Rename StringDictionaryProxy get/add transient string methods.

ienkovich · ienkovich · commit 0c290d1bb269 · 2023-09-25T21:51:38.000-05:00
Signed-off-by: ienkovich &lt;ilya.enkovich@intel.com&gt;
diff --git a/omniscidb/QueryEngine/Execute.cpp b/omniscidb/QueryEngine/Execute.cpp
@@ -742,7 +742,7 @@ std::vector<int8_t> Executor::serializeLiterals(
                 ? getStringDictionaryProxy(p->second, row_set_mem_owner_, true)
                       ->getIdOfString(p->first)
                 : getStringDictionaryProxy(p->second, row_set_mem_owner_, true)
-                      ->getOrAddTransient(p->first);
+                      ->getOrAdd(p->first);
         memcpy(&serialized[off - lit_bytes], &str_id, lit_bytes);
         break;
       }
diff --git a/omniscidb/QueryEngine/StringOpsIR.cpp b/omniscidb/QueryEngine/StringOpsIR.cpp
@@ -60,7 +60,7 @@ extern "C" RUNTIME_EXPORT int32_t lower_encoded(int32_t string_id,
   StringDictionaryProxy* string_dict_proxy =
       reinterpret_cast<StringDictionaryProxy*>(string_dict_proxy_address);
   auto str = string_dict_proxy->getString(string_id);
-  return string_dict_proxy->getOrAddTransient(boost::locale::to_lower(str));
+  return string_dict_proxy->getOrAdd(boost::locale::to_lower(str));
 }
 
 llvm::Value* CodeGenerator::codegen(const hdk::ir::CharLengthExpr* expr,
diff --git a/omniscidb/QueryEngine/Visitors/TransientStringLiteralsVisitor.h b/omniscidb/QueryEngine/Visitors/TransientStringLiteralsVisitor.h
@@ -30,7 +30,7 @@ class TransientStringLiteralsVisitor : public hdk::ir::ExprVisitor<void> {
   void visitConstant(const hdk::ir::Constant* constant) override {
     if (constant->type()->isString() && !constant->isNull()) {
       CHECK(constant->value().stringval);
-      sdp_->getOrAddTransient(*constant->value().stringval);
+      sdp_->getOrAdd(*constant->value().stringval);
     }
   }
 
diff --git a/omniscidb/StringDictionary/StringDictionaryProxy.cpp b/omniscidb/StringDictionary/StringDictionaryProxy.cpp
@@ -52,15 +52,15 @@ int32_t truncate_to_generation(const int32_t id, const size_t generation) {
   return static_cast<size_t>(id) >= generation ? StringDictionary::INVALID_STR_ID : id;
 }
 
-std::vector<int32_t> StringDictionaryProxy::getTransientBulk(
+std::vector<int32_t> StringDictionaryProxy::getBulk(
     const std::vector<std::string>& strings) const {
   CHECK_GE(generation_, 0);
   std::vector<int32_t> string_ids(strings.size());
   getTransientBulkImpl(strings, string_ids.data(), true);
   return string_ids;
 }
 
-std::vector<int32_t> StringDictionaryProxy::getOrAddTransientBulk(
+std::vector<int32_t> StringDictionaryProxy::getOrAddBulk(
     const std::vector<std::string>& strings) {
   CHECK_GE(generation_, 0);
   const size_t num_strings = strings.size();
@@ -101,7 +101,7 @@ int32_t StringDictionaryProxy::getOrAddTransientUnlocked(String const& str) {
   return transient_id;
 }
 
-int32_t StringDictionaryProxy::getOrAddTransient(const std::string& str) {
+int32_t StringDictionaryProxy::getOrAdd(const std::string& str) {
   auto const string_id = getIdOfStringFromClient(str);
   if (string_id != StringDictionary::INVALID_STR_ID) {
     return string_id;
diff --git a/omniscidb/StringDictionary/StringDictionaryProxy.h b/omniscidb/StringDictionary/StringDictionaryProxy.h
@@ -69,10 +69,10 @@ class StringDictionaryProxy {
   * StringDictionary::INVALID_STR_ID for strings not found.
   */
 
