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

16
CMakeLists.txt
View file

@ -135,14 +135,14 @@ if(ARCHEUS_TESTS)
add_executable(tests
tests/test.c
#tests/std/config.c
#tests/std/entity.c
#tests/std/hashtable.c
#tests/std/lexer.c
#tests/std/parser.c
#tests/std/parser/csv.c
#tests/std/parser/parserlang.c
#tests/std/vector.c
tests/std/config.c
tests/std/entity.c
tests/std/hashtable.c
tests/std/lexer.c
tests/std/parser.c
tests/std/parser/csv.c
tests/std/parser/parserlang.c
tests/std/vector.c
tests/std/vector/inline.c
${ARCHEUS_SOURCES}

16
doc/pages/standard/vector.md
View file

@ -85,10 +85,10 @@ int main(){
//print the values within the vector
for(uint32_t index = 0; index < ARC_Vector_GetSize(vector); index++){
//cast the return value back to what it initially was
valueRef = (int32_t *)ARC_Vector_Get(vector, index);
int32_t *valueRef = (int32_t *)ARC_Vector_Get(vector, index);
//print out the index and value
printf("%d) %d\n", index, *value);
printf("%d) %d\n", index, *valueRef);
}
//remove the value
@ -97,10 +97,10 @@ int main(){
//print the values again to show that the value was removed
for(uint32_t index = 0; index < ARC_Vector_GetSize(vector); index++){
//cast the return value back to what it initially was
valueRef = (int32_t *)ARC_Vector_Get(vector, index);
int32_t *valueRef = (int32_t *)ARC_Vector_Get(vector, index);
//print out the index and value
printf("%d) %d\n", index, *value);
printf("%d) %d\n", index, *valueRef);
}
//cleanup
@ -147,10 +147,10 @@ int main(){
//print the values within the vector
for(uint32_t index = 0; index < ARC_Vector_GetSize(vector); index++){
//cast the return value back to what it initially was
valueRef = (int32_t *)ARC_Vector_Get(vector, index);
int32_t *valueRef = (int32_t *)ARC_Vector_Get(vector, index);
//print out the index and value
printf("%d) %d\n", index, *value);
printf("%d) %d\n", index, *valueRef);
}
//example to demonstrate that there is no memory leak on removal due to the destroy callback
@ -159,10 +159,10 @@ int main(){
//print the values again to show that the value was removed
for(uint32_t index = 0; index < ARC_Vector_GetSize(vector); index++){
//cast the return value back to what it initially was
valueRef = (int32_t *)ARC_Vector_Get(vector, index);
int32_t valueRef = (int32_t *)ARC_Vector_Get(vector, index);
//print out the index and value
printf("%d) %d\n", index, *value);
printf("%d) %d\n", index, *valueRef);
}
//cleanup

70
include/arc/std/lexer.h
View file

@ -242,76 +242,6 @@ ARC_LexerTokenRule ARC_LexerTokenRule_CreateAndReturnMatchStringRule(uint32_t id
*/
ARC_LexerTokenRule ARC_LexerTokenRule_CreateAndReturnMatchCharInStringRule(uint32_t id, ARC_String *string);
/**
* @{
* @brief basic tokens
*/
#define ARC_LEXER_TOKEN_NULL 0
#define ARC_LEXER_TOKEN_NUMBER 1
#define ARC_LEXER_TOKEN_ALPHA_LOWER_CHAR 2
#define ARC_LEXER_TOKEN_ALPHA_UPPER_CHAR 3
#define ARC_LEXER_TOKEN_WHITESPACE 4
/**
* @}
*/
/**
* @{
* @brief basic token type ids, chars, and tags
*/
#define ARC_LEXER_TOKEN_NEWLINE_ID 5
#define ARC_LEXER_TOKEN_NEWLINE_CHAR '\n'
#define ARC_LEXER_TOKEN_COLON_ID 6
#define ARC_LEXER_TOKEN_COLON_CHAR ':'
#define ARC_LEXER_TOKEN_COLON_TAG "COLON"
#define ARC_LEXER_TOKEN_SEMICOLON_ID 7
#define ARC_LEXER_TOKEN_SEMICOLON_CHAR ';'
#define ARC_LEXER_TOKEN_SEMICOLON_TAG "SEMICOLON"
#define ARC_LEXER_TOKEN_COMMA_ID 8
#define ARC_LEXER_TOKEN_COMMA_CHAR ','
#define ARC_LEXER_TOKEN_COMMA_TAG "COMMA"
#define ARC_LEXER_TOKEN_PERIOD_ID 9
#define ARC_LEXER_TOKEN_PERIOD_CHAR '.'
