thevar1able/ClickHouse
1
0
Fork 0
mirror of https://github.com/ClickHouse/ClickHouse.git synced 2024-11-21 23:21:59 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' into grouping-comp

Browse Source
This commit is contained in:
Dmitry Novik 2022-09-12 15:19:51 +02:00 committed by GitHub
commit c236706703
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
468 changed files with 24736 additions and 14071 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

35
base/base/JSON.cpp
View File

@ -22,7 +22,7 @@ POCO_IMPLEMENT_EXCEPTION(JSONException, Poco::Exception, "JSONException") // NOL
#endif #endif
/// Прочитать беззнаковое целое в простом формате из не-0-terminated строки. /// Read unsigned integer in a simple form from a non-0-terminated string.
static UInt64 readUIntText(const char * buf, const char * end) static UInt64 readUIntText(const char * buf, const char * end)
{ {
UInt64 x = 0; UInt64 x = 0;
@ -59,7 +59,7 @@ static UInt64 readUIntText(const char * buf, const char * end)
} }
/// Прочитать знаковое целое в простом формате из не-0-terminated строки. /// Read signed integer in a simple form from a non-0-terminated string.
static Int64 readIntText(const char * buf, const char * end) static Int64 readIntText(const char * buf, const char * end)
{ {
bool negative = false; bool negative = false;
@ -102,7 +102,7 @@ static Int64 readIntText(const char * buf, const char * end)
} }
/// Прочитать число с плавающей запятой в простом формате, с грубым округлением, из не-0-terminated строки. /// Read floating point number in simple format, imprecisely, from a non-0-terminated string.
static double readFloatText(const char * buf, const char * end) static double readFloatText(const char * buf, const char * end)
{ {
bool negative = false; bool negative = false;
@ -151,8 +151,8 @@ static double readFloatText(const char * buf, const char * end)
case 'E': case 'E':
{ {
++buf; ++buf;
Int32 exponent = readIntText(buf, end); auto exponent = readIntText(buf, end);
x *= preciseExp10(exponent); x *= preciseExp10(static_cast<double>(exponent));
run = false; run = false;
break; break;
@ -207,7 +207,7 @@ JSON::ElementType JSON::getType() const
return TYPE_NUMBER; return TYPE_NUMBER;
case '"': case '"':
{ {
/// Проверим - это просто строка или name-value pair /// Is it a string or a name-value pair?
Pos after_string = skipString(); Pos after_string = skipString();
if (after_string < ptr_end && *after_string == ':') if (after_string < ptr_end && *after_string == ':')
return TYPE_NAME_VALUE_PAIR; return TYPE_NAME_VALUE_PAIR;
@ -229,15 +229,13 @@ void JSON::checkPos(Pos pos) const
JSON::Pos JSON::skipString() const JSON::Pos JSON::skipString() const
{ {
//std::cerr << "skipString()\t" << data() << std::endl;
Pos pos = ptr_begin; Pos pos = ptr_begin;
checkPos(pos); checkPos(pos);
if (*pos != '"') if (*pos != '"')
throw JSONException(std::string("JSON: expected \", got ") + *pos); throw JSONException(std::string("JSON: expected \", got ") + *pos);
++pos; ++pos;
/// fast path: находим следующую двойную кавычку. Если перед ней нет бэкслеша - значит это конец строки (при допущении корректности JSON). /// fast path: find next double quote. If it is not escaped by backslash - then it's an end of string (assuming JSON is valid).
Pos closing_quote = reinterpret_cast<const char *>(memchr(reinterpret_cast<const void *>(pos), '\"', ptr_end - pos)); Pos closing_quote = reinterpret_cast<const char *>(memchr(reinterpret_cast<const void *>(pos), '\"', ptr_end - pos));
if (nullptr != closing_quote && closing_quote[-1] != '\\') if (nullptr != closing_quote && closing_quote[-1] != '\\')
return closing_quote + 1; return closing_quote + 1;
@ -269,8 +267,6 @@ JSON::Pos JSON::skipString() const
JSON::Pos JSON::skipNumber() const JSON::Pos JSON::skipNumber() const
{ {
//std::cerr << "skipNumber()\t" << data() << std::endl;
Pos pos = ptr_begin; Pos pos = ptr_begin;
checkPos(pos); checkPos(pos);
@ -296,8 +292,6 @@ JSON::Pos JSON::skipNumber() const
JSON::Pos JSON::skipBool() const JSON::Pos JSON::skipBool() const
{ {
//std::cerr << "skipBool()\t" << data() << std::endl;
Pos pos = ptr_begin; Pos pos = ptr_begin;
checkPos(pos); checkPos(pos);
@ -314,16 +308,12 @@ JSON::Pos JSON::skipBool() const
JSON::Pos JSON::skipNull() const JSON::Pos JSON::skipNull() const
{ {
//std::cerr << "skipNull()\t" << data() << std::endl;
return ptr_begin + 4; return ptr_begin + 4;
} }
JSON::Pos JSON::skipNameValuePair() const JSON::Pos JSON::skipNameValuePair() const
{ {
//std::cerr << "skipNameValuePair()\t" << data() << std::endl;
Pos pos = skipString(); Pos pos = skipString();
checkPos(pos); checkPos(pos);
@ -338,8 +328,6 @@ JSON::Pos JSON::skipNameValuePair() const
JSON::Pos JSON::skipArray() const JSON::Pos JSON::skipArray() const
{ {
//std::cerr << "skipArray()\t" << data() << std::endl;
if (!isArray()) if (!isArray())
throw JSONException("JSON: expected ["); throw JSONException("JSON: expected [");
Pos pos = ptr_begin; Pos pos = ptr_begin;
@ -370,8 +358,6 @@ JSON::Pos JSON::skipArray() const
JSON::Pos JSON::skipObject() const JSON::Pos JSON::skipObject() const
{ {
//std::cerr << "skipObject()\t" << data() << std::endl;
if (!isObject()) if (!isObject())
throw JSONException("JSON: expected {"); throw JSONException("JSON: expected {");
Pos pos = ptr_begin; Pos pos = ptr_begin;
@ -402,8 +388,6 @@ JSON::Pos JSON::skipObject() const
JSON::Pos JSON::skipElement() const JSON::Pos JSON::skipElement() const
{ {
//std::cerr << "skipElement()\t" << data() << std::endl;
ElementType type = getType(); ElementType type = getType();
switch (type) switch (type)
@ -640,7 +624,7 @@ std::string JSON::getString() const
{ {
throw JSONException("JSON: incorrect syntax: incorrect HEX code."); throw JSONException("JSON: incorrect syntax: incorrect HEX code.");
} }
buf.resize(buf.size() + 6); /// максимальный размер UTF8 многобайтовой последовательности buf.resize(buf.size() + 6); /// Max size of UTF-8 sequence, including pre-standard mapping of UCS-4 to UTF-8.
int res = utf8.convert(unicode, int res = utf8.convert(unicode,
reinterpret_cast<unsigned char *>(const_cast<char*>(buf.data())) + buf.size() - 6, 6); reinterpret_cast<unsigned char *>(const_cast<char*>(buf.data())) + buf.size() - 6, 6);
if (!res) if (!res)
@ -754,8 +738,6 @@ JSON::iterator JSON::iterator::begin() const
if (type != TYPE_ARRAY && type != TYPE_OBJECT) if (type != TYPE_ARRAY && type != TYPE_OBJECT)
throw JSONException("JSON: not array or object when calling begin() method."); throw JSONException("JSON: not array or object when calling begin() method.");
//std::cerr << "begin()\t" << data() << std::endl;
Pos pos = ptr_begin + 1; Pos pos = ptr_begin + 1;
checkPos(pos); checkPos(pos);
if (*pos == '}' || *pos == ']') if (*pos == '}' || *pos == ']')
@ -846,4 +828,3 @@ bool JSON::isType<bool>() const
{ {
return isBool(); return isBool();
} }

6
base/base/StringRef.h
View File

@ -227,7 +227,7 @@ inline UInt64 shiftMix(UInt64 val)
return val ^ (val >> 47); return val ^ (val >> 47);
} }
inline UInt64 rotateByAtLeast1(UInt64 val, int shift) inline UInt64 rotateByAtLeast1(UInt64 val, UInt8 shift)
{ {
return (val >> shift) | (val << (64 - shift)); return (val >> shift) | (val << (64 - shift));
} }
@ -249,7 +249,7 @@ inline size_t hashLessThan8(const char * data, size_t size)
uint8_t b = data[size >> 1]; uint8_t b = data[size >> 1];
uint8_t c = data[size - 1]; uint8_t c = data[size - 1];
uint32_t y = static_cast<uint32_t>(a) + (static_cast<uint32_t>(b) << 8); uint32_t y = static_cast<uint32_t>(a) + (static_cast<uint32_t>(b) << 8);
uint32_t z = size + (static_cast<uint32_t>(c) << 2); uint32_t z = static_cast<uint32_t>(size) + (static_cast<uint32_t>(c) << 2);
return shiftMix(y * k2 ^ z * k3) * k2; return shiftMix(y * k2 ^ z * k3) * k2;
} }
@ -262,7 +262,7 @@ inline size_t hashLessThan16(const char * data, size_t size)
{ {
UInt64 a = unalignedLoad<UInt64>(data); UInt64 a = unalignedLoad<UInt64>(data);
UInt64 b = unalignedLoad<UInt64>(data + size - 8); UInt64 b = unalignedLoad<UInt64>(data + size - 8);
return hashLen16(a, rotateByAtLeast1(b + size, size)) ^ b; return hashLen16(a, rotateByAtLeast1(b + size, static_cast<UInt8>(size))) ^ b;
} }
return hashLessThan8(data, size); return hashLessThan8(data, size);

2
base/base/getThreadId.cpp
View File

@ -22,7 +22,7 @@ uint64_t getThreadId()
#if defined(OS_ANDROID) #if defined(OS_ANDROID)
current_tid = gettid(); current_tid = gettid();
#elif defined(OS_LINUX) #elif defined(OS_LINUX)
current_tid = syscall(SYS_gettid); /// This call is always successful. - man gettid current_tid = static_cast<uint64_t>(syscall(SYS_gettid)); /// This call is always successful. - man gettid
#elif defined(OS_FREEBSD) #elif defined(OS_FREEBSD)
current_tid = pthread_getthreadid_np(); current_tid = pthread_getthreadid_np();
#elif defined(OS_SUNOS) #elif defined(OS_SUNOS)

68
base/base/shift10.cpp
View File

@ -14,37 +14,37 @@ static T shift10Impl(T x, int exponent)
static const long double powers10[] = static const long double powers10[] =
{ {
1e-323L, 1e-322L, 1e-321L, 1e-320L, 1e-319L, 1e-318L, 1e-317L, 1e-316L, 1e-315L, 1e-314L, 1e-313L, 1e-312L, 1e-311L, 1e-323L, 1e-322L, 1e-321L, 1e-320L, 1e-319L, 1e-318L, 1e-317L, 1e-316L, 1e-315L, 1e-314L, 1e-313L, 1e-312L, 1e-311L,
1e-310L,1e-309L,1e-308L,1e-307L,1e-306L,1e-305L,1e-304L,1e-303L,1e-302L,1e-301L,1e-300L,1e-299L,1e-298L,1e-297L,1e-296L,1e-295L,1e-294L,1e-293L,1e-292L,1e-291L, 1e-310L, 1e-309L, 1e-308L, 1e-307L, 1e-306L, 1e-305L, 1e-304L, 1e-303L, 1e-302L, 1e-301L, 1e-300L, 1e-299L, 1e-298L, 1e-297L, 1e-296L, 1e-295L, 1e-294L, 1e-293L, 1e-292L, 1e-291L,
1e-290L,1e-289L,1e-288L,1e-287L,1e-286L,1e-285L,1e-284L,1e-283L,1e-282L,1e-281L,1e-280L,1e-279L,1e-278L,1e-277L,1e-276L,1e-275L,1e-274L,1e-273L,1e-272L,1e-271L, 1e-290L, 1e-289L, 1e-288L, 1e-287L, 1e-286L, 1e-285L, 1e-284L, 1e-283L, 1e-282L, 1e-281L, 1e-280L, 1e-279L, 1e-278L, 1e-277L, 1e-276L, 1e-275L, 1e-274L, 1e-273L, 1e-272L, 1e-271L,
1e-270L,1e-269L,1e-268L,1e-267L,1e-266L,1e-265L,1e-264L,1e-263L,1e-262L,1e-261L,1e-260L,1e-259L,1e-258L,1e-257L,1e-256L,1e-255L,1e-254L,1e-253L,1e-252L,1e-251L, 1e-270L, 1e-269L, 1e-268L, 1e-267L, 1e-266L, 1e-265L, 1e-264L, 1e-263L, 1e-262L, 1e-261L, 1e-260L, 1e-259L, 1e-258L, 1e-257L, 1e-256L, 1e-255L, 1e-254L, 1e-253L, 1e-252L, 1e-251L,
1e-250L,1e-249L,1e-248L,1e-247L,1e-246L,1e-245L,1e-244L,1e-243L,1e-242L,1e-241L,1e-240L,1e-239L,1e-238L,1e-237L,1e-236L,1e-235L,1e-234L,1e-233L,1e-232L,1e-231L, 1e-250L, 1e-249L, 1e-248L, 1e-247L, 1e-246L, 1e-245L, 1e-244L, 1e-243L, 1e-242L, 1e-241L, 1e-240L, 1e-239L, 1e-238L, 1e-237L, 1e-236L, 1e-235L, 1e-234L, 1e-233L, 1e-232L, 1e-231L,
1e-230L,1e-229L,1e-228L,1e-227L,1e-226L,1e-225L,1e-224L,1e-223L,1e-222L,1e-221L,1e-220L,1e-219L,1e-218L,1e-217L,1e-216L,1e-215L,1e-214L,1e-213L,1e-212L,1e-211L, 1e-230L, 1e-229L, 1e-228L, 1e-227L, 1e-226L, 1e-225L, 1e-224L, 1e-223L, 1e-222L, 1e-221L, 1e-220L, 1e-219L, 1e-218L, 1e-217L, 1e-216L, 1e-215L, 1e-214L, 1e-213L, 1e-212L, 1e-211L,
1e-210L,1e-209L,1e-208L,1e-207L,1e-206L,1e-205L,1e-204L,1e-203L,1e-202L,1e-201L,1e-200L,1e-199L,1e-198L,1e-197L,1e-196L,1e-195L,1e-194L,1e-193L,1e-192L,1e-191L, 1e-210L, 1e-209L, 1e-208L, 1e-207L, 1e-206L, 1e-205L, 1e-204L, 1e-203L, 1e-202L, 1e-201L, 1e-200L, 1e-199L, 1e-198L, 1e-197L, 1e-196L, 1e-195L, 1e-194L, 1e-193L, 1e-192L, 1e-191L,
1e-190L,1e-189L,1e-188L,1e-187L,1e-186L,1e-185L,1e-184L,1e-183L,1e-182L,1e-181L,1e-180L,1e-179L,1e-178L,1e-177L,1e-176L,1e-175L,1e-174L,1e-173L,1e-172L,1e-171L, 1e-190L, 1e-189L, 1e-188L, 1e-187L, 1e-186L, 1e-185L, 1e-184L, 1e-183L, 1e-182L, 1e-181L, 1e-180L, 1e-179L, 1e-178L, 1e-177L, 1e-176L, 1e-175L, 1e-174L, 1e-173L, 1e-172L, 1e-171L,
1e-170L,1e-169L,1e-168L,1e-167L,1e-166L,1e-165L,1e-164L,1e-163L,1e-162L,1e-161L,1e-160L,1e-159L,1e-158L,1e-157L,1e-156L,1e-155L,1e-154L,1e-153L,1e-152L,1e-151L, 1e-170L, 1e-169L, 1e-168L, 1e-167L, 1e-166L, 1e-165L, 1e-164L, 1e-163L, 1e-162L, 1e-161L, 1e-160L, 1e-159L, 1e-158L, 1e-157L, 1e-156L, 1e-155L, 1e-154L, 1e-153L, 1e-152L, 1e-151L,
1e-150L,1e-149L,1e-148L,1e-147L,1e-146L,1e-145L,1e-144L,1e-143L,1e-142L,1e-141L,1e-140L,1e-139L,1e-138L,1e-137L,1e-136L,1e-135L,1e-134L,1e-133L,1e-132L,1e-131L, 1e-150L, 1e-149L, 1e-148L, 1e-147L, 1e-146L, 1e-145L, 1e-144L, 1e-143L, 1e-142L, 1e-141L, 1e-140L, 1e-139L, 1e-138L, 1e-137L, 1e-136L, 1e-135L, 1e-134L, 1e-133L, 1e-132L, 1e-131L,
1e-130L,1e-129L,1e-128L,1e-127L,1e-126L,1e-125L,1e-124L,1e-123L,1e-122L,1e-121L,1e-120L,1e-119L,1e-118L,1e-117L,1e-116L,1e-115L,1e-114L,1e-113L,1e-112L,1e-111L, 1e-130L, 1e-129L, 1e-128L, 1e-127L, 1e-126L, 1e-125L, 1e-124L, 1e-123L, 1e-122L, 1e-121L, 1e-120L, 1e-119L, 1e-118L, 1e-117L, 1e-116L, 1e-115L, 1e-114L, 1e-113L, 1e-112L, 1e-111L,
1e-110L,1e-109L,1e-108L,1e-107L,1e-106L,1e-105L,1e-104L,1e-103L,1e-102L,1e-101L,1e-100L,1e-99L,1e-98L,1e-97L,1e-96L,1e-95L,1e-94L,1e-93L,1e-92L,1e-91L,1e-90L, 1e-110L, 1e-109L, 1e-108L, 1e-107L, 1e-106L, 1e-105L, 1e-104L, 1e-103L, 1e-102L, 1e-101L, 1e-100L, 1e-99L, 1e-98L, 1e-97L, 1e-96L, 1e-95L, 1e-94L, 1e-93L, 1e-92L, 1e-91L, 1e-90L,
1e-89L,1e-88L,1e-87L,1e-86L,1e-85L,1e-84L,1e-83L,1e-82L,1e-81L,1e-80L,1e-79L,1e-78L,1e-77L,1e-76L,1e-75L,1e-74L,1e-73L,1e-72L,1e-71L,1e-70, 1e-89L, 1e-88L, 1e-87L, 1e-86L, 1e-85L, 1e-84L, 1e-83L, 1e-82L, 1e-81L, 1e-80L, 1e-79L, 1e-78L, 1e-77L, 1e-76L, 1e-75L, 1e-74L, 1e-73L, 1e-72L, 1e-71L, 1e-70,
1e-69L,1e-68L,1e-67L,1e-66L,1e-65L,1e-64L,1e-63L,1e-62L,1e-61L,1e-60L,1e-59L,1e-58L,1e-57L,1e-56L,1e-55L,1e-54L,1e-53L,1e-52L,1e-51L,1e-50, 1e-69L, 1e-68L, 1e-67L, 1e-66L, 1e-65L, 1e-64L, 1e-63L, 1e-62L, 1e-61L, 1e-60L, 1e-59L, 1e-58L, 1e-57L, 1e-56L, 1e-55L, 1e-54L, 1e-53L, 1e-52L, 1e-51L, 1e-50,
1e-49L,1e-48L,1e-47L,1e-46L,1e-45L,1e-44L,1e-43L,1e-42L,1e-41L,1e-40L,1e-39L,1e-38L,1e-37L,1e-36L,1e-35L,1e-34L,1e-33L,1e-32L,1e-31L,1e-30, 1e-49L, 1e-48L, 1e-47L, 1e-46L, 1e-45L, 1e-44L, 1e-43L, 1e-42L, 1e-41L, 1e-40L, 1e-39L, 1e-38L, 1e-37L, 1e-36L, 1e-35L, 1e-34L, 1e-33L, 1e-32L, 1e-31L, 1e-30,
1e-29L,1e-28L,1e-27L,1e-26L,1e-25L,1e-24L,1e-23L,1e-22L,1e-21L,1e-20L,1e-19L,1e-18L,1e-17L,1e-16L,1e-15L,1e-14L,1e-13L,1e-12L,1e-11L,1e-10, 1e-29L, 1e-28L, 1e-27L, 1e-26L, 1e-25L, 1e-24L, 1e-23L, 1e-22L, 1e-21L, 1e-20L, 1e-19L, 1e-18L, 1e-17L, 1e-16L, 1e-15L, 1e-14L, 1e-13L, 1e-12L, 1e-11L, 1e-10,
1e-9L,1e-8L,1e-7L,1e-6L,1e-5L,1e-4L,1e-3L,1e-2L,1e-1L,1e0L,1e1L,1e2L,1e3L,1e4L,1e5L,1e6L,1e7L,1e8L,1e9L,1e10, 1e-9L, 1e-8L, 1e-7L, 1e-6L, 1e-5L, 1e-4L, 1e-3L, 1e-2L, 1e-1L, 1e0L, 1e1L, 1e2L, 1e3L, 1e4L, 1e5L, 1e6L, 1e7L, 1e8L, 1e9L, 1e10,
1e11L,1e12L,1e13L,1e14L,1e15L,1e16L,1e17L,1e18L,1e19L,1e20L,1e21L,1e22L,1e23L,1e24L,1e25L,1e26L,1e27L,1e28L,1e29L,1e30, 1e11L, 1e12L, 1e13L, 1e14L, 1e15L, 1e16L, 1e17L, 1e18L, 1e19L, 1e20L, 1e21L, 1e22L, 1e23L, 1e24L, 1e25L, 1e26L, 1e27L, 1e28L, 1e29L, 1e30,
1e31L,1e32L,1e33L,1e34L,1e35L,1e36L,1e37L,1e38L,1e39L,1e40L,1e41L,1e42L,1e43L,1e44L,1e45L,1e46L,1e47L,1e48L,1e49L,1e50, 1e31L, 1e32L, 1e33L, 1e34L, 1e35L, 1e36L, 1e37L, 1e38L, 1e39L, 1e40L, 1e41L, 1e42L, 1e43L, 1e44L, 1e45L, 1e46L, 1e47L, 1e48L, 1e49L, 1e50,
1e51L,1e52L,1e53L,1e54L,1e55L,1e56L,1e57L,1e58L,1e59L,1e60L,1e61L,1e62L,1e63L,1e64L,1e65L,1e66L,1e67L,1e68L,1e69L,1e70, 1e51L, 1e52L, 1e53L, 1e54L, 1e55L, 1e56L, 1e57L, 1e58L, 1e59L, 1e60L, 1e61L, 1e62L, 1e63L, 1e64L, 1e65L, 1e66L, 1e67L, 1e68L, 1e69L, 1e70,
1e71L,1e72L,1e73L,1e74L,1e75L,1e76L,1e77L,1e78L,1e79L,1e80L,1e81L,1e82L,1e83L,1e84L,1e85L,1e86L,1e87L,1e88L,1e89L,1e90, 1e71L, 1e72L, 1e73L, 1e74L, 1e75L, 1e76L, 1e77L, 1e78L, 1e79L, 1e80L, 1e81L, 1e82L, 1e83L, 1e84L, 1e85L, 1e86L, 1e87L, 1e88L, 1e89L, 1e90,
1e91L,1e92L,1e93L,1e94L,1e95L,1e96L,1e97L,1e98L,1e99L,1e100L,1e101L,1e102L,1e103L,1e104L,1e105L,1e106L,1e107L,1e108L,1e109L,1e110, 1e91L, 1e92L, 1e93L, 1e94L, 1e95L, 1e96L, 1e97L, 1e98L, 1e99L, 1e100L, 1e101L, 1e102L, 1e103L, 1e104L, 1e105L, 1e106L, 1e107L, 1e108L, 1e109L, 1e110,
1e111L,1e112L,1e113L,1e114L,1e115L,1e116L,1e117L,1e118L,1e119L,1e120L,1e121L,1e122L,1e123L,1e124L,1e125L,1e126L,1e127L,1e128L,1e129L,1e130, 1e111L, 1e112L, 1e113L, 1e114L, 1e115L, 1e116L, 1e117L, 1e118L, 1e119L, 1e120L, 1e121L, 1e122L, 1e123L, 1e124L, 1e125L, 1e126L, 1e127L, 1e128L, 1e129L, 1e130,
1e131L,1e132L,1e133L,1e134L,1e135L,1e136L,1e137L,1e138L,1e139L,1e140L,1e141L,1e142L,1e143L,1e144L,1e145L,1e146L,1e147L,1e148L,1e149L,1e150, 1e131L, 1e132L, 1e133L, 1e134L, 1e135L, 1e136L, 1e137L, 1e138L, 1e139L, 1e140L, 1e141L, 1e142L, 1e143L, 1e144L, 1e145L, 1e146L, 1e147L, 1e148L, 1e149L, 1e150,
1e151L,1e152L,1e153L,1e154L,1e155L,1e156L,1e157L,1e158L,1e159L,1e160L,1e161L,1e162L,1e163L,1e164L,1e165L,1e166L,1e167L,1e168L,1e169L,1e170, 1e151L, 1e152L, 1e153L, 1e154L, 1e155L, 1e156L, 1e157L, 1e158L, 1e159L, 1e160L, 1e161L, 1e162L, 1e163L, 1e164L, 1e165L, 1e166L, 1e167L, 1e168L, 1e169L, 1e170,
1e171L,1e172L,1e173L,1e174L,1e175L,1e176L,1e177L,1e178L,1e179L,1e180L,1e181L,1e182L,1e183L,1e184L,1e185L,1e186L,1e187L,1e188L,1e189L,1e190, 1e171L, 1e172L, 1e173L, 1e174L, 1e175L, 1e176L, 1e177L, 1e178L, 1e179L, 1e180L, 1e181L, 1e182L, 1e183L, 1e184L, 1e185L, 1e186L, 1e187L, 1e188L, 1e189L, 1e190,
1e191L,1e192L,1e193L,1e194L,1e195L,1e196L,1e197L,1e198L,1e199L,1e200L,1e201L,1e202L,1e203L,1e204L,1e205L,1e206L,1e207L,1e208L,1e209L,1e210, 1e191L, 1e192L, 1e193L, 1e194L, 1e195L, 1e196L, 1e197L, 1e198L, 1e199L, 1e200L, 1e201L, 1e202L, 1e203L, 1e204L, 1e205L, 1e206L, 1e207L, 1e208L, 1e209L, 1e210,
1e211L,1e212L,1e213L,1e214L,1e215L,1e216L,1e217L,1e218L,1e219L,1e220L,1e221L,1e222L,1e223L,1e224L,1e225L,1e226L,1e227L,1e228L,1e229L,1e230, 1e211L, 1e212L, 1e213L, 1e214L, 1e215L, 1e216L, 1e217L, 1e218L, 1e219L, 1e220L, 1e221L, 1e222L, 1e223L, 1e224L, 1e225L, 1e226L, 1e227L, 1e228L, 1e229L, 1e230,
1e231L,1e232L,1e233L,1e234L,1e235L,1e236L,1e237L,1e238L,1e239L,1e240L,1e241L,1e242L,1e243L,1e244L,1e245L,1e246L,1e247L,1e248L,1e249L,1e250, 1e231L, 1e232L, 1e233L, 1e234L, 1e235L, 1e236L, 1e237L, 1e238L, 1e239L, 1e240L, 1e241L, 1e242L, 1e243L, 1e244L, 1e245L, 1e246L, 1e247L, 1e248L, 1e249L, 1e250,
1e251L,1e252L,1e253L,1e254L,1e255L,1e256L,1e257L,1e258L,1e259L,1e260L,1e261L,1e262L,1e263L,1e264L,1e265L,1e266L,1e267L,1e268L,1e269L,1e270, 1e251L, 1e252L, 1e253L, 1e254L, 1e255L, 1e256L, 1e257L, 1e258L, 1e259L, 1e260L, 1e261L, 1e262L, 1e263L, 1e264L, 1e265L, 1e266L, 1e267L, 1e268L, 1e269L, 1e270,
1e271L,1e272L,1e273L,1e274L,1e275L,1e276L,1e277L,1e278L,1e279L,1e280L,1e281L,1e282L,1e283L,1e284L,1e285L,1e286L,1e287L,1e288L,1e289L,1e290, 1e271L, 1e272L, 1e273L, 1e274L, 1e275L, 1e276L, 1e277L, 1e278L, 1e279L, 1e280L, 1e281L, 1e282L, 1e283L, 1e284L, 1e285L, 1e286L, 1e287L, 1e288L, 1e289L, 1e290,
1e291L,1e292L,1e293L,1e294L,1e295L,1e296L,1e297L,1e298L,1e299L,1e300L,1e301L,1e302L,1e303L,1e304L,1e305L,1e306L,1e307L,1e308L 1e291L, 1e292L, 1e293L, 1e294L, 1e295L, 1e296L, 1e297L, 1e298L, 1e299L, 1e300L, 1e301L, 1e302L, 1e303L, 1e304L, 1e305L, 1e306L, 1e307L, 1e308L
}; };
if (unlikely(exponent < min_exponent)) /// Note: there are some values below MIN_EXPONENT that is greater than zero. if (unlikely(exponent < min_exponent)) /// Note: there are some values below MIN_EXPONENT that is greater than zero.
@ -52,7 +52,7 @@ static T shift10Impl(T x, int exponent)
else if (unlikely(exponent > max_exponent)) else if (unlikely(exponent > max_exponent))
x *= std::numeric_limits<T>::infinity(); /// Multiplying to keep the sign of infinity. x *= std::numeric_limits<T>::infinity(); /// Multiplying to keep the sign of infinity.
else else
x *= powers10[exponent - min_exponent]; x *= static_cast<T>(powers10[exponent - min_exponent]);
return x; return x;
} }
@ -68,12 +68,12 @@ float shift10(float x, int exponent)
return shift10Impl(x, exponent); return shift10Impl(x, exponent);
} }
double shift10(UInt64 x, int exponent) long double shift10(UInt64 x, int exponent)
{ {
return shift10Impl(static_cast<long double>(x), exponent); return shift10Impl(static_cast<long double>(x), exponent);
} }
double shift10(Int64 x, int exponent) long double shift10(Int64 x, int exponent)
{ {
return shift10Impl(static_cast<long double>(x), exponent); return shift10Impl(static_cast<long double>(x), exponent);
} }