-  std::vector<int32_t> getTransientBulk(const std::vector<std::string>& strings) const;
-  int32_t getOrAddTransient(const std::string& str);
+  std::vector<int32_t> getBulk(const std::vector<std::string>& strings) const;
+  int32_t getOrAdd(const std::string& str);
   // Not currently used
-  std::vector<int32_t> getOrAddTransientBulk(const std::vector<std::string>& strings);
+  std::vector<int32_t> getOrAddBulk(const std::vector<std::string>& strings);
   int32_t getIdOfString(const std::string& str) const;
   std::string getString(int32_t string_id) const;
   std::vector<std::string> getStrings(const std::vector<int32_t>& string_ids) const;
diff --git a/omniscidb/Tests/ResultSetTest.cpp b/omniscidb/Tests/ResultSetTest.cpp
@@ -882,7 +882,7 @@ void test_iterate(const std::vector<TargetInfo>& target_infos,
                        0,
                        0);
   for (size_t i = 0; i < query_mem_desc.getEntryCount(); ++i) {
-    sdp->getOrAddTransient(std::to_string(i));
+    sdp->getOrAdd(std::to_string(i));
   }
   const auto storage = result_set.allocateStorage();
   EvenNumberGenerator generator;
diff --git a/omniscidb/Tests/StringDictionaryBenchmark.cpp b/omniscidb/Tests/StringDictionaryBenchmark.cpp
@@ -282,8 +282,7 @@ BENCHMARK_DEFINE_F(StringDictionaryProxyFixture, GetOrAddTransientBulk_1M_Unique
 (benchmark::State& state) {
   const auto string_dict_proxy = create_str_proxy(1, true);
   for (auto _ : state) {
-    const auto string_ids =
-        string_dict_proxy->getOrAddTransientBulk(append_strings_10M_1M_10);
+    const auto string_ids = string_dict_proxy->getOrAddBulk(append_strings_10M_1M_10);
   }
 }
 
@@ -296,7 +295,7 @@ BENCHMARK_DEFINE_F(StringDictionaryProxyFixture, GetOrAddTransient_1M_Unique)
   for (auto _ : state) {
     for (size_t string_idx = 0; string_idx < num_strings; ++string_idx) {
       string_ids[string_idx] =
-          string_dict_proxy->getOrAddTransient(append_strings_10M_1M_10[string_idx]);
+          string_dict_proxy->getOrAdd(append_strings_10M_1M_10[string_idx]);
     }
   }
 }
@@ -308,7 +307,7 @@ BENCHMARK_DEFINE_F(StringDictionaryProxyFixture,
       create_and_populate_str_proxy(1, true, append_strings_10M_1M_10);
   for (auto _ : state) {
     const auto proxy_string_ids =
-        string_dict_proxy->getOrAddTransientBulk(append_strings_10M_1M_10_randomized);
+        string_dict_proxy->getOrAddBulk(append_strings_10M_1M_10_randomized);
   }
 }
 
@@ -320,8 +319,8 @@ BENCHMARK_DEFINE_F(StringDictionaryProxyFixture, GetOrAddTransient_AllPersisted_
   std::vector<int32_t> proxy_string_ids(num_strings);
   for (auto _ : state) {
     for (size_t string_idx = 0; string_idx < num_strings; ++string_idx) {
-      proxy_string_ids[string_idx] = string_proxy->getOrAddTransient(
-          append_strings_10M_1M_10_randomized[string_idx]);
+      proxy_string_ids[string_idx] =
+          string_proxy->getOrAdd(append_strings_10M_1M_10_randomized[string_idx]);
     }
   }
 }
@@ -360,7 +359,7 @@ BENCHMARK_DEFINE_F(
             append_strings_10M_10M_10_randomized_truncated_100.begin());
   auto dest_proxy = create_and_populate_str_proxy(
       2, true, append_strings_10M_10M_10_randomized_truncated_8M);
-  dest_proxy->getOrAddTransientBulk(append_strings_10M_10M_10_randomized_truncated_100);
+  dest_proxy->getOrAddBulk(append_strings_10M_10M_10_randomized_truncated_100);
   for (auto _ : state) {
     auto id_map =
         source_proxy->buildIntersectionTranslationMapToOtherProxy(dest_proxy.get());
@@ -390,7 +389,7 @@ BENCHMARK_DEFINE_F(
             append_strings_10M_10M_10_randomized_truncated_100.begin());
   auto dest_proxy = create_and_populate_str_proxy(
       2, true, append_strings_10M_10M_10_randomized_truncated_8M);
-  dest_proxy->getOrAddTransientBulk(append_strings_10M_10M_10_randomized_truncated_100);
+  dest_proxy->getOrAddBulk(append_strings_10M_10M_10_randomized_truncated_100);
   for (auto _ : state) {
     auto id_map = source_proxy->buildUnionTranslationMapToOtherProxy(dest_proxy.get());
     const size_t num_expected_untranslated_strings =
diff --git a/omniscidb/Tests/StringDictionaryTest.cpp b/omniscidb/Tests/StringDictionaryTest.cpp
@@ -286,7 +286,7 @@ TEST(StringDictionaryProxy, GetOrAddTransient) {
     }
 
