The Scanner has been refactored and some responsibilities were pulled from it. Confirmed working, the Parser still needs to be touched on however.
This commit is contained in:
@@ -1,32 +1,5 @@
|
||||
#include "scanner.h"
|
||||
#include <stdio.h>
|
||||
#include <stdlib.h>
|
||||
#include <string.h>
|
||||
#include <ctype.h>
|
||||
|
||||
typedef struct {
|
||||
char* keyword;
|
||||
TokenType type;
|
||||
} KeywordPair;
|
||||
|
||||
KeywordPair keywords[KEYWORD_COUNT] = {
|
||||
{ "and", AND },
|
||||
{ "class", CLASS },
|
||||
{ "else", ELSE },
|
||||
{ "false", FALSE },
|
||||
{ "for", FOR },
|
||||
{ "fun", FUN },
|
||||
{ "if", IF },
|
||||
{ "nil", NIL },
|
||||
{ "or", OR },
|
||||
{ "print", PRINT },
|
||||
{ "return", RETURN },
|
||||
{ "super", SUPER },
|
||||
{ "this", THIS },
|
||||
{ "true", TRUE },
|
||||
{ "var", VAR },
|
||||
{ "while", WHILE }
|
||||
};
|
||||
#include "token.h"
|
||||
|
||||
const char* source_code;
|
||||
//Start and Current hold the offsets that index into the string source_code.
|
||||
@@ -39,7 +12,7 @@ const char* SAdvance(void);
|
||||
int SIsAtEnd(void);
|
||||
void ScanToken(TokenList*);
|
||||
TokenList* CreateList(void);
|
||||
int AddTokenToList(TokenType, const char*, int, TokenList*);
|
||||
int AddToTokenList(Token*, TokenList*);
|
||||
int SMatch(char);
|
||||
char SPeek(void);
|
||||
char PeekNext(void);
|
||||
@@ -47,7 +20,7 @@ void ParseString(TokenList *);
|
||||
void ParseNumber(TokenList *);
|
||||
void ParseIdentifier(TokenList *);
|
||||
int IsAlpha(char c);
|
||||
KeywordPair* Get(char*);
|
||||
KeyValuePair* Get(const char*);
|
||||
|
||||
TokenList* ScanTokens(const char* source) {
|
||||
if (!source) return NULL;
|
||||
@@ -64,8 +37,7 @@ TokenList* ScanTokens(const char* source) {
|
||||
ScanToken(tokens);
|
||||
}
|
||||
|
||||
//Add EOF token and return list once that's set up.
|
||||
AddTokenToList(EndOF, NULL, 0, tokens);
|
||||
AddToTokenList(CreateToken(NULL, line, EndOF), tokens);
|
||||
|
||||
return tokens;
|
||||
}
|
||||
@@ -96,7 +68,10 @@ void DestroyTokenList(TokenList* list) {
|
||||
if (!list) return;
|
||||
|
||||
for(int i = 0; i < list->size; i++) {
|
||||
//free(list->tokens[i]->lexeme); This shouldn't be needed since the lexeme is a pointer into the source code.
|
||||
//Only free objects that required allocation, i.e. not in the TokenTypeMappings
|
||||
if (list->tokens[i]->type == String || list->tokens[i]->type == Number || list->tokens[i]->type == Identifier)
|
||||
free((void *) list->tokens[i]->lexeme);
|
||||
|
||||
free(list->tokens[i]);
|
||||
}
|
||||
|
||||
@@ -104,34 +79,24 @@ void DestroyTokenList(TokenList* list) {
|
||||
free(list);
|
||||
}
|
||||
|
||||
int AddTokenToList(TokenType type, const char* lexeme, int length, TokenList* tokens) {
|
||||
if (!tokens) return 0;
|
||||
Token* token = calloc(1, sizeof(Token));
|
||||
int AddToTokenList(Token* token, TokenList* list) {
|
||||
if (!list) return 0;
|
||||
if (!token) return 0;
|
||||
|
||||
if (!token) {
|
||||
fprintf(stderr, "Failed to calloc memory for new Token.\n");
|
||||
return 0;
|
||||
}
|
||||
|
||||
token->lexeme = lexeme;
|
||||
token->type = type;
|
||||
token->length = length; //Set the length of the lexeme (which is just a pointer into the complete source listing).
