Skip to content

ARROW-9131: [C++] Faster ascii_lower and ascii_upper. #7434

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
wants to merge 5 commits into from
Closed

ARROW-9131: [C++] Faster ascii_lower and ascii_upper. #7434

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
332747d
ARROW-9131: [C++] Faster ascii_lower and ascii_upper.
maartenbreddels Jun 15, 2020
b3b4b56
reword using proper nomenclature
maartenbreddels Jun 15, 2020
e26e5e0
lint/format
maartenbreddels Jun 15, 2020
f51e86f
format/linting test
maartenbreddels Jun 15, 2020
6309da7
fix typo
maartenbreddels Jun 15, 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
73 changes: 13 additions & 60 deletions cpp/src/arrow/compute/kernels/scalar_string.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -64,77 +64,30 @@ void StringDataTransform(KernelContext* ctx, const ExecBatch& batch,
}
}

// Generated with
//
// print("static constexpr uint8_t kAsciiUpperTable[] = {")
// for i in range(256):
// if i > 0: print(', ', end='')
// if i >= ord('a') and i <= ord('z'):
// print(i - 32, end='')
// else:
// print(i, end='')
// print("};")

static constexpr uint8_t kAsciiUpperTable[] = {
0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15,
16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31,
32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47,
48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63,
64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79,
80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95,
96, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79,
80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 123, 124, 125, 126, 127,
128, 129, 130, 131, 132, 133, 134, 135, 136, 137, 138, 139, 140, 141, 142, 143,
144, 145, 146, 147, 148, 149, 150, 151, 152, 153, 154, 155, 156, 157, 158, 159,
160, 161, 162, 163, 164, 165, 166, 167, 168, 169, 170, 171, 172, 173, 174, 175,
176, 177, 178, 179, 180, 181, 182, 183, 184, 185, 186, 187, 188, 189, 190, 191,
192, 193, 194, 195, 196, 197, 198, 199, 200, 201, 202, 203, 204, 205, 206, 207,
208, 209, 210, 211, 212, 213, 214, 215, 216, 217, 218, 219, 220, 221, 222, 223,
224, 225, 226, 227, 228, 229, 230, 231, 232, 233, 234, 235, 236, 237, 238, 239,
240, 241, 242, 243, 244, 245, 246, 247, 248, 249, 250, 251, 252, 253, 254, 255};

void TransformAsciiUpper(const uint8_t* input, int64_t length, uint8_t* output) {
for (int64_t i = 0; i < length; ++i) {
*output++ = kAsciiUpperTable[*input++];
const uint8_t utf8_code_unit = *input++;
// Code units in the range [a-z] can only be an encoding of an ascii
// character/codepoint, not the 2nd, 3rd or 4th code unit (byte) of an different
// codepoint. This guaranteed by non-overlap design of the unicode standard. (see
// section 2.5 of Unicode Standard Core Specification v13.0)
*output++ = ((utf8_code_unit >= 'a') && (utf8_code_unit <= 'z'))
? (utf8_code_unit - 32)
: utf8_code_unit;
}
}

void AsciiUpperExec(KernelContext* ctx, const ExecBatch& batch, Datum* out) {
StringDataTransform(ctx, batch, TransformAsciiUpper, out);
}

// Generated with
//
// print("static constexpr uint8_t kAsciiLowerTable[] = {")
// for i in range(256):
// if i > 0: print(', ', end='')
// if i >= ord('A') and i <= ord('Z'):
// print(i + 32, end='')
// else:
// print(i, end='')
// print("};")

static constexpr uint8_t kAsciiLowerTable[] = {
0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15,
16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31,
32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47,
48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63,
64, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111,
112, 113, 114, 115, 116, 117, 118, 119, 120, 121, 122, 91, 92, 93, 94, 95,
96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111,
112, 113, 114, 115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126, 127,
128, 129, 130, 131, 132, 133, 134, 135, 136, 137, 138, 139, 140, 141, 142, 143,
144, 145, 146, 147, 148, 149, 150, 151, 152, 153, 154, 155, 156, 157, 158, 159,
160, 161, 162, 163, 164, 165, 166, 167, 168, 169, 170, 171, 172, 173, 174, 175,
176, 177, 178, 179, 180, 181, 182, 183, 184, 185, 186, 187, 188, 189, 190, 191,
192, 193, 194, 195, 196, 197, 198, 199, 200, 201, 202, 203, 204, 205, 206, 207,
208, 209, 210, 211, 212, 213, 214, 215, 216, 217, 218, 219, 220, 221, 222, 223,
224, 225, 226, 227, 228, 229, 230, 231, 232, 233, 234, 235, 236, 237, 238, 239,
240, 241, 242, 243, 244, 245, 246, 247, 248, 249, 250, 251, 252, 253, 254, 255};

void TransformAsciiLower(const uint8_t* input, int64_t length, uint8_t* output) {
for (int64_t i = 0; i < length; ++i) {
*output++ = kAsciiLowerTable[*input++];
// As with TransformAsciiUpper, the same guarantee holds for the range [A-Z]
const uint8_t utf8_code_unit = *input++;
*output++ = ((utf8_code_unit >= 'A') && (utf8_code_unit <= 'Z'))
? (utf8_code_unit + 32)
: utf8_code_unit;
}
}

Expand Down
8 changes: 4 additions & 4 deletions cpp/src/arrow/compute/kernels/scalar_string_test.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -57,13 +57,13 @@ TYPED_TEST(TestStringKernels, AsciiLength) {
}

TYPED_TEST(TestStringKernels, AsciiUpper) {
this->CheckUnary("ascii_upper", "[\"aAa&\", null, \"\", \"b\"]", this->string_type(),
"[\"AAA&\", null, \"\", \"B\"]");
this->CheckUnary("ascii_upper", "[\"aAazZæÆ&\", null, \"\", \"b\"]",
this->string_type(), "[\"AAAZZæÆ&\", null, \"\", \"B\"]");
}

TYPED_TEST(TestStringKernels, AsciiLower) {
this->CheckUnary("ascii_lower", "[\"aAa&\", null, \"\", \"b\"]", this->string_type(),
"[\"aaa&\", null, \"\", \"b\"]");
this->CheckUnary("ascii_lower", "[\"aAazZæÆ&\", null, \"\", \"b\"]",
this->string_type(), "[\"aaazzæÆ&\", null, \"\", \"b\"]");
}

TYPED_TEST(TestStringKernels, Strptime) {
Expand Down