basic vector complete but untested, added destroy callback to vector
This commit is contained in:
herbglitch
parent
6e814f12e6
commit
4c0c5d377d
4 changed files with 445 additions and 97 deletions
|
|
@ -9,35 +9,6 @@ extern "C" {
|
|||
#include "arc/std/string.h"
|
||||
#include <stdint.h>
|
||||
|
||||
/**
|
||||
* @brief
|
||||
*/
|
||||
typedef enum ARC_Lexer_BasicTokens {
|
||||
LEXER_TOKEN_LAMBDA = 0,
|
||||
LEXER_TOKEN_COLON = ':',
|
||||
LEXER_TOKEN_SEMICOLON = ';',
|
||||
LEXER_TOKEN_COMMA = ',',
|
||||
LEXER_TOKEN_PERIOD = '.',
|
||||
LEXER_TOKEN_FORWARD_SLASH = '/',
|
||||
LEXER_TOKEN_BACK_SLASH = '\\',
|
||||
LEXER_TOKEN_LEFT_PARENTHESIS = '(',
|
||||
LEXER_TOKEN_RIGHT_PARENTHESIS = ')',
|
||||
LEXER_TOKEN_LEFT_CURLY_BRACE = '{',
|
||||
LEXER_TOKEN_RIGHT_CURLY_BRACE = '}',
|
||||
} ARC_Lexer_BasicTokens;
|
||||
|
||||
/**
|
||||
* @brief checks to see if a string is a type of token
|
||||
*
|
||||
* @param[in/out] string a string to be checked to see if it matches a token,
|
||||
* this needs to srip the token out for the lexer to avoid an infinite loop
|
||||
* @param[out] tokenData a place to store token data (like a variable name), can be NULL if not needed
|
||||
* @param[in] automataData any data that needs to be used for the ARC_Lexer_AutomataFn
|
||||
*
|
||||
* @return if a token was successfully found ARC_True, otherwise ARC_False
|
||||
*/
|
||||
typedef ARC_Bool (* ARC_Lexer_AutomataFn)(ARC_String **string, ARC_String **tokenData, void *automataData);
|
||||
|
||||
/**
|
||||
* @brief a lexer type
|
||||
*/
|
||||
|
|
@ -47,46 +18,110 @@ typedef struct ARC_Lexer ARC_Lexer;
|
|||
* @brief a lexer token type
|
||||
*/
|
||||
typedef struct ARC_LexerToken {
|
||||
uint32_t id;
|
||||
|
||||
ARC_Lexer_AutomataFn automataFn;
|
||||
void *automataData;
|
||||
//TODO: automataData free callback
|
||||
uint32_t rule;
|
||||
ARC_String *data;
|
||||
} ARC_LexerToken;
|
||||
|
||||
/**
|
||||
* @brief
|
||||
* @brief checks to see if a string is a type of token
|
||||
*
|
||||
* @note do not set tokenData if this function returns ARC_False, doing so will create a memory leak
|
||||
*
|
||||
* @param[in/out] string a string to be checked to see if it matches a token,
|
||||
* this needs to srip the token out for the lexer to avoid an infinite loop
|
||||
* @param[out] tokenData a place to store token data (like a variable name), can be NULL if not needed
|
||||
* @param[in] automataData any data that needs to be used for the ARC_Lexer_AutomataFn
|
||||
*
|
||||
* @return if a token was successfully found ARC_True, otherwise ARC_False
|
||||
*/
|
||||
typedef ARC_Bool (* ARC_LexerTokenRule_AutomataFn)(ARC_String **string, ARC_String **tokenData, void *automataData);
|
||||
|
||||
/**
|
||||
* @brief a callback function to clean up ARC_LexerTokenRule's automataData
|
||||
*
|
||||
* @param automataData the void * automataData to destroy
|
||||
*/
|
||||
typedef void (* ARC_LexerTokenRule_DestroyAutomataDataFn)(void *automataData);
|
||||
|
||||
|
||||
/**
|
||||
* @brief a lexer token rule type
|
||||
*/
|
||||
typedef struct ARC_LexerTokenRule {
|
||||
uint32_t id;
|
||||
|
||||
void *automataData;
|
||||
|
||||
ARC_LexerTokenRule_AutomataFn automataFn;
|
||||
ARC_LexerTokenRule_DestroyAutomataDataFn destroyAutomataDataFn;
|
||||
} ARC_LexerTokenRule;
|
||||
|
||||
/**
|
||||
* @brief creates an ARC_Lexer type
|
||||
*
|
||||
* @param[out] lexer
|
||||
*/
|
||||
void ARC_Lexer_Create(ARC_Lexer **lexer);
|
||||
|
||||
/**
|
||||
* @brief
|
||||
* @brief destroys an ARC_Lexer type
|
||||
*
|
||||
* @param[in] lexer ARC_Lexer to free
|
||||
*/
|
||||
void ARC_Lexer_Destroy(ARC_Lexer *lexer);
|
||||
|
||||
/**
|
||||
* @brief
|
||||
* @brief adds a token rule to a lexer
|
||||
*
|
||||
* @param [in] lexer
|
||||
* @param [in] token
|
||||
* @param [in] lexer the lexer to add a token rule to
|
||||
* @param [in] tokenRule the token rule to add
|
||||
*/
|
||||
void ARC_Lexer_RegisterToken(ARC_Lexer *lexer, ARC_LexerToken token);
|
||||
void ARC_Lexer_RegisterTokenRule(ARC_Lexer *lexer, ARC_LexerTokenRule tokenRule);
|
||||
|
||||
/**
|
||||
* @brief
|
||||
* @brief creates tokens using a given string with ARC_LexerToken rules
