ARROW-5880: [C++][Parquet] Use TypedBufferBuilder instead of ArrayBuilder in writer.cc#4827

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
emkornfield wants to merge 11 commits into from
Closed

ARROW-5880: [C++][Parquet] Use TypedBufferBuilder instead of ArrayBuilder in writer.cc #4827

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
7795352
change from array builder to buffer builde
emkornfield Jul 7, 2019
4516110
Small style issues
emkornfield Jul 8, 2019
325af52
undo reserve
emkornfield Jul 8, 2019
83ee5ae
Update cpp/src/parquet/arrow/writer.cc
emkornfield Jul 10, 2019
7cbc8e4
Update cpp/src/parquet/arrow/writer.cc
emkornfield Jul 10, 2019
6776e61
Update cpp/src/parquet/arrow/writer.cc
emkornfield Jul 10, 2019
ef7fade
remove unneeded nesting
emkornfield Jul 10, 2019
67ccf3e
update references
emkornfield Jul 10, 2019
152a6ee
change back to signed it seems to be what the API uses
emkornfield Jul 10, 2019
e1698e5
fix compilation issues
emkornfield Jul 10, 2019
2f77313
Export operator<< symbols for DataType, TimeUnit on Windows
wesm Jul 10, 2019
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
6 changes: 2 additions & 4 deletions cpp/src/arrow/buffer-builder.h
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -220,10 +220,8 @@ class TypedBufferBuilder<T, typename std::enable_if<std::is_arithmetic<T>::value

void UnsafeAppend(const int64_t num_copies, T value) {
auto data = mutable_data() + length();
bytes_builder_.UnsafeAppend(num_copies * sizeof(T), 0);
for (const auto end = data + num_copies; data != end; ++data) {
*data = value;
}
bytes_builder_.UnsafeAdvance(num_copies * sizeof(T));
std::fill(data, data + num_copies, value);
}

Status Resize(const int64_t new_capacity, bool shrink_to_fit = true) {
Expand Down
2 changes: 2 additions & 0 deletions cpp/src/arrow/type.h
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -215,6 +215,7 @@ class ARROW_EXPORT DataType {
ARROW_DISALLOW_COPY_AND_ASSIGN(DataType);
};

ARROW_EXPORT
std::ostream& operator<<(std::ostream& os, const DataType& type);

/// \brief Base class for all fixed-width data types
Expand DownExpand Up@@ -762,6 +763,7 @@ struct TimeUnit {
enum type { SECOND = 0, MILLI = 1, MICRO = 2, NANO = 3 };
};

ARROW_EXPORT
std::ostream& operator<<(std::ostream& os, TimeUnit::type unit);

/// Base type class for time data
Expand Down
87 changes: 43 additions & 44 deletions cpp/src/parquet/arrow/writer.cc
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -49,8 +49,7 @@ using arrow::ChunkedArray;
using arrow::Decimal128Array;
using arrow::Field;
using arrow::FixedSizeBinaryArray;
using arrow::Int16Array;
using arrow::Int16Builder;
using Int16BufferBuilder = arrow::TypedBufferBuilder<int16_t>;
using arrow::ListArray;
using arrow::MemoryPool;
using arrow::NumericArray;
Expand DownExpand Up@@ -81,8 +80,7 @@ namespace {

class LevelBuilder {
public:
explicit LevelBuilder(MemoryPool* pool)
: def_levels_(::arrow::int16(), pool), rep_levels_(::arrow::int16(), pool) {}
explicit LevelBuilder(MemoryPool* pool) : def_levels_(pool), rep_levels_(pool) {}

Status VisitInline(const Array& array);

Expand All@@ -102,6 +100,7 @@ class LevelBuilder {
null_counts_.push_back(array.null_count());
offsets_.push_back(array.raw_value_offsets());

// Min offset isn't always zero in the case of sliced Arrays.
min_offset_idx_ = array.value_offset(min_offset_idx_);
max_offset_idx_ = array.value_offset(max_offset_idx_);

Expand DownExpand Up@@ -176,18 +175,17 @@ class LevelBuilder {
}
*num_levels = array.length();
} else {
// Note it is hard to estimate memory consumption due to zero length
// arrays otherwise we would preallocate. An upper boun on memory

@bkietzbkietzJul 9, 2019

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

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

Suggested change
// arrays otherwise we would preallocate. An upper boun on memory
// arrays otherwise we would preallocate. An upper bound on memory

// is the sum of the length of each list array + number of elements
// but this might be too loose of an upper bound so we choose to use
// safe methods.
RETURN_NOT_OK(rep_levels_.Append(0));
RETURN_NOT_OK(HandleListEntries(0, 0, 0, array.length()));

std::shared_ptr<Array> def_levels_array;
std::shared_ptr<Array> rep_levels_array;

RETURN_NOT_OK(def_levels_.Finish(&def_levels_array));
RETURN_NOT_OK(rep_levels_.Finish(&rep_levels_array));

*def_levels_out = static_cast<PrimitiveArray*>(def_levels_array.get())->values();
*rep_levels_out = static_cast<PrimitiveArray*>(rep_levels_array.get())->values();
*num_levels = rep_levels_array->length();
RETURN_NOT_OK(def_levels_.Finish(def_levels_out));
Comment thread
emkornfield marked this conversation as resolved.
Outdated
RETURN_NOT_OK(rep_levels_.Finish(rep_levels_out));
*num_levels = (*rep_levels_out)->size() / sizeof(int16_t);
}

return Status::OK();
Expand DownExpand Up@@ -217,36 +215,37 @@ class LevelBuilder {
return HandleListEntries(static_cast<int16_t>(def_level + 1),
static_cast<int16_t>(rep_level + 1), inner_offset,
inner_length);
} else {
// We have reached the leaf: primitive list, handle remaining nullables
const bool nullable_level = nullable_[recursion_level];
const int64_t level_null_count = null_counts_[recursion_level];
const uint8_t* level_valid_bitmap = valid_bitmaps_[recursion_level];

for (int64_t i = 0; i < inner_length; i++) {
if (i > 0) {
RETURN_NOT_OK(rep_levels_.Append(static_cast<int16_t>(rep_level + 1)));
}
if (level_null_count && level_valid_bitmap == nullptr) {
// Special case: this is a null array (all elements are null)
RETURN_NOT_OK(def_levels_.Append(static_cast<int16_t>(def_level + 1)));
} else if (nullable_level &&
((level_null_count == 0) ||
BitUtil::GetBit(
level_valid_bitmap,
inner_offset + i + array_offsets_[recursion_level]))) {
// Non-null element in a null level
RETURN_NOT_OK(def_levels_.Append(static_cast<int16_t>(def_level + 2)));
} else {
// This can be produced in two case:
// * elements are nullable and this one is null (i.e. max_def_level = def_level
// + 2)
// * elements are non-nullable (i.e. max_def_level = def_level + 1)
RETURN_NOT_OK(def_levels_.Append(static_cast<int16_t>(def_level + 1)));
}
}
// We have reached the leaf: primitive list, handle remaining nullables
const bool nullable_level = nullable_[recursion_level];
const int64_t level_null_count = null_counts_[recursion_level];
const uint8_t* level_valid_bitmap = valid_bitmaps_[recursion_level];

if (inner_length >= 1) {
RETURN_NOT_OK(
rep_levels_.Append(inner_length - 1, static_cast<int16_t>(rep_level + 1)));
}

// Special case: this is a null array (all elements are null)
if (level_null_count && level_valid_bitmap == nullptr) {
return def_levels_.Append(inner_length, static_cast<int16_t>(def_level + 1));
}
for (int64_t i = 0; i < inner_length; i++) {
if (nullable_level &&
((level_null_count == 0) ||
BitUtil::GetBit(level_valid_bitmap,
inner_offset + i + array_offsets_[recursion_level]))) {
// Non-null element in a null level
RETURN_NOT_OK(def_levels_.Append(static_cast<int16_t>(def_level + 2)));
} else {
// This can be produced in two cases:
// * elements are nullable and this one is null
// (i.e. max_def_level = def_level + 2)
// * elements are non-nullable (i.e. max_def_level = def_level + 1)
RETURN_NOT_OK(def_levels_.Append(static_cast<int16_t>(def_level + 1)));
}
return Status::OK();
}
return Status::OK();
}

Status HandleListEntries(int16_t def_level, int16_t rep_level, int64_t offset,
Expand All@@ -261,8 +260,8 @@ class LevelBuilder {
}

private:
Int16Builder def_levels_;
Int16Builder rep_levels_;
Int16BufferBuilder def_levels_;
Int16BufferBuilder rep_levels_;

std::vector<int64_t> null_counts_;
std::vector<const uint8_t*> valid_bitmaps_;
Expand DownExpand Up@@ -307,7 +306,7 @@ struct ColumnWriterContext {
Status GetLeafType(const ::arrow::DataType& type, ::arrow::Type::type* leaf_type) {
if (type.id() == ::arrow::Type::LIST || type.id() == ::arrow::Type::STRUCT) {
if (type.num_children() != 1) {
return Status::Invalid("Nested column branch had multiple children");
return Status::Invalid("Nested column branch had multiple children: ", type);
}
return GetLeafType(*type.child(0)->type(), leaf_type);
} else {
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
ARROW-5880: [C++][Parquet] Use TypedBufferBuilder instead of ArrayBuilder in writer.cc#4827

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

emkornfield
wants to merge
11
commits into

from

 Closed


ARROW-5880: [C++][Parquet] Use TypedBufferBuilder instead of ArrayBuilder in writer.cc
#4827
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


