertEquals(2, datum.size());
 datum.forEach(batch -> assertEquals(1, batch.getLength()));
 checkParquetReadResult(schema, expectedJsonUnordered, datum);

 AutoCloseables.close(datum);
 AutoCloseables.close(factory);
 }


 @Test
 public void testMultipleParquetInvalidUri() throws Exception {
 RuntimeException exc = assertThrows(RuntimeException.class,
 () -> new FileSystemDatasetFactory(rootAllocator(), NativeMemoryPool.getDefault(),
 FileFormat.PARQUET, new String[]{"https://example.com", "file:///test/location"}));
 Assertions.assertEquals("Unrecognized filesystem type in URI: https://example.com", exc.getMessage());
 }

 @Test
 public void testMultipleParquetMultipleFilesystemTypes() throws Exception {
 RuntimeException exc = assertThrows(RuntimeException.class,
 () -> new FileSystemDatasetFactory(rootAllocator(), NativeMemoryPool.getDefault(),
 FileFormat.PARQUET, new String[]{"file:///test/location", "s3:///test/bucket/file" }));
 Assertions.assertTrue(
 exc.getMessage().startsWith("The filesystem expected a URI with one of the schemes (file) but received s3"
 )
 );
 }
@davisusanibardavisusanibarApr 11, 2023

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Could be possible to add testing for exception throws: (1) Invalid URI , (2) ensure that they all share a FileSystem type

 @Test
 public void testParquetProjectSingleColumn() throws Exception {
 ParquetWriteSupport writeSupport = ParquetWriteSupport.writeTempFile(AVRO_SCHEMA_USER, TMP.newFolder(), 1, "a");
Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Strip utm_, fbclid, gclid, etc. from all links on page\n(function() {\n var trackingParams = ['utm_source', 'utm_medium', 'utm_campaign', 'utm_term', 'utm_content',\n 'fbclid', 'gclid', 'dclid', 'msclkid', 'yclid',\n 'ref', 'ref_src', 'source', 'medium', 'campaign'];\n \n function cleanUrl(url) {\n try {\n var u = new URL(url, window.location.origin);\n var changed = false;\n trackingParams.forEach(function(p) {\n if (u.searchParams.has(p)) {\n u.searchParams.delete(p);\n changed = true;\n }\n });\n return changed ? u.toString() : url;\n } catch (e) {\n return url;\n }\n }\n \n function cleanLinks() {\n document.querySelectorAll('a[href]').forEach(function(a) {\n var clean = cleanUrl(a.href);\n if (clean !== a.href) a.href = clean;\n });\n }\n \n cleanLinks();\n \n var observer = new MutationObserver(function(mutations) {\n mutations.forEach(function(m) {\n m.addedNodes.forEach(function(node) {\n if (node.nodeType === 1) {\n if (node.tagName === 'A') cleanLinks();\n node.querySelectorAll('a[href]').forEach(function(a) {\n var clean = cleanUrl(a.href);\n if (clean !== a.href) a.href = clean;\n });\n }\n });\n });\n });\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Remove Tracking Parameters from Links");
}
} catch(__e) { console.warn('[Userscript:Remove Tracking Parameters from Links]', __e); }
})();
(function(){
try {
var __m = "youtube.com";
var __re = new RegExp('^' + "youtube\\.com" + '

Skip to content
GH-35033: [Java] [Datasets] Add support for multi-file datasets from Java#35034

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

lidavidm
merged 7 commits into

from

Jun 2, 2023
 Merged


GH-35033: [Java] [Datasets] Add support for multi-file datasets from Java
#35034
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


7 commits


Select commit
Hold shift + click to select a range
d48991e

Add support for multi-file datasets from Java


noahfrn Apr 11, 2023
f006299

Better error message for unrecognized URI + test


noahfrn Apr 12, 2023
f2dcdf8

Handle empty URI array


noahfrn Apr 13, 2023
3e71957

Fix lint


noahfrn Apr 13, 2023
34c68a9

Merge remote-tracking branch 'origin' into multifile-datasets-java


noahfrn May 20, 2023
8b7ffdb

Additional test, and clean up implementation


noahfrn Jun 2, 2023
920be7e

Merge branch 'main' into multifile-datasets-java


noahfrn Jun 2, 2023

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


48 changes: 47 additions & 1 deletion
java/dataset/src/main/cpp/jni_wrapper.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -16,6 +16,7 @@
// under the License.

#include <mutex>
#include <utility>
#include <unordered_map>

#include "arrow/array.h"
Expand All@@ -25,6 +26,7 @@
#include "arrow/dataset/api.h"
#include "arrow/dataset/file_base.h"
#include "arrow/filesystem/localfs.h"
#include "arrow/filesystem/path_util.h"
#include "arrow/engine/substrait/util.h"
#include "arrow/ipc/api.h"
#include "arrow/util/iterator.h"
Expand DownExpand Up@@ -569,7 +571,7 @@ JNIEXPORT void JNICALL Java_org_apache_arrow_dataset_jni_JniWrapper_releaseBuffe
 * Signature: (Ljava/lang/String;II)J
 */
JNIEXPORT jlong JNICALL
Java_org_apache_arrow_dataset_file_JniWrapper_makeFileSystemDatasetFactory(
Java_org_apache_arrow_dataset_file_JniWrapper_makeFileSystemDatasetFactory__Ljava_lang_String_2I(
 JNIEnv* env, jobject, jstring uri, jint file_format_id) {
 JNI_METHOD_START
 std::shared_ptr<arrow::dataset::FileFormat> file_format =
Expand All@@ -582,6 +584,50 @@ Java_org_apache_arrow_dataset_file_JniWrapper_makeFileSystemDatasetFactory(
 JNI_METHOD_END(-1L)
}