|
||||
*
|
||||
* @param[in] lexer
|
||||
* @param[in] path
|
||||
* @param[in] lexer the lexer to get the ARC_LexerTokens from
|
||||
* @param[in/out] data the string to lex, will be freed and set to NULL by the end of this function
|
||||
*/
|
||||
void ARC_Lexer_LexString(ARC_Lexer *lexer, ARC_String **data);
|
||||
|
||||
/**
|
||||
* @brief reads in and lexs a file
|
||||
*
|
||||
* @note this function will call ARC_Lexer_LexString, so it's notes are applicable to this function
|
||||
*
|
||||
* @param[in] lexer the lexer which holds to rules to use
|
||||
* @param[in] path path of file to read in and lex
|
||||
*/
|
||||
void ARC_Lexer_LexFile(ARC_Lexer *lexer, ARC_String *path);
|
||||
|
||||
/**
|
||||
* @brief gets a token at a given index from a lexer
|
||||
*
|
||||
* @note unless you have a very good reason, you probably don't want to mess with the tokens string.
|
||||
* that will probably change the token's string inside the lexer
|
||||
*
|
||||
* @param[in] lexer the lexer to get the token from
|
||||
* @param[in] index the index of the token in the lexer to get
|
||||
*
|
||||
* @return a copy of the token, or a token with max value for rule and NULL for data on error
|
||||
*/
|
||||
ARC_LexerToken ARC_Lexer_GetToken(ARC_Lexer *lexer, uint32_t index);
|
||||
|
||||
/**
|
||||
* @brief gets a token at a given index from a lexer
|
||||
*
|
||||
* @param[in] lexer the lexer to get the tokens size from
|
||||
*
|
||||
* @return the size of the token array in a lexer
|
||||
*/
|
||||
uint32_t ARC_Lexer_GetTokensSize(ARC_Lexer *lexer);
|
||||
|
||||
/**
|
||||
* @brief checks if the first character of string matches the automataData cast as a char
|
||||
*
|
||||
* @note this is intended as a helper callback
|
||||
* @note this function is a ARC_Lexer_AutomataFn callback
|
||||
*
|
||||
* @param[in/out] string a string to be checked to see if it matches a token,
|
||||
|
|
@ -101,6 +136,7 @@ ARC_Bool ARC_Lexer_AutomataMatchCharFn(ARC_String **string, ARC_String **tokenDa
|
|||
/**
|
||||
* @brief checks if the substring automataData as an ARC_String matches the first part of string
|
||||
*
|
||||
* @note this is intended as a helper callback
|
||||
* @note this function is a ARC_Lexer_AutomataFn callback
|
||||
*
|
||||
* @param[in/out] string a string to be checked to see if it matches a token,
|
||||
|
|
@ -112,6 +148,81 @@ ARC_Bool ARC_Lexer_AutomataMatchCharFn(ARC_String **string, ARC_String **tokenDa
|
|||
*/
|
||||
ARC_Bool ARC_Lexer_AutomataMatchStringFn(ARC_String **string, ARC_String **tokenData, void *automataData);
|
||||
|
||||
/**
|
||||
* @brief creates a ARC_LexerTokenRule with a given id and character
|
||||
*
|
||||
* @note this is intended as a helper funtion
|
||||
*
|
||||
* @param[in] id a tokens id (basically the token value)
|
||||
* @param[in] character the character to match against
|
||||
*
|
||||
* @return a token rule based in the id and character
|
||||
*/
|
||||
ARC_LexerTokenRule ARC_LexerTokenRule_CreateAndReturnMatchCharRule(uint32_t id, char character);
|
||||
|
||||
/**
|
||||
* @brief creates a ARC_LexerTokenRule with a given id and string
|
||||
*
|
||||
* @note this is intended as a helper funtion
|
||||
* #note string will not be freed (it will be copied and the copy will be freed)
|
||||
*
|
||||
* @param[in] id a tokens id (basically the token value)
|
||||
* @param[in] character the string to match against, will be copied
|
||||
*
|
||||
* @return a token rule based in the id and string
|
||||
*/
|
||||
ARC_LexerTokenRule ARC_LexerTokenRule_CreateAndReturnMatchStringRule(uint32_t id, ARC_String *string);
|
||||
|
||||
/**
|
||||
* @brief basic token type ids, chars, and tags
|
||||
*/
|
||||
#define LEXER_TOKEN_COLON_ID 1
|
||||
#define LEXER_TOKEN_COLON_CHAR ':'
|
||||
#define LEXER_TOKEN_COLON_TAG "COLON"
|
||||
#define LEXER_TOKEN_SEMICOLON_ID 2
|
||||
#define LEXER_TOKEN_SEMICOLON_CHAR ';'
|
||||
#define LEXER_TOKEN_SEMICOLON_TAG "SEMICOLON"
|
||||
#define LEXER_TOKEN_COMMA_ID 3
|
||||
#define LEXER_TOKEN_COMMA_CHAR ','
|
||||
#define LEXER_TOKEN_COMMA_TAG "COMMA"
|
||||
#define LEXER_TOKEN_PERIOD_ID 4
|
||||
#define LEXER_TOKEN_PERIOD_CHAR '.'