11 commits


Select commit
Hold shift + click to select a range
7795352

change from array builder to buffer builde


emkornfield Jul 7, 2019
4516110

Small style issues


emkornfield Jul 8, 2019
325af52

undo reserve


emkornfield Jul 8, 2019
83ee5ae

Update cpp/src/parquet/arrow/writer.cc


emkornfield Jul 10, 2019
7cbc8e4

Update cpp/src/parquet/arrow/writer.cc


emkornfield Jul 10, 2019
6776e61

Update cpp/src/parquet/arrow/writer.cc


emkornfield Jul 10, 2019
ef7fade

remove unneeded nesting


emkornfield Jul 10, 2019
67ccf3e

update references


emkornfield Jul 10, 2019
152a6ee

change back to signed it seems to be what the API uses


emkornfield Jul 10, 2019
e1698e5

fix compilation issues


emkornfield Jul 10, 2019
2f77313

Export operator<< symbols for DataType, TimeUnit on Windows


wesm Jul 10, 2019

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


6 changes: 2 additions & 4 deletions
cpp/src/arrow/buffer-builder.h

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -220,10 +220,8 @@ class TypedBufferBuilder<T, typename std::enable_if<std::is_arithmetic<T>::value

 void UnsafeAppend(const int64_t num_copies, T value) {
 auto data = mutable_data() + length();
 bytes_builder_.UnsafeAppend(num_copies * sizeof(T), 0);
 for (const auto end = data + num_copies; data != end; ++data) {
 *data = value;
 }
 bytes_builder_.UnsafeAdvance(num_copies * sizeof(T));
 std::fill(data, data + num_copies, value);
 }

 Status Resize(const int64_t new_capacity, bool shrink_to_fit = true) {
Expand Down

2 changes: 2 additions & 0 deletions
cpp/src/arrow/type.h

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -215,6 +215,7 @@ class ARROW_EXPORT DataType {
 ARROW_DISALLOW_COPY_AND_ASSIGN(DataType);
};

ARROW_EXPORT
std::ostream& operator<<(std::ostream& os, const DataType& type);

/// \brief Base class for all fixed-width data types
Expand DownExpand Up@@ -762,6 +763,7 @@ struct TimeUnit {
 enum type { SECOND = 0, MILLI = 1, MICRO = 2, NANO = 3 };
};

ARROW_EXPORT
std::ostream& operator<<(std::ostream& os, TimeUnit::type unit);

/// Base type class for time data
Expand Down

87 changes: 43 additions & 44 deletions
cpp/src/parquet/arrow/writer.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -49,8 +49,7 @@ using arrow::ChunkedArray;
using arrow::Decimal128Array;
using arrow::Field;
using arrow::FixedSizeBinaryArray;
using arrow::Int16Array;
using arrow::Int16Builder;
using Int16BufferBuilder = arrow::TypedBufferBuilder<int16_t>;
using arrow::ListArray;
using arrow::MemoryPool;
using arrow::NumericArray;
Expand DownExpand Up@@ -81,8 +80,7 @@ namespace {

class LevelBuilder {
 public:
 explicit LevelBuilder(MemoryPool* pool)
 : def_levels_(::arrow::int16(), pool), rep_levels_(::arrow::int16(), pool) {}
 explicit LevelBuilder(MemoryPool* pool) : def_levels_(pool), rep_levels_(pool) {}

 Status VisitInline(const Array& array);

Expand All@@ -102,6 +100,7 @@ class LevelBuilder {
 null_counts_.push_back(array.null_count());
 offsets_.push_back(array.raw_value_offsets());

 // Min offset isn't always zero in the case of sliced Arrays.
 min_offset_idx_ = array.value_offset(min_offset_idx_);
 max_offset_idx_ = array.value_offset(max_offset_idx_);

Expand DownExpand Up@@ -176,18 +175,17 @@ class LevelBuilder {
 }
 *num_levels = array.length();
 } else {
 // Note it is hard to estimate memory consumption due to zero length
 // arrays otherwise we would preallocate. An upper boun on memory
@bkietzbkietzJul 9, 2019

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

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


Suggested change

// arrays otherwise we would preallocate. An upper boun on memory
// arrays otherwise we would preallocate. An upper bound on memory
 // is the sum of the length of each list array + number of elements
 // but this might be too loose of an upper bound so we choose to use
 // safe methods.
 RETURN_NOT_OK(rep_levels_.Append(0));
 RETURN_NOT_OK(HandleListEntries(0, 0, 0, array.length()));

 std::shared_ptr<Array> def_levels_array;
 std::shared_ptr<Array> rep_levels_array;

 RETURN_NOT_OK(def_levels_.Finish(&def_levels_array));
 RETURN_NOT_OK(rep_levels_.Finish(&rep_levels_array));

 *def_levels_out = static_cast<PrimitiveArray*>(def_levels_array.get())->values();
 *rep_levels_out = static_cast<PrimitiveArray*>(rep_levels_array.get())->values();
 *num_levels = rep_levels_array->length();
 RETURN_NOT_OK(def_levels_.Finish(def_levels_out));
Comment thread
emkornfield marked this conversation as resolved.


Outdated

 RETURN_NOT_OK(rep_levels_.Finish(rep_levels_out));
 *num_levels = (*rep_levels_out)->size() / sizeof(int16_t);
 }

 return Status::OK();
Expand DownExpand Up@@ -217,36 +215,37 @@ class LevelBuilder {
 return HandleListEntries(static_cast<int16_t>(def_level + 1),
 static_cast<int16_t>(rep_level + 1), inner_offset,
 inner_length);
 } else {
 // We have reached the leaf: primitive list, handle remaining nullables
 const bool nullable_level = nullable_[recursion_level];
 const int64_t level_null_count = null_counts_[recursion_level];
 const uint8_t* level_valid_bitmap = valid_bitmaps_[recursion_level];

 for (int64_t i = 0; i < inner_length; i++) {
 if (i > 0) {
 RETURN_NOT_OK(rep_levels_.Append(static_cast<int16_t>(rep_level + 1)));
 }
 if (level_null_count && level_valid_bitmap == nullptr) {
 // Special case: this is a null array (all elements are null)
 RETURN_NOT_OK(def_levels_.Append(static_cast<int16_t>(def_level + 1)));
 } else if (nullable_level &&
 ((level_null_count == 0) ||
 BitUtil::GetBit(
 level_valid_bitmap,
 inner_offset + i + array_offsets_[recursion_level]))) {
 // Non-null element in a null level
 RETURN_NOT_OK(def_levels_.Append(static_cast<int16_t>(def_level + 2)));
 } else {
 // This can be produced in two case:
 // * elements are nullable and this one is null (i.e. max_def_level = def_level
 // + 2)
 // * elements are non-nullable (i.e. max_def_level = def_level + 1)
 RETURN_NOT_OK(def_levels_.Append(static_cast<int16_t>(def_level + 1)));
 }
 }
 // We have reached the leaf: primitive list, handle remaining nullables
 const bool nullable_level = nullable_[recursion_level];
 const int64_t level_null_count = null_counts_[recursion_level];
 const uint8_t* level_valid_bitmap = valid_bitmaps_[recursion_level];

 if (inner_length >= 1) {
 RETURN_NOT_OK(
 rep_levels_.Append(inner_length - 1, static_cast<int16_t>(rep_level + 1)));
 }

 // Special case: this is a null array (all elements are null)
 if (level_null_count && level_valid_bitmap == nullptr) {
 return def_levels_.Append(inner_length, static_cast<int16_t>(def_level + 1));
 }
 for (int64_t i = 0; i < inner_length; i++) {
 if (nullable_level &&
 ((level_null_count == 0) ||
 BitUtil::GetBit(level_valid_bitmap,
 inner_offset + i + array_offsets_[recursion_level]))) {
 // Non-null element in a null level
 RETURN_NOT_OK(def_levels_.Append(static_cast<int16_t>(def_level + 2)));
 } else {
 // This can be produced in two cases:
 // * elements are nullable and this one is null
 // (i.e. max_def_level = def_level + 2)
 // * elements are non-nullable (i.e. max_def_level = def_level + 1)
 RETURN_NOT_OK(def_levels_.Append(static_cast<int16_t>(def_level + 1)));
 }
 return Status::OK();
 }
 return Status::OK();
 }

 Status HandleListEntries(int16_t def_level, int16_t rep_level, int64_t offset,
Expand All@@ -261,8 +260,8 @@ class LevelBuilder {
 }

 private:
Int16Builder def_levels_;
Int16Builder rep_levels_;
Int16BufferBuilder def_levels_;
Int16BufferBuilder rep_levels_;

 std::vector<int64_t> null_counts_;
 std::vector<const uint8_t*> valid_bitmaps_;
Expand DownExpand Up@@ -307,7 +306,7 @@ struct ColumnWriterContext {
Status GetLeafType(const ::arrow::DataType& type, ::arrow::Type::type* leaf_type) {
 if (type.id() == ::arrow::Type::LIST || type.id() == ::arrow::Type::STRUCT) {
 if (type.num_children() != 1) {
 return Status::Invalid("Nested column branch had multiple children");
 return Status::Invalid("Nested column branch had multiple children: ", type);
 }
 return GetLeafType(*type.child(0)->type(), leaf_type);
 } else {
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
ARROW-5880: [C++][Parquet] Use TypedBufferBuilder instead of ArrayBuilder in writer.cc#4827

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

emkornfield
wants to merge
11
commits into

from

 Closed


ARROW-5880: [C++][Parquet] Use TypedBufferBuilder instead of ArrayBuilder in writer.cc
#4827
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


