GH-39049: [C++] Use Cast() instead of CastTo() for Dictionary Scalar in test#39362

New issue

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

Sign up for GitHub

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

Already on GitHub? Sign in to your account

Merged
kou merged 4 commits into from
Jan 6, 2024
Merged

GH-39049: [C++] Use Cast() instead of CastTo() for Dictionary Scalar in test #39362

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
030c445
Add casting from string to dictionary
llama90 Dec 24, 2023
731e944
Fix adding dictionary cast kernel
llama90 Dec 24, 2023
ea42725
Update the suggestions from the review
llama90 Jan 5, 2024
b4996ef
Update to use ScalarKernel constructor
llama90 Jan 6, 2024
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
30 changes: 21 additions & 9 deletions cpp/src/arrow/compute/kernels/scalar_cast_dictionary.cc
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -36,14 +36,22 @@ Status CastToDictionary(KernelContext* ctx, const ExecSpan& batch, ExecResult* o
const CastOptions& options = CastState::Get(ctx);
const auto& out_type = checked_cast<const DictionaryType&>(*out->type());

std::shared_ptr<ArrayData> in_array = batch[0].array.ToArrayData();

// if out type is same as in type, return input
if (out_type.Equals(*batch[0].type())) {
/// XXX: This is the wrong place to do a zero-copy optimization
out->value = batch[0].array.ToArrayData();
out->value = in_array;
return Status::OK();
}

std::shared_ptr<ArrayData> in_array = batch[0].array.ToArrayData();
// If the input type is STRING, it is first encoded as a dictionary to facilitate
// processing. This approach allows the subsequent code to uniformly handle STRING
// inputs as if they were originally provided in dictionary format. Encoding as a
// dictionary helps in reusing the same logic for dictionary operations.
if (batch[0].type()->id() == Type::STRING) {
in_array = DictionaryEncode(in_array)->array();
}
const auto& in_type = checked_cast<const DictionaryType&>(*in_array->type);

ArrayData* out_array = out->array_data().get();
Expand DownExpand Up@@ -77,17 +85,21 @@ Status CastToDictionary(KernelContext* ctx, const ExecSpan& batch, ExecResult* o
return Status::OK();
}

std::vector<std::shared_ptr<CastFunction>> GetDictionaryCasts() {
auto func = std::make_shared<CastFunction>("cast_dictionary", Type::DICTIONARY);

AddCommonCasts(Type::DICTIONARY, kOutputTargetType, func.get());
ScalarKernel kernel({InputType(Type::DICTIONARY)}, kOutputTargetType, CastToDictionary);
template <typename SrcType>
void AddDictionaryCast(CastFunction* func) {
ScalarKernel kernel({InputType(SrcType::type_id)}, kOutputTargetType, CastToDictionary);
kernel.null_handling = NullHandling::COMPUTED_NO_PREALLOCATE;
kernel.mem_allocation = MemAllocation::NO_PREALLOCATE;
Comment thread
llama90 marked this conversation as resolved.
DCHECK_OK(func->AddKernel(SrcType::type_id, std::move(kernel)));
}

DCHECK_OK(func->AddKernel(Type::DICTIONARY, std::move(kernel)));
std::vector<std::shared_ptr<CastFunction>> GetDictionaryCasts() {
auto cast_dict = std::make_shared<CastFunction>("cast_dictionary", Type::DICTIONARY);
AddCommonCasts(Type::DICTIONARY, kOutputTargetType, cast_dict.get());
AddDictionaryCast<DictionaryType>(cast_dict.get());
AddDictionaryCast<StringType>(cast_dict.get());
Comment thread
llama90 marked this conversation as resolved.

return {func};
return {cast_dict};
}

} // namespace internal
Expand Down
4 changes: 2 additions & 2 deletions cpp/src/arrow/dataset/partition_test.cc
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -316,7 +316,7 @@ TEST_F(TestPartitioning, DirectoryPartitioningFormatDictionary) {
ArrayVector{dictionary});
written_schema_ = partitioning_->schema();

ASSERT_OK_AND_ASSIGN(auto dict_hello, MakeScalar("hello")->CastTo(DictStr("")->type()));
ASSERT_OK_AND_ASSIGN(auto dict_hello, Cast(MakeScalar("hello"), DictStr("")->type()));
AssertFormat(equal(field_ref("alpha"), literal(dict_hello)), "hello");
}

Expand All@@ -329,7 +329,7 @@ TEST_F(TestPartitioning, DirectoryPartitioningFormatDictionaryCustomIndex) {
schema({field("alpha", dict_type)}), ArrayVector{dictionary});
written_schema_ = partitioning_->schema();

ASSERT_OK_AND_ASSIGN(auto dict_hello, MakeScalar("hello")->CastTo(dict_type));
ASSERT_OK_AND_ASSIGN(auto dict_hello, Cast(MakeScalar("hello"), dict_type));
AssertFormat(equal(field_ref("alpha"), literal(dict_hello)), "hello");
}

