ARROW-8471: [C++][Integration] Represent 64 bit integers as strings#7292

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
bkietz wants to merge 6 commits into from
Closed

ARROW-8471: [C++][Integration] Represent 64 bit integers as strings #7292

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
e14f60a
ARROW-8471: [C++][Integration] Represent 64 bit integers as strings
bkietz May 27, 2020
47ce0f8
refactor Go to emit and expect 64 bit ints as strings
bkietz May 27, 2020
2e97dff
also adjust duration and date in Go
bkietz May 28, 2020
dbdd293
emit '0' in null slots
bkietz May 28, 2020
bf37227
add extremes to integer ranges
bkietz Jun 2, 2020
1ec2517
repair go indentation
bkietz Jun 2, 2020
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: 3 additions & 3 deletions cpp/src/arrow/ipc/json_integration_test.cc
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -255,7 +255,7 @@ static const char* JSON_EXAMPLE = R"example(
"fields": [
{
"name": "foo",
"type": {"name": "int", "isSigned": true, "bitWidth": 32},
"type": {"name": "int", "isSigned": true, "bitWidth": 64},
Comment thread
fsaintjacques marked this conversation as resolved.
Outdated
"nullable": true, "children": []
},
{
Expand All@@ -272,7 +272,7 @@ static const char* JSON_EXAMPLE = R"example(
{
"name": "foo",
"count": 5,
"DATA": [1, 2, 3, 4, 5],
"DATA": ["1", "2", "3", "4", "5"],
Comment thread
bkietz marked this conversation as resolved.
Outdated
"VALIDITY": [1, 0, 1, 1, 1]
},
{
Expand All@@ -289,7 +289,7 @@ static const char* JSON_EXAMPLE = R"example(
{
"name": "foo",
"count": 4,
"DATA": [1, 2, 3, 4],
"DATA": ["-1", "0", "9223372036854775807", "-9223372036854775808"],
"VALIDITY": [1, 0, 1, 1]
},
{
Expand Down
63 changes: 39 additions & 24 deletions cpp/src/arrow/ipc/json_internal.cc
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -19,6 +19,7 @@

#include <cstdint>
#include <cstdlib>
#include <iostream>
#include <memory>
#include <string>
#include <type_traits>
Expand DownExpand Up@@ -440,29 +441,37 @@ class ArrayWriter {
return Status::OK();
}

template <typename T, bool IsSigned = std::is_signed<typename T::value_type>::value>
void WriteIntegerDataValues(const T& arr) {
static const char null_string[] = "0";
const auto data = arr.raw_values();
template <typename ArrayType, typename TypeClass = typename ArrayType::TypeClass,
typename CType = typename TypeClass::c_type>
enable_if_t<is_physical_integer_type<TypeClass>::value &&
sizeof(CType) != sizeof(int64_t)>
WriteDataValues(const ArrayType& arr) {
static const std::string null_string = "0";
for (int64_t i = 0; i < arr.length(); ++i) {
if (arr.IsValid(i)) {
IsSigned ? writer_->Int64(data[i]) : writer_->Uint64(data[i]);
writer_->Int64(arr.Value(i));
} else {
writer_->RawNumber(null_string, sizeof(null_string));
writer_->RawNumber(null_string.data(), null_string.size());
}
}
}

template <typename ArrayType>
enable_if_physical_signed_integer<typename ArrayType::TypeClass> WriteDataValues(
const ArrayType& arr) {
WriteIntegerDataValues<ArrayType>(arr);
}
template <typename ArrayType, typename TypeClass = typename ArrayType::TypeClass,
typename CType = typename TypeClass::c_type>
enable_if_t<is_physical_integer_type<TypeClass>::value &&
sizeof(CType) == sizeof(int64_t)>
WriteDataValues(const ArrayType& arr) {
::arrow::internal::StringFormatter<typename CTypeTraits<CType>::ArrowType> fmt;

template <typename ArrayType>
enable_if_physical_unsigned_integer<typename ArrayType::TypeClass> WriteDataValues(
const ArrayType& arr) {
WriteIntegerDataValues<ArrayType>(arr);
static const std::string null_string = "0";
for (int64_t i = 0; i < arr.length(); ++i) {
if (arr.IsValid(i)) {
fmt(arr.Value(i),
[&](util::string_view repr) { writer_->String(repr.data(), repr.size()); });
} else {
writer_->String(null_string.data(), null_string.size());
}
}
}

template <typename ArrayType>
Expand DownExpand Up@@ -1154,18 +1163,24 @@ enable_if_boolean<T, bool> UnboxValue(const rj::Value& val) {
return val.GetBool();
}

template <typename T>
enable_if_physical_signed_integer<T, typename T::c_type> UnboxValue(
const rj::Value& val) {
template <typename T, typename CType = typename T::c_type>
enable_if_t<is_physical_integer_type<T>::value && sizeof(CType) != sizeof(int64_t), CType>
UnboxValue(const rj::Value& val) {
DCHECK(val.IsInt64());
return static_cast<typename T::c_type>(val.GetInt64());
return static_cast<CType>(val.GetInt64());
}

template <typename T>
enable_if_physical_unsigned_integer<T, typename T::c_type> UnboxValue(
const rj::Value& val) {
DCHECK(val.IsUint());
return static_cast<typename T::c_type>(val.GetUint64());
template <typename T, typename CType = typename T::c_type>
enable_if_t<is_physical_integer_type<T>::value && sizeof(CType) == sizeof(int64_t), CType>
UnboxValue(const rj::Value& val) {
DCHECK(val.IsString());

CType out;
bool success = ::arrow::internal::ParseValue<typename CTypeTraits<CType>::ArrowType>(
val.GetString(), val.GetStringLength(), &out);

DCHECK(success);
return out;
}

template <typename T>
Expand Down
8 changes: 8 additions & 0 deletions cpp/src/arrow/type_traits.h
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -646,6 +646,14 @@ template <typename T, typename R = void>
using enable_if_physical_unsigned_integer =
enable_if_t<is_physical_unsigned_integer_type<T>::value, R>;

template <typename T>
using is_physical_integer_type =
std::integral_constant<bool, is_physical_unsigned_integer_type<T>::value ||
is_physical_signed_integer_type<T>::value>;

@kiszkkiszkJun 2, 2020

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.

not sure 100%. but, is this indentation correct?

@bkietzbkietzJun 2, 2020

Copy link
Copy Markdown
MemberAuthor

Choose a reason for hiding this comment

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

C++ indentation is deferred to clang-format. We have a CI job which ensures that running clang-format is a no-op. As for explaining why it made this choice... I'm not familiar enough with its implementation to say, sorry


template <typename T, typename R = void>
using enable_if_physical_integer = enable_if_t<is_physical_integer_type<T>::value, R>;

// Like is_floating_type but excluding half-floats which don't have a
// float-like c type.
template <typename T>
Expand Down
9 changes: 6 additions & 3 deletions cpp/src/arrow/util/formatting.h
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -41,6 +41,9 @@ namespace internal {
template <typename ARROW_TYPE, typename Enable = void>
class StringFormatter;

template <typename Appender>
using Return = decltype(std::declval<Appender>()(util::string_view{}));

template <>
class StringFormatter<BooleanType> {
public:
Expand All@@ -49,7 +52,7 @@ class StringFormatter<BooleanType> {
using value_type = bool;

template <typename Appender>
Status operator()(bool value, Appender&& append) {
Return<Appender> operator()(bool value, Appender&& append) {
if (value) {
const char string[] = "true";
return append(util::string_view(string));
Expand DownExpand Up@@ -95,7 +98,7 @@ class IntToStringFormatterMixin {
(is_signed ? 2 : 1) + std::numeric_limits<value_type>::digits10;

template <typename Appender>
Status operator()(value_type value, Appender&& append) {
Return<Appender> operator()(value_type value, Appender&& append) {
char buffer[buffer_size];
char* ptr = buffer + buffer_size;
int32_t size = 0;
Expand DownExpand Up@@ -206,7 +209,7 @@ class FloatToStringFormatterMixin : public FloatToStringFormatter {
explicit FloatToStringFormatterMixin(const std::shared_ptr<DataType>& = NULLPTR) {}

template <typename Appender>
Status operator()(value_type value, Appender&& append) {
Return<Appender> operator()(value_type value, Appender&& append) {
char buffer[buffer_size];
int size = FormatFloat(value, buffer, buffer_size);
return append(util::string_view(buffer, size));
Expand Down
19 changes: 12 additions & 7 deletions dev/archery/archery/integration/datagen.py
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -176,11 +176,15 @@ def _get_type(self):

def generate_column(self, size, name=None):
lower_bound, upper_bound = self._get_generated_data_bounds()
return self.generate_range(size, lower_bound, upper_bound, name=name)
return self.generate_range(size, lower_bound, upper_bound,
name=name, include_extremes=True)

def generate_range(self, size, lower, upper, name=None):
values = [int(x) for x in
np.random.randint(lower, upper, size=size)]
def generate_range(self, size, lower, upper, name=None,
include_extremes=False):
values = np.random.randint(lower, upper, size=size)
if include_extremes and size >= 2:
values[:2] = [lower, upper]
values = list(map(int if self.bit_width < 64 else str, values))

is_valid = self._make_is_valid(size)

Expand DownExpand Up@@ -1540,9 +1544,10 @@ def _temp_path():
.skip_category('Java') # TODO(ARROW-7779)
.skip_category('JS'),

generate_extension_case().skip_category('Go')
.skip_category('JS')
.skip_category('Rust'),
generate_extension_case()
.skip_category('Go')
.skip_category('JS')
.skip_category('Rust'),
]

if flight:
Expand Down
3 changes: 2 additions & 1 deletion dev/archery/archery/integration/tester_go.py
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -26,7 +26,8 @@ class GoTester(Tester):
CONSUMER = True

# FIXME(sbinet): revisit for Go modules
GOPATH = os.getenv('GOPATH', '~/go')
HOME = os.getenv('HOME', '~')

@fsaintjacquesfsaintjacquesMay 29, 2020

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

Why the change, just set GOPATH if you have something else?

@bkietzbkietzJun 2, 2020

Copy link
Copy Markdown
MemberAuthor

Choose a reason for hiding this comment

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

I don't know why ~ failed resolve to $HOME locally but this seemed like a way to save someone the next person from the frustration of reading the script to figure out that GOPATH needs set.

GOPATH = os.getenv('GOPATH', os.path.join(HOME, 'go'))
GOBIN = os.environ.get('GOBIN', os.path.join(GOPATH, 'bin'))

GO_INTEGRATION_EXE = os.path.join(GOBIN, 'arrow-json-integration-test')
Expand Down
52 changes: 38 additions & 14 deletions go/arrow/internal/arrjson/arrjson.go
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -963,19 +963,23 @@ func i32ToJSON(arr *array.Int32) []interface{} {
func i64FromJSON(vs []interface{}) []int64 {
o := make([]int64, len(vs))
for i, v := range vs {
vv, err := v.(json.Number).Int64()
vv, err := strconv.ParseInt(v.(string), 10, 64)
if err != nil {
panic(err)
}
o[i] = int64(vv)
o[i] = vv
}
return o
}

func i64ToJSON(arr *array.Int64) []interface{} {
o := make([]interface{}, arr.Len())
for i := range o {
o[i] = arr.Value(i)
if arr.IsValid(i) {
o[i] = strconv.FormatInt(arr.Value(i), 10)
} else {
o[i] = "0"
}
}
return o
}
Expand DownExpand Up@@ -1043,19 +1047,23 @@ func u32ToJSON(arr *array.Uint32) []interface{} {
func u64FromJSON(vs []interface{}) []uint64 {
o := make([]uint64, len(vs))
for i, v := range vs {
vv, err := strconv.ParseUint(v.(json.Number).String(), 10, 64)
vv, err := strconv.ParseUint(v.(string), 10, 64)
if err != nil {
panic(err)
}
o[i] = uint64(vv)
o[i] = vv
}
return o
}

func u64ToJSON(arr *array.Uint64) []interface{} {
o := make([]interface{}, arr.Len())
for i := range o {
o[i] = arr.Value(i)
if arr.IsValid(i) {
o[i] = strconv.FormatUint(arr.Value(i), 10)
} else {
o[i] = "0"
}
}
return o
}
Expand DownExpand Up@@ -1193,7 +1201,7 @@ func date32ToJSON(arr *array.Date32) []interface{} {
func date64FromJSON(vs []interface{}) []arrow.Date64 {
o := make([]arrow.Date64, len(vs))
for i, v := range vs {
vv, err := v.(json.Number).Int64()
vv, err := strconv.ParseInt(v.(string), 10, 64)
if err != nil {
panic(err)
}
Expand All@@ -1205,7 +1213,11 @@ func date64FromJSON(vs []interface{}) []arrow.Date64 {
func date64ToJSON(arr *array.Date64) []interface{} {
o := make([]interface{}, arr.Len())
for i := range o {
o[i] = int64(arr.Value(i))
if arr.IsValid(i) {
o[i] = strconv.FormatInt(int64(arr.Value(i)), 10)
} else {
o[i] = "0"
}
}
return o
}
Expand DownExpand Up@@ -1233,7 +1245,7 @@ func time32ToJSON(arr *array.Time32) []interface{} {
func time64FromJSON(vs []interface{}) []arrow.Time64 {
o := make([]arrow.Time64, len(vs))
for i, v := range vs {
vv, err := v.(json.Number).Int64()
vv, err := strconv.ParseInt(v.(string), 10, 64)
if err != nil {
panic(err)
}
Expand All@@ -1245,15 +1257,19 @@ func time64FromJSON(vs []interface{}) []arrow.Time64 {
func time64ToJSON(arr *array.Time64) []interface{} {
o := make([]interface{}, arr.Len())
for i := range o {
o[i] = int64(arr.Value(i))
if arr.IsValid(i) {
o[i] = strconv.FormatInt(int64(arr.Value(i)), 10)
} else {
o[i] = "0"
}
}
return o
}

func timestampFromJSON(vs []interface{}) []arrow.Timestamp {
o := make([]arrow.Timestamp, len(vs))
for i, v := range vs {
vv, err := v.(json.Number).Int64()
vv, err := strconv.ParseInt(v.(string), 10, 64)
if err != nil {
panic(err)
}
Expand All@@ -1265,7 +1281,11 @@ func timestampFromJSON(vs []interface{}) []arrow.Timestamp {
func timestampToJSON(arr *array.Timestamp) []interface{} {
o := make([]interface{}, arr.Len())
for i := range o {
o[i] = int64(arr.Value(i))
if arr.IsValid(i) {
o[i] = strconv.FormatInt(int64(arr.Value(i)), 10)
} else {
o[i] = "0"
}
}
return o
}
Expand DownExpand Up@@ -1318,7 +1338,7 @@ func daytimeintervalToJSON(arr *array.DayTimeInterval) []interface{} {
func durationFromJSON(vs []interface{}) []arrow.Duration {
o := make([]arrow.Duration, len(vs))
for i, v := range vs {
vv, err := v.(json.Number).Int64()
vv, err := strconv.ParseInt(v.(string), 10, 64)
if err != nil {
panic(err)
}
Expand All@@ -1330,7 +1350,11 @@ func durationFromJSON(vs []interface{}) []arrow.Duration {
func durationToJSON(arr *array.Duration) []interface{} {
o := make([]interface{}, arr.Len())
for i := range o {
o[i] = arr.Value(i)
if arr.IsValid(i) {
o[i] = strconv.FormatInt(int64(arr.Value(i)), 10)
} else {
o[i] = "0"
}
}
return o
}
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-8471: [C++][Integration] Represent 64 bit integers as strings#7292

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

bkietz
wants to merge
6
commits into

from

 Closed


ARROW-8471: [C++][Integration] Represent 64 bit integers as strings
#7292
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


6 commits


Select commit
Hold shift + click to select a range
e14f60a

ARROW-8471: [C++][Integration] Represent 64 bit integers as strings


bkietz May 27, 2020
47ce0f8

refactor Go to emit and expect 64 bit ints as strings


bkietz May 27, 2020
2e97dff

also adjust duration and date in Go


bkietz May 28, 2020
dbdd293

emit '0' in null slots


bkietz May 28, 2020
bf37227

add extremes to integer ranges


bkietz Jun 2, 2020
1ec2517

repair go indentation


bkietz Jun 2, 2020

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: 3 additions & 3 deletions
cpp/src/arrow/ipc/json_integration_test.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -255,7 +255,7 @@ static const char* JSON_EXAMPLE = R"example(
 "fields": [
 {
 "name": "foo",
 "type": {"name": "int", "isSigned": true, "bitWidth": 32},
 "type": {"name": "int", "isSigned": true, "bitWidth": 64},
Comment thread
fsaintjacques marked this conversation as resolved.