11 commits


Select commit
Hold shift + click to select a range
7795352

change from array builder to buffer builde


emkornfield Jul 7, 2019
4516110

Small style issues


emkornfield Jul 8, 2019
325af52

undo reserve


emkornfield Jul 8, 2019
83ee5ae

Update cpp/src/parquet/arrow/writer.cc


emkornfield Jul 10, 2019
7cbc8e4

Update cpp/src/parquet/arrow/writer.cc


emkornfield Jul 10, 2019
6776e61

Update cpp/src/parquet/arrow/writer.cc


emkornfield Jul 10, 2019
ef7fade

remove unneeded nesting


emkornfield Jul 10, 2019
67ccf3e

update references


emkornfield Jul 10, 2019
152a6ee

change back to signed it seems to be what the API uses


emkornfield Jul 10, 2019
e1698e5

fix compilation issues


emkornfield Jul 10, 2019
2f77313

Export operator<< symbols for DataType, TimeUnit on Windows


wesm Jul 10, 2019

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


6 changes: 2 additions & 4 deletions
cpp/src/arrow/buffer-builder.h

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -220,10 +220,8 @@ class TypedBufferBuilder<T, typename std::enable_if<std::is_arithmetic<T>::value

 void UnsafeAppend(const int64_t num_copies, T value) {
 auto data = mutable_data() + length();
 bytes_builder_.UnsafeAppend(num_copies * sizeof(T), 0);
 for (const auto end = data + num_copies; data != end; ++data) {
 *data = value;
 }
 bytes_builder_.UnsafeAdvance(num_copies * sizeof(T));
 std::fill(data, data + num_copies, value);
 }

 Status Resize(const int64_t new_capacity, bool shrink_to_fit = true) {
Expand Down

2 changes: 2 additions & 0 deletions
cpp/src/arrow/type.h

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -215,6 +215,7 @@ class ARROW_EXPORT DataType {
 ARROW_DISALLOW_COPY_AND_ASSIGN(DataType);
};

ARROW_EXPORT
std::ostream& operator<<(std::ostream& os, const DataType& type);

/// \brief Base class for all fixed-width data types
Expand DownExpand Up@@ -762,6 +763,7 @@ struct TimeUnit {
 enum type { SECOND = 0, MILLI = 1, MICRO = 2, NANO = 3 };
};

ARROW_EXPORT
std::ostream& operator<<(std::ostream& os, TimeUnit::type unit);

/// Base type class for time data
Expand Down

87 changes: 43 additions & 44 deletions
cpp/src/parquet/arrow/writer.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -49,8 +49,7 @@ using arrow::ChunkedArray;
using arrow::Decimal128Array;
using arrow::Field;
using arrow::FixedSizeBinaryArray;
using arrow::Int16Array;
using arrow::Int16Builder;
using Int16BufferBuilder = arrow::TypedBufferBuilder<int16_t>;
using arrow::ListArray;
using arrow::MemoryPool;
using arrow::NumericArray;
Expand DownExpand Up@@ -81,8 +80,7 @@ namespace {

class LevelBuilder {
 public:
 explicit LevelBuilder(MemoryPool* pool)
 : def_levels_(::arrow::int16(), pool), rep_levels_(::arrow::int16(), pool) {}
 explicit LevelBuilder(MemoryPool* pool) : def_levels_(pool), rep_levels_(pool) {}

 Status VisitInline(const Array& array);

Expand All@@ -102,6 +100,7 @@ class LevelBuilder {
 null_counts_.push_back(array.null_count());
 offsets_.push_back(array.raw_value_offsets());

 // Min offset isn't always zero in the case of sliced Arrays.
 min_offset_idx_ = array.value_offset(min_offset_idx_);
 max_offset_idx_ = array.value_offset(max_offset_idx_);

Expand DownExpand Up@@ -176,18 +175,17 @@ class LevelBuilder {
 }
 *num_levels = array.length();
 } else {
 // Note it is hard to estimate memory consumption due to zero length
 // arrays otherwise we would preallocate. An upper boun on memory
@bkietzbkietzJul 9, 2019

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

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


Suggested change

// arrays otherwise we would preallocate. An upper boun on memory
// arrays otherwise we would preallocate. An upper bound on memory
 // is the sum of the length of each list array + number of elements
 // but this might be too loose of an upper bound so we choose to use
 // safe methods.
 RETURN_NOT_OK(rep_levels_.Append(0));
 RETURN_NOT_OK(HandleListEntries(0, 0, 0, array.length()));

 std::shared_ptr<Array> def_levels_array;
 std::shared_ptr<Array> rep_levels_array;

 RETURN_NOT_OK(def_levels_.Finish(&def_levels_array));
 RETURN_NOT_OK(rep_levels_.Finish(&rep_levels_array));

 *def_levels_out = static_cast<PrimitiveArray*>(def_levels_array.get())->values();
 *rep_levels_out = static_cast<PrimitiveArray*>(rep_levels_array.get())->values();
 *num_levels = rep_levels_array->length();
 RETURN_NOT_OK(def_levels_.Finish(def_levels_out));
Comment thread
emkornfield marked this conversation as resolved.


Outdated

 RETURN_NOT_OK(rep_levels_.Finish(rep_levels_out));
 *num_levels = (*rep_levels_out)->size() / sizeof(int16_t);
 }

 return Status::OK();
Expand DownExpand Up@@ -217,36 +215,37 @@ class LevelBuilder {
 return HandleListEntries(static_cast<int16_t>(def_level + 1),
 static_cast<int16_t>(rep_level + 1), inner_offset,
 inner_length);
 } else {
 // We have reached the leaf: primitive list, handle remaining nullables
 const bool nullable_level = nullable_[recursion_level];
 const int64_t level_null_count = null_counts_[recursion_level];
 const uint8_t* level_valid_bitmap = valid_bitmaps_[recursion_level];

 for (int64_t i = 0; i < inner_length; i++) {
 if (i > 0) {
 RETURN_NOT_OK(rep_levels_.Append(static_cast<int16_t>(rep_level + 1)));
 }
 if (level_null_count && level_valid_bitmap == nullptr) {
 // Special case: this is a null array (all elements are null)
 RETURN_NOT_OK(def_levels_.Append(static_cast<int16_t>(def_level + 1)));
 } else if (nullable_level &&
 ((level_null_count == 0) ||
 BitUtil::GetBit(
 level_valid_bitmap,
 inner_offset + i + array_offsets_[recursion_level]))) {
 // Non-null element in a null level
 RETURN_NOT_OK(def_levels_.Append(static_cast<int16_t>(def_level + 2)));
 } else {
 // This can be produced in two case:
 // * elements are nullable and this one is null (i.e. max_def_level = def_level
 // + 2)
 // * elements are non-nullable (i.e. max_def_level = def_level + 1)
 RETURN_NOT_OK(def_levels_.Append(static_cast<int16_t>(def_level + 1)));
 }
 }
 // We have reached the leaf: primitive list, handle remaining nullables
 const bool nullable_level = nullable_[recursion_level];
 const int64_t level_null_count = null_counts_[recursion_level];
 const uint8_t* level_valid_bitmap = valid_bitmaps_[recursion_level];

 if (inner_length >= 1) {
 RETURN_NOT_OK(
 rep_levels_.Append(inner_length - 1, static_cast<int16_t>(rep_level + 1)));
 }

 // Special case: this is a null array (all elements are null)
 if (level_null_count && level_valid_bitmap == nullptr) {
 return def_levels_.Append(inner_length, static_cast<int16_t>(def_level + 1));
 }
 for (int64_t i = 0; i < inner_length; i++) {
 if (nullable_level &&
 ((level_null_count == 0) ||
 BitUtil::GetBit(level_valid_bitmap,
 inner_offset + i + array_offsets_[recursion_level]))) {
 // Non-null element in a null level
 RETURN_NOT_OK(def_levels_.Append(static_cast<int16_t>(def_level + 2)));
 } else {
 // This can be produced in two cases:
 // * elements are nullable and this one is null
 // (i.e. max_def_level = def_level + 2)
 // * elements are non-nullable (i.e. max_def_level = def_level + 1)
 RETURN_NOT_OK(def_levels_.Append(static_cast<int16_t>(def_level + 1)));
 }
 return Status::OK();
 }
 return Status::OK();
 }

 Status HandleListEntries(int16_t def_level, int16_t rep_level, int64_t offset,
Expand All@@ -261,8 +260,8 @@ class LevelBuilder {
 }

 private:
Int16Builder def_levels_;
Int16Builder rep_levels_;
Int16BufferBuilder def_levels_;
Int16BufferBuilder rep_levels_;

 std::vector<int64_t> null_counts_;
 std::vector<const uint8_t*> valid_bitmaps_;
Expand DownExpand Up@@ -307,7 +306,7 @@ struct ColumnWriterContext {
Status GetLeafType(const ::arrow::DataType& type, ::arrow::Type::type* leaf_type) {
 if (type.id() == ::arrow::Type::LIST || type.id() == ::arrow::Type::STRUCT) {
 if (type.num_children() != 1) {
 return Status::Invalid("Nested column branch had multiple children");
 return Status::Invalid("Nested column branch had multiple children: ", type);
 }
 return GetLeafType(*type.child(0)->type(), leaf_type);
 } else {
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
ARROW-5880: [C++][Parquet] Use TypedBufferBuilder instead of ArrayBuilder in writer.cc#4827

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

emkornfield
wants to merge
11
commits into

from

 Closed


ARROW-5880: [C++][Parquet] Use TypedBufferBuilder instead of ArrayBuilder in writer.cc
#4827
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