Expand Down
3 changes: 2 additions & 1 deletion cpp/src/arrow/scalar_test.cc
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -1479,7 +1479,8 @@ TEST(TestDictionaryScalar, Cast) {
auto alpha =
dict->IsValid(i) ? MakeScalar(dict->GetString(i)) : MakeNullScalar(utf8());
// Cast string to dict(..., string)
ASSERT_OK_AND_ASSIGN(auto cast_alpha, alpha->CastTo(ty));
ASSERT_OK_AND_ASSIGN(auto cast_alpha_datum, Cast(alpha, ty));
const auto& cast_alpha = cast_alpha_datum.scalar();
ASSERT_OK(cast_alpha->ValidateFull());
ASSERT_OK_AND_ASSIGN(
auto roundtripped_alpha,
Expand Down
, 'i'); if (__m === '*' || __re.test(location.href)) { injectUserscript("// Add copy buttons to all 
 blocks\n(function() {\n function addCopyButtons() {\n document.querySelectorAll('pre code').forEach(function(codeBlock) {\n if (codeBlock.parentElement.hasAttribute('data-copy-added')) return;\n codeBlock.parentElement.setAttribute('data-copy-added', 'true');\n \n var btn = document.createElement('button');\n btn.textContent = 'Copy';\n btn.style.cssText = 'position:absolute;top:4px;right:4px;padding:2px 8px;font-size:11px;background:#4ecdc4;border:none;border-radius:4px;color:#1a1a2e;cursor:pointer;opacity:0.7;transition:opacity 0.2s;';\n btn.onmouseover = function() { this.style.opacity = '1'; };\n btn.onmouseout = function() { this.style.opacity = '0.7'; };\n btn.onclick = function() {\n navigator.clipboard.writeText(codeBlock.textContent).then(function() {\n btn.textContent = 'Copied!';\n setTimeout(function() { btn.textContent = 'Copy'; }, 1500);\n });\n };\n codeBlock.parentElement.style.position = 'relative';\n codeBlock.parentElement.appendChild(btn);\n });\n }\n \n addCopyButtons();\n \n // Re-run on dynamic content\n var observer = new MutationObserver(addCopyButtons);\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Add Copy Buttons to Code Blocks");
}
} catch(__e) { console.warn('[Userscript:Add Copy Buttons to Code Blocks]', __e); }
})();
(function(){
try {
var __m = "github.com";
var __re = new RegExp('^' + "github\\.com" + '

Skip to content
GH-39049: [C++] Use Cast() instead of CastTo() for Dictionary Scalar in test#39362

New issue

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

 Sign up for GitHub

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

Already on GitHub?
Sign in
to your account

 Merged

kou
merged 4 commits into

from

Jan 6, 2024
 Merged


GH-39049: [C++] Use Cast() instead of CastTo() for Dictionary Scalar in test
#39362
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


4 commits


Select commit
Hold shift + click to select a range
030c445

Add casting from string to dictionary


llama90 Dec 24, 2023
731e944

Fix adding dictionary cast kernel


llama90 Dec 24, 2023
ea42725

Update the suggestions from the review


llama90 Jan 5, 2024
b4996ef

Update to use ScalarKernel constructor


llama90 Jan 6, 2024

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


30 changes: 21 additions & 9 deletions
cpp/src/arrow/compute/kernels/scalar_cast_dictionary.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -36,14 +36,22 @@ Status CastToDictionary(KernelContext* ctx, const ExecSpan& batch, ExecResult* o
 const CastOptions& options = CastState::Get(ctx);
 const auto& out_type = checked_cast<const DictionaryType&>(*out->type());

 std::shared_ptr<ArrayData> in_array = batch[0].array.ToArrayData();

 // if out type is same as in type, return input
 if (out_type.Equals(*batch[0].type())) {
 /// XXX: This is the wrong place to do a zero-copy optimization
 out->value = batch[0].array.ToArrayData();
 out->value = in_array;
 return Status::OK();
 }

 std::shared_ptr<ArrayData> in_array = batch[0].array.ToArrayData();
 // If the input type is STRING, it is first encoded as a dictionary to facilitate
 // processing. This approach allows the subsequent code to uniformly handle STRING
 // inputs as if they were originally provided in dictionary format. Encoding as a
 // dictionary helps in reusing the same logic for dictionary operations.
 if (batch[0].type()->id() == Type::STRING) {
 in_array = DictionaryEncode(in_array)->array();
 }
 const auto& in_type = checked_cast<const DictionaryType&>(*in_array->type);

 ArrayData* out_array = out->array_data().get();
Expand DownExpand Up@@ -77,17 +85,21 @@ Status CastToDictionary(KernelContext* ctx, const ExecSpan& batch, ExecResult* o
 return Status::OK();
}

std::vector<std::shared_ptr<CastFunction>> GetDictionaryCasts() {
 auto func = std::make_shared<CastFunction>("cast_dictionary", Type::DICTIONARY);

 AddCommonCasts(Type::DICTIONARY, kOutputTargetType, func.get());
 ScalarKernel kernel({InputType(Type::DICTIONARY)}, kOutputTargetType, CastToDictionary);
template <typename SrcType>
void AddDictionaryCast(CastFunction* func) {
 ScalarKernel kernel({InputType(SrcType::type_id)}, kOutputTargetType, CastToDictionary);
 kernel.null_handling = NullHandling::COMPUTED_NO_PREALLOCATE;
 kernel.mem_allocation = MemAllocation::NO_PREALLOCATE;
Comment thread
llama90 marked this conversation as resolved.

 DCHECK_OK(func->AddKernel(SrcType::type_id, std::move(kernel)));
}

 DCHECK_OK(func->AddKernel(Type::DICTIONARY, std::move(kernel)));
std::vector<std::shared_ptr<CastFunction>> GetDictionaryCasts() {
 auto cast_dict = std::make_shared<CastFunction>("cast_dictionary", Type::DICTIONARY);
 AddCommonCasts(Type::DICTIONARY, kOutputTargetType, cast_dict.get());
 AddDictionaryCast<DictionaryType>(cast_dict.get());
 AddDictionaryCast<StringType>(cast_dict.get());
Comment thread
llama90 marked this conversation as resolved.


 return {func};
 return {cast_dict};
}

} // namespace internal
Expand Down

4 changes: 2 additions & 2 deletions
cpp/src/arrow/dataset/partition_test.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -316,7 +316,7 @@ TEST_F(TestPartitioning, DirectoryPartitioningFormatDictionary) {
 ArrayVector{dictionary});
 written_schema_ = partitioning_->schema();

 ASSERT_OK_AND_ASSIGN(auto dict_hello, MakeScalar("hello")->CastTo(DictStr("")->type()));
 ASSERT_OK_AND_ASSIGN(auto dict_hello, Cast(MakeScalar("hello"), DictStr("")->type()));
 AssertFormat(equal(field_ref("alpha"), literal(dict_hello)), "hello");
}

Expand All@@ -329,7 +329,7 @@ TEST_F(TestPartitioning, DirectoryPartitioningFormatDictionaryCustomIndex) {
 schema({field("alpha", dict_type)}), ArrayVector{dictionary});
 written_schema_ = partitioning_->schema();