#define ARC_LEXER_TOKEN_PERIOD_TAG "PERIOD"
#define ARC_LEXER_TOKEN_FORWARD_SLASH_ID 10
#define ARC_LEXER_TOKEN_FORWARD_SLASH_CHAR '/'
#define ARC_LEXER_TOKEN_FORWARD_SLASH_TAG "FORWARD_SLASH"
#define ARC_LEXER_TOKEN_BACK_SLASH_ID 11
#define ARC_LEXER_TOKEN_BACK_SLASH_CHAR '\\'
#define ARC_LEXER_TOKEN_BACK_SLASH_TAG "BACK_SLASH"
#define ARC_LEXER_TOKEN_LEFT_PARENTHESIS_ID 12
#define ARC_LEXER_TOKEN_LEFT_PARENTHESIS_CHAR '('
#define ARC_LEXER_TOKEN_LEFT_PARENTHESIS_TAG "LEFT_PARENTHESIS"
#define ARC_LEXER_TOKEN_RIGHT_PARENTHESIS_ID 13
#define ARC_LEXER_TOKEN_RIGHT_PARENTHESIS_CHAR ')'
#define ARC_LEXER_TOKEN_RIGHT_PARENTHESIS_TAG "RIGHT_PARENTHESIS"
#define ARC_LEXER_TOKEN_LEFT_CURLY_BRACE_ID 14
#define ARC_LEXER_TOKEN_LEFT_CURLY_BRACE_CHAR '{'
#define ARC_LEXER_TOKEN_LEFT_CURLY_BRACE_TAG "LEFT_CURLY_BRACE"
#define ARC_LEXER_TOKEN_RIGHT_CURLY_BRACE_ID 15
#define ARC_LEXER_TOKEN_RIGHT_CURLY_BRACE_CHAR '}'
#define ARC_LEXER_TOKEN_RIGHT_CURLY_BRACE_TAG "RIGHT_CURLY_BRACE"
#define ARC_LEXER_TOKEN_BANG_ID 16
#define ARC_LEXER_TOKEN_BANG_CHAR '!'
#define ARC_LEXER_TOKEN_BANG_TAG "BANG"
#define ARC_LEXER_TOKEN_AT_ID 17
#define ARC_LEXER_TOKEN_AT_CHAR '!'
#define ARC_LEXER_TOKEN_AT_TAG "AT"
#define ARC_LEXER_TOKEN_HASH_ID 18
#define ARC_LEXER_TOKEN_HASH_CHAR '#'
#define ARC_LEXER_TOKEN_HASH_TAG "HASH"
#define ARC_LEXER_TOKEN_PERCENT_ID 19
#define ARC_LEXER_TOKEN_PERCENT_CHAR '%'
#define ARC_LEXER_TOKEN_PERCENT_TAG "PERCENT"
/**
* @}
*/
/**
* @brief adds a bunch of basic token rules (matching the BasicTokens above)
*/
void ARC_Lexer_InitBasicTokenRules(ARC_Lexer *lexer);
#ifdef __cplusplus
}
#endif

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

79
tests/std/config.c
View file

@ -1,92 +1,15 @@
#include "../test.h"
#include "arc/std/errno.h"
#include "arc/std/config.h"
#include "arc/std/parser.h"
#include "arc/std/parser/helpers.h"
#include <stdlib.h>
static const char *testType = "int32";
void TEST_configType_CopyInt32Fn(void **type, ARC_ParserTagToken *parsedData, ARC_Config *config, void *userdata){
//go into the <numberSign> tag
ARC_ParserTagToken *childTagToken = (ARC_ParserTagToken *)ARC_Vector_Get(parsedData->tagTokens, 0);
if(childTagToken->id != ARC_CONFIG_NUMBER_SIGN){
arc_errno = ARC_ERRNO_DATA;
ARC_DEBUG_LOG_ERROR("TEST_configType_CopyInt32Fn(type, parsedData, config), parsed data was not a <numberSign>");
*type = NULL;
return;
}
//check if the first tag is a minus sign and create a string starting with that if it is
childTagToken = (ARC_ParserTagToken *)ARC_Vector_Get(childTagToken->tagTokens, 0);
ARC_String *int32String;
ARC_String_Create(&int32String, NULL, 0);
if(childTagToken->id == ARC_CONFIG_MINUS){
ARC_String_AppendCStringWithStrlen(&int32String, "-");
