herbglitch/archeus
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

fixed a memory leak in lexer, all tests are now memory safe

Browse source
This commit is contained in:
herbglitch 2025-03-28 02:53:03 -06:00
parent cb48a9f573
commit a9a26ec122
8 changed files with 378 additions and 518 deletions
Download patch file Download diff file Expand all files Collapse all files

56
src/std/lexer.c
View file

@ -208,6 +208,10 @@ void ARC_Lexer_LexString(ARC_Lexer *lexer, ARC_String **data){
//check if a token was found if it wasn't continue. I'm doing this to try to cut down on the ammount of indentation
if(tokenLength == 0){
if(tokenData != NULL){
ARC_String_Destroy(tokenData);
}
continue;
}
@ -225,6 +229,12 @@ void ARC_Lexer_LexString(ARC_Lexer *lexer, ARC_String **data){
//update the last found tokenLength to the max length
lastTokenLength = tokenLength;
continue;
}
if(tokenData != NULL){
ARC_String_Destroy(tokenData);
}
}
@ -397,6 +407,11 @@ void ARC_LexerTokenRule_DestroyCharAutomataDataFn(void *automataData){
free((char *)automataData);
}
//private function to free automataData stored as an ARC_String
void ARC_LexerTokenRule_DestroyStringAutomataDataFn(void *automataData){
ARC_String_Destroy((ARC_String *)automataData);
}
ARC_LexerTokenRule ARC_LexerTokenRule_CreateAndReturnMatchCharRule(uint32_t id, char character){
//create the token rule
ARC_LexerTokenRule tokenRule;
@ -442,11 +457,6 @@ ARC_LexerTokenRule ARC_LexerTokenRule_CreateAndReturnMatchCharOrBetween(uint32_t
return tokenRule;
}
//private function to free automataData stored as an ARC_String
void ARC_LexerTokenRule_DestroyStringAutomataDataFn(void *automataData){
ARC_String_Destroy((ARC_String *)automataData);
}
ARC_LexerTokenRule ARC_LexerTokenRule_CreateAndReturnMatchStringRule(uint32_t id, ARC_String *string){
//create the token rule
ARC_LexerTokenRule tokenRule;
@ -490,39 +500,3 @@ ARC_LexerTokenRule ARC_LexerTokenRule_CreateAndReturnMatchCharInStringRule(uint3
//return the created tokenRule
return tokenRule;
}
void ARC_Lexer_InitBasicTokenRules(ARC_Lexer *lexer){
//null
ARC_Lexer_RegisterTokenRule(lexer, ARC_LexerTokenRule_CreateAndReturnMatchCharRule(ARC_LEXER_TOKEN_NULL, 0));
//number
ARC_Lexer_RegisterTokenRule(lexer, ARC_LexerTokenRule_CreateAndReturnMatchCharOrBetween(ARC_LEXER_TOKEN_NUMBER, '0', '9'));
//alpha char
ARC_Lexer_RegisterTokenRule(lexer, ARC_LexerTokenRule_CreateAndReturnMatchCharOrBetween(ARC_LEXER_TOKEN_ALPHA_LOWER_CHAR, 'a', 'z'));
ARC_Lexer_RegisterTokenRule(lexer, ARC_LexerTokenRule_CreateAndReturnMatchCharOrBetween(ARC_LEXER_TOKEN_ALPHA_UPPER_CHAR, 'A', 'Z'));
//whitespace
//TODO: fix this
ARC_String *whitespaceString;
ARC_String_CreateWithStrlen(&whitespaceString, " \t");
ARC_Lexer_RegisterTokenRule(lexer, ARC_LexerTokenRule_CreateAndReturnMatchCharInStringRule(ARC_LEXER_TOKEN_WHITESPACE, whitespaceString));