 ASSERT_OK_AND_ASSIGN(auto dict_hello, MakeScalar("hello")->CastTo(dict_type));
 ASSERT_OK_AND_ASSIGN(auto dict_hello, Cast(MakeScalar("hello"), dict_type));
 AssertFormat(equal(field_ref("alpha"), literal(dict_hello)), "hello");
}

Expand Down

3 changes: 2 additions & 1 deletion
cpp/src/arrow/scalar_test.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -1479,7 +1479,8 @@ TEST(TestDictionaryScalar, Cast) {
 auto alpha =
 dict->IsValid(i) ? MakeScalar(dict->GetString(i)) : MakeNullScalar(utf8());
 // Cast string to dict(..., string)
 ASSERT_OK_AND_ASSIGN(auto cast_alpha, alpha->CastTo(ty));
 ASSERT_OK_AND_ASSIGN(auto cast_alpha_datum, Cast(alpha, ty));
 const auto& cast_alpha = cast_alpha_datum.scalar();
 ASSERT_OK(cast_alpha->ValidateFull());
 ASSERT_OK_AND_ASSIGN(
 auto roundtripped_alpha,
Expand Down

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

Skip to content
GH-39049: [C++] Use Cast() instead of CastTo() for Dictionary Scalar in test#39362

New issue

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

 Sign up for GitHub

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

Already on GitHub?
Sign in
to your account

 Merged

kou
merged 4 commits into

from

Jan 6, 2024
 Merged


GH-39049: [C++] Use Cast() instead of CastTo() for Dictionary Scalar in test
#39362
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


4 commits


Select commit
Hold shift + click to select a range
030c445

Add casting from string to dictionary


llama90 Dec 24, 2023
731e944

Fix adding dictionary cast kernel


llama90 Dec 24, 2023
ea42725

Update the suggestions from the review


llama90 Jan 5, 2024
b4996ef

Update to use ScalarKernel constructor


llama90 Jan 6, 2024

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


30 changes: 21 additions & 9 deletions
cpp/src/arrow/compute/kernels/scalar_cast_dictionary.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -36,14 +36,22 @@ Status CastToDictionary(KernelContext* ctx, const ExecSpan& batch, ExecResult* o
 const CastOptions& options = CastState::Get(ctx);
 const auto& out_type = checked_cast<const DictionaryType&>(*out->type());

 std::shared_ptr<ArrayData> in_array = batch[0].array.ToArrayData();

 // if out type is same as in type, return input
 if (out_type.Equals(*batch[0].type())) {
 /// XXX: This is the wrong place to do a zero-copy optimization
 out->value = batch[0].array.ToArrayData();
 out->value = in_array;
 return Status::OK();
 }

 std::shared_ptr<ArrayData> in_array = batch[0].array.ToArrayData();
 // If the input type is STRING, it is first encoded as a dictionary to facilitate
 // processing. This approach allows the subsequent code to uniformly handle STRING
 // inputs as if they were originally provided in dictionary format. Encoding as a
 // dictionary helps in reusing the same logic for dictionary operations.
 if (batch[0].type()->id() == Type::STRING) {
 in_array = DictionaryEncode(in_array)->array();
 }
 const auto& in_type = checked_cast<const DictionaryType&>(*in_array->type);

 ArrayData* out_array = out->array_data().get();
Expand DownExpand Up@@ -77,17 +85,21 @@ Status CastToDictionary(KernelContext* ctx, const ExecSpan& batch, ExecResult* o
 return Status::OK();
}

std::vector<std::shared_ptr<CastFunction>> GetDictionaryCasts() {
 auto func = std::make_shared<CastFunction>("cast_dictionary", Type::DICTIONARY);

 AddCommonCasts(Type::DICTIONARY, kOutputTargetType, func.get());
 ScalarKernel kernel({InputType(Type::DICTIONARY)}, kOutputTargetType, CastToDictionary);
template <typename SrcType>
void AddDictionaryCast(CastFunction* func) {
 ScalarKernel kernel({InputType(SrcType::type_id)}, kOutputTargetType, CastToDictionary);
 kernel.null_handling = NullHandling::COMPUTED_NO_PREALLOCATE;
 kernel.mem_allocation = MemAllocation::NO_PREALLOCATE;
Comment thread
llama90 marked this conversation as resolved.

 DCHECK_OK(func->AddKernel(SrcType::type_id, std::move(kernel)));
}

 DCHECK_OK(func->AddKernel(Type::DICTIONARY, std::move(kernel)));
std::vector<std::shared_ptr<CastFunction>> GetDictionaryCasts() {
 auto cast_dict = std::make_shared<CastFunction>("cast_dictionary", Type::DICTIONARY);
 AddCommonCasts(Type::DICTIONARY, kOutputTargetType, cast_dict.get());
 AddDictionaryCast<DictionaryType>(cast_dict.get());
 AddDictionaryCast<StringType>(cast_dict.get());
Comment thread
llama90 marked this conversation as resolved.


 return {func};
 return {cast_dict};
}

} // namespace internal
Expand Down

4 changes: 2 additions & 2 deletions
cpp/src/arrow/dataset/partition_test.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -316,7 +316,7 @@ TEST_F(TestPartitioning, DirectoryPartitioningFormatDictionary) {
 ArrayVector{dictionary});
 written_schema_ = partitioning_->schema();

 ASSERT_OK_AND_ASSIGN(auto dict_hello, MakeScalar("hello")->CastTo(DictStr("")->type()));
 ASSERT_OK_AND_ASSIGN(auto dict_hello, Cast(MakeScalar("hello"), DictStr("")->type()));
 AssertFormat(equal(field_ref("alpha"), literal(dict_hello)), "hello");
}

Expand All@@ -329,7 +329,7 @@ TEST_F(TestPartitioning, DirectoryPartitioningFormatDictionaryCustomIndex) {
 schema({field("alpha", dict_type)}), ArrayVector{dictionary});
 written_schema_ = partitioning_->schema();

 ASSERT_OK_AND_ASSIGN(auto dict_hello, MakeScalar("hello")->CastTo(dict_type));
 ASSERT_OK_AND_ASSIGN(auto dict_hello, Cast(MakeScalar("hello"), dict_type));
 AssertFormat(equal(field_ref("alpha"), literal(dict_hello)), "hello");
}