}
ARC_ParserData_HelperRecurseStringAdd(&int32String, parsedData);
//set the max character size 2,147,483,647 (10 characters) or -2,147,483,648 (11 characters)
uint32_t maxInt32Size = 10;
if(int32String->data[0] == '-'){
maxInt32Size++;
}
//if the string is bigger than the possible size return NULL and error
if(int32String->length > maxInt32Size){
arc_errno = ARC_ERRNO_DATA;
ARC_DEBUG_LOG_ERROR_WITH_VARIABLES("TEST_configType_CopyInt32Fn(type, parsedData, config), size \"%s\" was bigger or smaller than the max 2,147,483,647 or min -2,147,483,648", int32String->data);
*type = NULL;
ARC_String_Destroy(int32String);
return;
}
if(int32String->length == maxInt32Size){
char maxint32CStr[10] = "2147483647";
//offset starting index and last number if there is a negative
uint8_t stringIndex = 0;
if(int32String->data[0] == '-'){
stringIndex++;
maxint32CStr[9]++;
}
for(uint8_t index = 0; index < 10; index++, stringIndex++){
if(int32String->data[stringIndex] > maxint32CStr[index]){
arc_errno = ARC_ERRNO_DATA;
ARC_DEBUG_LOG_ERROR_WITH_VARIABLES("TEST_configType_CopyInt32Fn(type, parsedData, config), size \"%s\" was bigger or smaller than the max 2,147,483,647 or min -2,147,483,648", int32String->data);
*type = NULL;
ARC_String_Destroy(int32String);
return;
}
}
}
//copy the int32_t
*type = malloc(sizeof(int32_t));
*(int32_t *)(*type) = (int32_t)ARC_String_ToInt64_t(int32String);
//cleanup
ARC_String_Destroy(int32String);
}
void TEST_configType_DestroyInt32Fn(void *type){
free((int32_t *)type);
}
ARC_TEST(config_BasicTest){
ARC_Config *config;
ARC_Config_Create(&config);
ARC_CHECK(arc_errno == 0);
ARC_ConfigType int32Type = {
TEST_configType_CopyInt32Fn,
TEST_configType_DestroyInt32Fn,
NULL
};
ARC_Config_RegisterTypeWithCStr(config, testType, int32Type);
ARC_Config_InitStd(config);
char *tempCString = "tests/res/std/config/first.chemical";
ARC_String *tempString;

86
tests/std/lexer.c
View file

@ -1,6 +1,92 @@
#include "../test.h"
#include "arc/std/lexer.h"
#define ARC_LEXER_TOKEN_NULL 0
#define ARC_LEXER_TOKEN_NUMBER 1
#define ARC_LEXER_TOKEN_ALPHA_LOWER_CHAR 2
#define ARC_LEXER_TOKEN_ALPHA_UPPER_CHAR 3
#define ARC_LEXER_TOKEN_WHITESPACE 4
#define ARC_LEXER_TOKEN_NEWLINE_ID 5
#define ARC_LEXER_TOKEN_NEWLINE_CHAR '\n'
#define ARC_LEXER_TOKEN_COLON_ID 6
#define ARC_LEXER_TOKEN_COLON_CHAR ':'
#define ARC_LEXER_TOKEN_COLON_TAG "COLON"
#define ARC_LEXER_TOKEN_SEMICOLON_ID 7
#define ARC_LEXER_TOKEN_SEMICOLON_CHAR ';'
#define ARC_LEXER_TOKEN_SEMICOLON_TAG "SEMICOLON"
#define ARC_LEXER_TOKEN_COMMA_ID 8
#define ARC_LEXER_TOKEN_COMMA_CHAR ','
#define ARC_LEXER_TOKEN_COMMA_TAG "COMMA"
#define ARC_LEXER_TOKEN_PERIOD_ID 9
#define ARC_LEXER_TOKEN_PERIOD_CHAR '.'