|
||||
#define LEXER_TOKEN_PERIOD_TAG "PERIOD"
|
||||
#define LEXER_TOKEN_FORWARD_SLASH_ID 5
|
||||
#define LEXER_TOKEN_FORWARD_SLASH_CHAR '/'
|
||||
#define LEXER_TOKEN_FORWARD_SLASH_TAG "FORWARD_SLASH"
|
||||
#define LEXER_TOKEN_BACK_SLASH_ID 6
|
||||
#define LEXER_TOKEN_BACK_SLASH_CHAR '\\'
|
||||
#define LEXER_TOKEN_BACK_SLASH_TAG "BACK_SLASH"
|
||||
#define LEXER_TOKEN_LEFT_PARENTHESIS_ID 7
|
||||
#define LEXER_TOKEN_LEFT_PARENTHESIS_CHAR '('
|
||||
#define LEXER_TOKEN_LEFT_PARENTHESIS_TAG "LEFT_PARENTHESIS"
|
||||
#define LEXER_TOKEN_RIGHT_PARENTHESIS_ID 8
|
||||
#define LEXER_TOKEN_RIGHT_PARENTHESIS_CHAR ')'
|
||||
#define LEXER_TOKEN_RIGHT_PARENTHESIS_TAG "RIGHT_PARENTHESIS"
|
||||
#define LEXER_TOKEN_LEFT_CURLY_BRACE_ID 9
|
||||
#define LEXER_TOKEN_LEFT_CURLY_BRACE_CHAR '{'
|
||||
#define LEXER_TOKEN_LEFT_CURLY_BRACE_TAG "LEFT_CURLY_BRACE"
|
||||
#define LEXER_TOKEN_RIGHT_CURLY_BRACE_ID 10
|
||||
#define LEXER_TOKEN_RIGHT_CURLY_BRACE_CHAR '}'
|
||||
#define LEXER_TOKEN_RIGHT_CURLY_BRACE_TAG "RIGHT_CURLY_BRACE"
|
||||
#define LEXER_TOKEN_BANG_ID 11
|
||||
#define LEXER_TOKEN_BANG_CHAR '!'
|
||||
#define LEXER_TOKEN_BANG_TAG "BANG"
|
||||
#define LEXER_TOKEN_AT_ID 12
|
||||
#define LEXER_TOKEN_AT_CHAR '!'
|
||||
#define LEXER_TOKEN_AT_TAG "AT"
|
||||
#define LEXER_TOKEN_HASH_ID 13
|
||||
#define LEXER_TOKEN_HASH_CHAR '#'
|
||||
#define LEXER_TOKEN_HASH_TAG "HASH"
|
||||
#define LEXER_TOKEN_PERCENT_ID 14
|
||||
#define LEXER_TOKEN_PERCENT_CHAR '%'
|
||||
#define 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
|
||||
}
|
||||
|
|
|
|||
|
|
@ -26,9 +26,9 @@ typedef ARC_Bool (* ARC_Vector_CompareDataFn)(void *dataA, void *dataB);
|
|||
/**
|
||||
* @brief a callback that cleans up memory when it is removed from the vector
|
||||
*
|
||||
* @param[in] data the item to delete
|
||||
* @param[in] data the item to destroy
|
||||
*/
|
||||
typedef void (* ARC_Vector_DeleteDataFn)(void *data);
|
||||
typedef void (* ARC_Vector_DestroyDataFn)(void *data);
|
||||
|
||||
/**
|
||||
* @brief creates an ARC_Vector which is an "expandable" array
|
||||
|
|
@ -39,9 +39,9 @@ typedef void (* ARC_Vector_DeleteDataFn)(void *data);
|
|||
* @param[out] vector ARC_Vector to initialize
|
||||
* @param[in] compareDataFn a callback that checks if data stored in the array matches,
|
||||
* if set to NULL and ARC_Vector_Remove is called, the pointer addresses will be compared
|
||||
* @param[in] deleteDataFn a callback that frees an item on remove or clear, can be set to NULL to do nothing
|
||||
* @param[in] destroyDataFn a callback that frees an item on remove or clear, can be set to NULL to do nothing
|
||||
*/
|
||||
void ARC_Vector_Create(ARC_Vector **vector, ARC_Vector_CompareDataFn *compareDataFn, ARC_Vector_DeleteDataFn *deleteDataFn);
|
||||
void ARC_Vector_Create(ARC_Vector **vector, ARC_Vector_CompareDataFn *compareDataFn, ARC_Vector_DestroyDataFn *destroyDataFn);
|
||||
|
||||
/**
|
||||
* @brief destroys an ARC_Vector
|
||||
|
|
@ -86,6 +86,15 @@ void ARC_Vector_Remove(ARC_Vector *vector, void *data);
|
|||
*/
|
||||
void ARC_Vector_RemoveIndex(ARC_Vector *vector, uint32_t index);
|
||||
|
||||
/**
|
||||
* @brief clears all items from a vector
|
||||
*
|
||||
* @note this function will call ARC_Vector_RemoveIndex, so it's notes are also applicable to this function
|
||||
*
|
||||
* @param[in] vector ARC_Vector to clear
|
||||
*/
|
||||
void ARC_Vector_Clear(ARC_Vector *vector);
|
||||
|
||||
/**
|
||||
