[Chore](hash) use google/crc32c to instead rocksdb/crc32c and crc_hash

be/cmake/thirdparty.cmake

@@ -68,6 +68,7 @@ add_thirdparty(curl)
 add_thirdparty(lz4)
 add_thirdparty(thrift)
 add_thirdparty(thriftnb)
+add_thirdparty(crc32c)
 
 add_thirdparty(libevent_core LIBNAME "lib/libevent_core.a")
 add_thirdparty(libevent_openssl LIBNAME "lib/libevent_openssl.a")

be/src/exprs/block_bloom_filter.hpp

@@ -76,7 +76,7 @@ class BlockBloomFilter {
     // Same as above with convenience of hashing the key.
     void insert(const StringRef& key) noexcept {
         if (key.data) {
-            insert(HashUtil::crc_hash(key.data, uint32_t(key.size), _hash_seed));
+            insert(HashUtil::crc32c_hash(key.data, uint32_t(key.size), _hash_seed));
         }
     }
 
@@ -105,7 +105,7 @@ class BlockBloomFilter {
     // Same as above with convenience of hashing the key.
     bool find(const StringRef& key) const noexcept {
         if (key.data) {
-            return find(HashUtil::crc_hash(key.data, uint32_t(key.size), _hash_seed));
+            return find(HashUtil::crc32c_hash(key.data, uint32_t(key.size), _hash_seed));
         }
         return false;
     }

be/src/util/crc32c.h

@@ -15,39 +15,22 @@
 // specific language governing permissions and limitations
 // under the License.
 
-// the following code are modified from RocksDB:
-// https://github.com/facebook/rocksdb/blob/master/util/crc32c.h
-
 #pragma once
 
-#include <stddef.h>
-#include <stdint.h>
-
 #include <vector>
 
 #include "util/slice.h"
 
 namespace doris {
 namespace crc32c {
 
-// Return the crc32c of concat(A, data[0,n-1]) where init_crc is the
-// crc32c of some string A.  Extend() is often used to maintain the
-// crc32c of a stream of data.
-extern uint32_t Extend(uint32_t init_crc, const char* data, size_t n);
+uint32_t Extend(uint32_t crc, const char* data, size_t n);
 
 // Return the crc32c of data[0,n-1]
-inline uint32_t Value(const char* data, size_t n) {
-    return Extend(0, data, n);
-}
+uint32_t Value(const char* data, size_t n);
 
 // Return the crc32c of data content in all slices
-inline uint32_t Value(const std::vector<Slice>& slices) {
-    uint32_t crc = 0;
-    for (auto& slice : slices) {
-        crc = Extend(crc, slice.get_data(), slice.get_size());
-    }
-    return crc;
-}
+uint32_t Value(const std::vector<Slice>& slices);
 
 } // namespace crc32c
 } // namespace doris

be/src/util/hash_util.hpp

@@ -30,6 +30,7 @@
 
 #include "common/compiler_util.h" // IWYU pragma: keep
 #include "util/cpu_info.h"
+#include "util/crc32c.h"
 #include "util/hash/city.h"
 #include "util/murmur_hash3.h"
 #include "util/sse_util.hpp"
@@ -49,7 +50,12 @@ class HashUtil {
         return (uint32_t)crc32(hash, (const unsigned char*)(&INT_VALUE), 4);
     }
 
-#if defined(__SSE4_2__) || defined(__aarch64__)
+    // ATTN: crc32c's result is different with zlib_crc32 coz of different polynomial
+    // crc32c have better performance than zlib_crc32/crc_hash
+    static uint32_t crc32c_hash(const void* data, uint32_t bytes, uint32_t hash) {
+        return crc32c::Extend(hash, static_cast<const char*>(data), bytes);
+    }
+
     // Compute the Crc32 hash for data using SSE4 instructions.  The input hash parameter is
     // the current hash/seed value.
     // This should only be called if SSE is supported.
@@ -59,6 +65,8 @@ class HashUtil {
     // NOTE: Any changes made to this function need to be reflected in Codegen::GetHashFn.
     // TODO: crc32 hashes with different seeds do not result in different hash functions.
     // The resulting hashes are correlated.
+    // ATTN: prefer do not use this function anymore, use crc32c_hash instead
+    // This function is retained because it is not certain whether there are compatibility issues with historical data.
     static uint32_t crc_hash(const void* data, uint32_t bytes, uint32_t hash) {
         if (!CpuInfo::is_supported(CpuInfo::SSE4_2)) {
             return zlib_crc_hash(data, bytes, hash);
@@ -117,11 +125,6 @@ class HashUtil {
 
         return converter.u64;
     }
-#else
-    static uint32_t crc_hash(const void* data, uint32_t bytes, uint32_t hash) {
-        return zlib_crc_hash(data, bytes, hash);
-    }
-#endif
 
     // refer to https://github.com/apache/commons-codec/blob/master/src/main/java/org/apache/commons/codec/digest/MurmurHash3.java
     static const uint32_t MURMUR3_32_SEED = 104729;

be/src/vec/columns/column_dictionary.h

@@ -345,7 +345,7 @@ class ColumnDictI32 final : public COWHelper<IColumn, ColumnDictI32> {
                 if (type == FieldType::OLAP_FIELD_TYPE_CHAR) {
                     len = strnlen(sv.data, sv.size);
                 }
-                uint32_t hash_val = HashUtil::crc_hash(sv.data, static_cast<uint32_t>(len), 0);
+                uint32_t hash_val = HashUtil::crc32c_hash(sv.data, static_cast<uint32_t>(len), 0);
                 _hash_values[code] = hash_val;
                 _compute_hash_value_flags[code] = 1;
                 return _hash_values[code];

be/src/vec/functions/function_string.h

@@ -4598,7 +4598,7 @@ class FunctionNgramSearch : public IFunction {
 
     uint32_t sub_str_hash(const char* data, int32_t length) const {
         constexpr static uint32_t seed = 0;
-        return HashUtil::crc_hash(data, length, seed);
+        return HashUtil::crc32c_hash(data, length, seed);
     }
 
     template <bool column_const>