ceph/src/arrow/cpp/src/gandiva/hash_utils_test.cc

   1 // Licensed to the Apache Software Foundation (ASF) under one
   2 // or more contributor license agreements.  See the NOTICE file
   3 // distributed with this work for additional information
   4 // regarding copyright ownership.  The ASF licenses this file
   5 // to you under the Apache License, Version 2.0 (the
   6 // "License"); you may not use this file except in compliance
   7 // with the License.  You may obtain a copy of the License at
   8 //
   9 //   http://www.apache.org/licenses/LICENSE-2.0
  10 //
  11 // Unless required by applicable law or agreed to in writing,
  12 // software distributed under the License is distributed on an
  13 // "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
  14 // KIND, either express or implied.  See the License for the
  15 // specific language governing permissions and limitations
  16 // under the License.
  17
  18 #include <gtest/gtest.h>
  19 #include <unordered_set>
  20
  21 #include "gandiva/execution_context.h"
  22 #include "gandiva/hash_utils.h"
  23
  24 TEST(TestShaHashUtils, TestSha1Numeric) {
  25   gandiva::ExecutionContext ctx;
  26
  27   auto ctx_ptr = reinterpret_cast<int64_t>(&ctx);
  28
  29   std::vector<uint64_t> values_to_be_hashed;
  30
  31   // Generate a list of values to obtains the SHA1 hash
  32   values_to_be_hashed.push_back(gandiva::gdv_double_to_long(0.0));
  33   values_to_be_hashed.push_back(gandiva::gdv_double_to_long(0.1));
  34   values_to_be_hashed.push_back(gandiva::gdv_double_to_long(0.2));
  35   values_to_be_hashed.push_back(gandiva::gdv_double_to_long(-0.10000001));
  36   values_to_be_hashed.push_back(gandiva::gdv_double_to_long(-0.0000001));
  37   values_to_be_hashed.push_back(gandiva::gdv_double_to_long(1.000000));
  38   values_to_be_hashed.push_back(gandiva::gdv_double_to_long(-0.0000002));
  39   values_to_be_hashed.push_back(gandiva::gdv_double_to_long(0.999999));
  40
  41   // Checks if the hash value is different for each one of the values
  42   std::unordered_set<std::string> sha_values;
  43
  44   int sha1_size = 40;
  45
  46   for (auto value : values_to_be_hashed) {
  47     int out_length;
  48     const char* sha_1 =
  49         gandiva::gdv_hash_using_sha1(ctx_ptr, &value, sizeof(value), &out_length);
  50     std::string sha1_as_str(sha_1, out_length);
  51     EXPECT_EQ(sha1_as_str.size(), sha1_size);
  52
  53     // The value can not exists inside the set with the hash results
  54     EXPECT_EQ(sha_values.find(sha1_as_str), sha_values.end());
  55     sha_values.insert(sha1_as_str);
  56   }
  57 }
  58
  59 TEST(TestShaHashUtils, TestSha256Numeric) {
  60   gandiva::ExecutionContext ctx;
  61
  62   auto ctx_ptr = reinterpret_cast<int64_t>(&ctx);
  63
  64   std::vector<uint64_t> values_to_be_hashed;
  65
  66   // Generate a list of values to obtains the SHA1 hash
  67   values_to_be_hashed.push_back(gandiva::gdv_double_to_long(0.0));
  68   values_to_be_hashed.push_back(gandiva::gdv_double_to_long(0.1));
  69   values_to_be_hashed.push_back(gandiva::gdv_double_to_long(0.2));
  70   values_to_be_hashed.push_back(gandiva::gdv_double_to_long(-0.10000001));
  71   values_to_be_hashed.push_back(gandiva::gdv_double_to_long(-0.0000001));
  72   values_to_be_hashed.push_back(gandiva::gdv_double_to_long(1.000000));
  73   values_to_be_hashed.push_back(gandiva::gdv_double_to_long(-0.0000002));
  74   values_to_be_hashed.push_back(gandiva::gdv_double_to_long(0.999999));
  75
  76   // Checks if the hash value is different for each one of the values
  77   std::unordered_set<std::string> sha_values;
  78
  79   int sha256_size = 64;
  80
  81   for (auto value : values_to_be_hashed) {
  82     int out_length;