* @brief gets the current size of an ARC_Vector as an unsigned 32 bit integer
|
||||
*
|
||||
|
|
|
|||
298
src/std/lexer.c
298
src/std/lexer.c
|
|
@ -1,73 +1,293 @@
|
|||
#include "arc/std/lexer.h"
|
||||
|
||||
#include "arc/std/bool.h"
|
||||
#include "arc/std/errno.h"
|
||||
#include "arc/std/string.h"
|
||||
#include "arc/std/vector.h"
|
||||
#include "arc/std/io.h"
|
||||
#include <stdlib.h>
|
||||
|
||||
struct ARC_Lexer {
|
||||
ARC_Vector *tokenRules;
|
||||
ARC_Vector *tokens;
|
||||
};
|
||||
|
||||
void ARC_Lexer_Create(ARC_Lexer **lexer){
|
||||
*lexer = (ARC_Lexer *)malloc(sizeof(ARC_Lexer));
|
||||
//private function for checking if two lexer token rules are the same in a vector (based on id)
|
||||
ARC_Bool ARC_LexerTokenRule_VectorCompareDataFn(void *dataA, void *dataB){
|
||||
ARC_LexerTokenRule *tokenRuleA = (ARC_LexerTokenRule *)dataA;
|
||||
ARC_LexerTokenRule *tokenRuleB = (ARC_LexerTokenRule *)dataB;
|
||||
|
||||
//TODO: add compare and delete callbacks
|
||||
ARC_Vector_Create(&(*lexer)->tokens, NULL, NULL);
|
||||
}
|
||||
|
||||
void ARC_Lexer_Destroy(ARC_Lexer *lexer){
|
||||
ARC_Vector_Destroy(lexer->tokens);
|
||||
|
||||
free(lexer);
|
||||
}
|
||||
|
||||
void ARC_Lexer_RegisterToken(ARC_Lexer *lexer, ARC_LexerToken token){
|
||||
ARC_LexerToken *storedToken = (ARC_LexerToken *)malloc(sizeof(ARC_LexerToken));
|
||||
*storedToken = token;
|
||||
ARC_Vector_Add(lexer->tokens, storedToken);
|
||||
}
|
||||
|
||||
void ARC_Lexer_LexFile(ARC_Lexer *lexer, ARC_String *path){
|
||||
ARC_String *data;
|
||||
ARC_IO_FileToStr(path, &data);
|
||||
|
||||
|
||||
if(data != NULL){
|
||||
ARC_String_Destroy(data);
|
||||
}
|
||||
}
|
||||
|
||||
ARC_Bool ARC_Lexer_AutomataMatchCharFn(ARC_String **string, ARC_String **tokenData, void *automataData){
|
||||
*tokenData = NULL;
|
||||
|
||||
if((*string)->data[0] == *(char *)automataData){
|
||||
if((*string)->length == 1){
|
||||
ARC_String_Destroy(*string);
|
||||
*string = NULL;
|
||||
}
|
||||
|
||||
ARC_String_ReplaceWithSubstring(string, 1, (*string)->length - 1);
|
||||
if(tokenRuleA->id == tokenRuleB->id){
|
||||
return ARC_True;
|
||||
}
|
||||
|
||||
return ARC_False;
|
||||
}
|
||||
|
||||
ARC_Bool ARC_Lexer_AutomataMatchStringFn(ARC_String **string, ARC_String **tokenData, void *automataData){
|
||||
//private function for destroying a lexer token rule from a vector
|
||||
void ARC_LexerTokenRule_VectorDestroyDataFn(void *data){
|
||||
ARC_LexerTokenRule *tokenRule = (ARC_LexerTokenRule *)data;
|
||||
tokenRule->destroyAutomataDataFn(tokenRule->automataData);
|
||||
free(tokenRule);
|
||||
}
|
||||
|
||||
|
||||
//private function for destroying a lexer token from a vector
|
||||
void ARC_LexerToken_VectorDestroyDataFn(void *data){
|
||||
ARC_LexerToken *token = (ARC_LexerToken *)data;
|
||||
free(token);
|
||||
}
|
||||
|
||||
void ARC_Lexer_Create(ARC_Lexer **lexer){
|
||||
//create the lexer
|
||||
*lexer = (ARC_Lexer *)malloc(sizeof(ARC_Lexer));
|
||||
|
||||
//setup token rules vector with compare and delete functions
|
||||
ARC_Vector_CompareDataFn tokenRulesVectorCompareDataFn = ARC_LexerTokenRule_VectorCompareDataFn;
|
||||
ARC_Vector_DestroyDataFn tokenRulesVectorDestroyDataFn = ARC_LexerTokenRule_VectorDestroyDataFn;
|
||||
ARC_Vector_Create(&(*lexer)->tokenRules, &tokenRulesVectorCompareDataFn, &tokenRulesVectorDestroyDataFn);
|
||||
|
||||
//setup tokens vector with delete funtion, we don't want a deleteDataFn because their index will be used as the id
|
||||