     for (size_t i = 0; i < g_op_count; ++i) {
-      string_ids[i] = string_dict_proxy.getOrAddTransient(strings[i]);
+      string_ids[i] = string_dict_proxy.getOrAdd(strings[i]);
     }
 
     for (int i = 0; i < g_op_count; ++i) {
@@ -312,7 +312,7 @@ TEST(StringDictionaryProxy, GetOrAddTransient) {
     }
 
     for (size_t i = 0; i < g_op_count; ++i) {
-      string_ids[i] = string_dict_proxy.getOrAddTransient(strings[i]);
+      string_ids[i] = string_dict_proxy.getOrAdd(strings[i]);
     }
 
     for (int i = 0; i < g_op_count; ++i) {
@@ -363,7 +363,7 @@ TEST(StringDictionaryProxy, GetOrAddTransientBulk) {
       }
     }
 
-    const auto string_ids = string_dict_proxy.getOrAddTransientBulk(strings);
+    const auto string_ids = string_dict_proxy.getOrAddBulk(strings);
 
     for (int i = 0; i < g_op_count; ++i) {
       if (i % 2 == 0) {
@@ -386,7 +386,7 @@ TEST(StringDictionaryProxy, GetOrAddTransientBulk) {
       }
     }
 
-    const auto string_ids = string_dict_proxy.getOrAddTransientBulk(strings);
+    const auto string_ids = string_dict_proxy.getOrAddBulk(strings);
 
     for (int i = 0; i < g_op_count; ++i) {
       if (i % 2 == 0) {
@@ -415,7 +415,7 @@ TEST(StringDictionaryProxy, GetTransientBulk) {
       }
     }
 
-    const auto string_ids = string_dict_proxy.getTransientBulk(strings);
+    const auto string_ids = string_dict_proxy.getBulk(strings);
 
     for (int i = 0; i < g_op_count; ++i) {
       if (i % 2 == 0) {
@@ -437,7 +437,7 @@ TEST(StringDictionaryProxy, GetTransientBulk) {
       }
     }
 
-    const auto string_ids = string_dict_proxy.getTransientBulk(strings);
+    const auto string_ids = string_dict_proxy.getBulk(strings);
 
     for (int i = 0; i < g_op_count; ++i) {
       if (i % 2 == 0) {
@@ -514,12 +514,12 @@ TEST(StringDictionaryProxy, BuildIntersectionTranslationMapToOtherProxy) {
     for (int i = proxy_transient_start;
          i < proxy_transient_start + num_source_proxy_transient_ids;
          ++i) {
-      source_string_dict_proxy->getOrAddTransient(std::to_string(i));
+      source_string_dict_proxy->getOrAdd(std::to_string(i));
     }
     for (int i = proxy_transient_start;
          i < proxy_transient_start + num_dest_proxy_transient_ids;
          ++i) {
-      dest_string_dict_proxy->getOrAddTransient(std::to_string(i));
+      dest_string_dict_proxy->getOrAdd(std::to_string(i));
     }
 
     const auto str_proxy_translation_map =
@@ -632,7 +632,7 @@ std::vector<std::string> add_strings_numeric_range(StringDictionaryProxy& sdp,
   for (int32_t int_val = start_val; int_val > end_val; --int_val) {
     strings[start_val - int_val] = std::to_string(int_val);
   }
-  sdp.getOrAddTransientBulk(strings);
+  sdp.getOrAddBulk(strings);
   return strings;
 }
 