#define ARC_LEXER_TOKEN_PERIOD_TAG "PERIOD"
#define ARC_LEXER_TOKEN_FORWARD_SLASH_ID 10
#define ARC_LEXER_TOKEN_FORWARD_SLASH_CHAR '/'
#define ARC_LEXER_TOKEN_FORWARD_SLASH_TAG "FORWARD_SLASH"
#define ARC_LEXER_TOKEN_BACK_SLASH_ID 11
#define ARC_LEXER_TOKEN_BACK_SLASH_CHAR '\\'
#define ARC_LEXER_TOKEN_BACK_SLASH_TAG "BACK_SLASH"
#define ARC_LEXER_TOKEN_LEFT_PARENTHESIS_ID 12
#define ARC_LEXER_TOKEN_LEFT_PARENTHESIS_CHAR '('
#define ARC_LEXER_TOKEN_LEFT_PARENTHESIS_TAG "LEFT_PARENTHESIS"
#define ARC_LEXER_TOKEN_RIGHT_PARENTHESIS_ID 13
#define ARC_LEXER_TOKEN_RIGHT_PARENTHESIS_CHAR ')'
#define ARC_LEXER_TOKEN_RIGHT_PARENTHESIS_TAG "RIGHT_PARENTHESIS"
#define ARC_LEXER_TOKEN_LEFT_CURLY_BRACE_ID 14
#define ARC_LEXER_TOKEN_LEFT_CURLY_BRACE_CHAR '{'
#define ARC_LEXER_TOKEN_LEFT_CURLY_BRACE_TAG "LEFT_CURLY_BRACE"
#define ARC_LEXER_TOKEN_RIGHT_CURLY_BRACE_ID 15
#define ARC_LEXER_TOKEN_RIGHT_CURLY_BRACE_CHAR '}'
#define ARC_LEXER_TOKEN_RIGHT_CURLY_BRACE_TAG "RIGHT_CURLY_BRACE"
#define ARC_LEXER_TOKEN_BANG_ID 16
#define ARC_LEXER_TOKEN_BANG_CHAR '!'
#define ARC_LEXER_TOKEN_BANG_TAG "BANG"
#define ARC_LEXER_TOKEN_AT_ID 17
#define ARC_LEXER_TOKEN_AT_CHAR '!'
#define ARC_LEXER_TOKEN_AT_TAG "AT"
#define ARC_LEXER_TOKEN_HASH_ID 18
#define ARC_LEXER_TOKEN_HASH_CHAR '#'
#define ARC_LEXER_TOKEN_HASH_TAG "HASH"
#define ARC_LEXER_TOKEN_PERCENT_ID 19
#define ARC_LEXER_TOKEN_PERCENT_CHAR '%'
#define ARC_LEXER_TOKEN_PERCENT_TAG "PERCENT"
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 ));
}
ARC_TEST(Lexer_Char_Match){
ARC_Lexer *lexer;
ARC_Lexer_Create(&lexer);

571
tests/std/parser.c
View file

@ -8,315 +8,262 @@
#include <stddef.h>
#include <stdlib.h>
const uint32_t TEST_PARSER_CHAR_OR_NUM = 23;
const uint32_t TEST_PARSER_VARIABLE_NAME = 24;
const uint32_t TEST_PARSER_VARIABLE = 25;
const uint32_t TEST_PARSER_ALPHA_LOWER_CHAR = 1;
const uint32_t TEST_PARSER_ALPHA_UPPER_CHAR = 2;
const uint32_t TEST_PARSER_ALPHA_CHAR = 3;
void TEST_ParserData_CreateStringFn(void **data, ARC_ParserTagToken *parsedData, void *userData){
ARC_String_Create((ARC_String **)data, NULL, 0);
ARC_ParserData_HelperRecurseStringAdd((ARC_String **)data, parsedData);
}
void TEST_ParserData_DestroyStringFn(void *data, ARC_Bool clear, void *userData){
if(data == NULL){
return;
}
ARC_String_Destroy((ARC_String *)data);
}
uint32_t *charOrNumTokens[] = { (uint32_t[]){ 1, ARC_LEXER_TOKEN_ALPHA_LOWER_CHAR }, (uint32_t[]){ 1, ARC_LEXER_TOKEN_NUMBER } };
uint32_t *variableNameTags[] = { (uint32_t[]){ 2, TEST_PARSER_CHAR_OR_NUM, TEST_PARSER_VARIABLE_NAME }, (uint32_t[]){ 1, ARC_PARSER_TAG_LAMBDA } };
uint32_t *variableTokensOrTags[] = { (uint32_t[]){ 2, ARC_LEXER_TOKEN_ALPHA_LOWER_CHAR, TEST_PARSER_VARIABLE_NAME } };
//TODO: note how language function callbacks work, and how they use the parentData if createDataFn is NULL
ARC_ParserTag testTags[3] = {
{
TEST_PARSER_VARIABLE, //tagId
variableTokensOrTags, //tokensOrTags
1 //tokenOrTagsSize
},
{
TEST_PARSER_VARIABLE_NAME, //tagId
variableNameTags, //tokensOrTags
2 //tokenOrTagsSize
},
{
TEST_PARSER_CHAR_OR_NUM, //tagId
charOrNumTokens, //tokensOrTags
2 //tokenOrTagsSize
}
};
ARC_Array languageArray = {
3, //size
testTags //data
};
void TEST_Parser_InitLexerRulesFn(ARC_Lexer *lexer){
ARC_Lexer_InitBasicTokenRules(lexer);
}
ARC_TEST(Parser_Init){
