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

Backport #62853 to 24.3: Fix GCD codec

Browse Source
This commit is contained in:
robot-clickhouse 2024-04-26 18:04:55 +00:00
parent e1f0cd1f92
commit 83c68ee08e
3 changed files with 23 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
src/Compression/CompressionCodecGCD.cpp
View File

@ -24,6 +24,7 @@ public:
void updateHash(SipHash & hash) const override;
protected:
/// 1 byte (`gcd_bytes_size` value) + 1 byte (`bytes_to_skip` value) + `bytes_to_skip` bytes (trash) + `gcd_bytes_size` bytes (gcd value) + (`source_size` - `bytes_to_skip`) bytes (data)
UInt32 doCompressData(const char * source, UInt32 source_size, char * dest) const override;
void doDecompressData(const char * source, UInt32 source_size, char * dest, UInt32 uncompressed_size) const override;
UInt32 getMaxCompressedDataSize(UInt32 uncompressed_size) const override;
@ -54,7 +55,7 @@ UInt32 CompressionCodecGCD::getMaxCompressedDataSize(UInt32 uncompressed_size) c
{
return uncompressed_size
+ gcd_bytes_size // To store gcd
+ 2; // Local header
+ 2; // Values of `gcd_bytes_size` and `bytes_to_skip`
}
uint8_t CompressionCodecGCD::getMethodByte() const
@ -147,7 +148,7 @@ void decompressDataForType(const char * source, UInt32 source_size, char * dest,
if (source_size - sizeof(T) != output_size)
throw Exception(ErrorCodes::CANNOT_DECOMPRESS, "Cannot decompress GCD-encoded data");
memcpy(dest, source, source_size);
memcpy(dest, source, source_size - sizeof(T));
return;
}
@ -160,6 +161,7 @@ void decompressDataForType(const char * source, UInt32 source_size, char * dest,
source += sizeof(T);
dest += sizeof(T);
}
chassert(source == source_end);
}
}
@ -209,6 +211,8 @@ void CompressionCodecGCD::doDecompressData(const char * source, UInt32 source_si
throw Exception(ErrorCodes::CANNOT_DECOMPRESS, "Cannot decompress GCD-encoded data. File has wrong header");
UInt8 bytes_to_skip = uncompressed_size % bytes_size;
chassert(bytes_to_skip == static_cast<UInt8>(source[1]));
UInt32 output_size = uncompressed_size - bytes_to_skip;
if (static_cast<UInt32>(2 + bytes_to_skip) > source_size)

0
tests/queries/0_stateless/03093_bug_gcd_codec.reference Normal file
View File

17
tests/queries/0_stateless/03093_bug_gcd_codec.sql Normal file
View File

@ -0,0 +1,17 @@
-- Tags: long
CREATE TABLE test_gcd(test_col UInt32 CODEC(GCD, LZ4))
ENGINE = MergeTree
ORDER BY tuple()
SETTINGS index_granularity = 8192, index_granularity_bytes = 1024;
INSERT INTO test_gcd SELECT floor(randUniform(1, 3)) FROM numbers(150000);
OPTIMIZE TABLE test_gcd FINAL;
CREATE TABLE test_gcd2(test_col UInt32 CODEC(GCD, LZ4))
ENGINE = MergeTree
ORDER BY tuple()
SETTINGS index_granularity = 8192, index_granularity_bytes = 1024, min_bytes_for_wide_part = 0, max_compress_block_size = 1024, min_compress_block_size = 1024;
INSERT INTO test_gcd2 SELECT floor(randUniform(1, 3)) FROM numbers(150000);
OPTIMIZE TABLE test_gcd2 FINAL;