ARROW-10998: [C++] Detect URIs where a filesystem path is expected#11997

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
pitrou wants to merge 3 commits into from
Closed

ARROW-10998: [C++] Detect URIs where a filesystem path is expected #11997

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
088129c
ARROW-10998: [C++] Detect URIs where a filesystem path is expected
pitrou Dec 20, 2021
88c7858
Use preferred URI scheme in GCS tests
pitrou Dec 20, 2021
fe73f3a
Fix typo
pitrou 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
121 changes: 61 additions & 60 deletions cpp/src/arrow/filesystem/filesystem.cc
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -245,6 +245,17 @@ Result<std::shared_ptr<io::OutputStream>> FileSystem::OpenAppendStream(
//////////////////////////////////////////////////////////////////////////
// SubTreeFileSystem implementation

namespace {

Status ValidateSubPath(util::string_view s) {
if (internal::IsLikelyUri(s)) {
return Status::Invalid("Expected a filesystem path, got a URI: '", s, "'");
}
return Status::OK();
}

} // namespace

SubTreeFileSystem::SubTreeFileSystem(const std::string& base_path,
std::shared_ptr<FileSystem> base_fs)
: FileSystem(base_fs->io_context()),
Expand All@@ -270,20 +281,21 @@ bool SubTreeFileSystem::Equals(const FileSystem& other) const {
return base_path_ == subfs.base_path_ && base_fs_->Equals(subfs.base_fs_);
}

std::string SubTreeFileSystem::PrependBase(const std::string& s) const {
Result<std::string> SubTreeFileSystem::PrependBase(const std::string& s) const {
RETURN_NOT_OK(ValidateSubPath(s));
if (s.empty()) {
return base_path_;
} else {
return ConcatAbstractPath(base_path_, s);
}
}

Status SubTreeFileSystem::PrependBaseNonEmpty(std::string* s) const {
if (s->empty()) {
Result<std::string> SubTreeFileSystem::PrependBaseNonEmpty(const std::string& s) const {
RETURN_NOT_OK(ValidateSubPath(s));
if (s.empty()) {
return Status::IOError("Empty path");
} else {
*s = ConcatAbstractPath(base_path_, *s);
return Status::OK();
return ConcatAbstractPath(base_path_, s);
}
}

Expand All@@ -305,19 +317,21 @@ Status SubTreeFileSystem::FixInfo(FileInfo* info) const {
}

Result<std::string> SubTreeFileSystem::NormalizePath(std::string path) {
ARROW_ASSIGN_OR_RAISE(auto normalized, base_fs_->NormalizePath(PrependBase(path)));
ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBase(path));
ARROW_ASSIGN_OR_RAISE(auto normalized, base_fs_->NormalizePath(real_path));
return StripBase(std::move(normalized));
}

Result<FileInfo> SubTreeFileSystem::GetFileInfo(const std::string& path) {
ARROW_ASSIGN_OR_RAISE(FileInfo info, base_fs_->GetFileInfo(PrependBase(path)));
ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBase(path));
ARROW_ASSIGN_OR_RAISE(FileInfo info, base_fs_->GetFileInfo(real_path));
RETURN_NOT_OK(FixInfo(&info));
return info;
}

Result<std::vector<FileInfo>> SubTreeFileSystem::GetFileInfo(const FileSelector& select) {
auto selector = select;
selector.base_dir = PrependBase(selector.base_dir);
ARROW_ASSIGN_OR_RAISE(selector.base_dir, PrependBase(selector.base_dir));
ARROW_ASSIGN_OR_RAISE(auto infos, base_fs_->GetFileInfo(selector));
for (auto& info : infos) {
RETURN_NOT_OK(FixInfo(&info));
Expand All@@ -327,7 +341,11 @@ Result<std::vector<FileInfo>> SubTreeFileSystem::GetFileInfo(const FileSelector&

FileInfoGenerator SubTreeFileSystem::GetFileInfoGenerator(const FileSelector& select) {
auto selector = select;
selector.base_dir = PrependBase(selector.base_dir);
auto maybe_base_dir = PrependBase(selector.base_dir);
if (!maybe_base_dir.ok()) {
return MakeFailingGenerator<std::vector<FileInfo>>(maybe_base_dir.status());
}
selector.base_dir = *std::move(maybe_base_dir);
auto gen = base_fs_->GetFileInfoGenerator(selector);

auto self = checked_pointer_cast<SubTreeFileSystem>(shared_from_this());
Expand All@@ -343,23 +361,21 @@ FileInfoGenerator SubTreeFileSystem::GetFileInfoGenerator(const FileSelector& se
}

Status SubTreeFileSystem::CreateDir(const std::string& path, bool recursive) {
auto s = path;
RETURN_NOT_OK(PrependBaseNonEmpty(&s));
return base_fs_->CreateDir(s, recursive);
ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
return base_fs_->CreateDir(real_path, recursive);
}

Status SubTreeFileSystem::DeleteDir(const std::string& path) {
auto s = path;
RETURN_NOT_OK(PrependBaseNonEmpty(&s));
return base_fs_->DeleteDir(s);
ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
return base_fs_->DeleteDir(real_path);
}

Status SubTreeFileSystem::DeleteDirContents(const std::string& path) {
if (internal::IsEmptyPath(path)) {
return internal::InvalidDeleteDirContents(path);
}
auto s = PrependBase(path);
return base_fs_->DeleteDirContents(s);
ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBase(path));
return base_fs_->DeleteDirContents(real_path);
}

Status SubTreeFileSystem::DeleteRootDirContents() {
Expand All@@ -371,103 +387,88 @@ Status SubTreeFileSystem::DeleteRootDirContents() {
}

Status SubTreeFileSystem::DeleteFile(const std::string& path) {
auto s = path;
RETURN_NOT_OK(PrependBaseNonEmpty(&s));
return base_fs_->DeleteFile(s);
ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
return base_fs_->DeleteFile(real_path);
}

Status SubTreeFileSystem::Move(const std::string& src, const std::string& dest) {
auto s = src;
auto d = dest;
RETURN_NOT_OK(PrependBaseNonEmpty(&s));
RETURN_NOT_OK(PrependBaseNonEmpty(&d));
return base_fs_->Move(s, d);
ARROW_ASSIGN_OR_RAISE(auto real_src, PrependBaseNonEmpty(src));
ARROW_ASSIGN_OR_RAISE(auto real_dest, PrependBaseNonEmpty(dest));
return base_fs_->Move(real_src, real_dest);
}

Status SubTreeFileSystem::CopyFile(const std::string& src, const std::string& dest) {
auto s = src;
auto d = dest;
RETURN_NOT_OK(PrependBaseNonEmpty(&s));
RETURN_NOT_OK(PrependBaseNonEmpty(&d));
return base_fs_->CopyFile(s, d);
ARROW_ASSIGN_OR_RAISE(auto real_src, PrependBaseNonEmpty(src));
ARROW_ASSIGN_OR_RAISE(auto real_dest, PrependBaseNonEmpty(dest));
return base_fs_->CopyFile(real_src, real_dest);
}

Result<std::shared_ptr<io::InputStream>> SubTreeFileSystem::OpenInputStream(
const std::string& path) {
auto s = path;
RETURN_NOT_OK(PrependBaseNonEmpty(&s));
return base_fs_->OpenInputStream(s);
ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
return base_fs_->OpenInputStream(real_path);
}

Result<std::shared_ptr<io::InputStream>> SubTreeFileSystem::OpenInputStream(
const FileInfo& info) {
auto s = info.path();
RETURN_NOT_OK(PrependBaseNonEmpty(&s));
ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(info.path()));
FileInfo new_info(info);
new_info.set_path(std::move(s));
new_info.set_path(std::move(real_path));
return base_fs_->OpenInputStream(new_info);
}

Future<std::shared_ptr<io::InputStream>> SubTreeFileSystem::OpenInputStreamAsync(
const std::string& path) {
auto s = path;
RETURN_NOT_OK(PrependBaseNonEmpty(&s));
return base_fs_->OpenInputStreamAsync(s);
ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
return base_fs_->OpenInputStreamAsync(real_path);
}

Future<std::shared_ptr<io::InputStream>> SubTreeFileSystem::OpenInputStreamAsync(
const FileInfo& info) {
auto s = info.path();
RETURN_NOT_OK(PrependBaseNonEmpty(&s));
ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(info.path()));
FileInfo new_info(info);
new_info.set_path(std::move(s));
new_info.set_path(std::move(real_path));
return base_fs_->OpenInputStreamAsync(new_info);
}

Result<std::shared_ptr<io::RandomAccessFile>> SubTreeFileSystem::OpenInputFile(
const std::string& path) {
auto s = path;
RETURN_NOT_OK(PrependBaseNonEmpty(&s));
return base_fs_->OpenInputFile(s);
ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
return base_fs_->OpenInputFile(real_path);
}

Result<std::shared_ptr<io::RandomAccessFile>> SubTreeFileSystem::OpenInputFile(
const FileInfo& info) {
auto s = info.path();
RETURN_NOT_OK(PrependBaseNonEmpty(&s));
ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(info.path()));
FileInfo new_info(info);
new_info.set_path(std::move(s));
new_info.set_path(std::move(real_path));
return base_fs_->OpenInputFile(new_info);
}

Future<std::shared_ptr<io::RandomAccessFile>> SubTreeFileSystem::OpenInputFileAsync(
const std::string& path) {
auto s = path;
RETURN_NOT_OK(PrependBaseNonEmpty(&s));
return base_fs_->OpenInputFileAsync(s);
ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
return base_fs_->OpenInputFileAsync(real_path);
}

Future<std::shared_ptr<io::RandomAccessFile>> SubTreeFileSystem::OpenInputFileAsync(
const FileInfo& info) {
auto s = info.path();
RETURN_NOT_OK(PrependBaseNonEmpty(&s));
ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(info.path()));
FileInfo new_info(info);
new_info.set_path(std::move(s));
new_info.set_path(std::move(real_path));
return base_fs_->OpenInputFileAsync(new_info);
}

Result<std::shared_ptr<io::OutputStream>> SubTreeFileSystem::OpenOutputStream(
const std::string& path, const std::shared_ptr<const KeyValueMetadata>& metadata) {
auto s = path;
RETURN_NOT_OK(PrependBaseNonEmpty(&s));
return base_fs_->OpenOutputStream(s, metadata);
ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
return base_fs_->OpenOutputStream(real_path, metadata);
}

Result<std::shared_ptr<io::OutputStream>> SubTreeFileSystem::OpenAppendStream(
const std::string& path, const std::shared_ptr<const KeyValueMetadata>& metadata) {
auto s = path;
RETURN_NOT_OK(PrependBaseNonEmpty(&s));
return base_fs_->OpenAppendStream(s, metadata);
ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
return base_fs_->OpenAppendStream(real_path, metadata);
}

//////////////////////////////////////////////////////////////////////////
Expand Down
4 changes: 2 additions & 2 deletions cpp/src/arrow/filesystem/filesystem.h
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -384,8 +384,8 @@ class ARROW_EXPORT SubTreeFileSystem : public FileSystem {
const std::string base_path_;
std::shared_ptr<FileSystem> base_fs_;

std::string PrependBase(const std::string& s) const;
Status PrependBaseNonEmpty(std::string* s) const;
Result<std::string> PrependBase(const std::string& s) const;
Result<std::string> PrependBaseNonEmpty(const std::string& s) const;
Result<std::string> StripBase(const std::string& s) const;
Status FixInfo(FileInfo* info) const;

Expand Down
4 changes: 4 additions & 0 deletions cpp/src/arrow/filesystem/gcsfs.cc
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -57,6 +57,10 @@ struct GcsPath {
std::string object;

static Result<GcsPath> FromString(const std::string& s) {
if (internal::IsLikelyUri(s)) {
return Status::Invalid(
"Expected a GCS object path of the form 'bucket/key...', got a URI: '", s, "'");
}
auto const first_sep = s.find_first_of(internal::kSep);
if (first_sep == 0) {
return Status::Invalid("Path cannot start with a separator ('", s, "')");
Expand Down
54 changes: 54 additions & 0 deletions cpp/src/arrow/filesystem/gcsfs_test.cc
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -478,6 +478,9 @@ TEST(GcsFileSystem, ObjectMetadataRoundtrip) {
TEST_F(GcsIntegrationTest, GetFileInfoBucket) {
auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
arrow::fs::AssertFileInfo(fs.get(), PreexistingBucketPath(), FileType::Directory);

// URI
ASSERT_RAISES(Invalid, fs->GetFileInfo("gs://" + PreexistingBucketPath()));
}

TEST_F(GcsIntegrationTest, GetFileInfoObject) {
Expand All@@ -487,6 +490,9 @@ TEST_F(GcsIntegrationTest, GetFileInfoObject) {
ASSERT_TRUE(object.ok()) << "status=" << object.status();
arrow::fs::AssertFileInfo(fs.get(), PreexistingObjectPath(), FileType::File,
object->time_created(), static_cast<int64_t>(object->size()));

// URI
ASSERT_RAISES(Invalid, fs->GetFileInfo("gs://" + PreexistingObjectName()));
}

TEST_F(GcsIntegrationTest, GetFileInfoSelectorRecursive) {
Expand All@@ -508,6 +514,10 @@ TEST_F(GcsIntegrationTest, GetFileInfoSelectorRecursive) {
selector.max_recursion = 16;
ASSERT_OK_AND_ASSIGN(auto results, fs->GetFileInfo(selector));
EXPECT_THAT(results, UnorderedElementsAreArray(expected.begin(), expected.end()));

// URI
selector.base_dir = "gs://" + selector.base_dir;
ASSERT_RAISES(Invalid, fs->GetFileInfo(selector));
}

TEST_F(GcsIntegrationTest, GetFileInfoSelectorNonRecursive) {
Expand DownExpand Up@@ -626,6 +636,11 @@ TEST_F(GcsIntegrationTest, CreateDirRecursiveBucketAndFolder) {
arrow::fs::AssertFileInfo(fs.get(), bucket_name + "/", FileType::Directory);
}

TEST_F(GcsIntegrationTest, CreateDirUri) {
auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
ASSERT_RAISES(Invalid, fs->CreateDir("gs://" + RandomBucketName(), true));
}

TEST_F(GcsIntegrationTest, DeleteDirSuccess) {
auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
ASSERT_OK_AND_ASSIGN(auto hierarchy, CreateHierarchy(fs));
Expand All@@ -641,6 +656,11 @@ TEST_F(GcsIntegrationTest, DeleteDirSuccess) {
}
}

TEST_F(GcsIntegrationTest, DeleteDirUri) {
auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
ASSERT_RAISES(Invalid, fs->DeleteDir("gs://" + PreexistingBucketPath()));
}

TEST_F(GcsIntegrationTest, DeleteDirContentsSuccess) {
auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
ASSERT_OK_AND_ASSIGN(auto hierarchy, CreateHierarchy(fs));
Expand DownExpand Up@@ -682,6 +702,11 @@ TEST_F(GcsIntegrationTest, DeleteFileDirectoryFails) {
ASSERT_RAISES(IOError, fs->DeleteFile(path));
}

TEST_F(GcsIntegrationTest, DeleteFileUri) {
auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
ASSERT_RAISES(Invalid, fs->DeleteFile("gs://" + PreexistingObjectPath()));
}

TEST_F(GcsIntegrationTest, MoveFileSuccess) {
auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
const auto destination_path = PreexistingBucketPath() + "move-destination";
Expand All@@ -708,6 +733,13 @@ TEST_F(GcsIntegrationTest, MoveFileCannotRenameToDirectory) {
PreexistingBucketPath() + "destination/"));
}

TEST_F(GcsIntegrationTest, MoveFileUri) {
auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
const auto destination_path = PreexistingBucketPath() + "move-destination";
ASSERT_RAISES(Invalid, fs->Move("gs://" + PreexistingObjectPath(), destination_path));
ASSERT_RAISES(Invalid, fs->Move(PreexistingObjectPath(), "gs://" + destination_path));
}

TEST_F(GcsIntegrationTest, CopyFileSuccess) {
auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
const auto destination_path = PreexistingBucketPath() + "copy-destination";
Expand All@@ -721,6 +753,15 @@ TEST_F(GcsIntegrationTest, CopyFileNotFound) {
ASSERT_RAISES(IOError, fs->CopyFile(NotFoundObjectPath(), destination_path));
}

TEST_F(GcsIntegrationTest, CopyFileUri) {
auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
const auto destination_path = PreexistingBucketPath() + "copy-destination";
ASSERT_RAISES(Invalid,
fs->CopyFile("gs://" + PreexistingObjectPath(), destination_path));
ASSERT_RAISES(Invalid,
fs->CopyFile(PreexistingObjectPath(), "gs://" + destination_path));
}