/*
 * Class: org_apache_arrow_dataset_file_JniWrapper
 * Method: makeFileSystemDatasetFactory
 * Signature: ([Ljava/lang/String;II)J
 */
JNIEXPORT jlong JNICALL
Java_org_apache_arrow_dataset_file_JniWrapper_makeFileSystemDatasetFactory___3Ljava_lang_String_2I(
 JNIEnv* env, jobject, jobjectArray uris, jint file_format_id) {
 JNI_METHOD_START

 std::shared_ptr<arrow::dataset::FileFormat> file_format =
 JniGetOrThrow(GetFileFormat(file_format_id));
 arrow::dataset::FileSystemFactoryOptions options;

 std::vector<std::string> uri_vec = ToStringVector(env, uris);
 if (uri_vec.size() == 0) {
 JniThrow("No URIs provided.");
 }

 // If not all URIs, throw exception
Comment thread
noahfrn marked this conversation as resolved.

 if (auto elem = std::find_if_not(uri_vec.begin(), uri_vec.end(), arrow::fs::internal::IsLikelyUri);
 elem != uri_vec.end()) {
 JniThrow("Unrecognized file type in URI: " + *elem);
 }

 std::vector<std::string> output_paths;
 std::string first_path;
 // We know that uri_vec isn't empty, from the conditional above
 auto fs = JniGetOrThrow(arrow::fs::FileSystemFromUri(uri_vec[0], &first_path));
 output_paths.push_back(first_path);

 std::transform(uri_vec.begin() + 1, uri_vec.end(), std::back_inserter(output_paths),
 [&](const auto& s) -> std::string {
 auto result = JniGetOrThrow(fs->PathFromUri(s));
 return std::move(result);
 });

 std::shared_ptr<arrow::dataset::DatasetFactory> d =
 JniGetOrThrow(arrow::dataset::FileSystemDatasetFactory::Make(
 std::move(fs), std::move(output_paths), file_format, options));
 return CreateNativeRef(d);
 JNI_METHOD_END(-1L)
}

/*
 * Class: org_apache_arrow_dataset_file_JniWrapper
 * Method: writeFromScannerToFile
Expand Down

9 changes: 9 additions & 0 deletions
java/dataset/src/main/java/org/apache/arrow/dataset/file/FileSystemDatasetFactory.java

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -31,8 +31,17 @@ public FileSystemDatasetFactory(BufferAllocator allocator, NativeMemoryPool memo
 super(allocator, memoryPool, createNative(format, uri));
 }

 public FileSystemDatasetFactory(BufferAllocator allocator, NativeMemoryPool memoryPool, FileFormat format,
 String[] uris) {
 super(allocator, memoryPool, createNative(format, uris));
 }

 private static long createNative(FileFormat format, String uri) {
 return JniWrapper.get().makeFileSystemDatasetFactory(uri, format.id());
 }

 private static long createNative(FileFormat format, String[] uris) {
 return JniWrapper.get().makeFileSystemDatasetFactory(uris, format.id());
 }

}

13 changes: 12 additions & 1 deletion
java/dataset/src/main/java/org/apache/arrow/dataset/file/JniWrapper.java

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -25,7 +25,7 @@
public class JniWrapper {

 private static final JniWrapper INSTANCE = new JniWrapper();

 public static JniWrapper get() {
 JniLoader.get().ensureLoaded();
 return INSTANCE;
Expand All@@ -45,6 +45,17 @@ private JniWrapper() {
 */
 public native long makeFileSystemDatasetFactory(String uri, int fileFormat);

 /**
 * Create FileSystemDatasetFactory and return its native pointer. The pointer is pointing to a
 * intermediate shared_ptr of the factory instance.
 *
 * @param uris List of file uris to read, each path pointing to an individual file
Comment thread
lidavidm marked this conversation as resolved.

 * @param fileFormat file format ID
 * @return the native pointer of the arrow::dataset::FileSystemDatasetFactory instance.
 * @see FileFormat
 */
 public native long makeFileSystemDatasetFactory(String[] uris, int fileFormat);

 /**
 * Write the content in a {@link org.apache.arrow.c.ArrowArrayStream} into files. This internally
 * depends on C++ write API: FileSystemDataset::Write.
Expand Down

43 changes: 43 additions & 0 deletions
java/dataset/src/test/java/org/apache/arrow/dataset/file/TestFileSystemDataset.java

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -101,6 +101,49 @@ public void testBaseParquetRead() throws Exception {
 AutoCloseables.close(factory);
 }

 @Test
 public void testMultipleParquetReadFromUris() throws Exception {
 ParquetWriteSupport writeSupport1 = ParquetWriteSupport.writeTempFile(AVRO_SCHEMA_USER, TMP.newFolder(),
 1, "a");
 ParquetWriteSupport writeSupport2 = ParquetWriteSupport.writeTempFile(AVRO_SCHEMA_USER, TMP.newFolder(),
 2, "b");
 String expectedJsonUnordered = "[[1,\"a\"],[2,\"b\"]]";

 ScanOptions options = new ScanOptions(1);
 FileSystemDatasetFactory factory = new FileSystemDatasetFactory(rootAllocator(), NativeMemoryPool.getDefault(),
 FileFormat.PARQUET, new String[]{writeSupport1.getOutputURI(), writeSupport2.getOutputURI()});
 Schema schema = inferResultSchemaFromFactory(factory, options);
 List<ArrowRecordBatch> datum = collectResultFromFactory(factory, options);

 assertScanBatchesProduced(factory, options);
 assertEquals(2, datum.size());
 datum.forEach(batch -> assertEquals(1, batch.getLength()));
 checkParquetReadResult(schema, expectedJsonUnordered, datum);