|
||||
token->line = line;
|
||||
|
||||
if ((tokens->size + 1) > tokens->capacity) {
|
||||
void* new_ptr = realloc(tokens->tokens, sizeof(Token*) * tokens->capacity * 2);
|
||||
if ((list->size + 1) > list->capacity) {
|
||||
void* new_ptr = realloc(list->tokens, sizeof(Token*) * list->capacity * 2);
|
||||
|
||||
if (!new_ptr) {
|
||||
fprintf(stderr, "Failed to realloc TokenList to size %d.\n", tokens->capacity * 2);
|
||||
fprintf(stderr, "Failed to realloc TokenList to size %d.\n", list->capacity * 2);
|
||||
return 0;
|
||||
}
|
||||
|
||||
tokens->tokens = new_ptr;
|
||||
tokens->capacity = tokens->capacity * 2;
|
||||
list->tokens = new_ptr;
|
||||
list->capacity = list->capacity * 2;
|
||||
}
|
||||
|
||||
tokens->tokens[tokens->size] = token;
|
||||
tokens->size++;
|
||||
list->tokens[list->size] = token;
|
||||
list->size++;
|
||||
|
||||
return 1;
|
||||
}
|
||||
@@ -141,58 +106,55 @@ void ScanToken(TokenList* tokens) {
|
||||
|
||||
switch (*c) {
|
||||
case '(':
|
||||
AddTokenToList(LParen, c, 1, tokens);
|
||||
AddToTokenList(CreateToken(NULL, line, LParen), tokens);
|
||||
break;
|
||||
case ')':
|
||||
AddTokenToList(RParen, c, 1, tokens);
|
||||
AddToTokenList(CreateToken(NULL, line, LParen), tokens);
|
||||
break;
|
||||
case '{':
|
||||
AddTokenToList(LBrace, c, 1, tokens);
|
||||
AddToTokenList(CreateToken(NULL, line, LParen), tokens);
|
||||
break;
|
||||
case '}':
|
||||
AddTokenToList(RBrace, c, 1, tokens);
|
||||
AddToTokenList(CreateToken(NULL, line, RParen), tokens);
|
||||
break;
|
||||
case ',':
|
||||
AddTokenToList(Comma, c, 1, tokens);
|
||||
AddToTokenList(CreateToken(NULL, line, Comma), tokens);
|
||||
break;
|
||||
case '.':
|
||||
AddTokenToList(Dot, c, 1, tokens);
|
||||
AddToTokenList(CreateToken(NULL, line, Dot), tokens);
|
||||
break;
|
||||
case '-':
|
||||
AddTokenToList(Minus, c, 1, tokens);
|
||||
AddToTokenList(CreateToken(NULL, line, Minus), tokens);
|
||||
break;
|
||||
case '+':
|
||||
AddTokenToList(Plus, c, 1, tokens);
|
||||
AddToTokenList(CreateToken(NULL, line, Plus), tokens);
|
||||
break;
|
||||
case ';':
|
||||
AddTokenToList(Semicolon, c, 1, tokens);
|
||||
AddToTokenList(CreateToken(NULL, line, Semicolon), tokens);
|
||||
break;
|
||||
case '*':
|
||||
AddTokenToList(Star, c, 1, tokens);
|
||||
AddToTokenList(CreateToken(NULL, line, Star), tokens);
|
||||
break;
|
||||
case '!':
|
||||
if (SMatch('=')) AddTokenToList(Bang_Equal, "!=", 2, tokens);
|
||||
else AddTokenToList(Bang, c, 1, tokens);
|
||||
if (SMatch('=')) AddToTokenList(CreateToken(NULL, line, Bang_Equal), tokens);
|
||||
else AddToTokenList(CreateToken(NULL, line, Bang), tokens);
|
||||
break;
|
||||
case '=':
|
||||
if (SMatch('=')) AddTokenToList(Equal_Equal, "==", 2, tokens);
|
||||
else AddTokenToList(Equal, c, 1, tokens);
|
||||
if (SMatch('=')) AddToTokenList(CreateToken(NULL, line, Equal_Equal), tokens);
|
||||
else AddToTokenList(CreateToken(NULL, line, Equal), tokens);
|
||||
break;
|
||||
case '<':
|
||||
if (SMatch('=')) AddTokenToList(Less_Equal, "<=", 2, tokens);
|
||||
else AddTokenToList(Less, c, 1, tokens);
|
||||
if (SMatch('=')) AddToTokenList(CreateToken(NULL, line, Less_Equal), tokens);
|
||||
else AddToTokenList(CreateToken(NULL, line, Less), tokens);
|
||||
break;
|
||||
case '>':
|
||||