Expand Down

3 changes: 2 additions & 1 deletion
cpp/src/arrow/scalar_test.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -1479,7 +1479,8 @@ TEST(TestDictionaryScalar, Cast) {
 auto alpha =
 dict->IsValid(i) ? MakeScalar(dict->GetString(i)) : MakeNullScalar(utf8());
 // Cast string to dict(..., string)
 ASSERT_OK_AND_ASSIGN(auto cast_alpha, alpha->CastTo(ty));
 ASSERT_OK_AND_ASSIGN(auto cast_alpha_datum, Cast(alpha, ty));
 const auto& cast_alpha = cast_alpha_datum.scalar();
 ASSERT_OK(cast_alpha->ValidateFull());
 ASSERT_OK_AND_ASSIGN(
 auto roundtripped_alpha,
Expand Down

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

Skip to content
GH-39049: [C++] Use Cast() instead of CastTo() for Dictionary Scalar in test#39362

New issue

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

 Sign up for GitHub

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

Already on GitHub?
Sign in
to your account

 Merged

kou
merged 4 commits into

from

Jan 6, 2024
 Merged


GH-39049: [C++] Use Cast() instead of CastTo() for Dictionary Scalar in test
#39362
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


4 commits


Select commit
Hold shift + click to select a range
030c445

Add casting from string to dictionary


llama90 Dec 24, 2023
731e944

Fix adding dictionary cast kernel


llama90 Dec 24, 2023
ea42725

Update the suggestions from the review


llama90 Jan 5, 2024
b4996ef

Update to use ScalarKernel constructor


llama90 Jan 6, 2024

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


30 changes: 21 additions & 9 deletions
cpp/src/arrow/compute/kernels/scalar_cast_dictionary.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -36,14 +36,22 @@ Status CastToDictionary(KernelContext* ctx, const ExecSpan& batch, ExecResult* o
 const CastOptions& options = CastState::Get(ctx);
 const auto& out_type = checked_cast<const DictionaryType&>(*out->type());

 std::shared_ptr<ArrayData> in_array = batch[0].array.ToArrayData();

 // if out type is same as in type, return input
 if (out_type.Equals(*batch[0].type())) {
 /// XXX: This is the wrong place to do a zero-copy optimization
 out->value = batch[0].array.ToArrayData();
 out->value = in_array;
 return Status::OK();
 }

 std::shared_ptr<ArrayData> in_array = batch[0].array.ToArrayData();
 // If the input type is STRING, it is first encoded as a dictionary to facilitate
 // processing. This approach allows the subsequent code to uniformly handle STRING
 // inputs as if they were originally provided in dictionary format. Encoding as a
 // dictionary helps in reusing the same logic for dictionary operations.
 if (batch[0].type()->id() == Type::STRING) {
 in_array = DictionaryEncode(in_array)->array();
 }
 const auto& in_type = checked_cast<const DictionaryType&>(*in_array->type);

 ArrayData* out_array = out->array_data().get();
Expand DownExpand Up@@ -77,17 +85,21 @@ Status CastToDictionary(KernelContext* ctx, const ExecSpan& batch, ExecResult* o
 return Status::OK();
}

std::vector<std::shared_ptr<CastFunction>> GetDictionaryCasts() {
 auto func = std::make_shared<CastFunction>("cast_dictionary", Type::DICTIONARY);

 AddCommonCasts(Type::DICTIONARY, kOutputTargetType, func.get());
 ScalarKernel kernel({InputType(Type::DICTIONARY)}, kOutputTargetType, CastToDictionary);
template <typename SrcType>
void AddDictionaryCast(CastFunction* func) {
 ScalarKernel kernel({InputType(SrcType::type_id)}, kOutputTargetType, CastToDictionary);
 kernel.null_handling = NullHandling::COMPUTED_NO_PREALLOCATE;
 kernel.mem_allocation = MemAllocation::NO_PREALLOCATE;
Comment thread
llama90 marked this conversation as resolved.

 DCHECK_OK(func->AddKernel(SrcType::type_id, std::move(kernel)));
}

 DCHECK_OK(func->AddKernel(Type::DICTIONARY, std::move(kernel)));
std::vector<std::shared_ptr<CastFunction>> GetDictionaryCasts() {
 auto cast_dict = std::make_shared<CastFunction>("cast_dictionary", Type::DICTIONARY);
 AddCommonCasts(Type::DICTIONARY, kOutputTargetType, cast_dict.get());
 AddDictionaryCast<DictionaryType>(cast_dict.get());
 AddDictionaryCast<StringType>(cast_dict.get());
Comment thread
llama90 marked this conversation as resolved.


 return {func};
 return {cast_dict};
}

} // namespace internal
Expand Down

4 changes: 2 additions & 2 deletions
cpp/src/arrow/dataset/partition_test.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -316,7 +316,7 @@ TEST_F(TestPartitioning, DirectoryPartitioningFormatDictionary) {
 ArrayVector{dictionary});
 written_schema_ = partitioning_->schema();

 ASSERT_OK_AND_ASSIGN(auto dict_hello, MakeScalar("hello")->CastTo(DictStr("")->type()));
 ASSERT_OK_AND_ASSIGN(auto dict_hello, Cast(MakeScalar("hello"), DictStr("")->type()));
 AssertFormat(equal(field_ref("alpha"), literal(dict_hello)), "hello");
}

Expand All@@ -329,7 +329,7 @@ TEST_F(TestPartitioning, DirectoryPartitioningFormatDictionaryCustomIndex) {
 schema({field("alpha", dict_type)}), ArrayVector{dictionary});
 written_schema_ = partitioning_->schema();

 ASSERT_OK_AND_ASSIGN(auto dict_hello, MakeScalar("hello")->CastTo(dict_type));
 ASSERT_OK_AND_ASSIGN(auto dict_hello, Cast(MakeScalar("hello"), dict_type));
 AssertFormat(equal(field_ref("alpha"), literal(dict_hello)), "hello");
}