Original file line number	Diff line number	Diff line change
`@@ -742,7 +742,7 @@ std::vector<int8_t> Executor::serializeLiterals(`
`742`	`742`	`? getStringDictionaryProxy(p->second, row_set_mem_owner_, true)`
`743`	`743`	`->getIdOfString(p->first)`
`744`	`744`	`: getStringDictionaryProxy(p->second, row_set_mem_owner_, true)`
`745`		`- ->getOrAddTransient(p->first);`
	`745`	`+ ->getOrAdd(p->first);`
`746`	`746`	`memcpy(&serialized[off - lit_bytes], &str_id, lit_bytes);`
`747`	`747`	`break;`
`748`	`748`	`}`
Original file line number	Diff line number	Diff line change
`@@ -60,7 +60,7 @@ extern "C" RUNTIME_EXPORT int32_t lower_encoded(int32_t string_id,`
`60`	`60`	`StringDictionaryProxy* string_dict_proxy =`
`61`	`61`	`reinterpret_cast<StringDictionaryProxy*>(string_dict_proxy_address);`
`62`	`62`	`auto str = string_dict_proxy->getString(string_id);`
`63`		`- return string_dict_proxy->getOrAddTransient(boost::locale::to_lower(str));`
	`63`	`+ return string_dict_proxy->getOrAdd(boost::locale::to_lower(str));`
`64`	`64`	`}`
`65`	`65`
`66`	`66`	`llvm::Value* CodeGenerator::codegen(const hdk::ir::CharLengthExpr* expr,`
Original file line number	Diff line number	Diff line change
`@@ -30,7 +30,7 @@ class TransientStringLiteralsVisitor : public hdk::ir::ExprVisitor<void> {`
`30`	`30`	`void visitConstant(const hdk::ir::Constant* constant) override {`
`31`	`31`	`if (constant->type()->isString() && !constant->isNull()) {`
`32`	`32`	`CHECK(constant->value().stringval);`
`33`		`- sdp_->getOrAddTransient(*constant->value().stringval);`
	`33`	`+ sdp_->getOrAdd(*constant->value().stringval);`
`34`	`34`	`}`
`35`	`35`	`}`
`36`	`36`
Original file line number	Diff line number	Diff line change
`@@ -882,7 +882,7 @@ void test_iterate(const std::vector<TargetInfo>& target_infos,`
`882`	`882`	`0,`
`883`	`883`	`0);`
`884`	`884`	`for (size_t i = 0; i < query_mem_desc.getEntryCount(); ++i) {`
`885`		`- sdp->getOrAddTransient(std::to_string(i));`
	`885`	`+ sdp->getOrAdd(std::to_string(i));`
`886`	`886`	`}`
`887`	`887`	`const auto storage = result_set.allocateStorage();`
`888`	`888`	`EvenNumberGenerator generator;`
Original file line number	Diff line number	Diff line change
`@@ -282,8 +282,7 @@ BENCHMARK_DEFINE_F(StringDictionaryProxyFixture, GetOrAddTransientBulk_1M_Unique`
`282`	`282`	`(benchmark::State& state) {`
`283`	`283`	`const auto string_dict_proxy = create_str_proxy(1, true);`
`284`	`284`	`for (auto _ : state) {`
`285`		`- const auto string_ids =`
`286`		`- string_dict_proxy->getOrAddTransientBulk(append_strings_10M_1M_10);`
	`285`	`+ const auto string_ids = string_dict_proxy->getOrAddBulk(append_strings_10M_1M_10);`
`287`	`286`	`}`
`288`	`287`	`}`
`289`	`288`
`@@ -296,7 +295,7 @@ BENCHMARK_DEFINE_F(StringDictionaryProxyFixture, GetOrAddTransient_1M_Unique)`
`296`	`295`	`for (auto _ : state) {`
`297`	`296`	`for (size_t string_idx = 0; string_idx < num_strings; ++string_idx) {`
`298`	`297`	`string_ids[string_idx] =`
