ARROW-15115: [C++] GcsFileSystem return errors if using closed streams#11976

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

Closed
coryan wants to merge 2 commits into from
Closed

ARROW-15115: [C++] GcsFileSystem return errors if using closed streams #11976

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
d211922
ARROW-15115: [C++] GcsFileSystem return errors if using closed streams
coryan Dec 16, 2021
6ab9447
Address review comments
coryan Dec 20, 2021
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
35 changes: 27 additions & 8 deletions cpp/src/arrow/filesystem/gcsfs.cc
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -96,28 +96,32 @@ class GcsInputStream : public arrow::io::InputStream {
// @name FileInterface
Status Close() override {
stream_.Close();
closed_ = true;
return Status::OK();
}

Result<int64_t> Tell() const override {
if (!stream_) {
return Status::IOError("invalid stream");
}
if (closed()) return Status::Invalid("Cannot use Tell() on a closed stream");
return stream_.tellg() + offset_;
}

bool closed() const override { return !stream_.IsOpen(); }
// A gcs::ObjectReadStream can be "born closed". For small objects the stream returns
// `IsOpen() == false` as soon as it is created, but the application can still read from
// it.
bool closed() const override { return closed_ && !stream_.IsOpen(); }

@pitroupitrouDec 20, 2021

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

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

Is there a reason this is && rather than ||?

@coryancoryanDec 20, 2021

Copy link
Copy Markdown
ContributorAuthor

Choose a reason for hiding this comment

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

Yes. zero-length objects are "born closed" in google-cloud-cpp. Probably a bug (or at least a very poorly thought API), but you can read() from them, while they return IsOpen() == false.

@pitroupitrouDec 20, 2021

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

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

Ah, can you add a comment about that?

@coryancoryanDec 20, 2021

Copy link
Copy Markdown
ContributorAuthor

Choose a reason for hiding this comment

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

Done. That got me thinking about the similar expression for output streams, and you were right in that case. Fixed that too.

//@}

//@{
// @name Readable
Result<int64_t> Read(int64_t nbytes, void* out) override {
if (closed()) return Status::Invalid("Cannot read from a closed stream");
stream_.read(static_cast<char*>(out), nbytes);
ARROW_GCS_RETURN_NOT_OK(stream_.status());
return stream_.gcount();
}

Result<std::shared_ptr<Buffer>> Read(int64_t nbytes) override {
if (closed()) return Status::Invalid("Cannot read from a closed stream");
ARROW_ASSIGN_OR_RAISE(auto buffer, arrow::AllocateResizableBuffer(nbytes));
stream_.read(reinterpret_cast<char*>(buffer->mutable_data()), nbytes);
ARROW_GCS_RETURN_NOT_OK(stream_.status());
Expand All@@ -142,6 +146,7 @@ class GcsInputStream : public arrow::io::InputStream {
gcs::Generation generation_;
std::int64_t offset_;
gcs::Client client_;
bool closed_ = false;
};

class GcsOutputStream : public arrow::io::OutputStream {
Expand All@@ -151,19 +156,28 @@ class GcsOutputStream : public arrow::io::OutputStream {

Status Close() override {
stream_.Close();
closed_ = true;
return internal::ToArrowStatus(stream_.last_status());
}

Result<int64_t> Tell() const override {
if (!stream_) {
return Status::IOError("invalid stream");
}
if (closed()) return Status::Invalid("Cannot use Tell() on a closed stream");
return tell_;
}

bool closed() const override { return !stream_.IsOpen(); }
// gcs::ObjectWriteStream can be "closed" without an explicit Close() call. At this time
// this class does not use any of the mechanisms [*] that trigger such behavior.
// Nevertheless, we defensively prepare for them by checking either condition.
//
// [*]: These mechanisms include:
// - resumable uploads that are "resumed" after the upload completed are born
// "closed",
// - uploads that prescribe their total size using the `x-upload-content-length` header
// are completed and "closed" as soon as the upload reaches that size.
bool closed() const override { return closed_ || !stream_.IsOpen(); }

Status Write(const void* data, int64_t nbytes) override {
if (closed()) return Status::Invalid("Cannot write to a closed stream");
if (stream_.write(reinterpret_cast<const char*>(data), nbytes)) {
tell_ += nbytes;
return Status::OK();
Expand All@@ -172,13 +186,15 @@ class GcsOutputStream : public arrow::io::OutputStream {
}

Status Flush() override {
if (closed()) return Status::Invalid("Cannot flush a closed stream");
stream_.flush();
return Status::OK();
}

private:
gcs::ObjectWriteStream stream_;
int64_t tell_ = 0;
bool closed_ = false;
};

using InputStreamFactory = std::function<Result<std::shared_ptr<io::InputStream>>(
Expand DownExpand Up@@ -225,13 +241,15 @@ class GcsRandomAccessFile : public arrow::io::RandomAccessFile {
// @name RandomAccessFile
Result<int64_t> GetSize() override { return metadata_.size(); }
Result<int64_t> ReadAt(int64_t position, int64_t nbytes, void* out) override {
if (closed()) return Status::Invalid("Cannot read from closed file");
std::shared_ptr<io::InputStream> stream;
ARROW_ASSIGN_OR_RAISE(stream, factory_(metadata_.bucket(), metadata_.name(),
gcs::Generation(metadata_.generation()),
gcs::ReadFromOffset(position)));
return stream->Read(nbytes, out);
}
Result<std::shared_ptr<Buffer>> ReadAt(int64_t position, int64_t nbytes) override {
if (closed()) return Status::Invalid("Cannot read from closed file");
std::shared_ptr<io::InputStream> stream;
ARROW_ASSIGN_OR_RAISE(stream, factory_(metadata_.bucket(), metadata_.name(),
gcs::Generation(metadata_.generation()),
Expand All@@ -242,6 +260,7 @@ class GcsRandomAccessFile : public arrow::io::RandomAccessFile {

// from Seekable
Status Seek(int64_t position) override {
if (closed()) return Status::Invalid("Cannot seek in a closed file");
ARROW_ASSIGN_OR_RAISE(stream_, factory_(metadata_.bucket(), metadata_.name(),
gcs::Generation(metadata_.generation()),
gcs::ReadFromOffset(position)));
Expand Down
70 changes: 61 additions & 9 deletions cpp/src/arrow/filesystem/gcsfs_test.cc
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -671,7 +671,7 @@ TEST_F(GcsIntegrationTest, CopyFileNotFound) {
ASSERT_RAISES(IOError, fs->CopyFile(NotFoundObjectPath(), destination_path));
}

TEST_F(GcsIntegrationTest, ReadObjectString) {
TEST_F(GcsIntegrationTest, OpenInputStreamString) {
auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

std::shared_ptr<io::InputStream> stream;
Expand All@@ -684,7 +684,7 @@ TEST_F(GcsIntegrationTest, ReadObjectString) {
EXPECT_EQ(std::string(buffer.data(), size), kLoremIpsum);
}

TEST_F(GcsIntegrationTest, ReadObjectStringBuffers) {
TEST_F(GcsIntegrationTest, OpenInputStreamStringBuffers) {
auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

std::shared_ptr<io::InputStream> stream;
Expand All@@ -700,7 +700,7 @@ TEST_F(GcsIntegrationTest, ReadObjectStringBuffers) {
EXPECT_EQ(contents, kLoremIpsum);
}

TEST_F(GcsIntegrationTest, ReadObjectInfo) {
TEST_F(GcsIntegrationTest, OpenInputStreamInfo) {
auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

arrow::fs::FileInfo info;
Expand All@@ -716,13 +716,27 @@ TEST_F(GcsIntegrationTest, ReadObjectInfo) {
EXPECT_EQ(std::string(buffer.data(), size), kLoremIpsum);
}

TEST_F(GcsIntegrationTest, ReadObjectNotFound) {
TEST_F(GcsIntegrationTest, OpenInputStreamEmpty) {
auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

const auto object_path =
internal::ConcatAbstractPath(PreexistingBucketName(), "empty-object.txt");
CreateFile(fs.get(), object_path, std::string());

ASSERT_OK_AND_ASSIGN(auto stream, fs->OpenInputStream(object_path));
std::array<char, 1024> buffer{};
std::int64_t size;
ASSERT_OK_AND_ASSIGN(size, stream->Read(buffer.size(), buffer.data()));
EXPECT_EQ(size, 0);
}

TEST_F(GcsIntegrationTest, OpenInputStreamNotFound) {
auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

ASSERT_RAISES(IOError, fs->OpenInputStream(NotFoundObjectPath()));
}

TEST_F(GcsIntegrationTest, ReadObjectInfoInvalid) {
TEST_F(GcsIntegrationTest, OpenInputStreamInfoInvalid) {
auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

arrow::fs::FileInfo info;
Expand All@@ -733,10 +747,10 @@ TEST_F(GcsIntegrationTest, ReadObjectInfoInvalid) {
ASSERT_RAISES(IOError, fs->OpenInputStream(info));
}

TEST_F(GcsIntegrationTest, ReadObjectReadMetadata) {
TEST_F(GcsIntegrationTest, OpenInputStreamReadMetadata) {
auto client = GcsClient();
const auto custom_time = std::chrono::system_clock::now() + std::chrono::hours(1);
const std::string object_name = "ReadObjectMetadataTest/simple.txt";
const std::string object_name = "OpenInputStreamMetadataTest/simple.txt";
const gcs::ObjectMetadata expected =
client
.InsertObject(PreexistingBucketName(), object_name,
Expand DownExpand Up@@ -795,7 +809,18 @@ TEST_F(GcsIntegrationTest, ReadObjectReadMetadata) {
ASSERT_FALSE(actual->Contains("kmsKeyName"));
}

TEST_F(GcsIntegrationTest, WriteObjectSmall) {
TEST_F(GcsIntegrationTest, OpenInputStreamClosed) {
auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

ASSERT_OK_AND_ASSIGN(auto stream, fs->OpenInputStream(PreexistingObjectPath()));
ASSERT_OK(stream->Close());
std::array<char, 16> buffer{};
ASSERT_RAISES(Invalid, stream->Read(buffer.size(), buffer.data()));
ASSERT_RAISES(Invalid, stream->Read(buffer.size()));
ASSERT_RAISES(Invalid, stream->Tell());
}

TEST_F(GcsIntegrationTest, OpenOutputStreamSmall) {
auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

const auto path = PreexistingBucketPath() + "test-write-object";
Expand All@@ -816,7 +841,7 @@ TEST_F(GcsIntegrationTest, WriteObjectSmall) {
EXPECT_EQ(std::string(inbuf.data(), size), expected);
}

TEST_F(GcsIntegrationTest, WriteObjectLarge) {
TEST_F(GcsIntegrationTest, OpenOutputStreamLarge) {
auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

const auto path = PreexistingBucketPath() + "test-write-object";
Expand DownExpand Up@@ -852,6 +877,19 @@ TEST_F(GcsIntegrationTest, WriteObjectLarge) {
EXPECT_EQ(contents, buffers[0] + buffers[1] + buffers[2]);
}

TEST_F(GcsIntegrationTest, OpenOutputStreamClosed) {
auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

const auto path = internal::ConcatAbstractPath(PreexistingBucketName(),
"open-output-stream-closed.txt");
std::shared_ptr<io::OutputStream> output;
ASSERT_OK_AND_ASSIGN(output, fs->OpenOutputStream(path, {}));
ASSERT_OK(output->Close());
ASSERT_RAISES(Invalid, output->Write(kLoremIpsum, std::strlen(kLoremIpsum)));
ASSERT_RAISES(Invalid, output->Flush());
ASSERT_RAISES(Invalid, output->Tell());
}

TEST_F(GcsIntegrationTest, OpenInputFileMixedReadVsReadAt) {
auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

Expand DownExpand Up@@ -971,6 +1009,20 @@ TEST_F(GcsIntegrationTest, OpenInputFileInfoInvalid) {
ASSERT_RAISES(IOError, fs->OpenInputFile(info));
}

TEST_F(GcsIntegrationTest, OpenInputFileClosed) {
auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

ASSERT_OK_AND_ASSIGN(auto stream, fs->OpenInputFile(PreexistingObjectPath()));
ASSERT_OK(stream->Close());
std::array<char, 16> buffer{};
ASSERT_RAISES(Invalid, stream->Tell());
ASSERT_RAISES(Invalid, stream->Read(buffer.size(), buffer.data()));
ASSERT_RAISES(Invalid, stream->Read(buffer.size()));
ASSERT_RAISES(Invalid, stream->ReadAt(1, buffer.size(), buffer.data()));
ASSERT_RAISES(Invalid, stream->ReadAt(1, 1));
ASSERT_RAISES(Invalid, stream->Seek(2));
}

} // namespace
} // namespace fs
} // namespace arrow
, '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
ARROW-15115: [C++] GcsFileSystem return errors if using closed streams#11976

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

 Closed

coryan
wants to merge
2
commits into

from

 Closed


ARROW-15115: [C++] GcsFileSystem return errors if using closed streams
#11976
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