Expand Down

3 changes: 2 additions & 1 deletion
cpp/src/arrow/scalar_test.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -1479,7 +1479,8 @@ TEST(TestDictionaryScalar, Cast) {
 auto alpha =
 dict->IsValid(i) ? MakeScalar(dict->GetString(i)) : MakeNullScalar(utf8());
 // Cast string to dict(..., string)
 ASSERT_OK_AND_ASSIGN(auto cast_alpha, alpha->CastTo(ty));
 ASSERT_OK_AND_ASSIGN(auto cast_alpha_datum, Cast(alpha, ty));
 const auto& cast_alpha = cast_alpha_datum.scalar();
 ASSERT_OK(cast_alpha->ValidateFull());
 ASSERT_OK_AND_ASSIGN(
 auto roundtripped_alpha,
Expand Down

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

Skip to content
GH-39049: [C++] Use Cast() instead of CastTo() for Dictionary Scalar in test#39362

New issue

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

 Sign up for GitHub

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

Already on GitHub?
Sign in
to your account

 Merged

kou
merged 4 commits into

from

Jan 6, 2024
 Merged


GH-39049: [C++] Use Cast() instead of CastTo() for Dictionary Scalar in test
#39362
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


4 commits


Select commit
Hold shift + click to select a range
030c445

Add casting from string to dictionary


llama90 Dec 24, 2023
731e944

Fix adding dictionary cast kernel


llama90 Dec 24, 2023
ea42725

Update the suggestions from the review


llama90 Jan 5, 2024
b4996ef

Update to use ScalarKernel constructor


llama90 Jan 6, 2024

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


30 changes: 21 additions & 9 deletions
cpp/src/arrow/compute/kernels/scalar_cast_dictionary.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -36,14 +36,22 @@ Status CastToDictionary(KernelContext* ctx, const ExecSpan& batch, ExecResult* o
 const CastOptions& options = CastState::Get(ctx);
 const auto& out_type = checked_cast<const DictionaryType&>(*out->type());

 std::shared_ptr<ArrayData> in_array = batch[0].array.ToArrayData();

 // if out type is same as in type, return input
 if (out_type.Equals(*batch[0].type())) {
 /// XXX: This is the wrong place to do a zero-copy optimization
 out->value = batch[0].array.ToArrayData();
 out->value = in_array;
 return Status::OK();
 }

 std::shared_ptr<ArrayData> in_array = batch[0].array.ToArrayData();
 // If the input type is STRING, it is first encoded as a dictionary to facilitate
 // processing. This approach allows the subsequent code to uniformly handle STRING
 // inputs as if they were originally provided in dictionary format. Encoding as a
 // dictionary helps in reusing the same logic for dictionary operations.
 if (batch[0].type()->id() == Type::STRING) {
 in_array = DictionaryEncode(in_array)->array();
 }
 const auto& in_type = checked_cast<const DictionaryType&>(*in_array->type);

 ArrayData* out_array = out->array_data().get();
Expand DownExpand Up@@ -77,17 +85,21 @@ Status CastToDictionary(KernelContext* ctx, const ExecSpan& batch, ExecResult* o
 return Status::OK();
}

std::vector<std::shared_ptr<CastFunction>> GetDictionaryCasts() {
 auto func = std::make_shared<CastFunction>("cast_dictionary", Type::DICTIONARY);

 AddCommonCasts(Type::DICTIONARY, kOutputTargetType, func.get());
 ScalarKernel kernel({InputType(Type::DICTIONARY)}, kOutputTargetType, CastToDictionary);
template <typename SrcType>
void AddDictionaryCast(CastFunction* func) {
 ScalarKernel kernel({InputType(SrcType::type_id)}, kOutputTargetType, CastToDictionary);
 kernel.null_handling = NullHandling::COMPUTED_NO_PREALLOCATE;
 kernel.mem_allocation = MemAllocation::NO_PREALLOCATE;
Comment thread
llama90 marked this conversation as resolved.

 DCHECK_OK(func->AddKernel(SrcType::type_id, std::move(kernel)));
}

 DCHECK_OK(func->AddKernel(Type::DICTIONARY, std::move(kernel)));
std::vector<std::shared_ptr<CastFunction>> GetDictionaryCasts() {
 auto cast_dict = std::make_shared<CastFunction>("cast_dictionary", Type::DICTIONARY);
 AddCommonCasts(Type::DICTIONARY, kOutputTargetType, cast_dict.get());
 AddDictionaryCast<DictionaryType>(cast_dict.get());
 AddDictionaryCast<StringType>(cast_dict.get());
Comment thread
llama90 marked this conversation as resolved.


 return {func};
 return {cast_dict};
}

} // namespace internal
Expand Down

4 changes: 2 additions & 2 deletions
cpp/src/arrow/dataset/partition_test.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -316,7 +316,7 @@ TEST_F(TestPartitioning, DirectoryPartitioningFormatDictionary) {
 ArrayVector{dictionary});
 written_schema_ = partitioning_->schema();

 ASSERT_OK_AND_ASSIGN(auto dict_hello, MakeScalar("hello")->CastTo(DictStr("")->type()));
 ASSERT_OK_AND_ASSIGN(auto dict_hello, Cast(MakeScalar("hello"), DictStr("")->type()));
 AssertFormat(equal(field_ref("alpha"), literal(dict_hello)), "hello");
}

Expand All@@ -329,7 +329,7 @@ TEST_F(TestPartitioning, DirectoryPartitioningFormatDictionaryCustomIndex) {
 schema({field("alpha", dict_type)}), ArrayVector{dictionary});
 written_schema_ = partitioning_->schema();

 ASSERT_OK_AND_ASSIGN(auto dict_hello, MakeScalar("hello")->CastTo(dict_type));
 ASSERT_OK_AND_ASSIGN(auto dict_hello, Cast(MakeScalar("hello"), dict_type));
 AssertFormat(equal(field_ref("alpha"), literal(dict_hello)), "hello");
}