 AutoCloseables.close(datum);
 AutoCloseables.close(factory);
 }


 @Test
 public void testMultipleParquetInvalidUri() throws Exception {
 RuntimeException exc = assertThrows(RuntimeException.class,
 () -> new FileSystemDatasetFactory(rootAllocator(), NativeMemoryPool.getDefault(),
 FileFormat.PARQUET, new String[]{"https://example.com", "file:///test/location"}));
 Assertions.assertEquals("Unrecognized filesystem type in URI: https://example.com", exc.getMessage());
 }

 @Test
 public void testMultipleParquetMultipleFilesystemTypes() throws Exception {
 RuntimeException exc = assertThrows(RuntimeException.class,
 () -> new FileSystemDatasetFactory(rootAllocator(), NativeMemoryPool.getDefault(),
 FileFormat.PARQUET, new String[]{"file:///test/location", "s3:///test/bucket/file" }));
 Assertions.assertTrue(
 exc.getMessage().startsWith("The filesystem expected a URI with one of the schemes (file) but received s3"
 )
 );
 }
@davisusanibardavisusanibarApr 11, 2023

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Could be possible to add testing for exception throws: (1) Invalid URI , (2) ensure that they all share a FileSystem type

 @Test
 public void testParquetProjectSingleColumn() throws Exception {
 ParquetWriteSupport writeSupport = ParquetWriteSupport.writeTempFile(AVRO_SCHEMA_USER, TMP.newFolder(), 1, "a");
Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Auto-enable theater mode on YouTube\n(function() {\n function tryTheater() {\n var btn = document.querySelector('button[aria-label=\"Theater mode\"], ytd-player #player button[title=\"Theater mode\"]');\n if (btn && !btn.classList.contains('activated')) {\n btn.click();\n }\n }\n \n // Try immediately\n tryTheater();\n \n // Try after navigation (SPA)\n var lastUrl = location.href;\n setInterval(function() {\n if (location.href !== lastUrl) {\n lastUrl = location.href;\n setTimeout(tryTheater, 500);\n }\n }, 1000);\n \n // Also try on player load\n var observer = new MutationObserver(tryTheater);\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "YouTube Theater Mode Default");
}
} catch(__e) { console.warn('[Userscript:YouTube Theater Mode Default]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
GH-35033: [Java] [Datasets] Add support for multi-file datasets from Java#35034

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

lidavidm
merged 7 commits into

from

Jun 2, 2023
 Merged


GH-35033: [Java] [Datasets] Add support for multi-file datasets from Java
#35034
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


7 commits


Select commit
Hold shift + click to select a range
d48991e

Add support for multi-file datasets from Java


noahfrn Apr 11, 2023
f006299

Better error message for unrecognized URI + test


noahfrn Apr 12, 2023
f2dcdf8

Handle empty URI array


noahfrn Apr 13, 2023
3e71957

Fix lint


noahfrn Apr 13, 2023
34c68a9

Merge remote-tracking branch 'origin' into multifile-datasets-java


noahfrn May 20, 2023
8b7ffdb

Additional test, and clean up implementation


noahfrn Jun 2, 2023
920be7e

Merge branch 'main' into multifile-datasets-java


noahfrn Jun 2, 2023

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


48 changes: 47 additions & 1 deletion
java/dataset/src/main/cpp/jni_wrapper.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -16,6 +16,7 @@
// under the License.

#include <mutex>
#include <utility>
#include <unordered_map>

#include "arrow/array.h"
Expand All@@ -25,6 +26,7 @@
#include "arrow/dataset/api.h"
#include "arrow/dataset/file_base.h"
#include "arrow/filesystem/localfs.h"
#include "arrow/filesystem/path_util.h"
#include "arrow/engine/substrait/util.h"
#include "arrow/ipc/api.h"
#include "arrow/util/iterator.h"
Expand DownExpand Up@@ -569,7 +571,7 @@ JNIEXPORT void JNICALL Java_org_apache_arrow_dataset_jni_JniWrapper_releaseBuffe
 * Signature: (Ljava/lang/String;II)J
 */
JNIEXPORT jlong JNICALL
Java_org_apache_arrow_dataset_file_JniWrapper_makeFileSystemDatasetFactory(
Java_org_apache_arrow_dataset_file_JniWrapper_makeFileSystemDatasetFactory__Ljava_lang_String_2I(
 JNIEnv* env, jobject, jstring uri, jint file_format_id) {
 JNI_METHOD_START
 std::shared_ptr<arrow::dataset::FileFormat> file_format =
Expand All@@ -582,6 +584,50 @@ Java_org_apache_arrow_dataset_file_JniWrapper_makeFileSystemDatasetFactory(
 JNI_METHOD_END(-1L)
}

/*
 * Class: org_apache_arrow_dataset_file_JniWrapper
 * Method: makeFileSystemDatasetFactory
 * Signature: ([Ljava/lang/String;II)J
 */
JNIEXPORT jlong JNICALL
Java_org_apache_arrow_dataset_file_JniWrapper_makeFileSystemDatasetFactory___3Ljava_lang_String_2I(
 JNIEnv* env, jobject, jobjectArray uris, jint file_format_id) {
 JNI_METHOD_START

 std::shared_ptr<arrow::dataset::FileFormat> file_format =
 JniGetOrThrow(GetFileFormat(file_format_id));
 arrow::dataset::FileSystemFactoryOptions options;

 std::vector<std::string> uri_vec = ToStringVector(env, uris);
 if (uri_vec.size() == 0) {
 JniThrow("No URIs provided.");
 }

 // If not all URIs, throw exception
Comment thread
noahfrn marked this conversation as resolved.