4
base/base/shift10.h
View File

@ -12,5 +12,5 @@
double shift10(double x, int exponent); double shift10(double x, int exponent);
float shift10(float x, int exponent); float shift10(float x, int exponent);
double shift10(UInt64 x, int exponent); long double shift10(UInt64 x, int exponent);
double shift10(Int64 x, int exponent); long double shift10(Int64 x, int exponent);

10
base/base/terminalColors.cpp
View File

@ -11,12 +11,12 @@ std::string setColor(UInt64 hash)
/// It still looks awesome. /// It still looks awesome.
UInt8 y = 128; UInt8 y = 128;
UInt8 cb = hash % 256; UInt8 cb = static_cast<UInt8>(hash % 256);
UInt8 cr = hash / 256 % 256; UInt8 cr = static_cast<UInt8>(hash / 256 % 256);
UInt8 r = std::max(0.0, std::min(255.0, y + 1.402 * (cr - 128))); UInt8 r = static_cast<UInt8>(std::max(0.0, std::min(255.0, y + 1.402 * (cr - 128))));
UInt8 g = std::max(0.0, std::min(255.0, y - 0.344136 * (cb - 128) - 0.714136 * (cr - 128))); UInt8 g = static_cast<UInt8>(std::max(0.0, std::min(255.0, y - 0.344136 * (cb - 128) - 0.714136 * (cr - 128))));
UInt8 b = std::max(0.0, std::min(255.0, y + 1.772 * (cb - 128))); UInt8 b = static_cast<UInt8>(std::max(0.0, std::min(255.0, y + 1.772 * (cb - 128))));
/// ANSI escape sequence to set 24-bit foreground font color in terminal. /// ANSI escape sequence to set 24-bit foreground font color in terminal.
return "\033[38;2;" + std::to_string(r) + ";" + std::to_string(g) + ";" + std::to_string(b) + "m"; return "\033[38;2;" + std::to_string(r) + ";" + std::to_string(g) + ";" + std::to_string(b) + "m";

6
base/base/wide_integer_impl.h
View File

@ -453,7 +453,7 @@ private:
if constexpr (sizeof(T) <= sizeof(base_type)) if constexpr (sizeof(T) <= sizeof(base_type))
{ {
if (0 == idx) if (0 == idx)
return x; return static_cast<base_type>(x);
} }
else if (idx * sizeof(base_type) < sizeof(T)) else if (idx * sizeof(base_type) < sizeof(T))
return x >> (idx * base_bits); // & std::numeric_limits<base_type>::max() return x >> (idx * base_bits); // & std::numeric_limits<base_type>::max()
@ -1239,13 +1239,13 @@ constexpr integer<Bits, Signed>::operator long double() const noexcept
template <size_t Bits, typename Signed> template <size_t Bits, typename Signed>
constexpr integer<Bits, Signed>::operator double() const noexcept constexpr integer<Bits, Signed>::operator double() const noexcept
{ {
return static_cast<long double>(*this); return static_cast<double>(static_cast<long double>(*this));
} }
template <size_t Bits, typename Signed> template <size_t Bits, typename Signed>
constexpr integer<Bits, Signed>::operator float() const noexcept constexpr integer<Bits, Signed>::operator float() const noexcept
{ {
return static_cast<long double>(*this); return static_cast<float>(static_cast<long double>(*this));
} }
// Unary operators // Unary operators

2
contrib/capnproto vendored

@ -1 +1 @@
Subproject commit c8189ec3c27dacbd4a3288e682473010e377f593 Subproject commit 2e88221d3dde22266bfccf40eaee6ff9b40d113d

30
contrib/vectorscan-cmake/CMakeLists.txt
View File

@ -1,11 +1,9 @@
# We use vectorscan, a portable and API/ABI-compatible drop-in replacement for hyperscan. # We use vectorscan, a portable and API/ABI-compatible drop-in replacement for hyperscan.
if (ARCH_AMD64 AND NOT NO_SSE3_OR_HIGHER) if ((ARCH_AMD64 AND NOT NO_SSE3_OR_HIGHER) OR ARCH_AARCH64)
option (ENABLE_VECTORSCAN "Enable vectorscan library" ${ENABLE_LIBRARIES}) option (ENABLE_VECTORSCAN "Enable vectorscan library" ${ENABLE_LIBRARIES})
endif() endif()
# TODO: vectorscan supports ARM yet some tests involving cyrillic letters fail (PR #38171) ... needs further investigation
# TODO PPC should generally work but needs manual generation of ppc/config.h file on a PPC machine # TODO PPC should generally work but needs manual generation of ppc/config.h file on a PPC machine
if (NOT ENABLE_VECTORSCAN) if (NOT ENABLE_VECTORSCAN)
@ -236,11 +234,27 @@ set (SRCS
# The original build system invokes ragel on src/parser/{Parser|control_verbs}.rl (+ a few more .rl files which are unneeded). To avoid a # The original build system invokes ragel on src/parser/{Parser|control_verbs}.rl (+ a few more .rl files which are unneeded). To avoid a
# build-time dependency on ragel (via contrib/ or find_program()), add the manually generated output of ragel to the sources. # build-time dependency on ragel (via contrib/ or find_program()), add the manually generated output of ragel to the sources.
# Please regenerate these files if you update vectorscan. #
list (APPEND SRCS # Please regenerate these files if you update vectorscan. They must be regenerated for each platform separately because ragel produces for
"${LIBRARY_DIR}/../vectorscan-cmake/rageled_files/Parser.cpp" # weird reasons different constants in the output.
"${LIBRARY_DIR}/../vectorscan-cmake/rageled_files/control_verbs.cpp" #
) # Also, please use upstream versions of colm and ragel, the packages in Ubuntu 22.04 seem to produce wrong output on ARM.
if (ARCH_AMD64)
list (APPEND SRCS
"${LIBRARY_DIR}/../vectorscan-cmake/rageled_files/amd64/Parser.cpp"
"${LIBRARY_DIR}/../vectorscan-cmake/rageled_files/amd64/control_verbs.cpp"
)
elseif (ARCH_AARCH64)
list (APPEND SRCS
"${LIBRARY_DIR}/../vectorscan-cmake/rageled_files/aarch64/Parser.cpp"
"${LIBRARY_DIR}/../vectorscan-cmake/rageled_files/aarch64/control_verbs.cpp"
)
set_source_files_properties(
"${LIBRARY_DIR}/../vectorscan-cmake/rageled_files/aarch64/Parser.cpp"
"${LIBRARY_DIR}/../vectorscan-cmake/rageled_files/aarch64/control_verbs.cpp"
COMPILE_FLAGS -Wno-c++11-narrowing
)
endif()
# Platform-dependent files # Platform-dependent files
if (ARCH_AMD64) if (ARCH_AMD64)

5605
contrib/vectorscan-cmake/rageled_files/Parser.cpp
View File

File diff suppressed because it is too large Load Diff

10725
contrib/vectorscan-cmake/rageled_files/aarch64/Parser.cpp Normal file
View File

File diff suppressed because it is too large Load Diff

547
contrib/vectorscan-cmake/rageled_files/aarch64/control_verbs.cpp Normal file
View File

@ -0,0 +1,547 @@
#line 1 "control_verbs.rl"
/*
* Copyright (c) 2017, Intel Corporation
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are met:
*
* * Redistributions of source code must retain the above copyright notice,
* this list of conditions and the following disclaimer.
* * Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* * Neither the name of Intel Corporation nor the names of its contributors
* may be used to endorse or promote products derived from this software
* without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
* AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
* LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
* CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
* SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
* INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
* CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
* ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
* POSSIBILITY OF SUCH DAMAGE.
*/
/**
* \file
* \brief Parser for control verbs that can occur at the beginning of a pattern.
*/
#include "parser/control_verbs.h"
#include "parser/Parser.h"
#include "parser/parse_error.h"
#include <cstring>
#include <sstream>
using namespace std;
namespace ue2 {
const char *read_control_verbs(const char *ptr, const char *end, size_t start,
ParseMode &mode) {
const char *p = ptr;
const char *pe = end;
const char *eof = pe;
const char *ts, *te;
int cs;
UNUSED int act;
#line 56 "control_verbs.cpp"
static const signed char _ControlVerbs_actions[] = {
0, 1, 0, 1, 1, 1, 2, 1,
3, 1, 4, 1, 5, 1, 6, 1,
7, 1, 8, 1, 9, 0
};
static const short _ControlVerbs_key_offsets[] = {
0, 7, 8, 10, 12, 14, 16, 18,
20, 21, 23, 25, 27, 30, 32, 34,
36, 38, 40, 42, 44, 46, 48, 50,
52, 55, 57, 59, 61, 63, 66, 68,
70, 72, 74, 76, 79, 82, 84, 86,
88, 90, 92, 94, 96, 98, 100, 102,
105, 107, 109, 111, 113, 115, 117, 119,
121, 123, 125, 127, 129, 131, 133, 135,
137, 139, 141, 143, 146, 148, 149, 151,
155, 157, 159, 160, 161, 0
};
static const char _ControlVerbs_trans_keys[] = {
41u, 65u, 66u, 67u, 76u, 78u, 85u, 41u,
41u, 78u, 41u, 89u, 41u, 67u, 41u, 82u,
41u, 76u, 41u, 70u, 41u, 41u, 83u, 41u,
82u, 41u, 95u, 41u, 65u, 85u, 41u, 78u,
41u, 89u, 41u, 67u, 41u, 78u, 41u, 73u,
41u, 67u, 41u, 79u, 41u, 68u, 41u, 69u,
41u, 82u, 41u, 76u, 41u, 70u, 73u, 41u,
77u, 41u, 73u, 41u, 84u, 41u, 95u, 41u,
77u, 82u, 41u, 65u, 41u, 84u, 41u, 67u,
41u, 72u, 41u, 61u, 41u, 48u, 57u, 41u,
48u, 57u, 41u, 69u, 41u, 67u, 41u, 85u,
41u, 82u, 41u, 83u, 41u, 73u, 41u, 79u,
41u, 78u, 41u, 79u, 41u, 95u, 41u, 65u,
83u, 41u, 85u, 41u, 84u, 41u, 79u, 41u,
95u, 41u, 80u, 41u, 79u, 41u, 83u, 41u,
83u, 41u, 69u, 41u, 83u, 41u, 83u, 41u,
84u, 41u, 65u, 41u, 82u, 41u, 84u, 41u,
95u, 41u, 79u, 41u, 80u, 41u, 84u, 41u,
67u, 84u, 41u, 80u, 41u, 41u, 70u, 41u,
49u, 51u, 56u, 41u, 54u, 41u, 50u, 41u,
40u, 42u, 0u
};
static const signed char _ControlVerbs_single_lengths[] = {
7, 1, 2, 2, 2, 2, 2, 2,
1, 2, 2, 2, 3, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2,
3, 2, 2, 2, 2, 3, 2, 2,
2, 2, 2, 1, 1, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 3,
2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 3, 2, 1, 2, 4,
2, 2, 1, 1, 1, 0
};
static const signed char _ControlVerbs_range_lengths[] = {
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 1, 1, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0
};
static const short _ControlVerbs_index_offsets[] = {
0, 8, 10, 13, 16, 19, 22, 25,
28, 30, 33, 36, 39, 43, 46, 49,
52, 55, 58, 61, 64, 67, 70, 73,
76, 80, 83, 86, 89, 92, 96, 99,
102, 105, 108, 111, 114, 117, 120, 123,
126, 129, 132, 135, 138, 141, 144, 147,
151, 154, 157, 160, 163, 166, 169, 172,
175, 178, 181, 184, 187, 190, 193, 196,
199, 202, 205, 208, 212, 215, 217, 220,
225, 228, 231, 233, 235, 0
};
static const signed char _ControlVerbs_cond_targs[] = {
75, 2, 9, 22, 24, 45, 67, 1,
75, 1, 75, 3, 1, 75, 4, 1,
75, 5, 1, 75, 6, 1, 75, 7,
1, 75, 8, 1, 75, 1, 75, 10,
1, 75, 11, 1, 75, 12, 1, 75,
13, 16, 1, 75, 14, 1, 75, 15,
1, 75, 5, 1, 75, 17, 1, 75,
18, 1, 75, 19, 1, 75, 20, 1,
75, 21, 1, 75, 8, 1, 75, 23,
1, 75, 7, 1, 75, 8, 25, 1,
75, 26, 1, 75, 27, 1, 75, 28,
1, 75, 29, 1, 75, 30, 37, 1,
75, 31, 1, 75, 32, 1, 75, 33,
1, 75, 34, 1, 75, 35, 1, 75,
36, 1, 75, 36, 1, 75, 38, 1,
75, 39, 1, 75, 40, 1, 75, 41,
1, 75, 42, 1, 75, 43, 1, 75,
44, 1, 75, 34, 1, 75, 46, 1,
75, 47, 1, 75, 48, 59, 1, 75,
49, 1, 75, 50, 1, 75, 51, 1,
75, 52, 1, 75, 53, 1, 75, 54,
1, 75, 55, 1, 75, 56, 1, 75,
57, 1, 75, 58, 1, 75, 8, 1,
75, 60, 1, 75, 61, 1, 75, 62,
1, 75, 63, 1, 75, 64, 1, 75,
65, 1, 75, 66, 1, 75, 8, 1,
75, 68, 70, 1, 75, 69, 1, 75,
1, 75, 71, 1, 75, 72, 73, 74,
1, 75, 8, 1, 75, 8, 1, 75,
1, 76, 75, 0, 75, 75, 75, 75,
75, 75, 75, 75, 75, 75, 75, 75,
75, 75, 75, 75, 75, 75, 75, 75,
75, 75, 75, 75, 75, 75, 75, 75,
75, 75, 75, 75, 75, 75, 75, 75,
75, 75, 75, 75, 75, 75, 75, 75,
75, 75, 75, 75, 75, 75, 75, 75,
75, 75, 75, 75, 75, 75, 75, 75,
75, 75, 75, 75, 75, 75, 75, 75,
75, 75, 75, 75, 75, 75, 75, 75,
75, 75, 0
};
static const signed char _ControlVerbs_cond_actions[] = {
19, 0, 0, 0, 0, 0, 0, 0,
13, 0, 13, 0, 0, 13, 0, 0,
11, 0, 0, 13, 0, 0, 13, 0,
0, 13, 0, 0, 11, 0, 13, 0,
0, 13, 0, 0, 13, 0, 0, 13,
0, 0, 0, 13, 0, 0, 13, 0,
0, 13, 0, 0, 13, 0, 0, 13,
0, 0, 13, 0, 0, 13, 0, 0,
13, 0, 0, 13, 0, 0, 13, 0,
0, 11, 0, 0, 13, 0, 0, 0,
13, 0, 0, 13, 0, 0, 13, 0,
0, 13, 0, 0, 13, 0, 0, 0,
13, 0, 0, 13, 0, 0, 13, 0,
0, 13, 0, 0, 13, 0, 0, 13,
0, 0, 11, 0, 0, 13, 0, 0,
13, 0, 0, 13, 0, 0, 13, 0,
0, 13, 0, 0, 13, 0, 0, 13,
0, 0, 13, 0, 0, 13, 0, 0,
13, 0, 0, 13, 0, 0, 0, 13,
0, 0, 13, 0, 0, 13, 0, 0,
13, 0, 0, 13, 0, 0, 13, 0,
0, 13, 0, 0, 13, 0, 0, 13,
0, 0, 13, 0, 0, 13, 0, 0,
13, 0, 0, 13, 0, 0, 13, 0,
0, 13, 0, 0, 13, 0, 0, 13,
0, 0, 13, 0, 0, 13, 0, 0,
13, 0, 0, 0, 13, 0, 0, 9,
0, 13, 0, 0, 7, 0, 0, 0,
0, 13, 0, 0, 13, 0, 0, 7,
0, 5, 15, 0, 17, 19, 19, 19,
19, 19, 19, 19, 19, 19, 19, 19,
19, 19, 19, 19, 19, 19, 19, 19,
19, 19, 19, 19, 19, 19, 19, 19,
19, 19, 19, 19, 19, 19, 19, 19,
19, 19, 19, 19, 19, 19, 19, 19,
19, 19, 19, 19, 19, 19, 19, 19,
19, 19, 19, 19, 19, 19, 19, 19,
19, 19, 19, 19, 19, 19, 19, 19,
19, 19, 19, 19, 19, 19, 19, 19,
0, 17, 0
};
static const signed char _ControlVerbs_to_state_actions[] = {
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 1, 0, 0
};
static const signed char _ControlVerbs_from_state_actions[] = {
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 3, 0, 0
};
static const short _ControlVerbs_eof_trans[] = {
238, 239, 240, 241, 242, 243, 244, 245,
246, 247, 248, 249, 250, 251, 252, 253,
254, 255, 256, 257, 258, 259, 260, 261,
262, 263, 264, 265, 266, 267, 268, 269,
270, 271, 272, 273, 274, 275, 276, 277,
278, 279, 280, 281, 282, 283, 284, 285,
286, 287, 288, 289, 290, 291, 292, 293,
294, 295, 296, 297, 298, 299, 300, 301,
302, 303, 304, 305, 306, 307, 308, 309,
310, 311, 312, 313, 314, 0
};
static const int ControlVerbs_start = 75;
static const int ControlVerbs_first_final = 75;
static const int ControlVerbs_error = -1;
static const int ControlVerbs_en_main = 75;
#line 269 "control_verbs.cpp"
{
cs = (int)ControlVerbs_start;
ts = 0;
te = 0;
}
#line 105 "control_verbs.rl"
try {
#line 278 "control_verbs.cpp"
{
int _klen;
unsigned int _trans = 0;
const char * _keys;
const signed char * _acts;
unsigned int _nacts;
_resume: {}
if ( p == pe && p != eof )
goto _out;
_acts = ( _ControlVerbs_actions + (_ControlVerbs_from_state_actions[cs]));
_nacts = (unsigned int)(*( _acts));
_acts += 1;
while ( _nacts > 0 ) {
switch ( (*( _acts)) ) {
case 1: {
{
#line 1 "NONE"
{ts = p;}}
#line 297 "control_verbs.cpp"
break;
}
}
_nacts -= 1;
_acts += 1;
}
if ( p == eof ) {
if ( _ControlVerbs_eof_trans[cs] > 0 ) {
_trans = (unsigned int)_ControlVerbs_eof_trans[cs] - 1;
}
}
else {
_keys = ( _ControlVerbs_trans_keys + (_ControlVerbs_key_offsets[cs]));
_trans = (unsigned int)_ControlVerbs_index_offsets[cs];
_klen = (int)_ControlVerbs_single_lengths[cs];
if ( _klen > 0 ) {
const char *_lower = _keys;
const char *_upper = _keys + _klen - 1;
const char *_mid;
while ( 1 ) {
if ( _upper < _lower ) {
_keys += _klen;
_trans += (unsigned int)_klen;
break;
}
_mid = _lower + ((_upper-_lower) >> 1);
if ( ( (*( p))) < (*( _mid)) )
_upper = _mid - 1;
else if ( ( (*( p))) > (*( _mid)) )
_lower = _mid + 1;
else {
_trans += (unsigned int)(_mid - _keys);
goto _match;
}
}
}
_klen = (int)_ControlVerbs_range_lengths[cs];
if ( _klen > 0 ) {
const char *_lower = _keys;
const char *_upper = _keys + (_klen<<1) - 2;
const char *_mid;
while ( 1 ) {
if ( _upper < _lower ) {
_trans += (unsigned int)_klen;
break;
}
_mid = _lower + (((_upper-_lower) >> 1) & ~1);
if ( ( (*( p))) < (*( _mid)) )
_upper = _mid - 2;
else if ( ( (*( p))) > (*( _mid + 1)) )
_lower = _mid + 2;
else {
_trans += (unsigned int)((_mid - _keys)>>1);
break;
}
}
}
_match: {}
}
cs = (int)_ControlVerbs_cond_targs[_trans];
if ( _ControlVerbs_cond_actions[_trans] != 0 ) {
_acts = ( _ControlVerbs_actions + (_ControlVerbs_cond_actions[_trans]));
_nacts = (unsigned int)(*( _acts));
_acts += 1;
while ( _nacts > 0 ) {
switch ( (*( _acts)) )
{
case 2: {
{
#line 1 "NONE"
{te = p+1;}}
#line 378 "control_verbs.cpp"
break;
}
case 3: {
{
#line 76 "control_verbs.rl"
{te = p+1;{
#line 76 "control_verbs.rl"
mode.utf8 = true;
}
}}
#line 391 "control_verbs.cpp"
break;
}
case 4: {
{
#line 80 "control_verbs.rl"
{te = p+1;{
#line 80 "control_verbs.rl"
mode.ucp = true;
}
}}
#line 404 "control_verbs.cpp"
break;
}
case 5: {
{
#line 84 "control_verbs.rl"
{te = p+1;{
#line 84 "control_verbs.rl"
ostringstream str;
str << "Unsupported control verb " << string(ts, te - ts);
throw LocatedParseError(str.str());
}
}}
#line 419 "control_verbs.cpp"
break;
}
case 6: {
{
#line 90 "control_verbs.rl"
{te = p+1;{
#line 90 "control_verbs.rl"
ostringstream str;
str << "Unknown control verb " << string(ts, te - ts);
throw LocatedParseError(str.str());
}
}}
#line 434 "control_verbs.cpp"
break;
}
case 7: {
{
#line 97 "control_verbs.rl"
{te = p+1;{
#line 97 "control_verbs.rl"
{p = p - 1; }
{p += 1; goto _out; }
}
}}
#line 448 "control_verbs.cpp"
break;
}
case 8: {
{
#line 97 "control_verbs.rl"
{te = p;p = p - 1;{
#line 97 "control_verbs.rl"
{p = p - 1; }
{p += 1; goto _out; }
}
}}
#line 462 "control_verbs.cpp"
break;
}
case 9: {
{
#line 97 "control_verbs.rl"
{p = ((te))-1;
{
#line 97 "control_verbs.rl"
{p = p - 1; }
{p += 1; goto _out; }
}
}}
#line 477 "control_verbs.cpp"
break;
}
}
_nacts -= 1;
_acts += 1;
}
}
if ( p == eof ) {
if ( cs >= 75 )
goto _out;
}
else {
_acts = ( _ControlVerbs_actions + (_ControlVerbs_to_state_actions[cs]));
_nacts = (unsigned int)(*( _acts));
_acts += 1;
while ( _nacts > 0 ) {
switch ( (*( _acts)) ) {
case 0: {
{
#line 1 "NONE"
{ts = 0;}}
#line 502 "control_verbs.cpp"
break;
}
}
_nacts -= 1;
_acts += 1;
}
p += 1;
goto _resume;
}
_out: {}
}
#line 108 "control_verbs.rl"
} catch (LocatedParseError &error) {
if (ts >= ptr && ts <= pe) {
error.locate(ts - ptr + start);
} else {
error.locate(0);
}
throw;
}
return p;
}
} // namespace ue2

10725
contrib/vectorscan-cmake/rageled_files/amd64/Parser.cpp Normal file
View File

File diff suppressed because it is too large Load Diff

547
contrib/vectorscan-cmake/rageled_files/amd64/control_verbs.cpp Normal file
View File