ARC_Parser *parser;
ARC_Parser_Create(&parser, &languageArray, TEST_Parser_InitLexerRulesFn, NULL, NULL, NULL);
ARC_Parser_Destroy(parser);
ARC_CHECK(arc_errno == 0);
}
ARC_TEST(Parser_Basic_Parse){
ARC_Parser *parser;
ARC_Parser_Create(&parser, &languageArray, TEST_Parser_InitLexerRulesFn, NULL, NULL, NULL);
ARC_String *tempString;
/* ~ first test ~ */
ARC_String_CreateWithStrlen(&tempString, "myvar1");
//this destroys string, so no need for cleanup
ARC_Parser_Parse(parser, &tempString);
ARC_CHECK(arc_errno == 0);
/* ~ second test ~ */
ARC_String_CreateWithStrlen(&tempString, "z1xwvq");
//this destroys string, so no need for cleanup
ARC_Parser_Parse(parser, &tempString);
ARC_CHECK(arc_errno == 0);
/* ~ third test ~ */
ARC_String_CreateWithStrlen(&tempString, "z1234");
//this destroys string, so no need for cleanup
ARC_Parser_Parse(parser, &tempString);
ARC_CHECK(arc_errno == 0);
/* ~ fourth test ~ */
ARC_String_CreateWithStrlen(&tempString, "aaaaa");
//this destroys string, so no need for cleanup
ARC_Parser_Parse(parser, &tempString);
ARC_CHECK(arc_errno == 0);
/* ~ cleanup ~ */
ARC_Parser_Destroy(parser);
}
ARC_TEST(Parser_Basic_ParseError){
ARC_Parser *parser;
ARC_Parser_Create(&parser, &languageArray, TEST_Parser_InitLexerRulesFn, NULL, NULL, NULL);
ARC_String *tempString;
/* ~ first test ~ */
ARC_String_CreateWithStrlen(&tempString, "!myVar1");
//this destroys string, so no need for cleanup
ARC_Parser_Parse(parser, &tempString);
ARC_CHECK(arc_errno == ARC_ERRNO_DATA);
/* ~ second test ~ */
//check again with moved character
arc_errno = 0;
ARC_String_CreateWithStrlen(&tempString, "my!Var1");
//this destroys string, so no need for cleanup
ARC_Parser_Parse(parser, &tempString);
ARC_CHECK(arc_errno == ARC_ERRNO_DATA);
/* ~ third test ~ */
//check again with moved character
arc_errno = 0;
ARC_String_CreateWithStrlen(&tempString, "myVar1!");
//this destroys string, so no need for cleanup
ARC_Parser_Parse(parser, &tempString);
ARC_CHECK(arc_errno == ARC_ERRNO_DATA);
/* ~ cleanup ~ */
ARC_Parser_Destroy(parser);
//reset for next test
arc_errno = 0;
}
ARC_TEST(Parser_Basic_GetParsedValue){
ARC_Parser *parser;
ARC_ParserData_CreateFn createStringFn = TEST_ParserData_CreateStringFn;
ARC_ParserData_DestroyFn destroyStringFn = TEST_ParserData_DestroyStringFn;
ARC_Parser_Create(&parser, &languageArray, TEST_Parser_InitLexerRulesFn, &createStringFn, &destroyStringFn, NULL);
ARC_String *tempString;
/* ~ first test ~ */
ARC_String_CreateWithStrlen(&tempString, "myvar1");
//this destroys string, so no need for cleanup
ARC_Parser_Parse(parser, &tempString);
ARC_CHECK(arc_errno == 0);
ARC_String *checkValue = (ARC_String *)ARC_Parser_GetData(parser);
ARC_CHECK(ARC_String_EqualsCStringWithStrlen(checkValue, "myvar1"));
/* ~ cleanup ~ */
ARC_Parser_Destroy(parser);
}
ARC_TEST(Parser_ParserLang_BasicVector){
ARC_Vector *testLanguage;
ARC_Vector_Create(&testLanguage, NULL, NULL);
ARC_Vector_Add(testLanguage, testTags + 0);
ARC_Vector_Add(testLanguage, testTags + 1);
ARC_Vector_Add(testLanguage, testTags + 2);
ARC_Parser *parser;
ARC_Parser_CreateFromVector(&parser, testLanguage, TEST_Parser_InitLexerRulesFn, NULL, NULL, NULL);
ARC_String *tempString;
ARC_String_CreateWithStrlen(&tempString, "variablename");
//this destroys string, so no need for cleanup