2 commits


Select commit
Hold shift + click to select a range
d211922

ARROW-15115: [C++] GcsFileSystem return errors if using closed streams


coryan Dec 16, 2021
6ab9447

Address review comments


coryan Dec 20, 2021

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


35 changes: 27 additions & 8 deletions
cpp/src/arrow/filesystem/gcsfs.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -96,28 +96,32 @@ class GcsInputStream : public arrow::io::InputStream {
 // @name FileInterface
 Status Close() override {
 stream_.Close();
 closed_ = true;
 return Status::OK();
 }

 Result<int64_t> Tell() const override {
 if (!stream_) {
 return Status::IOError("invalid stream");
 }
 if (closed()) return Status::Invalid("Cannot use Tell() on a closed stream");
 return stream_.tellg() + offset_;
 }

 bool closed() const override { return !stream_.IsOpen(); }
 // A gcs::ObjectReadStream can be "born closed". For small objects the stream returns
 // `IsOpen() == false` as soon as it is created, but the application can still read from
 // it.
 bool closed() const override { return closed_ && !stream_.IsOpen(); }
@pitroupitrouDec 20, 2021

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

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

Is there a reason this is && rather than ||?
@coryancoryanDec 20, 2021

Copy link


Copy Markdown

ContributorAuthor
Choose a reason for hiding this comment

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

Yes. zero-length objects are "born closed" in google-cloud-cpp. Probably a bug (or at least a very poorly thought API), but you can read() from them, while they return IsOpen() == false.
@pitroupitrouDec 20, 2021

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

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

Ah, can you add a comment about that?
@coryancoryanDec 20, 2021

Copy link


Copy Markdown

ContributorAuthor
Choose a reason for hiding this comment

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

Done. That got me thinking about the similar expression for output streams, and you were right in that case. Fixed that too.
 //@}

 //@{
 // @name Readable
 Result<int64_t> Read(int64_t nbytes, void* out) override {
 if (closed()) return Status::Invalid("Cannot read from a closed stream");
 stream_.read(static_cast<char*>(out), nbytes);
 ARROW_GCS_RETURN_NOT_OK(stream_.status());
 return stream_.gcount();
 }

 Result<std::shared_ptr<Buffer>> Read(int64_t nbytes) override {
 if (closed()) return Status::Invalid("Cannot read from a closed stream");
 ARROW_ASSIGN_OR_RAISE(auto buffer, arrow::AllocateResizableBuffer(nbytes));
 stream_.read(reinterpret_cast<char*>(buffer->mutable_data()), nbytes);
 ARROW_GCS_RETURN_NOT_OK(stream_.status());
Expand All@@ -142,6 +146,7 @@ class GcsInputStream : public arrow::io::InputStream {
 gcs::Generation generation_;
 std::int64_t offset_;
 gcs::Client client_;
 bool closed_ = false;
};

class GcsOutputStream : public arrow::io::OutputStream {
Expand All@@ -151,19 +156,28 @@ class GcsOutputStream : public arrow::io::OutputStream {

 Status Close() override {
 stream_.Close();
 closed_ = true;
 return internal::ToArrowStatus(stream_.last_status());
 }

 Result<int64_t> Tell() const override {
 if (!stream_) {
 return Status::IOError("invalid stream");
 }
 if (closed()) return Status::Invalid("Cannot use Tell() on a closed stream");
 return tell_;
 }

 bool closed() const override { return !stream_.IsOpen(); }
 // gcs::ObjectWriteStream can be "closed" without an explicit Close() call. At this time
 // this class does not use any of the mechanisms [*] that trigger such behavior.
 // Nevertheless, we defensively prepare for them by checking either condition.
 //
 // [*]: These mechanisms include:
 // - resumable uploads that are "resumed" after the upload completed are born
 // "closed",
 // - uploads that prescribe their total size using the `x-upload-content-length` header
 // are completed and "closed" as soon as the upload reaches that size.
 bool closed() const override { return closed_ || !stream_.IsOpen(); }

 Status Write(const void* data, int64_t nbytes) override {
 if (closed()) return Status::Invalid("Cannot write to a closed stream");
 if (stream_.write(reinterpret_cast<const char*>(data), nbytes)) {
 tell_ += nbytes;
 return Status::OK();
Expand All@@ -172,13 +186,15 @@ class GcsOutputStream : public arrow::io::OutputStream {
 }

 Status Flush() override {
 if (closed()) return Status::Invalid("Cannot flush a closed stream");
 stream_.flush();
 return Status::OK();
 }

 private:
 gcs::ObjectWriteStream stream_;
 int64_t tell_ = 0;
 bool closed_ = false;
};

using InputStreamFactory = std::function<Result<std::shared_ptr<io::InputStream>>(
Expand DownExpand Up@@ -225,13 +241,15 @@ class GcsRandomAccessFile : public arrow::io::RandomAccessFile {
 // @name RandomAccessFile
 Result<int64_t> GetSize() override { return metadata_.size(); }
 Result<int64_t> ReadAt(int64_t position, int64_t nbytes, void* out) override {
 if (closed()) return Status::Invalid("Cannot read from closed file");
 std::shared_ptr<io::InputStream> stream;
 ARROW_ASSIGN_OR_RAISE(stream, factory_(metadata_.bucket(), metadata_.name(),
 gcs::Generation(metadata_.generation()),
 gcs::ReadFromOffset(position)));
 return stream->Read(nbytes, out);
 }
 Result<std::shared_ptr<Buffer>> ReadAt(int64_t position, int64_t nbytes) override {
 if (closed()) return Status::Invalid("Cannot read from closed file");
 std::shared_ptr<io::InputStream> stream;
 ARROW_ASSIGN_OR_RAISE(stream, factory_(metadata_.bucket(), metadata_.name(),
 gcs::Generation(metadata_.generation()),
Expand All@@ -242,6 +260,7 @@ class GcsRandomAccessFile : public arrow::io::RandomAccessFile {

 // from Seekable
 Status Seek(int64_t position) override {
 if (closed()) return Status::Invalid("Cannot seek in a closed file");
 ARROW_ASSIGN_OR_RAISE(stream_, factory_(metadata_.bucket(), metadata_.name(),
 gcs::Generation(metadata_.generation()),
 gcs::ReadFromOffset(position)));
Expand Down

70 changes: 61 additions & 9 deletions
cpp/src/arrow/filesystem/gcsfs_test.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -671,7 +671,7 @@ TEST_F(GcsIntegrationTest, CopyFileNotFound) {
 ASSERT_RAISES(IOError, fs->CopyFile(NotFoundObjectPath(), destination_path));
}

TEST_F(GcsIntegrationTest, ReadObjectString) {
TEST_F(GcsIntegrationTest, OpenInputStreamString) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 std::shared_ptr<io::InputStream> stream;
Expand All@@ -684,7 +684,7 @@ TEST_F(GcsIntegrationTest, ReadObjectString) {
 EXPECT_EQ(std::string(buffer.data(), size), kLoremIpsum);
}

TEST_F(GcsIntegrationTest, ReadObjectStringBuffers) {
TEST_F(GcsIntegrationTest, OpenInputStreamStringBuffers) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 std::shared_ptr<io::InputStream> stream;
Expand All@@ -700,7 +700,7 @@ TEST_F(GcsIntegrationTest, ReadObjectStringBuffers) {
 EXPECT_EQ(contents, kLoremIpsum);
}

TEST_F(GcsIntegrationTest, ReadObjectInfo) {
TEST_F(GcsIntegrationTest, OpenInputStreamInfo) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 arrow::fs::FileInfo info;
Expand All@@ -716,13 +716,27 @@ TEST_F(GcsIntegrationTest, ReadObjectInfo) {
 EXPECT_EQ(std::string(buffer.data(), size), kLoremIpsum);
}

TEST_F(GcsIntegrationTest, ReadObjectNotFound) {
TEST_F(GcsIntegrationTest, OpenInputStreamEmpty) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 const auto object_path =
 internal::ConcatAbstractPath(PreexistingBucketName(), "empty-object.txt");
 CreateFile(fs.get(), object_path, std::string());

 ASSERT_OK_AND_ASSIGN(auto stream, fs->OpenInputStream(object_path));
 std::array<char, 1024> buffer{};
 std::int64_t size;
 ASSERT_OK_AND_ASSIGN(size, stream->Read(buffer.size(), buffer.data()));
 EXPECT_EQ(size, 0);
}

TEST_F(GcsIntegrationTest, OpenInputStreamNotFound) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 ASSERT_RAISES(IOError, fs->OpenInputStream(NotFoundObjectPath()));
}

TEST_F(GcsIntegrationTest, ReadObjectInfoInvalid) {
TEST_F(GcsIntegrationTest, OpenInputStreamInfoInvalid) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 arrow::fs::FileInfo info;
Expand All@@ -733,10 +747,10 @@ TEST_F(GcsIntegrationTest, ReadObjectInfoInvalid) {
 ASSERT_RAISES(IOError, fs->OpenInputStream(info));
}

TEST_F(GcsIntegrationTest, ReadObjectReadMetadata) {
TEST_F(GcsIntegrationTest, OpenInputStreamReadMetadata) {
 auto client = GcsClient();
 const auto custom_time = std::chrono::system_clock::now() + std::chrono::hours(1);
 const std::string object_name = "ReadObjectMetadataTest/simple.txt";
 const std::string object_name = "OpenInputStreamMetadataTest/simple.txt";
 const gcs::ObjectMetadata expected =
 client
 .InsertObject(PreexistingBucketName(), object_name,
Expand DownExpand Up@@ -795,7 +809,18 @@ TEST_F(GcsIntegrationTest, ReadObjectReadMetadata) {
 ASSERT_FALSE(actual->Contains("kmsKeyName"));
}

TEST_F(GcsIntegrationTest, WriteObjectSmall) {
TEST_F(GcsIntegrationTest, OpenInputStreamClosed) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 ASSERT_OK_AND_ASSIGN(auto stream, fs->OpenInputStream(PreexistingObjectPath()));
 ASSERT_OK(stream->Close());
 std::array<char, 16> buffer{};
 ASSERT_RAISES(Invalid, stream->Read(buffer.size(), buffer.data()));
 ASSERT_RAISES(Invalid, stream->Read(buffer.size()));
 ASSERT_RAISES(Invalid, stream->Tell());
}

TEST_F(GcsIntegrationTest, OpenOutputStreamSmall) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 const auto path = PreexistingBucketPath() + "test-write-object";
Expand All@@ -816,7 +841,7 @@ TEST_F(GcsIntegrationTest, WriteObjectSmall) {
 EXPECT_EQ(std::string(inbuf.data(), size), expected);
}

TEST_F(GcsIntegrationTest, WriteObjectLarge) {
TEST_F(GcsIntegrationTest, OpenOutputStreamLarge) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 const auto path = PreexistingBucketPath() + "test-write-object";
Expand DownExpand Up@@ -852,6 +877,19 @@ TEST_F(GcsIntegrationTest, WriteObjectLarge) {
 EXPECT_EQ(contents, buffers[0] + buffers[1] + buffers[2]);
}

TEST_F(GcsIntegrationTest, OpenOutputStreamClosed) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 const auto path = internal::ConcatAbstractPath(PreexistingBucketName(),
 "open-output-stream-closed.txt");
 std::shared_ptr<io::OutputStream> output;
 ASSERT_OK_AND_ASSIGN(output, fs->OpenOutputStream(path, {}));
 ASSERT_OK(output->Close());
 ASSERT_RAISES(Invalid, output->Write(kLoremIpsum, std::strlen(kLoremIpsum)));
 ASSERT_RAISES(Invalid, output->Flush());
 ASSERT_RAISES(Invalid, output->Tell());
}

TEST_F(GcsIntegrationTest, OpenInputFileMixedReadVsReadAt) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

Expand DownExpand Up@@ -971,6 +1009,20 @@ TEST_F(GcsIntegrationTest, OpenInputFileInfoInvalid) {
 ASSERT_RAISES(IOError, fs->OpenInputFile(info));
}

TEST_F(GcsIntegrationTest, OpenInputFileClosed) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 ASSERT_OK_AND_ASSIGN(auto stream, fs->OpenInputFile(PreexistingObjectPath()));
 ASSERT_OK(stream->Close());
 std::array<char, 16> buffer{};
 ASSERT_RAISES(Invalid, stream->Tell());
 ASSERT_RAISES(Invalid, stream->Read(buffer.size(), buffer.data()));
 ASSERT_RAISES(Invalid, stream->Read(buffer.size()));
 ASSERT_RAISES(Invalid, stream->ReadAt(1, buffer.size(), buffer.data()));
 ASSERT_RAISES(Invalid, stream->ReadAt(1, 1));
 ASSERT_RAISES(Invalid, stream->Seek(2));
}

} // namespace
} // namespace fs
} // namespace arrow

, '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
ARROW-15115: [C++] GcsFileSystem return errors if using closed streams#11976

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

 Closed

coryan
wants to merge
2
commits into

from

 Closed


ARROW-15115: [C++] GcsFileSystem return errors if using closed streams
#11976
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