11 commits


Select commit
Hold shift + click to select a range
7795352

change from array builder to buffer builde


emkornfield Jul 7, 2019
4516110

Small style issues


emkornfield Jul 8, 2019
325af52

undo reserve


emkornfield Jul 8, 2019
83ee5ae

Update cpp/src/parquet/arrow/writer.cc


emkornfield Jul 10, 2019
7cbc8e4

Update cpp/src/parquet/arrow/writer.cc


emkornfield Jul 10, 2019
6776e61

Update cpp/src/parquet/arrow/writer.cc


emkornfield Jul 10, 2019
ef7fade

remove unneeded nesting


emkornfield Jul 10, 2019
67ccf3e

update references


emkornfield Jul 10, 2019
152a6ee

change back to signed it seems to be what the API uses


emkornfield Jul 10, 2019
e1698e5

fix compilation issues


emkornfield Jul 10, 2019
2f77313

Export operator<< symbols for DataType, TimeUnit on Windows


wesm Jul 10, 2019

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


6 changes: 2 additions & 4 deletions
cpp/src/arrow/buffer-builder.h

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -220,10 +220,8 @@ class TypedBufferBuilder<T, typename std::enable_if<std::is_arithmetic<T>::value

 void UnsafeAppend(const int64_t num_copies, T value) {
 auto data = mutable_data() + length();
 bytes_builder_.UnsafeAppend(num_copies * sizeof(T), 0);
 for (const auto end = data + num_copies; data != end; ++data) {
 *data = value;
 }
 bytes_builder_.UnsafeAdvance(num_copies * sizeof(T));
 std::fill(data, data + num_copies, value);
 }

 Status Resize(const int64_t new_capacity, bool shrink_to_fit = true) {
Expand Down

2 changes: 2 additions & 0 deletions
cpp/src/arrow/type.h

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -215,6 +215,7 @@ class ARROW_EXPORT DataType {
 ARROW_DISALLOW_COPY_AND_ASSIGN(DataType);
};

ARROW_EXPORT
std::ostream& operator<<(std::ostream& os, const DataType& type);

/// \brief Base class for all fixed-width data types
Expand DownExpand Up@@ -762,6 +763,7 @@ struct TimeUnit {
 enum type { SECOND = 0, MILLI = 1, MICRO = 2, NANO = 3 };
};

ARROW_EXPORT
std::ostream& operator<<(std::ostream& os, TimeUnit::type unit);

/// Base type class for time data
Expand Down

87 changes: 43 additions & 44 deletions
cpp/src/parquet/arrow/writer.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -49,8 +49,7 @@ using arrow::ChunkedArray;
using arrow::Decimal128Array;
using arrow::Field;
using arrow::FixedSizeBinaryArray;
using arrow::Int16Array;
using arrow::Int16Builder;
using Int16BufferBuilder = arrow::TypedBufferBuilder<int16_t>;
using arrow::ListArray;
using arrow::MemoryPool;
using arrow::NumericArray;
Expand DownExpand Up@@ -81,8 +80,7 @@ namespace {

class LevelBuilder {
 public:
 explicit LevelBuilder(MemoryPool* pool)
 : def_levels_(::arrow::int16(), pool), rep_levels_(::arrow::int16(), pool) {}
 explicit LevelBuilder(MemoryPool* pool) : def_levels_(pool), rep_levels_(pool) {}

 Status VisitInline(const Array& array);

Expand All@@ -102,6 +100,7 @@ class LevelBuilder {
 null_counts_.push_back(array.null_count());
 offsets_.push_back(array.raw_value_offsets());

 // Min offset isn't always zero in the case of sliced Arrays.
 min_offset_idx_ = array.value_offset(min_offset_idx_);
 max_offset_idx_ = array.value_offset(max_offset_idx_);

Expand DownExpand Up@@ -176,18 +175,17 @@ class LevelBuilder {
 }
 *num_levels = array.length();
 } else {
 // Note it is hard to estimate memory consumption due to zero length
 // arrays otherwise we would preallocate. An upper boun on memory
@bkietzbkietzJul 9, 2019

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

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


Suggested change

// arrays otherwise we would preallocate. An upper boun on memory
// arrays otherwise we would preallocate. An upper bound on memory
 // is the sum of the length of each list array + number of elements
 // but this might be too loose of an upper bound so we choose to use
 // safe methods.
 RETURN_NOT_OK(rep_levels_.Append(0));
 RETURN_NOT_OK(HandleListEntries(0, 0, 0, array.length()));

 std::shared_ptr<Array> def_levels_array;
 std::shared_ptr<Array> rep_levels_array;

 RETURN_NOT_OK(def_levels_.Finish(&def_levels_array));
 RETURN_NOT_OK(rep_levels_.Finish(&rep_levels_array));

 *def_levels_out = static_cast<PrimitiveArray*>(def_levels_array.get())->values();
 *rep_levels_out = static_cast<PrimitiveArray*>(rep_levels_array.get())->values();
 *num_levels = rep_levels_array->length();
 RETURN_NOT_OK(def_levels_.Finish(def_levels_out));
Comment thread
emkornfield marked this conversation as resolved.


Outdated

 RETURN_NOT_OK(rep_levels_.Finish(rep_levels_out));
 *num_levels = (*rep_levels_out)->size() / sizeof(int16_t);
 }

 return Status::OK();
Expand DownExpand Up@@ -217,36 +215,37 @@ class LevelBuilder {
 return HandleListEntries(static_cast<int16_t>(def_level + 1),
 static_cast<int16_t>(rep_level + 1), inner_offset,
 inner_length);
 } else {
 // We have reached the leaf: primitive list, handle remaining nullables
 const bool nullable_level = nullable_[recursion_level];
 const int64_t level_null_count = null_counts_[recursion_level];
 const uint8_t* level_valid_bitmap = valid_bitmaps_[recursion_level];

 for (int64_t i = 0; i < inner_length; i++) {
 if (i > 0) {
 RETURN_NOT_OK(rep_levels_.Append(static_cast<int16_t>(rep_level + 1)));
 }
 if (level_null_count && level_valid_bitmap == nullptr) {
 // Special case: this is a null array (all elements are null)
 RETURN_NOT_OK(def_levels_.Append(static_cast<int16_t>(def_level + 1)));
 } else if (nullable_level &&
 ((level_null_count == 0) ||
 BitUtil::GetBit(
 level_valid_bitmap,
 inner_offset + i + array_offsets_[recursion_level]))) {
 // Non-null element in a null level
 RETURN_NOT_OK(def_levels_.Append(static_cast<int16_t>(def_level + 2)));
 } else {
 // This can be produced in two case:
 // * elements are nullable and this one is null (i.e. max_def_level = def_level
 // + 2)
 // * elements are non-nullable (i.e. max_def_level = def_level + 1)
 RETURN_NOT_OK(def_levels_.Append(static_cast<int16_t>(def_level + 1)));
 }
 }
 // We have reached the leaf: primitive list, handle remaining nullables
 const bool nullable_level = nullable_[recursion_level];
 const int64_t level_null_count = null_counts_[recursion_level];
 const uint8_t* level_valid_bitmap = valid_bitmaps_[recursion_level];

 if (inner_length >= 1) {
 RETURN_NOT_OK(
 rep_levels_.Append(inner_length - 1, static_cast<int16_t>(rep_level + 1)));
 }

 // Special case: this is a null array (all elements are null)
 if (level_null_count && level_valid_bitmap == nullptr) {
 return def_levels_.Append(inner_length, static_cast<int16_t>(def_level + 1));
 }
 for (int64_t i = 0; i < inner_length; i++) {
 if (nullable_level &&
 ((level_null_count == 0) ||
 BitUtil::GetBit(level_valid_bitmap,
 inner_offset + i + array_offsets_[recursion_level]))) {
 // Non-null element in a null level
 RETURN_NOT_OK(def_levels_.Append(static_cast<int16_t>(def_level + 2)));
 } else {
 // This can be produced in two cases:
 // * elements are nullable and this one is null
 // (i.e. max_def_level = def_level + 2)
 // * elements are non-nullable (i.e. max_def_level = def_level + 1)
 RETURN_NOT_OK(def_levels_.Append(static_cast<int16_t>(def_level + 1)));
 }
 return Status::OK();
 }
 return Status::OK();
 }

 Status HandleListEntries(int16_t def_level, int16_t rep_level, int64_t offset,
Expand All@@ -261,8 +260,8 @@ class LevelBuilder {
 }

 private:
Int16Builder def_levels_;
Int16Builder rep_levels_;
Int16BufferBuilder def_levels_;
Int16BufferBuilder rep_levels_;

 std::vector<int64_t> null_counts_;
 std::vector<const uint8_t*> valid_bitmaps_;
Expand DownExpand Up@@ -307,7 +306,7 @@ struct ColumnWriterContext {
Status GetLeafType(const ::arrow::DataType& type, ::arrow::Type::type* leaf_type) {
 if (type.id() == ::arrow::Type::LIST || type.id() == ::arrow::Type::STRUCT) {
 if (type.num_children() != 1) {
 return Status::Invalid("Nested column branch had multiple children");
 return Status::Invalid("Nested column branch had multiple children: ", type);
 }
 return GetLeafType(*type.child(0)->type(), leaf_type);
 } else {
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
ARROW-5880: [C++][Parquet] Use TypedBufferBuilder instead of ArrayBuilder in writer.cc#4827