Outdated

 "nullable": true, "children": []
 },
 {
Expand All@@ -272,7 +272,7 @@ static const char* JSON_EXAMPLE = R"example(
 {
 "name": "foo",
 "count": 5,
 "DATA": [1, 2, 3, 4, 5],
 "DATA": ["1", "2", "3", "4", "5"],
Comment thread
bkietz marked this conversation as resolved.


Outdated

 "VALIDITY": [1, 0, 1, 1, 1]
 },
 {
Expand All@@ -289,7 +289,7 @@ static const char* JSON_EXAMPLE = R"example(
 {
 "name": "foo",
 "count": 4,
 "DATA": [1, 2, 3, 4],
 "DATA": ["-1", "0", "9223372036854775807", "-9223372036854775808"],
 "VALIDITY": [1, 0, 1, 1]
 },
 {
Expand Down

63 changes: 39 additions & 24 deletions
cpp/src/arrow/ipc/json_internal.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -19,6 +19,7 @@

#include <cstdint>
#include <cstdlib>
#include <iostream>
#include <memory>
#include <string>
#include <type_traits>
Expand DownExpand Up@@ -440,29 +441,37 @@ class ArrayWriter {
 return Status::OK();
 }

 template <typename T, bool IsSigned = std::is_signed<typename T::value_type>::value>
 void WriteIntegerDataValues(const T& arr) {
 static const char null_string[] = "0";
 const auto data = arr.raw_values();
 template <typename ArrayType, typename TypeClass = typename ArrayType::TypeClass,
 typename CType = typename TypeClass::c_type>
 enable_if_t<is_physical_integer_type<TypeClass>::value &&
 sizeof(CType) != sizeof(int64_t)>
 WriteDataValues(const ArrayType& arr) {
 static const std::string null_string = "0";
 for (int64_t i = 0; i < arr.length(); ++i) {
 if (arr.IsValid(i)) {
IsSigned ? writer_->Int64(data[i]) : writer_->Uint64(data[i]);
 writer_->Int64(arr.Value(i));
 } else {
 writer_->RawNumber(null_string, sizeof(null_string));
 writer_->RawNumber(null_string.data(), null_string.size());
 }
 }
 }

 template <typename ArrayType>
 enable_if_physical_signed_integer<typename ArrayType::TypeClass> WriteDataValues(
 const ArrayType& arr) {
 WriteIntegerDataValues<ArrayType>(arr);
 }
 template <typename ArrayType, typename TypeClass = typename ArrayType::TypeClass,
 typename CType = typename TypeClass::c_type>
 enable_if_t<is_physical_integer_type<TypeClass>::value &&
 sizeof(CType) == sizeof(int64_t)>
 WriteDataValues(const ArrayType& arr) {
 ::arrow::internal::StringFormatter<typename CTypeTraits<CType>::ArrowType> fmt;

 template <typename ArrayType>
 enable_if_physical_unsigned_integer<typename ArrayType::TypeClass> WriteDataValues(
 const ArrayType& arr) {
 WriteIntegerDataValues<ArrayType>(arr);
 static const std::string null_string = "0";
 for (int64_t i = 0; i < arr.length(); ++i) {
 if (arr.IsValid(i)) {
 fmt(arr.Value(i),
 [&](util::string_view repr) { writer_->String(repr.data(), repr.size()); });
 } else {
 writer_->String(null_string.data(), null_string.size());
 }
 }
 }

 template <typename ArrayType>
Expand DownExpand Up@@ -1154,18 +1163,24 @@ enable_if_boolean<T, bool> UnboxValue(const rj::Value& val) {
 return val.GetBool();
}

template <typename T>
enable_if_physical_signed_integer<T, typename T::c_type> UnboxValue(
const rj::Value& val) {
template <typename T, typename CType = typename T::c_type>
enable_if_t<is_physical_integer_type<T>::value && sizeof(CType) != sizeof(int64_t), CType>
UnboxValue(const rj::Value& val) {
 DCHECK(val.IsInt64());
 return static_cast<typename T::c_type>(val.GetInt64());
 return static_cast<CType>(val.GetInt64());
}

template <typename T>
enable_if_physical_unsigned_integer<T, typename T::c_type> UnboxValue(
 const rj::Value& val) {
 DCHECK(val.IsUint());
 return static_cast<typename T::c_type>(val.GetUint64());
template <typename T, typename CType = typename T::c_type>
enable_if_t<is_physical_integer_type<T>::value && sizeof(CType) == sizeof(int64_t), CType>
UnboxValue(const rj::Value& val) {
 DCHECK(val.IsString());

 CType out;
 bool success = ::arrow::internal::ParseValue<typename CTypeTraits<CType>::ArrowType>(
 val.GetString(), val.GetStringLength(), &out);

 DCHECK(success);
 return out;
}

template <typename T>
Expand Down

8 changes: 8 additions & 0 deletions
cpp/src/arrow/type_traits.h

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -646,6 +646,14 @@ template <typename T, typename R = void>
using enable_if_physical_unsigned_integer =
 enable_if_t<is_physical_unsigned_integer_type<T>::value, R>;

template <typename T>
using is_physical_integer_type =
 std::integral_constant<bool, is_physical_unsigned_integer_type<T>::value ||
 is_physical_signed_integer_type<T>::value>;
@kiszkkiszkJun 2, 2020

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.

not sure 100%. but, is this indentation correct?
@bkietzbkietzJun 2, 2020

Copy link


Copy Markdown

MemberAuthor
Choose a reason for hiding this comment

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

C++ indentation is deferred to clang-format. We have a CI job which ensures that running clang-format is a no-op. As for explaining why it made this choice... I'm not familiar enough with its implementation to say, sorry

template <typename T, typename R = void>
using enable_if_physical_integer = enable_if_t<is_physical_integer_type<T>::value, R>;

// Like is_floating_type but excluding half-floats which don't have a
// float-like c type.
template <typename T>
Expand Down

9 changes: 6 additions & 3 deletions
cpp/src/arrow/util/formatting.h

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -41,6 +41,9 @@ namespace internal {
template <typename ARROW_TYPE, typename Enable = void>
class StringFormatter;

template <typename Appender>
using Return = decltype(std::declval<Appender>()(util::string_view{}));

template <>
class StringFormatter<BooleanType> {
 public:
Expand All@@ -49,7 +52,7 @@ class StringFormatter<BooleanType> {
 using value_type = bool;

 template <typename Appender>
Status operator()(bool value, Appender&& append) {
Return<Appender> operator()(bool value, Appender&& append) {
 if (value) {
 const char string[] = "true";
 return append(util::string_view(string));
Expand DownExpand Up@@ -95,7 +98,7 @@ class IntToStringFormatterMixin {
 (is_signed ? 2 : 1) + std::numeric_limits<value_type>::digits10;

 template <typename Appender>
Status operator()(value_type value, Appender&& append) {
Return<Appender> operator()(value_type value, Appender&& append) {
 char buffer[buffer_size];
 char* ptr = buffer + buffer_size;
 int32_t size = 0;
Expand DownExpand Up@@ -206,7 +209,7 @@ class FloatToStringFormatterMixin : public FloatToStringFormatter {
 explicit FloatToStringFormatterMixin(const std::shared_ptr<DataType>& = NULLPTR) {}

 template <typename Appender>
Status operator()(value_type value, Appender&& append) {
Return<Appender> operator()(value_type value, Appender&& append) {
 char buffer[buffer_size];
 int size = FormatFloat(value, buffer, buffer_size);
 return append(util::string_view(buffer, size));
Expand Down

19 changes: 12 additions & 7 deletions
dev/archery/archery/integration/datagen.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -176,11 +176,15 @@ def _get_type(self):

 def generate_column(self, size, name=None):
 lower_bound, upper_bound = self._get_generated_data_bounds()
 return self.generate_range(size, lower_bound, upper_bound, name=name)
 return self.generate_range(size, lower_bound, upper_bound,
 name=name, include_extremes=True)

 def generate_range(self, size, lower, upper, name=None):
 values = [int(x) for x in
 np.random.randint(lower, upper, size=size)]
 def generate_range(self, size, lower, upper, name=None,
 include_extremes=False):
 values = np.random.randint(lower, upper, size=size)
 if include_extremes and size >= 2:
 values[:2] = [lower, upper]
 values = list(map(int if self.bit_width < 64 else str, values))

 is_valid = self._make_is_valid(size)

Expand DownExpand Up@@ -1540,9 +1544,10 @@ def _temp_path():
 .skip_category('Java') # TODO(ARROW-7779)
 .skip_category('JS'),

 generate_extension_case().skip_category('Go')
 .skip_category('JS')
 .skip_category('Rust'),
 generate_extension_case()
 .skip_category('Go')
 .skip_category('JS')
 .skip_category('Rust'),
 ]

 if flight:
Expand Down

3 changes: 2 additions & 1 deletion
dev/archery/archery/integration/tester_go.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -26,7 +26,8 @@ class GoTester(Tester):
 CONSUMER = True

 # FIXME(sbinet): revisit for Go modules
 GOPATH = os.getenv('GOPATH', '~/go')
 HOME = os.getenv('HOME', '~')
@fsaintjacquesfsaintjacquesMay 29, 2020

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

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

Why the change, just set GOPATH if you have something else?
@bkietzbkietzJun 2, 2020

Copy link


Copy Markdown

MemberAuthor
Choose a reason for hiding this comment

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

I don't know why ~ failed resolve to $HOME locally but this seemed like a way to save someone the next person from the frustration of reading the script to figure out that GOPATH needs set.
 GOPATH = os.getenv('GOPATH', os.path.join(HOME, 'go'))
 GOBIN = os.environ.get('GOBIN', os.path.join(GOPATH, 'bin'))

 GO_INTEGRATION_EXE = os.path.join(GOBIN, 'arrow-json-integration-test')
Expand Down

52 changes: 38 additions & 14 deletions
go/arrow/internal/arrjson/arrjson.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -963,19 +963,23 @@ func i32ToJSON(arr *array.Int32) []interface{} {
func i64FromJSON(vs []interface{}) []int64 {
	o := make([]int64, len(vs))
	for i, v := range vs {
 vv, err := v.(json.Number).Int64()
 vv, err := strconv.ParseInt(v.(string), 10, 64)
 if err != nil {
 panic(err)
 }
 o[i] = int64(vv)
 o[i] = vv
	}
	return o
}

func i64ToJSON(arr *array.Int64) []interface{} {
	o := make([]interface{}, arr.Len())
	for i := range o {
 o[i] = arr.Value(i)
 if arr.IsValid(i) {
 o[i] = strconv.FormatInt(arr.Value(i), 10)
 } else {
 o[i] = "0"
 }
	}
	return o
}
Expand DownExpand Up@@ -1043,19 +1047,23 @@ func u32ToJSON(arr *array.Uint32) []interface{} {
func u64FromJSON(vs []interface{}) []uint64 {
	o := make([]uint64, len(vs))
	for i, v := range vs {
 vv, err := strconv.ParseUint(v.(json.Number).String(), 10, 64)
 vv, err := strconv.ParseUint(v.(string), 10, 64)
 if err != nil {
 panic(err)
 }
 o[i] = uint64(vv)
 o[i] = vv
	}
	return o
}

func u64ToJSON(arr *array.Uint64) []interface{} {
	o := make([]interface{}, arr.Len())
	for i := range o {
 o[i] = arr.Value(i)
 if arr.IsValid(i) {
 o[i] = strconv.FormatUint(arr.Value(i), 10)
 } else {
 o[i] = "0"
 }
	}
	return o
}
Expand DownExpand Up@@ -1193,7 +1201,7 @@ func date32ToJSON(arr *array.Date32) []interface{} {
func date64FromJSON(vs []interface{}) []arrow.Date64 {
	o := make([]arrow.Date64, len(vs))
	for i, v := range vs {
 vv, err := v.(json.Number).Int64()
 vv, err := strconv.ParseInt(v.(string), 10, 64)
 if err != nil {
 panic(err)
 }
Expand All@@ -1205,7 +1213,11 @@ func date64FromJSON(vs []interface{}) []arrow.Date64 {
func date64ToJSON(arr *array.Date64) []interface{} {
	o := make([]interface{}, arr.Len())
	for i := range o {
 o[i] = int64(arr.Value(i))
 if arr.IsValid(i) {
 o[i] = strconv.FormatInt(int64(arr.Value(i)), 10)
 } else {
 o[i] = "0"
 }
	}
	return o
}
Expand DownExpand Up@@ -1233,7 +1245,7 @@ func time32ToJSON(arr *array.Time32) []interface{} {
func time64FromJSON(vs []interface{}) []arrow.Time64 {
	o := make([]arrow.Time64, len(vs))
	for i, v := range vs {
 vv, err := v.(json.Number).Int64()
 vv, err := strconv.ParseInt(v.(string), 10, 64)
 if err != nil {
 panic(err)
 }
Expand All@@ -1245,15 +1257,19 @@ func time64FromJSON(vs []interface{}) []arrow.Time64 {
func time64ToJSON(arr *array.Time64) []interface{} {
	o := make([]interface{}, arr.Len())
	for i := range o {
 o[i] = int64(arr.Value(i))
 if arr.IsValid(i) {
 o[i] = strconv.FormatInt(int64(arr.Value(i)), 10)
 } else {
 o[i] = "0"
 }
	}
	return o
}

func timestampFromJSON(vs []interface{}) []arrow.Timestamp {
	o := make([]arrow.Timestamp, len(vs))
	for i, v := range vs {
 vv, err := v.(json.Number).Int64()
 vv, err := strconv.ParseInt(v.(string), 10, 64)
 if err != nil {
 panic(err)
 }
Expand All@@ -1265,7 +1281,11 @@ func timestampFromJSON(vs []interface{}) []arrow.Timestamp {
func timestampToJSON(arr *array.Timestamp) []interface{} {
	o := make([]interface{}, arr.Len())
	for i := range o {
 o[i] = int64(arr.Value(i))
 if arr.IsValid(i) {
 o[i] = strconv.FormatInt(int64(arr.Value(i)), 10)
 } else {
 o[i] = "0"
 }
	}
	return o
}
Expand DownExpand Up@@ -1318,7 +1338,7 @@ func daytimeintervalToJSON(arr *array.DayTimeInterval) []interface{} {
func durationFromJSON(vs []interface{}) []arrow.Duration {
	o := make([]arrow.Duration, len(vs))
	for i, v := range vs {
 vv, err := v.(json.Number).Int64()
 vv, err := strconv.ParseInt(v.(string), 10, 64)
 if err != nil {
 panic(err)
 }
Expand All@@ -1330,7 +1350,11 @@ func durationFromJSON(vs []interface{}) []arrow.Duration {
func durationToJSON(arr *array.Duration) []interface{} {
	o := make([]interface{}, arr.Len())
	for i := range o {
 o[i] = arr.Value(i)
 if arr.IsValid(i) {
 o[i] = strconv.FormatInt(int64(arr.Value(i)), 10)
 } else {
 o[i] = "0"
 }
	}
	return o
}
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-8471: [C++][Integration] Represent 64 bit integers as strings#7292

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

bkietz
wants to merge
6
commits into

from

 Closed


ARROW-8471: [C++][Integration] Represent 64 bit integers as strings
#7292
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


6 commits


Select commit
Hold shift + click to select a range
e14f60a

ARROW-8471: [C++][Integration] Represent 64 bit integers as strings


bkietz May 27, 2020
47ce0f8

refactor Go to emit and expect 64 bit ints as strings


bkietz May 27, 2020
2e97dff

also adjust duration and date in Go


bkietz May 28, 2020
dbdd293

emit '0' in null slots


bkietz May 28, 2020
bf37227

add extremes to integer ranges


bkietz Jun 2, 2020
1ec2517

repair go indentation


bkietz Jun 2, 2020

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: 3 additions & 3 deletions
cpp/src/arrow/ipc/json_integration_test.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -255,7 +255,7 @@ static const char* JSON_EXAMPLE = R"example(
 "fields": [
 {
 "name": "foo",
 "type": {"name": "int", "isSigned": true, "bitWidth": 32},
 "type": {"name": "int", "isSigned": true, "bitWidth": 64},
Comment thread
fsaintjacques marked this conversation as resolved.