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

Expand DownExpand Up@@ -797,6 +838,11 @@ TEST_F(GcsIntegrationTest, OpenInputStreamInfoInvalid) {
ASSERT_RAISES(IOError, fs->OpenInputStream(info));
}

TEST_F(GcsIntegrationTest, OpenInputStreamUri) {
auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
ASSERT_RAISES(Invalid, fs->OpenInputStream("gs://" + PreexistingObjectPath()));
}

TEST_F(GcsIntegrationTest, OpenInputStreamReadMetadata) {
auto client = GcsClient();
const auto custom_time = std::chrono::system_clock::now() + std::chrono::hours(1);
Expand DownExpand Up@@ -940,6 +986,14 @@ TEST_F(GcsIntegrationTest, OpenOutputStreamClosed) {
ASSERT_RAISES(Invalid, output->Tell());
}

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

const auto path =
internal::ConcatAbstractPath(PreexistingBucketName(), "open-output-stream-uri.txt");
ASSERT_RAISES(Invalid, fs->OpenInputStream("gs://" + path));
}

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

Expand Down
Loading
, '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-10998: [C++] Detect URIs where a filesystem path is expected#11997

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

pitrou
wants to merge
3
commits into

from

 Closed


ARROW-10998: [C++] Detect URIs where a filesystem path is expected
#11997
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


3 commits


Select commit
Hold shift + click to select a range
088129c

ARROW-10998: [C++] Detect URIs where a filesystem path is expected


pitrou Dec 20, 2021
88c7858

Use preferred URI scheme in GCS tests


pitrou Dec 20, 2021
fe73f3a

Fix typo


pitrou 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


121 changes: 61 additions & 60 deletions
cpp/src/arrow/filesystem/filesystem.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -245,6 +245,17 @@ Result<std::shared_ptr<io::OutputStream>> FileSystem::OpenAppendStream(
//////////////////////////////////////////////////////////////////////////
// SubTreeFileSystem implementation

namespace {

Status ValidateSubPath(util::string_view s) {
 if (internal::IsLikelyUri(s)) {
 return Status::Invalid("Expected a filesystem path, got a URI: '", s, "'");
 }
 return Status::OK();
}

} // namespace

SubTreeFileSystem::SubTreeFileSystem(const std::string& base_path,
 std::shared_ptr<FileSystem> base_fs)
 : FileSystem(base_fs->io_context()),
Expand All@@ -270,20 +281,21 @@ bool SubTreeFileSystem::Equals(const FileSystem& other) const {
 return base_path_ == subfs.base_path_ && base_fs_->Equals(subfs.base_fs_);
}

std::string SubTreeFileSystem::PrependBase(const std::string& s) const {
Result<std::string> SubTreeFileSystem::PrependBase(const std::string& s) const {
 RETURN_NOT_OK(ValidateSubPath(s));
 if (s.empty()) {
 return base_path_;
 } else {
 return ConcatAbstractPath(base_path_, s);
 }
}

Status SubTreeFileSystem::PrependBaseNonEmpty(std::string* s) const {
 if (s->empty()) {
Result<std::string> SubTreeFileSystem::PrependBaseNonEmpty(const std::string& s) const {
 RETURN_NOT_OK(ValidateSubPath(s));
 if (s.empty()) {
 return Status::IOError("Empty path");
 } else {
 *s = ConcatAbstractPath(base_path_, *s);
 return Status::OK();
 return ConcatAbstractPath(base_path_, s);
 }
}

Expand All@@ -305,19 +317,21 @@ Status SubTreeFileSystem::FixInfo(FileInfo* info) const {
}

Result<std::string> SubTreeFileSystem::NormalizePath(std::string path) {
 ARROW_ASSIGN_OR_RAISE(auto normalized, base_fs_->NormalizePath(PrependBase(path)));
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBase(path));
 ARROW_ASSIGN_OR_RAISE(auto normalized, base_fs_->NormalizePath(real_path));
 return StripBase(std::move(normalized));
}

Result<FileInfo> SubTreeFileSystem::GetFileInfo(const std::string& path) {
 ARROW_ASSIGN_OR_RAISE(FileInfo info, base_fs_->GetFileInfo(PrependBase(path)));
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBase(path));
 ARROW_ASSIGN_OR_RAISE(FileInfo info, base_fs_->GetFileInfo(real_path));
 RETURN_NOT_OK(FixInfo(&info));
 return info;
}

Result<std::vector<FileInfo>> SubTreeFileSystem::GetFileInfo(const FileSelector& select) {
 auto selector = select;
 selector.base_dir = PrependBase(selector.base_dir);
ARROW_ASSIGN_OR_RAISE(selector.base_dir, PrependBase(selector.base_dir));
 ARROW_ASSIGN_OR_RAISE(auto infos, base_fs_->GetFileInfo(selector));
 for (auto& info : infos) {
 RETURN_NOT_OK(FixInfo(&info));
Expand All@@ -327,7 +341,11 @@ Result<std::vector<FileInfo>> SubTreeFileSystem::GetFileInfo(const FileSelector&

FileInfoGenerator SubTreeFileSystem::GetFileInfoGenerator(const FileSelector& select) {
 auto selector = select;
 selector.base_dir = PrependBase(selector.base_dir);
 auto maybe_base_dir = PrependBase(selector.base_dir);
 if (!maybe_base_dir.ok()) {
 return MakeFailingGenerator<std::vector<FileInfo>>(maybe_base_dir.status());
 }
 selector.base_dir = *std::move(maybe_base_dir);
 auto gen = base_fs_->GetFileInfoGenerator(selector);

 auto self = checked_pointer_cast<SubTreeFileSystem>(shared_from_this());
Expand All@@ -343,23 +361,21 @@ FileInfoGenerator SubTreeFileSystem::GetFileInfoGenerator(const FileSelector& se
}

Status SubTreeFileSystem::CreateDir(const std::string& path, bool recursive) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->CreateDir(s, recursive);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->CreateDir(real_path, recursive);
}

Status SubTreeFileSystem::DeleteDir(const std::string& path) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->DeleteDir(s);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->DeleteDir(real_path);
}

Status SubTreeFileSystem::DeleteDirContents(const std::string& path) {
 if (internal::IsEmptyPath(path)) {
 return internal::InvalidDeleteDirContents(path);
 }
 auto s = PrependBase(path);
 return base_fs_->DeleteDirContents(s);
ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBase(path));
 return base_fs_->DeleteDirContents(real_path);
}

Status SubTreeFileSystem::DeleteRootDirContents() {
Expand All@@ -371,103 +387,88 @@ Status SubTreeFileSystem::DeleteRootDirContents() {
}

Status SubTreeFileSystem::DeleteFile(const std::string& path) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->DeleteFile(s);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->DeleteFile(real_path);
}

Status SubTreeFileSystem::Move(const std::string& src, const std::string& dest) {
 auto s = src;
 auto d = dest;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 RETURN_NOT_OK(PrependBaseNonEmpty(&d));
 return base_fs_->Move(s, d);
 ARROW_ASSIGN_OR_RAISE(auto real_src, PrependBaseNonEmpty(src));
 ARROW_ASSIGN_OR_RAISE(auto real_dest, PrependBaseNonEmpty(dest));
 return base_fs_->Move(real_src, real_dest);
}

Status SubTreeFileSystem::CopyFile(const std::string& src, const std::string& dest) {
 auto s = src;
 auto d = dest;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 RETURN_NOT_OK(PrependBaseNonEmpty(&d));
 return base_fs_->CopyFile(s, d);
 ARROW_ASSIGN_OR_RAISE(auto real_src, PrependBaseNonEmpty(src));
 ARROW_ASSIGN_OR_RAISE(auto real_dest, PrependBaseNonEmpty(dest));
 return base_fs_->CopyFile(real_src, real_dest);
}

Result<std::shared_ptr<io::InputStream>> SubTreeFileSystem::OpenInputStream(
 const std::string& path) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->OpenInputStream(s);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->OpenInputStream(real_path);
}

Result<std::shared_ptr<io::InputStream>> SubTreeFileSystem::OpenInputStream(
 const FileInfo& info) {
 auto s = info.path();
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(info.path()));
 FileInfo new_info(info);
 new_info.set_path(std::move(s));
 new_info.set_path(std::move(real_path));
 return base_fs_->OpenInputStream(new_info);
}

Future<std::shared_ptr<io::InputStream>> SubTreeFileSystem::OpenInputStreamAsync(
 const std::string& path) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->OpenInputStreamAsync(s);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->OpenInputStreamAsync(real_path);
}

Future<std::shared_ptr<io::InputStream>> SubTreeFileSystem::OpenInputStreamAsync(
 const FileInfo& info) {
 auto s = info.path();
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(info.path()));
 FileInfo new_info(info);
 new_info.set_path(std::move(s));
 new_info.set_path(std::move(real_path));
 return base_fs_->OpenInputStreamAsync(new_info);
}

Result<std::shared_ptr<io::RandomAccessFile>> SubTreeFileSystem::OpenInputFile(
 const std::string& path) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->OpenInputFile(s);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->OpenInputFile(real_path);
}

Result<std::shared_ptr<io::RandomAccessFile>> SubTreeFileSystem::OpenInputFile(
 const FileInfo& info) {
 auto s = info.path();
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(info.path()));
 FileInfo new_info(info);
 new_info.set_path(std::move(s));
 new_info.set_path(std::move(real_path));
 return base_fs_->OpenInputFile(new_info);
}

Future<std::shared_ptr<io::RandomAccessFile>> SubTreeFileSystem::OpenInputFileAsync(
 const std::string& path) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->OpenInputFileAsync(s);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->OpenInputFileAsync(real_path);
}

Future<std::shared_ptr<io::RandomAccessFile>> SubTreeFileSystem::OpenInputFileAsync(
 const FileInfo& info) {
 auto s = info.path();
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(info.path()));
 FileInfo new_info(info);
 new_info.set_path(std::move(s));
 new_info.set_path(std::move(real_path));
 return base_fs_->OpenInputFileAsync(new_info);
}

Result<std::shared_ptr<io::OutputStream>> SubTreeFileSystem::OpenOutputStream(
 const std::string& path, const std::shared_ptr<const KeyValueMetadata>& metadata) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->OpenOutputStream(s, metadata);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->OpenOutputStream(real_path, metadata);
}

Result<std::shared_ptr<io::OutputStream>> SubTreeFileSystem::OpenAppendStream(
 const std::string& path, const std::shared_ptr<const KeyValueMetadata>& metadata) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->OpenAppendStream(s, metadata);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->OpenAppendStream(real_path, metadata);
}

//////////////////////////////////////////////////////////////////////////
Expand Down

4 changes: 2 additions & 2 deletions
cpp/src/arrow/filesystem/filesystem.h

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -384,8 +384,8 @@ class ARROW_EXPORT SubTreeFileSystem : public FileSystem {
 const std::string base_path_;
 std::shared_ptr<FileSystem> base_fs_;

 std::string PrependBase(const std::string& s) const;
Status PrependBaseNonEmpty(std::string* s) const;
Result<std::string> PrependBase(const std::string& s) const;
Result<std::string> PrependBaseNonEmpty(const std::string& s) const;
 Result<std::string> StripBase(const std::string& s) const;
 Status FixInfo(FileInfo* info) const;

Expand Down

4 changes: 4 additions & 0 deletions
cpp/src/arrow/filesystem/gcsfs.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -57,6 +57,10 @@ struct GcsPath {
 std::string object;

 static Result<GcsPath> FromString(const std::string& s) {
 if (internal::IsLikelyUri(s)) {
 return Status::Invalid(
 "Expected a GCS object path of the form 'bucket/key...', got a URI: '", s, "'");
 }
 auto const first_sep = s.find_first_of(internal::kSep);
 if (first_sep == 0) {
 return Status::Invalid("Path cannot start with a separator ('", s, "')");
Expand Down

54 changes: 54 additions & 0 deletions
cpp/src/arrow/filesystem/gcsfs_test.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -478,6 +478,9 @@ TEST(GcsFileSystem, ObjectMetadataRoundtrip) {
TEST_F(GcsIntegrationTest, GetFileInfoBucket) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 arrow::fs::AssertFileInfo(fs.get(), PreexistingBucketPath(), FileType::Directory);

 // URI
 ASSERT_RAISES(Invalid, fs->GetFileInfo("gs://" + PreexistingBucketPath()));
}

TEST_F(GcsIntegrationTest, GetFileInfoObject) {
Expand All@@ -487,6 +490,9 @@ TEST_F(GcsIntegrationTest, GetFileInfoObject) {
 ASSERT_TRUE(object.ok()) << "status=" << object.status();
 arrow::fs::AssertFileInfo(fs.get(), PreexistingObjectPath(), FileType::File,
 object->time_created(), static_cast<int64_t>(object->size()));

 // URI
 ASSERT_RAISES(Invalid, fs->GetFileInfo("gs://" + PreexistingObjectName()));
}

TEST_F(GcsIntegrationTest, GetFileInfoSelectorRecursive) {
Expand All@@ -508,6 +514,10 @@ TEST_F(GcsIntegrationTest, GetFileInfoSelectorRecursive) {
 selector.max_recursion = 16;
 ASSERT_OK_AND_ASSIGN(auto results, fs->GetFileInfo(selector));
 EXPECT_THAT(results, UnorderedElementsAreArray(expected.begin(), expected.end()));

 // URI
 selector.base_dir = "gs://" + selector.base_dir;
 ASSERT_RAISES(Invalid, fs->GetFileInfo(selector));
}

TEST_F(GcsIntegrationTest, GetFileInfoSelectorNonRecursive) {
Expand DownExpand Up@@ -626,6 +636,11 @@ TEST_F(GcsIntegrationTest, CreateDirRecursiveBucketAndFolder) {
 arrow::fs::AssertFileInfo(fs.get(), bucket_name + "/", FileType::Directory);
}

TEST_F(GcsIntegrationTest, CreateDirUri) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 ASSERT_RAISES(Invalid, fs->CreateDir("gs://" + RandomBucketName(), true));
}

TEST_F(GcsIntegrationTest, DeleteDirSuccess) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 ASSERT_OK_AND_ASSIGN(auto hierarchy, CreateHierarchy(fs));
Expand All@@ -641,6 +656,11 @@ TEST_F(GcsIntegrationTest, DeleteDirSuccess) {
 }
}

TEST_F(GcsIntegrationTest, DeleteDirUri) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 ASSERT_RAISES(Invalid, fs->DeleteDir("gs://" + PreexistingBucketPath()));
}

TEST_F(GcsIntegrationTest, DeleteDirContentsSuccess) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 ASSERT_OK_AND_ASSIGN(auto hierarchy, CreateHierarchy(fs));
Expand DownExpand Up@@ -682,6 +702,11 @@ TEST_F(GcsIntegrationTest, DeleteFileDirectoryFails) {
 ASSERT_RAISES(IOError, fs->DeleteFile(path));
}

TEST_F(GcsIntegrationTest, DeleteFileUri) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 ASSERT_RAISES(Invalid, fs->DeleteFile("gs://" + PreexistingObjectPath()));
}

TEST_F(GcsIntegrationTest, MoveFileSuccess) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 const auto destination_path = PreexistingBucketPath() + "move-destination";
Expand All@@ -708,6 +733,13 @@ TEST_F(GcsIntegrationTest, MoveFileCannotRenameToDirectory) {
 PreexistingBucketPath() + "destination/"));
}

TEST_F(GcsIntegrationTest, MoveFileUri) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 const auto destination_path = PreexistingBucketPath() + "move-destination";
 ASSERT_RAISES(Invalid, fs->Move("gs://" + PreexistingObjectPath(), destination_path));
 ASSERT_RAISES(Invalid, fs->Move(PreexistingObjectPath(), "gs://" + destination_path));
}

TEST_F(GcsIntegrationTest, CopyFileSuccess) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 const auto destination_path = PreexistingBucketPath() + "copy-destination";
Expand All@@ -721,6 +753,15 @@ TEST_F(GcsIntegrationTest, CopyFileNotFound) {
 ASSERT_RAISES(IOError, fs->CopyFile(NotFoundObjectPath(), destination_path));
}

TEST_F(GcsIntegrationTest, CopyFileUri) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 const auto destination_path = PreexistingBucketPath() + "copy-destination";
 ASSERT_RAISES(Invalid,
 fs->CopyFile("gs://" + PreexistingObjectPath(), destination_path));
 ASSERT_RAISES(Invalid,
 fs->CopyFile(PreexistingObjectPath(), "gs://" + destination_path));
}

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

Expand DownExpand Up@@ -797,6 +838,11 @@ TEST_F(GcsIntegrationTest, OpenInputStreamInfoInvalid) {
 ASSERT_RAISES(IOError, fs->OpenInputStream(info));
}