ARC_Vector_DestroyDataFn tokenVectorDestroyDataFn = ARC_LexerToken_VectorDestroyDataFn;
|
||||
ARC_Vector_Create(&(*lexer)->tokens, NULL, &tokenVectorDestroyDataFn);
|
||||
}
|
||||
|
||||
void ARC_Lexer_Destroy(ARC_Lexer *lexer){
|
||||
//free the tokens (there is a vectorDeleteDataFn, so tokens should be freed)
|
||||
ARC_Vector_Destroy(lexer->tokens);
|
||||
|
||||
//free the token rules (there is a vectorDeleteDataFn, so token rules should be freed)
|
||||
ARC_Vector_Destroy(lexer->tokenRules);
|
||||
|
||||
//free the lexer
|
||||
free(lexer);
|
||||
}
|
||||
|
||||
void ARC_Lexer_RegisterTokenRule(ARC_Lexer *lexer, ARC_LexerTokenRule tokenRule){
|
||||
//copy the token to a new pointer
|
||||
ARC_LexerTokenRule *storedTokenRule = (ARC_LexerTokenRule *)malloc(sizeof(ARC_LexerTokenRule));
|
||||
*storedTokenRule = tokenRule;
|
||||
|
||||
//add to the vector and check for error (I'd be surprised if the error ever happened because that would most likely mean overflow)
|
||||
ARC_Vector_Add(lexer->tokenRules, storedTokenRule);
|
||||
if(arc_errno){
|
||||
ARC_DEBUG_LOG_ERROR("ARC_Lexer_RegisterTokenRule(lexer, tokenRule), errored when running ARC_Vector_Add(lexer->tokenRules, storedTokenRule);. check logs for more info");
|
||||
free(storedTokenRule);
|
||||
}
|
||||
}
|
||||
|
||||
void ARC_Lexer_LexString(ARC_Lexer *lexer, ARC_String **data){
|
||||
//check if there are any token rules to use
|
||||
if(ARC_Vector_GetSize(lexer->tokenRules) == 0){
|
||||
arc_errno = ARC_ERRNO_DATA;
|
||||
ARC_DEBUG_LOG_ERROR("ARC_Lexer_LexString(lexer, data), no tokens registered to lexer to use");
|
||||
return;
|
||||
}
|
||||
|
||||
//this will run untill everything token is stripped or there is an error
|
||||
while(data != NULL){
|
||||
ARC_Bool tokenFound = ARC_False;
|
||||
for(uint32_t index = 0; index < ARC_Vector_GetSize(lexer->tokenRules); index++){
|
||||
//check if the token rule is found
|
||||
ARC_LexerTokenRule *tokenRule = ARC_Vector_Get(lexer->tokenRules, index);
|
||||
|
||||
//tokenData should only exist if tokenFound is ARC_True as stated in the header
|
||||
ARC_String *tokenData;
|
||||
tokenFound = tokenRule->automataFn(data, &tokenData, tokenRule->automataData);
|
||||
|
||||
//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(tokenFound != ARC_True){
|
||||
continue;
|
||||
}
|
||||
|
||||
//create the token to add
|
||||
ARC_LexerToken *token = (ARC_LexerToken *)malloc(sizeof(ARC_LexerToken));
|
||||
token->rule = tokenRule->id;
|
||||
token->data = tokenData;
|
||||
|
||||
//add to the vector and check for error (I'd be surprised if the error ever happened because that would most likely mean overflow)
|
||||
ARC_Vector_Add(lexer->tokens, token);
|
||||
if(arc_errno){
|
||||
ARC_DEBUG_LOG_ERROR("ARC_Lexer_LexString(lexer, data), errored when running ARC_Vector_Add(lexer->tokens, token);. check logs for more info");
|
||||
free(token);
|
||||
|
||||
//clean up errored string
|
||||
ARC_String_Destroy(*data);
|
||||
*data = NULL;
|
||||
return;
|
||||
}
|
||||
|
||||
//the token was added, so break to start checking tokens again
|
||||
break;
|
||||
}
|
||||
|
||||
//if no token was found, throw an error
|
||||
if(tokenFound == ARC_False){
|
||||
arc_errno = ARC_ERRNO_DATA;
|
||||
ARC_DEBUG_LOG_ERROR_WITH_VARIABLES("ARC_Lexer_LexString(lexer, data), no tokens found with current string: \"%s\"", (*data)->data);
|
||||
|
||||
//clean up errored string
|
||||
ARC_String_Destroy(*data);
|
||||
*data = NULL;
|
||||