`299`		`- string_dict_proxy->getOrAddTransient(append_strings_10M_1M_10[string_idx]);`
	`298`	`+ string_dict_proxy->getOrAdd(append_strings_10M_1M_10[string_idx]);`
`300`	`299`	`}`
`301`	`300`	`}`
`302`	`301`	`}`
`@@ -308,7 +307,7 @@ BENCHMARK_DEFINE_F(StringDictionaryProxyFixture,`
`308`	`307`	`create_and_populate_str_proxy(1, true, append_strings_10M_1M_10);`
`309`	`308`	`for (auto _ : state) {`
`310`	`309`	`const auto proxy_string_ids =`
`311`		`- string_dict_proxy->getOrAddTransientBulk(append_strings_10M_1M_10_randomized);`
	`310`	`+ string_dict_proxy->getOrAddBulk(append_strings_10M_1M_10_randomized);`
`312`	`311`	`}`
`313`	`312`	`}`
`314`	`313`
`@@ -320,8 +319,8 @@ BENCHMARK_DEFINE_F(StringDictionaryProxyFixture, GetOrAddTransient_AllPersisted_`
`320`	`319`	`std::vector<int32_t> proxy_string_ids(num_strings);`
`321`	`320`	`for (auto _ : state) {`
`322`	`321`	`for (size_t string_idx = 0; string_idx < num_strings; ++string_idx) {`
`323`		`- proxy_string_ids[string_idx] = string_proxy->getOrAddTransient(`
`324`		`- append_strings_10M_1M_10_randomized[string_idx]);`
	`322`	`+ proxy_string_ids[string_idx] =`
	`323`	`+ string_proxy->getOrAdd(append_strings_10M_1M_10_randomized[string_idx]);`
`325`	`324`	`}`
`326`	`325`	`}`
`327`	`326`	`}`
`@@ -360,7 +359,7 @@ BENCHMARK_DEFINE_F(`
`360`	`359`	`append_strings_10M_10M_10_randomized_truncated_100.begin());`
`361`	`360`	`auto dest_proxy = create_and_populate_str_proxy(`
`362`	`361`	`2, true, append_strings_10M_10M_10_randomized_truncated_8M);`
`363`		`- dest_proxy->getOrAddTransientBulk(append_strings_10M_10M_10_randomized_truncated_100);`
	`362`	`+ dest_proxy->getOrAddBulk(append_strings_10M_10M_10_randomized_truncated_100);`
`364`	`363`	`for (auto _ : state) {`
`365`	`364`	`auto id_map =`
`366`	`365`	`source_proxy->buildIntersectionTranslationMapToOtherProxy(dest_proxy.get());`
`@@ -390,7 +389,7 @@ BENCHMARK_DEFINE_F(`
`390`	`389`	`append_strings_10M_10M_10_randomized_truncated_100.begin());`
`391`	`390`	`auto dest_proxy = create_and_populate_str_proxy(`
`392`	`391`	`2, true, append_strings_10M_10M_10_randomized_truncated_8M);`
`393`		`- dest_proxy->getOrAddTransientBulk(append_strings_10M_10M_10_randomized_truncated_100);`
	`392`	`+ dest_proxy->getOrAddBulk(append_strings_10M_10M_10_randomized_truncated_100);`
`394`	`393`	`for (auto _ : state) {`
`395`	`394`	`auto id_map = source_proxy->buildUnionTranslationMapToOtherProxy(dest_proxy.get());`
`396`	`395`	`const size_t num_expected_untranslated_strings =`
Original file line number	Diff line number	Diff line change
`@@ -286,7 +286,7 @@ TEST(StringDictionaryProxy, GetOrAddTransient) {`
`286`	`286`	`}`
`287`	`287`
`288`	`288`	`for (size_t i = 0; i < g_op_count; ++i) {`
`289`		`- string_ids[i] = string_dict_proxy.getOrAddTransient(strings[i]);`
	`289`	`+ string_ids[i] = string_dict_proxy.getOrAdd(strings[i]);`
`290`	`290`	`}`
`291`	`291`
`292`	`292`	`for (int i = 0; i < g_op_count; ++i) {`
`@@ -312,7 +312,7 @@ TEST(StringDictionaryProxy, GetOrAddTransient) {`