TEST_F(GcsIntegrationTest, OpenInputStreamUri) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 ASSERT_RAISES(Invalid, fs->OpenInputStream("gs://" + PreexistingObjectPath()));
}

TEST_F(GcsIntegrationTest, OpenInputStreamReadMetadata) {
 auto client = GcsClient();
 const auto custom_time = std::chrono::system_clock::now() + std::chrono::hours(1);
Expand DownExpand Up@@ -940,6 +986,14 @@ TEST_F(GcsIntegrationTest, OpenOutputStreamClosed) {
 ASSERT_RAISES(Invalid, output->Tell());
}

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

 const auto path =
 internal::ConcatAbstractPath(PreexistingBucketName(), "open-output-stream-uri.txt");
 ASSERT_RAISES(Invalid, fs->OpenInputStream("gs://" + path));
}

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

Expand Down
Loading

, '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-10998: [C++] Detect URIs where a filesystem path is expected#11997

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

pitrou
wants to merge
3
commits into

from

 Closed


ARROW-10998: [C++] Detect URIs where a filesystem path is expected
#11997
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


3 commits


Select commit
Hold shift + click to select a range
088129c

ARROW-10998: [C++] Detect URIs where a filesystem path is expected


pitrou Dec 20, 2021
88c7858

Use preferred URI scheme in GCS tests


pitrou Dec 20, 2021
fe73f3a

Fix typo


pitrou 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


121 changes: 61 additions & 60 deletions
cpp/src/arrow/filesystem/filesystem.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -245,6 +245,17 @@ Result<std::shared_ptr<io::OutputStream>> FileSystem::OpenAppendStream(
//////////////////////////////////////////////////////////////////////////
// SubTreeFileSystem implementation

namespace {

Status ValidateSubPath(util::string_view s) {
 if (internal::IsLikelyUri(s)) {
 return Status::Invalid("Expected a filesystem path, got a URI: '", s, "'");
 }
 return Status::OK();
}

} // namespace

SubTreeFileSystem::SubTreeFileSystem(const std::string& base_path,
 std::shared_ptr<FileSystem> base_fs)
 : FileSystem(base_fs->io_context()),
Expand All@@ -270,20 +281,21 @@ bool SubTreeFileSystem::Equals(const FileSystem& other) const {
 return base_path_ == subfs.base_path_ && base_fs_->Equals(subfs.base_fs_);
}

std::string SubTreeFileSystem::PrependBase(const std::string& s) const {
Result<std::string> SubTreeFileSystem::PrependBase(const std::string& s) const {
 RETURN_NOT_OK(ValidateSubPath(s));
 if (s.empty()) {
 return base_path_;
 } else {
 return ConcatAbstractPath(base_path_, s);
 }
}

Status SubTreeFileSystem::PrependBaseNonEmpty(std::string* s) const {
 if (s->empty()) {
Result<std::string> SubTreeFileSystem::PrependBaseNonEmpty(const std::string& s) const {
 RETURN_NOT_OK(ValidateSubPath(s));
 if (s.empty()) {
 return Status::IOError("Empty path");
 } else {
 *s = ConcatAbstractPath(base_path_, *s);
 return Status::OK();
 return ConcatAbstractPath(base_path_, s);
 }
}

Expand All@@ -305,19 +317,21 @@ Status SubTreeFileSystem::FixInfo(FileInfo* info) const {
}

Result<std::string> SubTreeFileSystem::NormalizePath(std::string path) {
 ARROW_ASSIGN_OR_RAISE(auto normalized, base_fs_->NormalizePath(PrependBase(path)));
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBase(path));
 ARROW_ASSIGN_OR_RAISE(auto normalized, base_fs_->NormalizePath(real_path));
 return StripBase(std::move(normalized));
}

Result<FileInfo> SubTreeFileSystem::GetFileInfo(const std::string& path) {
 ARROW_ASSIGN_OR_RAISE(FileInfo info, base_fs_->GetFileInfo(PrependBase(path)));
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBase(path));
 ARROW_ASSIGN_OR_RAISE(FileInfo info, base_fs_->GetFileInfo(real_path));
 RETURN_NOT_OK(FixInfo(&info));
 return info;
}

Result<std::vector<FileInfo>> SubTreeFileSystem::GetFileInfo(const FileSelector& select) {
 auto selector = select;
 selector.base_dir = PrependBase(selector.base_dir);
ARROW_ASSIGN_OR_RAISE(selector.base_dir, PrependBase(selector.base_dir));
 ARROW_ASSIGN_OR_RAISE(auto infos, base_fs_->GetFileInfo(selector));
 for (auto& info : infos) {
 RETURN_NOT_OK(FixInfo(&info));
Expand All@@ -327,7 +341,11 @@ Result<std::vector<FileInfo>> SubTreeFileSystem::GetFileInfo(const FileSelector&

FileInfoGenerator SubTreeFileSystem::GetFileInfoGenerator(const FileSelector& select) {
 auto selector = select;
 selector.base_dir = PrependBase(selector.base_dir);
 auto maybe_base_dir = PrependBase(selector.base_dir);
 if (!maybe_base_dir.ok()) {
 return MakeFailingGenerator<std::vector<FileInfo>>(maybe_base_dir.status());
 }
 selector.base_dir = *std::move(maybe_base_dir);
 auto gen = base_fs_->GetFileInfoGenerator(selector);

 auto self = checked_pointer_cast<SubTreeFileSystem>(shared_from_this());
Expand All@@ -343,23 +361,21 @@ FileInfoGenerator SubTreeFileSystem::GetFileInfoGenerator(const FileSelector& se
}

Status SubTreeFileSystem::CreateDir(const std::string& path, bool recursive) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->CreateDir(s, recursive);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->CreateDir(real_path, recursive);
}

Status SubTreeFileSystem::DeleteDir(const std::string& path) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->DeleteDir(s);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->DeleteDir(real_path);
}

Status SubTreeFileSystem::DeleteDirContents(const std::string& path) {
 if (internal::IsEmptyPath(path)) {
 return internal::InvalidDeleteDirContents(path);
 }
 auto s = PrependBase(path);
 return base_fs_->DeleteDirContents(s);
ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBase(path));
 return base_fs_->DeleteDirContents(real_path);
}

Status SubTreeFileSystem::DeleteRootDirContents() {
Expand All@@ -371,103 +387,88 @@ Status SubTreeFileSystem::DeleteRootDirContents() {
}

Status SubTreeFileSystem::DeleteFile(const std::string& path) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->DeleteFile(s);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->DeleteFile(real_path);
}

Status SubTreeFileSystem::Move(const std::string& src, const std::string& dest) {
 auto s = src;
 auto d = dest;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 RETURN_NOT_OK(PrependBaseNonEmpty(&d));
 return base_fs_->Move(s, d);
 ARROW_ASSIGN_OR_RAISE(auto real_src, PrependBaseNonEmpty(src));
 ARROW_ASSIGN_OR_RAISE(auto real_dest, PrependBaseNonEmpty(dest));
 return base_fs_->Move(real_src, real_dest);
}

Status SubTreeFileSystem::CopyFile(const std::string& src, const std::string& dest) {
 auto s = src;
 auto d = dest;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 RETURN_NOT_OK(PrependBaseNonEmpty(&d));
 return base_fs_->CopyFile(s, d);
 ARROW_ASSIGN_OR_RAISE(auto real_src, PrependBaseNonEmpty(src));
 ARROW_ASSIGN_OR_RAISE(auto real_dest, PrependBaseNonEmpty(dest));
 return base_fs_->CopyFile(real_src, real_dest);
}

Result<std::shared_ptr<io::InputStream>> SubTreeFileSystem::OpenInputStream(
 const std::string& path) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->OpenInputStream(s);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->OpenInputStream(real_path);
}

Result<std::shared_ptr<io::InputStream>> SubTreeFileSystem::OpenInputStream(
 const FileInfo& info) {
 auto s = info.path();
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(info.path()));
 FileInfo new_info(info);
 new_info.set_path(std::move(s));
 new_info.set_path(std::move(real_path));
 return base_fs_->OpenInputStream(new_info);
}

Future<std::shared_ptr<io::InputStream>> SubTreeFileSystem::OpenInputStreamAsync(
 const std::string& path) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->OpenInputStreamAsync(s);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->OpenInputStreamAsync(real_path);
}

Future<std::shared_ptr<io::InputStream>> SubTreeFileSystem::OpenInputStreamAsync(
 const FileInfo& info) {
 auto s = info.path();
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(info.path()));
 FileInfo new_info(info);
 new_info.set_path(std::move(s));
 new_info.set_path(std::move(real_path));
 return base_fs_->OpenInputStreamAsync(new_info);
}

Result<std::shared_ptr<io::RandomAccessFile>> SubTreeFileSystem::OpenInputFile(
 const std::string& path) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->OpenInputFile(s);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->OpenInputFile(real_path);
}

Result<std::shared_ptr<io::RandomAccessFile>> SubTreeFileSystem::OpenInputFile(
 const FileInfo& info) {
 auto s = info.path();
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(info.path()));
 FileInfo new_info(info);
 new_info.set_path(std::move(s));
 new_info.set_path(std::move(real_path));
 return base_fs_->OpenInputFile(new_info);
}

Future<std::shared_ptr<io::RandomAccessFile>> SubTreeFileSystem::OpenInputFileAsync(
 const std::string& path) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->OpenInputFileAsync(s);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->OpenInputFileAsync(real_path);
}

Future<std::shared_ptr<io::RandomAccessFile>> SubTreeFileSystem::OpenInputFileAsync(
 const FileInfo& info) {
 auto s = info.path();
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(info.path()));
 FileInfo new_info(info);
 new_info.set_path(std::move(s));
 new_info.set_path(std::move(real_path));
 return base_fs_->OpenInputFileAsync(new_info);
}

Result<std::shared_ptr<io::OutputStream>> SubTreeFileSystem::OpenOutputStream(
 const std::string& path, const std::shared_ptr<const KeyValueMetadata>& metadata) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->OpenOutputStream(s, metadata);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->OpenOutputStream(real_path, metadata);
}

Result<std::shared_ptr<io::OutputStream>> SubTreeFileSystem::OpenAppendStream(
 const std::string& path, const std::shared_ptr<const KeyValueMetadata>& metadata) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->OpenAppendStream(s, metadata);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->OpenAppendStream(real_path, metadata);
}

//////////////////////////////////////////////////////////////////////////
Expand Down

4 changes: 2 additions & 2 deletions
cpp/src/arrow/filesystem/filesystem.h

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -384,8 +384,8 @@ class ARROW_EXPORT SubTreeFileSystem : public FileSystem {
 const std::string base_path_;
 std::shared_ptr<FileSystem> base_fs_;

 std::string PrependBase(const std::string& s) const;
Status PrependBaseNonEmpty(std::string* s) const;
Result<std::string> PrependBase(const std::string& s) const;
Result<std::string> PrependBaseNonEmpty(const std::string& s) const;
 Result<std::string> StripBase(const std::string& s) const;
 Status FixInfo(FileInfo* info) const;

Expand Down

4 changes: 4 additions & 0 deletions
cpp/src/arrow/filesystem/gcsfs.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -57,6 +57,10 @@ struct GcsPath {
 std::string object;

 static Result<GcsPath> FromString(const std::string& s) {
 if (internal::IsLikelyUri(s)) {
 return Status::Invalid(
 "Expected a GCS object path of the form 'bucket/key...', got a URI: '", s, "'");
 }
 auto const first_sep = s.find_first_of(internal::kSep);
 if (first_sep == 0) {
 return Status::Invalid("Path cannot start with a separator ('", s, "')");
Expand Down

54 changes: 54 additions & 0 deletions
cpp/src/arrow/filesystem/gcsfs_test.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -478,6 +478,9 @@ TEST(GcsFileSystem, ObjectMetadataRoundtrip) {
TEST_F(GcsIntegrationTest, GetFileInfoBucket) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 arrow::fs::AssertFileInfo(fs.get(), PreexistingBucketPath(), FileType::Directory);

 // URI
 ASSERT_RAISES(Invalid, fs->GetFileInfo("gs://" + PreexistingBucketPath()));
}

TEST_F(GcsIntegrationTest, GetFileInfoObject) {
Expand All@@ -487,6 +490,9 @@ TEST_F(GcsIntegrationTest, GetFileInfoObject) {
 ASSERT_TRUE(object.ok()) << "status=" << object.status();
 arrow::fs::AssertFileInfo(fs.get(), PreexistingObjectPath(), FileType::File,
 object->time_created(), static_cast<int64_t>(object->size()));

 // URI
 ASSERT_RAISES(Invalid, fs->GetFileInfo("gs://" + PreexistingObjectName()));
}

TEST_F(GcsIntegrationTest, GetFileInfoSelectorRecursive) {
Expand All@@ -508,6 +514,10 @@ TEST_F(GcsIntegrationTest, GetFileInfoSelectorRecursive) {
 selector.max_recursion = 16;
 ASSERT_OK_AND_ASSIGN(auto results, fs->GetFileInfo(selector));
 EXPECT_THAT(results, UnorderedElementsAreArray(expected.begin(), expected.end()));

 // URI
 selector.base_dir = "gs://" + selector.base_dir;
 ASSERT_RAISES(Invalid, fs->GetFileInfo(selector));
}

TEST_F(GcsIntegrationTest, GetFileInfoSelectorNonRecursive) {
Expand DownExpand Up@@ -626,6 +636,11 @@ TEST_F(GcsIntegrationTest, CreateDirRecursiveBucketAndFolder) {
 arrow::fs::AssertFileInfo(fs.get(), bucket_name + "/", FileType::Directory);
}

TEST_F(GcsIntegrationTest, CreateDirUri) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 ASSERT_RAISES(Invalid, fs->CreateDir("gs://" + RandomBucketName(), true));
}

TEST_F(GcsIntegrationTest, DeleteDirSuccess) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 ASSERT_OK_AND_ASSIGN(auto hierarchy, CreateHierarchy(fs));
Expand All@@ -641,6 +656,11 @@ TEST_F(GcsIntegrationTest, DeleteDirSuccess) {
 }
}

TEST_F(GcsIntegrationTest, DeleteDirUri) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 ASSERT_RAISES(Invalid, fs->DeleteDir("gs://" + PreexistingBucketPath()));
}

TEST_F(GcsIntegrationTest, DeleteDirContentsSuccess) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 ASSERT_OK_AND_ASSIGN(auto hierarchy, CreateHierarchy(fs));
Expand DownExpand Up@@ -682,6 +702,11 @@ TEST_F(GcsIntegrationTest, DeleteFileDirectoryFails) {
 ASSERT_RAISES(IOError, fs->DeleteFile(path));
}

TEST_F(GcsIntegrationTest, DeleteFileUri) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 ASSERT_RAISES(Invalid, fs->DeleteFile("gs://" + PreexistingObjectPath()));
}

TEST_F(GcsIntegrationTest, MoveFileSuccess) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 const auto destination_path = PreexistingBucketPath() + "move-destination";
Expand All@@ -708,6 +733,13 @@ TEST_F(GcsIntegrationTest, MoveFileCannotRenameToDirectory) {
 PreexistingBucketPath() + "destination/"));
}

TEST_F(GcsIntegrationTest, MoveFileUri) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 const auto destination_path = PreexistingBucketPath() + "move-destination";
 ASSERT_RAISES(Invalid, fs->Move("gs://" + PreexistingObjectPath(), destination_path));
 ASSERT_RAISES(Invalid, fs->Move(PreexistingObjectPath(), "gs://" + destination_path));
}

TEST_F(GcsIntegrationTest, CopyFileSuccess) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 const auto destination_path = PreexistingBucketPath() + "copy-destination";
Expand All@@ -721,6 +753,15 @@ TEST_F(GcsIntegrationTest, CopyFileNotFound) {
 ASSERT_RAISES(IOError, fs->CopyFile(NotFoundObjectPath(), destination_path));
}

TEST_F(GcsIntegrationTest, CopyFileUri) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 const auto destination_path = PreexistingBucketPath() + "copy-destination";
 ASSERT_RAISES(Invalid,
 fs->CopyFile("gs://" + PreexistingObjectPath(), destination_path));
 ASSERT_RAISES(Invalid,
 fs->CopyFile(PreexistingObjectPath(), "gs://" + destination_path));
}

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

Expand DownExpand Up@@ -797,6 +838,11 @@ TEST_F(GcsIntegrationTest, OpenInputStreamInfoInvalid) {
 ASSERT_RAISES(IOError, fs->OpenInputStream(info));
}

TEST_F(GcsIntegrationTest, OpenInputStreamUri) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 ASSERT_RAISES(Invalid, fs->OpenInputStream("gs://" + PreexistingObjectPath()));
}

