Merge pull request 'refactor-lexer' (#11) from refactor-lexer into main

Reviewed-on: #11

.gitignore

@@ -9,6 +9,7 @@ out/Release/
 
 # Cmake files
 CMakeCache.txt
+cmake
 CMakeFiles/
 cmake_install.cmake
 CTestTestfile.cmake

CMakeLists.txt

@@ -3,16 +3,8 @@ project(calculator VERSION 1.0 LANGUAGES C)
 
 set(CMAKE_C_STANDARD 11)
 set(CMAKE_C_STANDARD_REQUIRED ON)
-include(FetchContent)
 
-FetchContent_Declare(
-    arena
-    GIT_REPOSITORY https://laentropia-homelab.tail7368da.ts.net/laentropia/Arena.git
-    GIT_TAG main
-    SOURCE_DIR ${CMAKE_SOURCE_DIR}/external/arena
-)
-
-# Export compile_commands.json (para clangd)
+# clangd
 set(CMAKE_EXPORT_COMPILE_COMMANDS ON)
 
 add_compile_options(
@@ -21,22 +13,24 @@ add_compile_options(
     -Wpedantic
 )
 
+include(cmake/CPM.cmake)
 
-FetchContent_MakeAvailable(arena)
-
-add_library(arena STATIC
-    external/arena/src/arena.c
+CPMAddPackage(
+    NAME arena
+    GIT_REPOSITORY https://laentropia-homelab.tail7368da.ts.net/laentropia/Arena.git
+    GIT_TAG main
 )
 
-target_include_directories(arena
-    PUBLIC ${CMAKE_SOURCE_DIR}/external/arena/include
+CPMAddPackage(
+    NAME arraylist
+    GIT_REPOSITORY https://laentropia-homelab.tail7368da.ts.net/laentropia/ArrayList.git
+    GIT_TAG main
 )
 
 add_library(calculator_lib
     src/lexer.c
     src/parser.c
     src/evaluator.c
-    src/ASTNodeArray.c
 )
 
 target_include_directories(calculator_lib
@@ -45,16 +39,11 @@ target_include_directories(calculator_lib
 
 target_link_libraries(calculator_lib
     PUBLIC arena
+    PUBLIC arraylist
 )
 
 add_executable(calculator src/main.c)
-
 target_link_libraries(calculator calculator_lib)
 
-# ------------------------
-# Testing
-# ------------------------
-
 enable_testing()
 add_subdirectory(test)
-

include/lexer.h

@@ -1,6 +1,7 @@
 #ifndef LEXER_H
 #define LEXER_H
 
+#include "arraylist.h"
 #include <stddef.h>
 #include <stdbool.h>
 #include <stdint.h>
@@ -9,6 +10,8 @@
 typedef enum {
     NODE_INTEGER,
     NODE_BINARY_OP,
+    NODE_UNARY_OP,
+    NODE_PARENTHESIS,
 } ASTNodeType;
 
 // For classify operators
@@ -16,26 +19,19 @@ typedef enum {
     OP_ADD,
     OP_SUB,
     OP_MUL,
-    OP_DIV
+    OP_DIV,
+    OP_POW,
+    OP_FACTORIAL,
+    OP_START_PAR,
+    OP_END_PAR,
 } Operator;
 
-typedef enum {
-    ARRAY_OK = 0,
-    ARRAY_NULL,
-    ARRAY_EMPTY,
-    ARRAY_OUT_OF_BOUNDS,
-    ARRAY_NULL_ARG,
-    ARRAY_ALLOC,
-} ASTNodeArrayErr;
-
 typedef enum {
     LEXER_OK = 0,
     LEXER_INT_OVERFLOW,
     LEXER_FAILED_NUMBER_CONVERSION,
     LEXER_NOT_RECOGNIZED_SYMBOL,
     LEXER_EMPTY_INPUT,
-    LEXER_NULL_ARG,
-    LEXER_WRONG_SYNTAX,
     LEXER_BUF_OVERFLOW,
 } LexerErr;
 
@@ -49,28 +45,45 @@ typedef struct ASTNode {
             struct ASTNode *right;
             Operator op;
         } binary;
+        struct {
+            struct ASTNode *val;
+            Operator op;
+        } unary;
+        struct {
+            struct ASTNode *val;
+            Operator op;
+        } parenthesis;
     } data;
 } ASTNode;
 
-// I prefer ot have a dynamic array for storing the "tokens"
 typedef struct {
-    size_t len;
-    size_t cap;
-    ASTNode *data;
-} ASTNodeArray;
+    bool is_valid;
+    union {
+        LexerErr err;
+        ArrayList *arr;
+    };
+} TokenizeResult;
 