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

emkornfield
wants to merge
11
commits into

from

 Closed


ARROW-5880: [C++][Parquet] Use TypedBufferBuilder instead of ArrayBuilder in writer.cc
#4827
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


11 commits


Select commit
Hold shift + click to select a range
7795352

change from array builder to buffer builde


emkornfield Jul 7, 2019
4516110

Small style issues


emkornfield Jul 8, 2019
325af52

undo reserve


emkornfield Jul 8, 2019
83ee5ae

Update cpp/src/parquet/arrow/writer.cc


emkornfield Jul 10, 2019
7cbc8e4

Update cpp/src/parquet/arrow/writer.cc


emkornfield Jul 10, 2019
6776e61

Update cpp/src/parquet/arrow/writer.cc


emkornfield Jul 10, 2019
ef7fade

remove unneeded nesting


emkornfield Jul 10, 2019
67ccf3e

update references


emkornfield Jul 10, 2019
152a6ee

change back to signed it seems to be what the API uses


emkornfield Jul 10, 2019
e1698e5

fix compilation issues


emkornfield Jul 10, 2019
2f77313

Export operator<< symbols for DataType, TimeUnit on Windows


wesm Jul 10, 2019

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


6 changes: 2 additions & 4 deletions
cpp/src/arrow/buffer-builder.h

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -220,10 +220,8 @@ class TypedBufferBuilder<T, typename std::enable_if<std::is_arithmetic<T>::value

 void UnsafeAppend(const int64_t num_copies, T value) {
 auto data = mutable_data() + length();
 bytes_builder_.UnsafeAppend(num_copies * sizeof(T), 0);
 for (const auto end = data + num_copies; data != end; ++data) {
 *data = value;
 }
 bytes_builder_.UnsafeAdvance(num_copies * sizeof(T));
 std::fill(data, data + num_copies, value);
 }

 Status Resize(const int64_t new_capacity, bool shrink_to_fit = true) {
Expand Down

2 changes: 2 additions & 0 deletions
cpp/src/arrow/type.h

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -215,6 +215,7 @@ class ARROW_EXPORT DataType {
 ARROW_DISALLOW_COPY_AND_ASSIGN(DataType);
};

ARROW_EXPORT
std::ostream& operator<<(std::ostream& os, const DataType& type);

/// \brief Base class for all fixed-width data types
Expand DownExpand Up@@ -762,6 +763,7 @@ struct TimeUnit {
 enum type { SECOND = 0, MILLI = 1, MICRO = 2, NANO = 3 };
};

ARROW_EXPORT
std::ostream& operator<<(std::ostream& os, TimeUnit::type unit);

/// Base type class for time data
Expand Down

87 changes: 43 additions & 44 deletions
cpp/src/parquet/arrow/writer.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -49,8 +49,7 @@ using arrow::ChunkedArray;
using arrow::Decimal128Array;
using arrow::Field;
using arrow::FixedSizeBinaryArray;
using arrow::Int16Array;
using arrow::Int16Builder;
using Int16BufferBuilder = arrow::TypedBufferBuilder<int16_t>;
using arrow::ListArray;
using arrow::MemoryPool;
using arrow::NumericArray;
Expand DownExpand Up@@ -81,8 +80,7 @@ namespace {

class LevelBuilder {
 public:
 explicit LevelBuilder(MemoryPool* pool)
 : def_levels_(::arrow::int16(), pool), rep_levels_(::arrow::int16(), pool) {}
 explicit LevelBuilder(MemoryPool* pool) : def_levels_(pool), rep_levels_(pool) {}

 Status VisitInline(const Array& array);

Expand All@@ -102,6 +100,7 @@ class LevelBuilder {
 null_counts_.push_back(array.null_count());
 offsets_.push_back(array.raw_value_offsets());

 // Min offset isn't always zero in the case of sliced Arrays.
 min_offset_idx_ = array.value_offset(min_offset_idx_);
 max_offset_idx_ = array.value_offset(max_offset_idx_);

Expand DownExpand Up@@ -176,18 +175,17 @@ class LevelBuilder {
 }
 *num_levels = array.length();
 } else {
 // Note it is hard to estimate memory consumption due to zero length
 // arrays otherwise we would preallocate. An upper boun on memory
@bkietzbkietzJul 9, 2019

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

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


Suggested change

// arrays otherwise we would preallocate. An upper boun on memory
// arrays otherwise we would preallocate. An upper bound on memory
 // is the sum of the length of each list array + number of elements
 // but this might be too loose of an upper bound so we choose to use
 // safe methods.
 RETURN_NOT_OK(rep_levels_.Append(0));
 RETURN_NOT_OK(HandleListEntries(0, 0, 0, array.length()));

 std::shared_ptr<Array> def_levels_array;
 std::shared_ptr<Array> rep_levels_array;

 RETURN_NOT_OK(def_levels_.Finish(&def_levels_array));
 RETURN_NOT_OK(rep_levels_.Finish(&rep_levels_array));

 *def_levels_out = static_cast<PrimitiveArray*>(def_levels_array.get())->values();
 *rep_levels_out = static_cast<PrimitiveArray*>(rep_levels_array.get())->values();
 *num_levels = rep_levels_array->length();
 RETURN_NOT_OK(def_levels_.Finish(def_levels_out));
Comment thread
emkornfield marked this conversation as resolved.


Outdated

 RETURN_NOT_OK(rep_levels_.Finish(rep_levels_out));
 *num_levels = (*rep_levels_out)->size() / sizeof(int16_t);
 }

 return Status::OK();
Expand DownExpand Up@@ -217,36 +215,37 @@ class LevelBuilder {
 return HandleListEntries(static_cast<int16_t>(def_level + 1),
 static_cast<int16_t>(rep_level + 1), inner_offset,
 inner_length);
 } else {
 // We have reached the leaf: primitive list, handle remaining nullables
 const bool nullable_level = nullable_[recursion_level];
 const int64_t level_null_count = null_counts_[recursion_level];
 const uint8_t* level_valid_bitmap = valid_bitmaps_[recursion_level];

 for (int64_t i = 0; i < inner_length; i++) {
 if (i > 0) {
 RETURN_NOT_OK(rep_levels_.Append(static_cast<int16_t>(rep_level + 1)));
 }
 if (level_null_count && level_valid_bitmap == nullptr) {
 // Special case: this is a null array (all elements are null)
 RETURN_NOT_OK(def_levels_.Append(static_cast<int16_t>(def_level + 1)));
 } else if (nullable_level &&
 ((level_null_count == 0) ||
 BitUtil::GetBit(
 level_valid_bitmap,
 inner_offset + i + array_offsets_[recursion_level]))) {
 // Non-null element in a null level
 RETURN_NOT_OK(def_levels_.Append(static_cast<int16_t>(def_level + 2)));
 } else {
 // This can be produced in two case:
 // * elements are nullable and this one is null (i.e. max_def_level = def_level
 // + 2)
 // * elements are non-nullable (i.e. max_def_level = def_level + 1)
 RETURN_NOT_OK(def_levels_.Append(static_cast<int16_t>(def_level + 1)));
 }
 }
 // We have reached the leaf: primitive list, handle remaining nullables
 const bool nullable_level = nullable_[recursion_level];
 const int64_t level_null_count = null_counts_[recursion_level];
 const uint8_t* level_valid_bitmap = valid_bitmaps_[recursion_level];

 if (inner_length >= 1) {
 RETURN_NOT_OK(
 rep_levels_.Append(inner_length - 1, static_cast<int16_t>(rep_level + 1)));
 }

 // Special case: this is a null array (all elements are null)
 if (level_null_count && level_valid_bitmap == nullptr) {
 return def_levels_.Append(inner_length, static_cast<int16_t>(def_level + 1));
 }
 for (int64_t i = 0; i < inner_length; i++) {
 if (nullable_level &&
 ((level_null_count == 0) ||
 BitUtil::GetBit(level_valid_bitmap,
 inner_offset + i + array_offsets_[recursion_level]))) {
 // Non-null element in a null level
 RETURN_NOT_OK(def_levels_.Append(static_cast<int16_t>(def_level + 2)));
 } else {
 // This can be produced in two cases:
 // * elements are nullable and this one is null
 // (i.e. max_def_level = def_level + 2)
 // * elements are non-nullable (i.e. max_def_level = def_level + 1)
 RETURN_NOT_OK(def_levels_.Append(static_cast<int16_t>(def_level + 1)));
 }
 return Status::OK();
 }
 return Status::OK();
 }

 Status HandleListEntries(int16_t def_level, int16_t rep_level, int64_t offset,
Expand All@@ -261,8 +260,8 @@ class LevelBuilder {
 }

 private:
Int16Builder def_levels_;
Int16Builder rep_levels_;
Int16BufferBuilder def_levels_;
Int16BufferBuilder rep_levels_;

 std::vector<int64_t> null_counts_;
 std::vector<const uint8_t*> valid_bitmaps_;
Expand DownExpand Up@@ -307,7 +306,7 @@ struct ColumnWriterContext {
Status GetLeafType(const ::arrow::DataType& type, ::arrow::Type::type* leaf_type) {
 if (type.id() == ::arrow::Type::LIST || type.id() == ::arrow::Type::STRUCT) {
 if (type.num_children() != 1) {
 return Status::Invalid("Nested column branch had multiple children");
 return Status::Invalid("Nested column branch had multiple children: ", type);
 }
 return GetLeafType(*type.child(0)->type(), leaf_type);
 } else {
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
ARROW-5880: [C++][Parquet] Use TypedBufferBuilder instead of ArrayBuilder in writer.cc#4827