|
||||
//TODO: might want to do smthn with already tokened data
|
||||
return;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
void ARC_Lexer_LexFile(ARC_Lexer *lexer, ARC_String *path){
|
||||
//read file and clean up if it errors
|
||||
ARC_String *data;
|
||||
ARC_IO_FileToStr(path, &data);
|
||||
if(arc_errno){
|
||||
ARC_DEBUG_LOG_ERROR("ARC_Lexer_LexFile(lexer, path), errored when running ARC_IO_FileToStr(path, &data);. check logs for more info");
|
||||
if(data != NULL){
|
||||
ARC_String_Destroy(data);
|
||||
}
|
||||
|
||||
return;
|
||||
}
|
||||
|
||||
//lex the string and log if there is an error, ARC_Lexer_LexString will clean up the string
|
||||
ARC_Lexer_LexString(lexer, &data);
|
||||
if(arc_errno){
|
||||
ARC_DEBUG_LOG_ERROR("ARC_Lexer_LexFile(lexer, path), errored when running ARC_Lexer_LexString(lexer, data);. check logs for more info");
|
||||
}
|
||||
}
|
||||
|
||||
ARC_LexerToken ARC_Lexer_GetToken(ARC_Lexer *lexer, uint32_t index){
|
||||
//get the token and log if there is an error
|
||||
ARC_LexerToken *token = ARC_Vector_Get(lexer->tokens, index);
|
||||
if(arc_errno){
|
||||
ARC_DEBUG_LOG_ERROR("ARC_Lexer_GetToken(lexer, index), errored when running ARC_Vector_Get(lexer->tokens, index);. check logs for more info");
|
||||
|
||||
//return a token with max rule value, and NULL for the string to signify an error
|
||||
return (ARC_LexerToken){
|
||||
~(uint32_t)0,
|
||||
NULL
|
||||
};
|
||||
}
|
||||
|
||||
//the token was found, so return a copy to that
|
||||
return *token;
|
||||
}
|
||||
|
||||
uint32_t ARC_Lexer_GetTokensSize(ARC_Lexer *lexer){
|
||||
return ARC_Vector_GetSize(lexer->tokens);
|
||||
}
|
||||
|
||||
ARC_Bool ARC_Lexer_AutomataMatchCharFn(ARC_String **string, ARC_String **tokenData, void *automataData){
|
||||
//if there is a match the token will be the same as automataData, so we don't need to store it again
|
||||
*tokenData = NULL;
|
||||
|
||||
//check to see if there is a match with automataData as a char
|
||||
if((*string)->data[0] == *(char *)automataData){
|
||||
//to keep from erroring instead of stripping from a 1 character string we can just delete it
|
||||
if((*string)->length == 1){
|
||||
ARC_String_Destroy(*string);
|
||||
*string = NULL;
|
||||
return ARC_True;
|
||||
}
|
||||
|
||||
//strip the charater from the front of the string and return that a match was found
|
||||
ARC_String_ReplaceWithSubstring(string, 1, (*string)->length - 1);
|
||||
return ARC_True;
|
||||
}
|
||||
|
||||
//no match was found
|
||||
return ARC_False;
|
||||
}
|
||||
|
||||
ARC_Bool ARC_Lexer_AutomataMatchStringFn(ARC_String **string, ARC_String **tokenData, void *automataData){
|
||||
//if there is a match the token will be the same as automataData, so we don't need to store it again
|
||||
*tokenData = NULL;
|
||||
|
||||
//check to see if there is a match with automataData as a string
|
||||
ARC_String *automataDataString = (ARC_String *)automataData;
|
||||
//to keep from erroring instead of stripping from a same length string we can just delete it
|
||||
if(ARC_String_Equals(*string, automataDataString)){
|
||||
if((*string)->length == automataDataString->length){
|
||||
ARC_String_Destroy(*string);
|
||||
*string = NULL;
|
||||
}
|
||||
|
||||
//strip the token string from the front of the string and return that a match was found
|
||||
ARC_String_ReplaceWithSubstring(string, automataDataString->length, (*string)->length - automataDataString->length);
|
||||
return ARC_True;