@ -0,0 +1,547 @@
#line 1 "control_verbs.rl"
/*
* Copyright (c) 2017, Intel Corporation
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are met:
*
* * Redistributions of source code must retain the above copyright notice,
* this list of conditions and the following disclaimer.
* * Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* * Neither the name of Intel Corporation nor the names of its contributors
* may be used to endorse or promote products derived from this software
* without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
* AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
* LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
* CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
* SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
* INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
* CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
* ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
* POSSIBILITY OF SUCH DAMAGE.
*/
/**
* \file
* \brief Parser for control verbs that can occur at the beginning of a pattern.
*/
#include "parser/control_verbs.h"
#include "parser/Parser.h"
#include "parser/parse_error.h"
#include <cstring>
#include <sstream>
using namespace std;
namespace ue2 {
const char *read_control_verbs(const char *ptr, const char *end, size_t start,
ParseMode &mode) {
const char *p = ptr;
const char *pe = end;
const char *eof = pe;
const char *ts, *te;
int cs;
UNUSED int act;
#line 56 "control_verbs.cpp"
static const signed char _ControlVerbs_actions[] = {
0, 1, 0, 1, 1, 1, 2, 1,
3, 1, 4, 1, 5, 1, 6, 1,
7, 1, 8, 1, 9, 0
};
static const short _ControlVerbs_key_offsets[] = {
0, 7, 8, 10, 12, 14, 16, 18,
20, 21, 23, 25, 27, 30, 32, 34,
36, 38, 40, 42, 44, 46, 48, 50,
52, 55, 57, 59, 61, 63, 66, 68,
70, 72, 74, 76, 79, 82, 84, 86,
88, 90, 92, 94, 96, 98, 100, 102,
105, 107, 109, 111, 113, 115, 117, 119,
121, 123, 125, 127, 129, 131, 133, 135,
137, 139, 141, 143, 146, 148, 149, 151,
155, 157, 159, 160, 161, 0
};
static const char _ControlVerbs_trans_keys[] = {
41, 65, 66, 67, 76, 78, 85, 41,
41, 78, 41, 89, 41, 67, 41, 82,
41, 76, 41, 70, 41, 41, 83, 41,
82, 41, 95, 41, 65, 85, 41, 78,
41, 89, 41, 67, 41, 78, 41, 73,
41, 67, 41, 79, 41, 68, 41, 69,
41, 82, 41, 76, 41, 70, 73, 41,
77, 41, 73, 41, 84, 41, 95, 41,
77, 82, 41, 65, 41, 84, 41, 67,
41, 72, 41, 61, 41, 48, 57, 41,
48, 57, 41, 69, 41, 67, 41, 85,
41, 82, 41, 83, 41, 73, 41, 79,
41, 78, 41, 79, 41, 95, 41, 65,
83, 41, 85, 41, 84, 41, 79, 41,
95, 41, 80, 41, 79, 41, 83, 41,
83, 41, 69, 41, 83, 41, 83, 41,
84, 41, 65, 41, 82, 41, 84, 41,
95, 41, 79, 41, 80, 41, 84, 41,
67, 84, 41, 80, 41, 41, 70, 41,
49, 51, 56, 41, 54, 41, 50, 41,
40, 42, 0
};
static const signed char _ControlVerbs_single_lengths[] = {
7, 1, 2, 2, 2, 2, 2, 2,
1, 2, 2, 2, 3, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2,
3, 2, 2, 2, 2, 3, 2, 2,
2, 2, 2, 1, 1, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 3,
2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 3, 2, 1, 2, 4,
2, 2, 1, 1, 1, 0
};
static const signed char _ControlVerbs_range_lengths[] = {
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 1, 1, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0
};
static const short _ControlVerbs_index_offsets[] = {
0, 8, 10, 13, 16, 19, 22, 25,
28, 30, 33, 36, 39, 43, 46, 49,
52, 55, 58, 61, 64, 67, 70, 73,
76, 80, 83, 86, 89, 92, 96, 99,
102, 105, 108, 111, 114, 117, 120, 123,
126, 129, 132, 135, 138, 141, 144, 147,
151, 154, 157, 160, 163, 166, 169, 172,
175, 178, 181, 184, 187, 190, 193, 196,
199, 202, 205, 208, 212, 215, 217, 220,
225, 228, 231, 233, 235, 0
};
static const signed char _ControlVerbs_cond_targs[] = {
75, 2, 9, 22, 24, 45, 67, 1,
75, 1, 75, 3, 1, 75, 4, 1,
75, 5, 1, 75, 6, 1, 75, 7,
1, 75, 8, 1, 75, 1, 75, 10,
1, 75, 11, 1, 75, 12, 1, 75,
13, 16, 1, 75, 14, 1, 75, 15,
1, 75, 5, 1, 75, 17, 1, 75,
18, 1, 75, 19, 1, 75, 20, 1,
75, 21, 1, 75, 8, 1, 75, 23,
1, 75, 7, 1, 75, 8, 25, 1,
75, 26, 1, 75, 27, 1, 75, 28,
1, 75, 29, 1, 75, 30, 37, 1,
75, 31, 1, 75, 32, 1, 75, 33,
1, 75, 34, 1, 75, 35, 1, 75,
36, 1, 75, 36, 1, 75, 38, 1,
75, 39, 1, 75, 40, 1, 75, 41,
1, 75, 42, 1, 75, 43, 1, 75,
44, 1, 75, 34, 1, 75, 46, 1,
75, 47, 1, 75, 48, 59, 1, 75,
49, 1, 75, 50, 1, 75, 51, 1,
75, 52, 1, 75, 53, 1, 75, 54,
1, 75, 55, 1, 75, 56, 1, 75,
57, 1, 75, 58, 1, 75, 8, 1,
75, 60, 1, 75, 61, 1, 75, 62,
1, 75, 63, 1, 75, 64, 1, 75,
65, 1, 75, 66, 1, 75, 8, 1,
75, 68, 70, 1, 75, 69, 1, 75,
1, 75, 71, 1, 75, 72, 73, 74,
1, 75, 8, 1, 75, 8, 1, 75,
1, 76, 75, 0, 75, 75, 75, 75,
75, 75, 75, 75, 75, 75, 75, 75,
75, 75, 75, 75, 75, 75, 75, 75,
75, 75, 75, 75, 75, 75, 75, 75,
75, 75, 75, 75, 75, 75, 75, 75,
75, 75, 75, 75, 75, 75, 75, 75,
75, 75, 75, 75, 75, 75, 75, 75,
75, 75, 75, 75, 75, 75, 75, 75,
75, 75, 75, 75, 75, 75, 75, 75,
75, 75, 75, 75, 75, 75, 75, 75,
75, 75, 0
};
static const signed char _ControlVerbs_cond_actions[] = {
19, 0, 0, 0, 0, 0, 0, 0,
13, 0, 13, 0, 0, 13, 0, 0,
11, 0, 0, 13, 0, 0, 13, 0,
0, 13, 0, 0, 11, 0, 13, 0,
0, 13, 0, 0, 13, 0, 0, 13,
0, 0, 0, 13, 0, 0, 13, 0,
0, 13, 0, 0, 13, 0, 0, 13,
0, 0, 13, 0, 0, 13, 0, 0,
13, 0, 0, 13, 0, 0, 13, 0,
0, 11, 0, 0, 13, 0, 0, 0,
13, 0, 0, 13, 0, 0, 13, 0,
0, 13, 0, 0, 13, 0, 0, 0,
13, 0, 0, 13, 0, 0, 13, 0,
0, 13, 0, 0, 13, 0, 0, 13,
0, 0, 11, 0, 0, 13, 0, 0,
13, 0, 0, 13, 0, 0, 13, 0,
0, 13, 0, 0, 13, 0, 0, 13,
0, 0, 13, 0, 0, 13, 0, 0,
13, 0, 0, 13, 0, 0, 0, 13,
0, 0, 13, 0, 0, 13, 0, 0,
13, 0, 0, 13, 0, 0, 13, 0,
0, 13, 0, 0, 13, 0, 0, 13,
0, 0, 13, 0, 0, 13, 0, 0,
13, 0, 0, 13, 0, 0, 13, 0,
0, 13, 0, 0, 13, 0, 0, 13,
0, 0, 13, 0, 0, 13, 0, 0,
13, 0, 0, 0, 13, 0, 0, 9,
0, 13, 0, 0, 7, 0, 0, 0,
0, 13, 0, 0, 13, 0, 0, 7,
0, 5, 15, 0, 17, 19, 19, 19,
19, 19, 19, 19, 19, 19, 19, 19,
19, 19, 19, 19, 19, 19, 19, 19,
19, 19, 19, 19, 19, 19, 19, 19,
19, 19, 19, 19, 19, 19, 19, 19,
19, 19, 19, 19, 19, 19, 19, 19,
19, 19, 19, 19, 19, 19, 19, 19,
19, 19, 19, 19, 19, 19, 19, 19,
19, 19, 19, 19, 19, 19, 19, 19,
19, 19, 19, 19, 19, 19, 19, 19,
0, 17, 0
};
static const signed char _ControlVerbs_to_state_actions[] = {
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 1, 0, 0
};
static const signed char _ControlVerbs_from_state_actions[] = {
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 3, 0, 0
};
static const short _ControlVerbs_eof_trans[] = {
238, 239, 240, 241, 242, 243, 244, 245,
246, 247, 248, 249, 250, 251, 252, 253,
254, 255, 256, 257, 258, 259, 260, 261,
262, 263, 264, 265, 266, 267, 268, 269,
270, 271, 272, 273, 274, 275, 276, 277,
278, 279, 280, 281, 282, 283, 284, 285,
286, 287, 288, 289, 290, 291, 292, 293,
294, 295, 296, 297, 298, 299, 300, 301,
302, 303, 304, 305, 306, 307, 308, 309,
310, 311, 312, 313, 314, 0
};
static const int ControlVerbs_start = 75;
static const int ControlVerbs_first_final = 75;
static const int ControlVerbs_error = -1;
static const int ControlVerbs_en_main = 75;
#line 269 "control_verbs.cpp"
{
cs = (int)ControlVerbs_start;
ts = 0;
te = 0;
}
#line 105 "control_verbs.rl"
try {
#line 278 "control_verbs.cpp"
{
int _klen;
unsigned int _trans = 0;
const char * _keys;
const signed char * _acts;
unsigned int _nacts;
_resume: {}
if ( p == pe && p != eof )
goto _out;
_acts = ( _ControlVerbs_actions + (_ControlVerbs_from_state_actions[cs]));
_nacts = (unsigned int)(*( _acts));
_acts += 1;
while ( _nacts > 0 ) {
switch ( (*( _acts)) ) {
case 1: {
{
#line 1 "NONE"
{ts = p;}}
#line 297 "control_verbs.cpp"
break;
}
}
_nacts -= 1;
_acts += 1;
}
if ( p == eof ) {
if ( _ControlVerbs_eof_trans[cs] > 0 ) {
_trans = (unsigned int)_ControlVerbs_eof_trans[cs] - 1;
}
}
else {
_keys = ( _ControlVerbs_trans_keys + (_ControlVerbs_key_offsets[cs]));
_trans = (unsigned int)_ControlVerbs_index_offsets[cs];
_klen = (int)_ControlVerbs_single_lengths[cs];
if ( _klen > 0 ) {
const char *_lower = _keys;
const char *_upper = _keys + _klen - 1;
const char *_mid;
while ( 1 ) {
if ( _upper < _lower ) {
_keys += _klen;
_trans += (unsigned int)_klen;
break;
}
_mid = _lower + ((_upper-_lower) >> 1);
if ( ( (*( p))) < (*( _mid)) )
_upper = _mid - 1;
else if ( ( (*( p))) > (*( _mid)) )
_lower = _mid + 1;
else {
_trans += (unsigned int)(_mid - _keys);
goto _match;
}
}
}
_klen = (int)_ControlVerbs_range_lengths[cs];
if ( _klen > 0 ) {
const char *_lower = _keys;
const char *_upper = _keys + (_klen<<1) - 2;
const char *_mid;
while ( 1 ) {
if ( _upper < _lower ) {
_trans += (unsigned int)_klen;
break;
}
_mid = _lower + (((_upper-_lower) >> 1) & ~1);
if ( ( (*( p))) < (*( _mid)) )
_upper = _mid - 2;
else if ( ( (*( p))) > (*( _mid + 1)) )
_lower = _mid + 2;
else {
_trans += (unsigned int)((_mid - _keys)>>1);
break;
}
}
}
_match: {}
}
cs = (int)_ControlVerbs_cond_targs[_trans];
if ( _ControlVerbs_cond_actions[_trans] != 0 ) {
_acts = ( _ControlVerbs_actions + (_ControlVerbs_cond_actions[_trans]));
_nacts = (unsigned int)(*( _acts));
_acts += 1;
while ( _nacts > 0 ) {
switch ( (*( _acts)) )
{
case 2: {
{
#line 1 "NONE"
{te = p+1;}}
#line 378 "control_verbs.cpp"
break;
}
case 3: {
{
#line 76 "control_verbs.rl"
{te = p+1;{
#line 76 "control_verbs.rl"
mode.utf8 = true;
}
}}
#line 391 "control_verbs.cpp"
break;
}
case 4: {
{
#line 80 "control_verbs.rl"
{te = p+1;{
#line 80 "control_verbs.rl"
mode.ucp = true;
}
}}
#line 404 "control_verbs.cpp"
break;
}
case 5: {
{
#line 84 "control_verbs.rl"
{te = p+1;{
#line 84 "control_verbs.rl"
ostringstream str;
str << "Unsupported control verb " << string(ts, te - ts);
throw LocatedParseError(str.str());
}
}}
#line 419 "control_verbs.cpp"
break;
}
case 6: {
{
#line 90 "control_verbs.rl"
{te = p+1;{
#line 90 "control_verbs.rl"
ostringstream str;
str << "Unknown control verb " << string(ts, te - ts);
throw LocatedParseError(str.str());
}
}}
#line 434 "control_verbs.cpp"
break;
}
case 7: {
{
#line 97 "control_verbs.rl"
{te = p+1;{
#line 97 "control_verbs.rl"
{p = p - 1; }
{p += 1; goto _out; }
}
}}
#line 448 "control_verbs.cpp"
break;
}
case 8: {
{
#line 97 "control_verbs.rl"
{te = p;p = p - 1;{
#line 97 "control_verbs.rl"
{p = p - 1; }
{p += 1; goto _out; }
}
}}
#line 462 "control_verbs.cpp"
break;
}
case 9: {
{
#line 97 "control_verbs.rl"
{p = ((te))-1;
{
#line 97 "control_verbs.rl"
{p = p - 1; }
{p += 1; goto _out; }
}
}}
#line 477 "control_verbs.cpp"
break;
}
}
_nacts -= 1;
_acts += 1;
}
}
if ( p == eof ) {
if ( cs >= 75 )
goto _out;
}
else {
_acts = ( _ControlVerbs_actions + (_ControlVerbs_to_state_actions[cs]));
_nacts = (unsigned int)(*( _acts));
_acts += 1;
while ( _nacts > 0 ) {
switch ( (*( _acts)) ) {
case 0: {
{
#line 1 "NONE"
{ts = 0;}}
#line 502 "control_verbs.cpp"
break;
}
}
_nacts -= 1;
_acts += 1;
}
p += 1;
goto _resume;
}
_out: {}
}
#line 108 "control_verbs.rl"
} catch (LocatedParseError &error) {
if (ts >= ptr && ts <= pe) {
error.locate(ts - ptr + start);
} else {
error.locate(0);
}
throw;
}
return p;
}
} // namespace ue2

443
contrib/vectorscan-cmake/rageled_files/control_verbs.cpp
View File

@ -1,443 +0,0 @@
#line 1 "control_verbs.rl"
/*
* Copyright (c) 2017, Intel Corporation
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are met:
*
* * Redistributions of source code must retain the above copyright notice,
* this list of conditions and the following disclaimer.
* * Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* * Neither the name of Intel Corporation nor the names of its contributors
* may be used to endorse or promote products derived from this software
* without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
* AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
* LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
* CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
* SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
* INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
* CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
* ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
* POSSIBILITY OF SUCH DAMAGE.
*/
/**
* \file
* \brief Parser for control verbs that can occur at the beginning of a pattern.
*/
#include "parser/control_verbs.h"
#include "parser/Parser.h"
#include "parser/parse_error.h"
#include <cstring>
#include <sstream>
using namespace std;
namespace ue2 {
const char *read_control_verbs(const char *ptr, const char *end, size_t start,
ParseMode &mode) {
const char *p = ptr;
const char *pe = end;
const char *eof = pe;
const char *ts, *te;
int cs;
UNUSED int act;
#line 59 "control_verbs.cpp"
static const char _ControlVerbs_actions[] = {
0, 1, 0, 1, 1, 1, 2, 1,
3, 1, 4, 1, 5, 1, 6, 1,
7, 1, 8, 1, 9
};
static const unsigned char _ControlVerbs_key_offsets[] = {
0, 7, 8, 10, 12, 14, 16, 18,
20, 21, 23, 25, 27, 30, 32, 34,
36, 38, 40, 42, 44, 46, 48, 50,
52, 55, 57, 59, 61, 63, 66, 68,
70, 72, 74, 76, 79, 82, 84, 86,
88, 90, 92, 94, 96, 98, 100, 102,
105, 107, 109, 111, 113, 115, 117, 119,
121, 123, 125, 127, 129, 131, 133, 135,
137, 139, 141, 143, 146, 148, 149, 151,
155, 157, 159, 160, 161
};
static const char _ControlVerbs_trans_keys[] = {
41, 65, 66, 67, 76, 78, 85, 41,
41, 78, 41, 89, 41, 67, 41, 82,
41, 76, 41, 70, 41, 41, 83, 41,
82, 41, 95, 41, 65, 85, 41, 78,
41, 89, 41, 67, 41, 78, 41, 73,
41, 67, 41, 79, 41, 68, 41, 69,
41, 82, 41, 76, 41, 70, 73, 41,
77, 41, 73, 41, 84, 41, 95, 41,
77, 82, 41, 65, 41, 84, 41, 67,
41, 72, 41, 61, 41, 48, 57, 41,
48, 57, 41, 69, 41, 67, 41, 85,
41, 82, 41, 83, 41, 73, 41, 79,
41, 78, 41, 79, 41, 95, 41, 65,
83, 41, 85, 41, 84, 41, 79, 41,
95, 41, 80, 41, 79, 41, 83, 41,
83, 41, 69, 41, 83, 41, 83, 41,
84, 41, 65, 41, 82, 41, 84, 41,
95, 41, 79, 41, 80, 41, 84, 41,
67, 84, 41, 80, 41, 41, 70, 41,
49, 51, 56, 41, 54, 41, 50, 41,
40, 42, 0
};
static const char _ControlVerbs_single_lengths[] = {
7, 1, 2, 2, 2, 2, 2, 2,
1, 2, 2, 2, 3, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2,
3, 2, 2, 2, 2, 3, 2, 2,
2, 2, 2, 1, 1, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 3,
2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 3, 2, 1, 2, 4,
2, 2, 1, 1, 1
};
static const char _ControlVerbs_range_lengths[] = {
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 1, 1, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0
};
static const short _ControlVerbs_index_offsets[] = {
0, 8, 10, 13, 16, 19, 22, 25,
28, 30, 33, 36, 39, 43, 46, 49,
52, 55, 58, 61, 64, 67, 70, 73,
76, 80, 83, 86, 89, 92, 96, 99,
102, 105, 108, 111, 114, 117, 120, 123,
126, 129, 132, 135, 138, 141, 144, 147,
151, 154, 157, 160, 163, 166, 169, 172,
175, 178, 181, 184, 187, 190, 193, 196,
199, 202, 205, 208, 212, 215, 217, 220,
225, 228, 231, 233, 235
};
static const char _ControlVerbs_indicies[] = {
0, 2, 3, 4, 5, 6, 7, 1,
8, 1, 8, 9, 1, 8, 10, 1,
11, 12, 1, 8, 13, 1, 8, 14,
1, 8, 15, 1, 11, 1, 8, 16,
1, 8, 17, 1, 8, 18, 1, 8,
19, 20, 1, 8, 21, 1, 8, 22,
1, 8, 12, 1, 8, 23, 1, 8,
24, 1, 8, 25, 1, 8, 26, 1,
8, 27, 1, 8, 15, 1, 8, 28,
1, 11, 14, 1, 8, 15, 29, 1,
8, 30, 1, 8, 31, 1, 8, 32,
1, 8, 33, 1, 8, 34, 35, 1,
8, 36, 1, 8, 37, 1, 8, 38,
1, 8, 39, 1, 8, 40, 1, 8,
41, 1, 11, 41, 1, 8, 42, 1,
8, 43, 1, 8, 44, 1, 8, 45,
1, 8, 46, 1, 8, 47, 1, 8,
48, 1, 8, 39, 1, 8, 49, 1,
8, 50, 1, 8, 51, 52, 1, 8,
53, 1, 8, 54, 1, 8, 55, 1,
8, 56, 1, 8, 57, 1, 8, 58,
1, 8, 59, 1, 8, 60, 1, 8,
61, 1, 8, 62, 1, 8, 15, 1,
8, 63, 1, 8, 64, 1, 8, 65,
1, 8, 66, 1, 8, 67, 1, 8,
68, 1, 8, 69, 1, 8, 15, 1,
8, 70, 71, 1, 8, 72, 1, 73,
1, 8, 74, 1, 75, 76, 77, 78,
1, 8, 15, 1, 8, 15, 1, 75,
1, 80, 79, 82, 81, 0
};
static const char _ControlVerbs_trans_targs[] = {
75, 1, 2, 9, 22, 24, 45, 67,
75, 3, 4, 75, 5, 6, 7, 8,
10, 11, 12, 13, 16, 14, 15, 17,
18, 19, 20, 21, 23, 25, 26, 27,
28, 29, 30, 37, 31, 32, 33, 34,
35, 36, 38, 39, 40, 41, 42, 43,
44, 46, 47, 48, 59, 49, 50, 51,
52, 53, 54, 55, 56, 57, 58, 60,
61, 62, 63, 64, 65, 66, 68, 70,
69, 75, 71, 75, 72, 73, 74, 75,
76, 75, 0
};
static const char _ControlVerbs_trans_actions[] = {
19, 0, 0, 0, 0, 0, 0, 0,
13, 0, 0, 11, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 9, 0, 7, 0, 0, 0, 15,
5, 17, 0
};
static const char _ControlVerbs_to_state_actions[] = {
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 1, 0
};
static const char _ControlVerbs_from_state_actions[] = {
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 3, 0
};
static const short _ControlVerbs_eof_trans[] = {
1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 0, 82
};
static const int ControlVerbs_start = 75;
static const int ControlVerbs_first_final = 75;
static const int ControlVerbs_error = -1;
static const int ControlVerbs_en_main = 75;
#line 249 "control_verbs.cpp"
{
cs = ControlVerbs_start;
ts = 0;
te = 0;
act = 0;
}
#line 105 "control_verbs.rl"
try {
#line 262 "control_verbs.cpp"
{
int _klen;
unsigned int _trans;
const char *_acts;
unsigned int _nacts;
const char *_keys;
if ( p == pe )
goto _test_eof;
_resume:
_acts = _ControlVerbs_actions + _ControlVerbs_from_state_actions[cs];
_nacts = (unsigned int) *_acts++;
while ( _nacts-- > 0 ) {
switch ( *_acts++ ) {
case 1:
#line 1 "NONE"
{ts = p;}
break;
#line 281 "control_verbs.cpp"
}
}
_keys = _ControlVerbs_trans_keys + _ControlVerbs_key_offsets[cs];
_trans = _ControlVerbs_index_offsets[cs];
_klen = _ControlVerbs_single_lengths[cs];
if ( _klen > 0 ) {
const char *_lower = _keys;
const char *_mid;
const char *_upper = _keys + _klen - 1;
while (1) {
if ( _upper < _lower )
break;
_mid = _lower + ((_upper-_lower) >> 1);
if ( (*p) < *_mid )
_upper = _mid - 1;
else if ( (*p) > *_mid )
_lower = _mid + 1;
else {
_trans += (unsigned int)(_mid - _keys);
goto _match;
}
}
_keys += _klen;
_trans += _klen;
}
_klen = _ControlVerbs_range_lengths[cs];
if ( _klen > 0 ) {
const char *_lower = _keys;
const char *_mid;
const char *_upper = _keys + (_klen<<1) - 2;
while (1) {
if ( _upper < _lower )
break;
_mid = _lower + (((_upper-_lower) >> 1) & ~1);
if ( (*p) < _mid[0] )
_upper = _mid - 2;
else if ( (*p) > _mid[1] )
_lower = _mid + 2;
else {
_trans += (unsigned int)((_mid - _keys)>>1);
goto _match;
}
}
_trans += _klen;
}
_match:
_trans = _ControlVerbs_indicies[_trans];
_eof_trans:
cs = _ControlVerbs_trans_targs[_trans];
if ( _ControlVerbs_trans_actions[_trans] == 0 )
goto _again;
_acts = _ControlVerbs_actions + _ControlVerbs_trans_actions[_trans];
_nacts = (unsigned int) *_acts++;
while ( _nacts-- > 0 )
{
switch ( *_acts++ )
{
case 2:
#line 1 "NONE"
{te = p+1;}
break;
case 3:
#line 76 "control_verbs.rl"
{te = p+1;{
mode.utf8 = true;
}}
break;
case 4:
#line 80 "control_verbs.rl"
{te = p+1;{
mode.ucp = true;
}}
break;
case 5:
#line 84 "control_verbs.rl"
{te = p+1;{
ostringstream str;
str << "Unsupported control verb " << string(ts, te - ts);
throw LocatedParseError(str.str());
}}
break;
case 6:
#line 90 "control_verbs.rl"
{te = p+1;{
ostringstream str;
str << "Unknown control verb " << string(ts, te - ts);
throw LocatedParseError(str.str());
}}
break;
case 7:
#line 97 "control_verbs.rl"
{te = p+1;{
p--;
{p++; goto _out; }
}}
break;
case 8:
#line 97 "control_verbs.rl"
{te = p;p--;{
p--;
{p++; goto _out; }
}}
break;
case 9:
#line 97 "control_verbs.rl"
{{p = ((te))-1;}{
p--;
{p++; goto _out; }
}}
break;
#line 400 "control_verbs.cpp"
}
}
_again:
_acts = _ControlVerbs_actions + _ControlVerbs_to_state_actions[cs];
_nacts = (unsigned int) *_acts++;
while ( _nacts-- > 0 ) {
switch ( *_acts++ ) {
case 0:
#line 1 "NONE"
{ts = 0;}
break;
#line 413 "control_verbs.cpp"
}
}
if ( ++p != pe )
goto _resume;
_test_eof: {}
if ( p == eof )
{
if ( _ControlVerbs_eof_trans[cs] > 0 ) {
_trans = _ControlVerbs_eof_trans[cs] - 1;
goto _eof_trans;
}
}
_out: {}
}
#line 109 "control_verbs.rl"
} catch (LocatedParseError &error) {
if (ts >= ptr && ts <= pe) {
error.locate(ts - ptr + start);
} else {
error.locate(0);
}
throw;
}
return p;
}
} // namespace ue2

23
docker/test/fuzzer/run-fuzzer.sh
View File

@ -1,8 +1,15 @@
#!/bin/bash #!/bin/bash
# shellcheck disable=SC2086,SC2001,SC2046,SC2030,SC2031 # shellcheck disable=SC2086,SC2001,SC2046,SC2030,SC2031
set -eux set -x
# core.COMM.PID-TID
sysctl kernel.core_pattern='core.%e.%p-%P'
set -e
set -u
set -o pipefail set -o pipefail
trap "exit" INT TERM trap "exit" INT TERM
# The watchdog is in the separate process group, so we have to kill it separately # The watchdog is in the separate process group, so we have to kill it separately
# if the script terminates earlier. # if the script terminates earlier.
@ -87,6 +94,19 @@ function configure
# TODO figure out which ones are needed # TODO figure out which ones are needed
cp -av --dereference "$repo_dir"/tests/config/config.d/listen.xml db/config.d cp -av --dereference "$repo_dir"/tests/config/config.d/listen.xml db/config.d
cp -av --dereference "$script_dir"/query-fuzzer-tweaks-users.xml db/users.d cp -av --dereference "$script_dir"/query-fuzzer-tweaks-users.xml db/users.d
cat > db/config.d/core.xml <<EOL
<clickhouse>
<core_dump>
<!-- 100GiB -->
<size_limit>107374182400</size_limit>
</core_dump>
<!-- NOTE: no need to configure core_path,
since clickhouse is not started as daemon (via clickhouse start)
-->
<core_path>$PWD</core_path>
</clickhouse>
EOL
} }
function watchdog function watchdog
@ -180,7 +200,6 @@ handle SIGUSR2 nostop noprint pass
handle SIG$RTMIN nostop noprint pass handle SIG$RTMIN nostop noprint pass
info signals info signals
continue continue
gcore
backtrace full backtrace full
thread apply all backtrace full thread apply all backtrace full
info registers info registers

9
docker/test/integration/runner/compose/docker_compose_keeper.yml
View File

@ -8,6 +8,9 @@ services:
- type: bind - type: bind
source: ${keeper_binary:-} source: ${keeper_binary:-}
target: /usr/bin/clickhouse target: /usr/bin/clickhouse
- type: bind
source: ${keeper_binary:-}
target: /usr/bin/clickhouse-keeper
- type: bind - type: bind
source: ${keeper_config_dir1:-} source: ${keeper_config_dir1:-}
target: /etc/clickhouse-keeper target: /etc/clickhouse-keeper
@ -38,6 +41,9 @@ services:
- type: bind - type: bind
source: ${keeper_binary:-} source: ${keeper_binary:-}
target: /usr/bin/clickhouse target: /usr/bin/clickhouse
- type: bind
source: ${keeper_binary:-}
target: /usr/bin/clickhouse-keeper
- type: bind - type: bind
source: ${keeper_config_dir2:-} source: ${keeper_config_dir2:-}
target: /etc/clickhouse-keeper target: /etc/clickhouse-keeper
@ -68,6 +74,9 @@ services:
- type: bind - type: bind
source: ${keeper_binary:-} source: ${keeper_binary:-}
target: /usr/bin/clickhouse target: /usr/bin/clickhouse
- type: bind
source: ${keeper_binary:-}
target: /usr/bin/clickhouse-keeper
- type: bind - type: bind
source: ${keeper_config_dir3:-} source: ${keeper_config_dir3:-}
target: /etc/clickhouse-keeper target: /etc/clickhouse-keeper

4
docker/test/stateless/setup_minio.sh
View File

@ -22,8 +22,8 @@ ls -lha
mkdir -p ./minio_data mkdir -p ./minio_data
if [ ! -f ./minio ]; then if [ ! -f ./minio ]; then
MINIO_SERVER_VERSION=${MINIO_SERVER_VERSION:-2022-01-03T18-22-58Z} MINIO_SERVER_VERSION=${MINIO_SERVER_VERSION:-2022-09-07T22-25-02Z}
MINIO_CLIENT_VERSION=${MINIO_CLIENT_VERSION:-2022-01-05T23-52-51Z} MINIO_CLIENT_VERSION=${MINIO_CLIENT_VERSION:-2022-08-28T20-08-11Z}
case $(uname -m) in case $(uname -m) in
x86_64) BIN_ARCH=amd64 ;; x86_64) BIN_ARCH=amd64 ;;
aarch64) BIN_ARCH=arm64 ;; aarch64) BIN_ARCH=arm64 ;;

20
docker/test/stress/run.sh
View File

@ -8,6 +8,9 @@ dmesg --clear
set -x set -x
# core.COMM.PID-TID
sysctl kernel.core_pattern='core.%e.%p-%P'
# Thread Fuzzer allows to check more permutations of possible thread scheduling # Thread Fuzzer allows to check more permutations of possible thread scheduling
# and find more potential issues. # and find more potential issues.
@ -104,6 +107,19 @@ EOL
</default> </default>
</profiles> </profiles>
</clickhouse> </clickhouse>
EOL
cat > /etc/clickhouse-server/config.d/core.xml <<EOL
<clickhouse>
<core_dump>
<!-- 100GiB -->
<size_limit>107374182400</size_limit>
</core_dump>
<!-- NOTE: no need to configure core_path,
since clickhouse is not started as daemon (via clickhouse start)
-->
<core_path>$PWD</core_path>
</clickhouse>
EOL EOL
} }
@ -160,7 +176,6 @@ handle SIGUSR2 nostop noprint pass
handle SIG$RTMIN nostop noprint pass handle SIG$RTMIN nostop noprint pass
info signals info signals
continue continue
gcore
backtrace full backtrace full
thread apply all backtrace full thread apply all backtrace full
info registers info registers
@ -504,8 +519,7 @@ done
clickhouse-local --structure "test String, res String" -q "SELECT 'failure', test FROM table WHERE res != 'OK' order by (lower(test) like '%hung%'), rowNumberInAllBlocks() LIMIT 1" < /test_output/test_results.tsv > /test_output/check_status.tsv clickhouse-local --structure "test String, res String" -q "SELECT 'failure', test FROM table WHERE res != 'OK' order by (lower(test) like '%hung%'), rowNumberInAllBlocks() LIMIT 1" < /test_output/test_results.tsv > /test_output/check_status.tsv
[ -s /test_output/check_status.tsv ] || echo -e "success\tNo errors found" > /test_output/check_status.tsv [ -s /test_output/check_status.tsv ] || echo -e "success\tNo errors found" > /test_output/check_status.tsv
# Core dumps (see gcore) # Core dumps
# Default filename is 'core.PROCESS_ID'
for core in core.*; do for core in core.*; do
pigz $core pigz $core
mv $core.gz /test_output/ mv $core.gz /test_output/

5
docs/en/sql-reference/statements/alter/delete.md
View File

@ -12,8 +12,9 @@ ALTER TABLE [db.]table [ON CLUSTER cluster] DELETE WHERE filter_expr
Deletes data matching the specified filtering expression. Implemented as a [mutation](../../../sql-reference/statements/alter/index.md#mutations). Deletes data matching the specified filtering expression. Implemented as a [mutation](../../../sql-reference/statements/alter/index.md#mutations).
:::note
The `ALTER TABLE` prefix makes this syntax different from most other systems supporting SQL. It is intended to signify that unlike similar queries in OLTP databases this is a heavy operation not designed for frequent use. :::note
The `ALTER TABLE` prefix makes this syntax different from most other systems supporting SQL. It is intended to signify that unlike similar queries in OLTP databases this is a heavy operation not designed for frequent use. `ALTER TABLE` is considered a heavyweight operation that requires the underlying data to be merged before it is deleted. For MergeTree tables, consider using the [`DELETE FROM` query](../delete.md), which performs a lightweight delete and can be considerably faster.
::: :::
The `filter_expr` must be of type `UInt8`. The query deletes rows in the table for which this expression takes a non-zero value. The `filter_expr` must be of type `UInt8`. The query deletes rows in the table for which this expression takes a non-zero value.