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

emkornfield
wants to merge
11
commits into

from

 Closed


ARROW-5880: [C++][Parquet] Use TypedBufferBuilder instead of ArrayBuilder in writer.cc
#4827
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


11 commits


Select commit
Hold shift + click to select a range
7795352

change from array builder to buffer builde


emkornfield Jul 7, 2019
4516110

Small style issues


emkornfield Jul 8, 2019
325af52

undo reserve


emkornfield Jul 8, 2019
83ee5ae

Update cpp/src/parquet/arrow/writer.cc


emkornfield Jul 10, 2019
7cbc8e4

Update cpp/src/parquet/arrow/writer.cc


emkornfield Jul 10, 2019
6776e61

Update cpp/src/parquet/arrow/writer.cc


emkornfield Jul 10, 2019
ef7fade

remove unneeded nesting


emkornfield Jul 10, 2019
67ccf3e

update references


emkornfield Jul 10, 2019
152a6ee

change back to signed it seems to be what the API uses


emkornfield Jul 10, 2019
e1698e5

fix compilation issues


emkornfield Jul 10, 2019
2f77313

Export operator<< symbols for DataType, TimeUnit on Windows


wesm Jul 10, 2019

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


6 changes: 2 additions & 4 deletions
cpp/src/arrow/buffer-builder.h

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -220,10 +220,8 @@ class TypedBufferBuilder<T, typename std::enable_if<std::is_arithmetic<T>::value

 void UnsafeAppend(const int64_t num_copies, T value) {
 auto data = mutable_data() + length();
 bytes_builder_.UnsafeAppend(num_copies * sizeof(T), 0);
 for (const auto end = data + num_copies; data != end; ++data) {
 *data = value;
 }
 bytes_builder_.UnsafeAdvance(num_copies * sizeof(T));
 std::fill(data, data + num_copies, value);
 }

 Status Resize(const int64_t new_capacity, bool shrink_to_fit = true) {
Expand Down

2 changes: 2 additions & 0 deletions
cpp/src/arrow/type.h

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -215,6 +215,7 @@ class ARROW_EXPORT DataType {
 ARROW_DISALLOW_COPY_AND_ASSIGN(DataType);
};

ARROW_EXPORT
std::ostream& operator<<(std::ostream& os, const DataType& type);

/// \brief Base class for all fixed-width data types
Expand DownExpand Up@@ -762,6 +763,7 @@ struct TimeUnit {
 enum type { SECOND = 0, MILLI = 1, MICRO = 2, NANO = 3 };
};

ARROW_EXPORT
std::ostream& operator<<(std::ostream& os, TimeUnit::type unit);

/// Base type class for time data
Expand Down

87 changes: 43 additions & 44 deletions
cpp/src/parquet/arrow/writer.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -49,8 +49,7 @@ using arrow::ChunkedArray;
using arrow::Decimal128Array;
using arrow::Field;
using arrow::FixedSizeBinaryArray;
using arrow::Int16Array;
using arrow::Int16Builder;
using Int16BufferBuilder = arrow::TypedBufferBuilder<int16_t>;
using arrow::ListArray;
using arrow::MemoryPool;
using arrow::NumericArray;
Expand DownExpand Up@@ -81,8 +80,7 @@ namespace {

class LevelBuilder {
 public:
 explicit LevelBuilder(MemoryPool* pool)
 : def_levels_(::arrow::int16(), pool), rep_levels_(::arrow::int16(), pool) {}
 explicit LevelBuilder(MemoryPool* pool) : def_levels_(pool), rep_levels_(pool) {}

 Status VisitInline(const Array& array);

Expand All@@ -102,6 +100,7 @@ class LevelBuilder {
 null_counts_.push_back(array.null_count());
 offsets_.push_back(array.raw_value_offsets());

 // Min offset isn't always zero in the case of sliced Arrays.
 min_offset_idx_ = array.value_offset(min_offset_idx_);
 max_offset_idx_ = array.value_offset(max_offset_idx_);

Expand DownExpand Up@@ -176,18 +175,17 @@ class LevelBuilder {
 }
 *num_levels = array.length();
 } else {
 // Note it is hard to estimate memory consumption due to zero length
 // arrays otherwise we would preallocate. An upper boun on memory
@bkietzbkietzJul 9, 2019

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

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


Suggested change

// arrays otherwise we would preallocate. An upper boun on memory
// arrays otherwise we would preallocate. An upper bound on memory
 // is the sum of the length of each list array + number of elements
 // but this might be too loose of an upper bound so we choose to use
 // safe methods.
 RETURN_NOT_OK(rep_levels_.Append(0));
 RETURN_NOT_OK(HandleListEntries(0, 0, 0, array.length()));

 std::shared_ptr<Array> def_levels_array;
 std::shared_ptr<Array> rep_levels_array;

 RETURN_NOT_OK(def_levels_.Finish(&def_levels_array));
 RETURN_NOT_OK(rep_levels_.Finish(&rep_levels_array));

 *def_levels_out = static_cast<PrimitiveArray*>(def_levels_array.get())->values();
 *rep_levels_out = static_cast<PrimitiveArray*>(rep_levels_array.get())->values();
 *num_levels = rep_levels_array->length();
 RETURN_NOT_OK(def_levels_.Finish(def_levels_out));
Comment thread
emkornfield marked this conversation as resolved.


Outdated

 RETURN_NOT_OK(rep_levels_.Finish(rep_levels_out));
 *num_levels = (*rep_levels_out)->size() / sizeof(int16_t);
 }

 return Status::OK();
Expand DownExpand Up@@ -217,36 +215,37 @@ class LevelBuilder {
 return HandleListEntries(static_cast<int16_t>(def_level + 1),
 static_cast<int16_t>(rep_level + 1), inner_offset,
 inner_length);
 } else {
 // We have reached the leaf: primitive list, handle remaining nullables
 const bool nullable_level = nullable_[recursion_level];
 const int64_t level_null_count = null_counts_[recursion_level];
 const uint8_t* level_valid_bitmap = valid_bitmaps_[recursion_level];

 for (int64_t i = 0; i < inner_length; i++) {
 if (i > 0) {
 RETURN_NOT_OK(rep_levels_.Append(static_cast<int16_t>(rep_level + 1)));
 }
 if (level_null_count && level_valid_bitmap == nullptr) {
 // Special case: this is a null array (all elements are null)
 RETURN_NOT_OK(def_levels_.Append(static_cast<int16_t>(def_level + 1)));
 } else if (nullable_level &&
 ((level_null_count == 0) ||
 BitUtil::GetBit(
 level_valid_bitmap,
 inner_offset + i + array_offsets_[recursion_level]))) {
 // Non-null element in a null level
 RETURN_NOT_OK(def_levels_.Append(static_cast<int16_t>(def_level + 2)));
 } else {
 // This can be produced in two case:
 // * elements are nullable and this one is null (i.e. max_def_level = def_level
 // + 2)
 // * elements are non-nullable (i.e. max_def_level = def_level + 1)
 RETURN_NOT_OK(def_levels_.Append(static_cast<int16_t>(def_level + 1)));
 }
 }
 // We have reached the leaf: primitive list, handle remaining nullables
 const bool nullable_level = nullable_[recursion_level];
 const int64_t level_null_count = null_counts_[recursion_level];
 const uint8_t* level_valid_bitmap = valid_bitmaps_[recursion_level];

 if (inner_length >= 1) {
 RETURN_NOT_OK(
 rep_levels_.Append(inner_length - 1, static_cast<int16_t>(rep_level + 1)));
 }

 // Special case: this is a null array (all elements are null)
 if (level_null_count && level_valid_bitmap == nullptr) {
 return def_levels_.Append(inner_length, static_cast<int16_t>(def_level + 1));
 }
 for (int64_t i = 0; i < inner_length; i++) {
 if (nullable_level &&
 ((level_null_count == 0) ||
 BitUtil::GetBit(level_valid_bitmap,
 inner_offset + i + array_offsets_[recursion_level]))) {
 // Non-null element in a null level
 RETURN_NOT_OK(def_levels_.Append(static_cast<int16_t>(def_level + 2)));
 } else {
 // This can be produced in two cases:
 // * elements are nullable and this one is null
 // (i.e. max_def_level = def_level + 2)
 // * elements are non-nullable (i.e. max_def_level = def_level + 1)
 RETURN_NOT_OK(def_levels_.Append(static_cast<int16_t>(def_level + 1)));
 }
 return Status::OK();
 }
 return Status::OK();
 }

 Status HandleListEntries(int16_t def_level, int16_t rep_level, int64_t offset,
Expand All@@ -261,8 +260,8 @@ class LevelBuilder {
 }

 private:
Int16Builder def_levels_;
Int16Builder rep_levels_;
Int16BufferBuilder def_levels_;
Int16BufferBuilder rep_levels_;

 std::vector<int64_t> null_counts_;
 std::vector<const uint8_t*> valid_bitmaps_;
Expand DownExpand Up@@ -307,7 +306,7 @@ struct ColumnWriterContext {
Status GetLeafType(const ::arrow::DataType& type, ::arrow::Type::type* leaf_type) {
 if (type.id() == ::arrow::Type::LIST || type.id() == ::arrow::Type::STRUCT) {
 if (type.num_children() != 1) {
 return Status::Invalid("Nested column branch had multiple children");
 return Status::Invalid("Nested column branch had multiple children: ", type);
 }
 return GetLeafType(*type.child(0)->type(), leaf_type);
 } else {
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
ARROW-5880: [C++][Parquet] Use TypedBufferBuilder instead of ArrayBuilder in writer.cc#4827

