commit fffd8298be288a0d5d046aa46882587a09bacf14
from: Sergey Bronnikov <sergeyb@tarantool.org>
date: Thu Jun 13 18:32:01 2024 UTC

test/fuzz: speedup string serialization

- clamp before cleaning string because cleaning is not cheap
  (O(n), where max n is equal to kMaxStrLength)
- call cleaning for identifiers only, there is no sense to
  cleaning string literals
- replace symbols disallowed by Lua grammar in indentifier's
  names with '_'

The patch saves 16 sec on 145k samples (401 sec before the patch
and 385 sec after the patch). It is actually not so much, but it
is about 2.5 min per hour.

NO_CHANGELOG=testing
NO_DOC=testing

commit - 9d3859b246977c307a22f5930755fe77e374a634
commit + fffd8298be288a0d5d046aa46882587a09bacf14
blob - b4500da9cad3d96ed0406836754e3336d1abe269
blob + 3895f1547c712dcbb87860f238a8369bb8bff502
--- test/fuzz/luaL_loadbuffer/serializer.cc
+++ test/fuzz/luaL_loadbuffer/serializer.cc
@@ -435,6 +435,8 @@ ClearIdentifier(const std::string &identifier)
 		} else if (std::isalpha(c) || c == '_') {
 			has_first_not_digit = true;
 			cleared += c;
+		} else {
+			cleared += '_';
 		}
 	}
 	return cleared;
@@ -456,12 +458,13 @@ clamp(double number, double upper, double lower)
 }
 
 inline std::string
-ConvertToStringDefault(const std::string &s)
+ConvertToStringDefault(const std::string &s, bool sanitize = false)
 {
-	std::string ident = ClearIdentifier(s);
-	ident = clamp(ident);
+	std::string ident = clamp(s);
+	if (sanitize)
+		ident = ClearIdentifier(ident);
 	if (ident.empty())
-		return std::string(kDefaultIdent);
+		ident = std::string(kDefaultIdent);
 	return ident;
 }
 
@@ -951,7 +954,7 @@ NESTED_PROTO_TOSTRING(IndexWithName, indexname, Variab
 {
 	std::string indexname_str = PrefixExpressionToString(
 		indexname.prefixexp());
-	std::string idx_str = ConvertToStringDefault(indexname.name());
+	std::string idx_str = ConvertToStringDefault(indexname.name(), true);
 	/* Prevent using reserved keywords as indices. */
 	if (KReservedLuaKeywords.find(idx_str) != KReservedLuaKeywords.end()) {
 		idx_str += "_1";
@@ -1196,8 +1199,12 @@ PROTO_TOSTRING(UnaryOperator, op)
  */
 PROTO_TOSTRING(Name, name)
 {
-	std::string ident = ConvertToStringDefault(name.name());
-	return ident + std::to_string(name.num() % kMaxIdentifiers);
+	std::string ident = ConvertToStringDefault(name.name(), true);
+	/* Identifier has default name, add an index. */
+	if (!ident.compare(kDefaultIdent)) {
+		ident += std::to_string(name.num() % kMaxIdentifiers);
+	}
+	return ident;
 }
 
 } /* namespace */