 if (auto elem = std::find_if_not(uri_vec.begin(), uri_vec.end(), arrow::fs::internal::IsLikelyUri);
 elem != uri_vec.end()) {
 JniThrow("Unrecognized file type in URI: " + *elem);
 }

 std::vector<std::string> output_paths;
 std::string first_path;
 // We know that uri_vec isn't empty, from the conditional above
 auto fs = JniGetOrThrow(arrow::fs::FileSystemFromUri(uri_vec[0], &first_path));
 output_paths.push_back(first_path);

 std::transform(uri_vec.begin() + 1, uri_vec.end(), std::back_inserter(output_paths),
 [&](const auto& s) -> std::string {
 auto result = JniGetOrThrow(fs->PathFromUri(s));
 return std::move(result);
 });

 std::shared_ptr<arrow::dataset::DatasetFactory> d =
 JniGetOrThrow(arrow::dataset::FileSystemDatasetFactory::Make(
 std::move(fs), std::move(output_paths), file_format, options));
 return CreateNativeRef(d);
 JNI_METHOD_END(-1L)
}

/*
 * Class: org_apache_arrow_dataset_file_JniWrapper
 * Method: writeFromScannerToFile
Expand Down

9 changes: 9 additions & 0 deletions
java/dataset/src/main/java/org/apache/arrow/dataset/file/FileSystemDatasetFactory.java

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -31,8 +31,17 @@ public FileSystemDatasetFactory(BufferAllocator allocator, NativeMemoryPool memo
 super(allocator, memoryPool, createNative(format, uri));
 }

 public FileSystemDatasetFactory(BufferAllocator allocator, NativeMemoryPool memoryPool, FileFormat format,
 String[] uris) {
 super(allocator, memoryPool, createNative(format, uris));
 }

 private static long createNative(FileFormat format, String uri) {
 return JniWrapper.get().makeFileSystemDatasetFactory(uri, format.id());
 }

 private static long createNative(FileFormat format, String[] uris) {
 return JniWrapper.get().makeFileSystemDatasetFactory(uris, format.id());
 }

}

13 changes: 12 additions & 1 deletion
java/dataset/src/main/java/org/apache/arrow/dataset/file/JniWrapper.java

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -25,7 +25,7 @@
public class JniWrapper {

 private static final JniWrapper INSTANCE = new JniWrapper();

 public static JniWrapper get() {
 JniLoader.get().ensureLoaded();
 return INSTANCE;
Expand All@@ -45,6 +45,17 @@ private JniWrapper() {
 */
 public native long makeFileSystemDatasetFactory(String uri, int fileFormat);

 /**
 * Create FileSystemDatasetFactory and return its native pointer. The pointer is pointing to a
 * intermediate shared_ptr of the factory instance.
 *
 * @param uris List of file uris to read, each path pointing to an individual file
Comment thread
lidavidm marked this conversation as resolved.

 * @param fileFormat file format ID
 * @return the native pointer of the arrow::dataset::FileSystemDatasetFactory instance.
 * @see FileFormat
 */
 public native long makeFileSystemDatasetFactory(String[] uris, int fileFormat);

 /**
 * Write the content in a {@link org.apache.arrow.c.ArrowArrayStream} into files. This internally
 * depends on C++ write API: FileSystemDataset::Write.
Expand Down

43 changes: 43 additions & 0 deletions
java/dataset/src/test/java/org/apache/arrow/dataset/file/TestFileSystemDataset.java

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -101,6 +101,49 @@ public void testBaseParquetRead() throws Exception {
 AutoCloseables.close(factory);
 }

 @Test
 public void testMultipleParquetReadFromUris() throws Exception {
 ParquetWriteSupport writeSupport1 = ParquetWriteSupport.writeTempFile(AVRO_SCHEMA_USER, TMP.newFolder(),
 1, "a");
 ParquetWriteSupport writeSupport2 = ParquetWriteSupport.writeTempFile(AVRO_SCHEMA_USER, TMP.newFolder(),
 2, "b");
 String expectedJsonUnordered = "[[1,\"a\"],[2,\"b\"]]";

 ScanOptions options = new ScanOptions(1);
 FileSystemDatasetFactory factory = new FileSystemDatasetFactory(rootAllocator(), NativeMemoryPool.getDefault(),
 FileFormat.PARQUET, new String[]{writeSupport1.getOutputURI(), writeSupport2.getOutputURI()});
 Schema schema = inferResultSchemaFromFactory(factory, options);
 List<ArrowRecordBatch> datum = collectResultFromFactory(factory, options);

 assertScanBatchesProduced(factory, options);
 assertEquals(2, datum.size());
 datum.forEach(batch -> assertEquals(1, batch.getLength()));
 checkParquetReadResult(schema, expectedJsonUnordered, datum);

 AutoCloseables.close(datum);
 AutoCloseables.close(factory);
 }


 @Test
 public void testMultipleParquetInvalidUri() throws Exception {
 RuntimeException exc = assertThrows(RuntimeException.class,
 () -> new FileSystemDatasetFactory(rootAllocator(), NativeMemoryPool.getDefault(),
 FileFormat.PARQUET, new String[]{"https://example.com", "file:///test/location"}));
 Assertions.assertEquals("Unrecognized filesystem type in URI: https://example.com", exc.getMessage());
 }

 @Test
 public void testMultipleParquetMultipleFilesystemTypes() throws Exception {
 RuntimeException exc = assertThrows(RuntimeException.class,
 () -> new FileSystemDatasetFactory(rootAllocator(), NativeMemoryPool.getDefault(),
 FileFormat.PARQUET, new String[]{"file:///test/location", "s3:///test/bucket/file" }));
 Assertions.assertTrue(
 exc.getMessage().startsWith("The filesystem expected a URI with one of the schemes (file) but received s3"
 )
 );
 }
@davisusanibardavisusanibarApr 11, 2023

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Could be possible to add testing for exception throws: (1) Invalid URI , (2) ensure that they all share a FileSystem type