ARC_Parser_Parse(parser, &tempString);
//cleanup
ARC_Parser_Destroy(parser);
ARC_Vector_Destroy(testLanguage);
ARC_CHECK(arc_errno == 0);
}
/* ~ parser tests ~ */
void TEST_Parser_InitBasicLexerTokenRules(ARC_Lexer *lexer){
//null
ARC_Lexer_RegisterTokenRule(lexer, ARC_LexerTokenRule_CreateAndReturnMatchCharRule(ARC_PARSER_TAG_LAMBDA, 0));
//alpha char
ARC_Lexer_RegisterTokenRule(lexer, ARC_LexerTokenRule_CreateAndReturnMatchCharOrBetween(TEST_PARSER_ALPHA_LOWER_CHAR, 'a', 'z'));
ARC_Lexer_RegisterTokenRule(lexer, ARC_LexerTokenRule_CreateAndReturnMatchCharOrBetween(TEST_PARSER_ALPHA_UPPER_CHAR, 'A', 'Z'));
}
uint32_t TEST_Parser_GetStringIdFn(ARC_String *string){
if(ARC_String_EqualsCStringWithStrlen(string, "<alphaChar>")){
return TEST_PARSER_ALPHA_CHAR;
}
if(ARC_String_EqualsCStringWithStrlen(string, "ALPHA_LOWER_CHAR")){
return TEST_PARSER_ALPHA_LOWER_CHAR;
}
if(ARC_String_EqualsCStringWithStrlen(string, "ALPHA_UPPER_CHAR")){
return TEST_PARSER_ALPHA_UPPER_CHAR;
}
return ~(uint32_t)0;
}
void TEST_ParserData_CreateCharFn(void **data, ARC_ParserTagToken *parsedData, void *userData){
if(parsedData == NULL){
*data = NULL;
return;
}
char *alphaChar = (char *)malloc(sizeof(char));
ARC_ParserTagToken *tagToken = (ARC_ParserTagToken *)ARC_Vector_Get(parsedData->tagTokens, 0);
*alphaChar = tagToken->token->data->data[0];
*data = (void *)alphaChar;
}
void TEST_ParserData_DestroyCharFn(void *data, ARC_Bool clear, void *userData){
if(data == NULL){
return;
}
free((char *)data);
}
ARC_TEST(Parser_Parser_BasicCreateWithStringTest){
ARC_Parser *parser;
/* ~ create the language ~ */
ARC_String *languageString;
ARC_String_CreateWithStrlen(&languageString, "<alphaChar> -> ALPHA_LOWER_CHAR | ALPHA_UPPER_CHAR\n");
ARC_ParserData_CreateFn createCharFn = TEST_ParserData_CreateCharFn;
ARC_ParserData_DestroyFn destroyCharFn = TEST_ParserData_DestroyCharFn;
ARC_Parser_CreateFromString(&parser, languageString, TEST_Parser_InitBasicLexerTokenRules, TEST_Parser_GetStringIdFn, &createCharFn, &destroyCharFn, NULL);
ARC_String_Destroy(languageString);
ARC_CHECK(arc_errno == 0);
/* ~ check if a can be parsed ~ */
ARC_String *tempString;
ARC_String_CreateWithStrlen(&tempString, "a");
ARC_Parser_Parse(parser, &tempString);
char *data = (char *)ARC_Parser_GetData(parser);
ARC_CHECK(*data == 'a');
ARC_Parser_ClearData(parser);
/* ~ check if Z can be parsed ~ */
ARC_String_CreateWithStrlen(&tempString, "Z");
ARC_Parser_Parse(parser, &tempString);
data = (char *)ARC_Parser_GetData(parser);
ARC_CHECK(*data == 'Z');
ARC_Parser_ClearData(parser);
/* ~ check if 8 errors ~ */
ARC_String_CreateWithStrlen(&tempString, "8");
ARC_Parser_Parse(parser, &tempString);
data = (char *)ARC_Parser_GetData(parser);
ARC_CHECK(arc_errno == ARC_ERRNO_DATA);
arc_errno = 0;
ARC_Parser_ClearData(parser);
//cleanup
ARC_Parser_Destroy(parser);
}
//TODO: rewrite these tests. ARC_Config does use both the parser and lexer so for now (very temporary) its tests function for these ones
//ARC_TEST(Parser_Init){
// ARC_Parser *parser;
// ARC_Parser_Create(&parser, &languageArray, TEST_Parser_InitLexerRulesFn, NULL, NULL, NULL);
//
// ARC_Parser_Destroy(parser);
//
// ARC_CHECK(arc_errno == 0);
//}
//
//ARC_TEST(Parser_Basic_Parse){
// ARC_Parser *parser;