TEST_F(GcsIntegrationTest, OpenInputStreamReadMetadata) {
 auto client = GcsClient();
 const auto custom_time = std::chrono::system_clock::now() + std::chrono::hours(1);
Expand DownExpand Up@@ -940,6 +986,14 @@ TEST_F(GcsIntegrationTest, OpenOutputStreamClosed) {
 ASSERT_RAISES(Invalid, output->Tell());
}

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

 const auto path =
 internal::ConcatAbstractPath(PreexistingBucketName(), "open-output-stream-uri.txt");
 ASSERT_RAISES(Invalid, fs->OpenInputStream("gs://" + path));
}

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

Expand Down
Loading

, '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-10998: [C++] Detect URIs where a filesystem path is expected#11997

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

pitrou
wants to merge
3
commits into

from

 Closed


ARROW-10998: [C++] Detect URIs where a filesystem path is expected
#11997
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


3 commits


Select commit
Hold shift + click to select a range
088129c

ARROW-10998: [C++] Detect URIs where a filesystem path is expected


pitrou Dec 20, 2021
88c7858

Use preferred URI scheme in GCS tests


pitrou Dec 20, 2021
fe73f3a

Fix typo


pitrou 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


121 changes: 61 additions & 60 deletions
cpp/src/arrow/filesystem/filesystem.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -245,6 +245,17 @@ Result<std::shared_ptr<io::OutputStream>> FileSystem::OpenAppendStream(
//////////////////////////////////////////////////////////////////////////
// SubTreeFileSystem implementation

namespace {

Status ValidateSubPath(util::string_view s) {
 if (internal::IsLikelyUri(s)) {
 return Status::Invalid("Expected a filesystem path, got a URI: '", s, "'");
 }
 return Status::OK();
}

} // namespace

SubTreeFileSystem::SubTreeFileSystem(const std::string& base_path,
 std::shared_ptr<FileSystem> base_fs)
 : FileSystem(base_fs->io_context()),
Expand All@@ -270,20 +281,21 @@ bool SubTreeFileSystem::Equals(const FileSystem& other) const {
 return base_path_ == subfs.base_path_ && base_fs_->Equals(subfs.base_fs_);
}

std::string SubTreeFileSystem::PrependBase(const std::string& s) const {
Result<std::string> SubTreeFileSystem::PrependBase(const std::string& s) const {
 RETURN_NOT_OK(ValidateSubPath(s));
 if (s.empty()) {
 return base_path_;
 } else {
 return ConcatAbstractPath(base_path_, s);
 }
}

Status SubTreeFileSystem::PrependBaseNonEmpty(std::string* s) const {
 if (s->empty()) {
Result<std::string> SubTreeFileSystem::PrependBaseNonEmpty(const std::string& s) const {
 RETURN_NOT_OK(ValidateSubPath(s));
 if (s.empty()) {
 return Status::IOError("Empty path");
 } else {
 *s = ConcatAbstractPath(base_path_, *s);
 return Status::OK();
 return ConcatAbstractPath(base_path_, s);
 }
}

Expand All@@ -305,19 +317,21 @@ Status SubTreeFileSystem::FixInfo(FileInfo* info) const {
}

Result<std::string> SubTreeFileSystem::NormalizePath(std::string path) {
 ARROW_ASSIGN_OR_RAISE(auto normalized, base_fs_->NormalizePath(PrependBase(path)));
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBase(path));
 ARROW_ASSIGN_OR_RAISE(auto normalized, base_fs_->NormalizePath(real_path));
 return StripBase(std::move(normalized));
}

Result<FileInfo> SubTreeFileSystem::GetFileInfo(const std::string& path) {
 ARROW_ASSIGN_OR_RAISE(FileInfo info, base_fs_->GetFileInfo(PrependBase(path)));
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBase(path));
 ARROW_ASSIGN_OR_RAISE(FileInfo info, base_fs_->GetFileInfo(real_path));
 RETURN_NOT_OK(FixInfo(&info));
 return info;
}

Result<std::vector<FileInfo>> SubTreeFileSystem::GetFileInfo(const FileSelector& select) {
 auto selector = select;
 selector.base_dir = PrependBase(selector.base_dir);
ARROW_ASSIGN_OR_RAISE(selector.base_dir, PrependBase(selector.base_dir));
 ARROW_ASSIGN_OR_RAISE(auto infos, base_fs_->GetFileInfo(selector));
 for (auto& info : infos) {
 RETURN_NOT_OK(FixInfo(&info));
Expand All@@ -327,7 +341,11 @@ Result<std::vector<FileInfo>> SubTreeFileSystem::GetFileInfo(const FileSelector&

FileInfoGenerator SubTreeFileSystem::GetFileInfoGenerator(const FileSelector& select) {
 auto selector = select;
 selector.base_dir = PrependBase(selector.base_dir);
 auto maybe_base_dir = PrependBase(selector.base_dir);
 if (!maybe_base_dir.ok()) {
 return MakeFailingGenerator<std::vector<FileInfo>>(maybe_base_dir.status());
 }
 selector.base_dir = *std::move(maybe_base_dir);
 auto gen = base_fs_->GetFileInfoGenerator(selector);

 auto self = checked_pointer_cast<SubTreeFileSystem>(shared_from_this());
Expand All@@ -343,23 +361,21 @@ FileInfoGenerator SubTreeFileSystem::GetFileInfoGenerator(const FileSelector& se
}

Status SubTreeFileSystem::CreateDir(const std::string& path, bool recursive) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->CreateDir(s, recursive);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->CreateDir(real_path, recursive);
}

Status SubTreeFileSystem::DeleteDir(const std::string& path) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->DeleteDir(s);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->DeleteDir(real_path);
}

Status SubTreeFileSystem::DeleteDirContents(const std::string& path) {
 if (internal::IsEmptyPath(path)) {
 return internal::InvalidDeleteDirContents(path);
 }
 auto s = PrependBase(path);
 return base_fs_->DeleteDirContents(s);
ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBase(path));
 return base_fs_->DeleteDirContents(real_path);
}

Status SubTreeFileSystem::DeleteRootDirContents() {
Expand All@@ -371,103 +387,88 @@ Status SubTreeFileSystem::DeleteRootDirContents() {
}

Status SubTreeFileSystem::DeleteFile(const std::string& path) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->DeleteFile(s);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->DeleteFile(real_path);
}

Status SubTreeFileSystem::Move(const std::string& src, const std::string& dest) {
 auto s = src;
 auto d = dest;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 RETURN_NOT_OK(PrependBaseNonEmpty(&d));
 return base_fs_->Move(s, d);
 ARROW_ASSIGN_OR_RAISE(auto real_src, PrependBaseNonEmpty(src));
 ARROW_ASSIGN_OR_RAISE(auto real_dest, PrependBaseNonEmpty(dest));
 return base_fs_->Move(real_src, real_dest);
}

Status SubTreeFileSystem::CopyFile(const std::string& src, const std::string& dest) {
 auto s = src;
 auto d = dest;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 RETURN_NOT_OK(PrependBaseNonEmpty(&d));
 return base_fs_->CopyFile(s, d);
 ARROW_ASSIGN_OR_RAISE(auto real_src, PrependBaseNonEmpty(src));
 ARROW_ASSIGN_OR_RAISE(auto real_dest, PrependBaseNonEmpty(dest));
 return base_fs_->CopyFile(real_src, real_dest);
}

Result<std::shared_ptr<io::InputStream>> SubTreeFileSystem::OpenInputStream(
 const std::string& path) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->OpenInputStream(s);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->OpenInputStream(real_path);
}

Result<std::shared_ptr<io::InputStream>> SubTreeFileSystem::OpenInputStream(
 const FileInfo& info) {
 auto s = info.path();
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(info.path()));
 FileInfo new_info(info);
 new_info.set_path(std::move(s));
 new_info.set_path(std::move(real_path));
 return base_fs_->OpenInputStream(new_info);
}

Future<std::shared_ptr<io::InputStream>> SubTreeFileSystem::OpenInputStreamAsync(
 const std::string& path) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->OpenInputStreamAsync(s);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->OpenInputStreamAsync(real_path);
}

Future<std::shared_ptr<io::InputStream>> SubTreeFileSystem::OpenInputStreamAsync(
 const FileInfo& info) {
 auto s = info.path();
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(info.path()));
 FileInfo new_info(info);
 new_info.set_path(std::move(s));
 new_info.set_path(std::move(real_path));
 return base_fs_->OpenInputStreamAsync(new_info);
}

Result<std::shared_ptr<io::RandomAccessFile>> SubTreeFileSystem::OpenInputFile(
 const std::string& path) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->OpenInputFile(s);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->OpenInputFile(real_path);
}

Result<std::shared_ptr<io::RandomAccessFile>> SubTreeFileSystem::OpenInputFile(
 const FileInfo& info) {
 auto s = info.path();
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(info.path()));
 FileInfo new_info(info);
 new_info.set_path(std::move(s));
 new_info.set_path(std::move(real_path));
 return base_fs_->OpenInputFile(new_info);
}

Future<std::shared_ptr<io::RandomAccessFile>> SubTreeFileSystem::OpenInputFileAsync(
 const std::string& path) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->OpenInputFileAsync(s);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->OpenInputFileAsync(real_path);
}

Future<std::shared_ptr<io::RandomAccessFile>> SubTreeFileSystem::OpenInputFileAsync(
 const FileInfo& info) {
 auto s = info.path();
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(info.path()));
 FileInfo new_info(info);
 new_info.set_path(std::move(s));
 new_info.set_path(std::move(real_path));
 return base_fs_->OpenInputFileAsync(new_info);
}

Result<std::shared_ptr<io::OutputStream>> SubTreeFileSystem::OpenOutputStream(
 const std::string& path, const std::shared_ptr<const KeyValueMetadata>& metadata) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->OpenOutputStream(s, metadata);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->OpenOutputStream(real_path, metadata);
}

Result<std::shared_ptr<io::OutputStream>> SubTreeFileSystem::OpenAppendStream(
 const std::string& path, const std::shared_ptr<const KeyValueMetadata>& metadata) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->OpenAppendStream(s, metadata);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->OpenAppendStream(real_path, metadata);
}

//////////////////////////////////////////////////////////////////////////
Expand Down

4 changes: 2 additions & 2 deletions
cpp/src/arrow/filesystem/filesystem.h

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -384,8 +384,8 @@ class ARROW_EXPORT SubTreeFileSystem : public FileSystem {
 const std::string base_path_;
 std::shared_ptr<FileSystem> base_fs_;

 std::string PrependBase(const std::string& s) const;
Status PrependBaseNonEmpty(std::string* s) const;
Result<std::string> PrependBase(const std::string& s) const;
Result<std::string> PrependBaseNonEmpty(const std::string& s) const;
 Result<std::string> StripBase(const std::string& s) const;
 Status FixInfo(FileInfo* info) const;

Expand Down

4 changes: 4 additions & 0 deletions
cpp/src/arrow/filesystem/gcsfs.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -57,6 +57,10 @@ struct GcsPath {
 std::string object;

 static Result<GcsPath> FromString(const std::string& s) {
 if (internal::IsLikelyUri(s)) {
 return Status::Invalid(
 "Expected a GCS object path of the form 'bucket/key...', got a URI: '", s, "'");
 }
 auto const first_sep = s.find_first_of(internal::kSep);
 if (first_sep == 0) {
 return Status::Invalid("Path cannot start with a separator ('", s, "')");
Expand Down

54 changes: 54 additions & 0 deletions
cpp/src/arrow/filesystem/gcsfs_test.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -478,6 +478,9 @@ TEST(GcsFileSystem, ObjectMetadataRoundtrip) {
TEST_F(GcsIntegrationTest, GetFileInfoBucket) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 arrow::fs::AssertFileInfo(fs.get(), PreexistingBucketPath(), FileType::Directory);

 // URI
 ASSERT_RAISES(Invalid, fs->GetFileInfo("gs://" + PreexistingBucketPath()));
}

TEST_F(GcsIntegrationTest, GetFileInfoObject) {
Expand All@@ -487,6 +490,9 @@ TEST_F(GcsIntegrationTest, GetFileInfoObject) {
 ASSERT_TRUE(object.ok()) << "status=" << object.status();
 arrow::fs::AssertFileInfo(fs.get(), PreexistingObjectPath(), FileType::File,
 object->time_created(), static_cast<int64_t>(object->size()));

 // URI
 ASSERT_RAISES(Invalid, fs->GetFileInfo("gs://" + PreexistingObjectName()));
}

TEST_F(GcsIntegrationTest, GetFileInfoSelectorRecursive) {
Expand All@@ -508,6 +514,10 @@ TEST_F(GcsIntegrationTest, GetFileInfoSelectorRecursive) {
 selector.max_recursion = 16;
 ASSERT_OK_AND_ASSIGN(auto results, fs->GetFileInfo(selector));
 EXPECT_THAT(results, UnorderedElementsAreArray(expected.begin(), expected.end()));

 // URI
 selector.base_dir = "gs://" + selector.base_dir;
 ASSERT_RAISES(Invalid, fs->GetFileInfo(selector));
}

TEST_F(GcsIntegrationTest, GetFileInfoSelectorNonRecursive) {
Expand DownExpand Up@@ -626,6 +636,11 @@ TEST_F(GcsIntegrationTest, CreateDirRecursiveBucketAndFolder) {
 arrow::fs::AssertFileInfo(fs.get(), bucket_name + "/", FileType::Directory);
}

TEST_F(GcsIntegrationTest, CreateDirUri) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 ASSERT_RAISES(Invalid, fs->CreateDir("gs://" + RandomBucketName(), true));
}

TEST_F(GcsIntegrationTest, DeleteDirSuccess) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 ASSERT_OK_AND_ASSIGN(auto hierarchy, CreateHierarchy(fs));
Expand All@@ -641,6 +656,11 @@ TEST_F(GcsIntegrationTest, DeleteDirSuccess) {
 }
}

TEST_F(GcsIntegrationTest, DeleteDirUri) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 ASSERT_RAISES(Invalid, fs->DeleteDir("gs://" + PreexistingBucketPath()));
}

TEST_F(GcsIntegrationTest, DeleteDirContentsSuccess) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 ASSERT_OK_AND_ASSIGN(auto hierarchy, CreateHierarchy(fs));
Expand DownExpand Up@@ -682,6 +702,11 @@ TEST_F(GcsIntegrationTest, DeleteFileDirectoryFails) {
 ASSERT_RAISES(IOError, fs->DeleteFile(path));
}

TEST_F(GcsIntegrationTest, DeleteFileUri) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 ASSERT_RAISES(Invalid, fs->DeleteFile("gs://" + PreexistingObjectPath()));
}

TEST_F(GcsIntegrationTest, MoveFileSuccess) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 const auto destination_path = PreexistingBucketPath() + "move-destination";
Expand All@@ -708,6 +733,13 @@ TEST_F(GcsIntegrationTest, MoveFileCannotRenameToDirectory) {
 PreexistingBucketPath() + "destination/"));
}

TEST_F(GcsIntegrationTest, MoveFileUri) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 const auto destination_path = PreexistingBucketPath() + "move-destination";
 ASSERT_RAISES(Invalid, fs->Move("gs://" + PreexistingObjectPath(), destination_path));
 ASSERT_RAISES(Invalid, fs->Move(PreexistingObjectPath(), "gs://" + destination_path));
}

TEST_F(GcsIntegrationTest, CopyFileSuccess) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 const auto destination_path = PreexistingBucketPath() + "copy-destination";
Expand All@@ -721,6 +753,15 @@ TEST_F(GcsIntegrationTest, CopyFileNotFound) {
 ASSERT_RAISES(IOError, fs->CopyFile(NotFoundObjectPath(), destination_path));
}

TEST_F(GcsIntegrationTest, CopyFileUri) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 const auto destination_path = PreexistingBucketPath() + "copy-destination";
 ASSERT_RAISES(Invalid,
 fs->CopyFile("gs://" + PreexistingObjectPath(), destination_path));
 ASSERT_RAISES(Invalid,
 fs->CopyFile(PreexistingObjectPath(), "gs://" + destination_path));
}

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

Expand DownExpand Up@@ -797,6 +838,11 @@ TEST_F(GcsIntegrationTest, OpenInputStreamInfoInvalid) {
 ASSERT_RAISES(IOError, fs->OpenInputStream(info));
}

TEST_F(GcsIntegrationTest, OpenInputStreamUri) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 ASSERT_RAISES(Invalid, fs->OpenInputStream("gs://" + PreexistingObjectPath()));
}