-ASTNodeArray ASTNodeArray_init(size_t size);
-void ASTNodeArray_free(ASTNodeArray *arr);
-ASTNodeArrayErr ASTNodeArray_push(ASTNodeArray *arr, ASTNode node);
-ASTNodeArrayErr ASTNodeArray_get(const ASTNodeArray *arr, size_t index, ASTNode *out);
-// Out in pop can be NULL so it doesn't return anything
-ASTNodeArrayErr ASTNodeArray_pop(ASTNodeArray *arr, size_t index, ASTNode *out);
-size_t ASTNodeArray_len(ASTNodeArray *arr);
+typedef struct {
+    bool is_valid;
+    union {
+        LexerErr err;
+        ASTNode node;
+    };
+} ASTNodeResult;
+
+typedef struct {
+    bool is_valid;
+    union {
+        LexerErr err;
+        int64_t number;
+    };
+} LexerI64Result;
 
 // Lexer funtions as well as few functionality
-LexerErr tokenize(const char* input, ASTNodeArray *out);
-LexerErr tokenize_number(const char* input, size_t *offset, ASTNode *out);
-LexerErr string_to_integer(const char buf[], int64_t *number);
+TokenizeResult tokenize(const char* input);
+ASTNodeResult tokenize_number(const char* input, size_t *offset);
+LexerI64Result string_to_integer(const char buf[]);
 bool isoperator(int c);
 Operator char_to_operator(int c);
 char operator_to_char(Operator op);

include/parser.h

@@ -3,33 +3,41 @@
 
 #include "lexer.h"
 #include "arena.h"
+#include "arraylist.h"
 #include <stdint.h>
 
 typedef struct {
     ASTNode *head;
 } AST;
 
-typedef struct {
-    ASTNodeArray *arr;
-    size_t pos;
-} ASTNodeSlice;
+typedef enum {
+    PARSER_OK = 0,
+    PARSER_UNEXPECTED_TOKEN,
+    PARSER_MISSING_OPERAND,
+    PARSER_UNMATCHED_PAREN,
+    PARSER_OUT_OF_MEMORY,
+} ParserErr;
 
 typedef struct {
+    bool is_valid;
+    union {
+        ParserErr err;
+        struct {
             Arena arena;
             ASTNode *tree;
+        };
+    };
 } ParseResult;
 
-ASTNode ASTNodeSlice_peek(ASTNodeSlice *slice);
-ASTNode ASTNodeSlice_next(ASTNodeSlice *slice);
-bool ASTNodeSlice_is_valid(ASTNodeSlice *slice);
+ASTNode *nud(ArraySlice *slice);
+ASTNode *led(ArraySlice *slice, size_t right_precedence);
 
-ASTNode *nud(ASTNodeSlice *slice);
-ASTNode *led(ASTNodeSlice *slice, size_t right_precedence);
+uint8_t prefix_rbp(ASTNode node);
+uint8_t postfix_lbp(ASTNode node);
+uint8_t infix_lbp(ASTNode node);
+uint8_t infix_rbp(ASTNode node);
 
-uint8_t node_lbp(ASTNode node);
-uint8_t node_rbp(ASTNode node);
-
-ParseResult parse(ASTNodeArray *arr);
-ASTNode *parse_expr(ASTNodeSlice *slice, Arena *arena, uint8_t min_bp);
+ParseResult parse(TokenizeResult tokens);
+ASTNode *parse_expr(ArraySlice *slice, Arena *arena, uint8_t min_bp);
 
 #endif // !PARSER_H

src/ASTNodeArray.c

@@ -1,108 +0,0 @@
-#include "lexer.h"
-#include <stdlib.h>
-
-#define NODE_ARRAY_DEFAULT_SIZE 64
-// Helps  state machine for the lexer :)
-typedef enum {
-    WAIT_FOR_NUMBER,
-    WAIT_FOR_OPERATOR,
-} LexerState;
-
-ASTNodeArray ASTNodeArray_init(size_t size) {
-    ASTNodeArray new;
-    new.len = 0;      // if 0 then use default
-    new.cap = size == 0 ? NODE_ARRAY_DEFAULT_SIZE : size;
-    new.data = malloc(new.cap * sizeof(ASTNode));
-    return new;
-}
-
-void ASTNodeArray_free(ASTNodeArray *arr) {
-    free(arr->data);
-    arr->cap = 0;
-    arr->len = 0;
-}
-
-ASTNodeArrayErr ASTNodeArray_get(const ASTNodeArray *arr, size_t index, ASTNode *out) {
-    if (arr == NULL) {
-        return ARRAY_NULL;
-    }
-
-    if (out == NULL) {
-        return ARRAY_NULL_ARG;
-    }
-
-    if (arr->len == 0) {
-        return ARRAY_EMPTY;
-    }
-
-    if (index >= arr->len) {
-        return ARRAY_OUT_OF_BOUNDS;
-    }
-
-    *out = arr->data[index];
-
-    return ARRAY_OK;
-}
-
-ASTNodeArrayErr ASTNodeArray_push(ASTNodeArray *arr, ASTNode node) {
-    if (arr == NULL) {
-        return ARRAY_NULL;
-    }
-
-    if (arr->len >= arr->cap) {
-        size_t new_cap = arr->cap * 2;
-        ASTNode *tmp = realloc(arr->data, new_cap * sizeof(ASTNode));
-        if (tmp == NULL) {
-            return ARRAY_ALLOC;
-        }
-        arr->data = tmp;
-        arr->cap = new_cap;
-    }
-
-    arr->data[arr->len] = node;
-    arr->len = arr->len + 1;
-
-    return ARRAY_OK;
-}
-
-ASTNodeArrayErr ASTNodeArray_pop(ASTNodeArray *arr, size_t index, ASTNode *out) {
-    if (arr == NULL) {
-        return ARRAY_NULL;
-    }
-
-    if (arr->len == 0) {
-        return ARRAY_EMPTY;
-    }
-
-    if (index >= arr->len) {
-        return ARRAY_OUT_OF_BOUNDS;
-    }
-
-    if (arr->cap / 4 > arr->len) {
-        size_t new_cap = arr->cap / 2;
-        ASTNode *tmp = realloc(arr->data, new_cap * sizeof(ASTNode));
-        if (tmp == NULL) {
-            return ARRAY_ALLOC;
-        }
-        arr->data = tmp;
-        arr->cap = new_cap;
-    }
-    
-    if (out != NULL) {
-        ASTNode node_to_delete = arr->data[index];
-        *out = node_to_delete;
-    }
-
-    for (size_t i = index; i < arr->len - 1; i++) {
-        arr->data[index] = arr->data[index + 1];
-    }
-
-    return ARRAY_OK;
-}
-
-size_t ASTNodeArray_len(ASTNodeArray *arr) {
-    if (arr == NULL) {
-        return 0;
-    }
-    return arr->len;
-}