ARC_String_Destroy(whitespaceString);
//single char tokens
ARC_Lexer_RegisterTokenRule(lexer, ARC_LexerTokenRule_CreateAndReturnMatchCharRule(ARC_LEXER_TOKEN_NEWLINE_ID , ARC_LEXER_TOKEN_NEWLINE_CHAR ));
ARC_Lexer_RegisterTokenRule(lexer, ARC_LexerTokenRule_CreateAndReturnMatchCharRule(ARC_LEXER_TOKEN_COLON_ID , ARC_LEXER_TOKEN_COLON_CHAR ));
ARC_Lexer_RegisterTokenRule(lexer, ARC_LexerTokenRule_CreateAndReturnMatchCharRule(ARC_LEXER_TOKEN_SEMICOLON_ID , ARC_LEXER_TOKEN_SEMICOLON_CHAR ));
ARC_Lexer_RegisterTokenRule(lexer, ARC_LexerTokenRule_CreateAndReturnMatchCharRule(ARC_LEXER_TOKEN_COMMA_ID , ARC_LEXER_TOKEN_COMMA_CHAR ));
ARC_Lexer_RegisterTokenRule(lexer, ARC_LexerTokenRule_CreateAndReturnMatchCharRule(ARC_LEXER_TOKEN_PERIOD_ID , ARC_LEXER_TOKEN_PERIOD_CHAR ));
ARC_Lexer_RegisterTokenRule(lexer, ARC_LexerTokenRule_CreateAndReturnMatchCharRule(ARC_LEXER_TOKEN_FORWARD_SLASH_ID , ARC_LEXER_TOKEN_FORWARD_SLASH_CHAR ));
ARC_Lexer_RegisterTokenRule(lexer, ARC_LexerTokenRule_CreateAndReturnMatchCharRule(ARC_LEXER_TOKEN_BACK_SLASH_ID , ARC_LEXER_TOKEN_BACK_SLASH_CHAR ));
ARC_Lexer_RegisterTokenRule(lexer, ARC_LexerTokenRule_CreateAndReturnMatchCharRule(ARC_LEXER_TOKEN_LEFT_PARENTHESIS_ID , ARC_LEXER_TOKEN_LEFT_PARENTHESIS_CHAR ));
ARC_Lexer_RegisterTokenRule(lexer, ARC_LexerTokenRule_CreateAndReturnMatchCharRule(ARC_LEXER_TOKEN_RIGHT_PARENTHESIS_ID, ARC_LEXER_TOKEN_RIGHT_PARENTHESIS_CHAR));
ARC_Lexer_RegisterTokenRule(lexer, ARC_LexerTokenRule_CreateAndReturnMatchCharRule(ARC_LEXER_TOKEN_LEFT_CURLY_BRACE_ID , ARC_LEXER_TOKEN_LEFT_CURLY_BRACE_CHAR ));
ARC_Lexer_RegisterTokenRule(lexer, ARC_LexerTokenRule_CreateAndReturnMatchCharRule(ARC_LEXER_TOKEN_RIGHT_CURLY_BRACE_ID, ARC_LEXER_TOKEN_RIGHT_CURLY_BRACE_CHAR));
ARC_Lexer_RegisterTokenRule(lexer, ARC_LexerTokenRule_CreateAndReturnMatchCharRule(ARC_LEXER_TOKEN_BANG_ID , ARC_LEXER_TOKEN_BANG_CHAR ));
ARC_Lexer_RegisterTokenRule(lexer, ARC_LexerTokenRule_CreateAndReturnMatchCharRule(ARC_LEXER_TOKEN_AT_ID , ARC_LEXER_TOKEN_AT_CHAR ));
ARC_Lexer_RegisterTokenRule(lexer, ARC_LexerTokenRule_CreateAndReturnMatchCharRule(ARC_LEXER_TOKEN_HASH_ID , ARC_LEXER_TOKEN_HASH_CHAR ));
ARC_Lexer_RegisterTokenRule(lexer, ARC_LexerTokenRule_CreateAndReturnMatchCharRule(ARC_LEXER_TOKEN_PERCENT_ID , ARC_LEXER_TOKEN_PERCENT_CHAR ));
}

2
src/std/parser/parserlang.c
View file

@ -23,7 +23,7 @@ void ARC_ParserLang_InitLexerRulesFn(ARC_Lexer *lexer){
//whitespace
ARC_String *whitespaceString;
ARC_String_CreateWithStrlen(&whitespaceString, " \t");
ARC_Lexer_RegisterTokenRule(lexer, ARC_LexerTokenRule_CreateAndReturnMatchCharInStringRule(ARC_LEXER_TOKEN_WHITESPACE, whitespaceString));
ARC_Lexer_RegisterTokenRule(lexer, ARC_LexerTokenRule_CreateAndReturnMatchCharInStringRule(ARC_PARSERLANG_TOKEN_WHITESPACE, whitespaceString));
ARC_String_Destroy(whitespaceString);
//single char tokens