Outdated

 "nullable": true, "children": []
 },
 {
Expand All@@ -272,7 +272,7 @@ static const char* JSON_EXAMPLE = R"example(
 {
 "name": "foo",
 "count": 5,
 "DATA": [1, 2, 3, 4, 5],
 "DATA": ["1", "2", "3", "4", "5"],
Comment thread
bkietz marked this conversation as resolved.


Outdated

 "VALIDITY": [1, 0, 1, 1, 1]
 },
 {
Expand All@@ -289,7 +289,7 @@ static const char* JSON_EXAMPLE = R"example(
 {
 "name": "foo",
 "count": 4,
 "DATA": [1, 2, 3, 4],
 "DATA": ["-1", "0", "9223372036854775807", "-9223372036854775808"],
 "VALIDITY": [1, 0, 1, 1]
 },
 {
Expand Down

63 changes: 39 additions & 24 deletions
cpp/src/arrow/ipc/json_internal.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -19,6 +19,7 @@

#include <cstdint>
#include <cstdlib>
#include <iostream>
#include <memory>
#include <string>
#include <type_traits>
Expand DownExpand Up@@ -440,29 +441,37 @@ class ArrayWriter {
 return Status::OK();
 }

 template <typename T, bool IsSigned = std::is_signed<typename T::value_type>::value>
 void WriteIntegerDataValues(const T& arr) {
 static const char null_string[] = "0";
 const auto data = arr.raw_values();
 template <typename ArrayType, typename TypeClass = typename ArrayType::TypeClass,
 typename CType = typename TypeClass::c_type>
 enable_if_t<is_physical_integer_type<TypeClass>::value &&
 sizeof(CType) != sizeof(int64_t)>
 WriteDataValues(const ArrayType& arr) {
 static const std::string null_string = "0";
 for (int64_t i = 0; i < arr.length(); ++i) {
 if (arr.IsValid(i)) {
IsSigned ? writer_->Int64(data[i]) : writer_->Uint64(data[i]);
 writer_->Int64(arr.Value(i));
 } else {
 writer_->RawNumber(null_string, sizeof(null_string));
 writer_->RawNumber(null_string.data(), null_string.size());
 }
 }
 }

 template <typename ArrayType>
 enable_if_physical_signed_integer<typename ArrayType::TypeClass> WriteDataValues(
 const ArrayType& arr) {
 WriteIntegerDataValues<ArrayType>(arr);
 }
 template <typename ArrayType, typename TypeClass = typename ArrayType::TypeClass,
 typename CType = typename TypeClass::c_type>
 enable_if_t<is_physical_integer_type<TypeClass>::value &&
 sizeof(CType) == sizeof(int64_t)>
 WriteDataValues(const ArrayType& arr) {
 ::arrow::internal::StringFormatter<typename CTypeTraits<CType>::ArrowType> fmt;

 template <typename ArrayType>
 enable_if_physical_unsigned_integer<typename ArrayType::TypeClass> WriteDataValues(
 const ArrayType& arr) {
 WriteIntegerDataValues<ArrayType>(arr);
 static const std::string null_string = "0";
 for (int64_t i = 0; i < arr.length(); ++i) {
 if (arr.IsValid(i)) {
 fmt(arr.Value(i),
 [&](util::string_view repr) { writer_->String(repr.data(), repr.size()); });
 } else {
 writer_->String(null_string.data(), null_string.size());
 }
 }
 }

 template <typename ArrayType>
Expand DownExpand Up@@ -1154,18 +1163,24 @@ enable_if_boolean<T, bool> UnboxValue(const rj::Value& val) {
 return val.GetBool();
}

template <typename T>
enable_if_physical_signed_integer<T, typename T::c_type> UnboxValue(
const rj::Value& val) {
template <typename T, typename CType = typename T::c_type>
enable_if_t<is_physical_integer_type<T>::value && sizeof(CType) != sizeof(int64_t), CType>
UnboxValue(const rj::Value& val) {
 DCHECK(val.IsInt64());
 return static_cast<typename T::c_type>(val.GetInt64());
 return static_cast<CType>(val.GetInt64());
}

template <typename T>
enable_if_physical_unsigned_integer<T, typename T::c_type> UnboxValue(
 const rj::Value& val) {
 DCHECK(val.IsUint());
 return static_cast<typename T::c_type>(val.GetUint64());
template <typename T, typename CType = typename T::c_type>
enable_if_t<is_physical_integer_type<T>::value && sizeof(CType) == sizeof(int64_t), CType>
UnboxValue(const rj::Value& val) {
 DCHECK(val.IsString());

 CType out;
 bool success = ::arrow::internal::ParseValue<typename CTypeTraits<CType>::ArrowType>(
 val.GetString(), val.GetStringLength(), &out);

 DCHECK(success);
 return out;
}

template <typename T>
Expand Down

8 changes: 8 additions & 0 deletions
cpp/src/arrow/type_traits.h

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -646,6 +646,14 @@ template <typename T, typename R = void>
using enable_if_physical_unsigned_integer =
 enable_if_t<is_physical_unsigned_integer_type<T>::value, R>;

template <typename T>
using is_physical_integer_type =
 std::integral_constant<bool, is_physical_unsigned_integer_type<T>::value ||
 is_physical_signed_integer_type<T>::value>;
@kiszkkiszkJun 2, 2020

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.

not sure 100%. but, is this indentation correct?
@bkietzbkietzJun 2, 2020

Copy link


Copy Markdown

MemberAuthor
Choose a reason for hiding this comment

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

C++ indentation is deferred to clang-format. We have a CI job which ensures that running clang-format is a no-op. As for explaining why it made this choice... I'm not familiar enough with its implementation to say, sorry

template <typename T, typename R = void>
using enable_if_physical_integer = enable_if_t<is_physical_integer_type<T>::value, R>;

// Like is_floating_type but excluding half-floats which don't have a
// float-like c type.
template <typename T>
Expand Down

9 changes: 6 additions & 3 deletions
cpp/src/arrow/util/formatting.h

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -41,6 +41,9 @@ namespace internal {
template <typename ARROW_TYPE, typename Enable = void>
class StringFormatter;

template <typename Appender>
using Return = decltype(std::declval<Appender>()(util::string_view{}));

template <>
class StringFormatter<BooleanType> {
 public:
Expand All@@ -49,7 +52,7 @@ class StringFormatter<BooleanType> {
 using value_type = bool;

 template <typename Appender>
Status operator()(bool value, Appender&& append) {
Return<Appender> operator()(bool value, Appender&& append) {
 if (value) {
 const char string[] = "true";
 return append(util::string_view(string));
Expand DownExpand Up@@ -95,7 +98,7 @@ class IntToStringFormatterMixin {
 (is_signed ? 2 : 1) + std::numeric_limits<value_type>::digits10;

 template <typename Appender>
Status operator()(value_type value, Appender&& append) {
Return<Appender> operator()(value_type value, Appender&& append) {
 char buffer[buffer_size];
 char* ptr = buffer + buffer_size;
 int32_t size = 0;
Expand DownExpand Up@@ -206,7 +209,7 @@ class FloatToStringFormatterMixin : public FloatToStringFormatter {
 explicit FloatToStringFormatterMixin(const std::shared_ptr<DataType>& = NULLPTR) {}

 template <typename Appender>
Status operator()(value_type value, Appender&& append) {
Return<Appender> operator()(value_type value, Appender&& append) {
 char buffer[buffer_size];
 int size = FormatFloat(value, buffer, buffer_size);
 return append(util::string_view(buffer, size));
Expand Down

19 changes: 12 additions & 7 deletions
dev/archery/archery/integration/datagen.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -176,11 +176,15 @@ def _get_type(self):

 def generate_column(self, size, name=None):
 lower_bound, upper_bound = self._get_generated_data_bounds()
 return self.generate_range(size, lower_bound, upper_bound, name=name)
 return self.generate_range(size, lower_bound, upper_bound,
 name=name, include_extremes=True)

 def generate_range(self, size, lower, upper, name=None):
 values = [int(x) for x in
 np.random.randint(lower, upper, size=size)]
 def generate_range(self, size, lower, upper, name=None,
 include_extremes=False):
 values = np.random.randint(lower, upper, size=size)
 if include_extremes and size >= 2:
 values[:2] = [lower, upper]
 values = list(map(int if self.bit_width < 64 else str, values))

 is_valid = self._make_is_valid(size)

Expand DownExpand Up@@ -1540,9 +1544,10 @@ def _temp_path():
 .skip_category('Java') # TODO(ARROW-7779)
 .skip_category('JS'),

 generate_extension_case().skip_category('Go')
 .skip_category('JS')
 .skip_category('Rust'),
 generate_extension_case()
 .skip_category('Go')
 .skip_category('JS')
 .skip_category('Rust'),
 ]

 if flight:
Expand Down

3 changes: 2 additions & 1 deletion
dev/archery/archery/integration/tester_go.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -26,7 +26,8 @@ class GoTester(Tester):
 CONSUMER = True

 # FIXME(sbinet): revisit for Go modules
 GOPATH = os.getenv('GOPATH', '~/go')
 HOME = os.getenv('HOME', '~')
@fsaintjacquesfsaintjacquesMay 29, 2020

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

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

Why the change, just set GOPATH if you have something else?
@bkietzbkietzJun 2, 2020

Copy link


Copy Markdown

MemberAuthor
Choose a reason for hiding this comment

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

I don't know why ~ failed resolve to $HOME locally but this seemed like a way to save someone the next person from the frustration of reading the script to figure out that GOPATH needs set.
 GOPATH = os.getenv('GOPATH', os.path.join(HOME, 'go'))
 GOBIN = os.environ.get('GOBIN', os.path.join(GOPATH, 'bin'))

 GO_INTEGRATION_EXE = os.path.join(GOBIN, 'arrow-json-integration-test')
Expand Down

52 changes: 38 additions & 14 deletions
go/arrow/internal/arrjson/arrjson.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -963,19 +963,23 @@ func i32ToJSON(arr *array.Int32) []interface{} {
func i64FromJSON(vs []interface{}) []int64 {
	o := make([]int64, len(vs))
	for i, v := range vs {
 vv, err := v.(json.Number).Int64()
 vv, err := strconv.ParseInt(v.(string), 10, 64)
 if err != nil {
 panic(err)
 }
 o[i] = int64(vv)
 o[i] = vv
	}
	return o
}

func i64ToJSON(arr *array.Int64) []interface{} {
	o := make([]interface{}, arr.Len())
	for i := range o {
 o[i] = arr.Value(i)
 if arr.IsValid(i) {
 o[i] = strconv.FormatInt(arr.Value(i), 10)
 } else {
 o[i] = "0"
 }
	}
	return o
}
Expand DownExpand Up@@ -1043,19 +1047,23 @@ func u32ToJSON(arr *array.Uint32) []interface{} {
func u64FromJSON(vs []interface{}) []uint64 {
	o := make([]uint64, len(vs))
	for i, v := range vs {
 vv, err := strconv.ParseUint(v.(json.Number).String(), 10, 64)
 vv, err := strconv.ParseUint(v.(string), 10, 64)
 if err != nil {
 panic(err)
 }
 o[i] = uint64(vv)
 o[i] = vv
	}
	return o
}

func u64ToJSON(arr *array.Uint64) []interface{} {
	o := make([]interface{}, arr.Len())
	for i := range o {
 o[i] = arr.Value(i)
 if arr.IsValid(i) {
 o[i] = strconv.FormatUint(arr.Value(i), 10)
 } else {
 o[i] = "0"
 }
	}
	return o
}
Expand DownExpand Up@@ -1193,7 +1201,7 @@ func date32ToJSON(arr *array.Date32) []interface{} {
func date64FromJSON(vs []interface{}) []arrow.Date64 {
	o := make([]arrow.Date64, len(vs))
	for i, v := range vs {
 vv, err := v.(json.Number).Int64()
 vv, err := strconv.ParseInt(v.(string), 10, 64)
 if err != nil {
 panic(err)
 }
Expand All@@ -1205,7 +1213,11 @@ func date64FromJSON(vs []interface{}) []arrow.Date64 {
func date64ToJSON(arr *array.Date64) []interface{} {
	o := make([]interface{}, arr.Len())
	for i := range o {
 o[i] = int64(arr.Value(i))
 if arr.IsValid(i) {
 o[i] = strconv.FormatInt(int64(arr.Value(i)), 10)
 } else {
 o[i] = "0"
 }
	}
	return o
}
Expand DownExpand Up@@ -1233,7 +1245,7 @@ func time32ToJSON(arr *array.Time32) []interface{} {
func time64FromJSON(vs []interface{}) []arrow.Time64 {
	o := make([]arrow.Time64, len(vs))
	for i, v := range vs {
 vv, err := v.(json.Number).Int64()
 vv, err := strconv.ParseInt(v.(string), 10, 64)
 if err != nil {
 panic(err)
 }
Expand All@@ -1245,15 +1257,19 @@ func time64FromJSON(vs []interface{}) []arrow.Time64 {
func time64ToJSON(arr *array.Time64) []interface{} {
	o := make([]interface{}, arr.Len())
	for i := range o {
 o[i] = int64(arr.Value(i))
 if arr.IsValid(i) {
 o[i] = strconv.FormatInt(int64(arr.Value(i)), 10)
 } else {
 o[i] = "0"
 }
	}
	return o
}

func timestampFromJSON(vs []interface{}) []arrow.Timestamp {
	o := make([]arrow.Timestamp, len(vs))
	for i, v := range vs {
 vv, err := v.(json.Number).Int64()
 vv, err := strconv.ParseInt(v.(string), 10, 64)
 if err != nil {
 panic(err)
 }
Expand All@@ -1265,7 +1281,11 @@ func timestampFromJSON(vs []interface{}) []arrow.Timestamp {
func timestampToJSON(arr *array.Timestamp) []interface{} {
	o := make([]interface{}, arr.Len())
	for i := range o {
 o[i] = int64(arr.Value(i))
 if arr.IsValid(i) {
 o[i] = strconv.FormatInt(int64(arr.Value(i)), 10)
 } else {
 o[i] = "0"
 }
	}
	return o
}
Expand DownExpand Up@@ -1318,7 +1338,7 @@ func daytimeintervalToJSON(arr *array.DayTimeInterval) []interface{} {
func durationFromJSON(vs []interface{}) []arrow.Duration {
	o := make([]arrow.Duration, len(vs))
	for i, v := range vs {
 vv, err := v.(json.Number).Int64()
 vv, err := strconv.ParseInt(v.(string), 10, 64)
 if err != nil {
 panic(err)
 }
Expand All@@ -1330,7 +1350,11 @@ func durationFromJSON(vs []interface{}) []arrow.Duration {
func durationToJSON(arr *array.Duration) []interface{} {
	o := make([]interface{}, arr.Len())
	for i := range o {
 o[i] = arr.Value(i)
 if arr.IsValid(i) {
 o[i] = strconv.FormatInt(int64(arr.Value(i)), 10)
 } else {
 o[i] = "0"
 }
	}
	return o
}
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-8471: [C++][Integration] Represent 64 bit integers as strings#7292

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

bkietz
wants to merge
6
commits into

from

 Closed


ARROW-8471: [C++][Integration] Represent 64 bit integers as strings
#7292
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


6 commits


Select commit
Hold shift + click to select a range
e14f60a

ARROW-8471: [C++][Integration] Represent 64 bit integers as strings


bkietz May 27, 2020
47ce0f8

refactor Go to emit and expect 64 bit ints as strings


bkietz May 27, 2020
2e97dff

also adjust duration and date in Go


bkietz May 28, 2020
dbdd293

emit '0' in null slots


bkietz May 28, 2020
bf37227

add extremes to integer ranges


bkietz Jun 2, 2020
1ec2517

repair go indentation


bkietz Jun 2, 2020

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: 3 additions & 3 deletions
cpp/src/arrow/ipc/json_integration_test.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -255,7 +255,7 @@ static const char* JSON_EXAMPLE = R"example(
 "fields": [
 {
 "name": "foo",
 "type": {"name": "int", "isSigned": true, "bitWidth": 32},
 "type": {"name": "int", "isSigned": true, "bitWidth": 64},
Comment thread
fsaintjacques marked this conversation as resolved.