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

emkornfield
wants to merge
11
commits into

from

 Closed


ARROW-5880: [C++][Parquet] Use TypedBufferBuilder instead of ArrayBuilder in writer.cc
#4827
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


11 commits


Select commit
Hold shift + click to select a range
7795352

change from array builder to buffer builde


emkornfield Jul 7, 2019
4516110

Small style issues


emkornfield Jul 8, 2019
325af52

undo reserve


emkornfield Jul 8, 2019
83ee5ae

Update cpp/src/parquet/arrow/writer.cc


emkornfield Jul 10, 2019
7cbc8e4

Update cpp/src/parquet/arrow/writer.cc


emkornfield Jul 10, 2019
6776e61

Update cpp/src/parquet/arrow/writer.cc


emkornfield Jul 10, 2019
ef7fade

remove unneeded nesting


emkornfield Jul 10, 2019
67ccf3e

update references


emkornfield Jul 10, 2019
152a6ee

change back to signed it seems to be what the API uses


emkornfield Jul 10, 2019
e1698e5

fix compilation issues


emkornfield Jul 10, 2019
2f77313

Export operator<< symbols for DataType, TimeUnit on Windows


wesm Jul 10, 2019

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


6 changes: 2 additions & 4 deletions
cpp/src/arrow/buffer-builder.h

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -220,10 +220,8 @@ class TypedBufferBuilder<T, typename std::enable_if<std::is_arithmetic<T>::value

 void UnsafeAppend(const int64_t num_copies, T value) {
 auto data = mutable_data() + length();
 bytes_builder_.UnsafeAppend(num_copies * sizeof(T), 0);
 for (const auto end = data + num_copies; data != end; ++data) {
 *data = value;
 }
 bytes_builder_.UnsafeAdvance(num_copies * sizeof(T));
 std::fill(data, data + num_copies, value);
 }

 Status Resize(const int64_t new_capacity, bool shrink_to_fit = true) {
Expand Down

2 changes: 2 additions & 0 deletions
cpp/src/arrow/type.h

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -215,6 +215,7 @@ class ARROW_EXPORT DataType {
 ARROW_DISALLOW_COPY_AND_ASSIGN(DataType);
};

ARROW_EXPORT
std::ostream& operator<<(std::ostream& os, const DataType& type);

/// \brief Base class for all fixed-width data types
Expand DownExpand Up@@ -762,6 +763,7 @@ struct TimeUnit {
 enum type { SECOND = 0, MILLI = 1, MICRO = 2, NANO = 3 };
};

ARROW_EXPORT
std::ostream& operator<<(std::ostream& os, TimeUnit::type unit);

/// Base type class for time data
Expand Down

87 changes: 43 additions & 44 deletions
cpp/src/parquet/arrow/writer.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -49,8 +49,7 @@ using arrow::ChunkedArray;
using arrow::Decimal128Array;
using arrow::Field;
using arrow::FixedSizeBinaryArray;
using arrow::Int16Array;
using arrow::Int16Builder;
using Int16BufferBuilder = arrow::TypedBufferBuilder<int16_t>;
using arrow::ListArray;
using arrow::MemoryPool;
using arrow::NumericArray;
Expand DownExpand Up@@ -81,8 +80,7 @@ namespace {

class LevelBuilder {
 public:
 explicit LevelBuilder(MemoryPool* pool)
 : def_levels_(::arrow::int16(), pool), rep_levels_(::arrow::int16(), pool) {}
 explicit LevelBuilder(MemoryPool* pool) : def_levels_(pool), rep_levels_(pool) {}

 Status VisitInline(const Array& array);

Expand All@@ -102,6 +100,7 @@ class LevelBuilder {
 null_counts_.push_back(array.null_count());
 offsets_.push_back(array.raw_value_offsets());

 // Min offset isn't always zero in the case of sliced Arrays.
 min_offset_idx_ = array.value_offset(min_offset_idx_);
 max_offset_idx_ = array.value_offset(max_offset_idx_);

Expand DownExpand Up@@ -176,18 +175,17 @@ class LevelBuilder {
 }
 *num_levels = array.length();
 } else {
 // Note it is hard to estimate memory consumption due to zero length
 // arrays otherwise we would preallocate. An upper boun on memory
@bkietzbkietzJul 9, 2019

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

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


Suggested change

// arrays otherwise we would preallocate. An upper boun on memory
// arrays otherwise we would preallocate. An upper bound on memory
 // is the sum of the length of each list array + number of elements
 // but this might be too loose of an upper bound so we choose to use
 // safe methods.
 RETURN_NOT_OK(rep_levels_.Append(0));
 RETURN_NOT_OK(HandleListEntries(0, 0, 0, array.length()));

 std::shared_ptr<Array> def_levels_array;
 std::shared_ptr<Array> rep_levels_array;

 RETURN_NOT_OK(def_levels_.Finish(&def_levels_array));
 RETURN_NOT_OK(rep_levels_.Finish(&rep_levels_array));

 *def_levels_out = static_cast<PrimitiveArray*>(def_levels_array.get())->values();
 *rep_levels_out = static_cast<PrimitiveArray*>(rep_levels_array.get())->values();
 *num_levels = rep_levels_array->length();
 RETURN_NOT_OK(def_levels_.Finish(def_levels_out));
Comment thread
emkornfield marked this conversation as resolved.


Outdated

 RETURN_NOT_OK(rep_levels_.Finish(rep_levels_out));
 *num_levels = (*rep_levels_out)->size() / sizeof(int16_t);
 }

 return Status::OK();
Expand DownExpand Up@@ -217,36 +215,37 @@ class LevelBuilder {
 return HandleListEntries(static_cast<int16_t>(def_level + 1),
 static_cast<int16_t>(rep_level + 1), inner_offset,
 inner_length);
 } else {
 // We have reached the leaf: primitive list, handle remaining nullables
 const bool nullable_level = nullable_[recursion_level];
 const int64_t level_null_count = null_counts_[recursion_level];
 const uint8_t* level_valid_bitmap = valid_bitmaps_[recursion_level];

 for (int64_t i = 0; i < inner_length; i++) {
 if (i > 0) {
 RETURN_NOT_OK(rep_levels_.Append(static_cast<int16_t>(rep_level + 1)));
 }
 if (level_null_count && level_valid_bitmap == nullptr) {
 // Special case: this is a null array (all elements are null)
 RETURN_NOT_OK(def_levels_.Append(static_cast<int16_t>(def_level + 1)));
 } else if (nullable_level &&
 ((level_null_count == 0) ||
 BitUtil::GetBit(
 level_valid_bitmap,
 inner_offset + i + array_offsets_[recursion_level]))) {
 // Non-null element in a null level
 RETURN_NOT_OK(def_levels_.Append(static_cast<int16_t>(def_level + 2)));
 } else {
 // This can be produced in two case:
 // * elements are nullable and this one is null (i.e. max_def_level = def_level
 // + 2)
 // * elements are non-nullable (i.e. max_def_level = def_level + 1)
 RETURN_NOT_OK(def_levels_.Append(static_cast<int16_t>(def_level + 1)));
 }
 }
 // We have reached the leaf: primitive list, handle remaining nullables
 const bool nullable_level = nullable_[recursion_level];
 const int64_t level_null_count = null_counts_[recursion_level];
 const uint8_t* level_valid_bitmap = valid_bitmaps_[recursion_level];

 if (inner_length >= 1) {
 RETURN_NOT_OK(
 rep_levels_.Append(inner_length - 1, static_cast<int16_t>(rep_level + 1)));
 }

 // Special case: this is a null array (all elements are null)
 if (level_null_count && level_valid_bitmap == nullptr) {
 return def_levels_.Append(inner_length, static_cast<int16_t>(def_level + 1));
 }
 for (int64_t i = 0; i < inner_length; i++) {
 if (nullable_level &&
 ((level_null_count == 0) ||
 BitUtil::GetBit(level_valid_bitmap,
 inner_offset + i + array_offsets_[recursion_level]))) {
 // Non-null element in a null level
 RETURN_NOT_OK(def_levels_.Append(static_cast<int16_t>(def_level + 2)));
 } else {
 // This can be produced in two cases:
 // * elements are nullable and this one is null
 // (i.e. max_def_level = def_level + 2)
 // * elements are non-nullable (i.e. max_def_level = def_level + 1)
 RETURN_NOT_OK(def_levels_.Append(static_cast<int16_t>(def_level + 1)));
 }
 return Status::OK();
 }
 return Status::OK();
 }

 Status HandleListEntries(int16_t def_level, int16_t rep_level, int64_t offset,
Expand All@@ -261,8 +260,8 @@ class LevelBuilder {
 }

 private:
Int16Builder def_levels_;
Int16Builder rep_levels_;
Int16BufferBuilder def_levels_;
Int16BufferBuilder rep_levels_;

 std::vector<int64_t> null_counts_;
 std::vector<const uint8_t*> valid_bitmaps_;
Expand DownExpand Up@@ -307,7 +306,7 @@ struct ColumnWriterContext {
Status GetLeafType(const ::arrow::DataType& type, ::arrow::Type::type* leaf_type) {
 if (type.id() == ::arrow::Type::LIST || type.id() == ::arrow::Type::STRUCT) {
 if (type.num_children() != 1) {
 return Status::Invalid("Nested column branch had multiple children");
 return Status::Invalid("Nested column branch had multiple children: ", type);
 }
 return GetLeafType(*type.child(0)->type(), leaf_type);
 } else {
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
ARROW-5880: [C++][Parquet] Use TypedBufferBuilder instead of ArrayBuilder in writer.cc#4827