  83     const char* sha_256 =
  84         gandiva::gdv_hash_using_sha256(ctx_ptr, &value, sizeof(value), &out_length);
  85     std::string sha256_as_str(sha_256, out_length);
  86     EXPECT_EQ(sha256_as_str.size(), sha256_size);
  87
  88     // The value can not exists inside the set with the hash results
  89     EXPECT_EQ(sha_values.find(sha256_as_str), sha_values.end());
  90     sha_values.insert(sha256_as_str);
  91   }
  92 }
  93
  94 TEST(TestShaHashUtils, TestSha1Varlen) {
  95   gandiva::ExecutionContext ctx;
  96
  97   auto ctx_ptr = reinterpret_cast<int64_t>(&ctx);
  98
  99   std::string first_string =
 100       "ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn\nY [ˈʏpsilɔn], "
 101       "Yen [jɛn], Yoga [ˈjoːgɑ]";
 102
 103   std::string second_string =
 104       "ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeın\nY [ˈʏpsilɔn], "
 105       "Yen [jɛn], Yoga [ˈjoːgɑ] コンニチハ";
 106
 107   // The strings expected hashes are obtained from shell executing the following command:
 108   // echo -n <output-string> | openssl dgst sha1
 109   std::string expected_first_result = "160fcdbc2fa694d884868f5fae7a4bae82706185";
 110   std::string expected_second_result = "a456b3e0f88669d2482170a42fade226a815bee1";
 111
 112   // Generate the hashes and compare with expected outputs
 113   const int sha1_size = 40;
 114   int out_length;
 115
 116   const char* sha_1 = gandiva::gdv_hash_using_sha1(ctx_ptr, first_string.c_str(),
 117                                                    first_string.size(), &out_length);
 118   std::string sha1_as_str(sha_1, out_length);
 119   EXPECT_EQ(sha1_as_str.size(), sha1_size);
 120   EXPECT_EQ(sha1_as_str, expected_first_result);
 121
 122   const char* sha_2 = gandiva::gdv_hash_using_sha1(ctx_ptr, second_string.c_str(),
 123                                                    second_string.size(), &out_length);
 124   std::string sha2_as_str(sha_2, out_length);
 125   EXPECT_EQ(sha2_as_str.size(), sha1_size);
 126   EXPECT_EQ(sha2_as_str, expected_second_result);
 127 }
 128
 129 TEST(TestShaHashUtils, TestSha256Varlen) {
 130   gandiva::ExecutionContext ctx;
 131
 132   auto ctx_ptr = reinterpret_cast<int64_t>(&ctx);
 133
 134   std::string first_string =
 135       "ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn\nY [ˈʏpsilɔn], "
 136       "Yen [jɛn], Yoga [ˈjoːgɑ]";
 137
 138   std::string second_string =
 139       "ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeın\nY [ˈʏpsilɔn], "
 140       "Yen [jɛn], Yoga [ˈjoːgɑ] コンニチハ";
 141
 142   // The strings expected hashes are obtained from shell executing the following command:
 143   // echo -n <output-string> | openssl dgst sha1
 144   std::string expected_first_result =
 145       "55aeb2e789871dbd289edae94d4c1c82a1c25ca0bcd5a873924da2fefdd57acb";
 146   std::string expected_second_result =
 147       "86b29c13d0d0e26ea8f85bfa649dc9b8622ae59a4da2409d7d9b463e86e796f2";
 148
 149   // Generate the hashes and compare with expected outputs
 150   const int sha256_size = 64;
 151   int out_length;
 152
 153   const char* sha_1 = gandiva::gdv_hash_using_sha256(ctx_ptr, first_string.c_str(),
 154                                                      first_string.size(), &out_length);
 155   std::string sha1_as_str(sha_1, out_length);
 156   EXPECT_EQ(sha1_as_str.size(), sha256_size);
 157   EXPECT_EQ(sha1_as_str, expected_first_result);
 158
 159   const char* sha_2 = gandiva::gdv_hash_using_sha256(ctx_ptr, second_string.c_str(),
 160                                                      second_string.size(), &out_length);
 161   std::string sha2_as_str(sha_2, out_length);
 162   EXPECT_EQ(sha2_as_str.size(), sha256_size);
 163   EXPECT_EQ(sha2_as_str, expected_second_result);
 164 }