if (SMatch('=')) AddTokenToList(Greater_Equal, ">=", 2, tokens);
|
||||
else AddTokenToList(Greater, c, 1, tokens);
|
||||
if (SMatch('=')) AddToTokenList(CreateToken(NULL, line, Greater_Equal), tokens);
|
||||
else AddToTokenList(CreateToken(NULL, line, Greater), tokens);
|
||||
break;
|
||||
case '/':
|
||||
if (SMatch('/')) {
|
||||
while(SPeek() != '\n' && !SIsAtEnd()) SAdvance();
|
||||
}
|
||||
else {
|
||||
AddTokenToList(Slash, c, 1, tokens);
|
||||
}
|
||||
if (SMatch('/')) while(SPeek() != '\n' && !SIsAtEnd()) { SAdvance(); }
|
||||
else AddToTokenList(CreateToken(NULL, line, Slash), tokens);
|
||||
|
||||
break;
|
||||
case '"':
|
||||
ParseString(tokens);
|
||||
@@ -254,7 +216,16 @@ void ParseString(TokenList *list) {
|
||||
return;
|
||||
}
|
||||
|
||||
AddTokenToList(String, &source_code[start], current - start, list);
|
||||
char* lexeme = calloc(current - start + 1, sizeof(char));
|
||||
|
||||
if (!lexeme) {
|
||||
fprintf(stderr, "Failed to calloc for string lexeme. %s\n", strerror(errno));
|
||||
return;
|
||||
}
|
||||
|
||||
snprintf(lexeme, current - start, "%s", &source_code[start]);
|
||||
|
||||
AddToTokenList(CreateToken(lexeme, line, String), list);
|
||||
|
||||
SAdvance(); // The closing ".
|
||||
}
|
||||
@@ -268,7 +239,16 @@ void ParseNumber(TokenList* list) {
|
||||
while(isdigit(SPeek())) SAdvance();
|
||||
}
|
||||
|
||||
AddTokenToList(Number, &source_code[start], current - start, list);
|
||||
char* lexeme = calloc(current - start + 2, sizeof(char));
|
||||
|
||||
if (!lexeme) {
|
||||
fprintf(stderr, "Failed to calloc for number lexeme. %s\n", strerror(errno));
|
||||
return;
|
||||
}
|
||||
|
||||
snprintf(lexeme, current - start + 1, "%s", &source_code[start]);
|
||||
|
||||
AddToTokenList(CreateToken(lexeme, line, Number), list);
|
||||
}
|
||||
|
||||
char PeekNext() {
|
||||
@@ -280,16 +260,18 @@ char PeekNext() {
|
||||
void ParseIdentifier(TokenList * list) {
|
||||
while(IsAlpha(SPeek())) SAdvance();
|
||||
|
||||
char* lexeme = calloc(sizeof(char*), (current - start + 1));
|
||||
char* lexeme = calloc(current - start + 2, sizeof(char));
|
||||
|
||||
snprintf(lexeme, current - start + 1, "%s", &source_code[start]);
|
||||
printf("%s\n", lexeme);
|
||||
KeyValuePair* result = Get(lexeme);
|
||||
|
||||
KeywordPair* result = Get(lexeme);
|
||||
if (result) {
|
||||
free(lexeme);
|
||||
|
||||
if (result) AddTokenToList(result->type, &source_code[start], current - start, list);
|
||||
else AddTokenToList(Identifier, &source_code[start], current - start, list);
|
||||
|
||||
free(lexeme);
|
||||
AddToTokenList(CreateToken(NULL, line, result->type), list);
|
||||
}
|
||||
else AddToTokenList(CreateToken(lexeme, line, Identifier), list);
|
||||
}
|
||||
|
||||
int IsAlpha(char c) {
|
||||
@@ -298,11 +280,11 @@ int IsAlpha(char c) {
|
||||
(c == '_');
|
||||
}
|
||||
|
||||
KeywordPair* Get(char* text) {
|
||||
KeyValuePair* Get(const char* text) {
|
||||
if (!text) return NULL;
|
||||
|
||||
for (int i = 0; i < KEYWORD_COUNT; i++)
|
||||
if (strcmp(text, keywords[i].keyword) == 0) return &keywords[i];
|
||||
|
||||
for (int i = 0; i < TOKENTYPE_MAPPINGS_COUNT; i++)
|
||||
if (strcmp(text, TokenTypeMappings[i].lexeme) == 0) return &TokenTypeMappings[i];
|
||||
|
||||
return NULL;
|
||||
}
|
||||
Reference in New Issue
Block a user