TEST_F(GcsIntegrationTest, OpenInputStreamReadMetadata) {
 auto client = GcsClient();
 const auto custom_time = std::chrono::system_clock::now() + std::chrono::hours(1);
Expand DownExpand Up@@ -940,6 +986,14 @@ TEST_F(GcsIntegrationTest, OpenOutputStreamClosed) {
 ASSERT_RAISES(Invalid, output->Tell());
}

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

 const auto path =
 internal::ConcatAbstractPath(PreexistingBucketName(), "open-output-stream-uri.txt");
 ASSERT_RAISES(Invalid, fs->OpenInputStream("gs://" + path));
}

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

Expand Down
Loading

, '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-10998: [C++] Detect URIs where a filesystem path is expected#11997

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

pitrou
wants to merge
3
commits into

from

 Closed


ARROW-10998: [C++] Detect URIs where a filesystem path is expected
#11997
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


3 commits


Select commit
Hold shift + click to select a range
088129c

ARROW-10998: [C++] Detect URIs where a filesystem path is expected


pitrou Dec 20, 2021
88c7858

Use preferred URI scheme in GCS tests


pitrou Dec 20, 2021
fe73f3a

Fix typo


pitrou 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


121 changes: 61 additions & 60 deletions
cpp/src/arrow/filesystem/filesystem.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -245,6 +245,17 @@ Result<std::shared_ptr<io::OutputStream>> FileSystem::OpenAppendStream(
//////////////////////////////////////////////////////////////////////////
// SubTreeFileSystem implementation

namespace {

Status ValidateSubPath(util::string_view s) {
 if (internal::IsLikelyUri(s)) {
 return Status::Invalid("Expected a filesystem path, got a URI: '", s, "'");
 }
 return Status::OK();
}

} // namespace

SubTreeFileSystem::SubTreeFileSystem(const std::string& base_path,
 std::shared_ptr<FileSystem> base_fs)
 : FileSystem(base_fs->io_context()),
Expand All@@ -270,20 +281,21 @@ bool SubTreeFileSystem::Equals(const FileSystem& other) const {
 return base_path_ == subfs.base_path_ && base_fs_->Equals(subfs.base_fs_);
}

std::string SubTreeFileSystem::PrependBase(const std::string& s) const {
Result<std::string> SubTreeFileSystem::PrependBase(const std::string& s) const {
 RETURN_NOT_OK(ValidateSubPath(s));
 if (s.empty()) {
 return base_path_;
 } else {
 return ConcatAbstractPath(base_path_, s);
 }
}

Status SubTreeFileSystem::PrependBaseNonEmpty(std::string* s) const {
 if (s->empty()) {
Result<std::string> SubTreeFileSystem::PrependBaseNonEmpty(const std::string& s) const {
 RETURN_NOT_OK(ValidateSubPath(s));
 if (s.empty()) {
 return Status::IOError("Empty path");
 } else {
 *s = ConcatAbstractPath(base_path_, *s);
 return Status::OK();
 return ConcatAbstractPath(base_path_, s);
 }
}

Expand All@@ -305,19 +317,21 @@ Status SubTreeFileSystem::FixInfo(FileInfo* info) const {
}

Result<std::string> SubTreeFileSystem::NormalizePath(std::string path) {
 ARROW_ASSIGN_OR_RAISE(auto normalized, base_fs_->NormalizePath(PrependBase(path)));
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBase(path));
 ARROW_ASSIGN_OR_RAISE(auto normalized, base_fs_->NormalizePath(real_path));
 return StripBase(std::move(normalized));
}

Result<FileInfo> SubTreeFileSystem::GetFileInfo(const std::string& path) {
 ARROW_ASSIGN_OR_RAISE(FileInfo info, base_fs_->GetFileInfo(PrependBase(path)));
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBase(path));
 ARROW_ASSIGN_OR_RAISE(FileInfo info, base_fs_->GetFileInfo(real_path));
 RETURN_NOT_OK(FixInfo(&info));
 return info;
}

Result<std::vector<FileInfo>> SubTreeFileSystem::GetFileInfo(const FileSelector& select) {
 auto selector = select;
 selector.base_dir = PrependBase(selector.base_dir);
ARROW_ASSIGN_OR_RAISE(selector.base_dir, PrependBase(selector.base_dir));
 ARROW_ASSIGN_OR_RAISE(auto infos, base_fs_->GetFileInfo(selector));
 for (auto& info : infos) {
 RETURN_NOT_OK(FixInfo(&info));
Expand All@@ -327,7 +341,11 @@ Result<std::vector<FileInfo>> SubTreeFileSystem::GetFileInfo(const FileSelector&

FileInfoGenerator SubTreeFileSystem::GetFileInfoGenerator(const FileSelector& select) {
 auto selector = select;
 selector.base_dir = PrependBase(selector.base_dir);
 auto maybe_base_dir = PrependBase(selector.base_dir);
 if (!maybe_base_dir.ok()) {
 return MakeFailingGenerator<std::vector<FileInfo>>(maybe_base_dir.status());
 }
 selector.base_dir = *std::move(maybe_base_dir);
 auto gen = base_fs_->GetFileInfoGenerator(selector);

 auto self = checked_pointer_cast<SubTreeFileSystem>(shared_from_this());
Expand All@@ -343,23 +361,21 @@ FileInfoGenerator SubTreeFileSystem::GetFileInfoGenerator(const FileSelector& se
}

Status SubTreeFileSystem::CreateDir(const std::string& path, bool recursive) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->CreateDir(s, recursive);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->CreateDir(real_path, recursive);
}

Status SubTreeFileSystem::DeleteDir(const std::string& path) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->DeleteDir(s);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->DeleteDir(real_path);
}

Status SubTreeFileSystem::DeleteDirContents(const std::string& path) {
 if (internal::IsEmptyPath(path)) {
 return internal::InvalidDeleteDirContents(path);
 }
 auto s = PrependBase(path);
 return base_fs_->DeleteDirContents(s);
ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBase(path));
 return base_fs_->DeleteDirContents(real_path);
}

Status SubTreeFileSystem::DeleteRootDirContents() {
Expand All@@ -371,103 +387,88 @@ Status SubTreeFileSystem::DeleteRootDirContents() {
}

Status SubTreeFileSystem::DeleteFile(const std::string& path) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->DeleteFile(s);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->DeleteFile(real_path);
}

Status SubTreeFileSystem::Move(const std::string& src, const std::string& dest) {
 auto s = src;
 auto d = dest;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 RETURN_NOT_OK(PrependBaseNonEmpty(&d));
 return base_fs_->Move(s, d);
 ARROW_ASSIGN_OR_RAISE(auto real_src, PrependBaseNonEmpty(src));
 ARROW_ASSIGN_OR_RAISE(auto real_dest, PrependBaseNonEmpty(dest));
 return base_fs_->Move(real_src, real_dest);
}

Status SubTreeFileSystem::CopyFile(const std::string& src, const std::string& dest) {
 auto s = src;
 auto d = dest;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 RETURN_NOT_OK(PrependBaseNonEmpty(&d));
 return base_fs_->CopyFile(s, d);
 ARROW_ASSIGN_OR_RAISE(auto real_src, PrependBaseNonEmpty(src));
 ARROW_ASSIGN_OR_RAISE(auto real_dest, PrependBaseNonEmpty(dest));
 return base_fs_->CopyFile(real_src, real_dest);
}

Result<std::shared_ptr<io::InputStream>> SubTreeFileSystem::OpenInputStream(
 const std::string& path) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->OpenInputStream(s);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->OpenInputStream(real_path);
}

Result<std::shared_ptr<io::InputStream>> SubTreeFileSystem::OpenInputStream(
 const FileInfo& info) {
 auto s = info.path();
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(info.path()));
 FileInfo new_info(info);
 new_info.set_path(std::move(s));
 new_info.set_path(std::move(real_path));
 return base_fs_->OpenInputStream(new_info);
}

Future<std::shared_ptr<io::InputStream>> SubTreeFileSystem::OpenInputStreamAsync(
 const std::string& path) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->OpenInputStreamAsync(s);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->OpenInputStreamAsync(real_path);
}

Future<std::shared_ptr<io::InputStream>> SubTreeFileSystem::OpenInputStreamAsync(
 const FileInfo& info) {
 auto s = info.path();
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(info.path()));
 FileInfo new_info(info);
 new_info.set_path(std::move(s));
 new_info.set_path(std::move(real_path));
 return base_fs_->OpenInputStreamAsync(new_info);
}

Result<std::shared_ptr<io::RandomAccessFile>> SubTreeFileSystem::OpenInputFile(
 const std::string& path) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->OpenInputFile(s);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->OpenInputFile(real_path);
}

Result<std::shared_ptr<io::RandomAccessFile>> SubTreeFileSystem::OpenInputFile(
 const FileInfo& info) {
 auto s = info.path();
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(info.path()));
 FileInfo new_info(info);
 new_info.set_path(std::move(s));
 new_info.set_path(std::move(real_path));
 return base_fs_->OpenInputFile(new_info);
}

Future<std::shared_ptr<io::RandomAccessFile>> SubTreeFileSystem::OpenInputFileAsync(
 const std::string& path) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->OpenInputFileAsync(s);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->OpenInputFileAsync(real_path);
}

Future<std::shared_ptr<io::RandomAccessFile>> SubTreeFileSystem::OpenInputFileAsync(
 const FileInfo& info) {
 auto s = info.path();
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(info.path()));
 FileInfo new_info(info);
 new_info.set_path(std::move(s));
 new_info.set_path(std::move(real_path));
 return base_fs_->OpenInputFileAsync(new_info);
}

Result<std::shared_ptr<io::OutputStream>> SubTreeFileSystem::OpenOutputStream(
 const std::string& path, const std::shared_ptr<const KeyValueMetadata>& metadata) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->OpenOutputStream(s, metadata);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->OpenOutputStream(real_path, metadata);
}

Result<std::shared_ptr<io::OutputStream>> SubTreeFileSystem::OpenAppendStream(
 const std::string& path, const std::shared_ptr<const KeyValueMetadata>& metadata) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->OpenAppendStream(s, metadata);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->OpenAppendStream(real_path, metadata);
}

//////////////////////////////////////////////////////////////////////////
Expand Down

4 changes: 2 additions & 2 deletions
cpp/src/arrow/filesystem/filesystem.h

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -384,8 +384,8 @@ class ARROW_EXPORT SubTreeFileSystem : public FileSystem {
 const std::string base_path_;
 std::shared_ptr<FileSystem> base_fs_;

 std::string PrependBase(const std::string& s) const;
Status PrependBaseNonEmpty(std::string* s) const;
Result<std::string> PrependBase(const std::string& s) const;
Result<std::string> PrependBaseNonEmpty(const std::string& s) const;
 Result<std::string> StripBase(const std::string& s) const;
 Status FixInfo(FileInfo* info) const;

Expand Down

4 changes: 4 additions & 0 deletions
cpp/src/arrow/filesystem/gcsfs.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -57,6 +57,10 @@ struct GcsPath {
 std::string object;

 static Result<GcsPath> FromString(const std::string& s) {
 if (internal::IsLikelyUri(s)) {
 return Status::Invalid(
 "Expected a GCS object path of the form 'bucket/key...', got a URI: '", s, "'");
 }
 auto const first_sep = s.find_first_of(internal::kSep);
 if (first_sep == 0) {
 return Status::Invalid("Path cannot start with a separator ('", s, "')");
Expand Down

54 changes: 54 additions & 0 deletions
cpp/src/arrow/filesystem/gcsfs_test.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -478,6 +478,9 @@ TEST(GcsFileSystem, ObjectMetadataRoundtrip) {
TEST_F(GcsIntegrationTest, GetFileInfoBucket) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 arrow::fs::AssertFileInfo(fs.get(), PreexistingBucketPath(), FileType::Directory);

 // URI
 ASSERT_RAISES(Invalid, fs->GetFileInfo("gs://" + PreexistingBucketPath()));
}

TEST_F(GcsIntegrationTest, GetFileInfoObject) {
Expand All@@ -487,6 +490,9 @@ TEST_F(GcsIntegrationTest, GetFileInfoObject) {
 ASSERT_TRUE(object.ok()) << "status=" << object.status();
 arrow::fs::AssertFileInfo(fs.get(), PreexistingObjectPath(), FileType::File,
 object->time_created(), static_cast<int64_t>(object->size()));

 // URI
 ASSERT_RAISES(Invalid, fs->GetFileInfo("gs://" + PreexistingObjectName()));
}

TEST_F(GcsIntegrationTest, GetFileInfoSelectorRecursive) {
Expand All@@ -508,6 +514,10 @@ TEST_F(GcsIntegrationTest, GetFileInfoSelectorRecursive) {
 selector.max_recursion = 16;
 ASSERT_OK_AND_ASSIGN(auto results, fs->GetFileInfo(selector));
 EXPECT_THAT(results, UnorderedElementsAreArray(expected.begin(), expected.end()));

 // URI
 selector.base_dir = "gs://" + selector.base_dir;
 ASSERT_RAISES(Invalid, fs->GetFileInfo(selector));
}

TEST_F(GcsIntegrationTest, GetFileInfoSelectorNonRecursive) {
Expand DownExpand Up@@ -626,6 +636,11 @@ TEST_F(GcsIntegrationTest, CreateDirRecursiveBucketAndFolder) {
 arrow::fs::AssertFileInfo(fs.get(), bucket_name + "/", FileType::Directory);
}

TEST_F(GcsIntegrationTest, CreateDirUri) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 ASSERT_RAISES(Invalid, fs->CreateDir("gs://" + RandomBucketName(), true));
}

TEST_F(GcsIntegrationTest, DeleteDirSuccess) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 ASSERT_OK_AND_ASSIGN(auto hierarchy, CreateHierarchy(fs));
Expand All@@ -641,6 +656,11 @@ TEST_F(GcsIntegrationTest, DeleteDirSuccess) {
 }
}

TEST_F(GcsIntegrationTest, DeleteDirUri) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 ASSERT_RAISES(Invalid, fs->DeleteDir("gs://" + PreexistingBucketPath()));
}

TEST_F(GcsIntegrationTest, DeleteDirContentsSuccess) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 ASSERT_OK_AND_ASSIGN(auto hierarchy, CreateHierarchy(fs));
Expand DownExpand Up@@ -682,6 +702,11 @@ TEST_F(GcsIntegrationTest, DeleteFileDirectoryFails) {
 ASSERT_RAISES(IOError, fs->DeleteFile(path));
}

TEST_F(GcsIntegrationTest, DeleteFileUri) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 ASSERT_RAISES(Invalid, fs->DeleteFile("gs://" + PreexistingObjectPath()));
}

TEST_F(GcsIntegrationTest, MoveFileSuccess) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 const auto destination_path = PreexistingBucketPath() + "move-destination";
Expand All@@ -708,6 +733,13 @@ TEST_F(GcsIntegrationTest, MoveFileCannotRenameToDirectory) {
 PreexistingBucketPath() + "destination/"));
}

TEST_F(GcsIntegrationTest, MoveFileUri) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 const auto destination_path = PreexistingBucketPath() + "move-destination";
 ASSERT_RAISES(Invalid, fs->Move("gs://" + PreexistingObjectPath(), destination_path));
 ASSERT_RAISES(Invalid, fs->Move(PreexistingObjectPath(), "gs://" + destination_path));
}

TEST_F(GcsIntegrationTest, CopyFileSuccess) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 const auto destination_path = PreexistingBucketPath() + "copy-destination";
Expand All@@ -721,6 +753,15 @@ TEST_F(GcsIntegrationTest, CopyFileNotFound) {
 ASSERT_RAISES(IOError, fs->CopyFile(NotFoundObjectPath(), destination_path));
}

TEST_F(GcsIntegrationTest, CopyFileUri) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 const auto destination_path = PreexistingBucketPath() + "copy-destination";
 ASSERT_RAISES(Invalid,
 fs->CopyFile("gs://" + PreexistingObjectPath(), destination_path));
 ASSERT_RAISES(Invalid,
 fs->CopyFile(PreexistingObjectPath(), "gs://" + destination_path));
}

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

Expand DownExpand Up@@ -797,6 +838,11 @@ TEST_F(GcsIntegrationTest, OpenInputStreamInfoInvalid) {
 ASSERT_RAISES(IOError, fs->OpenInputStream(info));
}

TEST_F(GcsIntegrationTest, OpenInputStreamUri) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 ASSERT_RAISES(Invalid, fs->OpenInputStream("gs://" + PreexistingObjectPath()));
}

TEST_F(GcsIntegrationTest, OpenInputStreamReadMetadata) {
 auto client = GcsClient();
 const auto custom_time = std::chrono::system_clock::now() + std::chrono::hours(1);
Expand DownExpand Up@@ -940,6 +986,14 @@ TEST_F(GcsIntegrationTest, OpenOutputStreamClosed) {
 ASSERT_RAISES(Invalid, output->Tell());
}