`312`	`312`	`}`
`313`	`313`
`314`	`314`	`for (size_t i = 0; i < g_op_count; ++i) {`
`315`		`- string_ids[i] = string_dict_proxy.getOrAddTransient(strings[i]);`
	`315`	`+ string_ids[i] = string_dict_proxy.getOrAdd(strings[i]);`
`316`	`316`	`}`
`317`	`317`
`318`	`318`	`for (int i = 0; i < g_op_count; ++i) {`
`@@ -363,7 +363,7 @@ TEST(StringDictionaryProxy, GetOrAddTransientBulk) {`
`363`	`363`	`}`
`364`	`364`	`}`
`365`	`365`
`366`		`- const auto string_ids = string_dict_proxy.getOrAddTransientBulk(strings);`
	`366`	`+ const auto string_ids = string_dict_proxy.getOrAddBulk(strings);`
`367`	`367`
`368`	`368`	`for (int i = 0; i < g_op_count; ++i) {`
`369`	`369`	`if (i % 2 == 0) {`
`@@ -386,7 +386,7 @@ TEST(StringDictionaryProxy, GetOrAddTransientBulk) {`
`386`	`386`	`}`
`387`	`387`	`}`
`388`	`388`
`389`		`- const auto string_ids = string_dict_proxy.getOrAddTransientBulk(strings);`
	`389`	`+ const auto string_ids = string_dict_proxy.getOrAddBulk(strings);`
`390`	`390`
`391`	`391`	`for (int i = 0; i < g_op_count; ++i) {`
`392`	`392`	`if (i % 2 == 0) {`
`@@ -415,7 +415,7 @@ TEST(StringDictionaryProxy, GetTransientBulk) {`
`415`	`415`	`}`
`416`	`416`	`}`
`417`	`417`
`418`		`- const auto string_ids = string_dict_proxy.getTransientBulk(strings);`
	`418`	`+ const auto string_ids = string_dict_proxy.getBulk(strings);`
`419`	`419`
`420`	`420`	`for (int i = 0; i < g_op_count; ++i) {`
`421`	`421`	`if (i % 2 == 0) {`
`@@ -437,7 +437,7 @@ TEST(StringDictionaryProxy, GetTransientBulk) {`
`437`	`437`	`}`
`438`	`438`	`}`
`439`	`439`
`440`		`- const auto string_ids = string_dict_proxy.getTransientBulk(strings);`
	`440`	`+ const auto string_ids = string_dict_proxy.getBulk(strings);`
`441`	`441`
`442`	`442`	`for (int i = 0; i < g_op_count; ++i) {`
`443`	`443`	`if (i % 2 == 0) {`
`@@ -514,12 +514,12 @@ TEST(StringDictionaryProxy, BuildIntersectionTranslationMapToOtherProxy) {`
`514`	`514`	`for (int i = proxy_transient_start;`
`515`	`515`	`i < proxy_transient_start + num_source_proxy_transient_ids;`
`516`	`516`	`++i) {`
`517`		`- source_string_dict_proxy->getOrAddTransient(std::to_string(i));`
	`517`	`+ source_string_dict_proxy->getOrAdd(std::to_string(i));`
`518`	`518`	`}`
`519`	`519`	`for (int i = proxy_transient_start;`
`520`	`520`	`i < proxy_transient_start + num_dest_proxy_transient_ids;`
`521`	`521`	`++i) {`
`522`		`- dest_string_dict_proxy->getOrAddTransient(std::to_string(i));`
	`522`	`+ dest_string_dict_proxy->getOrAdd(std::to_string(i));`
`523`	`523`	`}`
`524`	`524`
`525`	`525`	`const auto str_proxy_translation_map =`
`@@ -632,7 +632,7 @@ std::vector<std::string> add_strings_numeric_range(StringDictionaryProxy& sdp,`
`632`	`632`	`for (int32_t int_val = start_val; int_val > end_val; --int_val) {`
`633`	`633`	`strings[start_val - int_val] = std::to_string(int_val);`
`634`	`634`	`}`
`635`		`- sdp.getOrAddTransientBulk(strings);`
	`635`	`+ sdp.getOrAddBulk(strings);`
`636`	`636`	`return strings;`
`637`	`637`	`}`
`638`	`638`