37
docs/en/sql-reference/statements/delete.md Normal file
View File

@ -0,0 +1,37 @@
---
slug: /en/sql-reference/statements/delete
sidebar_position: 36
sidebar_label: DELETE
---
# DELETE Statement
``` sql
DELETE FROM [db.]table [WHERE expr]
```
`DELETE FROM` removes rows from table `[db.]table` that match expression `expr`. The deleted rows are marked as deleted immediately and will be automatically filtered out of all subsequent queries. Cleanup of data happens asynchronously in background. This feature is only available for MergeTree table engine family.
For example, the following query deletes all rows from the `hits` table where the `Title` column contains the text `hello`:
```sql
DELETE FROM hits WHERE Title LIKE '%hello%';
```
Lightweight deletes are asynchronous by default. Set `mutations_sync` equal to 1 to wait for one replica to process the statement, and set `mutations_sync` to 2 to wait for all replicas.
:::note
This feature is experimental and requires you to set `allow_experimental_lightweight_delete` to true:
```sql
SET allow_experimental_lightweight_delete = true;
```
:::
An [alternative way to delete rows](./alter/delete.md) in ClickHouse is `ALTER TABLE ... DELETE`, which might be more efficient if you do bulk deletes only occasionally and don't need the operation to be applied instantly. In most use cases the new lightweight `DELETE FROM` behavior will be considerably faster.
:::warning
Even though deletes are becoming more lightweight in ClickHouse, they should still not be used as aggressively as on OLTP system. Ligthweight deletes are currently efficient for wide parts, but for compact parts they can be a heavyweight operation, and it may be better to use `ALTER TABLE` for some scenarios.
:::

4
docs/en/sql-reference/statements/detach.md
View File

@ -10,7 +10,7 @@ Makes the server "forget" about the existence of a table, a materialized view, o
**Syntax** **Syntax**
``` sql ``` sql
DETACH TABLE|VIEW|DICTIONARY [IF EXISTS] [db.]name [ON CLUSTER cluster] [PERMANENTLY] DETACH TABLE|VIEW|DICTIONARY [IF EXISTS] [db.]name [ON CLUSTER cluster] [PERMANENTLY] [SYNC]
``` ```
Detaching does not delete the data or metadata of a table, a materialized view or a dictionary. If an entity was not detached `PERMANENTLY`, on the next server launch the server will read the metadata and recall the table/view/dictionary again. If an entity was detached `PERMANENTLY`, there will be no automatic recall. Detaching does not delete the data or metadata of a table, a materialized view or a dictionary. If an entity was not detached `PERMANENTLY`, on the next server launch the server will read the metadata and recall the table/view/dictionary again. If an entity was detached `PERMANENTLY`, there will be no automatic recall.
@ -24,6 +24,8 @@ Note that you can not detach permanently the table which is already detached (te
Also you can not [DROP](../../sql-reference/statements/drop#drop-table) the detached table, or [CREATE TABLE](../../sql-reference/statements/create/table.md) with the same name as detached permanently, or replace it with the other table with [RENAME TABLE](../../sql-reference/statements/rename.md) query. Also you can not [DROP](../../sql-reference/statements/drop#drop-table) the detached table, or [CREATE TABLE](../../sql-reference/statements/create/table.md) with the same name as detached permanently, or replace it with the other table with [RENAME TABLE](../../sql-reference/statements/rename.md) query.
The `SYNC` modifier executes the action without delay.
**Example** **Example**
Creating a table: Creating a table:

10
docs/en/sql-reference/statements/drop.md
View File

@ -6,7 +6,7 @@ sidebar_label: DROP
# DROP Statements # DROP Statements
Deletes existing entity. If the `IF EXISTS` clause is specified, these queries do not return an error if the entity does not exist. Deletes existing entity. If the `IF EXISTS` clause is specified, these queries do not return an error if the entity does not exist. If the `SYNC` modifier is specified, the entity is dropped without delay.
## DROP DATABASE ## DROP DATABASE
@ -15,7 +15,7 @@ Deletes all tables inside the `db` database, then deletes the `db` database itse
Syntax: Syntax:
``` sql ``` sql
DROP DATABASE [IF EXISTS] db [ON CLUSTER cluster] DROP DATABASE [IF EXISTS] db [ON CLUSTER cluster] [SYNC]
``` ```
## DROP TABLE ## DROP TABLE
@ -25,7 +25,7 @@ Deletes the table.
Syntax: Syntax:
``` sql ``` sql
DROP [TEMPORARY] TABLE [IF EXISTS] [db.]name [ON CLUSTER cluster] DROP [TEMPORARY] TABLE [IF EXISTS] [db.]name [ON CLUSTER cluster] [SYNC]
``` ```
## DROP DICTIONARY ## DROP DICTIONARY
@ -35,7 +35,7 @@ Deletes the dictionary.
Syntax: Syntax:
``` sql ``` sql
DROP DICTIONARY [IF EXISTS] [db.]name DROP DICTIONARY [IF EXISTS] [db.]name [SYNC]
``` ```
## DROP USER ## DROP USER
@ -95,7 +95,7 @@ Deletes a view. Views can be deleted by a `DROP TABLE` command as well but `DROP
Syntax: Syntax:
``` sql ``` sql
DROP VIEW [IF EXISTS] [db.]name [ON CLUSTER cluster] DROP VIEW [IF EXISTS] [db.]name [ON CLUSTER cluster] [SYNC]
``` ```
## DROP FUNCTION ## DROP FUNCTION

2
docs/zh/development/tests.md
View File

@ -1,5 +1,5 @@
--- ---
slug: /en/development/tests slug: /zh/development/tests
sidebar_position: 70 sidebar_position: 70
sidebar_label: Testing sidebar_label: Testing
title: ClickHouse Testing title: ClickHouse Testing

264
docs/zh/whats-new/changelog/2017.md
View File

@ -1,264 +0,0 @@
---
slug: /zh/whats-new/changelog/2017
---
### ClickHouse 版本 1.1.54327, 2017-12-21 {#clickhouse-release-1-1-54327-2017-12-21}
此版本包含先前版本 1.1.54318 的错误修复:
- 修复了可能导致数据丢失的复制中可能出现的竞争条件的错误. 此问题影响1.1.54310和1.1.54318版本. 如果将这些版本的任意一个与 Replicated 表一起使用，则强烈建议进行更新. 此问题显示在日志中的警告消息中，例如 `Part ... from own log does not exist.` 即使您没有在日志中看到这些消息，该问题也是相关的.
### ClickHouse 版本 1.1.54318, 2017-11-30 {#clickhouse-release-1-1-54318-2017-11-30}
此版本包含先前版本 1.1.54310 的错误修复:
- 修复了在 SummingMergeTree 引擎中合并期间不正确的行删除.
- 修复了未复制的 MergeTree 引擎中的内存泄漏.
- 修复了在 MergeTree 引擎中频繁插入导致性能下降的问题.
- 修复了导致复制队列停止运行的问题.
- 修复了服务器日志的轮换和归档.
### ClickHouse 版本 1.1.54310, 2017-11-01 {#clickhouse-release-1-1-54310-2017-11-01}
#### 新特征: {#new-features}
- MergeTree 系列表引擎的自定义分区键.
- [Kafka](https://clickhouse.com/docs/en/operations/table_engines/kafka/) 表引擎.
- 增加了对加载[CatBoost](https://catboost.yandex/)模型的支持, 并将它们应用到存储在ClickHouse中的数据.
- 添加了对 UTC 非整数偏移时区的支持
- 添加了对具有时间间隔的算术运算的支持.
- Date 和 DateTime 类型的值范围扩展到 2105 年.
- 添加了 `CREATE MATERIALIZED VIEW x TO y` 查询(指定用于存储物化视图数据的现有表).
- 添加了不带参数的`ATTACH TABLE` 查询.
- SummingMergeTree 表中名称以 -Map 结尾的嵌套列的处理逻辑被提取到 sumMap 聚合函数中. 您现在可以明确指定此类列.
- IP 树字典的最大大小增加到 128M 条目.
- 添加了 getSizeOfEnumType 函数.
- 添加了 sumWithOverflow 聚合函数.
- 添加了对 Cap'n Proto 输入格式的支持.
- 您现在可以在使用 zstd 算法时自定义压缩级别.
#### 向后不兼容的变化: {#backward-incompatible-changes}
- 不允许使用内存以外的引擎创建临时表.
- 不允许使用 View 或 MaterializedView 引擎显式创建表.
- 在表创建期间，新的检查验证采样键表达式是否包含在主键中.
#### Bug 修复: {#bug-fixes}
- 修复了同步插入分布式表时的挂断问题.
- 修复了复制表中部件的非原子添加和删除.
- 插入物化视图的数据不会进行不必要的重复数据删除.
- 对本地副本滞后且远程副本不可用的分布式表执行查询不再导致错误.
- 用户不再需要访问 `default` 数据库的权限来创建临时表.
- 修复了指定不带参数的 Array 类型时崩溃的问题.
- 修复了包含服务器日志的磁盘卷已满时的挂断问题.
- 修复了 Unix 纪元第一周 toRelativeWeekNum 函数中的溢出问题.
#### Build 改进: {#build-improvements}
- 更新了多个第三方库(尤其是 Poco)并转换为 git 子模块.
### ClickHouse 版本 1.1.54304, 2017-10-19 {#clickhouse-release-1-1-54304-2017-10-19}
#### 新特征: {#new-features-1}
- 本机协议中的 TLS 支持(要启用，请在 `config.xml` 中设置 `tcp_ssl_port`).
#### Bug 修复: {#bug-fixes-1}
- 复制表的`ALTER` 现在尝试尽快开始运行.
- 修复了使用设置 `preferred_block_size_bytes=0.` 读取数据时崩溃的问题.
- 修复了按下 `Page Down` 时 `clickhouse-client` 崩溃的问题.
- 使用 `GLOBAL IN` 和 `UNION ALL` 正确解释某些复杂的查询.
- `FREEZE PARTITION` 现在总是以原子方式工作.
- 空 POST 请求现在返回代码为 411 的响应.
- 修正了像 `CAST(1 AS Nullable(UInt8)).` 这样的表达式的解释错误.
- 修正了从 `MergeTree` 表中读取 `Array(Nullable(String))` 列时的错误.
- 修复了在解析诸如 `SELECT dummy AS dummy, dummy AS b` 之类的查询时崩溃的问题.
- 用户使用无效的 `users.xml` 正确更新.
- 可执行字典返回非零响应代码时的正确处理.
### ClickHouse 版本 1.1.54292, 2017-09-20 {#clickhouse-release-1-1-54292-2017-09-20}
#### 新特征: {#new-features-2}
- 添加了用于处理坐标平面上的坐标的 `pointInPolygon` 函数.
- 添加了用于计算数组总和的 `sumMap` 聚合函数, 类似于 `SummingMergeTree` .
- 添加了 `trunc` 功能. 改进了舍入函数(`round`、`floor`、`ceil`、`roundToExp2`)的性能并更正了它们工作方式的逻辑. 更改了分数和负数的 `roundToExp2` 函数的逻辑.
- ClickHouse 可执行文件现在较少依赖于 libc 版本. 同一个 ClickHouse 可执行文件可以在各种 Linux 系统上运行. 使用编译查询时仍然存在依赖性(使用设置 `compile = 1` , 默认情况下不使用).
- 减少动态编译查询所需的时间.
#### Bug 修复: {#bug-fixes-2}
- 修复了有时会产生 `part ... intersects previous part` 消息和削弱副本一致性的错误.
- 修复了关闭期间 ZooKeeper 不可用导致服务器锁定的错误.
- 恢复副本时删除了过多的日志记录.
- 修复了 UNION ALL 实现中的错误.
- 修复了如果块中的第一列具有 Array 类型时在 concat 函数中发生的错误.
- 进度现在在 system.merges 表中可以正确显示.
### ClickHouse 版本 1.1.54289, 2017-09-13 {#clickhouse-release-1-1-54289-2017-09-13}
#### 新特征: {#new-features-3}
- 用于服务器管理的 `SYSTEM` 查询: `SYSTEM RELOAD DICTIONARY`, `SYSTEM RELOAD DICTIONARIES`, `SYSTEM DROP DNS CACHE`, `SYSTEM SHUTDOWN`, `SYSTEM KILL`.
- 添加了用于处理数组的函数: `concat`, `arraySlice`, `arrayPushBack`, `arrayPushFront`, `arrayPopBack`, `arrayPopFront`.
- 为 ZooKeeper 配置添加了 `root` 和 `identity` 参数. 这将允许您隔离同一 ZooKeeper 集群上的各个用户.
- 添加了聚合函数 `groupBitAnd` 、 `groupBitOr` 和 `groupBitXor` (为了兼容性，它们也可以在名称 `BIT_AND` 、`BIT_OR`和`BIT_XOR` 下使用).
- 可以通过在文件系统中指定套接字来从 MySQL 加载外部字典.
- 可以通过 SSL 从 MySQL 加载外部字典 (`ssl_cert`, `ssl_key`, `ssl_ca` 参数).
- 添加了 `max_network_bandwidth_for_user` 设置以限制每个用户查询的总体带宽使用.
- 支持临时表的 `DROP TABLE`.
- 支持从 `CSV` 和 `JSONEachRow` 格式读取 Unix 时间戳格式的 `DateTime` 值.
- 现在默认排除分布式查询中的滞后副本(默认阈值为 5 分钟).
- 在 ALTER 期间使用 FIFO 锁定：对于连续运行的查询，ALTER 查询不会无限期阻塞.
- 在配置文件中设置 `umask` 的选项.
- 使用 `DISTINCT` 提高查询的性能.
#### Bug 修复: {#bug-fixes-3}
- 改进了在 ZooKeeper 中删除旧节点的过程. 以前, 如果插入非常频繁, 旧节点有时不会被删除, 从而导致服务器关闭缓慢等.
- 修复了为 ZooKeeper 连接选择主机时的随机化问题.
- 如果副本是本地主机, 则修复了在分布式查询中排除滞后副本的问题.
- 修复了在 `嵌套` 结构中的元素上运行 `ALTER MODIFY` 后, `ReplicatedMergeTree` 表中的数据部分可能被破坏的错误.
- 修复了可能导致 SELECT 查询 `hang` 的错误.
- 分布式 DDL 查询的改进.
- 修复了查询 `CREATE TABLE ... AS <materialized view>`.
- 解决了对 Buffer 表的 `ALTER ... CLEAR COLUMN IN PARTITION` 查询中的死锁.
- 修复了使用 `JSONEachRow` 和 `TSKV` 格式时 `Enum` 的无效默认值 (0 而不是最小值).
- 解决了使用带有 `可执行` 源的字典时出现僵尸进程的问题.
- 修复了 HEAD 查询的段错误.
#### 改进了开发和组装ClickHouse的工作流: {#improved-workflow-for-developing-and-assembling-clickhouse}
- 您可以使用 `pbuilder` 来构建 ClickHouse.
- 你可以使用 `libc++` 代替 `libstdc++` 在 Linux 上构建.
- 添加了使用静态代码分析工具的说明: `Coverage`, `clang-tidy`, `cppcheck`.
#### 升级时请注意: {#please-note-when-upgrading}
- 现在有更高的 MergeTree 设置默认值 `max_bytes_to_merge_at_max_space_in_pool` (要合并的数据部分的最大总大小, 以字节为单位): 它已从 100 GiB 增加到 150 GiB. 这可能会导致在服务器升级后运行大型合并, 从而导致磁盘子系统负载增加. 如果服务器上的可用空间小于正在运行的合并总量的两倍, 这将导致所有其他合并停止运行, 包括小数据部分的合并. 因此, INSERT 查询将失败并显示消息"合并的处理速度明显慢于插入." , 使用 `SELECT * FROM system.merges` 查询来监控情况. 您还可以在 `system.metrics` 表或 Graphite 中检查 `DiskSpaceReservedForMerge` 指标. 您不需要做任何事情来解决这个问题, 因为一旦大型合并完成, 问题就会自行解决. 如果您发现这不可接受, 您可以恢复 `max_bytes_to_merge_at_max_space_in_pool` 设置的先前值. 为此, 请转到 config.xml 中的 `<merge_tree>` 部分, 设置 ``` <merge_tree>``<max_bytes_to_merge_at_max_space_in_pool>107374182400</max_bytes_to_merge_at_max_space_in_pool> ``` 并重新启动服务器.
### ClickHouse 版本 1.1.54284, 2017-08-29 {#clickhouse-release-1-1-54284-2017-08-29}
- 这是先前 1.1.54282 版本的错误修复版本. 它修复了 ZooKeeper 中部分目录中的泄漏.
### ClickHouse 版本 1.1.54282, 2017-08-23 {#clickhouse-release-1-1-54282-2017-08-23}
此版本包含先前版本 1.1.54276 的错误修复:
- 修复了插入分布式表时的 `DB::Exception: Assertion violation: !_path.empty()`.
- 如果输入数据以 ';' 开头, 则在以 RowBinary 格式插入时固定解析.
- 某些聚合函数 (例如 `groupArray()` ) 的运行时编译期间的错误.
### ClickHouse 版本 1.1.54276, 2017-08-16 {#clickhouse-release-1-1-54276-2017-08-16}
#### 新特征: {#new-features-4}
- SELECT 查询添加了一个可选的 WITH 部分. 示例查询：`WITH 1+1 AS a SELECT a, a*a` .
- NSERT 可以在分布式表中同步执行：只有在所有数据都保存在所有分片上后才返回 OK. 这是通过设置 `insert_distributed_sync=1` 激活的.
- 添加了用于处理 16 字节标识符的 UUID 数据类型.
- 添加了 CHAR、FLOAT 和其他类型的别名以与 Tableau 兼容.
- 新增 toYYYYMM, toYYYYMMDD, toYYYYMMDDhhmmss 时间转数字功能.
- 您可以使用 IP 地址 (与主机名一起) 来识别集群 DDL 查询的服务器.
- 在函数 `substring(str, pos, len)` 中添加了对非常量参数和负偏移量的支持.
- 为 `groupArray(max_size)(column)` 聚合函数增加了max_size参数, 并优化了其性能.
#### Main Changes: {#main-changes}
- 安全改进：所有服务器文件都使用 0640 权限创建(可以通过 `<umask>` 配置参数更改).
- 改进了语法无效查询的错误消息.
- 合并大段 MergeTree 数据时显着减少内存消耗并提高性能.
- 显着提高了 ReplacingMergeTree 引擎的数据合并性能.
- 通过组合多个源插入提高了从分布式表进行异步插入的性能. 要启用此功能, 请使用设置 `distributed_directory_monitor_batch_inserts=1` .
#### Backward Incompatible Changes: {#backward-incompatible-changes-1}
- 更改了数组 `groupArray(array_column)` 函数聚合状态的二进制格式.
#### Complete List of Changes: {#complete-list-of-changes}
- 添加了 `output_format_json_quote_denormals` 设置, 可以以 JSON 格式输出 nan 和 inf 值.
- 从分布式表读取时优化流分配.
- 如果值不变, 可以在只读模式下配置设置.
- 加了检索 MergeTree 引擎的非整数粒度的功能, 以满足对 `preferred_block_size_bytes` 设置中指定的块大小的限制. 目的是在处理来自大列的表的查询时减少RAM的消耗并增加缓存局部性.
- 有效地使用包含像 `toStartOfHour(x)` 这样的表达式的索引来处理像 `toStartOfHour(x) op сonstexpr` 这样的条件.
- 添加了 MergeTree 引擎的新设置(config.xml 中的 merge_tree 部分):
- `replicad_deduplication_window_seconds` 设置允许在复制表中删除重复插入的秒数.
- `cleanup_delay_period` 设置启动清理以删除过时数据的频率.
- `Replicationd_can_become_leader` 可以防止副本成为领导者(并分配合并).
- 加速清理以从 ZooKeeper 中删除过时的数据.
- 集群 DDL 查询的多项改进和修复. 特别有趣的是新设置 `distributed_ddl_task_timeout`, 它限制了等待集群中服务器响应的时间. 如果 ddl 请求没有在所有主机上执行，响应将包含超时错误并且请求将以异步模式执行.
- 改进了服务器日志中堆栈跟踪的显示.
- 为压缩方法添加了 "none" 值.
- 您可以在 config.xml 中使用多个dictionaries_config 部分.
- 可以通过文件系统中的套接字连接到 MySQL.
- `system.parts` 表有一个新列, 其中包含有关标记大小的信息(以字节为单位).
#### Bug 修复: {#bug-fixes-4}
- 使用 Merge 表的分布式表现在可以正确用于带有 `_table` 字段条件的 SELECT 查询.
- 修复了检查数据部分时 ReplicatedMergeTree 中罕见的竞争条件.
- 修复了启动服务器时 `leader election` 可能会冻结的问题.
- 使用数据源的本地副本时，将忽略 `max_replica_delay_for_distributed_queries` 设置. 这已被修复.
- 修复了尝试清理不存在的列时 `ALTER TABLE CLEAR COLUMN IN PARTITION` 的错误行为.
- 修复了 multiIf 函数中使用空数组或字符串时的异常.
- 修复了反序列化本机格式时过多的内存分配.
- 修复了 Trie 词典的错误自动更新.
- 修复了在使用 SAMPLE 时从合并表中使用 GROUP BY 子句运行查询时的异常.
- 修复了 `distributed_aggregation_memory_efficient=1` 时 GROUP BY 的崩溃.
- 现在可以在 IN 和 JOIN 右侧指定 `database.table`.
- 太多线程用于并行聚合. 这已被修复.
- 修复了 `if` 函数如何与 FixedString 参数一起工作.
- 对于权重为 0 的分片, SELECT 在分布式表中工作不正确. 这已得到修复.
- 运行 `CREATE VIEW IF EXISTS 不再导致崩溃` .
- 修复了设置 `input_format_skip_unknown_fields=1` 且存在负数时的错误行为.
- 修复了如果字典中有一些无效数据, `dictGetHierarchy()` 函数中的无限循环.
- 修复了使用 IN 或 JOIN 子句和合并表中的子查询运行分布式查询时的 `Syntax error: unexpected (...)` 错误.
- 修复了对字典表中 SELECT 查询的错误解释.
- 修复了在超过 20 亿元素的 IN 和 JOIN 子句中使用数组时的 "Cannot mremap" 错误.
- 修复了以 MySQL 为源的字典的故障转移.
#### 改进了开发和组装ClickHouse的工作流: {#improved-workflow-for-developing-and-assembling-clickhouse-1}
- 可以在 Arcadia 中组装 Builds.
- 可以使用 gcc 7 编译 ClickHouse.
- 使用 ccache+distcc 的并行构建现在更快了.
### ClickHouse 版本 1.1.54245, 2017-07-04 {#clickhouse-release-1-1-54245-2017-07-04}
#### 新特征: {#new-features-5}
- 分布式 DDL(例如, `REATE TABLE ON CLUSTER`).
- 复制查询 `ALTER TABLE CLEAR COLUMN IN PARTITION.` .
- 字典表引擎 (以表的形式访问字典数据).
- 字典数据库引擎 (这种类型的数据库自动为所有连接的外部字典提供字典表).
- 您可以通过向源发送请求来检查字典的更新.
- 合格的列名.
- 使用双引号引用标识符.
- HTTP 接口中的会话.
- 复制表的 OPTIMIZE 查询不仅可以在领导者上运行.
#### 向后不兼容的变化: {#backward-incompatible-changes-2}
- 删除了 SET GLOBAL.
#### 次要更改: {#minor-changes}
- 目前在触发警报后，日志会打印完整的堆栈跟踪.
- 放宽了启动时损坏/额外数据部分数量的验证(误报太多).
#### Bug 修复: {#bug-fixes-5}
- 修复了插入分布式表时的错误连接"卡住"问题.
- GLOBAL IN 现在适用于来自查看分布式表的合并表的查询.
- 在 Google Compute Engine 虚拟机上检测到的内核数不正确. 这已被修复.
- 缓存外部字典的可执行源的工作方式发生了变化.
- 修正了包含空字符的字符串的比较.
- 修复了 Float32 主键字段与常量的比较.
- 以前，对字段大小的错误估计可能会导致分配过大.
- 修复了使用 ALTER 查询添加到表中的 Nullable 列时发生的崩溃.
- 修复了当行数小于 LIMIT 时按 Nullable 列排序时崩溃的问题.
- 修复了仅由常量值组成的 ORDER BY 子查询.
- 以前，复制表在 DROP TABLE 失败后可能保持无效状态.
- 结果为空的标量子查询的别名不再丢失.
- 现在，如果 .so 文件损坏，使用编译的查询不会因错误而失败.

1059
docs/zh/whats-new/changelog/2018.md
View File

File diff suppressed because it is too large Load Diff

1855
docs/zh/whats-new/changelog/2019.md
View File

File diff suppressed because it is too large Load Diff

3529
docs/zh/whats-new/changelog/2020.md
View File

File diff suppressed because it is too large Load Diff

6
programs/diagnostics/internal/platform/data/file_test.go
View File

@ -133,11 +133,11 @@ func TestConfigFileFrameCopy(t *testing.T) {
require.Empty(t, errs) require.Empty(t, errs)
i := 0 i := 0
sizes := map[string]int64{ sizes := map[string]int64{
"users.xml": int64(2039), "users.xml": int64(2017),
"default-password.xml": int64(188), "default-password.xml": int64(188),
"config.xml": int64(61282), "config.xml": int64(61260),
"server-include.xml": int64(168), "server-include.xml": int64(168),
"user-include.xml": int64(582), "user-include.xml": int64(559),
} }
var checkedFiles []string var checkedFiles []string
for { for {

1
programs/diagnostics/testdata/configs/include/xml/user-include.xml vendored
View File

@ -1,4 +1,3 @@
<?xml version="1.0" ?>
<clickhouse> <clickhouse>
<test_user> <test_user>
<networks> <networks>

1
programs/diagnostics/testdata/configs/xml/config.xml vendored
View File

@ -1,4 +1,3 @@
<?xml version="1.0"?>
<!-- <!--
NOTE: User and query level settings are set up in "users.xml" file. NOTE: User and query level settings are set up in "users.xml" file.
If you have accidentally specified user-level settings here, server won't start. If you have accidentally specified user-level settings here, server won't start.

1
programs/diagnostics/testdata/configs/xml/users.xml vendored
View File

@ -1,4 +1,3 @@
<?xml version="1.0"?>
<clickhouse> <clickhouse>
<!-- See also the files in users.d directory where the settings can be overridden. --> <!-- See also the files in users.d directory where the settings can be overridden. -->
<!-- Profiles of settings. --> <!-- Profiles of settings. -->

1
programs/diagnostics/testdata/configs/yandex_xml/config.xml vendored
View File

@ -1,4 +1,3 @@
<?xml version="1.0"?>
<!-- <!--
NOTE: User and query level settings are set up in "users.xml" file. NOTE: User and query level settings are set up in "users.xml" file.
If you have accidentally specified user-level settings here, server won't start. If you have accidentally specified user-level settings here, server won't start.

1
programs/diagnostics/testdata/docker/custom.xml vendored
View File

@ -1,4 +1,3 @@
<?xml version="1.0" ?>
<clickhouse> <clickhouse>
<listen_host>::</listen_host> <listen_host>::</listen_host>
<listen_host>0.0.0.0</listen_host> <listen_host>0.0.0.0</listen_host>

4
programs/obfuscator/Obfuscator.cpp
View File

@ -833,7 +833,7 @@ public:
} }
} }
if (params.frequency_desaturate) if (params.frequency_desaturate > 0.0)
{ {
for (auto & elem : table) for (auto & elem : table)
{ {
@ -846,7 +846,7 @@ public:
UInt64 new_total = 0; UInt64 new_total = 0;
for (auto & bucket : histogram.buckets) for (auto & bucket : histogram.buckets)
{ {
bucket.second = bucket.second * (1.0 - params.frequency_desaturate) + average * params.frequency_desaturate; bucket.second = static_cast<UInt64>(bucket.second * (1.0 - params.frequency_desaturate) + average * params.frequency_desaturate);
new_total += bucket.second; new_total += bucket.second;
} }

1
programs/server/config.xml
View File

@ -1,4 +1,3 @@
<?xml version="1.0"?>
<!-- <!--
NOTE: User and query level settings are set up in "users.xml" file. NOTE: User and query level settings are set up in "users.xml" file.
If you have accidentally specified user-level settings here, server won't start. If you have accidentally specified user-level settings here, server won't start.