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

 const auto path =
 internal::ConcatAbstractPath(PreexistingBucketName(), "open-output-stream-uri.txt");
 ASSERT_RAISES(Invalid, fs->OpenInputStream("gs://" + path));
}

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

Expand Down
Loading

, '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-10998: [C++] Detect URIs where a filesystem path is expected#11997

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

pitrou
wants to merge
3
commits into

from

 Closed


ARROW-10998: [C++] Detect URIs where a filesystem path is expected
#11997
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


3 commits


Select commit
Hold shift + click to select a range
088129c

ARROW-10998: [C++] Detect URIs where a filesystem path is expected


pitrou Dec 20, 2021
88c7858

Use preferred URI scheme in GCS tests


pitrou Dec 20, 2021
fe73f3a

Fix typo


pitrou 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


121 changes: 61 additions & 60 deletions
cpp/src/arrow/filesystem/filesystem.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -245,6 +245,17 @@ Result<std::shared_ptr<io::OutputStream>> FileSystem::OpenAppendStream(
//////////////////////////////////////////////////////////////////////////
// SubTreeFileSystem implementation

namespace {

Status ValidateSubPath(util::string_view s) {
 if (internal::IsLikelyUri(s)) {
 return Status::Invalid("Expected a filesystem path, got a URI: '", s, "'");
 }
 return Status::OK();
}

} // namespace

SubTreeFileSystem::SubTreeFileSystem(const std::string& base_path,
 std::shared_ptr<FileSystem> base_fs)
 : FileSystem(base_fs->io_context()),
Expand All@@ -270,20 +281,21 @@ bool SubTreeFileSystem::Equals(const FileSystem& other) const {
 return base_path_ == subfs.base_path_ && base_fs_->Equals(subfs.base_fs_);
}

std::string SubTreeFileSystem::PrependBase(const std::string& s) const {
Result<std::string> SubTreeFileSystem::PrependBase(const std::string& s) const {
 RETURN_NOT_OK(ValidateSubPath(s));
 if (s.empty()) {
 return base_path_;
 } else {
 return ConcatAbstractPath(base_path_, s);
 }
}

Status SubTreeFileSystem::PrependBaseNonEmpty(std::string* s) const {
 if (s->empty()) {
Result<std::string> SubTreeFileSystem::PrependBaseNonEmpty(const std::string& s) const {
 RETURN_NOT_OK(ValidateSubPath(s));
 if (s.empty()) {
 return Status::IOError("Empty path");
 } else {
 *s = ConcatAbstractPath(base_path_, *s);
 return Status::OK();
 return ConcatAbstractPath(base_path_, s);
 }
}

Expand All@@ -305,19 +317,21 @@ Status SubTreeFileSystem::FixInfo(FileInfo* info) const {
}

Result<std::string> SubTreeFileSystem::NormalizePath(std::string path) {
 ARROW_ASSIGN_OR_RAISE(auto normalized, base_fs_->NormalizePath(PrependBase(path)));
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBase(path));
 ARROW_ASSIGN_OR_RAISE(auto normalized, base_fs_->NormalizePath(real_path));
 return StripBase(std::move(normalized));
}

Result<FileInfo> SubTreeFileSystem::GetFileInfo(const std::string& path) {
 ARROW_ASSIGN_OR_RAISE(FileInfo info, base_fs_->GetFileInfo(PrependBase(path)));
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBase(path));
 ARROW_ASSIGN_OR_RAISE(FileInfo info, base_fs_->GetFileInfo(real_path));
 RETURN_NOT_OK(FixInfo(&info));
 return info;
}

Result<std::vector<FileInfo>> SubTreeFileSystem::GetFileInfo(const FileSelector& select) {
 auto selector = select;
 selector.base_dir = PrependBase(selector.base_dir);
ARROW_ASSIGN_OR_RAISE(selector.base_dir, PrependBase(selector.base_dir));
 ARROW_ASSIGN_OR_RAISE(auto infos, base_fs_->GetFileInfo(selector));
 for (auto& info : infos) {
 RETURN_NOT_OK(FixInfo(&info));
Expand All@@ -327,7 +341,11 @@ Result<std::vector<FileInfo>> SubTreeFileSystem::GetFileInfo(const FileSelector&

FileInfoGenerator SubTreeFileSystem::GetFileInfoGenerator(const FileSelector& select) {
 auto selector = select;
 selector.base_dir = PrependBase(selector.base_dir);
 auto maybe_base_dir = PrependBase(selector.base_dir);
 if (!maybe_base_dir.ok()) {
 return MakeFailingGenerator<std::vector<FileInfo>>(maybe_base_dir.status());
 }
 selector.base_dir = *std::move(maybe_base_dir);
 auto gen = base_fs_->GetFileInfoGenerator(selector);

 auto self = checked_pointer_cast<SubTreeFileSystem>(shared_from_this());
Expand All@@ -343,23 +361,21 @@ FileInfoGenerator SubTreeFileSystem::GetFileInfoGenerator(const FileSelector& se
}

Status SubTreeFileSystem::CreateDir(const std::string& path, bool recursive) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->CreateDir(s, recursive);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->CreateDir(real_path, recursive);
}

Status SubTreeFileSystem::DeleteDir(const std::string& path) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->DeleteDir(s);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->DeleteDir(real_path);
}

Status SubTreeFileSystem::DeleteDirContents(const std::string& path) {
 if (internal::IsEmptyPath(path)) {
 return internal::InvalidDeleteDirContents(path);
 }
 auto s = PrependBase(path);
 return base_fs_->DeleteDirContents(s);
ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBase(path));
 return base_fs_->DeleteDirContents(real_path);
}

Status SubTreeFileSystem::DeleteRootDirContents() {
Expand All@@ -371,103 +387,88 @@ Status SubTreeFileSystem::DeleteRootDirContents() {
}

Status SubTreeFileSystem::DeleteFile(const std::string& path) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->DeleteFile(s);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->DeleteFile(real_path);
}

Status SubTreeFileSystem::Move(const std::string& src, const std::string& dest) {
 auto s = src;
 auto d = dest;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 RETURN_NOT_OK(PrependBaseNonEmpty(&d));
 return base_fs_->Move(s, d);
 ARROW_ASSIGN_OR_RAISE(auto real_src, PrependBaseNonEmpty(src));
 ARROW_ASSIGN_OR_RAISE(auto real_dest, PrependBaseNonEmpty(dest));
 return base_fs_->Move(real_src, real_dest);
}

Status SubTreeFileSystem::CopyFile(const std::string& src, const std::string& dest) {
 auto s = src;
 auto d = dest;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 RETURN_NOT_OK(PrependBaseNonEmpty(&d));
 return base_fs_->CopyFile(s, d);
 ARROW_ASSIGN_OR_RAISE(auto real_src, PrependBaseNonEmpty(src));
 ARROW_ASSIGN_OR_RAISE(auto real_dest, PrependBaseNonEmpty(dest));
 return base_fs_->CopyFile(real_src, real_dest);
}

Result<std::shared_ptr<io::InputStream>> SubTreeFileSystem::OpenInputStream(
 const std::string& path) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->OpenInputStream(s);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->OpenInputStream(real_path);
}

Result<std::shared_ptr<io::InputStream>> SubTreeFileSystem::OpenInputStream(
 const FileInfo& info) {
 auto s = info.path();
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(info.path()));
 FileInfo new_info(info);
 new_info.set_path(std::move(s));
 new_info.set_path(std::move(real_path));
 return base_fs_->OpenInputStream(new_info);
}

Future<std::shared_ptr<io::InputStream>> SubTreeFileSystem::OpenInputStreamAsync(
 const std::string& path) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->OpenInputStreamAsync(s);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->OpenInputStreamAsync(real_path);
}

Future<std::shared_ptr<io::InputStream>> SubTreeFileSystem::OpenInputStreamAsync(
 const FileInfo& info) {
 auto s = info.path();
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(info.path()));
 FileInfo new_info(info);
 new_info.set_path(std::move(s));
 new_info.set_path(std::move(real_path));
 return base_fs_->OpenInputStreamAsync(new_info);
}

Result<std::shared_ptr<io::RandomAccessFile>> SubTreeFileSystem::OpenInputFile(
 const std::string& path) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->OpenInputFile(s);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->OpenInputFile(real_path);
}

Result<std::shared_ptr<io::RandomAccessFile>> SubTreeFileSystem::OpenInputFile(
 const FileInfo& info) {
 auto s = info.path();
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(info.path()));
 FileInfo new_info(info);
 new_info.set_path(std::move(s));
 new_info.set_path(std::move(real_path));
 return base_fs_->OpenInputFile(new_info);
}

Future<std::shared_ptr<io::RandomAccessFile>> SubTreeFileSystem::OpenInputFileAsync(
 const std::string& path) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->OpenInputFileAsync(s);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->OpenInputFileAsync(real_path);
}

Future<std::shared_ptr<io::RandomAccessFile>> SubTreeFileSystem::OpenInputFileAsync(
 const FileInfo& info) {
 auto s = info.path();
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(info.path()));
 FileInfo new_info(info);
 new_info.set_path(std::move(s));
 new_info.set_path(std::move(real_path));
 return base_fs_->OpenInputFileAsync(new_info);
}

Result<std::shared_ptr<io::OutputStream>> SubTreeFileSystem::OpenOutputStream(
 const std::string& path, const std::shared_ptr<const KeyValueMetadata>& metadata) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->OpenOutputStream(s, metadata);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->OpenOutputStream(real_path, metadata);
}

Result<std::shared_ptr<io::OutputStream>> SubTreeFileSystem::OpenAppendStream(
 const std::string& path, const std::shared_ptr<const KeyValueMetadata>& metadata) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->OpenAppendStream(s, metadata);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->OpenAppendStream(real_path, metadata);
}

//////////////////////////////////////////////////////////////////////////
Expand Down

4 changes: 2 additions & 2 deletions
cpp/src/arrow/filesystem/filesystem.h

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -384,8 +384,8 @@ class ARROW_EXPORT SubTreeFileSystem : public FileSystem {
 const std::string base_path_;
 std::shared_ptr<FileSystem> base_fs_;

 std::string PrependBase(const std::string& s) const;
Status PrependBaseNonEmpty(std::string* s) const;
Result<std::string> PrependBase(const std::string& s) const;
Result<std::string> PrependBaseNonEmpty(const std::string& s) const;
 Result<std::string> StripBase(const std::string& s) const;
 Status FixInfo(FileInfo* info) const;

Expand Down

4 changes: 4 additions & 0 deletions
cpp/src/arrow/filesystem/gcsfs.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -57,6 +57,10 @@ struct GcsPath {
 std::string object;

 static Result<GcsPath> FromString(const std::string& s) {
 if (internal::IsLikelyUri(s)) {
 return Status::Invalid(
 "Expected a GCS object path of the form 'bucket/key...', got a URI: '", s, "'");
 }
 auto const first_sep = s.find_first_of(internal::kSep);
 if (first_sep == 0) {
 return Status::Invalid("Path cannot start with a separator ('", s, "')");
Expand Down

54 changes: 54 additions & 0 deletions
cpp/src/arrow/filesystem/gcsfs_test.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -478,6 +478,9 @@ TEST(GcsFileSystem, ObjectMetadataRoundtrip) {
TEST_F(GcsIntegrationTest, GetFileInfoBucket) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 arrow::fs::AssertFileInfo(fs.get(), PreexistingBucketPath(), FileType::Directory);

 // URI
 ASSERT_RAISES(Invalid, fs->GetFileInfo("gs://" + PreexistingBucketPath()));
}

TEST_F(GcsIntegrationTest, GetFileInfoObject) {
Expand All@@ -487,6 +490,9 @@ TEST_F(GcsIntegrationTest, GetFileInfoObject) {
 ASSERT_TRUE(object.ok()) << "status=" << object.status();
 arrow::fs::AssertFileInfo(fs.get(), PreexistingObjectPath(), FileType::File,
 object->time_created(), static_cast<int64_t>(object->size()));

 // URI
 ASSERT_RAISES(Invalid, fs->GetFileInfo("gs://" + PreexistingObjectName()));
}

TEST_F(GcsIntegrationTest, GetFileInfoSelectorRecursive) {
Expand All@@ -508,6 +514,10 @@ TEST_F(GcsIntegrationTest, GetFileInfoSelectorRecursive) {
 selector.max_recursion = 16;
 ASSERT_OK_AND_ASSIGN(auto results, fs->GetFileInfo(selector));
 EXPECT_THAT(results, UnorderedElementsAreArray(expected.begin(), expected.end()));

 // URI
 selector.base_dir = "gs://" + selector.base_dir;
 ASSERT_RAISES(Invalid, fs->GetFileInfo(selector));
}

TEST_F(GcsIntegrationTest, GetFileInfoSelectorNonRecursive) {
Expand DownExpand Up@@ -626,6 +636,11 @@ TEST_F(GcsIntegrationTest, CreateDirRecursiveBucketAndFolder) {
 arrow::fs::AssertFileInfo(fs.get(), bucket_name + "/", FileType::Directory);
}

TEST_F(GcsIntegrationTest, CreateDirUri) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 ASSERT_RAISES(Invalid, fs->CreateDir("gs://" + RandomBucketName(), true));
}

TEST_F(GcsIntegrationTest, DeleteDirSuccess) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 ASSERT_OK_AND_ASSIGN(auto hierarchy, CreateHierarchy(fs));
Expand All@@ -641,6 +656,11 @@ TEST_F(GcsIntegrationTest, DeleteDirSuccess) {
 }
}

TEST_F(GcsIntegrationTest, DeleteDirUri) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 ASSERT_RAISES(Invalid, fs->DeleteDir("gs://" + PreexistingBucketPath()));
}

TEST_F(GcsIntegrationTest, DeleteDirContentsSuccess) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 ASSERT_OK_AND_ASSIGN(auto hierarchy, CreateHierarchy(fs));
Expand DownExpand Up@@ -682,6 +702,11 @@ TEST_F(GcsIntegrationTest, DeleteFileDirectoryFails) {
 ASSERT_RAISES(IOError, fs->DeleteFile(path));
}

TEST_F(GcsIntegrationTest, DeleteFileUri) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 ASSERT_RAISES(Invalid, fs->DeleteFile("gs://" + PreexistingObjectPath()));
}

TEST_F(GcsIntegrationTest, MoveFileSuccess) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 const auto destination_path = PreexistingBucketPath() + "move-destination";
Expand All@@ -708,6 +733,13 @@ TEST_F(GcsIntegrationTest, MoveFileCannotRenameToDirectory) {
 PreexistingBucketPath() + "destination/"));
}

TEST_F(GcsIntegrationTest, MoveFileUri) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 const auto destination_path = PreexistingBucketPath() + "move-destination";
 ASSERT_RAISES(Invalid, fs->Move("gs://" + PreexistingObjectPath(), destination_path));
 ASSERT_RAISES(Invalid, fs->Move(PreexistingObjectPath(), "gs://" + destination_path));
}

TEST_F(GcsIntegrationTest, CopyFileSuccess) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 const auto destination_path = PreexistingBucketPath() + "copy-destination";
Expand All@@ -721,6 +753,15 @@ TEST_F(GcsIntegrationTest, CopyFileNotFound) {
 ASSERT_RAISES(IOError, fs->CopyFile(NotFoundObjectPath(), destination_path));
}

TEST_F(GcsIntegrationTest, CopyFileUri) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 const auto destination_path = PreexistingBucketPath() + "copy-destination";
 ASSERT_RAISES(Invalid,
 fs->CopyFile("gs://" + PreexistingObjectPath(), destination_path));
 ASSERT_RAISES(Invalid,
 fs->CopyFile(PreexistingObjectPath(), "gs://" + destination_path));
}

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

Expand DownExpand Up@@ -797,6 +838,11 @@ TEST_F(GcsIntegrationTest, OpenInputStreamInfoInvalid) {
 ASSERT_RAISES(IOError, fs->OpenInputStream(info));
}

TEST_F(GcsIntegrationTest, OpenInputStreamUri) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 ASSERT_RAISES(Invalid, fs->OpenInputStream("gs://" + PreexistingObjectPath()));
}

TEST_F(GcsIntegrationTest, OpenInputStreamReadMetadata) {
 auto client = GcsClient();
 const auto custom_time = std::chrono::system_clock::now() + std::chrono::hours(1);
Expand DownExpand Up@@ -940,6 +986,14 @@ TEST_F(GcsIntegrationTest, OpenOutputStreamClosed) {
 ASSERT_RAISES(Invalid, output->Tell());
}

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

 const auto path =
 internal::ConcatAbstractPath(PreexistingBucketName(), "open-output-stream-uri.txt");
 ASSERT_RAISES(Invalid, fs->OpenInputStream("gs://" + path));
}