 @Test
 public void testParquetProjectSingleColumn() throws Exception {
 ParquetWriteSupport writeSupport = ParquetWriteSupport.writeTempFile(AVRO_SCHEMA_USER, TMP.newFolder(), 1, "a");
Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Remove or un-stick sticky/fixed headers that block content\n(function() {\n function unstick() {\n document.querySelectorAll('header, nav, [role=\"banner\"], .header, .navbar, .sticky, .fixed-top, [style*=\"position: fixed\"], [style*=\"position:sticky\"]').forEach(function(el) {\n if (el.style.position === 'fixed' || el.style.position === 'sticky' || \n getComputedStyle(el).position === 'fixed' || getComputedStyle(el).position === 'sticky') {\n el.style.position = 'static';\n el.style.top = 'auto';\n el.style.zIndex = 'auto';\n }\n });\n }\n \n unstick();\n \n var observer = new MutationObserver(unstick);\n observer.observe(document.body, { childList: true, subtree: true, attributes: true, attributeFilter: ['style', 'class'] });\n})();", "Kill Sticky Headers");
}
} catch(__e) { console.warn('[Userscript:Kill Sticky Headers]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
GH-35033: [Java] [Datasets] Add support for multi-file datasets from Java#35034

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

lidavidm
merged 7 commits into

from

Jun 2, 2023
 Merged


GH-35033: [Java] [Datasets] Add support for multi-file datasets from Java
#35034
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


7 commits


Select commit
Hold shift + click to select a range
d48991e

Add support for multi-file datasets from Java


noahfrn Apr 11, 2023
f006299

Better error message for unrecognized URI + test


noahfrn Apr 12, 2023
f2dcdf8

Handle empty URI array


noahfrn Apr 13, 2023
3e71957

Fix lint


noahfrn Apr 13, 2023
34c68a9

Merge remote-tracking branch 'origin' into multifile-datasets-java


noahfrn May 20, 2023
8b7ffdb

Additional test, and clean up implementation


noahfrn Jun 2, 2023
920be7e

Merge branch 'main' into multifile-datasets-java


noahfrn Jun 2, 2023

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


48 changes: 47 additions & 1 deletion
java/dataset/src/main/cpp/jni_wrapper.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -16,6 +16,7 @@
// under the License.

#include <mutex>
#include <utility>
#include <unordered_map>

#include "arrow/array.h"
Expand All@@ -25,6 +26,7 @@
#include "arrow/dataset/api.h"
#include "arrow/dataset/file_base.h"
#include "arrow/filesystem/localfs.h"
#include "arrow/filesystem/path_util.h"
#include "arrow/engine/substrait/util.h"
#include "arrow/ipc/api.h"
#include "arrow/util/iterator.h"
Expand DownExpand Up@@ -569,7 +571,7 @@ JNIEXPORT void JNICALL Java_org_apache_arrow_dataset_jni_JniWrapper_releaseBuffe
 * Signature: (Ljava/lang/String;II)J
 */
JNIEXPORT jlong JNICALL
Java_org_apache_arrow_dataset_file_JniWrapper_makeFileSystemDatasetFactory(
Java_org_apache_arrow_dataset_file_JniWrapper_makeFileSystemDatasetFactory__Ljava_lang_String_2I(
 JNIEnv* env, jobject, jstring uri, jint file_format_id) {
 JNI_METHOD_START
 std::shared_ptr<arrow::dataset::FileFormat> file_format =
Expand All@@ -582,6 +584,50 @@ Java_org_apache_arrow_dataset_file_JniWrapper_makeFileSystemDatasetFactory(
 JNI_METHOD_END(-1L)
}

/*
 * Class: org_apache_arrow_dataset_file_JniWrapper
 * Method: makeFileSystemDatasetFactory
 * Signature: ([Ljava/lang/String;II)J
 */
JNIEXPORT jlong JNICALL
Java_org_apache_arrow_dataset_file_JniWrapper_makeFileSystemDatasetFactory___3Ljava_lang_String_2I(
 JNIEnv* env, jobject, jobjectArray uris, jint file_format_id) {
 JNI_METHOD_START

 std::shared_ptr<arrow::dataset::FileFormat> file_format =
 JniGetOrThrow(GetFileFormat(file_format_id));
 arrow::dataset::FileSystemFactoryOptions options;

 std::vector<std::string> uri_vec = ToStringVector(env, uris);
 if (uri_vec.size() == 0) {
 JniThrow("No URIs provided.");
 }

 // If not all URIs, throw exception
Comment thread
noahfrn marked this conversation as resolved.

 if (auto elem = std::find_if_not(uri_vec.begin(), uri_vec.end(), arrow::fs::internal::IsLikelyUri);
 elem != uri_vec.end()) {
 JniThrow("Unrecognized file type in URI: " + *elem);
 }

 std::vector<std::string> output_paths;
 std::string first_path;
 // We know that uri_vec isn't empty, from the conditional above
 auto fs = JniGetOrThrow(arrow::fs::FileSystemFromUri(uri_vec[0], &first_path));
 output_paths.push_back(first_path);

 std::transform(uri_vec.begin() + 1, uri_vec.end(), std::back_inserter(output_paths),
 [&](const auto& s) -> std::string {
 auto result = JniGetOrThrow(fs->PathFromUri(s));
 return std::move(result);
 });

 std::shared_ptr<arrow::dataset::DatasetFactory> d =
 JniGetOrThrow(arrow::dataset::FileSystemDatasetFactory::Make(
 std::move(fs), std::move(output_paths), file_format, options));
 return CreateNativeRef(d);
 JNI_METHOD_END(-1L)
}

/*
 * Class: org_apache_arrow_dataset_file_JniWrapper
 * Method: writeFromScannerToFile
Expand Down

9 changes: 9 additions & 0 deletions
java/dataset/src/main/java/org/apache/arrow/dataset/file/FileSystemDatasetFactory.java