Outdated

 "nullable": true, "children": []
 },
 {
Expand All@@ -272,7 +272,7 @@ static const char* JSON_EXAMPLE = R"example(
 {
 "name": "foo",
 "count": 5,
 "DATA": [1, 2, 3, 4, 5],
 "DATA": ["1", "2", "3", "4", "5"],
Comment thread
bkietz marked this conversation as resolved.


Outdated

 "VALIDITY": [1, 0, 1, 1, 1]
 },
 {
Expand All@@ -289,7 +289,7 @@ static const char* JSON_EXAMPLE = R"example(
 {
 "name": "foo",
 "count": 4,
 "DATA": [1, 2, 3, 4],
 "DATA": ["-1", "0", "9223372036854775807", "-9223372036854775808"],
 "VALIDITY": [1, 0, 1, 1]
 },
 {
Expand Down

63 changes: 39 additions & 24 deletions
cpp/src/arrow/ipc/json_internal.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -19,6 +19,7 @@

#include <cstdint>
#include <cstdlib>
#include <iostream>
#include <memory>
#include <string>
#include <type_traits>
Expand DownExpand Up@@ -440,29 +441,37 @@ class ArrayWriter {
 return Status::OK();
 }

 template <typename T, bool IsSigned = std::is_signed<typename T::value_type>::value>
 void WriteIntegerDataValues(const T& arr) {
 static const char null_string[] = "0";
 const auto data = arr.raw_values();
 template <typename ArrayType, typename TypeClass = typename ArrayType::TypeClass,
 typename CType = typename TypeClass::c_type>
 enable_if_t<is_physical_integer_type<TypeClass>::value &&
 sizeof(CType) != sizeof(int64_t)>
 WriteDataValues(const ArrayType& arr) {
 static const std::string null_string = "0";
 for (int64_t i = 0; i < arr.length(); ++i) {
 if (arr.IsValid(i)) {
IsSigned ? writer_->Int64(data[i]) : writer_->Uint64(data[i]);
 writer_->Int64(arr.Value(i));
 } else {
 writer_->RawNumber(null_string, sizeof(null_string));
 writer_->RawNumber(null_string.data(), null_string.size());
 }
 }
 }

 template <typename ArrayType>
 enable_if_physical_signed_integer<typename ArrayType::TypeClass> WriteDataValues(
 const ArrayType& arr) {
 WriteIntegerDataValues<ArrayType>(arr);
 }
 template <typename ArrayType, typename TypeClass = typename ArrayType::TypeClass,
 typename CType = typename TypeClass::c_type>
 enable_if_t<is_physical_integer_type<TypeClass>::value &&
 sizeof(CType) == sizeof(int64_t)>
 WriteDataValues(const ArrayType& arr) {
 ::arrow::internal::StringFormatter<typename CTypeTraits<CType>::ArrowType> fmt;

 template <typename ArrayType>
 enable_if_physical_unsigned_integer<typename ArrayType::TypeClass> WriteDataValues(
 const ArrayType& arr) {
 WriteIntegerDataValues<ArrayType>(arr);
 static const std::string null_string = "0";
 for (int64_t i = 0; i < arr.length(); ++i) {
 if (arr.IsValid(i)) {
 fmt(arr.Value(i),
 [&](util::string_view repr) { writer_->String(repr.data(), repr.size()); });
 } else {
 writer_->String(null_string.data(), null_string.size());
 }
 }
 }

 template <typename ArrayType>
Expand DownExpand Up@@ -1154,18 +1163,24 @@ enable_if_boolean<T, bool> UnboxValue(const rj::Value& val) {
 return val.GetBool();
}

template <typename T>
enable_if_physical_signed_integer<T, typename T::c_type> UnboxValue(
const rj::Value& val) {
template <typename T, typename CType = typename T::c_type>
enable_if_t<is_physical_integer_type<T>::value && sizeof(CType) != sizeof(int64_t), CType>
UnboxValue(const rj::Value& val) {
 DCHECK(val.IsInt64());
 return static_cast<typename T::c_type>(val.GetInt64());
 return static_cast<CType>(val.GetInt64());
}

template <typename T>
enable_if_physical_unsigned_integer<T, typename T::c_type> UnboxValue(
 const rj::Value& val) {
 DCHECK(val.IsUint());
 return static_cast<typename T::c_type>(val.GetUint64());
template <typename T, typename CType = typename T::c_type>
enable_if_t<is_physical_integer_type<T>::value && sizeof(CType) == sizeof(int64_t), CType>
UnboxValue(const rj::Value& val) {
 DCHECK(val.IsString());

 CType out;
 bool success = ::arrow::internal::ParseValue<typename CTypeTraits<CType>::ArrowType>(
 val.GetString(), val.GetStringLength(), &out);

 DCHECK(success);
 return out;
}

template <typename T>
Expand Down

8 changes: 8 additions & 0 deletions
cpp/src/arrow/type_traits.h

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -646,6 +646,14 @@ template <typename T, typename R = void>
using enable_if_physical_unsigned_integer =
 enable_if_t<is_physical_unsigned_integer_type<T>::value, R>;

template <typename T>
using is_physical_integer_type =
 std::integral_constant<bool, is_physical_unsigned_integer_type<T>::value ||
 is_physical_signed_integer_type<T>::value>;
@kiszkkiszkJun 2, 2020

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.

not sure 100%. but, is this indentation correct?
@bkietzbkietzJun 2, 2020

Copy link


Copy Markdown

MemberAuthor
Choose a reason for hiding this comment

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

C++ indentation is deferred to clang-format. We have a CI job which ensures that running clang-format is a no-op. As for explaining why it made this choice... I'm not familiar enough with its implementation to say, sorry

template <typename T, typename R = void>
using enable_if_physical_integer = enable_if_t<is_physical_integer_type<T>::value, R>;

// Like is_floating_type but excluding half-floats which don't have a
// float-like c type.
template <typename T>
Expand Down

9 changes: 6 additions & 3 deletions
cpp/src/arrow/util/formatting.h

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -41,6 +41,9 @@ namespace internal {
template <typename ARROW_TYPE, typename Enable = void>
class StringFormatter;

template <typename Appender>
using Return = decltype(std::declval<Appender>()(util::string_view{}));

template <>
class StringFormatter<BooleanType> {
 public:
Expand All@@ -49,7 +52,7 @@ class StringFormatter<BooleanType> {
 using value_type = bool;

 template <typename Appender>
Status operator()(bool value, Appender&& append) {
Return<Appender> operator()(bool value, Appender&& append) {
 if (value) {
 const char string[] = "true";
 return append(util::string_view(string));
Expand DownExpand Up@@ -95,7 +98,7 @@ class IntToStringFormatterMixin {
 (is_signed ? 2 : 1) + std::numeric_limits<value_type>::digits10;

 template <typename Appender>
Status operator()(value_type value, Appender&& append) {
Return<Appender> operator()(value_type value, Appender&& append) {
 char buffer[buffer_size];
 char* ptr = buffer + buffer_size;
 int32_t size = 0;
Expand DownExpand Up@@ -206,7 +209,7 @@ class FloatToStringFormatterMixin : public FloatToStringFormatter {
 explicit FloatToStringFormatterMixin(const std::shared_ptr<DataType>& = NULLPTR) {}

 template <typename Appender>
Status operator()(value_type value, Appender&& append) {
Return<Appender> operator()(value_type value, Appender&& append) {
 char buffer[buffer_size];
 int size = FormatFloat(value, buffer, buffer_size);
 return append(util::string_view(buffer, size));
Expand Down

19 changes: 12 additions & 7 deletions
dev/archery/archery/integration/datagen.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -176,11 +176,15 @@ def _get_type(self):

 def generate_column(self, size, name=None):
 lower_bound, upper_bound = self._get_generated_data_bounds()
 return self.generate_range(size, lower_bound, upper_bound, name=name)
 return self.generate_range(size, lower_bound, upper_bound,
 name=name, include_extremes=True)

 def generate_range(self, size, lower, upper, name=None):
 values = [int(x) for x in
 np.random.randint(lower, upper, size=size)]
 def generate_range(self, size, lower, upper, name=None,
 include_extremes=False):
 values = np.random.randint(lower, upper, size=size)
 if include_extremes and size >= 2:
 values[:2] = [lower, upper]
 values = list(map(int if self.bit_width < 64 else str, values))

 is_valid = self._make_is_valid(size)

Expand DownExpand Up@@ -1540,9 +1544,10 @@ def _temp_path():
 .skip_category('Java') # TODO(ARROW-7779)
 .skip_category('JS'),

 generate_extension_case().skip_category('Go')
 .skip_category('JS')
 .skip_category('Rust'),
 generate_extension_case()
 .skip_category('Go')
 .skip_category('JS')
 .skip_category('Rust'),
 ]

 if flight:
Expand Down

3 changes: 2 additions & 1 deletion
dev/archery/archery/integration/tester_go.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -26,7 +26,8 @@ class GoTester(Tester):
 CONSUMER = True

 # FIXME(sbinet): revisit for Go modules
 GOPATH = os.getenv('GOPATH', '~/go')
 HOME = os.getenv('HOME', '~')
@fsaintjacquesfsaintjacquesMay 29, 2020

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

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

Why the change, just set GOPATH if you have something else?
@bkietzbkietzJun 2, 2020

Copy link


Copy Markdown

MemberAuthor
Choose a reason for hiding this comment

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

I don't know why ~ failed resolve to $HOME locally but this seemed like a way to save someone the next person from the frustration of reading the script to figure out that GOPATH needs set.
 GOPATH = os.getenv('GOPATH', os.path.join(HOME, 'go'))
 GOBIN = os.environ.get('GOBIN', os.path.join(GOPATH, 'bin'))

 GO_INTEGRATION_EXE = os.path.join(GOBIN, 'arrow-json-integration-test')
Expand Down

52 changes: 38 additions & 14 deletions
go/arrow/internal/arrjson/arrjson.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -963,19 +963,23 @@ func i32ToJSON(arr *array.Int32) []interface{} {
func i64FromJSON(vs []interface{}) []int64 {
	o := make([]int64, len(vs))
	for i, v := range vs {
 vv, err := v.(json.Number).Int64()
 vv, err := strconv.ParseInt(v.(string), 10, 64)
 if err != nil {
 panic(err)
 }
 o[i] = int64(vv)
 o[i] = vv
	}
	return o
}

func i64ToJSON(arr *array.Int64) []interface{} {
	o := make([]interface{}, arr.Len())
	for i := range o {
 o[i] = arr.Value(i)
 if arr.IsValid(i) {
 o[i] = strconv.FormatInt(arr.Value(i), 10)
 } else {
 o[i] = "0"
 }
	}
	return o
}
Expand DownExpand Up@@ -1043,19 +1047,23 @@ func u32ToJSON(arr *array.Uint32) []interface{} {
func u64FromJSON(vs []interface{}) []uint64 {
	o := make([]uint64, len(vs))
	for i, v := range vs {
 vv, err := strconv.ParseUint(v.(json.Number).String(), 10, 64)
 vv, err := strconv.ParseUint(v.(string), 10, 64)
 if err != nil {
 panic(err)
 }
 o[i] = uint64(vv)
 o[i] = vv
	}
	return o
}

func u64ToJSON(arr *array.Uint64) []interface{} {
	o := make([]interface{}, arr.Len())
	for i := range o {
 o[i] = arr.Value(i)
 if arr.IsValid(i) {
 o[i] = strconv.FormatUint(arr.Value(i), 10)
 } else {
 o[i] = "0"
 }
	}
	return o
}
Expand DownExpand Up@@ -1193,7 +1201,7 @@ func date32ToJSON(arr *array.Date32) []interface{} {
func date64FromJSON(vs []interface{}) []arrow.Date64 {
	o := make([]arrow.Date64, len(vs))
	for i, v := range vs {
 vv, err := v.(json.Number).Int64()
 vv, err := strconv.ParseInt(v.(string), 10, 64)
 if err != nil {
 panic(err)
 }
Expand All@@ -1205,7 +1213,11 @@ func date64FromJSON(vs []interface{}) []arrow.Date64 {
func date64ToJSON(arr *array.Date64) []interface{} {
	o := make([]interface{}, arr.Len())
	for i := range o {
 o[i] = int64(arr.Value(i))
 if arr.IsValid(i) {
 o[i] = strconv.FormatInt(int64(arr.Value(i)), 10)
 } else {
 o[i] = "0"
 }
	}
	return o
}
Expand DownExpand Up@@ -1233,7 +1245,7 @@ func time32ToJSON(arr *array.Time32) []interface{} {
func time64FromJSON(vs []interface{}) []arrow.Time64 {
	o := make([]arrow.Time64, len(vs))
	for i, v := range vs {
 vv, err := v.(json.Number).Int64()
 vv, err := strconv.ParseInt(v.(string), 10, 64)
 if err != nil {
 panic(err)
 }
Expand All@@ -1245,15 +1257,19 @@ func time64FromJSON(vs []interface{}) []arrow.Time64 {
func time64ToJSON(arr *array.Time64) []interface{} {
	o := make([]interface{}, arr.Len())
	for i := range o {
 o[i] = int64(arr.Value(i))
 if arr.IsValid(i) {
 o[i] = strconv.FormatInt(int64(arr.Value(i)), 10)
 } else {
 o[i] = "0"
 }
	}
	return o
}

func timestampFromJSON(vs []interface{}) []arrow.Timestamp {
	o := make([]arrow.Timestamp, len(vs))
	for i, v := range vs {
 vv, err := v.(json.Number).Int64()
 vv, err := strconv.ParseInt(v.(string), 10, 64)
 if err != nil {
 panic(err)
 }
Expand All@@ -1265,7 +1281,11 @@ func timestampFromJSON(vs []interface{}) []arrow.Timestamp {
func timestampToJSON(arr *array.Timestamp) []interface{} {
	o := make([]interface{}, arr.Len())
	for i := range o {
 o[i] = int64(arr.Value(i))
 if arr.IsValid(i) {
 o[i] = strconv.FormatInt(int64(arr.Value(i)), 10)
 } else {
 o[i] = "0"
 }
	}
	return o
}
Expand DownExpand Up@@ -1318,7 +1338,7 @@ func daytimeintervalToJSON(arr *array.DayTimeInterval) []interface{} {
func durationFromJSON(vs []interface{}) []arrow.Duration {
	o := make([]arrow.Duration, len(vs))
	for i, v := range vs {
 vv, err := v.(json.Number).Int64()
 vv, err := strconv.ParseInt(v.(string), 10, 64)
 if err != nil {
 panic(err)
 }
Expand All@@ -1330,7 +1350,11 @@ func durationFromJSON(vs []interface{}) []arrow.Duration {
func durationToJSON(arr *array.Duration) []interface{} {
	o := make([]interface{}, arr.Len())
	for i := range o {
 o[i] = arr.Value(i)
 if arr.IsValid(i) {
 o[i] = strconv.FormatInt(int64(arr.Value(i)), 10)
 } else {
 o[i] = "0"
 }
	}
	return o
}
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-8471: [C++][Integration] Represent 64 bit integers as strings#7292

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

bkietz
wants to merge
6
commits into

from

 Closed


ARROW-8471: [C++][Integration] Represent 64 bit integers as strings
#7292
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


6 commits


Select commit
Hold shift + click to select a range
e14f60a

ARROW-8471: [C++][Integration] Represent 64 bit integers as strings


bkietz May 27, 2020
47ce0f8

refactor Go to emit and expect 64 bit ints as strings


bkietz May 27, 2020
2e97dff

also adjust duration and date in Go


bkietz May 28, 2020
dbdd293

emit '0' in null slots


bkietz May 28, 2020
bf37227

add extremes to integer ranges


bkietz Jun 2, 2020
1ec2517

repair go indentation


bkietz Jun 2, 2020

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: 3 additions & 3 deletions
cpp/src/arrow/ipc/json_integration_test.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -255,7 +255,7 @@ static const char* JSON_EXAMPLE = R"example(
 "fields": [
 {
 "name": "foo",
 "type": {"name": "int", "isSigned": true, "bitWidth": 32},
 "type": {"name": "int", "isSigned": true, "bitWidth": 64},
Comment thread
fsaintjacques marked this conversation as resolved.