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

Expand Down
Loading

, '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-10998: [C++] Detect URIs where a filesystem path is expected#11997

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

pitrou
wants to merge
3
commits into

from

 Closed


ARROW-10998: [C++] Detect URIs where a filesystem path is expected
#11997
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


3 commits


Select commit
Hold shift + click to select a range
088129c

ARROW-10998: [C++] Detect URIs where a filesystem path is expected


pitrou Dec 20, 2021
88c7858

Use preferred URI scheme in GCS tests


pitrou Dec 20, 2021
fe73f3a

Fix typo


pitrou 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


121 changes: 61 additions & 60 deletions
cpp/src/arrow/filesystem/filesystem.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -245,6 +245,17 @@ Result<std::shared_ptr<io::OutputStream>> FileSystem::OpenAppendStream(
//////////////////////////////////////////////////////////////////////////
// SubTreeFileSystem implementation

namespace {

Status ValidateSubPath(util::string_view s) {
 if (internal::IsLikelyUri(s)) {
 return Status::Invalid("Expected a filesystem path, got a URI: '", s, "'");
 }
 return Status::OK();
}

} // namespace

SubTreeFileSystem::SubTreeFileSystem(const std::string& base_path,
 std::shared_ptr<FileSystem> base_fs)
 : FileSystem(base_fs->io_context()),
Expand All@@ -270,20 +281,21 @@ bool SubTreeFileSystem::Equals(const FileSystem& other) const {
 return base_path_ == subfs.base_path_ && base_fs_->Equals(subfs.base_fs_);
}

std::string SubTreeFileSystem::PrependBase(const std::string& s) const {
Result<std::string> SubTreeFileSystem::PrependBase(const std::string& s) const {
 RETURN_NOT_OK(ValidateSubPath(s));
 if (s.empty()) {
 return base_path_;
 } else {
 return ConcatAbstractPath(base_path_, s);
 }
}

Status SubTreeFileSystem::PrependBaseNonEmpty(std::string* s) const {
 if (s->empty()) {
Result<std::string> SubTreeFileSystem::PrependBaseNonEmpty(const std::string& s) const {
 RETURN_NOT_OK(ValidateSubPath(s));
 if (s.empty()) {
 return Status::IOError("Empty path");
 } else {
 *s = ConcatAbstractPath(base_path_, *s);
 return Status::OK();
 return ConcatAbstractPath(base_path_, s);
 }
}

Expand All@@ -305,19 +317,21 @@ Status SubTreeFileSystem::FixInfo(FileInfo* info) const {
}

Result<std::string> SubTreeFileSystem::NormalizePath(std::string path) {
 ARROW_ASSIGN_OR_RAISE(auto normalized, base_fs_->NormalizePath(PrependBase(path)));
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBase(path));
 ARROW_ASSIGN_OR_RAISE(auto normalized, base_fs_->NormalizePath(real_path));
 return StripBase(std::move(normalized));
}

Result<FileInfo> SubTreeFileSystem::GetFileInfo(const std::string& path) {
 ARROW_ASSIGN_OR_RAISE(FileInfo info, base_fs_->GetFileInfo(PrependBase(path)));
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBase(path));
 ARROW_ASSIGN_OR_RAISE(FileInfo info, base_fs_->GetFileInfo(real_path));
 RETURN_NOT_OK(FixInfo(&info));
 return info;
}

Result<std::vector<FileInfo>> SubTreeFileSystem::GetFileInfo(const FileSelector& select) {
 auto selector = select;
 selector.base_dir = PrependBase(selector.base_dir);
ARROW_ASSIGN_OR_RAISE(selector.base_dir, PrependBase(selector.base_dir));
 ARROW_ASSIGN_OR_RAISE(auto infos, base_fs_->GetFileInfo(selector));
 for (auto& info : infos) {
 RETURN_NOT_OK(FixInfo(&info));
Expand All@@ -327,7 +341,11 @@ Result<std::vector<FileInfo>> SubTreeFileSystem::GetFileInfo(const FileSelector&

FileInfoGenerator SubTreeFileSystem::GetFileInfoGenerator(const FileSelector& select) {
 auto selector = select;
 selector.base_dir = PrependBase(selector.base_dir);
 auto maybe_base_dir = PrependBase(selector.base_dir);
 if (!maybe_base_dir.ok()) {
 return MakeFailingGenerator<std::vector<FileInfo>>(maybe_base_dir.status());
 }
 selector.base_dir = *std::move(maybe_base_dir);
 auto gen = base_fs_->GetFileInfoGenerator(selector);

 auto self = checked_pointer_cast<SubTreeFileSystem>(shared_from_this());
Expand All@@ -343,23 +361,21 @@ FileInfoGenerator SubTreeFileSystem::GetFileInfoGenerator(const FileSelector& se
}

Status SubTreeFileSystem::CreateDir(const std::string& path, bool recursive) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->CreateDir(s, recursive);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->CreateDir(real_path, recursive);
}

Status SubTreeFileSystem::DeleteDir(const std::string& path) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->DeleteDir(s);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->DeleteDir(real_path);
}

Status SubTreeFileSystem::DeleteDirContents(const std::string& path) {
 if (internal::IsEmptyPath(path)) {
 return internal::InvalidDeleteDirContents(path);
 }
 auto s = PrependBase(path);
 return base_fs_->DeleteDirContents(s);
ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBase(path));
 return base_fs_->DeleteDirContents(real_path);
}

Status SubTreeFileSystem::DeleteRootDirContents() {
Expand All@@ -371,103 +387,88 @@ Status SubTreeFileSystem::DeleteRootDirContents() {
}

Status SubTreeFileSystem::DeleteFile(const std::string& path) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->DeleteFile(s);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->DeleteFile(real_path);
}

Status SubTreeFileSystem::Move(const std::string& src, const std::string& dest) {
 auto s = src;
 auto d = dest;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 RETURN_NOT_OK(PrependBaseNonEmpty(&d));
 return base_fs_->Move(s, d);
 ARROW_ASSIGN_OR_RAISE(auto real_src, PrependBaseNonEmpty(src));
 ARROW_ASSIGN_OR_RAISE(auto real_dest, PrependBaseNonEmpty(dest));
 return base_fs_->Move(real_src, real_dest);
}

Status SubTreeFileSystem::CopyFile(const std::string& src, const std::string& dest) {
 auto s = src;
 auto d = dest;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 RETURN_NOT_OK(PrependBaseNonEmpty(&d));
 return base_fs_->CopyFile(s, d);
 ARROW_ASSIGN_OR_RAISE(auto real_src, PrependBaseNonEmpty(src));
 ARROW_ASSIGN_OR_RAISE(auto real_dest, PrependBaseNonEmpty(dest));
 return base_fs_->CopyFile(real_src, real_dest);
}

Result<std::shared_ptr<io::InputStream>> SubTreeFileSystem::OpenInputStream(
 const std::string& path) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->OpenInputStream(s);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->OpenInputStream(real_path);
}

Result<std::shared_ptr<io::InputStream>> SubTreeFileSystem::OpenInputStream(
 const FileInfo& info) {
 auto s = info.path();
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(info.path()));
 FileInfo new_info(info);
 new_info.set_path(std::move(s));
 new_info.set_path(std::move(real_path));
 return base_fs_->OpenInputStream(new_info);
}

Future<std::shared_ptr<io::InputStream>> SubTreeFileSystem::OpenInputStreamAsync(
 const std::string& path) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->OpenInputStreamAsync(s);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->OpenInputStreamAsync(real_path);
}

Future<std::shared_ptr<io::InputStream>> SubTreeFileSystem::OpenInputStreamAsync(
 const FileInfo& info) {
 auto s = info.path();
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(info.path()));
 FileInfo new_info(info);
 new_info.set_path(std::move(s));
 new_info.set_path(std::move(real_path));
 return base_fs_->OpenInputStreamAsync(new_info);
}

Result<std::shared_ptr<io::RandomAccessFile>> SubTreeFileSystem::OpenInputFile(
 const std::string& path) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->OpenInputFile(s);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->OpenInputFile(real_path);
}

Result<std::shared_ptr<io::RandomAccessFile>> SubTreeFileSystem::OpenInputFile(
 const FileInfo& info) {
 auto s = info.path();
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(info.path()));
 FileInfo new_info(info);
 new_info.set_path(std::move(s));
 new_info.set_path(std::move(real_path));
 return base_fs_->OpenInputFile(new_info);
}

Future<std::shared_ptr<io::RandomAccessFile>> SubTreeFileSystem::OpenInputFileAsync(
 const std::string& path) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->OpenInputFileAsync(s);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->OpenInputFileAsync(real_path);
}

Future<std::shared_ptr<io::RandomAccessFile>> SubTreeFileSystem::OpenInputFileAsync(
 const FileInfo& info) {
 auto s = info.path();
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(info.path()));
 FileInfo new_info(info);
 new_info.set_path(std::move(s));
 new_info.set_path(std::move(real_path));
 return base_fs_->OpenInputFileAsync(new_info);
}

Result<std::shared_ptr<io::OutputStream>> SubTreeFileSystem::OpenOutputStream(
 const std::string& path, const std::shared_ptr<const KeyValueMetadata>& metadata) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->OpenOutputStream(s, metadata);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->OpenOutputStream(real_path, metadata);
}

Result<std::shared_ptr<io::OutputStream>> SubTreeFileSystem::OpenAppendStream(
 const std::string& path, const std::shared_ptr<const KeyValueMetadata>& metadata) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->OpenAppendStream(s, metadata);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->OpenAppendStream(real_path, metadata);
}

//////////////////////////////////////////////////////////////////////////
Expand Down

4 changes: 2 additions & 2 deletions
cpp/src/arrow/filesystem/filesystem.h

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -384,8 +384,8 @@ class ARROW_EXPORT SubTreeFileSystem : public FileSystem {
 const std::string base_path_;
 std::shared_ptr<FileSystem> base_fs_;

 std::string PrependBase(const std::string& s) const;
Status PrependBaseNonEmpty(std::string* s) const;
Result<std::string> PrependBase(const std::string& s) const;
Result<std::string> PrependBaseNonEmpty(const std::string& s) const;
 Result<std::string> StripBase(const std::string& s) const;
 Status FixInfo(FileInfo* info) const;

Expand Down

4 changes: 4 additions & 0 deletions
cpp/src/arrow/filesystem/gcsfs.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -57,6 +57,10 @@ struct GcsPath {
 std::string object;

 static Result<GcsPath> FromString(const std::string& s) {
 if (internal::IsLikelyUri(s)) {
 return Status::Invalid(
 "Expected a GCS object path of the form 'bucket/key...', got a URI: '", s, "'");
 }
 auto const first_sep = s.find_first_of(internal::kSep);
 if (first_sep == 0) {
 return Status::Invalid("Path cannot start with a separator ('", s, "')");
Expand Down

54 changes: 54 additions & 0 deletions
cpp/src/arrow/filesystem/gcsfs_test.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -478,6 +478,9 @@ TEST(GcsFileSystem, ObjectMetadataRoundtrip) {
TEST_F(GcsIntegrationTest, GetFileInfoBucket) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 arrow::fs::AssertFileInfo(fs.get(), PreexistingBucketPath(), FileType::Directory);

 // URI
 ASSERT_RAISES(Invalid, fs->GetFileInfo("gs://" + PreexistingBucketPath()));
}

TEST_F(GcsIntegrationTest, GetFileInfoObject) {
Expand All@@ -487,6 +490,9 @@ TEST_F(GcsIntegrationTest, GetFileInfoObject) {
 ASSERT_TRUE(object.ok()) << "status=" << object.status();
 arrow::fs::AssertFileInfo(fs.get(), PreexistingObjectPath(), FileType::File,
 object->time_created(), static_cast<int64_t>(object->size()));

 // URI
 ASSERT_RAISES(Invalid, fs->GetFileInfo("gs://" + PreexistingObjectName()));
}

TEST_F(GcsIntegrationTest, GetFileInfoSelectorRecursive) {
Expand All@@ -508,6 +514,10 @@ TEST_F(GcsIntegrationTest, GetFileInfoSelectorRecursive) {
 selector.max_recursion = 16;
 ASSERT_OK_AND_ASSIGN(auto results, fs->GetFileInfo(selector));
 EXPECT_THAT(results, UnorderedElementsAreArray(expected.begin(), expected.end()));

 // URI
 selector.base_dir = "gs://" + selector.base_dir;
 ASSERT_RAISES(Invalid, fs->GetFileInfo(selector));
}

TEST_F(GcsIntegrationTest, GetFileInfoSelectorNonRecursive) {
Expand DownExpand Up@@ -626,6 +636,11 @@ TEST_F(GcsIntegrationTest, CreateDirRecursiveBucketAndFolder) {
 arrow::fs::AssertFileInfo(fs.get(), bucket_name + "/", FileType::Directory);
}

TEST_F(GcsIntegrationTest, CreateDirUri) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 ASSERT_RAISES(Invalid, fs->CreateDir("gs://" + RandomBucketName(), true));
}

TEST_F(GcsIntegrationTest, DeleteDirSuccess) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 ASSERT_OK_AND_ASSIGN(auto hierarchy, CreateHierarchy(fs));
Expand All@@ -641,6 +656,11 @@ TEST_F(GcsIntegrationTest, DeleteDirSuccess) {
 }
}

TEST_F(GcsIntegrationTest, DeleteDirUri) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 ASSERT_RAISES(Invalid, fs->DeleteDir("gs://" + PreexistingBucketPath()));
}

TEST_F(GcsIntegrationTest, DeleteDirContentsSuccess) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 ASSERT_OK_AND_ASSIGN(auto hierarchy, CreateHierarchy(fs));
Expand DownExpand Up@@ -682,6 +702,11 @@ TEST_F(GcsIntegrationTest, DeleteFileDirectoryFails) {
 ASSERT_RAISES(IOError, fs->DeleteFile(path));
}

TEST_F(GcsIntegrationTest, DeleteFileUri) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 ASSERT_RAISES(Invalid, fs->DeleteFile("gs://" + PreexistingObjectPath()));
}

TEST_F(GcsIntegrationTest, MoveFileSuccess) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 const auto destination_path = PreexistingBucketPath() + "move-destination";
Expand All@@ -708,6 +733,13 @@ TEST_F(GcsIntegrationTest, MoveFileCannotRenameToDirectory) {
 PreexistingBucketPath() + "destination/"));
}

TEST_F(GcsIntegrationTest, MoveFileUri) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 const auto destination_path = PreexistingBucketPath() + "move-destination";
 ASSERT_RAISES(Invalid, fs->Move("gs://" + PreexistingObjectPath(), destination_path));
 ASSERT_RAISES(Invalid, fs->Move(PreexistingObjectPath(), "gs://" + destination_path));
}

TEST_F(GcsIntegrationTest, CopyFileSuccess) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 const auto destination_path = PreexistingBucketPath() + "copy-destination";
Expand All@@ -721,6 +753,15 @@ TEST_F(GcsIntegrationTest, CopyFileNotFound) {
 ASSERT_RAISES(IOError, fs->CopyFile(NotFoundObjectPath(), destination_path));
}

TEST_F(GcsIntegrationTest, CopyFileUri) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 const auto destination_path = PreexistingBucketPath() + "copy-destination";
 ASSERT_RAISES(Invalid,
 fs->CopyFile("gs://" + PreexistingObjectPath(), destination_path));
 ASSERT_RAISES(Invalid,
 fs->CopyFile(PreexistingObjectPath(), "gs://" + destination_path));
}

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

Expand DownExpand Up@@ -797,6 +838,11 @@ TEST_F(GcsIntegrationTest, OpenInputStreamInfoInvalid) {
 ASSERT_RAISES(IOError, fs->OpenInputStream(info));
}

TEST_F(GcsIntegrationTest, OpenInputStreamUri) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 ASSERT_RAISES(Invalid, fs->OpenInputStream("gs://" + PreexistingObjectPath()));
}

TEST_F(GcsIntegrationTest, OpenInputStreamReadMetadata) {
 auto client = GcsClient();
 const auto custom_time = std::chrono::system_clock::now() + std::chrono::hours(1);
Expand DownExpand Up@@ -940,6 +986,14 @@ TEST_F(GcsIntegrationTest, OpenOutputStreamClosed) {
 ASSERT_RAISES(Invalid, output->Tell());
}

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

 const auto path =
 internal::ConcatAbstractPath(PreexistingBucketName(), "open-output-stream-uri.txt");
 ASSERT_RAISES(Invalid, fs->OpenInputStream("gs://" + path));
}

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

Expand Down
Loading

, '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-10998: [C++] Detect URIs where a filesystem path is expected#11997