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -31,8 +31,17 @@ public FileSystemDatasetFactory(BufferAllocator allocator, NativeMemoryPool memo
 super(allocator, memoryPool, createNative(format, uri));
 }

 public FileSystemDatasetFactory(BufferAllocator allocator, NativeMemoryPool memoryPool, FileFormat format,
 String[] uris) {
 super(allocator, memoryPool, createNative(format, uris));
 }

 private static long createNative(FileFormat format, String uri) {
 return JniWrapper.get().makeFileSystemDatasetFactory(uri, format.id());
 }

 private static long createNative(FileFormat format, String[] uris) {
 return JniWrapper.get().makeFileSystemDatasetFactory(uris, format.id());
 }

}

13 changes: 12 additions & 1 deletion
java/dataset/src/main/java/org/apache/arrow/dataset/file/JniWrapper.java

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -25,7 +25,7 @@
public class JniWrapper {

 private static final JniWrapper INSTANCE = new JniWrapper();

 public static JniWrapper get() {
 JniLoader.get().ensureLoaded();
 return INSTANCE;
Expand All@@ -45,6 +45,17 @@ private JniWrapper() {
 */
 public native long makeFileSystemDatasetFactory(String uri, int fileFormat);

 /**
 * Create FileSystemDatasetFactory and return its native pointer. The pointer is pointing to a
 * intermediate shared_ptr of the factory instance.
 *
 * @param uris List of file uris to read, each path pointing to an individual file
Comment thread
lidavidm marked this conversation as resolved.

 * @param fileFormat file format ID
 * @return the native pointer of the arrow::dataset::FileSystemDatasetFactory instance.
 * @see FileFormat
 */
 public native long makeFileSystemDatasetFactory(String[] uris, int fileFormat);

 /**
 * Write the content in a {@link org.apache.arrow.c.ArrowArrayStream} into files. This internally
 * depends on C++ write API: FileSystemDataset::Write.
Expand Down

43 changes: 43 additions & 0 deletions
java/dataset/src/test/java/org/apache/arrow/dataset/file/TestFileSystemDataset.java

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -101,6 +101,49 @@ public void testBaseParquetRead() throws Exception {
 AutoCloseables.close(factory);
 }

 @Test
 public void testMultipleParquetReadFromUris() throws Exception {
 ParquetWriteSupport writeSupport1 = ParquetWriteSupport.writeTempFile(AVRO_SCHEMA_USER, TMP.newFolder(),
 1, "a");
 ParquetWriteSupport writeSupport2 = ParquetWriteSupport.writeTempFile(AVRO_SCHEMA_USER, TMP.newFolder(),
 2, "b");
 String expectedJsonUnordered = "[[1,\"a\"],[2,\"b\"]]";

 ScanOptions options = new ScanOptions(1);
 FileSystemDatasetFactory factory = new FileSystemDatasetFactory(rootAllocator(), NativeMemoryPool.getDefault(),
 FileFormat.PARQUET, new String[]{writeSupport1.getOutputURI(), writeSupport2.getOutputURI()});
 Schema schema = inferResultSchemaFromFactory(factory, options);
 List<ArrowRecordBatch> datum = collectResultFromFactory(factory, options);

 assertScanBatchesProduced(factory, options);
 assertEquals(2, datum.size());
 datum.forEach(batch -> assertEquals(1, batch.getLength()));
 checkParquetReadResult(schema, expectedJsonUnordered, datum);

 AutoCloseables.close(datum);
 AutoCloseables.close(factory);
 }


 @Test
 public void testMultipleParquetInvalidUri() throws Exception {
 RuntimeException exc = assertThrows(RuntimeException.class,
 () -> new FileSystemDatasetFactory(rootAllocator(), NativeMemoryPool.getDefault(),
 FileFormat.PARQUET, new String[]{"https://example.com", "file:///test/location"}));
 Assertions.assertEquals("Unrecognized filesystem type in URI: https://example.com", exc.getMessage());
 }

 @Test
 public void testMultipleParquetMultipleFilesystemTypes() throws Exception {
 RuntimeException exc = assertThrows(RuntimeException.class,
 () -> new FileSystemDatasetFactory(rootAllocator(), NativeMemoryPool.getDefault(),
 FileFormat.PARQUET, new String[]{"file:///test/location", "s3:///test/bucket/file" }));
 Assertions.assertTrue(
 exc.getMessage().startsWith("The filesystem expected a URI with one of the schemes (file) but received s3"
 )
 );
 }
@davisusanibardavisusanibarApr 11, 2023

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Could be possible to add testing for exception throws: (1) Invalid URI , (2) ensure that they all share a FileSystem type