Outdated

 "nullable": true, "children": []
 },
 {
Expand All@@ -272,7 +272,7 @@ static const char* JSON_EXAMPLE = R"example(
 {
 "name": "foo",
 "count": 5,
 "DATA": [1, 2, 3, 4, 5],
 "DATA": ["1", "2", "3", "4", "5"],
Comment thread
bkietz marked this conversation as resolved.


Outdated

 "VALIDITY": [1, 0, 1, 1, 1]
 },
 {
Expand All@@ -289,7 +289,7 @@ static const char* JSON_EXAMPLE = R"example(
 {
 "name": "foo",
 "count": 4,
 "DATA": [1, 2, 3, 4],
 "DATA": ["-1", "0", "9223372036854775807", "-9223372036854775808"],
 "VALIDITY": [1, 0, 1, 1]
 },
 {
Expand Down

63 changes: 39 additions & 24 deletions
cpp/src/arrow/ipc/json_internal.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -19,6 +19,7 @@

#include <cstdint>
#include <cstdlib>
#include <iostream>
#include <memory>
#include <string>
#include <type_traits>
Expand DownExpand Up@@ -440,29 +441,37 @@ class ArrayWriter {
 return Status::OK();
 }

 template <typename T, bool IsSigned = std::is_signed<typename T::value_type>::value>
 void WriteIntegerDataValues(const T& arr) {
 static const char null_string[] = "0";
 const auto data = arr.raw_values();
 template <typename ArrayType, typename TypeClass = typename ArrayType::TypeClass,
 typename CType = typename TypeClass::c_type>
 enable_if_t<is_physical_integer_type<TypeClass>::value &&
 sizeof(CType) != sizeof(int64_t)>
 WriteDataValues(const ArrayType& arr) {
 static const std::string null_string = "0";
 for (int64_t i = 0; i < arr.length(); ++i) {
 if (arr.IsValid(i)) {
IsSigned ? writer_->Int64(data[i]) : writer_->Uint64(data[i]);
 writer_->Int64(arr.Value(i));
 } else {
 writer_->RawNumber(null_string, sizeof(null_string));
 writer_->RawNumber(null_string.data(), null_string.size());
 }
 }
 }

 template <typename ArrayType>
 enable_if_physical_signed_integer<typename ArrayType::TypeClass> WriteDataValues(
 const ArrayType& arr) {
 WriteIntegerDataValues<ArrayType>(arr);
 }
 template <typename ArrayType, typename TypeClass = typename ArrayType::TypeClass,
 typename CType = typename TypeClass::c_type>
 enable_if_t<is_physical_integer_type<TypeClass>::value &&
 sizeof(CType) == sizeof(int64_t)>
 WriteDataValues(const ArrayType& arr) {
 ::arrow::internal::StringFormatter<typename CTypeTraits<CType>::ArrowType> fmt;

 template <typename ArrayType>
 enable_if_physical_unsigned_integer<typename ArrayType::TypeClass> WriteDataValues(
 const ArrayType& arr) {
 WriteIntegerDataValues<ArrayType>(arr);
 static const std::string null_string = "0";
 for (int64_t i = 0; i < arr.length(); ++i) {
 if (arr.IsValid(i)) {
 fmt(arr.Value(i),
 [&](util::string_view repr) { writer_->String(repr.data(), repr.size()); });
 } else {
 writer_->String(null_string.data(), null_string.size());
 }
 }
 }

 template <typename ArrayType>
Expand DownExpand Up@@ -1154,18 +1163,24 @@ enable_if_boolean<T, bool> UnboxValue(const rj::Value& val) {
 return val.GetBool();
}

template <typename T>
enable_if_physical_signed_integer<T, typename T::c_type> UnboxValue(
const rj::Value& val) {
template <typename T, typename CType = typename T::c_type>
enable_if_t<is_physical_integer_type<T>::value && sizeof(CType) != sizeof(int64_t), CType>
UnboxValue(const rj::Value& val) {
 DCHECK(val.IsInt64());
 return static_cast<typename T::c_type>(val.GetInt64());
 return static_cast<CType>(val.GetInt64());
}

template <typename T>
enable_if_physical_unsigned_integer<T, typename T::c_type> UnboxValue(
 const rj::Value& val) {
 DCHECK(val.IsUint());
 return static_cast<typename T::c_type>(val.GetUint64());
template <typename T, typename CType = typename T::c_type>
enable_if_t<is_physical_integer_type<T>::value && sizeof(CType) == sizeof(int64_t), CType>
UnboxValue(const rj::Value& val) {
 DCHECK(val.IsString());

 CType out;
 bool success = ::arrow::internal::ParseValue<typename CTypeTraits<CType>::ArrowType>(
 val.GetString(), val.GetStringLength(), &out);

 DCHECK(success);
 return out;
}

template <typename T>
Expand Down

8 changes: 8 additions & 0 deletions
cpp/src/arrow/type_traits.h

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -646,6 +646,14 @@ template <typename T, typename R = void>
using enable_if_physical_unsigned_integer =
 enable_if_t<is_physical_unsigned_integer_type<T>::value, R>;

template <typename T>
using is_physical_integer_type =
 std::integral_constant<bool, is_physical_unsigned_integer_type<T>::value ||
 is_physical_signed_integer_type<T>::value>;
@kiszkkiszkJun 2, 2020

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.

not sure 100%. but, is this indentation correct?
@bkietzbkietzJun 2, 2020

Copy link


Copy Markdown

MemberAuthor
Choose a reason for hiding this comment

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

C++ indentation is deferred to clang-format. We have a CI job which ensures that running clang-format is a no-op. As for explaining why it made this choice... I'm not familiar enough with its implementation to say, sorry

template <typename T, typename R = void>
using enable_if_physical_integer = enable_if_t<is_physical_integer_type<T>::value, R>;

// Like is_floating_type but excluding half-floats which don't have a
// float-like c type.
template <typename T>
Expand Down

9 changes: 6 additions & 3 deletions
cpp/src/arrow/util/formatting.h

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -41,6 +41,9 @@ namespace internal {
template <typename ARROW_TYPE, typename Enable = void>
class StringFormatter;

template <typename Appender>
using Return = decltype(std::declval<Appender>()(util::string_view{}));

template <>
class StringFormatter<BooleanType> {
 public:
Expand All@@ -49,7 +52,7 @@ class StringFormatter<BooleanType> {
 using value_type = bool;

 template <typename Appender>
Status operator()(bool value, Appender&& append) {
Return<Appender> operator()(bool value, Appender&& append) {
 if (value) {
 const char string[] = "true";
 return append(util::string_view(string));
Expand DownExpand Up@@ -95,7 +98,7 @@ class IntToStringFormatterMixin {
 (is_signed ? 2 : 1) + std::numeric_limits<value_type>::digits10;

 template <typename Appender>
Status operator()(value_type value, Appender&& append) {
Return<Appender> operator()(value_type value, Appender&& append) {
 char buffer[buffer_size];
 char* ptr = buffer + buffer_size;
 int32_t size = 0;
Expand DownExpand Up@@ -206,7 +209,7 @@ class FloatToStringFormatterMixin : public FloatToStringFormatter {
 explicit FloatToStringFormatterMixin(const std::shared_ptr<DataType>& = NULLPTR) {}

 template <typename Appender>
Status operator()(value_type value, Appender&& append) {
Return<Appender> operator()(value_type value, Appender&& append) {
 char buffer[buffer_size];
 int size = FormatFloat(value, buffer, buffer_size);
 return append(util::string_view(buffer, size));
Expand Down

19 changes: 12 additions & 7 deletions
dev/archery/archery/integration/datagen.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -176,11 +176,15 @@ def _get_type(self):

 def generate_column(self, size, name=None):
 lower_bound, upper_bound = self._get_generated_data_bounds()
 return self.generate_range(size, lower_bound, upper_bound, name=name)
 return self.generate_range(size, lower_bound, upper_bound,
 name=name, include_extremes=True)

 def generate_range(self, size, lower, upper, name=None):
 values = [int(x) for x in
 np.random.randint(lower, upper, size=size)]
 def generate_range(self, size, lower, upper, name=None,
 include_extremes=False):
 values = np.random.randint(lower, upper, size=size)
 if include_extremes and size >= 2:
 values[:2] = [lower, upper]
 values = list(map(int if self.bit_width < 64 else str, values))

 is_valid = self._make_is_valid(size)

Expand DownExpand Up@@ -1540,9 +1544,10 @@ def _temp_path():
 .skip_category('Java') # TODO(ARROW-7779)
 .skip_category('JS'),

 generate_extension_case().skip_category('Go')
 .skip_category('JS')
 .skip_category('Rust'),
 generate_extension_case()
 .skip_category('Go')
 .skip_category('JS')
 .skip_category('Rust'),
 ]

 if flight:
Expand Down

3 changes: 2 additions & 1 deletion
dev/archery/archery/integration/tester_go.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -26,7 +26,8 @@ class GoTester(Tester):
 CONSUMER = True

 # FIXME(sbinet): revisit for Go modules
 GOPATH = os.getenv('GOPATH', '~/go')
 HOME = os.getenv('HOME', '~')
@fsaintjacquesfsaintjacquesMay 29, 2020

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

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

Why the change, just set GOPATH if you have something else?
@bkietzbkietzJun 2, 2020

Copy link


Copy Markdown

MemberAuthor
Choose a reason for hiding this comment

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

I don't know why ~ failed resolve to $HOME locally but this seemed like a way to save someone the next person from the frustration of reading the script to figure out that GOPATH needs set.
 GOPATH = os.getenv('GOPATH', os.path.join(HOME, 'go'))
 GOBIN = os.environ.get('GOBIN', os.path.join(GOPATH, 'bin'))

 GO_INTEGRATION_EXE = os.path.join(GOBIN, 'arrow-json-integration-test')
Expand Down

52 changes: 38 additions & 14 deletions
go/arrow/internal/arrjson/arrjson.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -963,19 +963,23 @@ func i32ToJSON(arr *array.Int32) []interface{} {
func i64FromJSON(vs []interface{}) []int64 {
	o := make([]int64, len(vs))
	for i, v := range vs {
 vv, err := v.(json.Number).Int64()
 vv, err := strconv.ParseInt(v.(string), 10, 64)
 if err != nil {
 panic(err)
 }
 o[i] = int64(vv)
 o[i] = vv
	}
	return o
}

func i64ToJSON(arr *array.Int64) []interface{} {
	o := make([]interface{}, arr.Len())
	for i := range o {
 o[i] = arr.Value(i)
 if arr.IsValid(i) {
 o[i] = strconv.FormatInt(arr.Value(i), 10)
 } else {
 o[i] = "0"
 }
	}
	return o
}
Expand DownExpand Up@@ -1043,19 +1047,23 @@ func u32ToJSON(arr *array.Uint32) []interface{} {
func u64FromJSON(vs []interface{}) []uint64 {
	o := make([]uint64, len(vs))
	for i, v := range vs {
 vv, err := strconv.ParseUint(v.(json.Number).String(), 10, 64)
 vv, err := strconv.ParseUint(v.(string), 10, 64)
 if err != nil {
 panic(err)
 }
 o[i] = uint64(vv)
 o[i] = vv
	}
	return o
}

func u64ToJSON(arr *array.Uint64) []interface{} {
	o := make([]interface{}, arr.Len())
	for i := range o {
 o[i] = arr.Value(i)
 if arr.IsValid(i) {
 o[i] = strconv.FormatUint(arr.Value(i), 10)
 } else {
 o[i] = "0"
 }
	}
	return o
}
Expand DownExpand Up@@ -1193,7 +1201,7 @@ func date32ToJSON(arr *array.Date32) []interface{} {
func date64FromJSON(vs []interface{}) []arrow.Date64 {
	o := make([]arrow.Date64, len(vs))
	for i, v := range vs {
 vv, err := v.(json.Number).Int64()
 vv, err := strconv.ParseInt(v.(string), 10, 64)
 if err != nil {
 panic(err)
 }
Expand All@@ -1205,7 +1213,11 @@ func date64FromJSON(vs []interface{}) []arrow.Date64 {
func date64ToJSON(arr *array.Date64) []interface{} {
	o := make([]interface{}, arr.Len())
	for i := range o {
 o[i] = int64(arr.Value(i))
 if arr.IsValid(i) {
 o[i] = strconv.FormatInt(int64(arr.Value(i)), 10)
 } else {
 o[i] = "0"
 }
	}
	return o
}
Expand DownExpand Up@@ -1233,7 +1245,7 @@ func time32ToJSON(arr *array.Time32) []interface{} {
func time64FromJSON(vs []interface{}) []arrow.Time64 {
	o := make([]arrow.Time64, len(vs))
	for i, v := range vs {
 vv, err := v.(json.Number).Int64()
 vv, err := strconv.ParseInt(v.(string), 10, 64)
 if err != nil {
 panic(err)
 }
Expand All@@ -1245,15 +1257,19 @@ func time64FromJSON(vs []interface{}) []arrow.Time64 {
func time64ToJSON(arr *array.Time64) []interface{} {
	o := make([]interface{}, arr.Len())
	for i := range o {
 o[i] = int64(arr.Value(i))
 if arr.IsValid(i) {
 o[i] = strconv.FormatInt(int64(arr.Value(i)), 10)
 } else {
 o[i] = "0"
 }
	}
	return o
}

func timestampFromJSON(vs []interface{}) []arrow.Timestamp {
	o := make([]arrow.Timestamp, len(vs))
	for i, v := range vs {
 vv, err := v.(json.Number).Int64()
 vv, err := strconv.ParseInt(v.(string), 10, 64)
 if err != nil {
 panic(err)
 }
Expand All@@ -1265,7 +1281,11 @@ func timestampFromJSON(vs []interface{}) []arrow.Timestamp {
func timestampToJSON(arr *array.Timestamp) []interface{} {
	o := make([]interface{}, arr.Len())
	for i := range o {
 o[i] = int64(arr.Value(i))
 if arr.IsValid(i) {
 o[i] = strconv.FormatInt(int64(arr.Value(i)), 10)
 } else {
 o[i] = "0"
 }
	}
	return o
}
Expand DownExpand Up@@ -1318,7 +1338,7 @@ func daytimeintervalToJSON(arr *array.DayTimeInterval) []interface{} {
func durationFromJSON(vs []interface{}) []arrow.Duration {
	o := make([]arrow.Duration, len(vs))
	for i, v := range vs {
 vv, err := v.(json.Number).Int64()
 vv, err := strconv.ParseInt(v.(string), 10, 64)
 if err != nil {
 panic(err)
 }
Expand All@@ -1330,7 +1350,11 @@ func durationFromJSON(vs []interface{}) []arrow.Duration {
func durationToJSON(arr *array.Duration) []interface{} {
	o := make([]interface{}, arr.Len())
	for i := range o {
 o[i] = arr.Value(i)
 if arr.IsValid(i) {
 o[i] = strconv.FormatInt(int64(arr.Value(i)), 10)
 } else {
 o[i] = "0"
 }
	}
	return o
}
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-8471: [C++][Integration] Represent 64 bit integers as strings#7292

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

bkietz
wants to merge
6
commits into

from

 Closed


ARROW-8471: [C++][Integration] Represent 64 bit integers as strings
#7292
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


6 commits


Select commit
Hold shift + click to select a range
e14f60a

ARROW-8471: [C++][Integration] Represent 64 bit integers as strings


bkietz May 27, 2020
47ce0f8

refactor Go to emit and expect 64 bit ints as strings


bkietz May 27, 2020
2e97dff

also adjust duration and date in Go


bkietz May 28, 2020
dbdd293

emit '0' in null slots


bkietz May 28, 2020
bf37227

add extremes to integer ranges


bkietz Jun 2, 2020
1ec2517

repair go indentation


bkietz Jun 2, 2020

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: 3 additions & 3 deletions
cpp/src/arrow/ipc/json_integration_test.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -255,7 +255,7 @@ static const char* JSON_EXAMPLE = R"example(
 "fields": [
 {
 "name": "foo",
 "type": {"name": "int", "isSigned": true, "bitWidth": 32},
 "type": {"name": "int", "isSigned": true, "bitWidth": 64},
Comment thread
fsaintjacques marked this conversation as resolved.