|
||||
}
|
||||
|
||||
//no match was found
|
||||
return ARC_False;
|
||||
}
|
||||
|
||||
//private function to free automataData stored as a char
|
||||
void ARC_LexerTokenRule_DestroyCharAutomataDataFn(void *automataData){
|
||||
free((char *)automataData);
|
||||
}
|
||||
|
||||
ARC_LexerTokenRule ARC_LexerTokenRule_CreateAndReturnMatchCharRule(uint32_t id, char character){
|
||||
//create the token rule
|
||||
ARC_LexerTokenRule tokenRule;
|
||||
|
||||
//set the id
|
||||
tokenRule.id = id;
|
||||
|
||||
//create and store the automataData (which is just a char)
|
||||
char *automataData = (char *)malloc(sizeof(char));
|
||||
*automataData = character;
|
||||
tokenRule.automataData = (void *)automataData;
|
||||
|
||||
//we can use the ARC_Lexer_AutomataMatchCharFn for this
|
||||
tokenRule.automataFn = ARC_Lexer_AutomataMatchCharFn;
|
||||
|
||||
//add the private destroy function
|
||||
tokenRule.destroyAutomataDataFn = ARC_LexerTokenRule_DestroyCharAutomataDataFn;
|
||||
|
||||
//return the created tokenRule
|
||||
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;
|
||||
|
||||
//set the id
|
||||
tokenRule.id = id;
|
||||
|
||||
//copy and store the automataData (which is just an ARC_String)
|
||||
ARC_String *automataData;
|
||||
ARC_String_Copy(&automataData, string);
|
||||
tokenRule.automataData = (void *)automataData;
|
||||
|
||||
//we can use the ARC_Lexer_AutomataMatchCharFn for this
|
||||
tokenRule.automataFn = ARC_Lexer_AutomataMatchCharFn;
|
||||
|
||||
//add the private destroy function
|
||||
tokenRule.destroyAutomataDataFn = ARC_LexerTokenRule_DestroyStringAutomataDataFn;
|
||||
|
||||
//return the created tokenRule
|
||||
return tokenRule;
|
||||
}
|
||||
|
||||
void ARC_Lexer_InitBasicTokenRules(ARC_Lexer *lexer){
|
||||
ARC_Lexer_RegisterTokenRule(lexer, ARC_LexerTokenRule_CreateAndReturnMatchCharRule(LEXER_TOKEN_COLON_ID , LEXER_TOKEN_COLON_CHAR ));
|
||||
ARC_Lexer_RegisterTokenRule(lexer, ARC_LexerTokenRule_CreateAndReturnMatchCharRule(LEXER_TOKEN_SEMICOLON_ID , LEXER_TOKEN_SEMICOLON_CHAR ));
|
||||
ARC_Lexer_RegisterTokenRule(lexer, ARC_LexerTokenRule_CreateAndReturnMatchCharRule(LEXER_TOKEN_COMMA_ID , LEXER_TOKEN_COMMA_CHAR ));
|
||||
ARC_Lexer_RegisterTokenRule(lexer, ARC_LexerTokenRule_CreateAndReturnMatchCharRule(LEXER_TOKEN_PERIOD_ID , LEXER_TOKEN_PERIOD_CHAR ));
|
||||
ARC_Lexer_RegisterTokenRule(lexer, ARC_LexerTokenRule_CreateAndReturnMatchCharRule(LEXER_TOKEN_FORWARD_SLASH_ID , LEXER_TOKEN_FORWARD_SLASH_CHAR ));
|
||||
ARC_Lexer_RegisterTokenRule(lexer, ARC_LexerTokenRule_CreateAndReturnMatchCharRule(LEXER_TOKEN_BACK_SLASH_ID , LEXER_TOKEN_BACK_SLASH_CHAR ));
|
||||
ARC_Lexer_RegisterTokenRule(lexer, ARC_LexerTokenRule_CreateAndReturnMatchCharRule(LEXER_TOKEN_LEFT_PARENTHESIS_ID , LEXER_TOKEN_LEFT_PARENTHESIS_CHAR ));
|
||||
ARC_Lexer_RegisterTokenRule(lexer, ARC_LexerTokenRule_CreateAndReturnMatchCharRule(LEXER_TOKEN_RIGHT_PARENTHESIS_ID, LEXER_TOKEN_RIGHT_PARENTHESIS_CHAR));
|
||||
ARC_Lexer_RegisterTokenRule(lexer, ARC_LexerTokenRule_CreateAndReturnMatchCharRule(LEXER_TOKEN_LEFT_CURLY_BRACE_ID , LEXER_TOKEN_LEFT_CURLY_BRACE_CHAR ));
|
||||
ARC_Lexer_RegisterTokenRule(lexer, ARC_LexerTokenRule_CreateAndReturnMatchCharRule(LEXER_TOKEN_RIGHT_CURLY_BRACE_ID, LEXER_TOKEN_RIGHT_CURLY_BRACE_CHAR));
|
||||
ARC_Lexer_RegisterTokenRule(lexer, ARC_LexerTokenRule_CreateAndReturnMatchCharRule(LEXER_TOKEN_BANG_ID , LEXER_TOKEN_BANG_CHAR ));
|
||||