 @Test
 public void testParquetProjectSingleColumn() throws Exception {
 ParquetWriteSupport writeSupport = ParquetWriteSupport.writeTempFile(AVRO_SCHEMA_USER, TMP.newFolder(), 1, "a");
Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Universal Dark Mode - works on any site\n(function() {\n var enabled = true;\n \n function applyDarkMode() {\n if (!enabled) return;\n \n // Create style element if it doesn't exist\n var style = document.getElementById('universal-dark-mode-style');\n if (!style) {\n style = document.createElement('style');\n style.id = 'universal-dark-mode-style';\n document.head.appendChild(style);\n }\n \n // Dark mode CSS - inverts colors but preserves images/video\n style.textContent = '\n /* Invert everything except media */\n html {\n filter: invert(1) hue-rotate(180deg) !important;\n background: #1a1a2e !important;\n }\n \n /* Restore images, videos, iframes, canvas */\n img, video, iframe, canvas, svg, picture, [style*=\"background-image\"] {\n filter: invert(1) hue-rotate(180deg) !important;\n }\n \n /* Preserve specific elements that should not be inverted */\n .no-dark-mode, .no-dark-mode *,\n [data-theme=\"light\"], [data-theme=\"light\"],\n .ace_editor, .ace_editor *,\n .CodeMirror, .CodeMirror *,\n .monaco-editor, .monaco-editor *,\n .markdown-body pre, .markdown-body pre *,\n .highlight, .highlight *,\n pre code, pre code * {\n filter: none !important;\n }\n \n /* Fix common UI elements */\n .modal, .popup, .dropdown-menu, .tooltip, .popover {\n filter: invert(1) hue-rotate(180deg) !important;\n background: #2d2d44 !important;\n border-color: #444 !important;\n }\n \n /* Scrollbars */\n ::-webkit-scrollbar { background: #1a1a2e !important; }\n ::-webkit-scrollbar-thumb { background: #444 !important; }\n ::-webkit-scrollbar-thumb:hover { background: #555 !important; }\n \n /* Selection */\n ::selection { background: #4ecdc4 !important; color: #1a1a2e !important; }\n ::-moz-selection { background: #4ecdc4 !important; color: #1a1a2e !important; }\n ';\n }\n \n function removeDarkMode() {\n var style = document.getElementById('universal-dark-mode-style');\n if (style) style.remove();\n }\n \n // Toggle with Alt+Shift+D\n document.addEventListener('keydown', function(e) {\n if (e.altKey && e.shiftKey && e.key === 'D') {\n e.preventDefault();\n enabled = !enabled;\n if (enabled) {\n applyDarkMode();\n console.log('[Universal Dark Mode] Enabled');\n } else {\n removeDarkMode();\n console.log('[Universal Dark Mode] Disabled');\n }\n }\n });\n \n // Apply on load\n applyDarkMode();\n \n // Re-apply on dynamic content\n var observer = new MutationObserver(function(mutations) {\n if (enabled && !document.getElementById('universal-dark-mode-style')) {\n applyDarkMode();\n }\n });\n observer.observe(document.head, { childList: true });\n \n console.log('[Universal Dark Mode] Loaded - Press Alt+Shift+D to toggle');\n})();", "Universal Dark Mode");
}
} catch(__e) { console.warn('[Userscript:Universal Dark Mode]', __e); }
})();
})();

Skip to content
GH-35033: [Java] [Datasets] Add support for multi-file datasets from Java#35034

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

lidavidm
merged 7 commits into

from

Jun 2, 2023
 Merged


GH-35033: [Java] [Datasets] Add support for multi-file datasets from Java
#35034
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


7 commits


Select commit
Hold shift + click to select a range
d48991e

Add support for multi-file datasets from Java


noahfrn Apr 11, 2023
f006299

Better error message for unrecognized URI + test


noahfrn Apr 12, 2023
f2dcdf8

Handle empty URI array


noahfrn Apr 13, 2023
3e71957

Fix lint


noahfrn Apr 13, 2023
34c68a9

Merge remote-tracking branch 'origin' into multifile-datasets-java


noahfrn May 20, 2023
8b7ffdb

Additional test, and clean up implementation


noahfrn Jun 2, 2023
920be7e

Merge branch 'main' into multifile-datasets-java


noahfrn Jun 2, 2023

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


48 changes: 47 additions & 1 deletion
java/dataset/src/main/cpp/jni_wrapper.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -16,6 +16,7 @@
// under the License.

#include <mutex>
#include <utility>
#include <unordered_map>

#include "arrow/array.h"
Expand All@@ -25,6 +26,7 @@
#include "arrow/dataset/api.h"
#include "arrow/dataset/file_base.h"
#include "arrow/filesystem/localfs.h"
#include "arrow/filesystem/path_util.h"
#include "arrow/engine/substrait/util.h"
#include "arrow/ipc/api.h"
#include "arrow/util/iterator.h"
Expand DownExpand Up@@ -569,7 +571,7 @@ JNIEXPORT void JNICALL Java_org_apache_arrow_dataset_jni_JniWrapper_releaseBuffe
 * Signature: (Ljava/lang/String;II)J
 */
JNIEXPORT jlong JNICALL
Java_org_apache_arrow_dataset_file_JniWrapper_makeFileSystemDatasetFactory(
Java_org_apache_arrow_dataset_file_JniWrapper_makeFileSystemDatasetFactory__Ljava_lang_String_2I(
 JNIEnv* env, jobject, jstring uri, jint file_format_id) {
 JNI_METHOD_START
 std::shared_ptr<arrow::dataset::FileFormat> file_format =
Expand All@@ -582,6 +584,50 @@ Java_org_apache_arrow_dataset_file_JniWrapper_makeFileSystemDatasetFactory(
 JNI_METHOD_END(-1L)
}

/*
 * Class: org_apache_arrow_dataset_file_JniWrapper
 * Method: makeFileSystemDatasetFactory
 * Signature: ([Ljava/lang/String;II)J
 */
JNIEXPORT jlong JNICALL
Java_org_apache_arrow_dataset_file_JniWrapper_makeFileSystemDatasetFactory___3Ljava_lang_String_2I(
 JNIEnv* env, jobject, jobjectArray uris, jint file_format_id) {
 JNI_METHOD_START

 std::shared_ptr<arrow::dataset::FileFormat> file_format =
 JniGetOrThrow(GetFileFormat(file_format_id));
 arrow::dataset::FileSystemFactoryOptions options;

 std::vector<std::string> uri_vec = ToStringVector(env, uris);
 if (uri_vec.size() == 0) {
 JniThrow("No URIs provided.");
 }

 // If not all URIs, throw exception
Comment thread
noahfrn marked this conversation as resolved.