Outdated

 "nullable": true, "children": []
 },
 {
Expand All@@ -272,7 +272,7 @@ static const char* JSON_EXAMPLE = R"example(
 {
 "name": "foo",
 "count": 5,
 "DATA": [1, 2, 3, 4, 5],
 "DATA": ["1", "2", "3", "4", "5"],
Comment thread
bkietz marked this conversation as resolved.


Outdated

 "VALIDITY": [1, 0, 1, 1, 1]
 },
 {
Expand All@@ -289,7 +289,7 @@ static const char* JSON_EXAMPLE = R"example(
 {
 "name": "foo",
 "count": 4,
 "DATA": [1, 2, 3, 4],
 "DATA": ["-1", "0", "9223372036854775807", "-9223372036854775808"],
 "VALIDITY": [1, 0, 1, 1]
 },
 {
Expand Down

63 changes: 39 additions & 24 deletions
cpp/src/arrow/ipc/json_internal.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -19,6 +19,7 @@

#include <cstdint>
#include <cstdlib>
#include <iostream>
#include <memory>
#include <string>
#include <type_traits>
Expand DownExpand Up@@ -440,29 +441,37 @@ class ArrayWriter {
 return Status::OK();
 }

 template <typename T, bool IsSigned = std::is_signed<typename T::value_type>::value>
 void WriteIntegerDataValues(const T& arr) {
 static const char null_string[] = "0";
 const auto data = arr.raw_values();
 template <typename ArrayType, typename TypeClass = typename ArrayType::TypeClass,
 typename CType = typename TypeClass::c_type>
 enable_if_t<is_physical_integer_type<TypeClass>::value &&
 sizeof(CType) != sizeof(int64_t)>
 WriteDataValues(const ArrayType& arr) {
 static const std::string null_string = "0";
 for (int64_t i = 0; i < arr.length(); ++i) {
 if (arr.IsValid(i)) {
IsSigned ? writer_->Int64(data[i]) : writer_->Uint64(data[i]);
 writer_->Int64(arr.Value(i));
 } else {
 writer_->RawNumber(null_string, sizeof(null_string));
 writer_->RawNumber(null_string.data(), null_string.size());
 }
 }
 }

 template <typename ArrayType>
 enable_if_physical_signed_integer<typename ArrayType::TypeClass> WriteDataValues(
 const ArrayType& arr) {
 WriteIntegerDataValues<ArrayType>(arr);
 }
 template <typename ArrayType, typename TypeClass = typename ArrayType::TypeClass,
 typename CType = typename TypeClass::c_type>
 enable_if_t<is_physical_integer_type<TypeClass>::value &&
 sizeof(CType) == sizeof(int64_t)>
 WriteDataValues(const ArrayType& arr) {
 ::arrow::internal::StringFormatter<typename CTypeTraits<CType>::ArrowType> fmt;

 template <typename ArrayType>
 enable_if_physical_unsigned_integer<typename ArrayType::TypeClass> WriteDataValues(
 const ArrayType& arr) {
 WriteIntegerDataValues<ArrayType>(arr);
 static const std::string null_string = "0";
 for (int64_t i = 0; i < arr.length(); ++i) {
 if (arr.IsValid(i)) {
 fmt(arr.Value(i),
 [&](util::string_view repr) { writer_->String(repr.data(), repr.size()); });
 } else {
 writer_->String(null_string.data(), null_string.size());
 }
 }
 }

 template <typename ArrayType>
Expand DownExpand Up@@ -1154,18 +1163,24 @@ enable_if_boolean<T, bool> UnboxValue(const rj::Value& val) {
 return val.GetBool();
}

template <typename T>
enable_if_physical_signed_integer<T, typename T::c_type> UnboxValue(
const rj::Value& val) {
template <typename T, typename CType = typename T::c_type>
enable_if_t<is_physical_integer_type<T>::value && sizeof(CType) != sizeof(int64_t), CType>
UnboxValue(const rj::Value& val) {
 DCHECK(val.IsInt64());
 return static_cast<typename T::c_type>(val.GetInt64());
 return static_cast<CType>(val.GetInt64());
}

template <typename T>
enable_if_physical_unsigned_integer<T, typename T::c_type> UnboxValue(
 const rj::Value& val) {
 DCHECK(val.IsUint());
 return static_cast<typename T::c_type>(val.GetUint64());
template <typename T, typename CType = typename T::c_type>
enable_if_t<is_physical_integer_type<T>::value && sizeof(CType) == sizeof(int64_t), CType>
UnboxValue(const rj::Value& val) {
 DCHECK(val.IsString());

 CType out;
 bool success = ::arrow::internal::ParseValue<typename CTypeTraits<CType>::ArrowType>(
 val.GetString(), val.GetStringLength(), &out);

 DCHECK(success);
 return out;
}

template <typename T>
Expand Down

8 changes: 8 additions & 0 deletions
cpp/src/arrow/type_traits.h

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -646,6 +646,14 @@ template <typename T, typename R = void>
using enable_if_physical_unsigned_integer =
 enable_if_t<is_physical_unsigned_integer_type<T>::value, R>;

template <typename T>
using is_physical_integer_type =
 std::integral_constant<bool, is_physical_unsigned_integer_type<T>::value ||
 is_physical_signed_integer_type<T>::value>;
@kiszkkiszkJun 2, 2020

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.

not sure 100%. but, is this indentation correct?
@bkietzbkietzJun 2, 2020

Copy link


Copy Markdown

MemberAuthor
Choose a reason for hiding this comment

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

C++ indentation is deferred to clang-format. We have a CI job which ensures that running clang-format is a no-op. As for explaining why it made this choice... I'm not familiar enough with its implementation to say, sorry

template <typename T, typename R = void>
using enable_if_physical_integer = enable_if_t<is_physical_integer_type<T>::value, R>;

// Like is_floating_type but excluding half-floats which don't have a
// float-like c type.
template <typename T>
Expand Down

9 changes: 6 additions & 3 deletions
cpp/src/arrow/util/formatting.h

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -41,6 +41,9 @@ namespace internal {
template <typename ARROW_TYPE, typename Enable = void>
class StringFormatter;

template <typename Appender>
using Return = decltype(std::declval<Appender>()(util::string_view{}));

template <>
class StringFormatter<BooleanType> {
 public:
Expand All@@ -49,7 +52,7 @@ class StringFormatter<BooleanType> {
 using value_type = bool;

 template <typename Appender>
Status operator()(bool value, Appender&& append) {
Return<Appender> operator()(bool value, Appender&& append) {
 if (value) {
 const char string[] = "true";
 return append(util::string_view(string));
Expand DownExpand Up@@ -95,7 +98,7 @@ class IntToStringFormatterMixin {
 (is_signed ? 2 : 1) + std::numeric_limits<value_type>::digits10;

 template <typename Appender>
Status operator()(value_type value, Appender&& append) {
Return<Appender> operator()(value_type value, Appender&& append) {
 char buffer[buffer_size];
 char* ptr = buffer + buffer_size;
 int32_t size = 0;
Expand DownExpand Up@@ -206,7 +209,7 @@ class FloatToStringFormatterMixin : public FloatToStringFormatter {
 explicit FloatToStringFormatterMixin(const std::shared_ptr<DataType>& = NULLPTR) {}

 template <typename Appender>
Status operator()(value_type value, Appender&& append) {
Return<Appender> operator()(value_type value, Appender&& append) {
 char buffer[buffer_size];
 int size = FormatFloat(value, buffer, buffer_size);
 return append(util::string_view(buffer, size));
Expand Down

19 changes: 12 additions & 7 deletions
dev/archery/archery/integration/datagen.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -176,11 +176,15 @@ def _get_type(self):

 def generate_column(self, size, name=None):
 lower_bound, upper_bound = self._get_generated_data_bounds()
 return self.generate_range(size, lower_bound, upper_bound, name=name)
 return self.generate_range(size, lower_bound, upper_bound,
 name=name, include_extremes=True)

 def generate_range(self, size, lower, upper, name=None):
 values = [int(x) for x in
 np.random.randint(lower, upper, size=size)]
 def generate_range(self, size, lower, upper, name=None,
 include_extremes=False):
 values = np.random.randint(lower, upper, size=size)
 if include_extremes and size >= 2:
 values[:2] = [lower, upper]
 values = list(map(int if self.bit_width < 64 else str, values))

 is_valid = self._make_is_valid(size)

Expand DownExpand Up@@ -1540,9 +1544,10 @@ def _temp_path():
 .skip_category('Java') # TODO(ARROW-7779)
 .skip_category('JS'),

 generate_extension_case().skip_category('Go')
 .skip_category('JS')
 .skip_category('Rust'),
 generate_extension_case()
 .skip_category('Go')
 .skip_category('JS')
 .skip_category('Rust'),
 ]

 if flight:
Expand Down

3 changes: 2 additions & 1 deletion
dev/archery/archery/integration/tester_go.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -26,7 +26,8 @@ class GoTester(Tester):
 CONSUMER = True

 # FIXME(sbinet): revisit for Go modules
 GOPATH = os.getenv('GOPATH', '~/go')
 HOME = os.getenv('HOME', '~')
@fsaintjacquesfsaintjacquesMay 29, 2020

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

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

Why the change, just set GOPATH if you have something else?
@bkietzbkietzJun 2, 2020

Copy link


Copy Markdown

MemberAuthor
Choose a reason for hiding this comment

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

I don't know why ~ failed resolve to $HOME locally but this seemed like a way to save someone the next person from the frustration of reading the script to figure out that GOPATH needs set.
 GOPATH = os.getenv('GOPATH', os.path.join(HOME, 'go'))
 GOBIN = os.environ.get('GOBIN', os.path.join(GOPATH, 'bin'))

 GO_INTEGRATION_EXE = os.path.join(GOBIN, 'arrow-json-integration-test')
Expand Down

52 changes: 38 additions & 14 deletions
go/arrow/internal/arrjson/arrjson.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -963,19 +963,23 @@ func i32ToJSON(arr *array.Int32) []interface{} {
func i64FromJSON(vs []interface{}) []int64 {
	o := make([]int64, len(vs))
	for i, v := range vs {
 vv, err := v.(json.Number).Int64()
 vv, err := strconv.ParseInt(v.(string), 10, 64)
 if err != nil {
 panic(err)
 }
 o[i] = int64(vv)
 o[i] = vv
	}
	return o
}

func i64ToJSON(arr *array.Int64) []interface{} {
	o := make([]interface{}, arr.Len())
	for i := range o {
 o[i] = arr.Value(i)
 if arr.IsValid(i) {
 o[i] = strconv.FormatInt(arr.Value(i), 10)
 } else {
 o[i] = "0"
 }
	}
	return o
}
Expand DownExpand Up@@ -1043,19 +1047,23 @@ func u32ToJSON(arr *array.Uint32) []interface{} {
func u64FromJSON(vs []interface{}) []uint64 {
	o := make([]uint64, len(vs))
	for i, v := range vs {
 vv, err := strconv.ParseUint(v.(json.Number).String(), 10, 64)
 vv, err := strconv.ParseUint(v.(string), 10, 64)
 if err != nil {
 panic(err)
 }
 o[i] = uint64(vv)
 o[i] = vv
	}
	return o
}

func u64ToJSON(arr *array.Uint64) []interface{} {
	o := make([]interface{}, arr.Len())
	for i := range o {
 o[i] = arr.Value(i)
 if arr.IsValid(i) {
 o[i] = strconv.FormatUint(arr.Value(i), 10)
 } else {
 o[i] = "0"
 }
	}
	return o
}
Expand DownExpand Up@@ -1193,7 +1201,7 @@ func date32ToJSON(arr *array.Date32) []interface{} {
func date64FromJSON(vs []interface{}) []arrow.Date64 {
	o := make([]arrow.Date64, len(vs))
	for i, v := range vs {
 vv, err := v.(json.Number).Int64()
 vv, err := strconv.ParseInt(v.(string), 10, 64)
 if err != nil {
 panic(err)
 }
Expand All@@ -1205,7 +1213,11 @@ func date64FromJSON(vs []interface{}) []arrow.Date64 {
func date64ToJSON(arr *array.Date64) []interface{} {
	o := make([]interface{}, arr.Len())
	for i := range o {
 o[i] = int64(arr.Value(i))
 if arr.IsValid(i) {
 o[i] = strconv.FormatInt(int64(arr.Value(i)), 10)
 } else {
 o[i] = "0"
 }
	}
	return o
}
Expand DownExpand Up@@ -1233,7 +1245,7 @@ func time32ToJSON(arr *array.Time32) []interface{} {
func time64FromJSON(vs []interface{}) []arrow.Time64 {
	o := make([]arrow.Time64, len(vs))
	for i, v := range vs {
 vv, err := v.(json.Number).Int64()
 vv, err := strconv.ParseInt(v.(string), 10, 64)
 if err != nil {
 panic(err)
 }
Expand All@@ -1245,15 +1257,19 @@ func time64FromJSON(vs []interface{}) []arrow.Time64 {
func time64ToJSON(arr *array.Time64) []interface{} {
	o := make([]interface{}, arr.Len())
	for i := range o {
 o[i] = int64(arr.Value(i))
 if arr.IsValid(i) {
 o[i] = strconv.FormatInt(int64(arr.Value(i)), 10)
 } else {
 o[i] = "0"
 }
	}
	return o
}

func timestampFromJSON(vs []interface{}) []arrow.Timestamp {
	o := make([]arrow.Timestamp, len(vs))
	for i, v := range vs {
 vv, err := v.(json.Number).Int64()
 vv, err := strconv.ParseInt(v.(string), 10, 64)
 if err != nil {
 panic(err)
 }
Expand All@@ -1265,7 +1281,11 @@ func timestampFromJSON(vs []interface{}) []arrow.Timestamp {
func timestampToJSON(arr *array.Timestamp) []interface{} {
	o := make([]interface{}, arr.Len())
	for i := range o {
 o[i] = int64(arr.Value(i))
 if arr.IsValid(i) {
 o[i] = strconv.FormatInt(int64(arr.Value(i)), 10)
 } else {
 o[i] = "0"
 }
	}
	return o
}
Expand DownExpand Up@@ -1318,7 +1338,7 @@ func daytimeintervalToJSON(arr *array.DayTimeInterval) []interface{} {
func durationFromJSON(vs []interface{}) []arrow.Duration {
	o := make([]arrow.Duration, len(vs))
	for i, v := range vs {
 vv, err := v.(json.Number).Int64()
 vv, err := strconv.ParseInt(v.(string), 10, 64)
 if err != nil {
 panic(err)
 }
Expand All@@ -1330,7 +1350,11 @@ func durationFromJSON(vs []interface{}) []arrow.Duration {
func durationToJSON(arr *array.Duration) []interface{} {
	o := make([]interface{}, arr.Len())
	for i := range o {
 o[i] = arr.Value(i)
 if arr.IsValid(i) {
 o[i] = strconv.FormatInt(int64(arr.Value(i)), 10)
 } else {
 o[i] = "0"
 }
	}
	return o
}
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-8471: [C++][Integration] Represent 64 bit integers as strings#7292

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

bkietz
wants to merge
6
commits into

from

 Closed


ARROW-8471: [C++][Integration] Represent 64 bit integers as strings
#7292
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


6 commits


Select commit
Hold shift + click to select a range
e14f60a

ARROW-8471: [C++][Integration] Represent 64 bit integers as strings


bkietz May 27, 2020
47ce0f8

refactor Go to emit and expect 64 bit ints as strings


bkietz May 27, 2020
2e97dff

also adjust duration and date in Go


bkietz May 28, 2020
dbdd293

emit '0' in null slots


bkietz May 28, 2020
bf37227

add extremes to integer ranges


bkietz Jun 2, 2020
1ec2517

repair go indentation


bkietz Jun 2, 2020

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: 3 additions & 3 deletions
cpp/src/arrow/ipc/json_integration_test.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -255,7 +255,7 @@ static const char* JSON_EXAMPLE = R"example(
 "fields": [
 {
 "name": "foo",
 "type": {"name": "int", "isSigned": true, "bitWidth": 32},
 "type": {"name": "int", "isSigned": true, "bitWidth": 64},
Comment thread
fsaintjacques marked this conversation as resolved.