1
programs/server/embedded.xml
View File

@ -1,4 +1,3 @@
<?xml version="1.0"?>
<!-- Config that is used when server is run without config file. --> <!-- Config that is used when server is run without config file. -->
<clickhouse> <clickhouse>
<logger> <logger>

1
programs/server/users.d/allow_introspection_functions.xml
View File

@ -1,4 +1,3 @@
<?xml version="1.0"?>
<clickhouse> <clickhouse>
<profiles> <profiles>
<default> <default>

1
programs/server/users.d/allow_only_from_localhost.xml
View File

@ -1,4 +1,3 @@
<?xml version="1.0"?>
<clickhouse> <clickhouse>
<users> <users>
<default> <default>

10
programs/server/users.xml
View File

@ -1,4 +1,3 @@
<?xml version="1.0"?>
<clickhouse> <clickhouse>
<!-- See also the files in users.d directory where the settings can be overridden. --> <!-- See also the files in users.d directory where the settings can be overridden. -->
@ -6,15 +5,6 @@
<profiles> <profiles>
<!-- Default settings. --> <!-- Default settings. -->
<default> <default>
<!-- How to choose between replicas during distributed query processing.
random - choose random replica from set of replicas with minimum number of errors
nearest_hostname - from set of replicas with minimum number of errors, choose replica
with minimum number of different symbols between replica's hostname and local hostname
(Hamming distance).
in_order - first live replica is chosen in specified order.
first_or_random - if first replica one has higher number of errors, pick a random one from replicas with minimum number of errors.
-->
<load_balancing>random</load_balancing>
</default> </default>
<!-- Profile that allows only read queries. --> <!-- Profile that allows only read queries. -->

143
src/AggregateFunctions/AggregateFunctionQuantile.cpp
View File

@ -1,8 +1,9 @@
#include <AggregateFunctions/AggregateFunctionQuantile.h> #include <AggregateFunctions/AggregateFunctionQuantile.h>
#include <AggregateFunctions/QuantileReservoirSampler.h>
#include <AggregateFunctions/AggregateFunctionFactory.h> #include <AggregateFunctions/AggregateFunctionFactory.h>
#include <AggregateFunctions/Helpers.h> #include <AggregateFunctions/Helpers.h>
#include <DataTypes/DataTypeDate.h>
#include <DataTypes/DataTypeDateTime.h>
#include <Core/Field.h> #include <Core/Field.h>
@ -21,70 +22,6 @@ namespace
template <typename Value, bool float_return> using FuncQuantile = AggregateFunctionQuantile<Value, QuantileReservoirSampler<Value>, NameQuantile, false, std::conditional_t<float_return, Float64, void>, false>; template <typename Value, bool float_return> using FuncQuantile = AggregateFunctionQuantile<Value, QuantileReservoirSampler<Value>, NameQuantile, false, std::conditional_t<float_return, Float64, void>, false>;
template <typename Value, bool float_return> using FuncQuantiles = AggregateFunctionQuantile<Value, QuantileReservoirSampler<Value>, NameQuantiles, false, std::conditional_t<float_return, Float64, void>, true>; template <typename Value, bool float_return> using FuncQuantiles = AggregateFunctionQuantile<Value, QuantileReservoirSampler<Value>, NameQuantiles, false, std::conditional_t<float_return, Float64, void>, true>;
template <typename Value, bool float_return> using FuncQuantileDeterministic = AggregateFunctionQuantile<Value, QuantileReservoirSamplerDeterministic<Value>, NameQuantileDeterministic, true, std::conditional_t<float_return, Float64, void>, false>;
template <typename Value, bool float_return> using FuncQuantilesDeterministic = AggregateFunctionQuantile<Value, QuantileReservoirSamplerDeterministic<Value>, NameQuantilesDeterministic, true, std::conditional_t<float_return, Float64, void>, true>;
template <typename Value, bool _> using FuncQuantileExact = AggregateFunctionQuantile<Value, QuantileExact<Value>, NameQuantileExact, false, void, false>;
template <typename Value, bool _> using FuncQuantilesExact = AggregateFunctionQuantile<Value, QuantileExact<Value>, NameQuantilesExact, false, void, true>;
template <typename Value, bool _> using FuncQuantileExactLow = AggregateFunctionQuantile<Value, QuantileExactLow<Value>, NameQuantileExactLow, false, void, false>;
template <typename Value, bool _> using FuncQuantilesExactLow = AggregateFunctionQuantile<Value, QuantileExactLow<Value>, NameQuantilesExactLow, false, void, true>;
template <typename Value, bool _> using FuncQuantileExactHigh = AggregateFunctionQuantile<Value, QuantileExactHigh<Value>, NameQuantileExactHigh, false, void, false>;
template <typename Value, bool _> using FuncQuantilesExactHigh = AggregateFunctionQuantile<Value, QuantileExactHigh<Value>, NameQuantilesExactHigh, false, void, true>;
template <typename Value, bool _> using FuncQuantileExactExclusive = AggregateFunctionQuantile<Value, QuantileExactExclusive<Value>, NameQuantileExactExclusive, false, Float64, false>;
template <typename Value, bool _> using FuncQuantilesExactExclusive = AggregateFunctionQuantile<Value, QuantileExactExclusive<Value>, NameQuantilesExactExclusive, false, Float64, true>;
template <typename Value, bool _> using FuncQuantileExactInclusive = AggregateFunctionQuantile<Value, QuantileExactInclusive<Value>, NameQuantileExactInclusive, false, Float64, false>;
template <typename Value, bool _> using FuncQuantilesExactInclusive = AggregateFunctionQuantile<Value, QuantileExactInclusive<Value>, NameQuantilesExactInclusive, false, Float64, true>;
template <typename Value, bool _> using FuncQuantileExactWeighted = AggregateFunctionQuantile<Value, QuantileExactWeighted<Value>, NameQuantileExactWeighted, true, void, false>;
template <typename Value, bool _> using FuncQuantilesExactWeighted = AggregateFunctionQuantile<Value, QuantileExactWeighted<Value>, NameQuantilesExactWeighted, true, void, true>;
template <typename Value, bool _> using FuncQuantileTiming = AggregateFunctionQuantile<Value, QuantileTiming<Value>, NameQuantileTiming, false, Float32, false>;
template <typename Value, bool _> using FuncQuantilesTiming = AggregateFunctionQuantile<Value, QuantileTiming<Value>, NameQuantilesTiming, false, Float32, true>;
template <typename Value, bool _> using FuncQuantileTimingWeighted = AggregateFunctionQuantile<Value, QuantileTiming<Value>, NameQuantileTimingWeighted, true, Float32, false>;
template <typename Value, bool _> using FuncQuantilesTimingWeighted = AggregateFunctionQuantile<Value, QuantileTiming<Value>, NameQuantilesTimingWeighted, true, Float32, true>;
template <typename Value, bool float_return> using FuncQuantileTDigest = AggregateFunctionQuantile<Value, QuantileTDigest<Value>, NameQuantileTDigest, false, std::conditional_t<float_return, Float32, void>, false>;
template <typename Value, bool float_return> using FuncQuantilesTDigest = AggregateFunctionQuantile<Value, QuantileTDigest<Value>, NameQuantilesTDigest, false, std::conditional_t<float_return, Float32, void>, true>;
template <typename Value, bool float_return> using FuncQuantileTDigestWeighted = AggregateFunctionQuantile<Value, QuantileTDigest<Value>, NameQuantileTDigestWeighted, true, std::conditional_t<float_return, Float32, void>, false>;
template <typename Value, bool float_return> using FuncQuantilesTDigestWeighted = AggregateFunctionQuantile<Value, QuantileTDigest<Value>, NameQuantilesTDigestWeighted, true, std::conditional_t<float_return, Float32, void>, true>;
template <typename Value, bool float_return> using FuncQuantileBFloat16 = AggregateFunctionQuantile<Value, QuantileBFloat16Histogram<Value>, NameQuantileBFloat16, false, std::conditional_t<float_return, Float64, void>, false>;
template <typename Value, bool float_return> using FuncQuantilesBFloat16 = AggregateFunctionQuantile<Value, QuantileBFloat16Histogram<Value>, NameQuantilesBFloat16, false, std::conditional_t<float_return, Float64, void>, true>;
template <typename Value, bool float_return> using FuncQuantileBFloat16Weighted = AggregateFunctionQuantile<Value, QuantileBFloat16Histogram<Value>, NameQuantileBFloat16Weighted, true, std::conditional_t<float_return, Float64, void>, false>;
template <typename Value, bool float_return> using FuncQuantilesBFloat16Weighted = AggregateFunctionQuantile<Value, QuantileBFloat16Histogram<Value>, NameQuantilesBFloat16Weighted, true, std::conditional_t<float_return, Float64, void>, true>;
template <template <typename, bool> class Function>
constexpr bool supportDecimal()
{
return std::is_same_v<Function<Float32, false>, FuncQuantile<Float32, false>> ||
std::is_same_v<Function<Float32, false>, FuncQuantiles<Float32, false>> ||
std::is_same_v<Function<Float32, false>, FuncQuantileExact<Float32, false>> ||
std::is_same_v<Function<Float32, false>, FuncQuantileExactLow<Float32, false>> ||
std::is_same_v<Function<Float32, false>, FuncQuantileExactHigh<Float32, false>> ||
std::is_same_v<Function<Float32, false>, FuncQuantilesExact<Float32, false>> ||
std::is_same_v<Function<Float32, false>, FuncQuantilesExactLow<Float32, false>> ||
std::is_same_v<Function<Float32, false>, FuncQuantilesExactHigh<Float32, false>> ||
std::is_same_v<Function<Float32, false>, FuncQuantileExactWeighted<Float32, false>> ||
std::is_same_v<Function<Float32, false>, FuncQuantilesExactWeighted<Float32, false>>;
}
template <template <typename, bool> class Function>
constexpr bool supportBigInt()
{
return std::is_same_v<Function<Float32, false>, FuncQuantile<Float32, false>> ||
std::is_same_v<Function<Float32, false>, FuncQuantiles<Float32, false>> ||
std::is_same_v<Function<Float32, false>, FuncQuantileExact<Float32, false>> ||
std::is_same_v<Function<Float32, false>, FuncQuantilesExact<Float32, false>> ||
std::is_same_v<Function<Float32, false>, FuncQuantileExactWeighted<Float32, false>> ||
std::is_same_v<Function<Float32, false>, FuncQuantilesExactWeighted<Float32, false>>;
}
template <template <typename, bool> class Function> template <template <typename, bool> class Function>
AggregateFunctionPtr createAggregateFunctionQuantile( AggregateFunctionPtr createAggregateFunctionQuantile(
const std::string & name, const DataTypes & argument_types, const Array & params, const Settings *) const std::string & name, const DataTypes & argument_types, const Array & params, const Settings *)
@ -102,22 +39,16 @@ AggregateFunctionPtr createAggregateFunctionQuantile(
if (which.idx == TypeIndex::Date) return std::make_shared<Function<DataTypeDate::FieldType, false>>(argument_types, params); if (which.idx == TypeIndex::Date) return std::make_shared<Function<DataTypeDate::FieldType, false>>(argument_types, params);
if (which.idx == TypeIndex::DateTime) return std::make_shared<Function<DataTypeDateTime::FieldType, false>>(argument_types, params); if (which.idx == TypeIndex::DateTime) return std::make_shared<Function<DataTypeDateTime::FieldType, false>>(argument_types, params);
if constexpr (supportDecimal<Function>()) if (which.idx == TypeIndex::Decimal32) return std::make_shared<Function<Decimal32, false>>(argument_types, params);
{ if (which.idx == TypeIndex::Decimal64) return std::make_shared<Function<Decimal64, false>>(argument_types, params);
if (which.idx == TypeIndex::Decimal32) return std::make_shared<Function<Decimal32, false>>(argument_types, params); if (which.idx == TypeIndex::Decimal128) return std::make_shared<Function<Decimal128, false>>(argument_types, params);
if (which.idx == TypeIndex::Decimal64) return std::make_shared<Function<Decimal64, false>>(argument_types, params); if (which.idx == TypeIndex::Decimal256) return std::make_shared<Function<Decimal256, false>>(argument_types, params);
if (which.idx == TypeIndex::Decimal128) return std::make_shared<Function<Decimal128, false>>(argument_types, params); if (which.idx == TypeIndex::DateTime64) return std::make_shared<Function<DateTime64, false>>(argument_types, params);
if (which.idx == TypeIndex::Decimal256) return std::make_shared<Function<Decimal256, false>>(argument_types, params);
if (which.idx == TypeIndex::DateTime64) return std::make_shared<Function<DateTime64, false>>(argument_types, params);
}
if constexpr (supportBigInt<Function>()) if (which.idx == TypeIndex::Int128) return std::make_shared<Function<Int128, true>>(argument_types, params);
{ if (which.idx == TypeIndex::UInt128) return std::make_shared<Function<Int128, true>>(argument_types, params);
if (which.idx == TypeIndex::Int128) return std::make_shared<Function<Int128, true>>(argument_types, params); if (which.idx == TypeIndex::Int256) return std::make_shared<Function<Int256, true>>(argument_types, params);
if (which.idx == TypeIndex::UInt128) return std::make_shared<Function<Int128, true>>(argument_types, params); if (which.idx == TypeIndex::UInt256) return std::make_shared<Function<UInt256, true>>(argument_types, params);
if (which.idx == TypeIndex::Int256) return std::make_shared<Function<Int256, true>>(argument_types, params);
if (which.idx == TypeIndex::UInt256) return std::make_shared<Function<UInt256, true>>(argument_types, params);
}
throw Exception("Illegal type " + argument_type->getName() + " of argument for aggregate function " + name, throw Exception("Illegal type " + argument_type->getName() + " of argument for aggregate function " + name,
ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT); ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT);
@ -133,58 +64,8 @@ void registerAggregateFunctionsQuantile(AggregateFunctionFactory & factory)
factory.registerFunction(NameQuantile::name, createAggregateFunctionQuantile<FuncQuantile>); factory.registerFunction(NameQuantile::name, createAggregateFunctionQuantile<FuncQuantile>);
factory.registerFunction(NameQuantiles::name, { createAggregateFunctionQuantile<FuncQuantiles>, properties }); factory.registerFunction(NameQuantiles::name, { createAggregateFunctionQuantile<FuncQuantiles>, properties });
factory.registerFunction(NameQuantileDeterministic::name, createAggregateFunctionQuantile<FuncQuantileDeterministic>);
factory.registerFunction(NameQuantilesDeterministic::name, { createAggregateFunctionQuantile<FuncQuantilesDeterministic>, properties });
factory.registerFunction(NameQuantileExact::name, createAggregateFunctionQuantile<FuncQuantileExact>);
factory.registerFunction(NameQuantilesExact::name, { createAggregateFunctionQuantile<FuncQuantilesExact>, properties });
factory.registerFunction(NameQuantileExactLow::name, createAggregateFunctionQuantile<FuncQuantileExactLow>);
factory.registerFunction(NameQuantilesExactLow::name, { createAggregateFunctionQuantile<FuncQuantilesExactLow>, properties });
factory.registerFunction(NameQuantileExactHigh::name, createAggregateFunctionQuantile<FuncQuantileExactHigh>);
factory.registerFunction(NameQuantilesExactHigh::name, { createAggregateFunctionQuantile<FuncQuantilesExactHigh>, properties });
factory.registerFunction(NameQuantileExactExclusive::name, createAggregateFunctionQuantile<FuncQuantileExactExclusive>);
factory.registerFunction(NameQuantilesExactExclusive::name, { createAggregateFunctionQuantile<FuncQuantilesExactExclusive>, properties });
factory.registerFunction(NameQuantileExactInclusive::name, createAggregateFunctionQuantile<FuncQuantileExactInclusive>);
factory.registerFunction(NameQuantilesExactInclusive::name, { createAggregateFunctionQuantile<FuncQuantilesExactInclusive>, properties });
factory.registerFunction(NameQuantileExactWeighted::name, createAggregateFunctionQuantile<FuncQuantileExactWeighted>);
factory.registerFunction(NameQuantilesExactWeighted::name, { createAggregateFunctionQuantile<FuncQuantilesExactWeighted>, properties });
factory.registerFunction(NameQuantileTiming::name, createAggregateFunctionQuantile<FuncQuantileTiming>);
factory.registerFunction(NameQuantilesTiming::name, { createAggregateFunctionQuantile<FuncQuantilesTiming>, properties });
factory.registerFunction(NameQuantileTimingWeighted::name, createAggregateFunctionQuantile<FuncQuantileTimingWeighted>);
factory.registerFunction(NameQuantilesTimingWeighted::name, { createAggregateFunctionQuantile<FuncQuantilesTimingWeighted>, properties });
factory.registerFunction(NameQuantileTDigest::name, createAggregateFunctionQuantile<FuncQuantileTDigest>);
factory.registerFunction(NameQuantilesTDigest::name, { createAggregateFunctionQuantile<FuncQuantilesTDigest>, properties });
factory.registerFunction(NameQuantileTDigestWeighted::name, createAggregateFunctionQuantile<FuncQuantileTDigestWeighted>);
factory.registerFunction(NameQuantilesTDigestWeighted::name, { createAggregateFunctionQuantile<FuncQuantilesTDigestWeighted>, properties });
factory.registerFunction(NameQuantileBFloat16::name, createAggregateFunctionQuantile<FuncQuantileBFloat16>);
factory.registerFunction(NameQuantilesBFloat16::name, { createAggregateFunctionQuantile<FuncQuantilesBFloat16>, properties });
factory.registerFunction(NameQuantileBFloat16Weighted::name, createAggregateFunctionQuantile<FuncQuantileBFloat16Weighted>);
factory.registerFunction(NameQuantilesBFloat16Weighted::name, createAggregateFunctionQuantile<FuncQuantilesBFloat16Weighted>);
/// 'median' is an alias for 'quantile' /// 'median' is an alias for 'quantile'
factory.registerAlias("median", NameQuantile::name); factory.registerAlias("median", NameQuantile::name);
factory.registerAlias("medianDeterministic", NameQuantileDeterministic::name);
factory.registerAlias("medianExact", NameQuantileExact::name);
factory.registerAlias("medianExactLow", NameQuantileExactLow::name);
factory.registerAlias("medianExactHigh", NameQuantileExactHigh::name);
factory.registerAlias("medianExactWeighted", NameQuantileExactWeighted::name);
factory.registerAlias("medianTiming", NameQuantileTiming::name);
factory.registerAlias("medianTimingWeighted", NameQuantileTimingWeighted::name);
factory.registerAlias("medianTDigest", NameQuantileTDigest::name);
factory.registerAlias("medianTDigestWeighted", NameQuantileTDigestWeighted::name);
factory.registerAlias("medianBFloat16", NameQuantileBFloat16::name);
factory.registerAlias("medianBFloat16Weighted", NameQuantileBFloat16Weighted::name);
} }
} }

12
src/AggregateFunctions/AggregateFunctionQuantile.h
View File

@ -2,24 +2,12 @@
#include <AggregateFunctions/FactoryHelpers.h> #include <AggregateFunctions/FactoryHelpers.h>
#include <AggregateFunctions/AggregateFunctionFactory.h> #include <AggregateFunctions/AggregateFunctionFactory.h>
/// These must be exposed in header for the purpose of dynamic compilation.
#include <AggregateFunctions/QuantileReservoirSampler.h>
#include <AggregateFunctions/QuantileReservoirSamplerDeterministic.h>
#include <AggregateFunctions/QuantileExact.h>
#include <AggregateFunctions/QuantileExactWeighted.h>
#include <AggregateFunctions/QuantileTiming.h>
#include <AggregateFunctions/QuantileTDigest.h>
#include <AggregateFunctions/QuantileBFloat16Histogram.h>
#include <AggregateFunctions/IAggregateFunction.h> #include <AggregateFunctions/IAggregateFunction.h>
#include <AggregateFunctions/QuantilesCommon.h> #include <AggregateFunctions/QuantilesCommon.h>
#include <Columns/ColumnArray.h> #include <Columns/ColumnArray.h>
#include <Columns/ColumnDecimal.h> #include <Columns/ColumnDecimal.h>
#include <Columns/ColumnsNumber.h> #include <Columns/ColumnsNumber.h>
#include <DataTypes/DataTypeArray.h> #include <DataTypes/DataTypeArray.h>
#include <DataTypes/DataTypeDate.h>
#include <DataTypes/DataTypeDateTime.h>
#include <DataTypes/DataTypesNumber.h> #include <DataTypes/DataTypesNumber.h>
#include <DataTypes/DataTypeAggregateFunction.h> #include <DataTypes/DataTypeAggregateFunction.h>
#include <IO/ReadHelpers.h> #include <IO/ReadHelpers.h>

60
src/AggregateFunctions/AggregateFunctionQuantileBFloat16.cpp Normal file
View File

@ -0,0 +1,60 @@
#include <AggregateFunctions/AggregateFunctionQuantile.h>
#include <AggregateFunctions/QuantileBFloat16Histogram.h>
#include <AggregateFunctions/AggregateFunctionFactory.h>
#include <AggregateFunctions/Helpers.h>
#include <DataTypes/DataTypeDate.h>
#include <DataTypes/DataTypeDateTime.h>
#include <Core/Field.h>
namespace DB
{
struct Settings;
namespace ErrorCodes
{
extern const int ILLEGAL_TYPE_OF_ARGUMENT;
}
namespace
{
template <typename Value, bool float_return> using FuncQuantileBFloat16 = AggregateFunctionQuantile<Value, QuantileBFloat16Histogram<Value>, NameQuantileBFloat16, false, std::conditional_t<float_return, Float64, void>, false>;
template <typename Value, bool float_return> using FuncQuantilesBFloat16 = AggregateFunctionQuantile<Value, QuantileBFloat16Histogram<Value>, NameQuantilesBFloat16, false, std::conditional_t<float_return, Float64, void>, true>;
template <template <typename, bool> class Function>
AggregateFunctionPtr createAggregateFunctionQuantile(
const std::string & name, const DataTypes & argument_types, const Array & params, const Settings *)
{
/// Second argument type check doesn't depend on the type of the first one.
Function<void, true>::assertSecondArg(argument_types);
const DataTypePtr & argument_type = argument_types[0];
WhichDataType which(argument_type);
#define DISPATCH(TYPE) \
if (which.idx == TypeIndex::TYPE) return std::make_shared<Function<TYPE, true>>(argument_types, params);
FOR_BASIC_NUMERIC_TYPES(DISPATCH)
#undef DISPATCH
if (which.idx == TypeIndex::Date) return std::make_shared<Function<DataTypeDate::FieldType, false>>(argument_types, params);
if (which.idx == TypeIndex::DateTime) return std::make_shared<Function<DataTypeDateTime::FieldType, false>>(argument_types, params);
throw Exception("Illegal type " + argument_type->getName() + " of argument for aggregate function " + name,
ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT);
}
}
void registerAggregateFunctionsQuantileBFloat16(AggregateFunctionFactory & factory)
{
/// For aggregate functions returning array we cannot return NULL on empty set.
AggregateFunctionProperties properties = { .returns_default_when_only_null = true };
factory.registerFunction(NameQuantileBFloat16::name, createAggregateFunctionQuantile<FuncQuantileBFloat16>);
factory.registerFunction(NameQuantilesBFloat16::name, { createAggregateFunctionQuantile<FuncQuantilesBFloat16>, properties });
/// 'median' is an alias for 'quantile'
factory.registerAlias("medianBFloat16", NameQuantileBFloat16::name);
}
}

57
src/AggregateFunctions/AggregateFunctionQuantileBFloat16Weighted.cpp Normal file
View File

@ -0,0 +1,57 @@
#include <AggregateFunctions/AggregateFunctionQuantile.h>
#include <AggregateFunctions/QuantileBFloat16Histogram.h>
#include <AggregateFunctions/AggregateFunctionFactory.h>
#include <AggregateFunctions/Helpers.h>
#include <DataTypes/DataTypeDate.h>
#include <DataTypes/DataTypeDateTime.h>
#include <Core/Field.h>
namespace DB
{
struct Settings;
namespace ErrorCodes
{
extern const int ILLEGAL_TYPE_OF_ARGUMENT;
}
namespace
{
template <typename Value, bool float_return> using FuncQuantileBFloat16Weighted = AggregateFunctionQuantile<Value, QuantileBFloat16Histogram<Value>, NameQuantileBFloat16Weighted, true, std::conditional_t<float_return, Float64, void>, false>;
template <typename Value, bool float_return> using FuncQuantilesBFloat16Weighted = AggregateFunctionQuantile<Value, QuantileBFloat16Histogram<Value>, NameQuantilesBFloat16Weighted, true, std::conditional_t<float_return, Float64, void>, true>;
template <template <typename, bool> class Function>
AggregateFunctionPtr createAggregateFunctionQuantile(
const std::string & name, const DataTypes & argument_types, const Array & params, const Settings *)
{
/// Second argument type check doesn't depend on the type of the first one.
Function<void, true>::assertSecondArg(argument_types);
const DataTypePtr & argument_type = argument_types[0];
WhichDataType which(argument_type);
#define DISPATCH(TYPE) \
if (which.idx == TypeIndex::TYPE) return std::make_shared<Function<TYPE, true>>(argument_types, params);
FOR_BASIC_NUMERIC_TYPES(DISPATCH)
#undef DISPATCH
if (which.idx == TypeIndex::Date) return std::make_shared<Function<DataTypeDate::FieldType, false>>(argument_types, params);
if (which.idx == TypeIndex::DateTime) return std::make_shared<Function<DataTypeDateTime::FieldType, false>>(argument_types, params);
throw Exception("Illegal type " + argument_type->getName() + " of argument for aggregate function " + name,
ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT);
}
}
void registerAggregateFunctionsQuantileBFloat16Weighted(AggregateFunctionFactory & factory)
{
factory.registerFunction(NameQuantileBFloat16Weighted::name, createAggregateFunctionQuantile<FuncQuantileBFloat16Weighted>);
factory.registerFunction(NameQuantilesBFloat16Weighted::name, createAggregateFunctionQuantile<FuncQuantilesBFloat16Weighted>);
/// 'median' is an alias for 'quantile'
factory.registerAlias("medianBFloat16Weighted", NameQuantileBFloat16Weighted::name);
}
}

65
src/AggregateFunctions/AggregateFunctionQuantileDeterministic.cpp Normal file
View File

@ -0,0 +1,65 @@
#include <AggregateFunctions/AggregateFunctionQuantile.h>
#include <AggregateFunctions/QuantileReservoirSamplerDeterministic.h>
#include <AggregateFunctions/AggregateFunctionFactory.h>
#include <AggregateFunctions/Helpers.h>
#include <DataTypes/DataTypeDate.h>
#include <DataTypes/DataTypeDateTime.h>
#include <Core/Field.h>
namespace DB
{
struct Settings;
namespace ErrorCodes
{
extern const int ILLEGAL_TYPE_OF_ARGUMENT;
}
namespace
{
template <typename Value, bool float_return> using FuncQuantileDeterministic = AggregateFunctionQuantile<Value, QuantileReservoirSamplerDeterministic<Value>, NameQuantileDeterministic, true, std::conditional_t<float_return, Float64, void>, false>;
template <typename Value, bool float_return> using FuncQuantilesDeterministic = AggregateFunctionQuantile<Value, QuantileReservoirSamplerDeterministic<Value>, NameQuantilesDeterministic, true, std::conditional_t<float_return, Float64, void>, true>;
template <template <typename, bool> class Function>
AggregateFunctionPtr createAggregateFunctionQuantile(
const std::string & name, const DataTypes & argument_types, const Array & params, const Settings *)
{
/// Second argument type check doesn't depend on the type of the first one.
Function<void, true>::assertSecondArg(argument_types);
const DataTypePtr & argument_type = argument_types[0];
WhichDataType which(argument_type);
#define DISPATCH(TYPE) \
if (which.idx == TypeIndex::TYPE) return std::make_shared<Function<TYPE, true>>(argument_types, params);
FOR_BASIC_NUMERIC_TYPES(DISPATCH)
#undef DISPATCH
if (which.idx == TypeIndex::Date) return std::make_shared<Function<DataTypeDate::FieldType, false>>(argument_types, params);
if (which.idx == TypeIndex::DateTime) return std::make_shared<Function<DataTypeDateTime::FieldType, false>>(argument_types, params);
if (which.idx == TypeIndex::Int128) return std::make_shared<Function<Int128, true>>(argument_types, params);
if (which.idx == TypeIndex::UInt128) return std::make_shared<Function<Int128, true>>(argument_types, params);
if (which.idx == TypeIndex::Int256) return std::make_shared<Function<Int256, true>>(argument_types, params);
if (which.idx == TypeIndex::UInt256) return std::make_shared<Function<UInt256, true>>(argument_types, params);
throw Exception("Illegal type " + argument_type->getName() + " of argument for aggregate function " + name,
ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT);
}
}
void registerAggregateFunctionsQuantileDeterministic(AggregateFunctionFactory & factory)
{
/// For aggregate functions returning array we cannot return NULL on empty set.
AggregateFunctionProperties properties = { .returns_default_when_only_null = true };
factory.registerFunction(NameQuantileDeterministic::name, createAggregateFunctionQuantile<FuncQuantileDeterministic>);
factory.registerFunction(NameQuantilesDeterministic::name, { createAggregateFunctionQuantile<FuncQuantilesDeterministic>, properties });
/// 'median' is an alias for 'quantile'
factory.registerAlias("medianDeterministic", NameQuantileDeterministic::name);
}
}

72
src/AggregateFunctions/AggregateFunctionQuantileExact.cpp Normal file
View File

@ -0,0 +1,72 @@
#include <AggregateFunctions/AggregateFunctionQuantile.h>
#include <AggregateFunctions/QuantileExact.h>
#include <AggregateFunctions/AggregateFunctionFactory.h>
#include <AggregateFunctions/Helpers.h>
#include <DataTypes/DataTypeDate.h>
#include <DataTypes/DataTypeDateTime.h>
#include <Core/Field.h>
namespace DB
{
struct Settings;
namespace ErrorCodes
{
extern const int ILLEGAL_TYPE_OF_ARGUMENT;
}
namespace
{
template <typename Value, bool _> using FuncQuantileExact = AggregateFunctionQuantile<Value, QuantileExact<Value>, NameQuantileExact, false, void, false>;
template <typename Value, bool _> using FuncQuantilesExact = AggregateFunctionQuantile<Value, QuantileExact<Value>, NameQuantilesExact, false, void, true>;
template <template <typename, bool> class Function>
AggregateFunctionPtr createAggregateFunctionQuantile(
const std::string & name, const DataTypes & argument_types, const Array & params, const Settings *)
{
/// Second argument type check doesn't depend on the type of the first one.
Function<void, true>::assertSecondArg(argument_types);
const DataTypePtr & argument_type = argument_types[0];
WhichDataType which(argument_type);
#define DISPATCH(TYPE) \
if (which.idx == TypeIndex::TYPE) return std::make_shared<Function<TYPE, true>>(argument_types, params);
FOR_BASIC_NUMERIC_TYPES(DISPATCH)
#undef DISPATCH
if (which.idx == TypeIndex::Date) return std::make_shared<Function<DataTypeDate::FieldType, false>>(argument_types, params);
if (which.idx == TypeIndex::DateTime) return std::make_shared<Function<DataTypeDateTime::FieldType, false>>(argument_types, params);
if (which.idx == TypeIndex::Decimal32) return std::make_shared<Function<Decimal32, false>>(argument_types, params);
if (which.idx == TypeIndex::Decimal64) return std::make_shared<Function<Decimal64, false>>(argument_types, params);
if (which.idx == TypeIndex::Decimal128) return std::make_shared<Function<Decimal128, false>>(argument_types, params);
if (which.idx == TypeIndex::Decimal256) return std::make_shared<Function<Decimal256, false>>(argument_types, params);
if (which.idx == TypeIndex::DateTime64) return std::make_shared<Function<DateTime64, false>>(argument_types, params);
if (which.idx == TypeIndex::Int128) return std::make_shared<Function<Int128, true>>(argument_types, params);
if (which.idx == TypeIndex::UInt128) return std::make_shared<Function<Int128, true>>(argument_types, params);
if (which.idx == TypeIndex::Int256) return std::make_shared<Function<Int256, true>>(argument_types, params);
if (which.idx == TypeIndex::UInt256) return std::make_shared<Function<UInt256, true>>(argument_types, params);
throw Exception("Illegal type " + argument_type->getName() + " of argument for aggregate function " + name,
ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT);
}
}
void registerAggregateFunctionsQuantileExact(AggregateFunctionFactory & factory)
{
/// For aggregate functions returning array we cannot return NULL on empty set.
AggregateFunctionProperties properties = { .returns_default_when_only_null = true };
factory.registerFunction(NameQuantileExact::name, createAggregateFunctionQuantile<FuncQuantileExact>);
factory.registerFunction(NameQuantilesExact::name, { createAggregateFunctionQuantile<FuncQuantilesExact>, properties });
/// 'median' is an alias for 'quantile'
factory.registerAlias("medianExact", NameQuantileExact::name);
}
}

57
src/AggregateFunctions/AggregateFunctionQuantileExactExclusive.cpp Normal file
View File

@ -0,0 +1,57 @@
#include <AggregateFunctions/AggregateFunctionQuantile.h>
#include <AggregateFunctions/QuantileExact.h>
#include <AggregateFunctions/AggregateFunctionFactory.h>
#include <AggregateFunctions/Helpers.h>
#include <DataTypes/DataTypeDate.h>
#include <DataTypes/DataTypeDateTime.h>
#include <Core/Field.h>
namespace DB
{
struct Settings;
namespace ErrorCodes
{
extern const int ILLEGAL_TYPE_OF_ARGUMENT;
}
namespace
{
template <typename Value, bool _> using FuncQuantileExactExclusive = AggregateFunctionQuantile<Value, QuantileExactExclusive<Value>, NameQuantileExactExclusive, false, Float64, false>;
template <typename Value, bool _> using FuncQuantilesExactExclusive = AggregateFunctionQuantile<Value, QuantileExactExclusive<Value>, NameQuantilesExactExclusive, false, Float64, true>;
template <template <typename, bool> class Function>
AggregateFunctionPtr createAggregateFunctionQuantile(
const std::string & name, const DataTypes & argument_types, const Array & params, const Settings *)
{
/// Second argument type check doesn't depend on the type of the first one.
Function<void, true>::assertSecondArg(argument_types);
const DataTypePtr & argument_type = argument_types[0];
WhichDataType which(argument_type);
#define DISPATCH(TYPE) \
if (which.idx == TypeIndex::TYPE) return std::make_shared<Function<TYPE, true>>(argument_types, params);
FOR_BASIC_NUMERIC_TYPES(DISPATCH)
#undef DISPATCH
if (which.idx == TypeIndex::Date) return std::make_shared<Function<DataTypeDate::FieldType, false>>(argument_types, params);
if (which.idx == TypeIndex::DateTime) return std::make_shared<Function<DataTypeDateTime::FieldType, false>>(argument_types, params);
throw Exception("Illegal type " + argument_type->getName() + " of argument for aggregate function " + name,
ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT);
}
}
void registerAggregateFunctionsQuantileExactExclusive(AggregateFunctionFactory & factory)
{
/// For aggregate functions returning array we cannot return NULL on empty set.
AggregateFunctionProperties properties = { .returns_default_when_only_null = true };
factory.registerFunction(NameQuantileExactExclusive::name, createAggregateFunctionQuantile<FuncQuantileExactExclusive>);
factory.registerFunction(NameQuantilesExactExclusive::name, { createAggregateFunctionQuantile<FuncQuantilesExactExclusive>, properties });
}
}