// ARC_Parser_Create(&parser, &languageArray, TEST_Parser_InitLexerRulesFn, NULL, NULL, NULL);
//
// ARC_String *tempString;
//
//
// /* ~ first test ~ */
// ARC_String_CreateWithStrlen(&tempString, "myvar1");
//
// //this destroys string, so no need for cleanup
// ARC_Parser_Parse(parser, &tempString);
//
// ARC_CHECK(arc_errno == 0);
//
//
// /* ~ second test ~ */
// ARC_String_CreateWithStrlen(&tempString, "z1xwvq");
//
// //this destroys string, so no need for cleanup
// ARC_Parser_Parse(parser, &tempString);
//
// ARC_CHECK(arc_errno == 0);
//
//
// /* ~ third test ~ */
// ARC_String_CreateWithStrlen(&tempString, "z1234");
//
// //this destroys string, so no need for cleanup
// ARC_Parser_Parse(parser, &tempString);
//
// ARC_CHECK(arc_errno == 0);
//
//
// /* ~ fourth test ~ */
// ARC_String_CreateWithStrlen(&tempString, "aaaaa");
//
// //this destroys string, so no need for cleanup
// ARC_Parser_Parse(parser, &tempString);
//
// ARC_CHECK(arc_errno == 0);
//
//
// /* ~ cleanup ~ */
// ARC_Parser_Destroy(parser);
//}
//
//ARC_TEST(Parser_Basic_ParseError){
// ARC_Parser *parser;
// ARC_Parser_Create(&parser, &languageArray, TEST_Parser_InitLexerRulesFn, NULL, NULL, NULL);
//
// ARC_String *tempString;
//
//
// /* ~ first test ~ */
// ARC_String_CreateWithStrlen(&tempString, "!myVar1");
//
// //this destroys string, so no need for cleanup
// ARC_Parser_Parse(parser, &tempString);
//
// ARC_CHECK(arc_errno == ARC_ERRNO_DATA);
//
//
// /* ~ second test ~ */
// //check again with moved character
// arc_errno = 0;
// ARC_String_CreateWithStrlen(&tempString, "my!Var1");
//
// //this destroys string, so no need for cleanup
// ARC_Parser_Parse(parser, &tempString);
//
// ARC_CHECK(arc_errno == ARC_ERRNO_DATA);
//
//
// /* ~ third test ~ */
// //check again with moved character
// arc_errno = 0;
// ARC_String_CreateWithStrlen(&tempString, "myVar1!");
//
// //this destroys string, so no need for cleanup
// ARC_Parser_Parse(parser, &tempString);
//
// ARC_CHECK(arc_errno == ARC_ERRNO_DATA);
//
//
// /* ~ cleanup ~ */
// ARC_Parser_Destroy(parser);
//
// //reset for next test
// arc_errno = 0;
//}
//
//ARC_TEST(Parser_Basic_GetParsedValue){
// ARC_Parser *parser;
//
// ARC_ParserData_CreateFn createStringFn = TEST_ParserData_CreateStringFn;
// ARC_ParserData_DestroyFn destroyStringFn = TEST_ParserData_DestroyStringFn;
//
// ARC_Parser_Create(&parser, &languageArray, TEST_Parser_InitLexerRulesFn, &createStringFn, &destroyStringFn, NULL);
//
// ARC_String *tempString;
//
//
// /* ~ first test ~ */
// ARC_String_CreateWithStrlen(&tempString, "myvar1");
//
// //this destroys string, so no need for cleanup
// ARC_Parser_Parse(parser, &tempString);
//
// ARC_CHECK(arc_errno == 0);
//
// ARC_String *checkValue = (ARC_String *)ARC_Parser_GetData(parser);
// ARC_CHECK(ARC_String_EqualsCStringWithStrlen(checkValue, "myvar1"));
//
//
// /* ~ cleanup ~ */
// ARC_Parser_Destroy(parser);
//}
//
//ARC_TEST(Parser_ParserLang_BasicVector){
// ARC_Vector *testLanguage;
// ARC_Vector_Create(&testLanguage, NULL, NULL);
//
// ARC_Vector_Add(testLanguage, testTags + 0);
// ARC_Vector_Add(testLanguage, testTags + 1);
// ARC_Vector_Add(testLanguage, testTags + 2);
//
// ARC_Parser *parser;
// ARC_Parser_CreateFromVector(&parser, testLanguage, TEST_Parser_InitLexerRulesFn, NULL, NULL, NULL);
//
// ARC_String *tempString;