Expand Down

3 changes: 2 additions & 1 deletion
cpp/src/arrow/scalar_test.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -1479,7 +1479,8 @@ TEST(TestDictionaryScalar, Cast) {
 auto alpha =
 dict->IsValid(i) ? MakeScalar(dict->GetString(i)) : MakeNullScalar(utf8());
 // Cast string to dict(..., string)
 ASSERT_OK_AND_ASSIGN(auto cast_alpha, alpha->CastTo(ty));
 ASSERT_OK_AND_ASSIGN(auto cast_alpha_datum, Cast(alpha, ty));
 const auto& cast_alpha = cast_alpha_datum.scalar();
 ASSERT_OK(cast_alpha->ValidateFull());
 ASSERT_OK_AND_ASSIGN(
 auto roundtripped_alpha,
Expand Down

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

Skip to content
GH-39049: [C++] Use Cast() instead of CastTo() for Dictionary Scalar in test#39362

New issue

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

 Sign up for GitHub

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

Already on GitHub?
Sign in
to your account

 Merged

kou
merged 4 commits into

from

Jan 6, 2024
 Merged


GH-39049: [C++] Use Cast() instead of CastTo() for Dictionary Scalar in test
#39362
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


4 commits


Select commit
Hold shift + click to select a range
030c445

Add casting from string to dictionary


llama90 Dec 24, 2023
731e944

Fix adding dictionary cast kernel


llama90 Dec 24, 2023
ea42725

Update the suggestions from the review


llama90 Jan 5, 2024
b4996ef

Update to use ScalarKernel constructor


llama90 Jan 6, 2024

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


30 changes: 21 additions & 9 deletions
cpp/src/arrow/compute/kernels/scalar_cast_dictionary.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -36,14 +36,22 @@ Status CastToDictionary(KernelContext* ctx, const ExecSpan& batch, ExecResult* o
 const CastOptions& options = CastState::Get(ctx);
 const auto& out_type = checked_cast<const DictionaryType&>(*out->type());

 std::shared_ptr<ArrayData> in_array = batch[0].array.ToArrayData();

 // if out type is same as in type, return input
 if (out_type.Equals(*batch[0].type())) {
 /// XXX: This is the wrong place to do a zero-copy optimization
 out->value = batch[0].array.ToArrayData();
 out->value = in_array;
 return Status::OK();
 }

 std::shared_ptr<ArrayData> in_array = batch[0].array.ToArrayData();
 // If the input type is STRING, it is first encoded as a dictionary to facilitate
 // processing. This approach allows the subsequent code to uniformly handle STRING
 // inputs as if they were originally provided in dictionary format. Encoding as a
 // dictionary helps in reusing the same logic for dictionary operations.
 if (batch[0].type()->id() == Type::STRING) {
 in_array = DictionaryEncode(in_array)->array();
 }
 const auto& in_type = checked_cast<const DictionaryType&>(*in_array->type);

 ArrayData* out_array = out->array_data().get();
Expand DownExpand Up@@ -77,17 +85,21 @@ Status CastToDictionary(KernelContext* ctx, const ExecSpan& batch, ExecResult* o
 return Status::OK();
}

std::vector<std::shared_ptr<CastFunction>> GetDictionaryCasts() {
 auto func = std::make_shared<CastFunction>("cast_dictionary", Type::DICTIONARY);

 AddCommonCasts(Type::DICTIONARY, kOutputTargetType, func.get());
 ScalarKernel kernel({InputType(Type::DICTIONARY)}, kOutputTargetType, CastToDictionary);
template <typename SrcType>
void AddDictionaryCast(CastFunction* func) {
 ScalarKernel kernel({InputType(SrcType::type_id)}, kOutputTargetType, CastToDictionary);
 kernel.null_handling = NullHandling::COMPUTED_NO_PREALLOCATE;
 kernel.mem_allocation = MemAllocation::NO_PREALLOCATE;
Comment thread
llama90 marked this conversation as resolved.

 DCHECK_OK(func->AddKernel(SrcType::type_id, std::move(kernel)));
}

 DCHECK_OK(func->AddKernel(Type::DICTIONARY, std::move(kernel)));
std::vector<std::shared_ptr<CastFunction>> GetDictionaryCasts() {
 auto cast_dict = std::make_shared<CastFunction>("cast_dictionary", Type::DICTIONARY);
 AddCommonCasts(Type::DICTIONARY, kOutputTargetType, cast_dict.get());
 AddDictionaryCast<DictionaryType>(cast_dict.get());
 AddDictionaryCast<StringType>(cast_dict.get());
Comment thread
llama90 marked this conversation as resolved.


 return {func};
 return {cast_dict};
}

} // namespace internal
Expand Down

4 changes: 2 additions & 2 deletions
cpp/src/arrow/dataset/partition_test.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -316,7 +316,7 @@ TEST_F(TestPartitioning, DirectoryPartitioningFormatDictionary) {
 ArrayVector{dictionary});
 written_schema_ = partitioning_->schema();

 ASSERT_OK_AND_ASSIGN(auto dict_hello, MakeScalar("hello")->CastTo(DictStr("")->type()));
 ASSERT_OK_AND_ASSIGN(auto dict_hello, Cast(MakeScalar("hello"), DictStr("")->type()));
 AssertFormat(equal(field_ref("alpha"), literal(dict_hello)), "hello");
}

Expand All@@ -329,7 +329,7 @@ TEST_F(TestPartitioning, DirectoryPartitioningFormatDictionaryCustomIndex) {
 schema({field("alpha", dict_type)}), ArrayVector{dictionary});
 written_schema_ = partitioning_->schema();

 ASSERT_OK_AND_ASSIGN(auto dict_hello, MakeScalar("hello")->CastTo(dict_type));
 ASSERT_OK_AND_ASSIGN(auto dict_hello, Cast(MakeScalar("hello"), dict_type));
 AssertFormat(equal(field_ref("alpha"), literal(dict_hello)), "hello");
}

Expand Down

3 changes: 2 additions & 1 deletion
cpp/src/arrow/scalar_test.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -1479,7 +1479,8 @@ TEST(TestDictionaryScalar, Cast) {
 auto alpha =
 dict->IsValid(i) ? MakeScalar(dict->GetString(i)) : MakeNullScalar(utf8());
 // Cast string to dict(..., string)
 ASSERT_OK_AND_ASSIGN(auto cast_alpha, alpha->CastTo(ty));
 ASSERT_OK_AND_ASSIGN(auto cast_alpha_datum, Cast(alpha, ty));
 const auto& cast_alpha = cast_alpha_datum.scalar();
 ASSERT_OK(cast_alpha->ValidateFull());
 ASSERT_OK_AND_ASSIGN(
 auto roundtripped_alpha,
Expand Down