67
src/AggregateFunctions/AggregateFunctionQuantileExactHigh.cpp Normal file
View File

@ -0,0 +1,67 @@
#include <AggregateFunctions/AggregateFunctionQuantile.h>
#include <AggregateFunctions/QuantileExact.h>
#include <AggregateFunctions/AggregateFunctionFactory.h>
#include <AggregateFunctions/Helpers.h>
#include <DataTypes/DataTypeDate.h>
#include <DataTypes/DataTypeDateTime.h>
#include <Core/Field.h>
namespace DB
{
struct Settings;
namespace ErrorCodes
{
extern const int ILLEGAL_TYPE_OF_ARGUMENT;
}
namespace
{
template <typename Value, bool _> using FuncQuantileExactHigh = AggregateFunctionQuantile<Value, QuantileExactHigh<Value>, NameQuantileExactHigh, false, void, false>;
template <typename Value, bool _> using FuncQuantilesExactHigh = AggregateFunctionQuantile<Value, QuantileExactHigh<Value>, NameQuantilesExactHigh, false, void, true>;
template <template <typename, bool> class Function>
AggregateFunctionPtr createAggregateFunctionQuantile(
const std::string & name, const DataTypes & argument_types, const Array & params, const Settings *)
{
/// Second argument type check doesn't depend on the type of the first one.
Function<void, true>::assertSecondArg(argument_types);
const DataTypePtr & argument_type = argument_types[0];
WhichDataType which(argument_type);
#define DISPATCH(TYPE) \
if (which.idx == TypeIndex::TYPE) return std::make_shared<Function<TYPE, true>>(argument_types, params);
FOR_BASIC_NUMERIC_TYPES(DISPATCH)
#undef DISPATCH
if (which.idx == TypeIndex::Date) return std::make_shared<Function<DataTypeDate::FieldType, false>>(argument_types, params);
if (which.idx == TypeIndex::DateTime) return std::make_shared<Function<DataTypeDateTime::FieldType, false>>(argument_types, params);
if (which.idx == TypeIndex::Decimal32) return std::make_shared<Function<Decimal32, false>>(argument_types, params);
if (which.idx == TypeIndex::Decimal64) return std::make_shared<Function<Decimal64, false>>(argument_types, params);
if (which.idx == TypeIndex::Decimal128) return std::make_shared<Function<Decimal128, false>>(argument_types, params);
if (which.idx == TypeIndex::Decimal256) return std::make_shared<Function<Decimal256, false>>(argument_types, params);
if (which.idx == TypeIndex::DateTime64) return std::make_shared<Function<DateTime64, false>>(argument_types, params);
throw Exception("Illegal type " + argument_type->getName() + " of argument for aggregate function " + name,
ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT);
}
}
void registerAggregateFunctionsQuantileExactHigh(AggregateFunctionFactory & factory)
{
/// For aggregate functions returning array we cannot return NULL on empty set.
AggregateFunctionProperties properties = { .returns_default_when_only_null = true };
factory.registerFunction(NameQuantileExactHigh::name, createAggregateFunctionQuantile<FuncQuantileExactHigh>);
factory.registerFunction(NameQuantilesExactHigh::name, { createAggregateFunctionQuantile<FuncQuantilesExactHigh>, properties });
/// 'median' is an alias for 'quantile'
factory.registerAlias("medianExactHigh", NameQuantileExactHigh::name);
}
}

57
src/AggregateFunctions/AggregateFunctionQuantileExactInclusive.cpp Normal file
View File

@ -0,0 +1,57 @@
#include <AggregateFunctions/AggregateFunctionQuantile.h>
#include <AggregateFunctions/QuantileExact.h>
#include <AggregateFunctions/AggregateFunctionFactory.h>
#include <AggregateFunctions/Helpers.h>
#include <DataTypes/DataTypeDate.h>
#include <DataTypes/DataTypeDateTime.h>
#include <Core/Field.h>
namespace DB
{
struct Settings;
namespace ErrorCodes
{
extern const int ILLEGAL_TYPE_OF_ARGUMENT;
}
namespace
{
template <typename Value, bool _> using FuncQuantileExactInclusive = AggregateFunctionQuantile<Value, QuantileExactInclusive<Value>, NameQuantileExactInclusive, false, Float64, false>;
template <typename Value, bool _> using FuncQuantilesExactInclusive = AggregateFunctionQuantile<Value, QuantileExactInclusive<Value>, NameQuantilesExactInclusive, false, Float64, true>;
template <template <typename, bool> class Function>
AggregateFunctionPtr createAggregateFunctionQuantile(
const std::string & name, const DataTypes & argument_types, const Array & params, const Settings *)
{
/// Second argument type check doesn't depend on the type of the first one.
Function<void, true>::assertSecondArg(argument_types);
const DataTypePtr & argument_type = argument_types[0];
WhichDataType which(argument_type);
#define DISPATCH(TYPE) \
if (which.idx == TypeIndex::TYPE) return std::make_shared<Function<TYPE, true>>(argument_types, params);
FOR_BASIC_NUMERIC_TYPES(DISPATCH)
#undef DISPATCH
if (which.idx == TypeIndex::Date) return std::make_shared<Function<DataTypeDate::FieldType, false>>(argument_types, params);
if (which.idx == TypeIndex::DateTime) return std::make_shared<Function<DataTypeDateTime::FieldType, false>>(argument_types, params);
throw Exception("Illegal type " + argument_type->getName() + " of argument for aggregate function " + name,
ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT);
}
}
void registerAggregateFunctionsQuantileExactInclusive(AggregateFunctionFactory & factory)
{
/// For aggregate functions returning array we cannot return NULL on empty set.
AggregateFunctionProperties properties = { .returns_default_when_only_null = true };
factory.registerFunction(NameQuantileExactInclusive::name, createAggregateFunctionQuantile<FuncQuantileExactInclusive>);
factory.registerFunction(NameQuantilesExactInclusive::name, { createAggregateFunctionQuantile<FuncQuantilesExactInclusive>, properties });
}
}

66
src/AggregateFunctions/AggregateFunctionQuantileExactLow.cpp Normal file
View File

@ -0,0 +1,66 @@
#include <AggregateFunctions/AggregateFunctionQuantile.h>
#include <AggregateFunctions/QuantileExact.h>
#include <AggregateFunctions/AggregateFunctionFactory.h>
#include <AggregateFunctions/Helpers.h>
#include <DataTypes/DataTypeDate.h>
#include <DataTypes/DataTypeDateTime.h>
#include <Core/Field.h>
namespace DB
{
struct Settings;
namespace ErrorCodes
{
extern const int ILLEGAL_TYPE_OF_ARGUMENT;
}
namespace
{
template <typename Value, bool _> using FuncQuantileExactLow = AggregateFunctionQuantile<Value, QuantileExactLow<Value>, NameQuantileExactLow, false, void, false>;
template <typename Value, bool _> using FuncQuantilesExactLow = AggregateFunctionQuantile<Value, QuantileExactLow<Value>, NameQuantilesExactLow, false, void, true>;
template <template <typename, bool> class Function>
AggregateFunctionPtr createAggregateFunctionQuantile(
const std::string & name, const DataTypes & argument_types, const Array & params, const Settings *)
{
/// Second argument type check doesn't depend on the type of the first one.
Function<void, true>::assertSecondArg(argument_types);
const DataTypePtr & argument_type = argument_types[0];
WhichDataType which(argument_type);
#define DISPATCH(TYPE) \
if (which.idx == TypeIndex::TYPE) return std::make_shared<Function<TYPE, true>>(argument_types, params);
FOR_BASIC_NUMERIC_TYPES(DISPATCH)
#undef DISPATCH
if (which.idx == TypeIndex::Date) return std::make_shared<Function<DataTypeDate::FieldType, false>>(argument_types, params);
if (which.idx == TypeIndex::DateTime) return std::make_shared<Function<DataTypeDateTime::FieldType, false>>(argument_types, params);
if (which.idx == TypeIndex::Decimal32) return std::make_shared<Function<Decimal32, false>>(argument_types, params);
if (which.idx == TypeIndex::Decimal64) return std::make_shared<Function<Decimal64, false>>(argument_types, params);
if (which.idx == TypeIndex::Decimal128) return std::make_shared<Function<Decimal128, false>>(argument_types, params);
if (which.idx == TypeIndex::Decimal256) return std::make_shared<Function<Decimal256, false>>(argument_types, params);
if (which.idx == TypeIndex::DateTime64) return std::make_shared<Function<DateTime64, false>>(argument_types, params);
throw Exception("Illegal type " + argument_type->getName() + " of argument for aggregate function " + name,
ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT);
}
}
void registerAggregateFunctionsQuantileExactLow(AggregateFunctionFactory & factory)
{
/// For aggregate functions returning array we cannot return NULL on empty set.
AggregateFunctionProperties properties = { .returns_default_when_only_null = true };
factory.registerFunction(NameQuantileExactLow::name, createAggregateFunctionQuantile<FuncQuantileExactLow>);
factory.registerFunction(NameQuantilesExactLow::name, { createAggregateFunctionQuantile<FuncQuantilesExactLow>, properties });
/// 'median' is an alias for 'quantile'
factory.registerAlias("medianExactLow", NameQuantileExactLow::name);
}
}

71
src/AggregateFunctions/AggregateFunctionQuantileExactWeighted.cpp Normal file
View File

@ -0,0 +1,71 @@
#include <AggregateFunctions/AggregateFunctionQuantile.h>
#include <AggregateFunctions/QuantileExactWeighted.h>
#include <AggregateFunctions/AggregateFunctionFactory.h>
#include <AggregateFunctions/Helpers.h>
#include <DataTypes/DataTypeDate.h>
#include <DataTypes/DataTypeDateTime.h>
#include <Core/Field.h>
namespace DB
{
struct Settings;
namespace ErrorCodes
{
extern const int ILLEGAL_TYPE_OF_ARGUMENT;
}
namespace
{
template <typename Value, bool _> using FuncQuantileExactWeighted = AggregateFunctionQuantile<Value, QuantileExactWeighted<Value>, NameQuantileExactWeighted, true, void, false>;
template <typename Value, bool _> using FuncQuantilesExactWeighted = AggregateFunctionQuantile<Value, QuantileExactWeighted<Value>, NameQuantilesExactWeighted, true, void, true>;
template <template <typename, bool> class Function>
AggregateFunctionPtr createAggregateFunctionQuantile(
const std::string & name, const DataTypes & argument_types, const Array & params, const Settings *)
{
/// Second argument type check doesn't depend on the type of the first one.
Function<void, true>::assertSecondArg(argument_types);
const DataTypePtr & argument_type = argument_types[0];
WhichDataType which(argument_type);
#define DISPATCH(TYPE) \
if (which.idx == TypeIndex::TYPE) return std::make_shared<Function<TYPE, true>>(argument_types, params);
FOR_BASIC_NUMERIC_TYPES(DISPATCH)
#undef DISPATCH
if (which.idx == TypeIndex::Date) return std::make_shared<Function<DataTypeDate::FieldType, false>>(argument_types, params);
if (which.idx == TypeIndex::DateTime) return std::make_shared<Function<DataTypeDateTime::FieldType, false>>(argument_types, params);
if (which.idx == TypeIndex::Decimal32) return std::make_shared<Function<Decimal32, false>>(argument_types, params);
if (which.idx == TypeIndex::Decimal64) return std::make_shared<Function<Decimal64, false>>(argument_types, params);
if (which.idx == TypeIndex::Decimal128) return std::make_shared<Function<Decimal128, false>>(argument_types, params);
if (which.idx == TypeIndex::Decimal256) return std::make_shared<Function<Decimal256, false>>(argument_types, params);
if (which.idx == TypeIndex::DateTime64) return std::make_shared<Function<DateTime64, false>>(argument_types, params);
if (which.idx == TypeIndex::Int128) return std::make_shared<Function<Int128, true>>(argument_types, params);
if (which.idx == TypeIndex::UInt128) return std::make_shared<Function<Int128, true>>(argument_types, params);
if (which.idx == TypeIndex::Int256) return std::make_shared<Function<Int256, true>>(argument_types, params);
if (which.idx == TypeIndex::UInt256) return std::make_shared<Function<UInt256, true>>(argument_types, params);
throw Exception("Illegal type " + argument_type->getName() + " of argument for aggregate function " + name,
ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT);
}
}
void registerAggregateFunctionsQuantileExactWeighted(AggregateFunctionFactory & factory)
{
/// For aggregate functions returning array we cannot return NULL on empty set.
AggregateFunctionProperties properties = { .returns_default_when_only_null = true };
factory.registerFunction(NameQuantileExactWeighted::name, createAggregateFunctionQuantile<FuncQuantileExactWeighted>);
factory.registerFunction(NameQuantilesExactWeighted::name, { createAggregateFunctionQuantile<FuncQuantilesExactWeighted>, properties });
/// 'median' is an alias for 'quantile'
factory.registerAlias("medianExactWeighted", NameQuantileExactWeighted::name);
}
}

60
src/AggregateFunctions/AggregateFunctionQuantileTDigest.cpp Normal file
View File

@ -0,0 +1,60 @@
#include <AggregateFunctions/AggregateFunctionQuantile.h>
#include <AggregateFunctions/QuantileTDigest.h>
#include <AggregateFunctions/AggregateFunctionFactory.h>
#include <AggregateFunctions/Helpers.h>
#include <DataTypes/DataTypeDate.h>
#include <DataTypes/DataTypeDateTime.h>
#include <Core/Field.h>
namespace DB
{
struct Settings;
namespace ErrorCodes
{
extern const int ILLEGAL_TYPE_OF_ARGUMENT;
}
namespace
{
template <typename Value, bool float_return> using FuncQuantileTDigest = AggregateFunctionQuantile<Value, QuantileTDigest<Value>, NameQuantileTDigest, false, std::conditional_t<float_return, Float32, void>, false>;
template <typename Value, bool float_return> using FuncQuantilesTDigest = AggregateFunctionQuantile<Value, QuantileTDigest<Value>, NameQuantilesTDigest, false, std::conditional_t<float_return, Float32, void>, true>;
template <template <typename, bool> class Function>
AggregateFunctionPtr createAggregateFunctionQuantile(
const std::string & name, const DataTypes & argument_types, const Array & params, const Settings *)
{
/// Second argument type check doesn't depend on the type of the first one.
Function<void, true>::assertSecondArg(argument_types);
const DataTypePtr & argument_type = argument_types[0];
WhichDataType which(argument_type);
#define DISPATCH(TYPE) \
if (which.idx == TypeIndex::TYPE) return std::make_shared<Function<TYPE, true>>(argument_types, params);
FOR_BASIC_NUMERIC_TYPES(DISPATCH)
#undef DISPATCH
if (which.idx == TypeIndex::Date) return std::make_shared<Function<DataTypeDate::FieldType, false>>(argument_types, params);
if (which.idx == TypeIndex::DateTime) return std::make_shared<Function<DataTypeDateTime::FieldType, false>>(argument_types, params);
throw Exception("Illegal type " + argument_type->getName() + " of argument for aggregate function " + name,
ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT);
}
}
void registerAggregateFunctionsQuantileTDigest(AggregateFunctionFactory & factory)
{
/// For aggregate functions returning array we cannot return NULL on empty set.
AggregateFunctionProperties properties = { .returns_default_when_only_null = true };
factory.registerFunction(NameQuantileTDigest::name, createAggregateFunctionQuantile<FuncQuantileTDigest>);
factory.registerFunction(NameQuantilesTDigest::name, { createAggregateFunctionQuantile<FuncQuantilesTDigest>, properties });
/// 'median' is an alias for 'quantile'
factory.registerAlias("medianTDigest", NameQuantileTDigest::name);
}
}

60
src/AggregateFunctions/AggregateFunctionQuantileTDigestWeighted.cpp Normal file
View File

@ -0,0 +1,60 @@
#include <AggregateFunctions/AggregateFunctionQuantile.h>
#include <AggregateFunctions/QuantileTDigest.h>
#include <AggregateFunctions/AggregateFunctionFactory.h>
#include <AggregateFunctions/Helpers.h>
#include <DataTypes/DataTypeDate.h>
#include <DataTypes/DataTypeDateTime.h>
#include <Core/Field.h>
namespace DB
{
struct Settings;
namespace ErrorCodes
{
extern const int ILLEGAL_TYPE_OF_ARGUMENT;
}
namespace
{
template <typename Value, bool float_return> using FuncQuantileTDigestWeighted = AggregateFunctionQuantile<Value, QuantileTDigest<Value>, NameQuantileTDigestWeighted, true, std::conditional_t<float_return, Float32, void>, false>;
template <typename Value, bool float_return> using FuncQuantilesTDigestWeighted = AggregateFunctionQuantile<Value, QuantileTDigest<Value>, NameQuantilesTDigestWeighted, true, std::conditional_t<float_return, Float32, void>, true>;
template <template <typename, bool> class Function>
AggregateFunctionPtr createAggregateFunctionQuantile(
const std::string & name, const DataTypes & argument_types, const Array & params, const Settings *)
{
/// Second argument type check doesn't depend on the type of the first one.
Function<void, true>::assertSecondArg(argument_types);
const DataTypePtr & argument_type = argument_types[0];
WhichDataType which(argument_type);
#define DISPATCH(TYPE) \
if (which.idx == TypeIndex::TYPE) return std::make_shared<Function<TYPE, true>>(argument_types, params);
FOR_BASIC_NUMERIC_TYPES(DISPATCH)
#undef DISPATCH
if (which.idx == TypeIndex::Date) return std::make_shared<Function<DataTypeDate::FieldType, false>>(argument_types, params);
if (which.idx == TypeIndex::DateTime) return std::make_shared<Function<DataTypeDateTime::FieldType, false>>(argument_types, params);
throw Exception("Illegal type " + argument_type->getName() + " of argument for aggregate function " + name,
ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT);
}
}
void registerAggregateFunctionsQuantileTDigestWeighted(AggregateFunctionFactory & factory)
{
/// For aggregate functions returning array we cannot return NULL on empty set.
AggregateFunctionProperties properties = { .returns_default_when_only_null = true };
factory.registerFunction(NameQuantileTDigestWeighted::name, createAggregateFunctionQuantile<FuncQuantileTDigestWeighted>);
factory.registerFunction(NameQuantilesTDigestWeighted::name, { createAggregateFunctionQuantile<FuncQuantilesTDigestWeighted>, properties });
/// 'median' is an alias for 'quantile'
factory.registerAlias("medianTDigestWeighted", NameQuantileTDigestWeighted::name);
}
}

60
src/AggregateFunctions/AggregateFunctionQuantileTiming.cpp Normal file
View File

@ -0,0 +1,60 @@
#include <AggregateFunctions/AggregateFunctionQuantile.h>
#include <AggregateFunctions/QuantileTiming.h>
#include <AggregateFunctions/AggregateFunctionFactory.h>
#include <AggregateFunctions/Helpers.h>
#include <DataTypes/DataTypeDate.h>
#include <DataTypes/DataTypeDateTime.h>
#include <Core/Field.h>
namespace DB
{
struct Settings;
namespace ErrorCodes
{
extern const int ILLEGAL_TYPE_OF_ARGUMENT;
}
namespace
{
template <typename Value, bool _> using FuncQuantileTiming = AggregateFunctionQuantile<Value, QuantileTiming<Value>, NameQuantileTiming, false, Float32, false>;
template <typename Value, bool _> using FuncQuantilesTiming = AggregateFunctionQuantile<Value, QuantileTiming<Value>, NameQuantilesTiming, false, Float32, true>;
template <template <typename, bool> class Function>
AggregateFunctionPtr createAggregateFunctionQuantile(
const std::string & name, const DataTypes & argument_types, const Array & params, const Settings *)
{
/// Second argument type check doesn't depend on the type of the first one.
Function<void, true>::assertSecondArg(argument_types);
const DataTypePtr & argument_type = argument_types[0];
WhichDataType which(argument_type);
#define DISPATCH(TYPE) \
if (which.idx == TypeIndex::TYPE) return std::make_shared<Function<TYPE, true>>(argument_types, params);
FOR_BASIC_NUMERIC_TYPES(DISPATCH)
#undef DISPATCH
if (which.idx == TypeIndex::Date) return std::make_shared<Function<DataTypeDate::FieldType, false>>(argument_types, params);
if (which.idx == TypeIndex::DateTime) return std::make_shared<Function<DataTypeDateTime::FieldType, false>>(argument_types, params);
throw Exception("Illegal type " + argument_type->getName() + " of argument for aggregate function " + name,
ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT);
}
}
void registerAggregateFunctionsQuantileTiming(AggregateFunctionFactory & factory)
{
/// For aggregate functions returning array we cannot return NULL on empty set.
AggregateFunctionProperties properties = { .returns_default_when_only_null = true };
factory.registerFunction(NameQuantileTiming::name, createAggregateFunctionQuantile<FuncQuantileTiming>);
factory.registerFunction(NameQuantilesTiming::name, { createAggregateFunctionQuantile<FuncQuantilesTiming>, properties });
/// 'median' is an alias for 'quantile'
factory.registerAlias("medianTiming", NameQuantileTiming::name);
}
}

60
src/AggregateFunctions/AggregateFunctionQuantileTimingWeighted.cpp Normal file
View File

@ -0,0 +1,60 @@
#include <AggregateFunctions/AggregateFunctionQuantile.h>
#include <AggregateFunctions/QuantileTiming.h>
#include <AggregateFunctions/AggregateFunctionFactory.h>
#include <AggregateFunctions/Helpers.h>
#include <DataTypes/DataTypeDate.h>
#include <DataTypes/DataTypeDateTime.h>
#include <Core/Field.h>
namespace DB
{
struct Settings;
namespace ErrorCodes
{
extern const int ILLEGAL_TYPE_OF_ARGUMENT;
}
namespace
{
template <typename Value, bool _> using FuncQuantileTimingWeighted = AggregateFunctionQuantile<Value, QuantileTiming<Value>, NameQuantileTimingWeighted, true, Float32, false>;
template <typename Value, bool _> using FuncQuantilesTimingWeighted = AggregateFunctionQuantile<Value, QuantileTiming<Value>, NameQuantilesTimingWeighted, true, Float32, true>;
template <template <typename, bool> class Function>
AggregateFunctionPtr createAggregateFunctionQuantile(
const std::string & name, const DataTypes & argument_types, const Array & params, const Settings *)
{
/// Second argument type check doesn't depend on the type of the first one.
Function<void, true>::assertSecondArg(argument_types);
const DataTypePtr & argument_type = argument_types[0];
WhichDataType which(argument_type);
#define DISPATCH(TYPE) \
if (which.idx == TypeIndex::TYPE) return std::make_shared<Function<TYPE, true>>(argument_types, params);
FOR_BASIC_NUMERIC_TYPES(DISPATCH)
#undef DISPATCH
if (which.idx == TypeIndex::Date) return std::make_shared<Function<DataTypeDate::FieldType, false>>(argument_types, params);
if (which.idx == TypeIndex::DateTime) return std::make_shared<Function<DataTypeDateTime::FieldType, false>>(argument_types, params);
throw Exception("Illegal type " + argument_type->getName() + " of argument for aggregate function " + name,
ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT);
}
}
void registerAggregateFunctionsQuantileTimingWeighted(AggregateFunctionFactory & factory)
{
/// For aggregate functions returning array we cannot return NULL on empty set.
AggregateFunctionProperties properties = { .returns_default_when_only_null = true };
factory.registerFunction(NameQuantileTimingWeighted::name, createAggregateFunctionQuantile<FuncQuantileTimingWeighted>);
factory.registerFunction(NameQuantilesTimingWeighted::name, { createAggregateFunctionQuantile<FuncQuantilesTimingWeighted>, properties });
/// 'median' is an alias for 'quantile'
factory.registerAlias("medianTimingWeighted", NameQuantileTimingWeighted::name);
}
}

4
src/AggregateFunctions/AggregateFunctionSumMap.h
View File

@ -519,7 +519,7 @@ private:
template <typename FieldType> template <typename FieldType>
bool compareImpl(FieldType & x) const bool compareImpl(FieldType & x) const
{ {
auto val = get<FieldType>(rhs); auto val = rhs.get<FieldType>();
if (val > x) if (val > x)
{ {
x = val; x = val;
@ -554,7 +554,7 @@ private:
template <typename FieldType> template <typename FieldType>
bool compareImpl(FieldType & x) const bool compareImpl(FieldType & x) const
{ {
auto val = get<FieldType>(rhs); auto val = rhs.get<FieldType>();
if (val < x) if (val < x)
{ {
x = val; x = val;

7
src/AggregateFunctions/QuantileTDigest.h
View File

@ -81,7 +81,7 @@ class QuantileTDigest
*/ */
struct Params struct Params
{ {
Value epsilon = 0.01; Value epsilon = 0.01f;
size_t max_centroids = 2048; size_t max_centroids = 2048;
size_t max_unmerged = 2048; size_t max_unmerged = 2048;
}; };
@ -99,13 +99,12 @@ class QuantileTDigest
BetterFloat count = 0; BetterFloat count = 0;
size_t unmerged = 0; size_t unmerged = 0;
/** Linear interpolation at the point x on the line (x1, y1)..(x2, y2) /// Linear interpolation at the point x on the line (x1, y1)..(x2, y2)
*/
static Value interpolate(Value x, Value x1, Value y1, Value x2, Value y2) static Value interpolate(Value x, Value x1, Value y1, Value x2, Value y2)
{ {
/// Symmetric interpolation for better results with infinities. /// Symmetric interpolation for better results with infinities.
double k = (x - x1) / (x2 - x1); double k = (x - x1) / (x2 - x1);
return (1 - k) * y1 + k * y2; return static_cast<Value>((1 - k) * y1 + k * y2);
} }
struct RadixSortTraits struct RadixSortTraits

4
src/AggregateFunctions/QuantileTiming.h
View File

@ -178,7 +178,7 @@ namespace detail
if (!elems.empty()) if (!elems.empty())
{ {
size_t n = level < 1 size_t n = level < 1
? level * elems.size() ? static_cast<size_t>(level * elems.size())
: (elems.size() - 1); : (elems.size() - 1);
/// Sorting an array will not be considered a violation of constancy. /// Sorting an array will not be considered a violation of constancy.
@ -201,7 +201,7 @@ namespace detail
auto level = levels[level_index]; auto level = levels[level_index];
size_t n = level < 1 size_t n = level < 1
? level * elems.size() ? static_cast<size_t>(level * elems.size())
: (elems.size() - 1); : (elems.size() - 1);
::nth_element(array.begin() + prev_n, array.begin() + n, array.end()); ::nth_element(array.begin() + prev_n, array.begin() + n, array.end());

26
src/AggregateFunctions/registerAggregateFunctions.cpp
View File

@ -18,6 +18,19 @@ void registerAggregateFunctionGroupArray(AggregateFunctionFactory &);
void registerAggregateFunctionGroupUniqArray(AggregateFunctionFactory &); void registerAggregateFunctionGroupUniqArray(AggregateFunctionFactory &);
void registerAggregateFunctionGroupArrayInsertAt(AggregateFunctionFactory &); void registerAggregateFunctionGroupArrayInsertAt(AggregateFunctionFactory &);
void registerAggregateFunctionsQuantile(AggregateFunctionFactory &); void registerAggregateFunctionsQuantile(AggregateFunctionFactory &);
void registerAggregateFunctionsQuantileDeterministic(AggregateFunctionFactory &);
void registerAggregateFunctionsQuantileExact(AggregateFunctionFactory &);
void registerAggregateFunctionsQuantileExactWeighted(AggregateFunctionFactory &);
void registerAggregateFunctionsQuantileExactLow(AggregateFunctionFactory &);
void registerAggregateFunctionsQuantileExactHigh(AggregateFunctionFactory &);
void registerAggregateFunctionsQuantileExactInclusive(AggregateFunctionFactory &);
void registerAggregateFunctionsQuantileExactExclusive(AggregateFunctionFactory &);
void registerAggregateFunctionsQuantileTiming(AggregateFunctionFactory &);
void registerAggregateFunctionsQuantileTimingWeighted(AggregateFunctionFactory &);
void registerAggregateFunctionsQuantileTDigest(AggregateFunctionFactory &);
void registerAggregateFunctionsQuantileTDigestWeighted(AggregateFunctionFactory &);
void registerAggregateFunctionsQuantileBFloat16(AggregateFunctionFactory &);
void registerAggregateFunctionsQuantileBFloat16Weighted(AggregateFunctionFactory &);
void registerAggregateFunctionsSequenceMatch(AggregateFunctionFactory &); void registerAggregateFunctionsSequenceMatch(AggregateFunctionFactory &);
void registerAggregateFunctionWindowFunnel(AggregateFunctionFactory &); void registerAggregateFunctionWindowFunnel(AggregateFunctionFactory &);
void registerAggregateFunctionRate(AggregateFunctionFactory &); void registerAggregateFunctionRate(AggregateFunctionFactory &);
@ -89,6 +102,19 @@ void registerAggregateFunctions()
registerAggregateFunctionGroupUniqArray(factory); registerAggregateFunctionGroupUniqArray(factory);
registerAggregateFunctionGroupArrayInsertAt(factory); registerAggregateFunctionGroupArrayInsertAt(factory);
registerAggregateFunctionsQuantile(factory); registerAggregateFunctionsQuantile(factory);
registerAggregateFunctionsQuantileDeterministic(factory);
registerAggregateFunctionsQuantileExact(factory);
registerAggregateFunctionsQuantileExactWeighted(factory);
registerAggregateFunctionsQuantileExactLow(factory);
registerAggregateFunctionsQuantileExactHigh(factory);
registerAggregateFunctionsQuantileExactInclusive(factory);
registerAggregateFunctionsQuantileExactExclusive(factory);
registerAggregateFunctionsQuantileTiming(factory);
registerAggregateFunctionsQuantileTimingWeighted(factory);
registerAggregateFunctionsQuantileTDigest(factory);
registerAggregateFunctionsQuantileTDigestWeighted(factory);
registerAggregateFunctionsQuantileBFloat16(factory);
registerAggregateFunctionsQuantileBFloat16Weighted(factory);
registerAggregateFunctionsSequenceMatch(factory); registerAggregateFunctionsSequenceMatch(factory);
registerAggregateFunctionWindowFunnel(factory); registerAggregateFunctionWindowFunnel(factory);
registerAggregateFunctionRate(factory); registerAggregateFunctionRate(factory);