// ARC_String_CreateWithStrlen(&tempString, "variablename");
//
// //this destroys string, so no need for cleanup
// ARC_Parser_Parse(parser, &tempString);
//
// //cleanup
// ARC_Parser_Destroy(parser);
// ARC_Vector_Destroy(testLanguage);
//
// ARC_CHECK(arc_errno == 0);
//}
//
///* ~ parser tests ~ */
//void TEST_Parser_InitBasicLexerTokenRules(ARC_Lexer *lexer){
// //null
// ARC_Lexer_RegisterTokenRule(lexer, ARC_LexerTokenRule_CreateAndReturnMatchCharRule(ARC_PARSER_TAG_LAMBDA, 0));
//
// //alpha char
// ARC_Lexer_RegisterTokenRule(lexer, ARC_LexerTokenRule_CreateAndReturnMatchCharOrBetween(TEST_PARSER_ALPHA_LOWER_CHAR, 'a', 'z'));
// ARC_Lexer_RegisterTokenRule(lexer, ARC_LexerTokenRule_CreateAndReturnMatchCharOrBetween(TEST_PARSER_ALPHA_UPPER_CHAR, 'A', 'Z'));
//}
//
//uint32_t TEST_Parser_GetStringIdFn(ARC_String *string){
// if(ARC_String_EqualsCStringWithStrlen(string, "<alphaChar>")){
// return TEST_PARSER_ALPHA_CHAR;
// }
//
// if(ARC_String_EqualsCStringWithStrlen(string, "ALPHA_LOWER_CHAR")){
// return TEST_PARSER_ALPHA_LOWER_CHAR;
// }
//
// if(ARC_String_EqualsCStringWithStrlen(string, "ALPHA_UPPER_CHAR")){
// return TEST_PARSER_ALPHA_UPPER_CHAR;
// }
//
// return ~(uint32_t)0;
//}
//
//void TEST_ParserData_CreateCharFn(void **data, ARC_ParserTagToken *parsedData, void *userData){
// if(parsedData == NULL){
// *data = NULL;
// return;
// }
//
// char *alphaChar = (char *)malloc(sizeof(char));
//
// ARC_ParserTagToken *tagToken = (ARC_ParserTagToken *)ARC_Vector_Get(parsedData->tagTokens, 0);
// *alphaChar = tagToken->token->data->data[0];
//
// *data = (void *)alphaChar;
//}
//
//void TEST_ParserData_DestroyCharFn(void *data, ARC_Bool clear, void *userData){
// if(data == NULL){
// return;
// }
//
// free((char *)data);
//}
//
//ARC_TEST(Parser_Parser_BasicCreateWithStringTest){
// ARC_Parser *parser;
//
// /* ~ create the language ~ */
// ARC_String *languageString;
// ARC_String_CreateWithStrlen(&languageString, "<alphaChar> -> ALPHA_LOWER_CHAR | ALPHA_UPPER_CHAR\n");
//
// ARC_ParserData_CreateFn createCharFn = TEST_ParserData_CreateCharFn;
// ARC_ParserData_DestroyFn destroyCharFn = TEST_ParserData_DestroyCharFn;
// ARC_Parser_CreateFromString(&parser, languageString, TEST_Parser_InitBasicLexerTokenRules, TEST_Parser_GetStringIdFn, &createCharFn, &destroyCharFn, NULL);
//
// ARC_String_Destroy(languageString);
//
// ARC_CHECK(arc_errno == 0);
//
//
// /* ~ check if a can be parsed ~ */
// ARC_String *tempString;
// ARC_String_CreateWithStrlen(&tempString, "a");
//
// ARC_Parser_Parse(parser, &tempString);
//
// char *data = (char *)ARC_Parser_GetData(parser);
//
// ARC_CHECK(*data == 'a');
//
// ARC_Parser_ClearData(parser);
//
//
// /* ~ check if Z can be parsed ~ */
// ARC_String_CreateWithStrlen(&tempString, "Z");
//
// ARC_Parser_Parse(parser, &tempString);
//
// data = (char *)ARC_Parser_GetData(parser);
//
// ARC_CHECK(*data == 'Z');
//
// ARC_Parser_ClearData(parser);
//
//
// /* ~ check if 8 errors ~ */
// ARC_String_CreateWithStrlen(&tempString, "8");
//
// ARC_Parser_Parse(parser, &tempString);
//
// data = (char *)ARC_Parser_GetData(parser);
//
// ARC_CHECK(arc_errno == ARC_ERRNO_DATA);
// arc_errno = 0;
//
// ARC_Parser_ClearData(parser);
//
//
// //cleanup
// ARC_Parser_Destroy(parser);
//}