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

Skip to content
GH-39049: [C++] Use Cast() instead of CastTo() for Dictionary Scalar in test#39362

New issue

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

 Sign up for GitHub

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

Already on GitHub?
Sign in
to your account

 Merged

kou
merged 4 commits into

from

Jan 6, 2024
 Merged


GH-39049: [C++] Use Cast() instead of CastTo() for Dictionary Scalar in test
#39362
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


4 commits


Select commit
Hold shift + click to select a range
030c445

Add casting from string to dictionary


llama90 Dec 24, 2023
731e944

Fix adding dictionary cast kernel


llama90 Dec 24, 2023
ea42725

Update the suggestions from the review


llama90 Jan 5, 2024
b4996ef

Update to use ScalarKernel constructor


llama90 Jan 6, 2024

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


30 changes: 21 additions & 9 deletions
cpp/src/arrow/compute/kernels/scalar_cast_dictionary.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -36,14 +36,22 @@ Status CastToDictionary(KernelContext* ctx, const ExecSpan& batch, ExecResult* o
 const CastOptions& options = CastState::Get(ctx);
 const auto& out_type = checked_cast<const DictionaryType&>(*out->type());

 std::shared_ptr<ArrayData> in_array = batch[0].array.ToArrayData();

 // if out type is same as in type, return input
 if (out_type.Equals(*batch[0].type())) {
 /// XXX: This is the wrong place to do a zero-copy optimization
 out->value = batch[0].array.ToArrayData();
 out->value = in_array;
 return Status::OK();
 }

 std::shared_ptr<ArrayData> in_array = batch[0].array.ToArrayData();
 // If the input type is STRING, it is first encoded as a dictionary to facilitate
 // processing. This approach allows the subsequent code to uniformly handle STRING
 // inputs as if they were originally provided in dictionary format. Encoding as a
 // dictionary helps in reusing the same logic for dictionary operations.
 if (batch[0].type()->id() == Type::STRING) {
 in_array = DictionaryEncode(in_array)->array();
 }
 const auto& in_type = checked_cast<const DictionaryType&>(*in_array->type);

 ArrayData* out_array = out->array_data().get();
Expand DownExpand Up@@ -77,17 +85,21 @@ Status CastToDictionary(KernelContext* ctx, const ExecSpan& batch, ExecResult* o
 return Status::OK();
}

std::vector<std::shared_ptr<CastFunction>> GetDictionaryCasts() {
 auto func = std::make_shared<CastFunction>("cast_dictionary", Type::DICTIONARY);

 AddCommonCasts(Type::DICTIONARY, kOutputTargetType, func.get());
 ScalarKernel kernel({InputType(Type::DICTIONARY)}, kOutputTargetType, CastToDictionary);
template <typename SrcType>
void AddDictionaryCast(CastFunction* func) {
 ScalarKernel kernel({InputType(SrcType::type_id)}, kOutputTargetType, CastToDictionary);
 kernel.null_handling = NullHandling::COMPUTED_NO_PREALLOCATE;
 kernel.mem_allocation = MemAllocation::NO_PREALLOCATE;
Comment thread
llama90 marked this conversation as resolved.

 DCHECK_OK(func->AddKernel(SrcType::type_id, std::move(kernel)));
}

 DCHECK_OK(func->AddKernel(Type::DICTIONARY, std::move(kernel)));
std::vector<std::shared_ptr<CastFunction>> GetDictionaryCasts() {
 auto cast_dict = std::make_shared<CastFunction>("cast_dictionary", Type::DICTIONARY);
 AddCommonCasts(Type::DICTIONARY, kOutputTargetType, cast_dict.get());
 AddDictionaryCast<DictionaryType>(cast_dict.get());
 AddDictionaryCast<StringType>(cast_dict.get());
Comment thread
llama90 marked this conversation as resolved.


 return {func};
 return {cast_dict};
}

} // namespace internal
Expand Down

4 changes: 2 additions & 2 deletions
cpp/src/arrow/dataset/partition_test.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -316,7 +316,7 @@ TEST_F(TestPartitioning, DirectoryPartitioningFormatDictionary) {
 ArrayVector{dictionary});
 written_schema_ = partitioning_->schema();

 ASSERT_OK_AND_ASSIGN(auto dict_hello, MakeScalar("hello")->CastTo(DictStr("")->type()));
 ASSERT_OK_AND_ASSIGN(auto dict_hello, Cast(MakeScalar("hello"), DictStr("")->type()));
 AssertFormat(equal(field_ref("alpha"), literal(dict_hello)), "hello");
}

Expand All@@ -329,7 +329,7 @@ TEST_F(TestPartitioning, DirectoryPartitioningFormatDictionaryCustomIndex) {
 schema({field("alpha", dict_type)}), ArrayVector{dictionary});
 written_schema_ = partitioning_->schema();

 ASSERT_OK_AND_ASSIGN(auto dict_hello, MakeScalar("hello")->CastTo(dict_type));
 ASSERT_OK_AND_ASSIGN(auto dict_hello, Cast(MakeScalar("hello"), dict_type));
 AssertFormat(equal(field_ref("alpha"), literal(dict_hello)), "hello");
}

Expand Down

3 changes: 2 additions & 1 deletion
cpp/src/arrow/scalar_test.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -1479,7 +1479,8 @@ TEST(TestDictionaryScalar, Cast) {
 auto alpha =
 dict->IsValid(i) ? MakeScalar(dict->GetString(i)) : MakeNullScalar(utf8());
 // Cast string to dict(..., string)
 ASSERT_OK_AND_ASSIGN(auto cast_alpha, alpha->CastTo(ty));
 ASSERT_OK_AND_ASSIGN(auto cast_alpha_datum, Cast(alpha, ty));
 const auto& cast_alpha = cast_alpha_datum.scalar();
 ASSERT_OK(cast_alpha->ValidateFull());
 ASSERT_OK_AND_ASSIGN(
 auto roundtripped_alpha,
Expand Down