2
src/Client/QueryFuzzer.cpp
View File

@ -54,7 +54,7 @@ Field QueryFuzzer::getRandomField(int type)
} }
case 1: case 1:
{ {
static constexpr float values[] static constexpr double values[]
= {NAN, INFINITY, -INFINITY, 0., -0., 0.0001, 0.5, 0.9999, = {NAN, INFINITY, -INFINITY, 0., -0., 0.0001, 0.5, 0.9999,
1., 1.0001, 2., 10.0001, 100.0001, 1000.0001, 1e10, 1e20, 1., 1.0001, 2., 10.0001, 100.0001, 1000.0001, 1e10, 1e20,
FLT_MIN, FLT_MIN + FLT_EPSILON, FLT_MAX, FLT_MAX + FLT_EPSILON}; return values[fuzz_rand() % (sizeof(values) / sizeof(*values))]; FLT_MIN, FLT_MIN + FLT_EPSILON, FLT_MAX, FLT_MAX + FLT_EPSILON}; return values[fuzz_rand() % (sizeof(values) / sizeof(*values))];

2
src/Columns/ColumnAggregateFunction.cpp
View File

@ -607,7 +607,7 @@ MutableColumns ColumnAggregateFunction::scatter(IColumn::ColumnIndex num_columns
size_t num_rows = size(); size_t num_rows = size();
{ {
size_t reserve_size = static_cast<double>(num_rows) / num_columns * 1.1; /// 1.1 is just a guess. Better to use n-sigma rule. size_t reserve_size = static_cast<size_t>(static_cast<double>(num_rows) / num_columns * 1.1); /// 1.1 is just a guess. Better to use n-sigma rule.
if (reserve_size > 1) if (reserve_size > 1)
for (auto & column : columns) for (auto & column : columns)

6
src/Columns/ColumnArray.cpp
View File

@ -50,7 +50,7 @@ ColumnArray::ColumnArray(MutableColumnPtr && nested_column, MutableColumnPtr &&
if (!offsets_concrete) if (!offsets_concrete)
throw Exception("offsets_column must be a ColumnUInt64", ErrorCodes::LOGICAL_ERROR); throw Exception("offsets_column must be a ColumnUInt64", ErrorCodes::LOGICAL_ERROR);
if (!offsets_concrete->empty() && data) if (!offsets_concrete->empty() && data && !data->empty())
{ {
Offset last_offset = offsets_concrete->getData().back(); Offset last_offset = offsets_concrete->getData().back();
@ -141,7 +141,7 @@ void ColumnArray::get(size_t n, Field & res) const
size, max_array_size_as_field); size, max_array_size_as_field);
res = Array(); res = Array();
Array & res_arr = DB::get<Array &>(res); Array & res_arr = res.get<Array &>();
res_arr.reserve(size); res_arr.reserve(size);
for (size_t i = 0; i < size; ++i) for (size_t i = 0; i < size; ++i)
@ -296,7 +296,7 @@ void ColumnArray::updateHashFast(SipHash & hash) const
void ColumnArray::insert(const Field & x) void ColumnArray::insert(const Field & x)
{ {
const Array & array = DB::get<const Array &>(x); const Array & array = x.get<const Array &>();
size_t size = array.size(); size_t size = array.size();
for (size_t i = 0; i < size; ++i) for (size_t i = 0; i < size; ++i)
getData().insert(array[i]); getData().insert(array[i]);

2
src/Columns/ColumnDecimal.h
View File

@ -63,7 +63,7 @@ public:
{ {
data.resize_fill(data.size() + length); data.resize_fill(data.size() + length);
} }
void insert(const Field & x) override { data.push_back(DB::get<T>(x)); } void insert(const Field & x) override { data.push_back(x.get<T>()); }
void insertRangeFrom(const IColumn & src, size_t start, size_t length) override; void insertRangeFrom(const IColumn & src, size_t start, size_t length) override;
void popBack(size_t n) override void popBack(size_t n) override

2
src/Columns/ColumnFixedString.cpp
View File

@ -59,7 +59,7 @@ bool ColumnFixedString::isDefaultAt(size_t index) const
void ColumnFixedString::insert(const Field & x) void ColumnFixedString::insert(const Field & x)
{ {
const String & s = DB::get<const String &>(x); const String & s = x.get<const String &>();
if (s.size() > n) if (s.size() > n)
throw Exception("Too large string '" + s + "' for FixedString column", ErrorCodes::TOO_LARGE_STRING_SIZE); throw Exception("Too large string '" + s + "' for FixedString column", ErrorCodes::TOO_LARGE_STRING_SIZE);

6
src/Columns/ColumnLowCardinality.h
View File

@ -68,9 +68,9 @@ public:
UInt64 get64(size_t n) const override { return getDictionary().get64(getIndexes().getUInt(n)); } UInt64 get64(size_t n) const override { return getDictionary().get64(getIndexes().getUInt(n)); }
UInt64 getUInt(size_t n) const override { return getDictionary().getUInt(getIndexes().getUInt(n)); } UInt64 getUInt(size_t n) const override { return getDictionary().getUInt(getIndexes().getUInt(n)); }
Int64 getInt(size_t n) const override { return getDictionary().getInt(getIndexes().getUInt(n)); } Int64 getInt(size_t n) const override { return getDictionary().getInt(getIndexes().getUInt(n)); }
Float64 getFloat64(size_t n) const override { return getDictionary().getInt(getIndexes().getFloat64(n)); } Float64 getFloat64(size_t n) const override { return getDictionary().getFloat64(getIndexes().getUInt(n)); }
Float32 getFloat32(size_t n) const override { return getDictionary().getInt(getIndexes().getFloat32(n)); } Float32 getFloat32(size_t n) const override { return getDictionary().getFloat32(getIndexes().getUInt(n)); }
bool getBool(size_t n) const override { return getDictionary().getInt(getIndexes().getBool(n)); } bool getBool(size_t n) const override { return getDictionary().getBool(getIndexes().getUInt(n)); }
bool isNullAt(size_t n) const override { return getDictionary().isNullAt(getIndexes().getUInt(n)); } bool isNullAt(size_t n) const override { return getDictionary().isNullAt(getIndexes().getUInt(n)); }
ColumnPtr cut(size_t start, size_t length) const override ColumnPtr cut(size_t start, size_t length) const override
{ {

4
src/Columns/ColumnMap.cpp
View File

@ -74,7 +74,7 @@ void ColumnMap::get(size_t n, Field & res) const
size_t size = offsets[n] - offsets[n - 1]; size_t size = offsets[n] - offsets[n - 1];
res = Map(); res = Map();
auto & map = DB::get<Map &>(res); auto & map = res.get<Map &>();
map.reserve(size); map.reserve(size);
for (size_t i = 0; i < size; ++i) for (size_t i = 0; i < size; ++i)
@ -98,7 +98,7 @@ void ColumnMap::insertData(const char *, size_t)
void ColumnMap::insert(const Field & x) void ColumnMap::insert(const Field & x)
{ {
const auto & map = DB::get<const Map &>(x); const auto & map = x.get<const Map &>();
nested->insert(Array(map.begin(), map.end())); nested->insert(Array(map.begin(), map.end()));
} }

2
src/Columns/ColumnString.h
View File

@ -128,7 +128,7 @@ public:
void insert(const Field & x) override void insert(const Field & x) override
{ {
const String & s = DB::get<const String &>(x); const String & s = x.get<const String &>();
const size_t old_size = chars.size(); const size_t old_size = chars.size();
const size_t size_to_append = s.size() + 1; const size_t size_to_append = s.size() + 1;
const size_t new_size = old_size + size_to_append; const size_t new_size = old_size + size_to_append;

4
src/Columns/ColumnTuple.cpp
View File

@ -109,7 +109,7 @@ void ColumnTuple::get(size_t n, Field & res) const
const size_t tuple_size = columns.size(); const size_t tuple_size = columns.size();
res = Tuple(); res = Tuple();
Tuple & res_tuple = DB::get<Tuple &>(res); Tuple & res_tuple = res.get<Tuple &>();
res_tuple.reserve(tuple_size); res_tuple.reserve(tuple_size);
for (size_t i = 0; i < tuple_size; ++i) for (size_t i = 0; i < tuple_size; ++i)
@ -137,7 +137,7 @@ void ColumnTuple::insertData(const char *, size_t)
void ColumnTuple::insert(const Field & x) void ColumnTuple::insert(const Field & x)
{ {
const auto & tuple = DB::get<const Tuple &>(x); const auto & tuple = x.get<const Tuple &>();
const size_t tuple_size = columns.size(); const size_t tuple_size = columns.size();
if (tuple.size() != tuple_size) if (tuple.size() != tuple_size)

4
src/Columns/ColumnVector.cpp
View File

@ -90,7 +90,7 @@ void ColumnVector<T>::updateWeakHash32(WeakHash32 & hash) const
while (begin < end) while (begin < end)
{ {
*hash_data = intHashCRC32(*begin, *hash_data); *hash_data = hashCRC32(*begin, *hash_data);
++begin; ++begin;
++hash_data; ++hash_data;
} }
@ -918,7 +918,7 @@ ColumnPtr ColumnVector<T>::createWithOffsets(const IColumn::Offsets & offsets, c
auto res = this->create(); auto res = this->create();
auto & res_data = res->getData(); auto & res_data = res->getData();
T default_value = safeGet<T>(default_field); T default_value = default_field.safeGet<T>();
res_data.resize_fill(total_rows, default_value); res_data.resize_fill(total_rows, default_value);
for (size_t i = 0; i < offsets.size(); ++i) for (size_t i = 0; i < offsets.size(); ++i)
res_data[offsets[i]] = data[i + shift]; res_data[offsets[i]] = data[i + shift];

2
src/Columns/ColumnVector.h
View File

@ -301,7 +301,7 @@ public:
void insert(const Field & x) override void insert(const Field & x) override
{ {
data.push_back(DB::get<T>(x)); data.push_back(x.get<T>());
} }
void insertRangeFrom(const IColumn & src, size_t start, size_t length) override; void insertRangeFrom(const IColumn & src, size_t start, size_t length) override;

2
src/Columns/IColumnImpl.h
View File

@ -54,7 +54,7 @@ std::vector<IColumn::MutablePtr> IColumn::scatterImpl(ColumnIndex num_columns,
column = cloneEmpty(); column = cloneEmpty();
{ {
size_t reserve_size = num_rows * 1.1 / num_columns; /// 1.1 is just a guess. Better to use n-sigma rule. size_t reserve_size = static_cast<size_t>(num_rows * 1.1 / num_columns); /// 1.1 is just a guess. Better to use n-sigma rule.
if (reserve_size > 1) if (reserve_size > 1)
for (auto & column : columns) for (auto & column : columns)

3
src/Columns/MaskOperations.cpp
View File

@ -119,7 +119,7 @@ size_t extractMaskNumericImpl(
(*nulls)[i] = 1; (*nulls)[i] = 1;
} }
else else
value = !!data[index]; value = static_cast<bool>(data[index]);
if constexpr (inverted) if constexpr (inverted)
value = !value; value = !value;
@ -335,4 +335,3 @@ void copyMask(const PaddedPODArray<UInt8> & from, PaddedPODArray<UInt8> & to)
} }
} }

2
src/Common/BitHelpers.h
View File

@ -31,7 +31,7 @@ inline size_t roundUpToPowerOfTwoOrZero(size_t n)
template <typename T> template <typename T>
inline size_t getLeadingZeroBitsUnsafe(T x) inline uint32_t getLeadingZeroBitsUnsafe(T x)
{ {
assert(x != 0); assert(x != 0);

46
src/Common/DateLUTImpl.h
View File

@ -577,7 +577,7 @@ public:
/// also make the special timezones with no whole hour offset such as 'Australia/Lord_Howe' been taken into account. /// also make the special timezones with no whole hour offset such as 'Australia/Lord_Howe' been taken into account.
LUTIndex index = findIndex(t); LUTIndex index = findIndex(t);
UInt32 time = t - lut[index].date; UInt32 time = static_cast<UInt32>(t - lut[index].date);
if (time >= lut[index].time_at_offset_change()) if (time >= lut[index].time_at_offset_change())
time += lut[index].amount_of_offset_change(); time += lut[index].amount_of_offset_change();
@ -618,33 +618,33 @@ public:
} }
template <typename DateOrTime> template <typename DateOrTime>
inline unsigned toMonth(DateOrTime v) const { return lut[toLUTIndex(v)].month; } inline UInt8 toMonth(DateOrTime v) const { return lut[toLUTIndex(v)].month; }
template <typename DateOrTime> template <typename DateOrTime>
inline unsigned toQuarter(DateOrTime v) const { return (lut[toLUTIndex(v)].month - 1) / 3 + 1; } inline UInt8 toQuarter(DateOrTime v) const { return (lut[toLUTIndex(v)].month - 1) / 3 + 1; }
template <typename DateOrTime> template <typename DateOrTime>
inline Int16 toYear(DateOrTime v) const { return lut[toLUTIndex(v)].year; } inline Int16 toYear(DateOrTime v) const { return lut[toLUTIndex(v)].year; }
template <typename DateOrTime> template <typename DateOrTime>
inline unsigned toDayOfWeek(DateOrTime v) const { return lut[toLUTIndex(v)].day_of_week; } inline UInt8 toDayOfWeek(DateOrTime v) const { return lut[toLUTIndex(v)].day_of_week; }
template <typename DateOrTime> template <typename DateOrTime>
inline unsigned toDayOfMonth(DateOrTime v) const { return lut[toLUTIndex(v)].day_of_month; } inline UInt8 toDayOfMonth(DateOrTime v) const { return lut[toLUTIndex(v)].day_of_month; }
template <typename DateOrTime> template <typename DateOrTime>
inline unsigned toDayOfYear(DateOrTime v) const inline UInt16 toDayOfYear(DateOrTime v) const
{ {
// TODO: different overload for ExtendedDayNum // TODO: different overload for ExtendedDayNum
const LUTIndex i = toLUTIndex(v); const LUTIndex i = toLUTIndex(v);
return i + 1 - toFirstDayNumOfYearIndex(i); return static_cast<UInt16>(i + 1 - toFirstDayNumOfYearIndex(i));
} }
/// Number of week from some fixed moment in the past. Week begins at monday. /// Number of week from some fixed moment in the past. Week begins at monday.
/// (round down to monday and divide DayNum by 7; we made an assumption, /// (round down to monday and divide DayNum by 7; we made an assumption,
/// that in domain of the function there was no weeks with any other number of days than 7) /// that in domain of the function there was no weeks with any other number of days than 7)
template <typename DateOrTime> template <typename DateOrTime>
inline unsigned toRelativeWeekNum(DateOrTime v) const inline Int32 toRelativeWeekNum(DateOrTime v) const
{ {
const LUTIndex i = toLUTIndex(v); const LUTIndex i = toLUTIndex(v);
/// We add 8 to avoid underflow at beginning of unix epoch. /// We add 8 to avoid underflow at beginning of unix epoch.
@ -653,7 +653,7 @@ public:
/// Get year that contains most of the current week. Week begins at monday. /// Get year that contains most of the current week. Week begins at monday.
template <typename DateOrTime> template <typename DateOrTime>
inline unsigned toISOYear(DateOrTime v) const inline Int16 toISOYear(DateOrTime v) const
{ {
const LUTIndex i = toLUTIndex(v); const LUTIndex i = toLUTIndex(v);
/// That's effectively the year of thursday of current week. /// That's effectively the year of thursday of current week.
@ -694,7 +694,7 @@ public:
/// ISO 8601 week number. Week begins at monday. /// ISO 8601 week number. Week begins at monday.
/// The week number 1 is the first week in year that contains 4 or more days (that's more than half). /// The week number 1 is the first week in year that contains 4 or more days (that's more than half).
template <typename DateOrTime> template <typename DateOrTime>
inline unsigned toISOWeek(DateOrTime v) const inline UInt8 toISOWeek(DateOrTime v) const
{ {
return 1 + (toFirstDayNumOfWeek(v) - toDayNum(toFirstDayNumOfISOYearIndex(v))) / 7; return 1 + (toFirstDayNumOfWeek(v) - toDayNum(toFirstDayNumOfISOYearIndex(v))) / 7;
} }
@ -751,38 +751,40 @@ public:
YearWeek yw(toYear(i), 0); YearWeek yw(toYear(i), 0);
UInt16 days = 0; UInt16 days = 0;
const auto daynr = makeDayNum(yw.first, toMonth(i), toDayOfMonth(i)); const auto day_number = makeDayNum(yw.first, toMonth(i), toDayOfMonth(i));
auto first_daynr = makeDayNum(yw.first, 1, 1); auto first_day_number = makeDayNum(yw.first, 1, 1);
// 0 for monday, 1 for tuesday ... // 0 for monday, 1 for tuesday ...
// get weekday from first day in year. // get weekday from first day in year.
UInt16 weekday = calc_weekday(first_daynr, !monday_first_mode); UInt8 weekday = calc_weekday(first_day_number, !monday_first_mode);
if (toMonth(i) == 1 && toDayOfMonth(i) <= static_cast<UInt32>(7 - weekday)) if (toMonth(i) == 1 && toDayOfMonth(i) <= static_cast<UInt32>(7 - weekday))
{ {
if (!week_year_mode && ((first_weekday_mode && weekday != 0) || (!first_weekday_mode && weekday >= 4))) if (!week_year_mode && ((first_weekday_mode && weekday != 0) || (!first_weekday_mode && weekday >= 4)))
return yw; return yw;
week_year_mode = true; week_year_mode = true;
(yw.first)--; --yw.first;
first_daynr -= (days = calc_days_in_year(yw.first)); days = calc_days_in_year(yw.first);
first_day_number -= days;
weekday = (weekday + 53 * 7 - days) % 7; weekday = (weekday + 53 * 7 - days) % 7;
} }
if ((first_weekday_mode && weekday != 0) || (!first_weekday_mode && weekday >= 4)) if ((first_weekday_mode && weekday != 0) || (!first_weekday_mode && weekday >= 4))
days = daynr - (first_daynr + (7 - weekday)); days = day_number - (first_day_number + (7 - weekday));
else else
days = daynr - (first_daynr - weekday); days = day_number - (first_day_number - weekday);
if (week_year_mode && days >= 52 * 7) if (week_year_mode && days >= 52 * 7)
{ {
weekday = (weekday + calc_days_in_year(yw.first)) % 7; weekday = (weekday + calc_days_in_year(yw.first)) % 7;
if ((!first_weekday_mode && weekday < 4) || (first_weekday_mode && weekday == 0)) if ((!first_weekday_mode && weekday < 4) || (first_weekday_mode && weekday == 0))
{ {
(yw.first)++; ++yw.first;
yw.second = 1; yw.second = 1;
return yw; return yw;
} }
} }
yw.second = days / 7 + 1; yw.second = days / 7 + 1;
return yw; return yw;
} }
@ -853,7 +855,7 @@ public:
* Returns 0 for monday, 1 for tuesday... * Returns 0 for monday, 1 for tuesday...
*/ */
template <typename DateOrTime> template <typename DateOrTime>
inline unsigned calc_weekday(DateOrTime v, bool sunday_first_day_of_week) const /// NOLINT inline UInt8 calc_weekday(DateOrTime v, bool sunday_first_day_of_week) const /// NOLINT
{ {
const LUTIndex i = toLUTIndex(v); const LUTIndex i = toLUTIndex(v);
if (!sunday_first_day_of_week) if (!sunday_first_day_of_week)
@ -863,21 +865,21 @@ public:
} }
/// Calculate days in one year. /// Calculate days in one year.
inline unsigned calc_days_in_year(Int32 year) const /// NOLINT inline UInt16 calc_days_in_year(Int32 year) const /// NOLINT
{ {
return ((year & 3) == 0 && (year % 100 || (year % 400 == 0 && year)) ? 366 : 365); return ((year & 3) == 0 && (year % 100 || (year % 400 == 0 && year)) ? 366 : 365);
} }
/// Number of month from some fixed moment in the past (year * 12 + month) /// Number of month from some fixed moment in the past (year * 12 + month)
template <typename DateOrTime> template <typename DateOrTime>
inline unsigned toRelativeMonthNum(DateOrTime v) const inline Int32 toRelativeMonthNum(DateOrTime v) const
{ {
const LUTIndex i = toLUTIndex(v); const LUTIndex i = toLUTIndex(v);
return lut[i].year * 12 + lut[i].month; return lut[i].year * 12 + lut[i].month;
} }
template <typename DateOrTime> template <typename DateOrTime>
inline unsigned toRelativeQuarterNum(DateOrTime v) const inline Int32 toRelativeQuarterNum(DateOrTime v) const
{ {
const LUTIndex i = toLUTIndex(v); const LUTIndex i = toLUTIndex(v);
return lut[i].year * 4 + (lut[i].month - 1) / 3; return lut[i].year * 4 + (lut[i].month - 1) / 3;

2
src/Common/ErrorCodes.cpp
View File

@ -674,7 +674,7 @@ namespace ErrorCodes
ErrorCode getErrorCodeByName(std::string_view error_name) ErrorCode getErrorCodeByName(std::string_view error_name)
{ {
for (size_t i = 0, end = ErrorCodes::end(); i < end; ++i) for (int i = 0, end = ErrorCodes::end(); i < end; ++i)
{ {
std::string_view name = ErrorCodes::getName(i); std::string_view name = ErrorCodes::getName(i);

2
src/Common/Exception.h
View File

@ -127,7 +127,7 @@ public:
#endif #endif
; ;
int getLineNumber() const { return line_number; } ssize_t getLineNumber() const { return line_number; }
void setLineNumber(int line_number_) { line_number = line_number_;} void setLineNumber(int line_number_) { line_number = line_number_;}
String getFileName() const { return file_name; } String getFileName() const { return file_name; }

3
src/Common/FieldVisitorSum.cpp
View File

@ -19,7 +19,7 @@ bool FieldVisitorSum::operator() (UInt64 & x) const
return x != 0; return x != 0;
} }
bool FieldVisitorSum::operator() (Float64 & x) const { x += get<Float64>(rhs); return x != 0; } bool FieldVisitorSum::operator() (Float64 & x) const { x += rhs.get<Float64>(); return x != 0; }
bool FieldVisitorSum::operator() (Null &) const { throw Exception("Cannot sum Nulls", ErrorCodes::LOGICAL_ERROR); } bool FieldVisitorSum::operator() (Null &) const { throw Exception("Cannot sum Nulls", ErrorCodes::LOGICAL_ERROR); }
bool FieldVisitorSum::operator() (String &) const { throw Exception("Cannot sum Strings", ErrorCodes::LOGICAL_ERROR); } bool FieldVisitorSum::operator() (String &) const { throw Exception("Cannot sum Strings", ErrorCodes::LOGICAL_ERROR); }
@ -37,4 +37,3 @@ bool FieldVisitorSum::operator() (AggregateFunctionStateData &) const
bool FieldVisitorSum::operator() (bool &) const { throw Exception("Cannot sum Bools", ErrorCodes::LOGICAL_ERROR); } bool FieldVisitorSum::operator() (bool &) const { throw Exception("Cannot sum Bools", ErrorCodes::LOGICAL_ERROR); }
} }

3
src/Common/FieldVisitorSum.h
View File

@ -33,7 +33,7 @@ public:
template <typename T> template <typename T>
bool operator() (DecimalField<T> & x) const bool operator() (DecimalField<T> & x) const
{ {
x += get<DecimalField<T>>(rhs); x += rhs.get<DecimalField<T>>();
return x.getValue() != T(0); return x.getValue() != T(0);
} }
@ -47,4 +47,3 @@ public:
}; };
} }

4
src/Common/GetPriorityForLoadBalancing.cpp
View File

@ -16,7 +16,7 @@ std::function<size_t(size_t index)> GetPriorityForLoadBalancing::getPriorityFunc
case LoadBalancing::NEAREST_HOSTNAME: case LoadBalancing::NEAREST_HOSTNAME:
if (hostname_differences.empty()) if (hostname_differences.empty())
throw Exception(ErrorCodes::LOGICAL_ERROR, "It's a bug: hostname_differences is not initialized"); throw Exception(ErrorCodes::LOGICAL_ERROR, "It's a bug: hostname_differences is not initialized");
get_priority = [&](size_t i) { return hostname_differences[i]; }; get_priority = [this](size_t i) { return hostname_differences[i]; };
break; break;
case LoadBalancing::IN_ORDER: case LoadBalancing::IN_ORDER:
get_priority = [](size_t i) { return i; }; get_priority = [](size_t i) { return i; };
@ -36,7 +36,7 @@ std::function<size_t(size_t index)> GetPriorityForLoadBalancing::getPriorityFunc
* last_used = 3 -> get_priority: 4 3 0 1 2 * last_used = 3 -> get_priority: 4 3 0 1 2
* ... * ...
* */ * */
get_priority = [&](size_t i) get_priority = [this, pool_size](size_t i)
{ {
++i; ++i;
return i < last_used ? pool_size - i : i - last_used; return i < last_used ? pool_size - i : i - last_used;

8
src/Common/HashTable/Hash.h
View File

@ -220,7 +220,7 @@ template <typename T> struct HashCRC32;
template <typename T> template <typename T>
requires (sizeof(T) <= sizeof(UInt64)) requires (sizeof(T) <= sizeof(UInt64))
inline size_t hashCRC32(T key) inline size_t hashCRC32(T key, DB::UInt64 updated_value = -1)
{ {
union union
{ {
@ -229,14 +229,14 @@ inline size_t hashCRC32(T key)
} u; } u;
u.out = 0; u.out = 0;
u.in = key; u.in = key;
return intHashCRC32(u.out); return intHashCRC32(u.out, updated_value);
} }
template <typename T> template <typename T>
requires (sizeof(T) > sizeof(UInt64)) requires (sizeof(T) > sizeof(UInt64))
inline size_t hashCRC32(T key) inline size_t hashCRC32(T key, DB::UInt64 updated_value = -1)
{ {
return intHashCRC32(key, -1); return intHashCRC32(key, updated_value);
} }
#define DEFINE_HASH(T) \ #define DEFINE_HASH(T) \

6
src/Common/MemoryTracker.cpp
View File

@ -178,7 +178,7 @@ void MemoryTracker::allocImpl(Int64 size, bool throw_if_memory_exceeded, MemoryT
} }
std::bernoulli_distribution sample(sample_probability); std::bernoulli_distribution sample(sample_probability);
if (unlikely(sample_probability && sample(thread_local_rng))) if (unlikely(sample_probability > 0.0 && sample(thread_local_rng)))
{ {
MemoryTrackerBlockerInThread untrack_lock(VariableContext::Global); MemoryTrackerBlockerInThread untrack_lock(VariableContext::Global);
DB::TraceCollector::collect(DB::TraceType::MemorySample, StackTrace(), size); DB::TraceCollector::collect(DB::TraceType::MemorySample, StackTrace(), size);
@ -186,7 +186,7 @@ void MemoryTracker::allocImpl(Int64 size, bool throw_if_memory_exceeded, MemoryT
} }
std::bernoulli_distribution fault(fault_probability); std::bernoulli_distribution fault(fault_probability);
if (unlikely(fault_probability && fault(thread_local_rng))) if (unlikely(fault_probability > 0.0 && fault(thread_local_rng)))
{ {
if (memoryTrackerCanThrow(level, true) && throw_if_memory_exceeded) if (memoryTrackerCanThrow(level, true) && throw_if_memory_exceeded)
{ {
@ -318,7 +318,7 @@ void MemoryTracker::free(Int64 size)
} }
std::bernoulli_distribution sample(sample_probability); std::bernoulli_distribution sample(sample_probability);
if (unlikely(sample_probability && sample(thread_local_rng))) if (unlikely(sample_probability > 0.0 && sample(thread_local_rng)))
{ {
MemoryTrackerBlockerInThread untrack_lock(VariableContext::Global); MemoryTrackerBlockerInThread untrack_lock(VariableContext::Global);
DB::TraceCollector::collect(DB::TraceType::MemorySample, StackTrace(), -size); DB::TraceCollector::collect(DB::TraceType::MemorySample, StackTrace(), -size);

2
src/Common/SLRUCachePolicy.h
View File

@ -35,7 +35,7 @@ public:
*/ */
/// TODO: construct from special struct with cache policy parameters (also with max_protected_size). /// TODO: construct from special struct with cache policy parameters (also with max_protected_size).
SLRUCachePolicy(size_t max_size_, size_t max_elements_size_ = 0, double size_ratio = 0.5, OnWeightLossFunction on_weight_loss_function_ = {}) SLRUCachePolicy(size_t max_size_, size_t max_elements_size_ = 0, double size_ratio = 0.5, OnWeightLossFunction on_weight_loss_function_ = {})
: max_protected_size(max_size_ * std::min(1.0, size_ratio)) : max_protected_size(static_cast<size_t>(max_size_ * std::min(1.0, size_ratio)))
, max_size(max_size_) , max_size(max_size_)
, max_elements_size(max_elements_size_) , max_elements_size(max_elements_size_)
{ {

2
src/Common/SipHash.h
View File

@ -55,7 +55,7 @@ private:
ALWAYS_INLINE void finalize() ALWAYS_INLINE void finalize()
{ {
/// In the last free byte, we write the remainder of the division by 256. /// In the last free byte, we write the remainder of the division by 256.
current_bytes[7] = cnt; current_bytes[7] = static_cast<UInt8>(cnt);
v3 ^= current_word; v3 ^= current_word;
SIPROUND; SIPROUND;

2
src/Common/StudentTTest.h
View File

@ -31,7 +31,7 @@ private:
double avg() const double avg() const
{ {
return sum / size; return sum / static_cast<double>(size);
} }
double var() const double var() const

18
src/Common/ThreadFuzzer.cpp
View File

@ -157,22 +157,22 @@ bool ThreadFuzzer::isEffective() const
#if THREAD_FUZZER_WRAP_PTHREAD #if THREAD_FUZZER_WRAP_PTHREAD
# define CHECK_WRAPPER_PARAMS(RET, NAME, ...) \ # define CHECK_WRAPPER_PARAMS(RET, NAME, ...) \
if (NAME##_before_yield_probability.load(std::memory_order_relaxed)) \ if (NAME##_before_yield_probability.load(std::memory_order_relaxed) > 0.0) \
return true; \ return true; \
if (NAME##_before_migrate_probability.load(std::memory_order_relaxed)) \ if (NAME##_before_migrate_probability.load(std::memory_order_relaxed) > 0.0) \
return true; \ return true; \
if (NAME##_before_sleep_probability.load(std::memory_order_relaxed)) \ if (NAME##_before_sleep_probability.load(std::memory_order_relaxed) > 0.0) \
return true; \ return true; \
if (NAME##_before_sleep_time_us.load(std::memory_order_relaxed)) \ if (NAME##_before_sleep_time_us.load(std::memory_order_relaxed) > 0.0) \
return true; \ return true; \
\ \
if (NAME##_after_yield_probability.load(std::memory_order_relaxed)) \ if (NAME##_after_yield_probability.load(std::memory_order_relaxed) > 0.0) \
return true; \ return true; \
if (NAME##_after_migrate_probability.load(std::memory_order_relaxed)) \ if (NAME##_after_migrate_probability.load(std::memory_order_relaxed) > 0.0) \
return true; \ return true; \
if (NAME##_after_sleep_probability.load(std::memory_order_relaxed)) \ if (NAME##_after_sleep_probability.load(std::memory_order_relaxed) > 0.0) \
return true; \ return true; \
if (NAME##_after_sleep_time_us.load(std::memory_order_relaxed)) \ if (NAME##_after_sleep_time_us.load(std::memory_order_relaxed) > 0.0) \
return true; return true;
FOR_EACH_WRAPPED_FUNCTION(CHECK_WRAPPER_PARAMS) FOR_EACH_WRAPPED_FUNCTION(CHECK_WRAPPER_PARAMS)
@ -239,7 +239,7 @@ static void injection(
&& sleep_time_us > 0 && sleep_time_us > 0
&& std::bernoulli_distribution(sleep_probability)(thread_local_rng)) && std::bernoulli_distribution(sleep_probability)(thread_local_rng))
{ {
sleepForNanoseconds(sleep_time_us * 1000); sleepForNanoseconds(static_cast<uint64_t>(sleep_time_us * 1000));
} }
} }

4
src/Common/ThreadProfileEvents.cpp
View File

@ -558,8 +558,8 @@ void PerfEventsCounters::finalizeProfileEvents(ProfileEvents::Counters & profile
// deltas from old values. // deltas from old values.
const auto enabled = current_value.time_enabled - previous_value.time_enabled; const auto enabled = current_value.time_enabled - previous_value.time_enabled;
const auto running = current_value.time_running - previous_value.time_running; const auto running = current_value.time_running - previous_value.time_running;
const UInt64 delta = (current_value.value - previous_value.value) const UInt64 delta = static_cast<UInt64>(
* enabled / std::max(1.f, float(running)); (current_value.value - previous_value.value) * enabled / std::max(1.f, float(running)));
if (min_enabled_time > enabled) if (min_enabled_time > enabled)
{ {

2
src/Common/Throttler.cpp
View File

@ -66,7 +66,7 @@ void Throttler::add(size_t amount)
if (max_speed && current_speed > max_speed) if (max_speed && current_speed > max_speed)
{ {
/// If we was too fast then we have to sleep until our smoothed speed became <= max_speed /// If we was too fast then we have to sleep until our smoothed speed became <= max_speed
int64_t sleep_time = -window_ns * std::log2(max_speed / current_speed); int64_t sleep_time = static_cast<int64_t>(-window_ns * std::log2(max_speed / current_speed));
if (sleep_time > 0) if (sleep_time > 0)
{ {

7
src/Common/UnicodeBar.cpp
View File

@ -28,12 +28,12 @@ namespace UnicodeBar
size_t getWidthInBytes(double width) size_t getWidthInBytes(double width)
{ {
return ceil(width - 1.0 / 8) * UNICODE_BAR_CHAR_SIZE; return static_cast<size_t>(ceil(width - 1.0 / 8) * UNICODE_BAR_CHAR_SIZE);
} }
void render(double width, char * dst) void render(double width, char * dst)
{ {
size_t floor_width = floor(width); size_t floor_width = static_cast<size_t>(floor(width));
for (size_t i = 0; i < floor_width; ++i) for (size_t i = 0; i < floor_width; ++i)
{ {
@ -41,7 +41,7 @@ namespace UnicodeBar
dst += UNICODE_BAR_CHAR_SIZE; dst += UNICODE_BAR_CHAR_SIZE;
} }
size_t remainder = floor((width - floor_width) * 8); size_t remainder = static_cast<size_t>(floor((width - floor_width) * 8));
if (remainder) if (remainder)
{ {
@ -59,4 +59,3 @@ namespace UnicodeBar
return res; return res;
} }
} }

14
src/Common/VersionNumber.cpp
View File

@ -40,23 +40,17 @@ int VersionNumber::compare(const VersionNumber & rhs) const
size_t min = std::min(components.size(), rhs.components.size()); size_t min = std::min(components.size(), rhs.components.size());
for (size_t i = 0; i < min; ++i) for (size_t i = 0; i < min; ++i)
{ {
if (int d = components[i] - rhs.components[i]) if (auto d = components[i] - rhs.components[i])
return d; return d > 0 ? 1 : -1;
} }
if (components.size() > min) if (components.size() > min)
{ {
if (components[min] != 0) return components[min] >= 0 ? 1 : -1;
return components[min];
else
return 1;
} }
else if (rhs.components.size() > min) else if (rhs.components.size() > min)
{ {
if (rhs.components[min] != 0) return -rhs.components[min] > 0 ? 1 : -1;
return -rhs.components[min];
else
return -1;
} }
return 0; return 0;

2
src/Common/ZooKeeper/ZooKeeper.h
View File

@ -319,7 +319,7 @@ public:
void setZooKeeperLog(std::shared_ptr<DB::ZooKeeperLog> zk_log_); void setZooKeeperLog(std::shared_ptr<DB::ZooKeeperLog> zk_log_);
UInt32 getSessionUptime() const { return session_uptime.elapsedSeconds(); } UInt32 getSessionUptime() const { return static_cast<UInt32>(session_uptime.elapsedSeconds()); }
private: private:
friend class EphemeralNodeHolder; friend class EphemeralNodeHolder;

4
src/Common/ZooKeeper/ZooKeeperArgs.h
View File

@ -28,8 +28,8 @@ struct ZooKeeperArgs
int32_t connection_timeout_ms = Coordination::DEFAULT_CONNECTION_TIMEOUT_MS; int32_t connection_timeout_ms = Coordination::DEFAULT_CONNECTION_TIMEOUT_MS;
int32_t session_timeout_ms = Coordination::DEFAULT_SESSION_TIMEOUT_MS; int32_t session_timeout_ms = Coordination::DEFAULT_SESSION_TIMEOUT_MS;
int32_t operation_timeout_ms = Coordination::DEFAULT_OPERATION_TIMEOUT_MS; int32_t operation_timeout_ms = Coordination::DEFAULT_OPERATION_TIMEOUT_MS;
float send_fault_probability = 0; double send_fault_probability = 0.0;
float recv_fault_probability = 0; double recv_fault_probability = 0.0;
DB::GetPriorityForLoadBalancing get_priority_load_balancing; DB::GetPriorityForLoadBalancing get_priority_load_balancing;
}; };

133
src/Common/base58.cpp Normal file
View File

@ -0,0 +1,133 @@
#include <Common/base58.h>
namespace DB
{
size_t encodeBase58(const UInt8 * src, size_t src_length, UInt8 * dst)
{
const char * base58_encoding_alphabet = "123456789ABCDEFGHJKLMNPQRSTUVWXYZabcdefghijkmnopqrstuvwxyz";
size_t processed = 0;
size_t idx = 0;
size_t zeros = 0;
while (processed < src_length && *src == 0)
{
++processed;
++zeros;
*dst = '1';
++dst;
++src;
}
while (processed < src_length)
{
UInt32 carry = *src;
for (size_t j = 0; j < idx; ++j)
{
carry += static_cast<UInt32>(dst[j]) << 8;
dst[j] = static_cast<UInt8>(carry % 58);
carry /= 58;
}
while (carry > 0)
{
dst[idx] = static_cast<UInt8>(carry % 58);
++idx;
carry /= 58;
}
++src;
++processed;
}
size_t c_idx = idx >> 1;
for (size_t i = 0; i < c_idx; ++i)
{
char s = base58_encoding_alphabet[static_cast<UInt8>(dst[i])];
dst[i] = base58_encoding_alphabet[static_cast<UInt8>(dst[idx - (i + 1)])];
dst[idx - (i + 1)] = s;
}
if ((idx & 1))
{
dst[c_idx] = base58_encoding_alphabet[static_cast<UInt8>(dst[c_idx])];
}
return zeros + idx;
}
std::optional<size_t> decodeBase58(const UInt8 * src, size_t src_length, UInt8 * dst)
{
static const Int8 map_digits[256] =
{
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
-1, 0, 1, 2, 3, 4, 5, 6, 7, 8, -1, -1, -1, -1, -1, -1,
-1, 9, 10, 11, 12, 13, 14, 15, 16, -1, 17, 18, 19, 20, 21, -1,
22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, -1, -1, -1, -1, -1,
-1, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, -1, 44, 45, 46,
47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
};
size_t processed = 0;
size_t idx = 0;
size_t zeros = 0;
while (processed < src_length && *src == '1')
{
++processed;
++zeros;
*dst = '\0';
++dst;
++src;
}
while (processed < src_length)
{
Int8 digit = map_digits[*src];
UInt32 carry = digit == -1 ? 0xFFFFFFFFU : static_cast<UInt32>(digit);
if (carry == static_cast<UInt32>(-1))
{
return {};
}
for (size_t j = 0; j < idx; ++j)
{
carry += static_cast<UInt8>(dst[j]) * 58;
dst[j] = static_cast<UInt8>(carry & 0xFF);
carry >>= 8;
}
while (carry > 0)
{
dst[idx] = static_cast<UInt8>(carry & 0xFF);
++idx;
carry >>= 8;
}
++src;
++processed;
}
size_t c_idx = idx >> 1;
for (size_t i = 0; i < c_idx; ++i)
{
UInt8 s = dst[i];
dst[i] = dst[idx - (i + 1)];
dst[idx - (i + 1)] = s;
}
return zeros + idx;
}
}

115
src/Common/base58.h
View File

@ -1,116 +1,13 @@
#pragma once #pragma once
#include <climits>
#include <cstring> #include <Core/Types.h>
#include <optional>
namespace DB namespace DB
{ {
inline size_t encodeBase58(const char8_t * src, size_t srclen, char8_t * dst) size_t encodeBase58(const UInt8 * src, size_t src_length, UInt8 * dst);
{ std::optional<size_t> decodeBase58(const UInt8 * src, size_t src_length, UInt8 * dst);
const char * base58_encoding_alphabet = "123456789ABCDEFGHJKLMNPQRSTUVWXYZabcdefghijkmnopqrstuvwxyz";
size_t processed = 0;
size_t zeros = 0;
for (;*src == '\0' && processed < srclen-1; ++src)
{
++processed;
++zeros;
*dst++ = '1';
}
size_t idx = 0;
while (processed < srclen-1)
{
unsigned int carry = static_cast<unsigned char>(*src);
for (size_t j = 0; j < idx; ++j)
{
carry += static_cast<unsigned int>(dst[j] << 8);
dst[j] = static_cast<unsigned char>(carry % 58);
carry /= 58;
}
while (carry > 0)
{
dst[idx++] = static_cast<unsigned char>(carry % 58);
carry /= 58;
}
++src;
++processed;
}
size_t c_idx = idx >> 1;
for (size_t i = 0; i < c_idx; ++i)
{
char s = base58_encoding_alphabet[static_cast<unsigned char>(dst[i])];
dst[i] = base58_encoding_alphabet[static_cast<unsigned char>(dst[idx - (i + 1)])];
dst[idx - (i + 1)] = s;
}
if ((idx & 1))
{
dst[c_idx] = base58_encoding_alphabet[static_cast<unsigned char>(dst[c_idx])];
}
dst[idx] = '\0';
return zeros + idx + 1;
}
inline size_t decodeBase58(const char8_t * src, size_t srclen, char8_t * dst)
{
const signed char uint_max = UINT_MAX;
const signed char map_digits[128]
= {uint_max, uint_max, uint_max, uint_max, uint_max, uint_max, uint_max, uint_max, uint_max, uint_max, uint_max, uint_max, uint_max,
uint_max, uint_max, uint_max, uint_max, uint_max, uint_max, uint_max, uint_max, uint_max, uint_max, uint_max, uint_max, uint_max,
uint_max, uint_max, uint_max, uint_max, uint_max, uint_max, uint_max, uint_max, uint_max, uint_max, uint_max, uint_max, uint_max,
uint_max, uint_max, uint_max, uint_max, uint_max, uint_max, uint_max, uint_max, uint_max, uint_max, 0, 1, 2,
3, 4, 5, 6, 7, 8, uint_max, uint_max, uint_max, uint_max, uint_max, uint_max, uint_max,
9, 10, 11, 12, 13, 14, 15, 16, uint_max, 17, 18, 19, 20,
21, uint_max, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32,
uint_max, uint_max, uint_max, uint_max, uint_max, uint_max, 33, 34, 35, 36, 37, 38, 39,
40, 41, 42, 43, uint_max, 44, 45, 46, 47, 48, 49, 50, 51,
52, 53, 54, 55, 56, 57, uint_max, uint_max, uint_max, uint_max, uint_max};
size_t processed = 0;
size_t zeros = 0;
for (;*src == '1' && processed < srclen-1; ++src)
{
++processed;
++zeros;
*dst++ = '\0';
}
size_t idx = 0;
while (processed < srclen-1)
{
unsigned int carry = map_digits[*src];
if (unlikely(carry == UINT_MAX))
{
return 0;
}
for (size_t j = 0; j < idx; ++j)
{
carry += static_cast<unsigned char>(dst[j]) * 58;
dst[j] = static_cast<unsigned char>(carry & 0xff);
carry >>= 8;
}
while (carry > 0)
{
dst[idx++] = static_cast<unsigned char>(carry & 0xff);
carry >>= 8;
}
++src;
++processed;
}
size_t c_idx = idx >> 1;
for (size_t i = 0; i < c_idx; ++i)
{
char s = dst[i];
dst[i] = dst[idx - (i + 1)];
dst[idx - (i + 1)] = s;
}
dst[idx] = '\0';
return zeros + idx + 1;
}
} }

2
src/Common/checkStackSize.cpp
View File

@ -101,7 +101,7 @@ __attribute__((__weak__)) void checkStackSize()
throw Exception("Logical error: frame address is greater than stack begin address", ErrorCodes::LOGICAL_ERROR); throw Exception("Logical error: frame address is greater than stack begin address", ErrorCodes::LOGICAL_ERROR);
size_t stack_size = int_stack_address + max_stack_size - int_frame_address; size_t stack_size = int_stack_address + max_stack_size - int_frame_address;
size_t max_stack_size_allowed = max_stack_size * STACK_SIZE_FREE_RATIO; size_t max_stack_size_allowed = static_cast<size_t>(max_stack_size * STACK_SIZE_FREE_RATIO);
/// Just check if we have eat more than a STACK_SIZE_FREE_RATIO of stack size already. /// Just check if we have eat more than a STACK_SIZE_FREE_RATIO of stack size already.
if (stack_size > max_stack_size_allowed) if (stack_size > max_stack_size_allowed)

8
src/Common/getNumberOfPhysicalCPUCores.cpp
View File

@ -9,7 +9,7 @@
#include <thread> #include <thread>
#if defined(OS_LINUX) #if defined(OS_LINUX)
static int readFrom(const char * filename, int default_value) static int32_t readFrom(const char * filename, int default_value)
{ {
std::ifstream infile(filename); std::ifstream infile(filename);
if (!infile.is_open()) if (!infile.is_open())
@ -22,15 +22,15 @@ static int readFrom(const char * filename, int default_value)
} }
/// Try to look at cgroups limit if it is available. /// Try to look at cgroups limit if it is available.
static unsigned getCGroupLimitedCPUCores(unsigned default_cpu_count) static uint32_t getCGroupLimitedCPUCores(unsigned default_cpu_count)
{ {
unsigned quota_count = default_cpu_count; uint32_t quota_count = default_cpu_count;
/// Return the number of milliseconds per period process is guaranteed to run. /// Return the number of milliseconds per period process is guaranteed to run.
/// -1 for no quota /// -1 for no quota
int cgroup_quota = readFrom("/sys/fs/cgroup/cpu/cpu.cfs_quota_us", -1); int cgroup_quota = readFrom("/sys/fs/cgroup/cpu/cpu.cfs_quota_us", -1);
int cgroup_period = readFrom("/sys/fs/cgroup/cpu/cpu.cfs_period_us", -1); int cgroup_period = readFrom("/sys/fs/cgroup/cpu/cpu.cfs_period_us", -1);
if (cgroup_quota > -1 && cgroup_period > 0) if (cgroup_quota > -1 && cgroup_period > 0)
quota_count = ceil(static_cast<float>(cgroup_quota) / static_cast<float>(cgroup_period)); quota_count = static_cast<uint32_t>(ceil(static_cast<float>(cgroup_quota) / static_cast<float>(cgroup_period)));
return std::min(default_cpu_count, quota_count); return std::min(default_cpu_count, quota_count);
} }

1
src/Common/mysqlxx/mysqlxx/Value.h
View File

@ -248,7 +248,6 @@ template <> inline long Value::get<long >() cons
template <> inline unsigned long Value::get<unsigned long >() const { return getUInt(); } /// NOLINT template <> inline unsigned long Value::get<unsigned long >() const { return getUInt(); } /// NOLINT
template <> inline long long Value::get<long long >() const { return getInt(); } /// NOLINT template <> inline long long Value::get<long long >() const { return getInt(); } /// NOLINT
template <> inline unsigned long long Value::get<unsigned long long >() const { return getUInt(); } /// NOLINT template <> inline unsigned long long Value::get<unsigned long long >() const { return getUInt(); } /// NOLINT
template <> inline float Value::get<float >() const { return getDouble(); }
template <> inline double Value::get<double >() const { return getDouble(); } template <> inline double Value::get<double >() const { return getDouble(); }
template <> inline std::string Value::get<std::string >() const { return getString(); } template <> inline std::string Value::get<std::string >() const { return getString(); }
template <> inline LocalDate Value::get<LocalDate >() const { return getDate(); } template <> inline LocalDate Value::get<LocalDate >() const { return getDate(); }

3
src/Common/tests/gtest_getMultipleValuesFromConfig.cpp
View File

@ -10,8 +10,7 @@ using namespace DB;
TEST(Common, getMultipleValuesFromConfig) TEST(Common, getMultipleValuesFromConfig)
{ {
std::istringstream // STYLE_CHECK_ALLOW_STD_STRING_STREAM std::istringstream // STYLE_CHECK_ALLOW_STD_STRING_STREAM
xml_isteam(R"END(<?xml version="1.0"?> xml_isteam(R"END(<clickhouse>
<clickhouse>
<first_level> <first_level>
<second_level>0</second_level> <second_level>0</second_level>
<second_level>1</second_level> <second_level>1</second_level>

172
src/Common/tests/gtest_sensitive_data_masker.cpp
View File

@ -60,24 +60,6 @@ TEST(Common, SensitiveDataMasker)
"SELECT id FROM mysql('localhost:3308', 'database', 'table', 'root', '******') WHERE " "SELECT id FROM mysql('localhost:3308', 'database', 'table', 'root', '******') WHERE "
"ssn='000-00-0000' or email='hidden@hidden.test'"); "ssn='000-00-0000' or email='hidden@hidden.test'");
#ifndef NDEBUG
// simple benchmark
auto start = std::chrono::high_resolution_clock::now();
static constexpr size_t iterations = 200000;
for (int i = 0; i < iterations; ++i)
{
std::string query2 = "SELECT id FROM mysql('localhost:3308', 'database', 'table', 'root', 'qwerty123') WHERE ssn='123-45-6789' or "
"email='JonhSmith@secret.domain.test'";
masker2.wipeSensitiveData(query2);
}
auto finish = std::chrono::high_resolution_clock::now();
std::chrono::duration<double> elapsed = finish - start;
std::cout << "Elapsed time: " << elapsed.count() << "s per " << iterations <<" calls (" << elapsed.count() * 1000000 / iterations << "µs per call)"
<< std::endl;
// I have: "Elapsed time: 3.44022s per 200000 calls (17.2011µs per call)"
masker2.printStats();
#endif
DB::SensitiveDataMasker maskerbad(*empty_xml_config , ""); DB::SensitiveDataMasker maskerbad(*empty_xml_config , "");
// gtest has not good way to check exception content, so just do it manually (see https://github.com/google/googletest/issues/952 ) // gtest has not good way to check exception content, so just do it manually (see https://github.com/google/googletest/issues/952 )
@ -101,9 +83,83 @@ TEST(Common, SensitiveDataMasker)
EXPECT_EQ(maskerbad.rulesCount(), 0); EXPECT_EQ(maskerbad.rulesCount(), 0);
EXPECT_EQ(maskerbad.wipeSensitiveData(x), 0); EXPECT_EQ(maskerbad.wipeSensitiveData(x), 0);
try
{ {
std::istringstream // STYLE_CHECK_ALLOW_STD_STRING_STREAM std::istringstream // STYLE_CHECK_ALLOW_STD_STRING_STREAM
xml_isteam(R"END(<?xml version="1.0"?> xml_isteam(R"END(<clickhouse>
<query_masking_rules>
<rule>
<name>test</name>
<regexp>abc</regexp>
</rule>
<rule>
<name>test</name>
<regexp>abc</regexp>
</rule>
</query_masking_rules>
</clickhouse>)END");
Poco::AutoPtr<Poco::Util::XMLConfiguration> xml_config = new Poco::Util::XMLConfiguration(xml_isteam);
DB::SensitiveDataMasker masker_xml_based_exception_check(*xml_config, "query_masking_rules");
ADD_FAILURE() << "XML should throw an error on bad XML" << std::endl;
}
catch (const DB::Exception & e)
{
EXPECT_EQ(
std::string(e.what()),
"query_masking_rules configuration contains more than one rule named 'test'.");
EXPECT_EQ(e.code(), DB::ErrorCodes::INVALID_CONFIG_PARAMETER);
}
try
{
std::istringstream // STYLE_CHECK_ALLOW_STD_STRING_STREAM
xml_isteam(R"END(<clickhouse>
<query_masking_rules>
<rule><name>test</name></rule>
</query_masking_rules>
</clickhouse>)END");
Poco::AutoPtr<Poco::Util::XMLConfiguration> xml_config = new Poco::Util::XMLConfiguration(xml_isteam);
DB::SensitiveDataMasker masker_xml_based_exception_check(*xml_config, "query_masking_rules");
ADD_FAILURE() << "XML should throw an error on bad XML" << std::endl;
}
catch (const DB::Exception & e)
{
EXPECT_EQ(
std::string(e.what()),
"query_masking_rules configuration, rule 'test' has no <regexp> node or <regexp> is empty.");
EXPECT_EQ(e.code(), DB::ErrorCodes::NO_ELEMENTS_IN_CONFIG);
}
try
{
std::istringstream // STYLE_CHECK_ALLOW_STD_STRING_STREAM
xml_isteam(R"END(<clickhouse>
<query_masking_rules>
<rule><name>test</name><regexp>())(</regexp></rule>
</query_masking_rules>
</clickhouse>)END");
Poco::AutoPtr<Poco::Util::XMLConfiguration> xml_config = new Poco::Util::XMLConfiguration(xml_isteam);
DB::SensitiveDataMasker masker_xml_based_exception_check(*xml_config, "query_masking_rules");
ADD_FAILURE() << "XML should throw an error on bad XML" << std::endl;
}
catch (const DB::Exception & e)
{
EXPECT_EQ(
std::string(e.message()),
"SensitiveDataMasker: cannot compile re2: ())(, error: unexpected ): ())(. Look at https://github.com/google/re2/wiki/Syntax for reference.: while adding query masking rule 'test'."
);
EXPECT_EQ(e.code(), DB::ErrorCodes::CANNOT_COMPILE_REGEXP);
}
{
std::istringstream // STYLE_CHECK_ALLOW_STD_STRING_STREAM
xml_isteam(R"END(
<clickhouse> <clickhouse>
<query_masking_rules> <query_masking_rules>
<rule> <rule>
@ -150,82 +206,4 @@ TEST(Common, SensitiveDataMasker)
masker_xml_based.printStats(); masker_xml_based.printStats();
#endif #endif
} }
try
{
std::istringstream // STYLE_CHECK_ALLOW_STD_STRING_STREAM
xml_isteam_bad(R"END(<?xml version="1.0"?>
<clickhouse>
<query_masking_rules>
<rule>
<name>test</name>
<regexp>abc</regexp>
</rule>
<rule>
<name>test</name>
<regexp>abc</regexp>
</rule>
</query_masking_rules>
</clickhouse>)END");
Poco::AutoPtr<Poco::Util::XMLConfiguration> xml_config = new Poco::Util::XMLConfiguration(xml_isteam_bad);
DB::SensitiveDataMasker masker_xml_based_exception_check(*xml_config, "query_masking_rules");
ADD_FAILURE() << "XML should throw an error on bad XML" << std::endl;
}
catch (const DB::Exception & e)
{
EXPECT_EQ(
std::string(e.what()),
"query_masking_rules configuration contains more than one rule named 'test'.");
EXPECT_EQ(e.code(), DB::ErrorCodes::INVALID_CONFIG_PARAMETER);
}
try
{
std::istringstream // STYLE_CHECK_ALLOW_STD_STRING_STREAM
xml_isteam_bad(R"END(<?xml version="1.0"?>
<clickhouse>
<query_masking_rules>
<rule><name>test</name></rule>
</query_masking_rules>
</clickhouse>)END");
Poco::AutoPtr<Poco::Util::XMLConfiguration> xml_config = new Poco::Util::XMLConfiguration(xml_isteam_bad);
DB::SensitiveDataMasker masker_xml_based_exception_check(*xml_config, "query_masking_rules");
ADD_FAILURE() << "XML should throw an error on bad XML" << std::endl;
}
catch (const DB::Exception & e)
{
EXPECT_EQ(
std::string(e.what()),
"query_masking_rules configuration, rule 'test' has no <regexp> node or <regexp> is empty.");
EXPECT_EQ(e.code(), DB::ErrorCodes::NO_ELEMENTS_IN_CONFIG);
}
try
{
std::istringstream // STYLE_CHECK_ALLOW_STD_STRING_STREAM
xml_isteam_bad(R"END(<?xml version="1.0"?>
<clickhouse>
<query_masking_rules>
<rule><name>test</name><regexp>())(</regexp></rule>
</query_masking_rules>
</clickhouse>)END");
Poco::AutoPtr<Poco::Util::XMLConfiguration> xml_config = new Poco::Util::XMLConfiguration(xml_isteam_bad);
DB::SensitiveDataMasker masker_xml_based_exception_check(*xml_config, "query_masking_rules");
ADD_FAILURE() << "XML should throw an error on bad XML" << std::endl;
}
catch (const DB::Exception & e)
{
EXPECT_EQ(
std::string(e.message()),
"SensitiveDataMasker: cannot compile re2: ())(, error: unexpected ): ())(. Look at https://github.com/google/re2/wiki/Syntax for reference.: while adding query masking rule 'test'."
);
EXPECT_EQ(e.code(), DB::ErrorCodes::CANNOT_COMPILE_REGEXP);
}
} }

4
src/Compression/CompressionFactoryAdditions.cpp
View File

@ -116,8 +116,8 @@ ASTPtr CompressionCodecFactory::validateCodecAndGetPreprocessedAST(
} }
}; };
ISerialization::SubstreamPath path; auto serialization = column_type->getDefaultSerialization();
column_type->getDefaultSerialization()->enumerateStreams(path, callback, column_type); serialization->enumerateStreams(callback, column_type);
if (!result_codec) if (!result_codec)
throw Exception(ErrorCodes::LOGICAL_ERROR, "Cannot find any substream with data type for type {}. It's a bug", column_type->getName()); throw Exception(ErrorCodes::LOGICAL_ERROR, "Cannot find any substream with data type for type {}. It's a bug", column_type->getName());

25
src/Core/Field.h
View File

@ -882,30 +882,6 @@ inline char & Field::reinterpret<char>()
return *reinterpret_cast<char *>(&storage); return *reinterpret_cast<char *>(&storage);
} }
template <typename T>
T get(const Field & field)
{
return field.template get<T>();
}
template <typename T>
T get(Field & field)
{
return field.template get<T>();
}
template <typename T>
T safeGet(const Field & field)
{
return field.template safeGet<T>();
}
template <typename T>
T safeGet(Field & field)
{
return field.template safeGet<T>();
}
template <typename T> template <typename T>
Field::Field(T && rhs, enable_if_not_field_or_bool_or_stringlike_t<T>) //-V730 Field::Field(T && rhs, enable_if_not_field_or_bool_or_stringlike_t<T>) //-V730
{ {
@ -1036,4 +1012,3 @@ struct fmt::formatter<DB::Field>
return format_to(ctx.out(), "{}", toString(x)); return format_to(ctx.out(), "{}", toString(x));
} }
}; };

Some files were not shown because too many files have changed in this diff Show More