 if (auto elem = std::find_if_not(uri_vec.begin(), uri_vec.end(), arrow::fs::internal::IsLikelyUri);
 elem != uri_vec.end()) {
 JniThrow("Unrecognized file type in URI: " + *elem);
 }

 std::vector<std::string> output_paths;
 std::string first_path;
 // We know that uri_vec isn't empty, from the conditional above
 auto fs = JniGetOrThrow(arrow::fs::FileSystemFromUri(uri_vec[0], &first_path));
 output_paths.push_back(first_path);

 std::transform(uri_vec.begin() + 1, uri_vec.end(), std::back_inserter(output_paths),
 [&](const auto& s) -> std::string {
 auto result = JniGetOrThrow(fs->PathFromUri(s));
 return std::move(result);
 });

 std::shared_ptr<arrow::dataset::DatasetFactory> d =
 JniGetOrThrow(arrow::dataset::FileSystemDatasetFactory::Make(
 std::move(fs), std::move(output_paths), file_format, options));
 return CreateNativeRef(d);
 JNI_METHOD_END(-1L)
}

/*
 * Class: org_apache_arrow_dataset_file_JniWrapper
 * Method: writeFromScannerToFile
Expand Down

9 changes: 9 additions & 0 deletions
java/dataset/src/main/java/org/apache/arrow/dataset/file/FileSystemDatasetFactory.java

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -31,8 +31,17 @@ public FileSystemDatasetFactory(BufferAllocator allocator, NativeMemoryPool memo
 super(allocator, memoryPool, createNative(format, uri));
 }

 public FileSystemDatasetFactory(BufferAllocator allocator, NativeMemoryPool memoryPool, FileFormat format,
 String[] uris) {
 super(allocator, memoryPool, createNative(format, uris));
 }

 private static long createNative(FileFormat format, String uri) {
 return JniWrapper.get().makeFileSystemDatasetFactory(uri, format.id());
 }

 private static long createNative(FileFormat format, String[] uris) {
 return JniWrapper.get().makeFileSystemDatasetFactory(uris, format.id());
 }

}

13 changes: 12 additions & 1 deletion
java/dataset/src/main/java/org/apache/arrow/dataset/file/JniWrapper.java

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -25,7 +25,7 @@
public class JniWrapper {

 private static final JniWrapper INSTANCE = new JniWrapper();

 public static JniWrapper get() {
 JniLoader.get().ensureLoaded();
 return INSTANCE;
Expand All@@ -45,6 +45,17 @@ private JniWrapper() {
 */
 public native long makeFileSystemDatasetFactory(String uri, int fileFormat);

 /**
 * Create FileSystemDatasetFactory and return its native pointer. The pointer is pointing to a
 * intermediate shared_ptr of the factory instance.
 *
 * @param uris List of file uris to read, each path pointing to an individual file
Comment thread
lidavidm marked this conversation as resolved.

 * @param fileFormat file format ID
 * @return the native pointer of the arrow::dataset::FileSystemDatasetFactory instance.
 * @see FileFormat
 */
 public native long makeFileSystemDatasetFactory(String[] uris, int fileFormat);

 /**
 * Write the content in a {@link org.apache.arrow.c.ArrowArrayStream} into files. This internally
 * depends on C++ write API: FileSystemDataset::Write.
Expand Down

43 changes: 43 additions & 0 deletions
java/dataset/src/test/java/org/apache/arrow/dataset/file/TestFileSystemDataset.java

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -101,6 +101,49 @@ public void testBaseParquetRead() throws Exception {
 AutoCloseables.close(factory);
 }

 @Test
 public void testMultipleParquetReadFromUris() throws Exception {
 ParquetWriteSupport writeSupport1 = ParquetWriteSupport.writeTempFile(AVRO_SCHEMA_USER, TMP.newFolder(),
 1, "a");
 ParquetWriteSupport writeSupport2 = ParquetWriteSupport.writeTempFile(AVRO_SCHEMA_USER, TMP.newFolder(),
 2, "b");
 String expectedJsonUnordered = "[[1,\"a\"],[2,\"b\"]]";

 ScanOptions options = new ScanOptions(1);
 FileSystemDatasetFactory factory = new FileSystemDatasetFactory(rootAllocator(), NativeMemoryPool.getDefault(),
 FileFormat.PARQUET, new String[]{writeSupport1.getOutputURI(), writeSupport2.getOutputURI()});
 Schema schema = inferResultSchemaFromFactory(factory, options);
 List<ArrowRecordBatch> datum = collectResultFromFactory(factory, options);

 assertScanBatchesProduced(factory, options);
 assertEquals(2, datum.size());
 datum.forEach(batch -> assertEquals(1, batch.getLength()));
 checkParquetReadResult(schema, expectedJsonUnordered, datum);

 AutoCloseables.close(datum);
 AutoCloseables.close(factory);
 }


 @Test
 public void testMultipleParquetInvalidUri() throws Exception {
 RuntimeException exc = assertThrows(RuntimeException.class,
 () -> new FileSystemDatasetFactory(rootAllocator(), NativeMemoryPool.getDefault(),
 FileFormat.PARQUET, new String[]{"https://example.com", "file:///test/location"}));
 Assertions.assertEquals("Unrecognized filesystem type in URI: https://example.com", exc.getMessage());
 }

 @Test
 public void testMultipleParquetMultipleFilesystemTypes() throws Exception {
 RuntimeException exc = assertThrows(RuntimeException.class,
 () -> new FileSystemDatasetFactory(rootAllocator(), NativeMemoryPool.getDefault(),
 FileFormat.PARQUET, new String[]{"file:///test/location", "s3:///test/bucket/file" }));
 Assertions.assertTrue(
 exc.getMessage().startsWith("The filesystem expected a URI with one of the schemes (file) but received s3"
 )
 );
 }
@davisusanibardavisusanibarApr 11, 2023

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Could be possible to add testing for exception throws: (1) Invalid URI , (2) ensure that they all share a FileSystem type

 @Test
 public void testParquetProjectSingleColumn() throws Exception {
 ParquetWriteSupport writeSupport = ParquetWriteSupport.writeTempFile(AVRO_SCHEMA_USER, TMP.newFolder(), 1, "a");
Expand Down