Outdated

 "nullable": true, "children": []
 },
 {
Expand All@@ -272,7 +272,7 @@ static const char* JSON_EXAMPLE = R"example(
 {
 "name": "foo",
 "count": 5,
 "DATA": [1, 2, 3, 4, 5],
 "DATA": ["1", "2", "3", "4", "5"],
Comment thread
bkietz marked this conversation as resolved.


Outdated

 "VALIDITY": [1, 0, 1, 1, 1]
 },
 {
Expand All@@ -289,7 +289,7 @@ static const char* JSON_EXAMPLE = R"example(
 {
 "name": "foo",
 "count": 4,
 "DATA": [1, 2, 3, 4],
 "DATA": ["-1", "0", "9223372036854775807", "-9223372036854775808"],
 "VALIDITY": [1, 0, 1, 1]
 },
 {
Expand Down

63 changes: 39 additions & 24 deletions
cpp/src/arrow/ipc/json_internal.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -19,6 +19,7 @@

#include <cstdint>
#include <cstdlib>
#include <iostream>
#include <memory>
#include <string>
#include <type_traits>
Expand DownExpand Up@@ -440,29 +441,37 @@ class ArrayWriter {
 return Status::OK();
 }

 template <typename T, bool IsSigned = std::is_signed<typename T::value_type>::value>
 void WriteIntegerDataValues(const T& arr) {
 static const char null_string[] = "0";
 const auto data = arr.raw_values();
 template <typename ArrayType, typename TypeClass = typename ArrayType::TypeClass,
 typename CType = typename TypeClass::c_type>
 enable_if_t<is_physical_integer_type<TypeClass>::value &&
 sizeof(CType) != sizeof(int64_t)>
 WriteDataValues(const ArrayType& arr) {
 static const std::string null_string = "0";
 for (int64_t i = 0; i < arr.length(); ++i) {
 if (arr.IsValid(i)) {
IsSigned ? writer_->Int64(data[i]) : writer_->Uint64(data[i]);
 writer_->Int64(arr.Value(i));
 } else {
 writer_->RawNumber(null_string, sizeof(null_string));
 writer_->RawNumber(null_string.data(), null_string.size());
 }
 }
 }

 template <typename ArrayType>
 enable_if_physical_signed_integer<typename ArrayType::TypeClass> WriteDataValues(
 const ArrayType& arr) {
 WriteIntegerDataValues<ArrayType>(arr);
 }
 template <typename ArrayType, typename TypeClass = typename ArrayType::TypeClass,
 typename CType = typename TypeClass::c_type>
 enable_if_t<is_physical_integer_type<TypeClass>::value &&
 sizeof(CType) == sizeof(int64_t)>
 WriteDataValues(const ArrayType& arr) {
 ::arrow::internal::StringFormatter<typename CTypeTraits<CType>::ArrowType> fmt;

 template <typename ArrayType>
 enable_if_physical_unsigned_integer<typename ArrayType::TypeClass> WriteDataValues(
 const ArrayType& arr) {
 WriteIntegerDataValues<ArrayType>(arr);
 static const std::string null_string = "0";
 for (int64_t i = 0; i < arr.length(); ++i) {
 if (arr.IsValid(i)) {
 fmt(arr.Value(i),
 [&](util::string_view repr) { writer_->String(repr.data(), repr.size()); });
 } else {
 writer_->String(null_string.data(), null_string.size());
 }
 }
 }

 template <typename ArrayType>
Expand DownExpand Up@@ -1154,18 +1163,24 @@ enable_if_boolean<T, bool> UnboxValue(const rj::Value& val) {
 return val.GetBool();
}

template <typename T>
enable_if_physical_signed_integer<T, typename T::c_type> UnboxValue(
const rj::Value& val) {
template <typename T, typename CType = typename T::c_type>
enable_if_t<is_physical_integer_type<T>::value && sizeof(CType) != sizeof(int64_t), CType>
UnboxValue(const rj::Value& val) {
 DCHECK(val.IsInt64());
 return static_cast<typename T::c_type>(val.GetInt64());
 return static_cast<CType>(val.GetInt64());
}

template <typename T>
enable_if_physical_unsigned_integer<T, typename T::c_type> UnboxValue(
 const rj::Value& val) {
 DCHECK(val.IsUint());
 return static_cast<typename T::c_type>(val.GetUint64());
template <typename T, typename CType = typename T::c_type>
enable_if_t<is_physical_integer_type<T>::value && sizeof(CType) == sizeof(int64_t), CType>
UnboxValue(const rj::Value& val) {
 DCHECK(val.IsString());

 CType out;
 bool success = ::arrow::internal::ParseValue<typename CTypeTraits<CType>::ArrowType>(
 val.GetString(), val.GetStringLength(), &out);

 DCHECK(success);
 return out;
}

template <typename T>
Expand Down

8 changes: 8 additions & 0 deletions
cpp/src/arrow/type_traits.h

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -646,6 +646,14 @@ template <typename T, typename R = void>
using enable_if_physical_unsigned_integer =
 enable_if_t<is_physical_unsigned_integer_type<T>::value, R>;

template <typename T>
using is_physical_integer_type =
 std::integral_constant<bool, is_physical_unsigned_integer_type<T>::value ||
 is_physical_signed_integer_type<T>::value>;
@kiszkkiszkJun 2, 2020

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.

not sure 100%. but, is this indentation correct?
@bkietzbkietzJun 2, 2020

Copy link


Copy Markdown

MemberAuthor
Choose a reason for hiding this comment

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

C++ indentation is deferred to clang-format. We have a CI job which ensures that running clang-format is a no-op. As for explaining why it made this choice... I'm not familiar enough with its implementation to say, sorry

template <typename T, typename R = void>
using enable_if_physical_integer = enable_if_t<is_physical_integer_type<T>::value, R>;

// Like is_floating_type but excluding half-floats which don't have a
// float-like c type.
template <typename T>
Expand Down

9 changes: 6 additions & 3 deletions
cpp/src/arrow/util/formatting.h

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -41,6 +41,9 @@ namespace internal {
template <typename ARROW_TYPE, typename Enable = void>
class StringFormatter;

template <typename Appender>
using Return = decltype(std::declval<Appender>()(util::string_view{}));

template <>
class StringFormatter<BooleanType> {
 public:
Expand All@@ -49,7 +52,7 @@ class StringFormatter<BooleanType> {
 using value_type = bool;

 template <typename Appender>
Status operator()(bool value, Appender&& append) {
Return<Appender> operator()(bool value, Appender&& append) {
 if (value) {
 const char string[] = "true";
 return append(util::string_view(string));
Expand DownExpand Up@@ -95,7 +98,7 @@ class IntToStringFormatterMixin {
 (is_signed ? 2 : 1) + std::numeric_limits<value_type>::digits10;

 template <typename Appender>
Status operator()(value_type value, Appender&& append) {
Return<Appender> operator()(value_type value, Appender&& append) {
 char buffer[buffer_size];
 char* ptr = buffer + buffer_size;
 int32_t size = 0;
Expand DownExpand Up@@ -206,7 +209,7 @@ class FloatToStringFormatterMixin : public FloatToStringFormatter {
 explicit FloatToStringFormatterMixin(const std::shared_ptr<DataType>& = NULLPTR) {}

 template <typename Appender>
Status operator()(value_type value, Appender&& append) {
Return<Appender> operator()(value_type value, Appender&& append) {
 char buffer[buffer_size];
 int size = FormatFloat(value, buffer, buffer_size);
 return append(util::string_view(buffer, size));
Expand Down

19 changes: 12 additions & 7 deletions
dev/archery/archery/integration/datagen.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -176,11 +176,15 @@ def _get_type(self):

 def generate_column(self, size, name=None):
 lower_bound, upper_bound = self._get_generated_data_bounds()
 return self.generate_range(size, lower_bound, upper_bound, name=name)
 return self.generate_range(size, lower_bound, upper_bound,
 name=name, include_extremes=True)

 def generate_range(self, size, lower, upper, name=None):
 values = [int(x) for x in
 np.random.randint(lower, upper, size=size)]
 def generate_range(self, size, lower, upper, name=None,
 include_extremes=False):
 values = np.random.randint(lower, upper, size=size)
 if include_extremes and size >= 2:
 values[:2] = [lower, upper]
 values = list(map(int if self.bit_width < 64 else str, values))

 is_valid = self._make_is_valid(size)

Expand DownExpand Up@@ -1540,9 +1544,10 @@ def _temp_path():
 .skip_category('Java') # TODO(ARROW-7779)
 .skip_category('JS'),

 generate_extension_case().skip_category('Go')
 .skip_category('JS')
 .skip_category('Rust'),
 generate_extension_case()
 .skip_category('Go')
 .skip_category('JS')
 .skip_category('Rust'),
 ]

 if flight:
Expand Down

3 changes: 2 additions & 1 deletion
dev/archery/archery/integration/tester_go.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -26,7 +26,8 @@ class GoTester(Tester):
 CONSUMER = True

 # FIXME(sbinet): revisit for Go modules
 GOPATH = os.getenv('GOPATH', '~/go')
 HOME = os.getenv('HOME', '~')
@fsaintjacquesfsaintjacquesMay 29, 2020

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

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

Why the change, just set GOPATH if you have something else?
@bkietzbkietzJun 2, 2020

Copy link


Copy Markdown

MemberAuthor
Choose a reason for hiding this comment

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

I don't know why ~ failed resolve to $HOME locally but this seemed like a way to save someone the next person from the frustration of reading the script to figure out that GOPATH needs set.
 GOPATH = os.getenv('GOPATH', os.path.join(HOME, 'go'))
 GOBIN = os.environ.get('GOBIN', os.path.join(GOPATH, 'bin'))

 GO_INTEGRATION_EXE = os.path.join(GOBIN, 'arrow-json-integration-test')
Expand Down

52 changes: 38 additions & 14 deletions
go/arrow/internal/arrjson/arrjson.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -963,19 +963,23 @@ func i32ToJSON(arr *array.Int32) []interface{} {
func i64FromJSON(vs []interface{}) []int64 {
	o := make([]int64, len(vs))
	for i, v := range vs {
 vv, err := v.(json.Number).Int64()
 vv, err := strconv.ParseInt(v.(string), 10, 64)
 if err != nil {
 panic(err)
 }
 o[i] = int64(vv)
 o[i] = vv
	}
	return o
}

func i64ToJSON(arr *array.Int64) []interface{} {
	o := make([]interface{}, arr.Len())
	for i := range o {
 o[i] = arr.Value(i)
 if arr.IsValid(i) {
 o[i] = strconv.FormatInt(arr.Value(i), 10)
 } else {
 o[i] = "0"
 }
	}
	return o
}
Expand DownExpand Up@@ -1043,19 +1047,23 @@ func u32ToJSON(arr *array.Uint32) []interface{} {
func u64FromJSON(vs []interface{}) []uint64 {
	o := make([]uint64, len(vs))
	for i, v := range vs {
 vv, err := strconv.ParseUint(v.(json.Number).String(), 10, 64)
 vv, err := strconv.ParseUint(v.(string), 10, 64)
 if err != nil {
 panic(err)
 }
 o[i] = uint64(vv)
 o[i] = vv
	}
	return o
}

func u64ToJSON(arr *array.Uint64) []interface{} {
	o := make([]interface{}, arr.Len())
	for i := range o {
 o[i] = arr.Value(i)
 if arr.IsValid(i) {
 o[i] = strconv.FormatUint(arr.Value(i), 10)
 } else {
 o[i] = "0"
 }
	}
	return o
}
Expand DownExpand Up@@ -1193,7 +1201,7 @@ func date32ToJSON(arr *array.Date32) []interface{} {
func date64FromJSON(vs []interface{}) []arrow.Date64 {
	o := make([]arrow.Date64, len(vs))
	for i, v := range vs {
 vv, err := v.(json.Number).Int64()
 vv, err := strconv.ParseInt(v.(string), 10, 64)
 if err != nil {
 panic(err)
 }
Expand All@@ -1205,7 +1213,11 @@ func date64FromJSON(vs []interface{}) []arrow.Date64 {
func date64ToJSON(arr *array.Date64) []interface{} {
	o := make([]interface{}, arr.Len())
	for i := range o {
 o[i] = int64(arr.Value(i))
 if arr.IsValid(i) {
 o[i] = strconv.FormatInt(int64(arr.Value(i)), 10)
 } else {
 o[i] = "0"
 }
	}
	return o
}
Expand DownExpand Up@@ -1233,7 +1245,7 @@ func time32ToJSON(arr *array.Time32) []interface{} {
func time64FromJSON(vs []interface{}) []arrow.Time64 {
	o := make([]arrow.Time64, len(vs))
	for i, v := range vs {
 vv, err := v.(json.Number).Int64()
 vv, err := strconv.ParseInt(v.(string), 10, 64)
 if err != nil {
 panic(err)
 }
Expand All@@ -1245,15 +1257,19 @@ func time64FromJSON(vs []interface{}) []arrow.Time64 {
func time64ToJSON(arr *array.Time64) []interface{} {
	o := make([]interface{}, arr.Len())
	for i := range o {
 o[i] = int64(arr.Value(i))
 if arr.IsValid(i) {
 o[i] = strconv.FormatInt(int64(arr.Value(i)), 10)
 } else {
 o[i] = "0"
 }
	}
	return o
}

func timestampFromJSON(vs []interface{}) []arrow.Timestamp {
	o := make([]arrow.Timestamp, len(vs))
	for i, v := range vs {
 vv, err := v.(json.Number).Int64()
 vv, err := strconv.ParseInt(v.(string), 10, 64)
 if err != nil {
 panic(err)
 }
Expand All@@ -1265,7 +1281,11 @@ func timestampFromJSON(vs []interface{}) []arrow.Timestamp {
func timestampToJSON(arr *array.Timestamp) []interface{} {
	o := make([]interface{}, arr.Len())
	for i := range o {
 o[i] = int64(arr.Value(i))
 if arr.IsValid(i) {
 o[i] = strconv.FormatInt(int64(arr.Value(i)), 10)
 } else {
 o[i] = "0"
 }
	}
	return o
}
Expand DownExpand Up@@ -1318,7 +1338,7 @@ func daytimeintervalToJSON(arr *array.DayTimeInterval) []interface{} {
func durationFromJSON(vs []interface{}) []arrow.Duration {
	o := make([]arrow.Duration, len(vs))
	for i, v := range vs {
 vv, err := v.(json.Number).Int64()
 vv, err := strconv.ParseInt(v.(string), 10, 64)
 if err != nil {
 panic(err)
 }
Expand All@@ -1330,7 +1350,11 @@ func durationFromJSON(vs []interface{}) []arrow.Duration {
func durationToJSON(arr *array.Duration) []interface{} {
	o := make([]interface{}, arr.Len())
	for i := range o {
 o[i] = arr.Value(i)
 if arr.IsValid(i) {
 o[i] = strconv.FormatInt(int64(arr.Value(i)), 10)
 } else {
 o[i] = "0"
 }
	}
	return o
}
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-8471: [C++][Integration] Represent 64 bit integers as strings#7292

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

bkietz
wants to merge
6
commits into

from

 Closed


ARROW-8471: [C++][Integration] Represent 64 bit integers as strings
#7292
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


6 commits


Select commit
Hold shift + click to select a range
e14f60a

ARROW-8471: [C++][Integration] Represent 64 bit integers as strings


bkietz May 27, 2020
47ce0f8

refactor Go to emit and expect 64 bit ints as strings


bkietz May 27, 2020
2e97dff

also adjust duration and date in Go


bkietz May 28, 2020
dbdd293

emit '0' in null slots


bkietz May 28, 2020
bf37227

add extremes to integer ranges


bkietz Jun 2, 2020
1ec2517

repair go indentation


bkietz Jun 2, 2020

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: 3 additions & 3 deletions
cpp/src/arrow/ipc/json_integration_test.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -255,7 +255,7 @@ static const char* JSON_EXAMPLE = R"example(
 "fields": [
 {
 "name": "foo",
 "type": {"name": "int", "isSigned": true, "bitWidth": 32},
 "type": {"name": "int", "isSigned": true, "bitWidth": 64},
Comment thread
fsaintjacques marked this conversation as resolved.