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

pitrou
wants to merge
3
commits into

from

 Closed


ARROW-10998: [C++] Detect URIs where a filesystem path is expected
#11997
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


3 commits


Select commit
Hold shift + click to select a range
088129c

ARROW-10998: [C++] Detect URIs where a filesystem path is expected


pitrou Dec 20, 2021
88c7858

Use preferred URI scheme in GCS tests


pitrou Dec 20, 2021
fe73f3a

Fix typo


pitrou 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


121 changes: 61 additions & 60 deletions
cpp/src/arrow/filesystem/filesystem.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -245,6 +245,17 @@ Result<std::shared_ptr<io::OutputStream>> FileSystem::OpenAppendStream(
//////////////////////////////////////////////////////////////////////////
// SubTreeFileSystem implementation

namespace {

Status ValidateSubPath(util::string_view s) {
 if (internal::IsLikelyUri(s)) {
 return Status::Invalid("Expected a filesystem path, got a URI: '", s, "'");
 }
 return Status::OK();
}

} // namespace

SubTreeFileSystem::SubTreeFileSystem(const std::string& base_path,
 std::shared_ptr<FileSystem> base_fs)
 : FileSystem(base_fs->io_context()),
Expand All@@ -270,20 +281,21 @@ bool SubTreeFileSystem::Equals(const FileSystem& other) const {
 return base_path_ == subfs.base_path_ && base_fs_->Equals(subfs.base_fs_);
}

std::string SubTreeFileSystem::PrependBase(const std::string& s) const {
Result<std::string> SubTreeFileSystem::PrependBase(const std::string& s) const {
 RETURN_NOT_OK(ValidateSubPath(s));
 if (s.empty()) {
 return base_path_;
 } else {
 return ConcatAbstractPath(base_path_, s);
 }
}

Status SubTreeFileSystem::PrependBaseNonEmpty(std::string* s) const {
 if (s->empty()) {
Result<std::string> SubTreeFileSystem::PrependBaseNonEmpty(const std::string& s) const {
 RETURN_NOT_OK(ValidateSubPath(s));
 if (s.empty()) {
 return Status::IOError("Empty path");
 } else {
 *s = ConcatAbstractPath(base_path_, *s);
 return Status::OK();
 return ConcatAbstractPath(base_path_, s);
 }
}

Expand All@@ -305,19 +317,21 @@ Status SubTreeFileSystem::FixInfo(FileInfo* info) const {
}

Result<std::string> SubTreeFileSystem::NormalizePath(std::string path) {
 ARROW_ASSIGN_OR_RAISE(auto normalized, base_fs_->NormalizePath(PrependBase(path)));
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBase(path));
 ARROW_ASSIGN_OR_RAISE(auto normalized, base_fs_->NormalizePath(real_path));
 return StripBase(std::move(normalized));
}

Result<FileInfo> SubTreeFileSystem::GetFileInfo(const std::string& path) {
 ARROW_ASSIGN_OR_RAISE(FileInfo info, base_fs_->GetFileInfo(PrependBase(path)));
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBase(path));
 ARROW_ASSIGN_OR_RAISE(FileInfo info, base_fs_->GetFileInfo(real_path));
 RETURN_NOT_OK(FixInfo(&info));
 return info;
}

Result<std::vector<FileInfo>> SubTreeFileSystem::GetFileInfo(const FileSelector& select) {
 auto selector = select;
 selector.base_dir = PrependBase(selector.base_dir);
ARROW_ASSIGN_OR_RAISE(selector.base_dir, PrependBase(selector.base_dir));
 ARROW_ASSIGN_OR_RAISE(auto infos, base_fs_->GetFileInfo(selector));
 for (auto& info : infos) {
 RETURN_NOT_OK(FixInfo(&info));
Expand All@@ -327,7 +341,11 @@ Result<std::vector<FileInfo>> SubTreeFileSystem::GetFileInfo(const FileSelector&

FileInfoGenerator SubTreeFileSystem::GetFileInfoGenerator(const FileSelector& select) {
 auto selector = select;
 selector.base_dir = PrependBase(selector.base_dir);
 auto maybe_base_dir = PrependBase(selector.base_dir);
 if (!maybe_base_dir.ok()) {
 return MakeFailingGenerator<std::vector<FileInfo>>(maybe_base_dir.status());
 }
 selector.base_dir = *std::move(maybe_base_dir);
 auto gen = base_fs_->GetFileInfoGenerator(selector);

 auto self = checked_pointer_cast<SubTreeFileSystem>(shared_from_this());
Expand All@@ -343,23 +361,21 @@ FileInfoGenerator SubTreeFileSystem::GetFileInfoGenerator(const FileSelector& se
}

Status SubTreeFileSystem::CreateDir(const std::string& path, bool recursive) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->CreateDir(s, recursive);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->CreateDir(real_path, recursive);
}

Status SubTreeFileSystem::DeleteDir(const std::string& path) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->DeleteDir(s);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->DeleteDir(real_path);
}

Status SubTreeFileSystem::DeleteDirContents(const std::string& path) {
 if (internal::IsEmptyPath(path)) {
 return internal::InvalidDeleteDirContents(path);
 }
 auto s = PrependBase(path);
 return base_fs_->DeleteDirContents(s);
ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBase(path));
 return base_fs_->DeleteDirContents(real_path);
}

Status SubTreeFileSystem::DeleteRootDirContents() {
Expand All@@ -371,103 +387,88 @@ Status SubTreeFileSystem::DeleteRootDirContents() {
}

Status SubTreeFileSystem::DeleteFile(const std::string& path) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->DeleteFile(s);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->DeleteFile(real_path);
}

Status SubTreeFileSystem::Move(const std::string& src, const std::string& dest) {
 auto s = src;
 auto d = dest;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 RETURN_NOT_OK(PrependBaseNonEmpty(&d));
 return base_fs_->Move(s, d);
 ARROW_ASSIGN_OR_RAISE(auto real_src, PrependBaseNonEmpty(src));
 ARROW_ASSIGN_OR_RAISE(auto real_dest, PrependBaseNonEmpty(dest));
 return base_fs_->Move(real_src, real_dest);
}

Status SubTreeFileSystem::CopyFile(const std::string& src, const std::string& dest) {
 auto s = src;
 auto d = dest;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 RETURN_NOT_OK(PrependBaseNonEmpty(&d));
 return base_fs_->CopyFile(s, d);
 ARROW_ASSIGN_OR_RAISE(auto real_src, PrependBaseNonEmpty(src));
 ARROW_ASSIGN_OR_RAISE(auto real_dest, PrependBaseNonEmpty(dest));
 return base_fs_->CopyFile(real_src, real_dest);
}

Result<std::shared_ptr<io::InputStream>> SubTreeFileSystem::OpenInputStream(
 const std::string& path) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->OpenInputStream(s);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->OpenInputStream(real_path);
}

Result<std::shared_ptr<io::InputStream>> SubTreeFileSystem::OpenInputStream(
 const FileInfo& info) {
 auto s = info.path();
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(info.path()));
 FileInfo new_info(info);
 new_info.set_path(std::move(s));
 new_info.set_path(std::move(real_path));
 return base_fs_->OpenInputStream(new_info);
}

Future<std::shared_ptr<io::InputStream>> SubTreeFileSystem::OpenInputStreamAsync(
 const std::string& path) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->OpenInputStreamAsync(s);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->OpenInputStreamAsync(real_path);
}

Future<std::shared_ptr<io::InputStream>> SubTreeFileSystem::OpenInputStreamAsync(
 const FileInfo& info) {
 auto s = info.path();
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(info.path()));
 FileInfo new_info(info);
 new_info.set_path(std::move(s));
 new_info.set_path(std::move(real_path));
 return base_fs_->OpenInputStreamAsync(new_info);
}

Result<std::shared_ptr<io::RandomAccessFile>> SubTreeFileSystem::OpenInputFile(
 const std::string& path) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->OpenInputFile(s);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->OpenInputFile(real_path);
}

Result<std::shared_ptr<io::RandomAccessFile>> SubTreeFileSystem::OpenInputFile(
 const FileInfo& info) {
 auto s = info.path();
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(info.path()));
 FileInfo new_info(info);
 new_info.set_path(std::move(s));
 new_info.set_path(std::move(real_path));
 return base_fs_->OpenInputFile(new_info);
}

Future<std::shared_ptr<io::RandomAccessFile>> SubTreeFileSystem::OpenInputFileAsync(
 const std::string& path) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->OpenInputFileAsync(s);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->OpenInputFileAsync(real_path);
}

Future<std::shared_ptr<io::RandomAccessFile>> SubTreeFileSystem::OpenInputFileAsync(
 const FileInfo& info) {
 auto s = info.path();
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(info.path()));
 FileInfo new_info(info);
 new_info.set_path(std::move(s));
 new_info.set_path(std::move(real_path));
 return base_fs_->OpenInputFileAsync(new_info);
}

Result<std::shared_ptr<io::OutputStream>> SubTreeFileSystem::OpenOutputStream(
 const std::string& path, const std::shared_ptr<const KeyValueMetadata>& metadata) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->OpenOutputStream(s, metadata);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->OpenOutputStream(real_path, metadata);
}

Result<std::shared_ptr<io::OutputStream>> SubTreeFileSystem::OpenAppendStream(
 const std::string& path, const std::shared_ptr<const KeyValueMetadata>& metadata) {
 auto s = path;
 RETURN_NOT_OK(PrependBaseNonEmpty(&s));
 return base_fs_->OpenAppendStream(s, metadata);
 ARROW_ASSIGN_OR_RAISE(auto real_path, PrependBaseNonEmpty(path));
 return base_fs_->OpenAppendStream(real_path, metadata);
}

//////////////////////////////////////////////////////////////////////////
Expand Down

4 changes: 2 additions & 2 deletions
cpp/src/arrow/filesystem/filesystem.h

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -384,8 +384,8 @@ class ARROW_EXPORT SubTreeFileSystem : public FileSystem {
 const std::string base_path_;
 std::shared_ptr<FileSystem> base_fs_;

 std::string PrependBase(const std::string& s) const;
Status PrependBaseNonEmpty(std::string* s) const;
Result<std::string> PrependBase(const std::string& s) const;
Result<std::string> PrependBaseNonEmpty(const std::string& s) const;
 Result<std::string> StripBase(const std::string& s) const;
 Status FixInfo(FileInfo* info) const;

Expand Down

4 changes: 4 additions & 0 deletions
cpp/src/arrow/filesystem/gcsfs.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -57,6 +57,10 @@ struct GcsPath {
 std::string object;

 static Result<GcsPath> FromString(const std::string& s) {
 if (internal::IsLikelyUri(s)) {
 return Status::Invalid(
 "Expected a GCS object path of the form 'bucket/key...', got a URI: '", s, "'");
 }
 auto const first_sep = s.find_first_of(internal::kSep);
 if (first_sep == 0) {
 return Status::Invalid("Path cannot start with a separator ('", s, "')");
Expand Down

54 changes: 54 additions & 0 deletions
cpp/src/arrow/filesystem/gcsfs_test.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -478,6 +478,9 @@ TEST(GcsFileSystem, ObjectMetadataRoundtrip) {
TEST_F(GcsIntegrationTest, GetFileInfoBucket) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 arrow::fs::AssertFileInfo(fs.get(), PreexistingBucketPath(), FileType::Directory);

 // URI
 ASSERT_RAISES(Invalid, fs->GetFileInfo("gs://" + PreexistingBucketPath()));
}

TEST_F(GcsIntegrationTest, GetFileInfoObject) {
Expand All@@ -487,6 +490,9 @@ TEST_F(GcsIntegrationTest, GetFileInfoObject) {
 ASSERT_TRUE(object.ok()) << "status=" << object.status();
 arrow::fs::AssertFileInfo(fs.get(), PreexistingObjectPath(), FileType::File,
 object->time_created(), static_cast<int64_t>(object->size()));

 // URI
 ASSERT_RAISES(Invalid, fs->GetFileInfo("gs://" + PreexistingObjectName()));
}

TEST_F(GcsIntegrationTest, GetFileInfoSelectorRecursive) {
Expand All@@ -508,6 +514,10 @@ TEST_F(GcsIntegrationTest, GetFileInfoSelectorRecursive) {
 selector.max_recursion = 16;
 ASSERT_OK_AND_ASSIGN(auto results, fs->GetFileInfo(selector));
 EXPECT_THAT(results, UnorderedElementsAreArray(expected.begin(), expected.end()));

 // URI
 selector.base_dir = "gs://" + selector.base_dir;
 ASSERT_RAISES(Invalid, fs->GetFileInfo(selector));
}

TEST_F(GcsIntegrationTest, GetFileInfoSelectorNonRecursive) {
Expand DownExpand Up@@ -626,6 +636,11 @@ TEST_F(GcsIntegrationTest, CreateDirRecursiveBucketAndFolder) {
 arrow::fs::AssertFileInfo(fs.get(), bucket_name + "/", FileType::Directory);
}

TEST_F(GcsIntegrationTest, CreateDirUri) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 ASSERT_RAISES(Invalid, fs->CreateDir("gs://" + RandomBucketName(), true));
}

TEST_F(GcsIntegrationTest, DeleteDirSuccess) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 ASSERT_OK_AND_ASSIGN(auto hierarchy, CreateHierarchy(fs));
Expand All@@ -641,6 +656,11 @@ TEST_F(GcsIntegrationTest, DeleteDirSuccess) {
 }
}

TEST_F(GcsIntegrationTest, DeleteDirUri) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 ASSERT_RAISES(Invalid, fs->DeleteDir("gs://" + PreexistingBucketPath()));
}

TEST_F(GcsIntegrationTest, DeleteDirContentsSuccess) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 ASSERT_OK_AND_ASSIGN(auto hierarchy, CreateHierarchy(fs));
Expand DownExpand Up@@ -682,6 +702,11 @@ TEST_F(GcsIntegrationTest, DeleteFileDirectoryFails) {
 ASSERT_RAISES(IOError, fs->DeleteFile(path));
}

TEST_F(GcsIntegrationTest, DeleteFileUri) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 ASSERT_RAISES(Invalid, fs->DeleteFile("gs://" + PreexistingObjectPath()));
}

TEST_F(GcsIntegrationTest, MoveFileSuccess) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 const auto destination_path = PreexistingBucketPath() + "move-destination";
Expand All@@ -708,6 +733,13 @@ TEST_F(GcsIntegrationTest, MoveFileCannotRenameToDirectory) {
 PreexistingBucketPath() + "destination/"));
}

TEST_F(GcsIntegrationTest, MoveFileUri) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 const auto destination_path = PreexistingBucketPath() + "move-destination";
 ASSERT_RAISES(Invalid, fs->Move("gs://" + PreexistingObjectPath(), destination_path));
 ASSERT_RAISES(Invalid, fs->Move(PreexistingObjectPath(), "gs://" + destination_path));
}

TEST_F(GcsIntegrationTest, CopyFileSuccess) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 const auto destination_path = PreexistingBucketPath() + "copy-destination";
Expand All@@ -721,6 +753,15 @@ TEST_F(GcsIntegrationTest, CopyFileNotFound) {
 ASSERT_RAISES(IOError, fs->CopyFile(NotFoundObjectPath(), destination_path));
}

TEST_F(GcsIntegrationTest, CopyFileUri) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 const auto destination_path = PreexistingBucketPath() + "copy-destination";
 ASSERT_RAISES(Invalid,
 fs->CopyFile("gs://" + PreexistingObjectPath(), destination_path));
 ASSERT_RAISES(Invalid,
 fs->CopyFile(PreexistingObjectPath(), "gs://" + destination_path));
}

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

Expand DownExpand Up@@ -797,6 +838,11 @@ TEST_F(GcsIntegrationTest, OpenInputStreamInfoInvalid) {
 ASSERT_RAISES(IOError, fs->OpenInputStream(info));
}

TEST_F(GcsIntegrationTest, OpenInputStreamUri) {
 auto fs = internal::MakeGcsFileSystemForTest(TestGcsOptions());
 ASSERT_RAISES(Invalid, fs->OpenInputStream("gs://" + PreexistingObjectPath()));
}

TEST_F(GcsIntegrationTest, OpenInputStreamReadMetadata) {
 auto client = GcsClient();
 const auto custom_time = std::chrono::system_clock::now() + std::chrono::hours(1);
Expand DownExpand Up@@ -940,6 +986,14 @@ TEST_F(GcsIntegrationTest, OpenOutputStreamClosed) {
 ASSERT_RAISES(Invalid, output->Tell());
}

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

 const auto path =
 internal::ConcatAbstractPath(PreexistingBucketName(), "open-output-stream-uri.txt");
 ASSERT_RAISES(Invalid, fs->OpenInputStream("gs://" + path));
}

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

Expand Down
Loading