ARC_Lexer_RegisterTokenRule(lexer, ARC_LexerTokenRule_CreateAndReturnMatchCharRule(LEXER_TOKEN_AT_ID , LEXER_TOKEN_AT_CHAR ));
|
||||
ARC_Lexer_RegisterTokenRule(lexer, ARC_LexerTokenRule_CreateAndReturnMatchCharRule(LEXER_TOKEN_HASH_ID , LEXER_TOKEN_HASH_CHAR ));
|
||||
ARC_Lexer_RegisterTokenRule(lexer, ARC_LexerTokenRule_CreateAndReturnMatchCharRule(LEXER_TOKEN_PERCENT_ID , LEXER_TOKEN_PERCENT_CHAR ));
|
||||
}
|
||||
|
|
|
|||
|
|
@ -13,7 +13,7 @@ struct ARC_Vector {
|
|||
void **data;
|
||||
|
||||
ARC_Vector_CompareDataFn compareDataFn;
|
||||
ARC_Vector_DeleteDataFn *deleteDataFn;
|
||||
ARC_Vector_DestroyDataFn *destroyDataFn;
|
||||
};
|
||||
|
||||
//this is a private function used as the default check for removing data from a given pointer
|
||||
|
|
@ -25,7 +25,7 @@ ARC_Bool ARC_Vector_CompareDataDefaultFn(void *dataA, void *dataB){
|
|||
return ARC_False;
|
||||
}
|
||||
|
||||
void ARC_Vector_Create(ARC_Vector **vector, ARC_Vector_CompareDataFn *compareDataFn, ARC_Vector_DeleteDataFn *deleteDataFn){
|
||||
void ARC_Vector_Create(ARC_Vector **vector, ARC_Vector_CompareDataFn *compareDataFn, ARC_Vector_DestroyDataFn *destroyDataFn){
|
||||
//create the vector
|
||||
*vector = (ARC_Vector *)malloc(sizeof(ARC_Vector));
|
||||
|
||||
|
|
@ -41,19 +41,20 @@ void ARC_Vector_Create(ARC_Vector **vector, ARC_Vector_CompareDataFn *compareDat
|
|||
}
|
||||
|
||||
//set NULL as a default for deleteDataFn, then copy the delete data function callback if it exists
|
||||
(*vector)->deleteDataFn = NULL;
|
||||
if(deleteDataFn != NULL){
|
||||
(*vector)->deleteDataFn = (ARC_Vector_DeleteDataFn *)malloc(sizeof(ARC_Vector_DeleteDataFn));
|
||||
*((*vector)->deleteDataFn) = *deleteDataFn;
|
||||
(*vector)->destroyDataFn = NULL;
|
||||
if(destroyDataFn != NULL){
|
||||
(*vector)->destroyDataFn = (ARC_Vector_DestroyDataFn *)malloc(sizeof(ARC_Vector_DestroyDataFn));
|
||||
*((*vector)->destroyDataFn) = *destroyDataFn;
|
||||
}
|
||||
}
|
||||
|
||||
void ARC_Vector_Destroy(ARC_Vector *vector){
|
||||
//TODO: clear vector before destroying
|
||||
//remove all the contents before destroying the vector
|
||||
ARC_Vector_Clear(vector);
|
||||
|
||||
//free the delete data function if it exists
|
||||
if(vector->deleteDataFn){
|
||||
free(vector->deleteDataFn);
|
||||
if(vector->destroyDataFn){
|
||||
free(vector->destroyDataFn);
|
||||
}
|
||||
|
||||
//free everything stored in the vector
|
||||
|
|
@ -112,8 +113,8 @@ void ARC_Vector_RemoveIndex(ARC_Vector *vector, uint32_t index){
|
|||
}
|
||||
|
||||
//call delete data to clean up item if delete data function exists
|
||||
if(vector->deleteDataFn != NULL){
|
||||
(*(vector->deleteDataFn))(vector->data[index]);
|
||||
if(vector->destroyDataFn != NULL){
|
||||
(*(vector->destroyDataFn))(vector->data[index]);
|
||||
}
|
||||
|
||||
//we will be using index to iterate as we will not use it again, so we can skip the first part of the for loop
|
||||
|
|
@ -135,6 +136,13 @@ void ARC_Vector_RemoveIndex(ARC_Vector *vector, uint32_t index){
|
|||
vector->data = (void **)realloc(vector->data, sizeof(void *) * vector->currentCapacity);
|
||||
}
|
||||
|
||||
void ARC_Vector_Clear(ARC_Vector *vector){
|
||||
//remove each item in the vector untill the vector is empty
|
||||
while(ARC_Vector_GetSize(vector) != 0){
|
||||
ARC_Vector_RemoveIndex(vector, 0);
|
||||
}
|
||||
}
|
||||
|
||||
uint32_t ARC_Vector_GetSize(ARC_Vector *vector){
|
||||
return vector->currentSize;
|
||||
}
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue