mirror of
https://github.com/ClickHouse/ClickHouse.git
synced 2024-11-24 08:32:02 +00:00
Support crc32 function
This commit is contained in:
Ivan Remen
parent
153093fa48
commit
edff6e58dc
102
dbms/src/Functions/FunctionCRC32.cpp
Normal file
102
dbms/src/Functions/FunctionCRC32.cpp
Normal file
@ -0,0 +1,102 @@
|
||||
#include <DataTypes/DataTypeString.h>
|
||||
#include <Functions/FunctionFactory.h>
|
||||
#include <Functions/FunctionStringOrArrayToT.h>
|
||||
|
||||
|
||||
namespace DB
|
||||
{
|
||||
namespace ErrorCodes
|
||||
{
|
||||
extern const int ILLEGAL_TYPE_OF_ARGUMENT;
|
||||
}
|
||||
|
||||
/** Calculates the crc32 of a string
|
||||
*/
|
||||
struct CRC32Impl
|
||||
{
|
||||
static constexpr auto is_fixed_to_constant = true;
|
||||
|
||||
static void vector(const ColumnString::Chars & data, const ColumnString::Offsets & offsets, PaddedPODArray<UInt32> & res)
|
||||
{
|
||||
size_t size = offsets.size();
|
||||
|
||||
ColumnString::Offset prev_offset = 0;
|
||||
for (size_t i = 0; i < size; ++i)
|
||||
{
|
||||
res[i] = crc32(data, prev_offset, offsets[i] - prev_offset - 1);
|
||||
prev_offset = offsets[i];
|
||||
}
|
||||
}
|
||||
|
||||
static void vector_fixed_to_constant(const ColumnString::Chars & data, size_t n, UInt32 & res) { res = crc32(data, 0, n); }
|
||||
|
||||
static void vector_fixed_to_vector(const ColumnString::Chars & data, size_t n, PaddedPODArray<UInt32> & res)
|
||||
{
|
||||
size_t size = data.size() / n;
|
||||
|
||||
for (size_t i = 0; i < size; ++i)
|
||||
{
|
||||
res[i] = crc32(data, i * n, n);
|
||||
}
|
||||
}
|
||||
|
||||
static void array(const ColumnString::Offsets & /*offsets*/, PaddedPODArray<UInt32> & /*res*/)
|
||||
{
|
||||
throw Exception("Cannot apply function crc32 to Array argument", ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT);
|
||||
}
|
||||
|
||||
private:
|
||||
static uint32_t crc32(const ColumnString::Chars & buf, size_t offset, size_t size)
|
||||
{
|
||||
static const unsigned int crc32table[256] = {
|
||||
0x00000000, 0x77073096, 0xee0e612c, 0x990951ba, 0x076dc419, 0x706af48f, 0xe963a535, 0x9e6495a3, 0x0edb8832, 0x79dcb8a4,
|
||||
0xe0d5e91e, 0x97d2d988, 0x09b64c2b, 0x7eb17cbd, 0xe7b82d07, 0x90bf1d91, 0x1db71064, 0x6ab020f2, 0xf3b97148, 0x84be41de,
|
||||
0x1adad47d, 0x6ddde4eb, 0xf4d4b551, 0x83d385c7, 0x136c9856, 0x646ba8c0, 0xfd62f97a, 0x8a65c9ec, 0x14015c4f, 0x63066cd9,
|
||||
0xfa0f3d63, 0x8d080df5, 0x3b6e20c8, 0x4c69105e, 0xd56041e4, 0xa2677172, 0x3c03e4d1, 0x4b04d447, 0xd20d85fd, 0xa50ab56b,
|
||||
0x35b5a8fa, 0x42b2986c, 0xdbbbc9d6, 0xacbcf940, 0x32d86ce3, 0x45df5c75, 0xdcd60dcf, 0xabd13d59, 0x26d930ac, 0x51de003a,
|
||||
0xc8d75180, 0xbfd06116, 0x21b4f4b5, 0x56b3c423, 0xcfba9599, 0xb8bda50f, 0x2802b89e, 0x5f058808, 0xc60cd9b2, 0xb10be924,
|
||||
0x2f6f7c87, 0x58684c11, 0xc1611dab, 0xb6662d3d, 0x76dc4190, 0x01db7106, 0x98d220bc, 0xefd5102a, 0x71b18589, 0x06b6b51f,
|
||||
0x9fbfe4a5, 0xe8b8d433, 0x7807c9a2, 0x0f00f934, 0x9609a88e, 0xe10e9818, 0x7f6a0dbb, 0x086d3d2d, 0x91646c97, 0xe6635c01,
|
||||
0x6b6b51f4, 0x1c6c6162, 0x856530d8, 0xf262004e, 0x6c0695ed, 0x1b01a57b, 0x8208f4c1, 0xf50fc457, 0x65b0d9c6, 0x12b7e950,
|
||||
0x8bbeb8ea, 0xfcb9887c, 0x62dd1ddf, 0x15da2d49, 0x8cd37cf3, 0xfbd44c65, 0x4db26158, 0x3ab551ce, 0xa3bc0074, 0xd4bb30e2,
|
||||
0x4adfa541, 0x3dd895d7, 0xa4d1c46d, 0xd3d6f4fb, 0x4369e96a, 0x346ed9fc, 0xad678846, 0xda60b8d0, 0x44042d73, 0x33031de5,
|
||||
0xaa0a4c5f, 0xdd0d7cc9, 0x5005713c, 0x270241aa, 0xbe0b1010, 0xc90c2086, 0x5768b525, 0x206f85b3, 0xb966d409, 0xce61e49f,
|
||||
0x5edef90e, 0x29d9c998, 0xb0d09822, 0xc7d7a8b4, 0x59b33d17, 0x2eb40d81, 0xb7bd5c3b, 0xc0ba6cad, 0xedb88320, 0x9abfb3b6,
|
||||
0x03b6e20c, 0x74b1d29a, 0xead54739, 0x9dd277af, 0x04db2615, 0x73dc1683, 0xe3630b12, 0x94643b84, 0x0d6d6a3e, 0x7a6a5aa8,
|
||||
0xe40ecf0b, 0x9309ff9d, 0x0a00ae27, 0x7d079eb1, 0xf00f9344, 0x8708a3d2, 0x1e01f268, 0x6906c2fe, 0xf762575d, 0x806567cb,
|
||||
0x196c3671, 0x6e6b06e7, 0xfed41b76, 0x89d32be0, 0x10da7a5a, 0x67dd4acc, 0xf9b9df6f, 0x8ebeeff9, 0x17b7be43, 0x60b08ed5,
|
||||
0xd6d6a3e8, 0xa1d1937e, 0x38d8c2c4, 0x4fdff252, 0xd1bb67f1, 0xa6bc5767, 0x3fb506dd, 0x48b2364b, 0xd80d2bda, 0xaf0a1b4c,
|
||||
0x36034af6, 0x41047a60, 0xdf60efc3, 0xa867df55, 0x316e8eef, 0x4669be79, 0xcb61b38c, 0xbc66831a, 0x256fd2a0, 0x5268e236,
|
||||
0xcc0c7795, 0xbb0b4703, 0x220216b9, 0x5505262f, 0xc5ba3bbe, 0xb2bd0b28, 0x2bb45a92, 0x5cb36a04, 0xc2d7ffa7, 0xb5d0cf31,
|
||||
0x2cd99e8b, 0x5bdeae1d, 0x9b64c2b0, 0xec63f226, 0x756aa39c, 0x026d930a, 0x9c0906a9, 0xeb0e363f, 0x72076785, 0x05005713,
|
||||
0x95bf4a82, 0xe2b87a14, 0x7bb12bae, 0x0cb61b38, 0x92d28e9b, 0xe5d5be0d, 0x7cdcefb7, 0x0bdbdf21, 0x86d3d2d4, 0xf1d4e242,
|
||||
0x68ddb3f8, 0x1fda836e, 0x81be16cd, 0xf6b9265b, 0x6fb077e1, 0x18b74777, 0x88085ae6, 0xff0f6a70, 0x66063bca, 0x11010b5c,
|
||||
0x8f659eff, 0xf862ae69, 0x616bffd3, 0x166ccf45, 0xa00ae278, 0xd70dd2ee, 0x4e048354, 0x3903b3c2, 0xa7672661, 0xd06016f7,
|
||||
0x4969474d, 0x3e6e77db, 0xaed16a4a, 0xd9d65adc, 0x40df0b66, 0x37d83bf0, 0xa9bcae53, 0xdebb9ec5, 0x47b2cf7f, 0x30b5ffe9,
|
||||
0xbdbdf21c, 0xcabac28a, 0x53b39330, 0x24b4a3a6, 0xbad03605, 0xcdd70693, 0x54de5729, 0x23d967bf, 0xb3667a2e, 0xc4614ab8,
|
||||
0x5d681b02, 0x2a6f2b94, 0xb40bbe37, 0xc30c8ea1, 0x5a05df1b, 0x2d02ef8d,
|
||||
};
|
||||
|
||||
const char * p = reinterpret_cast<const char *>(&buf[0]) + offset;
|
||||
uint32_t crc = ~0U;
|
||||
|
||||
while (size--)
|
||||
{
|
||||
crc = crc32table[(crc ^ *p++) & 0xFF] ^ (crc >> 8);
|
||||
}
|
||||
return crc ^ ~0U;
|
||||
}
|
||||
};
|
||||
|
||||
struct NameCRC32
|
||||
{
|
||||
static constexpr auto name = "crc32";
|
||||
};
|
||||
using FunctionCRC32 = FunctionStringOrArrayToT<CRC32Impl, NameCRC32, UInt32>;
|
||||
|
||||
void registerFunctionCRC32(FunctionFactory & factory)
|
||||
{
|
||||
factory.registerFunction<FunctionCRC32>();
|
||||
}
|
||||
|
||||
}
|
||||
@ -2,7 +2,6 @@
|
||||
|
||||
namespace DB
|
||||
{
|
||||
|
||||
class FunctionFactory;
|
||||
|
||||
void registerFunctionEmpty(FunctionFactory &);
|
||||
@ -20,6 +19,8 @@ void registerFunctionReverseUTF8(FunctionFactory &);
|
||||
void registerFunctionsConcat(FunctionFactory &);
|
||||
void registerFunctionFormat(FunctionFactory &);
|
||||
void registerFunctionSubstring(FunctionFactory &);
|
||||
void registerFunctionSubstringUTF8(FunctionFactory &);
|
||||
void registerFunctionCRC32(FunctionFactory &);
|
||||
void registerFunctionAppendTrailingCharIfAbsent(FunctionFactory &);
|
||||
void registerFunctionStartsWith(FunctionFactory &);
|
||||
void registerFunctionEndsWith(FunctionFactory &);
|
||||
@ -45,6 +46,7 @@ void registerFunctionsString(FunctionFactory & factory)
|
||||
registerFunctionLowerUTF8(factory);
|
||||
registerFunctionUpperUTF8(factory);
|
||||
registerFunctionReverse(factory);
|
||||
registerFunctionCRC32(factory);
|
||||
registerFunctionReverseUTF8(factory);
|
||||
registerFunctionsConcat(factory);
|
||||
registerFunctionFormat(factory);
|
||||
@ -62,4 +64,3 @@ void registerFunctionsString(FunctionFactory & factory)
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
|
||||
File diff suppressed because one or more lines are too long
@ -0,0 +1,22 @@
|
||||
2663297705
|
||||
2663297705 3632233996
|
||||
0
|
||||
55151997
|
||||
3142898280
|
||||
3358319860
|
||||
3369829874
|
||||
0
|
||||
0
|
||||
2663297705
|
||||
4027020077
|
||||
4069886758
|
||||
0 0
|
||||
55151997 2663297705
|
||||
3142898280 4027020077
|
||||
3358319860 0
|
||||
3369829874 4069886758
|
||||
0 0
|
||||
qwerty string 55151997 2663297705
|
||||
qqq aaa 3142898280 4027020077
|
||||
zxcqwer 3358319860 0
|
||||
aasq xxz 3369829874 4069886758
|
||||
20
dbms/tests/queries/0_stateless/00936_crc32_function.sql
Normal file
20
dbms/tests/queries/0_stateless/00936_crc32_function.sql
Normal file
@ -0,0 +1,20 @@
|
||||
USE test;
|
||||
|
||||
DROP TABLE IF EXISTS table1;
|
||||
|
||||
CREATE TABLE table1 (str1 String, str2 String) ENGINE = Memory;
|
||||
|
||||
INSERT INTO table1 VALUES('qwerty', 'string');
|
||||
INSERT INTO table1 VALUES('qqq', 'aaa');
|
||||
INSERT INTO table1 VALUES('aasq', 'xxz');
|
||||
INSERT INTO table1 VALUES('zxcqwer', '');
|
||||
INSERT INTO table1 VALUES('', '');
|
||||
|
||||
select crc32('string');
|
||||
select crc32('string'), crc32('test');
|
||||
select crc32(str1) from table1 order by crc32(str1);
|
||||
select crc32(str2) from table1 order by crc32(str2);
|
||||
select crc32(str1), crc32(str2) from table1 order by crc32(str1), crc32(str2);
|
||||
select str1, str2, crc32(str1), crc32(str2) from table1 order by crc32(str1), crc32(str2);
|
||||
|
||||
DROP TABLE table1;
|
||||
@ -165,4 +165,9 @@ Returns a string that removes the whitespace characters on right side.
|
||||
|
||||
Returns a string that removes the whitespace characters on either side.
|
||||
|
||||
## crc32(s)
|
||||
|
||||
Returns the crc32 hashsum of a string
|
||||
The result type is UInt32.
|
||||
|
||||
[Original article](https://clickhouse.yandex/docs/en/query_language/functions/string_functions/) <!--hide-->
|
||||
|
||||
@ -117,4 +117,8 @@ SELECT format('{} {}', 'Hello', 'World')
|
||||
## tryBase64Decode(s)
|
||||
Функционал аналогичен base64Decode, но при невозможности декодирования возвращает пустую строку.
|
||||
|
||||
## crc32(s)
|
||||
Возвращает хэш-сумму crc32 данной строки.
|
||||
Тип результата - UInt32.
|
||||
|
||||
[Оригинальная статья](https://clickhouse.yandex/docs/ru/query_language/functions/string_functions/) <!--hide-->
|
||||
|
||||
Loading…
Reference in New Issue
Block a user