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

emkornfield
wants to merge
11
commits into

from

 Closed


ARROW-5880: [C++][Parquet] Use TypedBufferBuilder instead of ArrayBuilder in writer.cc
#4827
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


11 commits


Select commit
Hold shift + click to select a range
7795352

change from array builder to buffer builde


emkornfield Jul 7, 2019
4516110

Small style issues


emkornfield Jul 8, 2019
325af52

undo reserve


emkornfield Jul 8, 2019
83ee5ae

Update cpp/src/parquet/arrow/writer.cc


emkornfield Jul 10, 2019
7cbc8e4

Update cpp/src/parquet/arrow/writer.cc


emkornfield Jul 10, 2019
6776e61

Update cpp/src/parquet/arrow/writer.cc


emkornfield Jul 10, 2019
ef7fade

remove unneeded nesting


emkornfield Jul 10, 2019
67ccf3e

update references


emkornfield Jul 10, 2019
152a6ee

change back to signed it seems to be what the API uses


emkornfield Jul 10, 2019
e1698e5

fix compilation issues


emkornfield Jul 10, 2019
2f77313

Export operator<< symbols for DataType, TimeUnit on Windows


wesm Jul 10, 2019

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


6 changes: 2 additions & 4 deletions
cpp/src/arrow/buffer-builder.h

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -220,10 +220,8 @@ class TypedBufferBuilder<T, typename std::enable_if<std::is_arithmetic<T>::value

 void UnsafeAppend(const int64_t num_copies, T value) {
 auto data = mutable_data() + length();
 bytes_builder_.UnsafeAppend(num_copies * sizeof(T), 0);
 for (const auto end = data + num_copies; data != end; ++data) {
 *data = value;
 }
 bytes_builder_.UnsafeAdvance(num_copies * sizeof(T));
 std::fill(data, data + num_copies, value);
 }

 Status Resize(const int64_t new_capacity, bool shrink_to_fit = true) {
Expand Down

2 changes: 2 additions & 0 deletions
cpp/src/arrow/type.h

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -215,6 +215,7 @@ class ARROW_EXPORT DataType {
 ARROW_DISALLOW_COPY_AND_ASSIGN(DataType);
};

ARROW_EXPORT
std::ostream& operator<<(std::ostream& os, const DataType& type);

/// \brief Base class for all fixed-width data types
Expand DownExpand Up@@ -762,6 +763,7 @@ struct TimeUnit {
 enum type { SECOND = 0, MILLI = 1, MICRO = 2, NANO = 3 };
};

ARROW_EXPORT
std::ostream& operator<<(std::ostream& os, TimeUnit::type unit);

/// Base type class for time data
Expand Down

87 changes: 43 additions & 44 deletions
cpp/src/parquet/arrow/writer.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -49,8 +49,7 @@ using arrow::ChunkedArray;
using arrow::Decimal128Array;
using arrow::Field;
using arrow::FixedSizeBinaryArray;
using arrow::Int16Array;
using arrow::Int16Builder;
using Int16BufferBuilder = arrow::TypedBufferBuilder<int16_t>;
using arrow::ListArray;
using arrow::MemoryPool;
using arrow::NumericArray;
Expand DownExpand Up@@ -81,8 +80,7 @@ namespace {

class LevelBuilder {
 public:
 explicit LevelBuilder(MemoryPool* pool)
 : def_levels_(::arrow::int16(), pool), rep_levels_(::arrow::int16(), pool) {}
 explicit LevelBuilder(MemoryPool* pool) : def_levels_(pool), rep_levels_(pool) {}

 Status VisitInline(const Array& array);

Expand All@@ -102,6 +100,7 @@ class LevelBuilder {
 null_counts_.push_back(array.null_count());
 offsets_.push_back(array.raw_value_offsets());

 // Min offset isn't always zero in the case of sliced Arrays.
 min_offset_idx_ = array.value_offset(min_offset_idx_);
 max_offset_idx_ = array.value_offset(max_offset_idx_);

Expand DownExpand Up@@ -176,18 +175,17 @@ class LevelBuilder {
 }
 *num_levels = array.length();
 } else {
 // Note it is hard to estimate memory consumption due to zero length
 // arrays otherwise we would preallocate. An upper boun on memory
@bkietzbkietzJul 9, 2019

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

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


Suggested change

// arrays otherwise we would preallocate. An upper boun on memory
// arrays otherwise we would preallocate. An upper bound on memory
 // is the sum of the length of each list array + number of elements
 // but this might be too loose of an upper bound so we choose to use
 // safe methods.
 RETURN_NOT_OK(rep_levels_.Append(0));
 RETURN_NOT_OK(HandleListEntries(0, 0, 0, array.length()));

 std::shared_ptr<Array> def_levels_array;
 std::shared_ptr<Array> rep_levels_array;

 RETURN_NOT_OK(def_levels_.Finish(&def_levels_array));
 RETURN_NOT_OK(rep_levels_.Finish(&rep_levels_array));

 *def_levels_out = static_cast<PrimitiveArray*>(def_levels_array.get())->values();
 *rep_levels_out = static_cast<PrimitiveArray*>(rep_levels_array.get())->values();
 *num_levels = rep_levels_array->length();
 RETURN_NOT_OK(def_levels_.Finish(def_levels_out));
Comment thread
emkornfield marked this conversation as resolved.


Outdated

 RETURN_NOT_OK(rep_levels_.Finish(rep_levels_out));
 *num_levels = (*rep_levels_out)->size() / sizeof(int16_t);
 }

 return Status::OK();
Expand DownExpand Up@@ -217,36 +215,37 @@ class LevelBuilder {
 return HandleListEntries(static_cast<int16_t>(def_level + 1),
 static_cast<int16_t>(rep_level + 1), inner_offset,
 inner_length);
 } else {
 // We have reached the leaf: primitive list, handle remaining nullables
 const bool nullable_level = nullable_[recursion_level];
 const int64_t level_null_count = null_counts_[recursion_level];
 const uint8_t* level_valid_bitmap = valid_bitmaps_[recursion_level];

 for (int64_t i = 0; i < inner_length; i++) {
 if (i > 0) {
 RETURN_NOT_OK(rep_levels_.Append(static_cast<int16_t>(rep_level + 1)));
 }
 if (level_null_count && level_valid_bitmap == nullptr) {
 // Special case: this is a null array (all elements are null)
 RETURN_NOT_OK(def_levels_.Append(static_cast<int16_t>(def_level + 1)));
 } else if (nullable_level &&
 ((level_null_count == 0) ||
 BitUtil::GetBit(
 level_valid_bitmap,
 inner_offset + i + array_offsets_[recursion_level]))) {
 // Non-null element in a null level
 RETURN_NOT_OK(def_levels_.Append(static_cast<int16_t>(def_level + 2)));
 } else {
 // This can be produced in two case:
 // * elements are nullable and this one is null (i.e. max_def_level = def_level
 // + 2)
 // * elements are non-nullable (i.e. max_def_level = def_level + 1)
 RETURN_NOT_OK(def_levels_.Append(static_cast<int16_t>(def_level + 1)));
 }
 }
 // We have reached the leaf: primitive list, handle remaining nullables
 const bool nullable_level = nullable_[recursion_level];
 const int64_t level_null_count = null_counts_[recursion_level];
 const uint8_t* level_valid_bitmap = valid_bitmaps_[recursion_level];

 if (inner_length >= 1) {
 RETURN_NOT_OK(
 rep_levels_.Append(inner_length - 1, static_cast<int16_t>(rep_level + 1)));
 }

 // Special case: this is a null array (all elements are null)
 if (level_null_count && level_valid_bitmap == nullptr) {
 return def_levels_.Append(inner_length, static_cast<int16_t>(def_level + 1));
 }
 for (int64_t i = 0; i < inner_length; i++) {
 if (nullable_level &&
 ((level_null_count == 0) ||
 BitUtil::GetBit(level_valid_bitmap,
 inner_offset + i + array_offsets_[recursion_level]))) {
 // Non-null element in a null level
 RETURN_NOT_OK(def_levels_.Append(static_cast<int16_t>(def_level + 2)));
 } else {
 // This can be produced in two cases:
 // * elements are nullable and this one is null
 // (i.e. max_def_level = def_level + 2)
 // * elements are non-nullable (i.e. max_def_level = def_level + 1)
 RETURN_NOT_OK(def_levels_.Append(static_cast<int16_t>(def_level + 1)));
 }
 return Status::OK();
 }
 return Status::OK();
 }

 Status HandleListEntries(int16_t def_level, int16_t rep_level, int64_t offset,
Expand All@@ -261,8 +260,8 @@ class LevelBuilder {
 }

 private:
Int16Builder def_levels_;
Int16Builder rep_levels_;
Int16BufferBuilder def_levels_;
Int16BufferBuilder rep_levels_;

 std::vector<int64_t> null_counts_;
 std::vector<const uint8_t*> valid_bitmaps_;
Expand DownExpand Up@@ -307,7 +306,7 @@ struct ColumnWriterContext {
Status GetLeafType(const ::arrow::DataType& type, ::arrow::Type::type* leaf_type) {
 if (type.id() == ::arrow::Type::LIST || type.id() == ::arrow::Type::STRUCT) {
 if (type.num_children() != 1) {
 return Status::Invalid("Nested column branch had multiple children");
 return Status::Invalid("Nested column branch had multiple children: ", type);
 }
 return GetLeafType(*type.child(0)->type(), leaf_type);
 } else {
Expand Down