2 commits


Select commit
Hold shift + click to select a range
d211922

ARROW-15115: [C++] GcsFileSystem return errors if using closed streams


coryan Dec 16, 2021
6ab9447

Address review comments


coryan Dec 20, 2021

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


35 changes: 27 additions & 8 deletions
cpp/src/arrow/filesystem/gcsfs.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -96,28 +96,32 @@ class GcsInputStream : public arrow::io::InputStream {
 // @name FileInterface
 Status Close() override {
 stream_.Close();
 closed_ = true;
 return Status::OK();
 }

 Result<int64_t> Tell() const override {
 if (!stream_) {
 return Status::IOError("invalid stream");
 }
 if (closed()) return Status::Invalid("Cannot use Tell() on a closed stream");
 return stream_.tellg() + offset_;
 }

 bool closed() const override { return !stream_.IsOpen(); }
 // A gcs::ObjectReadStream can be "born closed". For small objects the stream returns
 // `IsOpen() == false` as soon as it is created, but the application can still read from
 // it.
 bool closed() const override { return closed_ && !stream_.IsOpen(); }
@pitroupitrouDec 20, 2021

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

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

Is there a reason this is && rather than ||?
@coryancoryanDec 20, 2021

Copy link


Copy Markdown

ContributorAuthor
Choose a reason for hiding this comment

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

Yes. zero-length objects are "born closed" in google-cloud-cpp. Probably a bug (or at least a very poorly thought API), but you can read() from them, while they return IsOpen() == false.
@pitroupitrouDec 20, 2021

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

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

Ah, can you add a comment about that?
@coryancoryanDec 20, 2021

Copy link


Copy Markdown

ContributorAuthor
Choose a reason for hiding this comment

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

Done. That got me thinking about the similar expression for output streams, and you were right in that case. Fixed that too.
 //@}

 //@{
 // @name Readable
 Result<int64_t> Read(int64_t nbytes, void* out) override {
 if (closed()) return Status::Invalid("Cannot read from a closed stream");
 stream_.read(static_cast<char*>(out), nbytes);
 ARROW_GCS_RETURN_NOT_OK(stream_.status());
 return stream_.gcount();
 }

 Result<std::shared_ptr<Buffer>> Read(int64_t nbytes) override {
 if (closed()) return Status::Invalid("Cannot read from a closed stream");
 ARROW_ASSIGN_OR_RAISE(auto buffer, arrow::AllocateResizableBuffer(nbytes));
 stream_.read(reinterpret_cast<char*>(buffer->mutable_data()), nbytes);
 ARROW_GCS_RETURN_NOT_OK(stream_.status());
Expand All@@ -142,6 +146,7 @@ class GcsInputStream : public arrow::io::InputStream {
 gcs::Generation generation_;
 std::int64_t offset_;
 gcs::Client client_;
 bool closed_ = false;
};

class GcsOutputStream : public arrow::io::OutputStream {
Expand All@@ -151,19 +156,28 @@ class GcsOutputStream : public arrow::io::OutputStream {

 Status Close() override {
 stream_.Close();
 closed_ = true;
 return internal::ToArrowStatus(stream_.last_status());
 }

 Result<int64_t> Tell() const override {
 if (!stream_) {
 return Status::IOError("invalid stream");
 }
 if (closed()) return Status::Invalid("Cannot use Tell() on a closed stream");
 return tell_;
 }

 bool closed() const override { return !stream_.IsOpen(); }
 // gcs::ObjectWriteStream can be "closed" without an explicit Close() call. At this time
 // this class does not use any of the mechanisms [*] that trigger such behavior.
 // Nevertheless, we defensively prepare for them by checking either condition.
 //
 // [*]: These mechanisms include:
 // - resumable uploads that are "resumed" after the upload completed are born
 // "closed",
 // - uploads that prescribe their total size using the `x-upload-content-length` header
 // are completed and "closed" as soon as the upload reaches that size.
 bool closed() const override { return closed_ || !stream_.IsOpen(); }

 Status Write(const void* data, int64_t nbytes) override {
 if (closed()) return Status::Invalid("Cannot write to a closed stream");
 if (stream_.write(reinterpret_cast<const char*>(data), nbytes)) {
 tell_ += nbytes;
 return Status::OK();
Expand All@@ -172,13 +186,15 @@ class GcsOutputStream : public arrow::io::OutputStream {
 }

 Status Flush() override {
 if (closed()) return Status::Invalid("Cannot flush a closed stream");
 stream_.flush();
 return Status::OK();
 }

 private:
 gcs::ObjectWriteStream stream_;
 int64_t tell_ = 0;
 bool closed_ = false;
};

using InputStreamFactory = std::function<Result<std::shared_ptr<io::InputStream>>(
Expand DownExpand Up@@ -225,13 +241,15 @@ class GcsRandomAccessFile : public arrow::io::RandomAccessFile {
 // @name RandomAccessFile
 Result<int64_t> GetSize() override { return metadata_.size(); }
 Result<int64_t> ReadAt(int64_t position, int64_t nbytes, void* out) override {
 if (closed()) return Status::Invalid("Cannot read from closed file");
 std::shared_ptr<io::InputStream> stream;
 ARROW_ASSIGN_OR_RAISE(stream, factory_(metadata_.bucket(), metadata_.name(),
 gcs::Generation(metadata_.generation()),
 gcs::ReadFromOffset(position)));
 return stream->Read(nbytes, out);
 }
 Result<std::shared_ptr<Buffer>> ReadAt(int64_t position, int64_t nbytes) override {
 if (closed()) return Status::Invalid("Cannot read from closed file");
 std::shared_ptr<io::InputStream> stream;
 ARROW_ASSIGN_OR_RAISE(stream, factory_(metadata_.bucket(), metadata_.name(),
 gcs::Generation(metadata_.generation()),
Expand All@@ -242,6 +260,7 @@ class GcsRandomAccessFile : public arrow::io::RandomAccessFile {

 // from Seekable
 Status Seek(int64_t position) override {
 if (closed()) return Status::Invalid("Cannot seek in a closed file");
 ARROW_ASSIGN_OR_RAISE(stream_, factory_(metadata_.bucket(), metadata_.name(),
 gcs::Generation(metadata_.generation()),
 gcs::ReadFromOffset(position)));
Expand Down

70 changes: 61 additions & 9 deletions
cpp/src/arrow/filesystem/gcsfs_test.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -671,7 +671,7 @@ TEST_F(GcsIntegrationTest, CopyFileNotFound) {
 ASSERT_RAISES(IOError, fs->CopyFile(NotFoundObjectPath(), destination_path));
}

TEST_F(GcsIntegrationTest, ReadObjectString) {
TEST_F(GcsIntegrationTest, OpenInputStreamString) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 std::shared_ptr<io::InputStream> stream;
Expand All@@ -684,7 +684,7 @@ TEST_F(GcsIntegrationTest, ReadObjectString) {
 EXPECT_EQ(std::string(buffer.data(), size), kLoremIpsum);
}

TEST_F(GcsIntegrationTest, ReadObjectStringBuffers) {
TEST_F(GcsIntegrationTest, OpenInputStreamStringBuffers) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 std::shared_ptr<io::InputStream> stream;
Expand All@@ -700,7 +700,7 @@ TEST_F(GcsIntegrationTest, ReadObjectStringBuffers) {
 EXPECT_EQ(contents, kLoremIpsum);
}

TEST_F(GcsIntegrationTest, ReadObjectInfo) {
TEST_F(GcsIntegrationTest, OpenInputStreamInfo) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 arrow::fs::FileInfo info;
Expand All@@ -716,13 +716,27 @@ TEST_F(GcsIntegrationTest, ReadObjectInfo) {
 EXPECT_EQ(std::string(buffer.data(), size), kLoremIpsum);
}

TEST_F(GcsIntegrationTest, ReadObjectNotFound) {
TEST_F(GcsIntegrationTest, OpenInputStreamEmpty) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 const auto object_path =
 internal::ConcatAbstractPath(PreexistingBucketName(), "empty-object.txt");
 CreateFile(fs.get(), object_path, std::string());

 ASSERT_OK_AND_ASSIGN(auto stream, fs->OpenInputStream(object_path));
 std::array<char, 1024> buffer{};
 std::int64_t size;
 ASSERT_OK_AND_ASSIGN(size, stream->Read(buffer.size(), buffer.data()));
 EXPECT_EQ(size, 0);
}

TEST_F(GcsIntegrationTest, OpenInputStreamNotFound) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 ASSERT_RAISES(IOError, fs->OpenInputStream(NotFoundObjectPath()));
}

TEST_F(GcsIntegrationTest, ReadObjectInfoInvalid) {
TEST_F(GcsIntegrationTest, OpenInputStreamInfoInvalid) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 arrow::fs::FileInfo info;
Expand All@@ -733,10 +747,10 @@ TEST_F(GcsIntegrationTest, ReadObjectInfoInvalid) {
 ASSERT_RAISES(IOError, fs->OpenInputStream(info));
}

TEST_F(GcsIntegrationTest, ReadObjectReadMetadata) {
TEST_F(GcsIntegrationTest, OpenInputStreamReadMetadata) {
 auto client = GcsClient();
 const auto custom_time = std::chrono::system_clock::now() + std::chrono::hours(1);
 const std::string object_name = "ReadObjectMetadataTest/simple.txt";
 const std::string object_name = "OpenInputStreamMetadataTest/simple.txt";
 const gcs::ObjectMetadata expected =
 client
 .InsertObject(PreexistingBucketName(), object_name,
Expand DownExpand Up@@ -795,7 +809,18 @@ TEST_F(GcsIntegrationTest, ReadObjectReadMetadata) {
 ASSERT_FALSE(actual->Contains("kmsKeyName"));
}

TEST_F(GcsIntegrationTest, WriteObjectSmall) {
TEST_F(GcsIntegrationTest, OpenInputStreamClosed) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 ASSERT_OK_AND_ASSIGN(auto stream, fs->OpenInputStream(PreexistingObjectPath()));
 ASSERT_OK(stream->Close());
 std::array<char, 16> buffer{};
 ASSERT_RAISES(Invalid, stream->Read(buffer.size(), buffer.data()));
 ASSERT_RAISES(Invalid, stream->Read(buffer.size()));
 ASSERT_RAISES(Invalid, stream->Tell());
}

TEST_F(GcsIntegrationTest, OpenOutputStreamSmall) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 const auto path = PreexistingBucketPath() + "test-write-object";
Expand All@@ -816,7 +841,7 @@ TEST_F(GcsIntegrationTest, WriteObjectSmall) {
 EXPECT_EQ(std::string(inbuf.data(), size), expected);
}

TEST_F(GcsIntegrationTest, WriteObjectLarge) {
TEST_F(GcsIntegrationTest, OpenOutputStreamLarge) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 const auto path = PreexistingBucketPath() + "test-write-object";
Expand DownExpand Up@@ -852,6 +877,19 @@ TEST_F(GcsIntegrationTest, WriteObjectLarge) {
 EXPECT_EQ(contents, buffers[0] + buffers[1] + buffers[2]);
}

TEST_F(GcsIntegrationTest, OpenOutputStreamClosed) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 const auto path = internal::ConcatAbstractPath(PreexistingBucketName(),
 "open-output-stream-closed.txt");
 std::shared_ptr<io::OutputStream> output;
 ASSERT_OK_AND_ASSIGN(output, fs->OpenOutputStream(path, {}));
 ASSERT_OK(output->Close());
 ASSERT_RAISES(Invalid, output->Write(kLoremIpsum, std::strlen(kLoremIpsum)));
 ASSERT_RAISES(Invalid, output->Flush());
 ASSERT_RAISES(Invalid, output->Tell());
}

TEST_F(GcsIntegrationTest, OpenInputFileMixedReadVsReadAt) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

Expand DownExpand Up@@ -971,6 +1009,20 @@ TEST_F(GcsIntegrationTest, OpenInputFileInfoInvalid) {
 ASSERT_RAISES(IOError, fs->OpenInputFile(info));
}

TEST_F(GcsIntegrationTest, OpenInputFileClosed) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 ASSERT_OK_AND_ASSIGN(auto stream, fs->OpenInputFile(PreexistingObjectPath()));
 ASSERT_OK(stream->Close());
 std::array<char, 16> buffer{};
 ASSERT_RAISES(Invalid, stream->Tell());
 ASSERT_RAISES(Invalid, stream->Read(buffer.size(), buffer.data()));
 ASSERT_RAISES(Invalid, stream->Read(buffer.size()));
 ASSERT_RAISES(Invalid, stream->ReadAt(1, buffer.size(), buffer.data()));
 ASSERT_RAISES(Invalid, stream->ReadAt(1, 1));
 ASSERT_RAISES(Invalid, stream->Seek(2));
}

} // namespace
} // namespace fs
} // namespace arrow

, '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
ARROW-15115: [C++] GcsFileSystem return errors if using closed streams#11976

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

 Closed

coryan
wants to merge
2
commits into

from

 Closed


ARROW-15115: [C++] GcsFileSystem return errors if using closed streams
#11976
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


2 commits


Select commit
Hold shift + click to select a range
d211922

ARROW-15115: [C++] GcsFileSystem return errors if using closed streams


coryan Dec 16, 2021
6ab9447

Address review comments


coryan Dec 20, 2021

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


35 changes: 27 additions & 8 deletions
cpp/src/arrow/filesystem/gcsfs.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -96,28 +96,32 @@ class GcsInputStream : public arrow::io::InputStream {
 // @name FileInterface
 Status Close() override {
 stream_.Close();
 closed_ = true;
 return Status::OK();
 }

 Result<int64_t> Tell() const override {
 if (!stream_) {
 return Status::IOError("invalid stream");
 }
 if (closed()) return Status::Invalid("Cannot use Tell() on a closed stream");
 return stream_.tellg() + offset_;
 }

 bool closed() const override { return !stream_.IsOpen(); }
 // A gcs::ObjectReadStream can be "born closed". For small objects the stream returns
 // `IsOpen() == false` as soon as it is created, but the application can still read from
 // it.
 bool closed() const override { return closed_ && !stream_.IsOpen(); }
@pitroupitrouDec 20, 2021

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

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

Is there a reason this is && rather than ||?
@coryancoryanDec 20, 2021

Copy link


Copy Markdown

ContributorAuthor
Choose a reason for hiding this comment

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

Yes. zero-length objects are "born closed" in google-cloud-cpp. Probably a bug (or at least a very poorly thought API), but you can read() from them, while they return IsOpen() == false.
@pitroupitrouDec 20, 2021

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

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

Ah, can you add a comment about that?
@coryancoryanDec 20, 2021

Copy link


Copy Markdown

ContributorAuthor
Choose a reason for hiding this comment

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

Done. That got me thinking about the similar expression for output streams, and you were right in that case. Fixed that too.
 //@}

 //@{
 // @name Readable
 Result<int64_t> Read(int64_t nbytes, void* out) override {
 if (closed()) return Status::Invalid("Cannot read from a closed stream");
 stream_.read(static_cast<char*>(out), nbytes);
 ARROW_GCS_RETURN_NOT_OK(stream_.status());
 return stream_.gcount();
 }

 Result<std::shared_ptr<Buffer>> Read(int64_t nbytes) override {
 if (closed()) return Status::Invalid("Cannot read from a closed stream");
 ARROW_ASSIGN_OR_RAISE(auto buffer, arrow::AllocateResizableBuffer(nbytes));
 stream_.read(reinterpret_cast<char*>(buffer->mutable_data()), nbytes);
 ARROW_GCS_RETURN_NOT_OK(stream_.status());
Expand All@@ -142,6 +146,7 @@ class GcsInputStream : public arrow::io::InputStream {
 gcs::Generation generation_;
 std::int64_t offset_;
 gcs::Client client_;
 bool closed_ = false;
};

class GcsOutputStream : public arrow::io::OutputStream {
Expand All@@ -151,19 +156,28 @@ class GcsOutputStream : public arrow::io::OutputStream {

 Status Close() override {
 stream_.Close();
 closed_ = true;
 return internal::ToArrowStatus(stream_.last_status());
 }

 Result<int64_t> Tell() const override {
 if (!stream_) {
 return Status::IOError("invalid stream");
 }
 if (closed()) return Status::Invalid("Cannot use Tell() on a closed stream");
 return tell_;
 }

 bool closed() const override { return !stream_.IsOpen(); }
 // gcs::ObjectWriteStream can be "closed" without an explicit Close() call. At this time
 // this class does not use any of the mechanisms [*] that trigger such behavior.
 // Nevertheless, we defensively prepare for them by checking either condition.
 //
 // [*]: These mechanisms include:
 // - resumable uploads that are "resumed" after the upload completed are born
 // "closed",
 // - uploads that prescribe their total size using the `x-upload-content-length` header
 // are completed and "closed" as soon as the upload reaches that size.
 bool closed() const override { return closed_ || !stream_.IsOpen(); }

 Status Write(const void* data, int64_t nbytes) override {
 if (closed()) return Status::Invalid("Cannot write to a closed stream");
 if (stream_.write(reinterpret_cast<const char*>(data), nbytes)) {
 tell_ += nbytes;
 return Status::OK();
Expand All@@ -172,13 +186,15 @@ class GcsOutputStream : public arrow::io::OutputStream {
 }

 Status Flush() override {
 if (closed()) return Status::Invalid("Cannot flush a closed stream");
 stream_.flush();
 return Status::OK();
 }

 private:
 gcs::ObjectWriteStream stream_;
 int64_t tell_ = 0;
 bool closed_ = false;
};

using InputStreamFactory = std::function<Result<std::shared_ptr<io::InputStream>>(
Expand DownExpand Up@@ -225,13 +241,15 @@ class GcsRandomAccessFile : public arrow::io::RandomAccessFile {
 // @name RandomAccessFile
 Result<int64_t> GetSize() override { return metadata_.size(); }
 Result<int64_t> ReadAt(int64_t position, int64_t nbytes, void* out) override {
 if (closed()) return Status::Invalid("Cannot read from closed file");
 std::shared_ptr<io::InputStream> stream;
 ARROW_ASSIGN_OR_RAISE(stream, factory_(metadata_.bucket(), metadata_.name(),
 gcs::Generation(metadata_.generation()),
 gcs::ReadFromOffset(position)));
 return stream->Read(nbytes, out);
 }
 Result<std::shared_ptr<Buffer>> ReadAt(int64_t position, int64_t nbytes) override {
 if (closed()) return Status::Invalid("Cannot read from closed file");
 std::shared_ptr<io::InputStream> stream;
 ARROW_ASSIGN_OR_RAISE(stream, factory_(metadata_.bucket(), metadata_.name(),
 gcs::Generation(metadata_.generation()),
Expand All@@ -242,6 +260,7 @@ class GcsRandomAccessFile : public arrow::io::RandomAccessFile {

 // from Seekable
 Status Seek(int64_t position) override {
 if (closed()) return Status::Invalid("Cannot seek in a closed file");
 ARROW_ASSIGN_OR_RAISE(stream_, factory_(metadata_.bucket(), metadata_.name(),
 gcs::Generation(metadata_.generation()),
 gcs::ReadFromOffset(position)));
Expand Down

70 changes: 61 additions & 9 deletions
cpp/src/arrow/filesystem/gcsfs_test.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -671,7 +671,7 @@ TEST_F(GcsIntegrationTest, CopyFileNotFound) {
 ASSERT_RAISES(IOError, fs->CopyFile(NotFoundObjectPath(), destination_path));
}

TEST_F(GcsIntegrationTest, ReadObjectString) {
TEST_F(GcsIntegrationTest, OpenInputStreamString) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 std::shared_ptr<io::InputStream> stream;
Expand All@@ -684,7 +684,7 @@ TEST_F(GcsIntegrationTest, ReadObjectString) {
 EXPECT_EQ(std::string(buffer.data(), size), kLoremIpsum);
}

TEST_F(GcsIntegrationTest, ReadObjectStringBuffers) {
TEST_F(GcsIntegrationTest, OpenInputStreamStringBuffers) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 std::shared_ptr<io::InputStream> stream;
Expand All@@ -700,7 +700,7 @@ TEST_F(GcsIntegrationTest, ReadObjectStringBuffers) {
 EXPECT_EQ(contents, kLoremIpsum);
}

TEST_F(GcsIntegrationTest, ReadObjectInfo) {
TEST_F(GcsIntegrationTest, OpenInputStreamInfo) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 arrow::fs::FileInfo info;
Expand All@@ -716,13 +716,27 @@ TEST_F(GcsIntegrationTest, ReadObjectInfo) {
 EXPECT_EQ(std::string(buffer.data(), size), kLoremIpsum);
}

TEST_F(GcsIntegrationTest, ReadObjectNotFound) {
TEST_F(GcsIntegrationTest, OpenInputStreamEmpty) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 const auto object_path =
 internal::ConcatAbstractPath(PreexistingBucketName(), "empty-object.txt");
 CreateFile(fs.get(), object_path, std::string());

 ASSERT_OK_AND_ASSIGN(auto stream, fs->OpenInputStream(object_path));
 std::array<char, 1024> buffer{};
 std::int64_t size;
 ASSERT_OK_AND_ASSIGN(size, stream->Read(buffer.size(), buffer.data()));
 EXPECT_EQ(size, 0);
}

TEST_F(GcsIntegrationTest, OpenInputStreamNotFound) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 ASSERT_RAISES(IOError, fs->OpenInputStream(NotFoundObjectPath()));
}

TEST_F(GcsIntegrationTest, ReadObjectInfoInvalid) {
TEST_F(GcsIntegrationTest, OpenInputStreamInfoInvalid) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 arrow::fs::FileInfo info;
Expand All@@ -733,10 +747,10 @@ TEST_F(GcsIntegrationTest, ReadObjectInfoInvalid) {
 ASSERT_RAISES(IOError, fs->OpenInputStream(info));
}

TEST_F(GcsIntegrationTest, ReadObjectReadMetadata) {
TEST_F(GcsIntegrationTest, OpenInputStreamReadMetadata) {
 auto client = GcsClient();
 const auto custom_time = std::chrono::system_clock::now() + std::chrono::hours(1);
 const std::string object_name = "ReadObjectMetadataTest/simple.txt";
 const std::string object_name = "OpenInputStreamMetadataTest/simple.txt";
 const gcs::ObjectMetadata expected =
 client
 .InsertObject(PreexistingBucketName(), object_name,
Expand DownExpand Up@@ -795,7 +809,18 @@ TEST_F(GcsIntegrationTest, ReadObjectReadMetadata) {
 ASSERT_FALSE(actual->Contains("kmsKeyName"));
}

TEST_F(GcsIntegrationTest, WriteObjectSmall) {
TEST_F(GcsIntegrationTest, OpenInputStreamClosed) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 ASSERT_OK_AND_ASSIGN(auto stream, fs->OpenInputStream(PreexistingObjectPath()));
 ASSERT_OK(stream->Close());
 std::array<char, 16> buffer{};
 ASSERT_RAISES(Invalid, stream->Read(buffer.size(), buffer.data()));
 ASSERT_RAISES(Invalid, stream->Read(buffer.size()));
 ASSERT_RAISES(Invalid, stream->Tell());
}

TEST_F(GcsIntegrationTest, OpenOutputStreamSmall) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 const auto path = PreexistingBucketPath() + "test-write-object";
Expand All@@ -816,7 +841,7 @@ TEST_F(GcsIntegrationTest, WriteObjectSmall) {
 EXPECT_EQ(std::string(inbuf.data(), size), expected);
}

TEST_F(GcsIntegrationTest, WriteObjectLarge) {
TEST_F(GcsIntegrationTest, OpenOutputStreamLarge) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 const auto path = PreexistingBucketPath() + "test-write-object";
Expand DownExpand Up@@ -852,6 +877,19 @@ TEST_F(GcsIntegrationTest, WriteObjectLarge) {
 EXPECT_EQ(contents, buffers[0] + buffers[1] + buffers[2]);
}

TEST_F(GcsIntegrationTest, OpenOutputStreamClosed) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 const auto path = internal::ConcatAbstractPath(PreexistingBucketName(),
 "open-output-stream-closed.txt");
 std::shared_ptr<io::OutputStream> output;
 ASSERT_OK_AND_ASSIGN(output, fs->OpenOutputStream(path, {}));
 ASSERT_OK(output->Close());
 ASSERT_RAISES(Invalid, output->Write(kLoremIpsum, std::strlen(kLoremIpsum)));
 ASSERT_RAISES(Invalid, output->Flush());
 ASSERT_RAISES(Invalid, output->Tell());
}

TEST_F(GcsIntegrationTest, OpenInputFileMixedReadVsReadAt) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

Expand DownExpand Up@@ -971,6 +1009,20 @@ TEST_F(GcsIntegrationTest, OpenInputFileInfoInvalid) {
 ASSERT_RAISES(IOError, fs->OpenInputFile(info));
}

TEST_F(GcsIntegrationTest, OpenInputFileClosed) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 ASSERT_OK_AND_ASSIGN(auto stream, fs->OpenInputFile(PreexistingObjectPath()));
 ASSERT_OK(stream->Close());
 std::array<char, 16> buffer{};
 ASSERT_RAISES(Invalid, stream->Tell());
 ASSERT_RAISES(Invalid, stream->Read(buffer.size(), buffer.data()));
 ASSERT_RAISES(Invalid, stream->Read(buffer.size()));
 ASSERT_RAISES(Invalid, stream->ReadAt(1, buffer.size(), buffer.data()));
 ASSERT_RAISES(Invalid, stream->ReadAt(1, 1));
 ASSERT_RAISES(Invalid, stream->Seek(2));
}

} // namespace
} // namespace fs
} // namespace arrow

, '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
ARROW-15115: [C++] GcsFileSystem return errors if using closed streams#11976

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

 Closed

coryan
wants to merge
2
commits into

from

 Closed


ARROW-15115: [C++] GcsFileSystem return errors if using closed streams
#11976
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


2 commits


Select commit
Hold shift + click to select a range
d211922

ARROW-15115: [C++] GcsFileSystem return errors if using closed streams


coryan Dec 16, 2021
6ab9447

Address review comments


coryan Dec 20, 2021

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


35 changes: 27 additions & 8 deletions
cpp/src/arrow/filesystem/gcsfs.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -96,28 +96,32 @@ class GcsInputStream : public arrow::io::InputStream {
 // @name FileInterface
 Status Close() override {
 stream_.Close();
 closed_ = true;
 return Status::OK();
 }

 Result<int64_t> Tell() const override {
 if (!stream_) {
 return Status::IOError("invalid stream");
 }
 if (closed()) return Status::Invalid("Cannot use Tell() on a closed stream");
 return stream_.tellg() + offset_;
 }

 bool closed() const override { return !stream_.IsOpen(); }
 // A gcs::ObjectReadStream can be "born closed". For small objects the stream returns
 // `IsOpen() == false` as soon as it is created, but the application can still read from
 // it.
 bool closed() const override { return closed_ && !stream_.IsOpen(); }
@pitroupitrouDec 20, 2021

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

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

Is there a reason this is && rather than ||?
@coryancoryanDec 20, 2021

Copy link


Copy Markdown

ContributorAuthor
Choose a reason for hiding this comment

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

Yes. zero-length objects are "born closed" in google-cloud-cpp. Probably a bug (or at least a very poorly thought API), but you can read() from them, while they return IsOpen() == false.
@pitroupitrouDec 20, 2021

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

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

Ah, can you add a comment about that?
@coryancoryanDec 20, 2021

Copy link


Copy Markdown

ContributorAuthor
Choose a reason for hiding this comment

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

Done. That got me thinking about the similar expression for output streams, and you were right in that case. Fixed that too.
 //@}

 //@{
 // @name Readable
 Result<int64_t> Read(int64_t nbytes, void* out) override {
 if (closed()) return Status::Invalid("Cannot read from a closed stream");
 stream_.read(static_cast<char*>(out), nbytes);
 ARROW_GCS_RETURN_NOT_OK(stream_.status());
 return stream_.gcount();
 }

 Result<std::shared_ptr<Buffer>> Read(int64_t nbytes) override {
 if (closed()) return Status::Invalid("Cannot read from a closed stream");
 ARROW_ASSIGN_OR_RAISE(auto buffer, arrow::AllocateResizableBuffer(nbytes));
 stream_.read(reinterpret_cast<char*>(buffer->mutable_data()), nbytes);
 ARROW_GCS_RETURN_NOT_OK(stream_.status());
Expand All@@ -142,6 +146,7 @@ class GcsInputStream : public arrow::io::InputStream {
 gcs::Generation generation_;
 std::int64_t offset_;
 gcs::Client client_;
 bool closed_ = false;
};

class GcsOutputStream : public arrow::io::OutputStream {
Expand All@@ -151,19 +156,28 @@ class GcsOutputStream : public arrow::io::OutputStream {

 Status Close() override {
 stream_.Close();
 closed_ = true;
 return internal::ToArrowStatus(stream_.last_status());
 }

 Result<int64_t> Tell() const override {
 if (!stream_) {
 return Status::IOError("invalid stream");
 }
 if (closed()) return Status::Invalid("Cannot use Tell() on a closed stream");
 return tell_;
 }

 bool closed() const override { return !stream_.IsOpen(); }
 // gcs::ObjectWriteStream can be "closed" without an explicit Close() call. At this time
 // this class does not use any of the mechanisms [*] that trigger such behavior.
 // Nevertheless, we defensively prepare for them by checking either condition.
 //
 // [*]: These mechanisms include:
 // - resumable uploads that are "resumed" after the upload completed are born
 // "closed",
 // - uploads that prescribe their total size using the `x-upload-content-length` header
 // are completed and "closed" as soon as the upload reaches that size.
 bool closed() const override { return closed_ || !stream_.IsOpen(); }

 Status Write(const void* data, int64_t nbytes) override {
 if (closed()) return Status::Invalid("Cannot write to a closed stream");
 if (stream_.write(reinterpret_cast<const char*>(data), nbytes)) {
 tell_ += nbytes;
 return Status::OK();
Expand All@@ -172,13 +186,15 @@ class GcsOutputStream : public arrow::io::OutputStream {
 }

 Status Flush() override {
 if (closed()) return Status::Invalid("Cannot flush a closed stream");
 stream_.flush();
 return Status::OK();
 }

 private:
 gcs::ObjectWriteStream stream_;
 int64_t tell_ = 0;
 bool closed_ = false;
};

using InputStreamFactory = std::function<Result<std::shared_ptr<io::InputStream>>(
Expand DownExpand Up@@ -225,13 +241,15 @@ class GcsRandomAccessFile : public arrow::io::RandomAccessFile {
 // @name RandomAccessFile
 Result<int64_t> GetSize() override { return metadata_.size(); }
 Result<int64_t> ReadAt(int64_t position, int64_t nbytes, void* out) override {
 if (closed()) return Status::Invalid("Cannot read from closed file");
 std::shared_ptr<io::InputStream> stream;
 ARROW_ASSIGN_OR_RAISE(stream, factory_(metadata_.bucket(), metadata_.name(),
 gcs::Generation(metadata_.generation()),
 gcs::ReadFromOffset(position)));
 return stream->Read(nbytes, out);
 }
 Result<std::shared_ptr<Buffer>> ReadAt(int64_t position, int64_t nbytes) override {
 if (closed()) return Status::Invalid("Cannot read from closed file");
 std::shared_ptr<io::InputStream> stream;
 ARROW_ASSIGN_OR_RAISE(stream, factory_(metadata_.bucket(), metadata_.name(),
 gcs::Generation(metadata_.generation()),
Expand All@@ -242,6 +260,7 @@ class GcsRandomAccessFile : public arrow::io::RandomAccessFile {

 // from Seekable
 Status Seek(int64_t position) override {
 if (closed()) return Status::Invalid("Cannot seek in a closed file");
 ARROW_ASSIGN_OR_RAISE(stream_, factory_(metadata_.bucket(), metadata_.name(),
 gcs::Generation(metadata_.generation()),
 gcs::ReadFromOffset(position)));
Expand Down

70 changes: 61 additions & 9 deletions
cpp/src/arrow/filesystem/gcsfs_test.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -671,7 +671,7 @@ TEST_F(GcsIntegrationTest, CopyFileNotFound) {
 ASSERT_RAISES(IOError, fs->CopyFile(NotFoundObjectPath(), destination_path));
}

TEST_F(GcsIntegrationTest, ReadObjectString) {
TEST_F(GcsIntegrationTest, OpenInputStreamString) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 std::shared_ptr<io::InputStream> stream;
Expand All@@ -684,7 +684,7 @@ TEST_F(GcsIntegrationTest, ReadObjectString) {
 EXPECT_EQ(std::string(buffer.data(), size), kLoremIpsum);
}

TEST_F(GcsIntegrationTest, ReadObjectStringBuffers) {
TEST_F(GcsIntegrationTest, OpenInputStreamStringBuffers) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 std::shared_ptr<io::InputStream> stream;
Expand All@@ -700,7 +700,7 @@ TEST_F(GcsIntegrationTest, ReadObjectStringBuffers) {
 EXPECT_EQ(contents, kLoremIpsum);
}

TEST_F(GcsIntegrationTest, ReadObjectInfo) {
TEST_F(GcsIntegrationTest, OpenInputStreamInfo) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 arrow::fs::FileInfo info;
Expand All@@ -716,13 +716,27 @@ TEST_F(GcsIntegrationTest, ReadObjectInfo) {
 EXPECT_EQ(std::string(buffer.data(), size), kLoremIpsum);
}

TEST_F(GcsIntegrationTest, ReadObjectNotFound) {
TEST_F(GcsIntegrationTest, OpenInputStreamEmpty) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 const auto object_path =
 internal::ConcatAbstractPath(PreexistingBucketName(), "empty-object.txt");
 CreateFile(fs.get(), object_path, std::string());

 ASSERT_OK_AND_ASSIGN(auto stream, fs->OpenInputStream(object_path));
 std::array<char, 1024> buffer{};
 std::int64_t size;
 ASSERT_OK_AND_ASSIGN(size, stream->Read(buffer.size(), buffer.data()));
 EXPECT_EQ(size, 0);
}

TEST_F(GcsIntegrationTest, OpenInputStreamNotFound) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 ASSERT_RAISES(IOError, fs->OpenInputStream(NotFoundObjectPath()));
}

TEST_F(GcsIntegrationTest, ReadObjectInfoInvalid) {
TEST_F(GcsIntegrationTest, OpenInputStreamInfoInvalid) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 arrow::fs::FileInfo info;
Expand All@@ -733,10 +747,10 @@ TEST_F(GcsIntegrationTest, ReadObjectInfoInvalid) {
 ASSERT_RAISES(IOError, fs->OpenInputStream(info));
}

TEST_F(GcsIntegrationTest, ReadObjectReadMetadata) {
TEST_F(GcsIntegrationTest, OpenInputStreamReadMetadata) {
 auto client = GcsClient();
 const auto custom_time = std::chrono::system_clock::now() + std::chrono::hours(1);
 const std::string object_name = "ReadObjectMetadataTest/simple.txt";
 const std::string object_name = "OpenInputStreamMetadataTest/simple.txt";
 const gcs::ObjectMetadata expected =
 client
 .InsertObject(PreexistingBucketName(), object_name,
Expand DownExpand Up@@ -795,7 +809,18 @@ TEST_F(GcsIntegrationTest, ReadObjectReadMetadata) {
 ASSERT_FALSE(actual->Contains("kmsKeyName"));
}

TEST_F(GcsIntegrationTest, WriteObjectSmall) {
TEST_F(GcsIntegrationTest, OpenInputStreamClosed) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 ASSERT_OK_AND_ASSIGN(auto stream, fs->OpenInputStream(PreexistingObjectPath()));
 ASSERT_OK(stream->Close());
 std::array<char, 16> buffer{};
 ASSERT_RAISES(Invalid, stream->Read(buffer.size(), buffer.data()));
 ASSERT_RAISES(Invalid, stream->Read(buffer.size()));
 ASSERT_RAISES(Invalid, stream->Tell());
}

TEST_F(GcsIntegrationTest, OpenOutputStreamSmall) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 const auto path = PreexistingBucketPath() + "test-write-object";
Expand All@@ -816,7 +841,7 @@ TEST_F(GcsIntegrationTest, WriteObjectSmall) {
 EXPECT_EQ(std::string(inbuf.data(), size), expected);
}

TEST_F(GcsIntegrationTest, WriteObjectLarge) {
TEST_F(GcsIntegrationTest, OpenOutputStreamLarge) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 const auto path = PreexistingBucketPath() + "test-write-object";
Expand DownExpand Up@@ -852,6 +877,19 @@ TEST_F(GcsIntegrationTest, WriteObjectLarge) {
 EXPECT_EQ(contents, buffers[0] + buffers[1] + buffers[2]);
}

TEST_F(GcsIntegrationTest, OpenOutputStreamClosed) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 const auto path = internal::ConcatAbstractPath(PreexistingBucketName(),
 "open-output-stream-closed.txt");
 std::shared_ptr<io::OutputStream> output;
 ASSERT_OK_AND_ASSIGN(output, fs->OpenOutputStream(path, {}));
 ASSERT_OK(output->Close());
 ASSERT_RAISES(Invalid, output->Write(kLoremIpsum, std::strlen(kLoremIpsum)));
 ASSERT_RAISES(Invalid, output->Flush());
 ASSERT_RAISES(Invalid, output->Tell());
}

TEST_F(GcsIntegrationTest, OpenInputFileMixedReadVsReadAt) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

Expand DownExpand Up@@ -971,6 +1009,20 @@ TEST_F(GcsIntegrationTest, OpenInputFileInfoInvalid) {
 ASSERT_RAISES(IOError, fs->OpenInputFile(info));
}

TEST_F(GcsIntegrationTest, OpenInputFileClosed) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 ASSERT_OK_AND_ASSIGN(auto stream, fs->OpenInputFile(PreexistingObjectPath()));
 ASSERT_OK(stream->Close());
 std::array<char, 16> buffer{};
 ASSERT_RAISES(Invalid, stream->Tell());
 ASSERT_RAISES(Invalid, stream->Read(buffer.size(), buffer.data()));
 ASSERT_RAISES(Invalid, stream->Read(buffer.size()));
 ASSERT_RAISES(Invalid, stream->ReadAt(1, buffer.size(), buffer.data()));
 ASSERT_RAISES(Invalid, stream->ReadAt(1, 1));
 ASSERT_RAISES(Invalid, stream->Seek(2));
}

} // namespace
} // namespace fs
} // namespace arrow

, '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
ARROW-15115: [C++] GcsFileSystem return errors if using closed streams#11976

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

 Closed

coryan
wants to merge
2
commits into

from

 Closed


ARROW-15115: [C++] GcsFileSystem return errors if using closed streams
#11976
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


2 commits


Select commit
Hold shift + click to select a range
d211922

ARROW-15115: [C++] GcsFileSystem return errors if using closed streams


coryan Dec 16, 2021
6ab9447

Address review comments


coryan Dec 20, 2021

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


35 changes: 27 additions & 8 deletions
cpp/src/arrow/filesystem/gcsfs.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -96,28 +96,32 @@ class GcsInputStream : public arrow::io::InputStream {
 // @name FileInterface
 Status Close() override {
 stream_.Close();
 closed_ = true;
 return Status::OK();
 }

 Result<int64_t> Tell() const override {
 if (!stream_) {
 return Status::IOError("invalid stream");
 }
 if (closed()) return Status::Invalid("Cannot use Tell() on a closed stream");
 return stream_.tellg() + offset_;
 }

 bool closed() const override { return !stream_.IsOpen(); }
 // A gcs::ObjectReadStream can be "born closed". For small objects the stream returns
 // `IsOpen() == false` as soon as it is created, but the application can still read from
 // it.
 bool closed() const override { return closed_ && !stream_.IsOpen(); }
@pitroupitrouDec 20, 2021

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

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

Is there a reason this is && rather than ||?
@coryancoryanDec 20, 2021

Copy link


Copy Markdown

ContributorAuthor
Choose a reason for hiding this comment

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

Yes. zero-length objects are "born closed" in google-cloud-cpp. Probably a bug (or at least a very poorly thought API), but you can read() from them, while they return IsOpen() == false.
@pitroupitrouDec 20, 2021

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

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

Ah, can you add a comment about that?
@coryancoryanDec 20, 2021

Copy link


Copy Markdown

ContributorAuthor
Choose a reason for hiding this comment

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

Done. That got me thinking about the similar expression for output streams, and you were right in that case. Fixed that too.
 //@}

 //@{
 // @name Readable
 Result<int64_t> Read(int64_t nbytes, void* out) override {
 if (closed()) return Status::Invalid("Cannot read from a closed stream");
 stream_.read(static_cast<char*>(out), nbytes);
 ARROW_GCS_RETURN_NOT_OK(stream_.status());
 return stream_.gcount();
 }

 Result<std::shared_ptr<Buffer>> Read(int64_t nbytes) override {
 if (closed()) return Status::Invalid("Cannot read from a closed stream");
 ARROW_ASSIGN_OR_RAISE(auto buffer, arrow::AllocateResizableBuffer(nbytes));
 stream_.read(reinterpret_cast<char*>(buffer->mutable_data()), nbytes);
 ARROW_GCS_RETURN_NOT_OK(stream_.status());
Expand All@@ -142,6 +146,7 @@ class GcsInputStream : public arrow::io::InputStream {
 gcs::Generation generation_;
 std::int64_t offset_;
 gcs::Client client_;
 bool closed_ = false;
};

class GcsOutputStream : public arrow::io::OutputStream {
Expand All@@ -151,19 +156,28 @@ class GcsOutputStream : public arrow::io::OutputStream {

 Status Close() override {
 stream_.Close();
 closed_ = true;
 return internal::ToArrowStatus(stream_.last_status());
 }

 Result<int64_t> Tell() const override {
 if (!stream_) {
 return Status::IOError("invalid stream");
 }
 if (closed()) return Status::Invalid("Cannot use Tell() on a closed stream");
 return tell_;
 }

 bool closed() const override { return !stream_.IsOpen(); }
 // gcs::ObjectWriteStream can be "closed" without an explicit Close() call. At this time
 // this class does not use any of the mechanisms [*] that trigger such behavior.
 // Nevertheless, we defensively prepare for them by checking either condition.
 //
 // [*]: These mechanisms include:
 // - resumable uploads that are "resumed" after the upload completed are born
 // "closed",
 // - uploads that prescribe their total size using the `x-upload-content-length` header
 // are completed and "closed" as soon as the upload reaches that size.
 bool closed() const override { return closed_ || !stream_.IsOpen(); }

 Status Write(const void* data, int64_t nbytes) override {
 if (closed()) return Status::Invalid("Cannot write to a closed stream");
 if (stream_.write(reinterpret_cast<const char*>(data), nbytes)) {
 tell_ += nbytes;
 return Status::OK();
Expand All@@ -172,13 +186,15 @@ class GcsOutputStream : public arrow::io::OutputStream {
 }

 Status Flush() override {
 if (closed()) return Status::Invalid("Cannot flush a closed stream");
 stream_.flush();
 return Status::OK();
 }

 private:
 gcs::ObjectWriteStream stream_;
 int64_t tell_ = 0;
 bool closed_ = false;
};

using InputStreamFactory = std::function<Result<std::shared_ptr<io::InputStream>>(
Expand DownExpand Up@@ -225,13 +241,15 @@ class GcsRandomAccessFile : public arrow::io::RandomAccessFile {
 // @name RandomAccessFile
 Result<int64_t> GetSize() override { return metadata_.size(); }
 Result<int64_t> ReadAt(int64_t position, int64_t nbytes, void* out) override {
 if (closed()) return Status::Invalid("Cannot read from closed file");
 std::shared_ptr<io::InputStream> stream;
 ARROW_ASSIGN_OR_RAISE(stream, factory_(metadata_.bucket(), metadata_.name(),
 gcs::Generation(metadata_.generation()),
 gcs::ReadFromOffset(position)));
 return stream->Read(nbytes, out);
 }
 Result<std::shared_ptr<Buffer>> ReadAt(int64_t position, int64_t nbytes) override {
 if (closed()) return Status::Invalid("Cannot read from closed file");
 std::shared_ptr<io::InputStream> stream;
 ARROW_ASSIGN_OR_RAISE(stream, factory_(metadata_.bucket(), metadata_.name(),
 gcs::Generation(metadata_.generation()),
Expand All@@ -242,6 +260,7 @@ class GcsRandomAccessFile : public arrow::io::RandomAccessFile {

 // from Seekable
 Status Seek(int64_t position) override {
 if (closed()) return Status::Invalid("Cannot seek in a closed file");
 ARROW_ASSIGN_OR_RAISE(stream_, factory_(metadata_.bucket(), metadata_.name(),
 gcs::Generation(metadata_.generation()),
 gcs::ReadFromOffset(position)));
Expand Down

70 changes: 61 additions & 9 deletions
cpp/src/arrow/filesystem/gcsfs_test.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -671,7 +671,7 @@ TEST_F(GcsIntegrationTest, CopyFileNotFound) {
 ASSERT_RAISES(IOError, fs->CopyFile(NotFoundObjectPath(), destination_path));
}

TEST_F(GcsIntegrationTest, ReadObjectString) {
TEST_F(GcsIntegrationTest, OpenInputStreamString) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 std::shared_ptr<io::InputStream> stream;
Expand All@@ -684,7 +684,7 @@ TEST_F(GcsIntegrationTest, ReadObjectString) {
 EXPECT_EQ(std::string(buffer.data(), size), kLoremIpsum);
}

TEST_F(GcsIntegrationTest, ReadObjectStringBuffers) {
TEST_F(GcsIntegrationTest, OpenInputStreamStringBuffers) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 std::shared_ptr<io::InputStream> stream;
Expand All@@ -700,7 +700,7 @@ TEST_F(GcsIntegrationTest, ReadObjectStringBuffers) {
 EXPECT_EQ(contents, kLoremIpsum);
}

TEST_F(GcsIntegrationTest, ReadObjectInfo) {
TEST_F(GcsIntegrationTest, OpenInputStreamInfo) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 arrow::fs::FileInfo info;
Expand All@@ -716,13 +716,27 @@ TEST_F(GcsIntegrationTest, ReadObjectInfo) {
 EXPECT_EQ(std::string(buffer.data(), size), kLoremIpsum);
}

TEST_F(GcsIntegrationTest, ReadObjectNotFound) {
TEST_F(GcsIntegrationTest, OpenInputStreamEmpty) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 const auto object_path =
 internal::ConcatAbstractPath(PreexistingBucketName(), "empty-object.txt");
 CreateFile(fs.get(), object_path, std::string());

 ASSERT_OK_AND_ASSIGN(auto stream, fs->OpenInputStream(object_path));
 std::array<char, 1024> buffer{};
 std::int64_t size;
 ASSERT_OK_AND_ASSIGN(size, stream->Read(buffer.size(), buffer.data()));
 EXPECT_EQ(size, 0);
}

TEST_F(GcsIntegrationTest, OpenInputStreamNotFound) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 ASSERT_RAISES(IOError, fs->OpenInputStream(NotFoundObjectPath()));
}

TEST_F(GcsIntegrationTest, ReadObjectInfoInvalid) {
TEST_F(GcsIntegrationTest, OpenInputStreamInfoInvalid) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 arrow::fs::FileInfo info;
Expand All@@ -733,10 +747,10 @@ TEST_F(GcsIntegrationTest, ReadObjectInfoInvalid) {
 ASSERT_RAISES(IOError, fs->OpenInputStream(info));
}

TEST_F(GcsIntegrationTest, ReadObjectReadMetadata) {
TEST_F(GcsIntegrationTest, OpenInputStreamReadMetadata) {
 auto client = GcsClient();
 const auto custom_time = std::chrono::system_clock::now() + std::chrono::hours(1);
 const std::string object_name = "ReadObjectMetadataTest/simple.txt";
 const std::string object_name = "OpenInputStreamMetadataTest/simple.txt";
 const gcs::ObjectMetadata expected =
 client
 .InsertObject(PreexistingBucketName(), object_name,
Expand DownExpand Up@@ -795,7 +809,18 @@ TEST_F(GcsIntegrationTest, ReadObjectReadMetadata) {
 ASSERT_FALSE(actual->Contains("kmsKeyName"));
}

TEST_F(GcsIntegrationTest, WriteObjectSmall) {
TEST_F(GcsIntegrationTest, OpenInputStreamClosed) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 ASSERT_OK_AND_ASSIGN(auto stream, fs->OpenInputStream(PreexistingObjectPath()));
 ASSERT_OK(stream->Close());
 std::array<char, 16> buffer{};
 ASSERT_RAISES(Invalid, stream->Read(buffer.size(), buffer.data()));
 ASSERT_RAISES(Invalid, stream->Read(buffer.size()));
 ASSERT_RAISES(Invalid, stream->Tell());
}

TEST_F(GcsIntegrationTest, OpenOutputStreamSmall) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 const auto path = PreexistingBucketPath() + "test-write-object";
Expand All@@ -816,7 +841,7 @@ TEST_F(GcsIntegrationTest, WriteObjectSmall) {
 EXPECT_EQ(std::string(inbuf.data(), size), expected);
}

TEST_F(GcsIntegrationTest, WriteObjectLarge) {
TEST_F(GcsIntegrationTest, OpenOutputStreamLarge) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 const auto path = PreexistingBucketPath() + "test-write-object";
Expand DownExpand Up@@ -852,6 +877,19 @@ TEST_F(GcsIntegrationTest, WriteObjectLarge) {
 EXPECT_EQ(contents, buffers[0] + buffers[1] + buffers[2]);
}

TEST_F(GcsIntegrationTest, OpenOutputStreamClosed) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 const auto path = internal::ConcatAbstractPath(PreexistingBucketName(),
 "open-output-stream-closed.txt");
 std::shared_ptr<io::OutputStream> output;
 ASSERT_OK_AND_ASSIGN(output, fs->OpenOutputStream(path, {}));
 ASSERT_OK(output->Close());
 ASSERT_RAISES(Invalid, output->Write(kLoremIpsum, std::strlen(kLoremIpsum)));
 ASSERT_RAISES(Invalid, output->Flush());
 ASSERT_RAISES(Invalid, output->Tell());
}

TEST_F(GcsIntegrationTest, OpenInputFileMixedReadVsReadAt) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

Expand DownExpand Up@@ -971,6 +1009,20 @@ TEST_F(GcsIntegrationTest, OpenInputFileInfoInvalid) {
 ASSERT_RAISES(IOError, fs->OpenInputFile(info));
}

TEST_F(GcsIntegrationTest, OpenInputFileClosed) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 ASSERT_OK_AND_ASSIGN(auto stream, fs->OpenInputFile(PreexistingObjectPath()));
 ASSERT_OK(stream->Close());
 std::array<char, 16> buffer{};
 ASSERT_RAISES(Invalid, stream->Tell());
 ASSERT_RAISES(Invalid, stream->Read(buffer.size(), buffer.data()));
 ASSERT_RAISES(Invalid, stream->Read(buffer.size()));
 ASSERT_RAISES(Invalid, stream->ReadAt(1, buffer.size(), buffer.data()));
 ASSERT_RAISES(Invalid, stream->ReadAt(1, 1));
 ASSERT_RAISES(Invalid, stream->Seek(2));
}

} // namespace
} // namespace fs
} // namespace arrow

, '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
ARROW-15115: [C++] GcsFileSystem return errors if using closed streams#11976

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

 Closed

coryan
wants to merge
2
commits into

from

 Closed


ARROW-15115: [C++] GcsFileSystem return errors if using closed streams
#11976
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


2 commits


Select commit
Hold shift + click to select a range
d211922

ARROW-15115: [C++] GcsFileSystem return errors if using closed streams


coryan Dec 16, 2021
6ab9447

Address review comments


coryan Dec 20, 2021

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


35 changes: 27 additions & 8 deletions
cpp/src/arrow/filesystem/gcsfs.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -96,28 +96,32 @@ class GcsInputStream : public arrow::io::InputStream {
 // @name FileInterface
 Status Close() override {
 stream_.Close();
 closed_ = true;
 return Status::OK();
 }

 Result<int64_t> Tell() const override {
 if (!stream_) {
 return Status::IOError("invalid stream");
 }
 if (closed()) return Status::Invalid("Cannot use Tell() on a closed stream");
 return stream_.tellg() + offset_;
 }

 bool closed() const override { return !stream_.IsOpen(); }
 // A gcs::ObjectReadStream can be "born closed". For small objects the stream returns
 // `IsOpen() == false` as soon as it is created, but the application can still read from
 // it.
 bool closed() const override { return closed_ && !stream_.IsOpen(); }
@pitroupitrouDec 20, 2021

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

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

Is there a reason this is && rather than ||?
@coryancoryanDec 20, 2021

Copy link


Copy Markdown

ContributorAuthor
Choose a reason for hiding this comment

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

Yes. zero-length objects are "born closed" in google-cloud-cpp. Probably a bug (or at least a very poorly thought API), but you can read() from them, while they return IsOpen() == false.
@pitroupitrouDec 20, 2021

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

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

Ah, can you add a comment about that?
@coryancoryanDec 20, 2021

Copy link


Copy Markdown

ContributorAuthor
Choose a reason for hiding this comment

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

Done. That got me thinking about the similar expression for output streams, and you were right in that case. Fixed that too.
 //@}

 //@{
 // @name Readable
 Result<int64_t> Read(int64_t nbytes, void* out) override {
 if (closed()) return Status::Invalid("Cannot read from a closed stream");
 stream_.read(static_cast<char*>(out), nbytes);
 ARROW_GCS_RETURN_NOT_OK(stream_.status());
 return stream_.gcount();
 }

 Result<std::shared_ptr<Buffer>> Read(int64_t nbytes) override {
 if (closed()) return Status::Invalid("Cannot read from a closed stream");
 ARROW_ASSIGN_OR_RAISE(auto buffer, arrow::AllocateResizableBuffer(nbytes));
 stream_.read(reinterpret_cast<char*>(buffer->mutable_data()), nbytes);
 ARROW_GCS_RETURN_NOT_OK(stream_.status());
Expand All@@ -142,6 +146,7 @@ class GcsInputStream : public arrow::io::InputStream {
 gcs::Generation generation_;
 std::int64_t offset_;
 gcs::Client client_;
 bool closed_ = false;
};

class GcsOutputStream : public arrow::io::OutputStream {
Expand All@@ -151,19 +156,28 @@ class GcsOutputStream : public arrow::io::OutputStream {

 Status Close() override {
 stream_.Close();
 closed_ = true;
 return internal::ToArrowStatus(stream_.last_status());
 }

 Result<int64_t> Tell() const override {
 if (!stream_) {
 return Status::IOError("invalid stream");
 }
 if (closed()) return Status::Invalid("Cannot use Tell() on a closed stream");
 return tell_;
 }

 bool closed() const override { return !stream_.IsOpen(); }
 // gcs::ObjectWriteStream can be "closed" without an explicit Close() call. At this time
 // this class does not use any of the mechanisms [*] that trigger such behavior.
 // Nevertheless, we defensively prepare for them by checking either condition.
 //
 // [*]: These mechanisms include:
 // - resumable uploads that are "resumed" after the upload completed are born
 // "closed",
 // - uploads that prescribe their total size using the `x-upload-content-length` header
 // are completed and "closed" as soon as the upload reaches that size.
 bool closed() const override { return closed_ || !stream_.IsOpen(); }

 Status Write(const void* data, int64_t nbytes) override {
 if (closed()) return Status::Invalid("Cannot write to a closed stream");
 if (stream_.write(reinterpret_cast<const char*>(data), nbytes)) {
 tell_ += nbytes;
 return Status::OK();
Expand All@@ -172,13 +186,15 @@ class GcsOutputStream : public arrow::io::OutputStream {
 }

 Status Flush() override {
 if (closed()) return Status::Invalid("Cannot flush a closed stream");
 stream_.flush();
 return Status::OK();
 }

 private:
 gcs::ObjectWriteStream stream_;
 int64_t tell_ = 0;
 bool closed_ = false;
};

using InputStreamFactory = std::function<Result<std::shared_ptr<io::InputStream>>(
Expand DownExpand Up@@ -225,13 +241,15 @@ class GcsRandomAccessFile : public arrow::io::RandomAccessFile {
 // @name RandomAccessFile
 Result<int64_t> GetSize() override { return metadata_.size(); }
 Result<int64_t> ReadAt(int64_t position, int64_t nbytes, void* out) override {
 if (closed()) return Status::Invalid("Cannot read from closed file");
 std::shared_ptr<io::InputStream> stream;
 ARROW_ASSIGN_OR_RAISE(stream, factory_(metadata_.bucket(), metadata_.name(),
 gcs::Generation(metadata_.generation()),
 gcs::ReadFromOffset(position)));
 return stream->Read(nbytes, out);
 }
 Result<std::shared_ptr<Buffer>> ReadAt(int64_t position, int64_t nbytes) override {
 if (closed()) return Status::Invalid("Cannot read from closed file");
 std::shared_ptr<io::InputStream> stream;
 ARROW_ASSIGN_OR_RAISE(stream, factory_(metadata_.bucket(), metadata_.name(),
 gcs::Generation(metadata_.generation()),
Expand All@@ -242,6 +260,7 @@ class GcsRandomAccessFile : public arrow::io::RandomAccessFile {

 // from Seekable
 Status Seek(int64_t position) override {
 if (closed()) return Status::Invalid("Cannot seek in a closed file");
 ARROW_ASSIGN_OR_RAISE(stream_, factory_(metadata_.bucket(), metadata_.name(),
 gcs::Generation(metadata_.generation()),
 gcs::ReadFromOffset(position)));
Expand Down

70 changes: 61 additions & 9 deletions
cpp/src/arrow/filesystem/gcsfs_test.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -671,7 +671,7 @@ TEST_F(GcsIntegrationTest, CopyFileNotFound) {
 ASSERT_RAISES(IOError, fs->CopyFile(NotFoundObjectPath(), destination_path));
}

TEST_F(GcsIntegrationTest, ReadObjectString) {
TEST_F(GcsIntegrationTest, OpenInputStreamString) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 std::shared_ptr<io::InputStream> stream;
Expand All@@ -684,7 +684,7 @@ TEST_F(GcsIntegrationTest, ReadObjectString) {
 EXPECT_EQ(std::string(buffer.data(), size), kLoremIpsum);
}

TEST_F(GcsIntegrationTest, ReadObjectStringBuffers) {
TEST_F(GcsIntegrationTest, OpenInputStreamStringBuffers) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 std::shared_ptr<io::InputStream> stream;
Expand All@@ -700,7 +700,7 @@ TEST_F(GcsIntegrationTest, ReadObjectStringBuffers) {
 EXPECT_EQ(contents, kLoremIpsum);
}

TEST_F(GcsIntegrationTest, ReadObjectInfo) {
TEST_F(GcsIntegrationTest, OpenInputStreamInfo) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 arrow::fs::FileInfo info;
Expand All@@ -716,13 +716,27 @@ TEST_F(GcsIntegrationTest, ReadObjectInfo) {
 EXPECT_EQ(std::string(buffer.data(), size), kLoremIpsum);
}

TEST_F(GcsIntegrationTest, ReadObjectNotFound) {
TEST_F(GcsIntegrationTest, OpenInputStreamEmpty) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 const auto object_path =
 internal::ConcatAbstractPath(PreexistingBucketName(), "empty-object.txt");
 CreateFile(fs.get(), object_path, std::string());

 ASSERT_OK_AND_ASSIGN(auto stream, fs->OpenInputStream(object_path));
 std::array<char, 1024> buffer{};
 std::int64_t size;
 ASSERT_OK_AND_ASSIGN(size, stream->Read(buffer.size(), buffer.data()));
 EXPECT_EQ(size, 0);
}

TEST_F(GcsIntegrationTest, OpenInputStreamNotFound) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 ASSERT_RAISES(IOError, fs->OpenInputStream(NotFoundObjectPath()));
}

TEST_F(GcsIntegrationTest, ReadObjectInfoInvalid) {
TEST_F(GcsIntegrationTest, OpenInputStreamInfoInvalid) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 arrow::fs::FileInfo info;
Expand All@@ -733,10 +747,10 @@ TEST_F(GcsIntegrationTest, ReadObjectInfoInvalid) {
 ASSERT_RAISES(IOError, fs->OpenInputStream(info));
}

TEST_F(GcsIntegrationTest, ReadObjectReadMetadata) {
TEST_F(GcsIntegrationTest, OpenInputStreamReadMetadata) {
 auto client = GcsClient();
 const auto custom_time = std::chrono::system_clock::now() + std::chrono::hours(1);
 const std::string object_name = "ReadObjectMetadataTest/simple.txt";
 const std::string object_name = "OpenInputStreamMetadataTest/simple.txt";
 const gcs::ObjectMetadata expected =
 client
 .InsertObject(PreexistingBucketName(), object_name,
Expand DownExpand Up@@ -795,7 +809,18 @@ TEST_F(GcsIntegrationTest, ReadObjectReadMetadata) {
 ASSERT_FALSE(actual->Contains("kmsKeyName"));
}

TEST_F(GcsIntegrationTest, WriteObjectSmall) {
TEST_F(GcsIntegrationTest, OpenInputStreamClosed) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 ASSERT_OK_AND_ASSIGN(auto stream, fs->OpenInputStream(PreexistingObjectPath()));
 ASSERT_OK(stream->Close());
 std::array<char, 16> buffer{};
 ASSERT_RAISES(Invalid, stream->Read(buffer.size(), buffer.data()));
 ASSERT_RAISES(Invalid, stream->Read(buffer.size()));
 ASSERT_RAISES(Invalid, stream->Tell());
}

TEST_F(GcsIntegrationTest, OpenOutputStreamSmall) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 const auto path = PreexistingBucketPath() + "test-write-object";
Expand All@@ -816,7 +841,7 @@ TEST_F(GcsIntegrationTest, WriteObjectSmall) {
 EXPECT_EQ(std::string(inbuf.data(), size), expected);
}

TEST_F(GcsIntegrationTest, WriteObjectLarge) {
TEST_F(GcsIntegrationTest, OpenOutputStreamLarge) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 const auto path = PreexistingBucketPath() + "test-write-object";
Expand DownExpand Up@@ -852,6 +877,19 @@ TEST_F(GcsIntegrationTest, WriteObjectLarge) {
 EXPECT_EQ(contents, buffers[0] + buffers[1] + buffers[2]);
}

TEST_F(GcsIntegrationTest, OpenOutputStreamClosed) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 const auto path = internal::ConcatAbstractPath(PreexistingBucketName(),
 "open-output-stream-closed.txt");
 std::shared_ptr<io::OutputStream> output;
 ASSERT_OK_AND_ASSIGN(output, fs->OpenOutputStream(path, {}));
 ASSERT_OK(output->Close());
 ASSERT_RAISES(Invalid, output->Write(kLoremIpsum, std::strlen(kLoremIpsum)));
 ASSERT_RAISES(Invalid, output->Flush());
 ASSERT_RAISES(Invalid, output->Tell());
}

TEST_F(GcsIntegrationTest, OpenInputFileMixedReadVsReadAt) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

Expand DownExpand Up@@ -971,6 +1009,20 @@ TEST_F(GcsIntegrationTest, OpenInputFileInfoInvalid) {
 ASSERT_RAISES(IOError, fs->OpenInputFile(info));
}

TEST_F(GcsIntegrationTest, OpenInputFileClosed) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 ASSERT_OK_AND_ASSIGN(auto stream, fs->OpenInputFile(PreexistingObjectPath()));
 ASSERT_OK(stream->Close());
 std::array<char, 16> buffer{};
 ASSERT_RAISES(Invalid, stream->Tell());
 ASSERT_RAISES(Invalid, stream->Read(buffer.size(), buffer.data()));
 ASSERT_RAISES(Invalid, stream->Read(buffer.size()));
 ASSERT_RAISES(Invalid, stream->ReadAt(1, buffer.size(), buffer.data()));
 ASSERT_RAISES(Invalid, stream->ReadAt(1, 1));
 ASSERT_RAISES(Invalid, stream->Seek(2));
}

} // namespace
} // namespace fs
} // namespace arrow

, '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
ARROW-15115: [C++] GcsFileSystem return errors if using closed streams#11976