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

Skip to content
GH-39049: [C++] Use Cast() instead of CastTo() for Dictionary Scalar in test#39362

New issue

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

 Sign up for GitHub

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

Already on GitHub?
Sign in
to your account

 Merged

kou
merged 4 commits into

from

Jan 6, 2024
 Merged


GH-39049: [C++] Use Cast() instead of CastTo() for Dictionary Scalar in test
#39362
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


4 commits


Select commit
Hold shift + click to select a range
030c445

Add casting from string to dictionary


llama90 Dec 24, 2023
731e944

Fix adding dictionary cast kernel


llama90 Dec 24, 2023
ea42725

Update the suggestions from the review


llama90 Jan 5, 2024
b4996ef

Update to use ScalarKernel constructor


llama90 Jan 6, 2024

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


30 changes: 21 additions & 9 deletions
cpp/src/arrow/compute/kernels/scalar_cast_dictionary.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -36,14 +36,22 @@ Status CastToDictionary(KernelContext* ctx, const ExecSpan& batch, ExecResult* o
 const CastOptions& options = CastState::Get(ctx);
 const auto& out_type = checked_cast<const DictionaryType&>(*out->type());

 std::shared_ptr<ArrayData> in_array = batch[0].array.ToArrayData();

 // if out type is same as in type, return input
 if (out_type.Equals(*batch[0].type())) {
 /// XXX: This is the wrong place to do a zero-copy optimization
 out->value = batch[0].array.ToArrayData();
 out->value = in_array;
 return Status::OK();
 }

 std::shared_ptr<ArrayData> in_array = batch[0].array.ToArrayData();
 // If the input type is STRING, it is first encoded as a dictionary to facilitate
 // processing. This approach allows the subsequent code to uniformly handle STRING
 // inputs as if they were originally provided in dictionary format. Encoding as a
 // dictionary helps in reusing the same logic for dictionary operations.
 if (batch[0].type()->id() == Type::STRING) {
 in_array = DictionaryEncode(in_array)->array();
 }
 const auto& in_type = checked_cast<const DictionaryType&>(*in_array->type);

 ArrayData* out_array = out->array_data().get();
Expand DownExpand Up@@ -77,17 +85,21 @@ Status CastToDictionary(KernelContext* ctx, const ExecSpan& batch, ExecResult* o
 return Status::OK();
}

std::vector<std::shared_ptr<CastFunction>> GetDictionaryCasts() {
 auto func = std::make_shared<CastFunction>("cast_dictionary", Type::DICTIONARY);

 AddCommonCasts(Type::DICTIONARY, kOutputTargetType, func.get());
 ScalarKernel kernel({InputType(Type::DICTIONARY)}, kOutputTargetType, CastToDictionary);
template <typename SrcType>
void AddDictionaryCast(CastFunction* func) {
 ScalarKernel kernel({InputType(SrcType::type_id)}, kOutputTargetType, CastToDictionary);
 kernel.null_handling = NullHandling::COMPUTED_NO_PREALLOCATE;
 kernel.mem_allocation = MemAllocation::NO_PREALLOCATE;
Comment thread
llama90 marked this conversation as resolved.

 DCHECK_OK(func->AddKernel(SrcType::type_id, std::move(kernel)));
}

 DCHECK_OK(func->AddKernel(Type::DICTIONARY, std::move(kernel)));
std::vector<std::shared_ptr<CastFunction>> GetDictionaryCasts() {
 auto cast_dict = std::make_shared<CastFunction>("cast_dictionary", Type::DICTIONARY);
 AddCommonCasts(Type::DICTIONARY, kOutputTargetType, cast_dict.get());
 AddDictionaryCast<DictionaryType>(cast_dict.get());
 AddDictionaryCast<StringType>(cast_dict.get());
Comment thread
llama90 marked this conversation as resolved.


 return {func};
 return {cast_dict};
}

} // namespace internal
Expand Down

4 changes: 2 additions & 2 deletions
cpp/src/arrow/dataset/partition_test.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -316,7 +316,7 @@ TEST_F(TestPartitioning, DirectoryPartitioningFormatDictionary) {
 ArrayVector{dictionary});
 written_schema_ = partitioning_->schema();

 ASSERT_OK_AND_ASSIGN(auto dict_hello, MakeScalar("hello")->CastTo(DictStr("")->type()));
 ASSERT_OK_AND_ASSIGN(auto dict_hello, Cast(MakeScalar("hello"), DictStr("")->type()));
 AssertFormat(equal(field_ref("alpha"), literal(dict_hello)), "hello");
}

Expand All@@ -329,7 +329,7 @@ TEST_F(TestPartitioning, DirectoryPartitioningFormatDictionaryCustomIndex) {
 schema({field("alpha", dict_type)}), ArrayVector{dictionary});
 written_schema_ = partitioning_->schema();

 ASSERT_OK_AND_ASSIGN(auto dict_hello, MakeScalar("hello")->CastTo(dict_type));
 ASSERT_OK_AND_ASSIGN(auto dict_hello, Cast(MakeScalar("hello"), dict_type));
 AssertFormat(equal(field_ref("alpha"), literal(dict_hello)), "hello");
}

Expand Down

3 changes: 2 additions & 1 deletion
cpp/src/arrow/scalar_test.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -1479,7 +1479,8 @@ TEST(TestDictionaryScalar, Cast) {
 auto alpha =
 dict->IsValid(i) ? MakeScalar(dict->GetString(i)) : MakeNullScalar(utf8());
 // Cast string to dict(..., string)
 ASSERT_OK_AND_ASSIGN(auto cast_alpha, alpha->CastTo(ty));
 ASSERT_OK_AND_ASSIGN(auto cast_alpha_datum, Cast(alpha, ty));
 const auto& cast_alpha = cast_alpha_datum.scalar();
 ASSERT_OK(cast_alpha->ValidateFull());
 ASSERT_OK_AND_ASSIGN(
 auto roundtripped_alpha,
Expand Down