Outdated

 "nullable": true, "children": []
 },
 {
Expand All@@ -272,7 +272,7 @@ static const char* JSON_EXAMPLE = R"example(
 {
 "name": "foo",
 "count": 5,
 "DATA": [1, 2, 3, 4, 5],
 "DATA": ["1", "2", "3", "4", "5"],
Comment thread
bkietz marked this conversation as resolved.


Outdated

 "VALIDITY": [1, 0, 1, 1, 1]
 },
 {
Expand All@@ -289,7 +289,7 @@ static const char* JSON_EXAMPLE = R"example(
 {
 "name": "foo",
 "count": 4,
 "DATA": [1, 2, 3, 4],
 "DATA": ["-1", "0", "9223372036854775807", "-9223372036854775808"],
 "VALIDITY": [1, 0, 1, 1]
 },
 {
Expand Down

63 changes: 39 additions & 24 deletions
cpp/src/arrow/ipc/json_internal.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -19,6 +19,7 @@

#include <cstdint>
#include <cstdlib>
#include <iostream>
#include <memory>
#include <string>
#include <type_traits>
Expand DownExpand Up@@ -440,29 +441,37 @@ class ArrayWriter {
 return Status::OK();
 }

 template <typename T, bool IsSigned = std::is_signed<typename T::value_type>::value>
 void WriteIntegerDataValues(const T& arr) {
 static const char null_string[] = "0";
 const auto data = arr.raw_values();
 template <typename ArrayType, typename TypeClass = typename ArrayType::TypeClass,
 typename CType = typename TypeClass::c_type>
 enable_if_t<is_physical_integer_type<TypeClass>::value &&
 sizeof(CType) != sizeof(int64_t)>
 WriteDataValues(const ArrayType& arr) {
 static const std::string null_string = "0";
 for (int64_t i = 0; i < arr.length(); ++i) {
 if (arr.IsValid(i)) {
IsSigned ? writer_->Int64(data[i]) : writer_->Uint64(data[i]);
 writer_->Int64(arr.Value(i));
 } else {
 writer_->RawNumber(null_string, sizeof(null_string));
 writer_->RawNumber(null_string.data(), null_string.size());
 }
 }
 }

 template <typename ArrayType>
 enable_if_physical_signed_integer<typename ArrayType::TypeClass> WriteDataValues(
 const ArrayType& arr) {
 WriteIntegerDataValues<ArrayType>(arr);
 }
 template <typename ArrayType, typename TypeClass = typename ArrayType::TypeClass,
 typename CType = typename TypeClass::c_type>
 enable_if_t<is_physical_integer_type<TypeClass>::value &&
 sizeof(CType) == sizeof(int64_t)>
 WriteDataValues(const ArrayType& arr) {
 ::arrow::internal::StringFormatter<typename CTypeTraits<CType>::ArrowType> fmt;

 template <typename ArrayType>
 enable_if_physical_unsigned_integer<typename ArrayType::TypeClass> WriteDataValues(
 const ArrayType& arr) {
 WriteIntegerDataValues<ArrayType>(arr);
 static const std::string null_string = "0";
 for (int64_t i = 0; i < arr.length(); ++i) {
 if (arr.IsValid(i)) {
 fmt(arr.Value(i),
 [&](util::string_view repr) { writer_->String(repr.data(), repr.size()); });
 } else {
 writer_->String(null_string.data(), null_string.size());
 }
 }
 }

 template <typename ArrayType>
Expand DownExpand Up@@ -1154,18 +1163,24 @@ enable_if_boolean<T, bool> UnboxValue(const rj::Value& val) {
 return val.GetBool();
}

template <typename T>
enable_if_physical_signed_integer<T, typename T::c_type> UnboxValue(
const rj::Value& val) {
template <typename T, typename CType = typename T::c_type>
enable_if_t<is_physical_integer_type<T>::value && sizeof(CType) != sizeof(int64_t), CType>
UnboxValue(const rj::Value& val) {
 DCHECK(val.IsInt64());
 return static_cast<typename T::c_type>(val.GetInt64());
 return static_cast<CType>(val.GetInt64());
}

template <typename T>
enable_if_physical_unsigned_integer<T, typename T::c_type> UnboxValue(
 const rj::Value& val) {
 DCHECK(val.IsUint());
 return static_cast<typename T::c_type>(val.GetUint64());
template <typename T, typename CType = typename T::c_type>
enable_if_t<is_physical_integer_type<T>::value && sizeof(CType) == sizeof(int64_t), CType>
UnboxValue(const rj::Value& val) {
 DCHECK(val.IsString());

 CType out;
 bool success = ::arrow::internal::ParseValue<typename CTypeTraits<CType>::ArrowType>(
 val.GetString(), val.GetStringLength(), &out);

 DCHECK(success);
 return out;
}

template <typename T>
Expand Down

8 changes: 8 additions & 0 deletions
cpp/src/arrow/type_traits.h

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -646,6 +646,14 @@ template <typename T, typename R = void>
using enable_if_physical_unsigned_integer =
 enable_if_t<is_physical_unsigned_integer_type<T>::value, R>;

template <typename T>
using is_physical_integer_type =
 std::integral_constant<bool, is_physical_unsigned_integer_type<T>::value ||
 is_physical_signed_integer_type<T>::value>;
@kiszkkiszkJun 2, 2020

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.

not sure 100%. but, is this indentation correct?
@bkietzbkietzJun 2, 2020

Copy link


Copy Markdown

MemberAuthor
Choose a reason for hiding this comment

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

C++ indentation is deferred to clang-format. We have a CI job which ensures that running clang-format is a no-op. As for explaining why it made this choice... I'm not familiar enough with its implementation to say, sorry

template <typename T, typename R = void>
using enable_if_physical_integer = enable_if_t<is_physical_integer_type<T>::value, R>;

// Like is_floating_type but excluding half-floats which don't have a
// float-like c type.
template <typename T>
Expand Down

9 changes: 6 additions & 3 deletions
cpp/src/arrow/util/formatting.h

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -41,6 +41,9 @@ namespace internal {
template <typename ARROW_TYPE, typename Enable = void>
class StringFormatter;

template <typename Appender>
using Return = decltype(std::declval<Appender>()(util::string_view{}));

template <>
class StringFormatter<BooleanType> {
 public:
Expand All@@ -49,7 +52,7 @@ class StringFormatter<BooleanType> {
 using value_type = bool;

 template <typename Appender>
Status operator()(bool value, Appender&& append) {
Return<Appender> operator()(bool value, Appender&& append) {
 if (value) {
 const char string[] = "true";
 return append(util::string_view(string));
Expand DownExpand Up@@ -95,7 +98,7 @@ class IntToStringFormatterMixin {
 (is_signed ? 2 : 1) + std::numeric_limits<value_type>::digits10;

 template <typename Appender>
Status operator()(value_type value, Appender&& append) {
Return<Appender> operator()(value_type value, Appender&& append) {
 char buffer[buffer_size];
 char* ptr = buffer + buffer_size;
 int32_t size = 0;
Expand DownExpand Up@@ -206,7 +209,7 @@ class FloatToStringFormatterMixin : public FloatToStringFormatter {
 explicit FloatToStringFormatterMixin(const std::shared_ptr<DataType>& = NULLPTR) {}

 template <typename Appender>
Status operator()(value_type value, Appender&& append) {
Return<Appender> operator()(value_type value, Appender&& append) {
 char buffer[buffer_size];
 int size = FormatFloat(value, buffer, buffer_size);
 return append(util::string_view(buffer, size));
Expand Down

19 changes: 12 additions & 7 deletions
dev/archery/archery/integration/datagen.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -176,11 +176,15 @@ def _get_type(self):

 def generate_column(self, size, name=None):
 lower_bound, upper_bound = self._get_generated_data_bounds()
 return self.generate_range(size, lower_bound, upper_bound, name=name)
 return self.generate_range(size, lower_bound, upper_bound,
 name=name, include_extremes=True)

 def generate_range(self, size, lower, upper, name=None):
 values = [int(x) for x in
 np.random.randint(lower, upper, size=size)]
 def generate_range(self, size, lower, upper, name=None,
 include_extremes=False):
 values = np.random.randint(lower, upper, size=size)
 if include_extremes and size >= 2:
 values[:2] = [lower, upper]
 values = list(map(int if self.bit_width < 64 else str, values))

 is_valid = self._make_is_valid(size)

Expand DownExpand Up@@ -1540,9 +1544,10 @@ def _temp_path():
 .skip_category('Java') # TODO(ARROW-7779)
 .skip_category('JS'),

 generate_extension_case().skip_category('Go')
 .skip_category('JS')
 .skip_category('Rust'),
 generate_extension_case()
 .skip_category('Go')
 .skip_category('JS')
 .skip_category('Rust'),
 ]

 if flight:
Expand Down

3 changes: 2 additions & 1 deletion
dev/archery/archery/integration/tester_go.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -26,7 +26,8 @@ class GoTester(Tester):
 CONSUMER = True

 # FIXME(sbinet): revisit for Go modules
 GOPATH = os.getenv('GOPATH', '~/go')
 HOME = os.getenv('HOME', '~')
@fsaintjacquesfsaintjacquesMay 29, 2020

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

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

Why the change, just set GOPATH if you have something else?
@bkietzbkietzJun 2, 2020

Copy link


Copy Markdown

MemberAuthor
Choose a reason for hiding this comment

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

I don't know why ~ failed resolve to $HOME locally but this seemed like a way to save someone the next person from the frustration of reading the script to figure out that GOPATH needs set.
 GOPATH = os.getenv('GOPATH', os.path.join(HOME, 'go'))
 GOBIN = os.environ.get('GOBIN', os.path.join(GOPATH, 'bin'))

 GO_INTEGRATION_EXE = os.path.join(GOBIN, 'arrow-json-integration-test')
Expand Down

52 changes: 38 additions & 14 deletions
go/arrow/internal/arrjson/arrjson.go

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -963,19 +963,23 @@ func i32ToJSON(arr *array.Int32) []interface{} {
func i64FromJSON(vs []interface{}) []int64 {
	o := make([]int64, len(vs))
	for i, v := range vs {
 vv, err := v.(json.Number).Int64()
 vv, err := strconv.ParseInt(v.(string), 10, 64)
 if err != nil {
 panic(err)
 }
 o[i] = int64(vv)
 o[i] = vv
	}
	return o
}

func i64ToJSON(arr *array.Int64) []interface{} {
	o := make([]interface{}, arr.Len())
	for i := range o {
 o[i] = arr.Value(i)
 if arr.IsValid(i) {
 o[i] = strconv.FormatInt(arr.Value(i), 10)
 } else {
 o[i] = "0"
 }
	}
	return o
}
Expand DownExpand Up@@ -1043,19 +1047,23 @@ func u32ToJSON(arr *array.Uint32) []interface{} {
func u64FromJSON(vs []interface{}) []uint64 {
	o := make([]uint64, len(vs))
	for i, v := range vs {
 vv, err := strconv.ParseUint(v.(json.Number).String(), 10, 64)
 vv, err := strconv.ParseUint(v.(string), 10, 64)
 if err != nil {
 panic(err)
 }
 o[i] = uint64(vv)
 o[i] = vv
	}
	return o
}

func u64ToJSON(arr *array.Uint64) []interface{} {
	o := make([]interface{}, arr.Len())
	for i := range o {
 o[i] = arr.Value(i)
 if arr.IsValid(i) {
 o[i] = strconv.FormatUint(arr.Value(i), 10)
 } else {
 o[i] = "0"
 }
	}
	return o
}
Expand DownExpand Up@@ -1193,7 +1201,7 @@ func date32ToJSON(arr *array.Date32) []interface{} {
func date64FromJSON(vs []interface{}) []arrow.Date64 {
	o := make([]arrow.Date64, len(vs))
	for i, v := range vs {
 vv, err := v.(json.Number).Int64()
 vv, err := strconv.ParseInt(v.(string), 10, 64)
 if err != nil {
 panic(err)
 }
Expand All@@ -1205,7 +1213,11 @@ func date64FromJSON(vs []interface{}) []arrow.Date64 {
func date64ToJSON(arr *array.Date64) []interface{} {
	o := make([]interface{}, arr.Len())
	for i := range o {
 o[i] = int64(arr.Value(i))
 if arr.IsValid(i) {
 o[i] = strconv.FormatInt(int64(arr.Value(i)), 10)
 } else {
 o[i] = "0"
 }
	}
	return o
}
Expand DownExpand Up@@ -1233,7 +1245,7 @@ func time32ToJSON(arr *array.Time32) []interface{} {
func time64FromJSON(vs []interface{}) []arrow.Time64 {
	o := make([]arrow.Time64, len(vs))
	for i, v := range vs {
 vv, err := v.(json.Number).Int64()
 vv, err := strconv.ParseInt(v.(string), 10, 64)
 if err != nil {
 panic(err)
 }
Expand All@@ -1245,15 +1257,19 @@ func time64FromJSON(vs []interface{}) []arrow.Time64 {
func time64ToJSON(arr *array.Time64) []interface{} {
	o := make([]interface{}, arr.Len())
	for i := range o {
 o[i] = int64(arr.Value(i))
 if arr.IsValid(i) {
 o[i] = strconv.FormatInt(int64(arr.Value(i)), 10)
 } else {
 o[i] = "0"
 }
	}
	return o
}

func timestampFromJSON(vs []interface{}) []arrow.Timestamp {
	o := make([]arrow.Timestamp, len(vs))
	for i, v := range vs {
 vv, err := v.(json.Number).Int64()
 vv, err := strconv.ParseInt(v.(string), 10, 64)
 if err != nil {
 panic(err)
 }
Expand All@@ -1265,7 +1281,11 @@ func timestampFromJSON(vs []interface{}) []arrow.Timestamp {
func timestampToJSON(arr *array.Timestamp) []interface{} {
	o := make([]interface{}, arr.Len())
	for i := range o {
 o[i] = int64(arr.Value(i))
 if arr.IsValid(i) {
 o[i] = strconv.FormatInt(int64(arr.Value(i)), 10)
 } else {
 o[i] = "0"
 }
	}
	return o
}
Expand DownExpand Up@@ -1318,7 +1338,7 @@ func daytimeintervalToJSON(arr *array.DayTimeInterval) []interface{} {
func durationFromJSON(vs []interface{}) []arrow.Duration {
	o := make([]arrow.Duration, len(vs))
	for i, v := range vs {
 vv, err := v.(json.Number).Int64()
 vv, err := strconv.ParseInt(v.(string), 10, 64)
 if err != nil {
 panic(err)
 }
Expand All@@ -1330,7 +1350,11 @@ func durationFromJSON(vs []interface{}) []arrow.Duration {
func durationToJSON(arr *array.Duration) []interface{} {
	o := make([]interface{}, arr.Len())
	for i := range o {
 o[i] = arr.Value(i)
 if arr.IsValid(i) {
 o[i] = strconv.FormatInt(int64(arr.Value(i)), 10)
 } else {
 o[i] = "0"
 }
	}
	return o
}
Expand Down