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

 Closed

coryan
wants to merge
2
commits into

from

 Closed


ARROW-15115: [C++] GcsFileSystem return errors if using closed streams
#11976
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


2 commits


Select commit
Hold shift + click to select a range
d211922

ARROW-15115: [C++] GcsFileSystem return errors if using closed streams


coryan Dec 16, 2021
6ab9447

Address review comments


coryan Dec 20, 2021

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


35 changes: 27 additions & 8 deletions
cpp/src/arrow/filesystem/gcsfs.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -96,28 +96,32 @@ class GcsInputStream : public arrow::io::InputStream {
 // @name FileInterface
 Status Close() override {
 stream_.Close();
 closed_ = true;
 return Status::OK();
 }

 Result<int64_t> Tell() const override {
 if (!stream_) {
 return Status::IOError("invalid stream");
 }
 if (closed()) return Status::Invalid("Cannot use Tell() on a closed stream");
 return stream_.tellg() + offset_;
 }

 bool closed() const override { return !stream_.IsOpen(); }
 // A gcs::ObjectReadStream can be "born closed". For small objects the stream returns
 // `IsOpen() == false` as soon as it is created, but the application can still read from
 // it.
 bool closed() const override { return closed_ && !stream_.IsOpen(); }
@pitroupitrouDec 20, 2021

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

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

Is there a reason this is && rather than ||?
@coryancoryanDec 20, 2021

Copy link


Copy Markdown

ContributorAuthor
Choose a reason for hiding this comment

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

Yes. zero-length objects are "born closed" in google-cloud-cpp. Probably a bug (or at least a very poorly thought API), but you can read() from them, while they return IsOpen() == false.
@pitroupitrouDec 20, 2021

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

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

Ah, can you add a comment about that?
@coryancoryanDec 20, 2021

Copy link


Copy Markdown

ContributorAuthor
Choose a reason for hiding this comment

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

Done. That got me thinking about the similar expression for output streams, and you were right in that case. Fixed that too.
 //@}

 //@{
 // @name Readable
 Result<int64_t> Read(int64_t nbytes, void* out) override {
 if (closed()) return Status::Invalid("Cannot read from a closed stream");
 stream_.read(static_cast<char*>(out), nbytes);
 ARROW_GCS_RETURN_NOT_OK(stream_.status());
 return stream_.gcount();
 }

 Result<std::shared_ptr<Buffer>> Read(int64_t nbytes) override {
 if (closed()) return Status::Invalid("Cannot read from a closed stream");
 ARROW_ASSIGN_OR_RAISE(auto buffer, arrow::AllocateResizableBuffer(nbytes));
 stream_.read(reinterpret_cast<char*>(buffer->mutable_data()), nbytes);
 ARROW_GCS_RETURN_NOT_OK(stream_.status());
Expand All@@ -142,6 +146,7 @@ class GcsInputStream : public arrow::io::InputStream {
 gcs::Generation generation_;
 std::int64_t offset_;
 gcs::Client client_;
 bool closed_ = false;
};

class GcsOutputStream : public arrow::io::OutputStream {
Expand All@@ -151,19 +156,28 @@ class GcsOutputStream : public arrow::io::OutputStream {

 Status Close() override {
 stream_.Close();
 closed_ = true;
 return internal::ToArrowStatus(stream_.last_status());
 }

 Result<int64_t> Tell() const override {
 if (!stream_) {
 return Status::IOError("invalid stream");
 }
 if (closed()) return Status::Invalid("Cannot use Tell() on a closed stream");
 return tell_;
 }

 bool closed() const override { return !stream_.IsOpen(); }
 // gcs::ObjectWriteStream can be "closed" without an explicit Close() call. At this time
 // this class does not use any of the mechanisms [*] that trigger such behavior.
 // Nevertheless, we defensively prepare for them by checking either condition.
 //
 // [*]: These mechanisms include:
 // - resumable uploads that are "resumed" after the upload completed are born
 // "closed",
 // - uploads that prescribe their total size using the `x-upload-content-length` header
 // are completed and "closed" as soon as the upload reaches that size.
 bool closed() const override { return closed_ || !stream_.IsOpen(); }

 Status Write(const void* data, int64_t nbytes) override {
 if (closed()) return Status::Invalid("Cannot write to a closed stream");
 if (stream_.write(reinterpret_cast<const char*>(data), nbytes)) {
 tell_ += nbytes;
 return Status::OK();
Expand All@@ -172,13 +186,15 @@ class GcsOutputStream : public arrow::io::OutputStream {
 }

 Status Flush() override {
 if (closed()) return Status::Invalid("Cannot flush a closed stream");
 stream_.flush();
 return Status::OK();
 }

 private:
 gcs::ObjectWriteStream stream_;
 int64_t tell_ = 0;
 bool closed_ = false;
};

using InputStreamFactory = std::function<Result<std::shared_ptr<io::InputStream>>(
Expand DownExpand Up@@ -225,13 +241,15 @@ class GcsRandomAccessFile : public arrow::io::RandomAccessFile {
 // @name RandomAccessFile
 Result<int64_t> GetSize() override { return metadata_.size(); }
 Result<int64_t> ReadAt(int64_t position, int64_t nbytes, void* out) override {
 if (closed()) return Status::Invalid("Cannot read from closed file");
 std::shared_ptr<io::InputStream> stream;
 ARROW_ASSIGN_OR_RAISE(stream, factory_(metadata_.bucket(), metadata_.name(),
 gcs::Generation(metadata_.generation()),
 gcs::ReadFromOffset(position)));
 return stream->Read(nbytes, out);
 }
 Result<std::shared_ptr<Buffer>> ReadAt(int64_t position, int64_t nbytes) override {
 if (closed()) return Status::Invalid("Cannot read from closed file");
 std::shared_ptr<io::InputStream> stream;
 ARROW_ASSIGN_OR_RAISE(stream, factory_(metadata_.bucket(), metadata_.name(),
 gcs::Generation(metadata_.generation()),
Expand All@@ -242,6 +260,7 @@ class GcsRandomAccessFile : public arrow::io::RandomAccessFile {

 // from Seekable
 Status Seek(int64_t position) override {
 if (closed()) return Status::Invalid("Cannot seek in a closed file");
 ARROW_ASSIGN_OR_RAISE(stream_, factory_(metadata_.bucket(), metadata_.name(),
 gcs::Generation(metadata_.generation()),
 gcs::ReadFromOffset(position)));
Expand Down

70 changes: 61 additions & 9 deletions
cpp/src/arrow/filesystem/gcsfs_test.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -671,7 +671,7 @@ TEST_F(GcsIntegrationTest, CopyFileNotFound) {
 ASSERT_RAISES(IOError, fs->CopyFile(NotFoundObjectPath(), destination_path));
}

TEST_F(GcsIntegrationTest, ReadObjectString) {
TEST_F(GcsIntegrationTest, OpenInputStreamString) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 std::shared_ptr<io::InputStream> stream;
Expand All@@ -684,7 +684,7 @@ TEST_F(GcsIntegrationTest, ReadObjectString) {
 EXPECT_EQ(std::string(buffer.data(), size), kLoremIpsum);
}

TEST_F(GcsIntegrationTest, ReadObjectStringBuffers) {
TEST_F(GcsIntegrationTest, OpenInputStreamStringBuffers) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 std::shared_ptr<io::InputStream> stream;
Expand All@@ -700,7 +700,7 @@ TEST_F(GcsIntegrationTest, ReadObjectStringBuffers) {
 EXPECT_EQ(contents, kLoremIpsum);
}

TEST_F(GcsIntegrationTest, ReadObjectInfo) {
TEST_F(GcsIntegrationTest, OpenInputStreamInfo) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 arrow::fs::FileInfo info;
Expand All@@ -716,13 +716,27 @@ TEST_F(GcsIntegrationTest, ReadObjectInfo) {
 EXPECT_EQ(std::string(buffer.data(), size), kLoremIpsum);
}

TEST_F(GcsIntegrationTest, ReadObjectNotFound) {
TEST_F(GcsIntegrationTest, OpenInputStreamEmpty) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 const auto object_path =
 internal::ConcatAbstractPath(PreexistingBucketName(), "empty-object.txt");
 CreateFile(fs.get(), object_path, std::string());

 ASSERT_OK_AND_ASSIGN(auto stream, fs->OpenInputStream(object_path));
 std::array<char, 1024> buffer{};
 std::int64_t size;
 ASSERT_OK_AND_ASSIGN(size, stream->Read(buffer.size(), buffer.data()));
 EXPECT_EQ(size, 0);
}

TEST_F(GcsIntegrationTest, OpenInputStreamNotFound) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 ASSERT_RAISES(IOError, fs->OpenInputStream(NotFoundObjectPath()));
}

TEST_F(GcsIntegrationTest, ReadObjectInfoInvalid) {
TEST_F(GcsIntegrationTest, OpenInputStreamInfoInvalid) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 arrow::fs::FileInfo info;
Expand All@@ -733,10 +747,10 @@ TEST_F(GcsIntegrationTest, ReadObjectInfoInvalid) {
 ASSERT_RAISES(IOError, fs->OpenInputStream(info));
}

TEST_F(GcsIntegrationTest, ReadObjectReadMetadata) {
TEST_F(GcsIntegrationTest, OpenInputStreamReadMetadata) {
 auto client = GcsClient();
 const auto custom_time = std::chrono::system_clock::now() + std::chrono::hours(1);
 const std::string object_name = "ReadObjectMetadataTest/simple.txt";
 const std::string object_name = "OpenInputStreamMetadataTest/simple.txt";
 const gcs::ObjectMetadata expected =
 client
 .InsertObject(PreexistingBucketName(), object_name,
Expand DownExpand Up@@ -795,7 +809,18 @@ TEST_F(GcsIntegrationTest, ReadObjectReadMetadata) {
 ASSERT_FALSE(actual->Contains("kmsKeyName"));
}

TEST_F(GcsIntegrationTest, WriteObjectSmall) {
TEST_F(GcsIntegrationTest, OpenInputStreamClosed) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 ASSERT_OK_AND_ASSIGN(auto stream, fs->OpenInputStream(PreexistingObjectPath()));
 ASSERT_OK(stream->Close());
 std::array<char, 16> buffer{};
 ASSERT_RAISES(Invalid, stream->Read(buffer.size(), buffer.data()));
 ASSERT_RAISES(Invalid, stream->Read(buffer.size()));
 ASSERT_RAISES(Invalid, stream->Tell());
}

TEST_F(GcsIntegrationTest, OpenOutputStreamSmall) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 const auto path = PreexistingBucketPath() + "test-write-object";
Expand All@@ -816,7 +841,7 @@ TEST_F(GcsIntegrationTest, WriteObjectSmall) {
 EXPECT_EQ(std::string(inbuf.data(), size), expected);
}

TEST_F(GcsIntegrationTest, WriteObjectLarge) {
TEST_F(GcsIntegrationTest, OpenOutputStreamLarge) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 const auto path = PreexistingBucketPath() + "test-write-object";
Expand DownExpand Up@@ -852,6 +877,19 @@ TEST_F(GcsIntegrationTest, WriteObjectLarge) {
 EXPECT_EQ(contents, buffers[0] + buffers[1] + buffers[2]);
}

TEST_F(GcsIntegrationTest, OpenOutputStreamClosed) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 const auto path = internal::ConcatAbstractPath(PreexistingBucketName(),
 "open-output-stream-closed.txt");
 std::shared_ptr<io::OutputStream> output;
 ASSERT_OK_AND_ASSIGN(output, fs->OpenOutputStream(path, {}));
 ASSERT_OK(output->Close());
 ASSERT_RAISES(Invalid, output->Write(kLoremIpsum, std::strlen(kLoremIpsum)));
 ASSERT_RAISES(Invalid, output->Flush());
 ASSERT_RAISES(Invalid, output->Tell());
}

TEST_F(GcsIntegrationTest, OpenInputFileMixedReadVsReadAt) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

Expand DownExpand Up@@ -971,6 +1009,20 @@ TEST_F(GcsIntegrationTest, OpenInputFileInfoInvalid) {
 ASSERT_RAISES(IOError, fs->OpenInputFile(info));
}

TEST_F(GcsIntegrationTest, OpenInputFileClosed) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());

 ASSERT_OK_AND_ASSIGN(auto stream, fs->OpenInputFile(PreexistingObjectPath()));
 ASSERT_OK(stream->Close());
 std::array<char, 16> buffer{};
 ASSERT_RAISES(Invalid, stream->Tell());
 ASSERT_RAISES(Invalid, stream->Read(buffer.size(), buffer.data()));
 ASSERT_RAISES(Invalid, stream->Read(buffer.size()));
 ASSERT_RAISES(Invalid, stream->ReadAt(1, buffer.size(), buffer.data()));
 ASSERT_RAISES(Invalid, stream->ReadAt(1, 1));
 ASSERT_RAISES(Invalid, stream->Seek(2));
}

} // namespace
} // namespace fs
} // namespace arrow