src/evaluator.c

@@ -3,6 +3,7 @@
 #include "lexer.h"
 #include "parser.h"
 #include <stdint.h>
+#include <math.h>
 
 
 int64_t evaluate_tree(ASTNode *tree) {
@@ -20,7 +21,8 @@ int64_t evaluate_tree(ASTNode *tree) {
                 return evaluate_tree(left) * evaluate_tree(right);
             case OP_DIV:
                 return evaluate_tree(left) / evaluate_tree(right);
-
+            case OP_POW:
+                return pow(evaluate_tree(left), evaluate_tree(right));
         }
     }
 

src/lexer.c

@@ -1,7 +1,9 @@
 #include "lexer.h"
+#include "arraylist.h"
 #include <ctype.h>
-#include <math.h>
+#include <stdbool.h>
 #include <stdint.h>
+#include <stdio.h>
 #include <stdlib.h>
 #include <strings.h>
 #include <limits.h>
@@ -12,74 +14,68 @@ typedef enum {
 } LexerState;
 
 
-LexerErr tokenize(const char *input, ASTNodeArray *out) {
+TokenizeResult tokenize(const char *input) {
+    ArrayList *arr = arraylist_init(64, sizeof(ASTNode));
     size_t offset = 0;
-    LexerState state = WAIT_FOR_NUMBER;
-    ASTNodeArray arr = ASTNodeArray_init(0); // 0 defaults to 64
 
-    while (input[offset] != '\n' && input[offset] != '\0') {
-        int current = input[offset];
+    while (
+        input[offset] != '\n' ||
+        input[offset] != EOF ||
+        input[offset] != '\0') {
 
-        if (isdigit(current)) {
-            if (state != WAIT_FOR_NUMBER) {
-                ASTNodeArray_free(&arr);
-                return LEXER_WRONG_SYNTAX;
-            }
-            ASTNode new_node;
-            LexerErr result = tokenize_number(input, &offset, &new_node);
+        if (isdigit(input[offset])) {
+            ASTNodeResult result = tokenize_number(input, &offset);
 
-            if (result != LEXER_OK) {
-                ASTNodeArray_free(&arr);
-                return result;
+            if (!result.is_valid) {
+                return (TokenizeResult) {.is_valid = false, .err = result.err};
             }
 
-            ASTNodeArray_push(&arr, new_node);
-            state = WAIT_FOR_OPERATOR;
-        } else if (isoperator(current)) {
-            if (state != WAIT_FOR_OPERATOR) {
-                return LEXER_WRONG_SYNTAX;
-            }
-            ASTNode new_node = {
+            arraylist_push_back(arr, &result.node);
+        } else if (isoperator(input[offset])) {
+            ASTNode op_node = {
                 .type = NODE_BINARY_OP,
-                .data.binary.op = char_to_operator(current),
-                .data.binary.right = NULL,
+                .data.binary.op = char_to_operator(input[offset]),
                 .data.binary.left = NULL,
+                .data.binary.right = NULL,
             };
             
-            ASTNodeArray_push(&arr, new_node);
-            state = WAIT_FOR_NUMBER;
-        } else if (isspace(current)) {
+            arraylist_push_back(arr, &op_node);
+        } else if (isspace(input[offset])) {
             // Nothing...
         } else {
-            ASTNodeArray_free(&arr);
-            return LEXER_NOT_RECOGNIZED_SYMBOL;
+            return (TokenizeResult) {
+                .is_valid = false,
+                .err = LEXER_NOT_RECOGNIZED_SYMBOL};
         }
 
         offset++;
     }
 
-    if (arr.len < 1) {
-        return LEXER_EMPTY_INPUT;
+    if (arraylist_size(arr) < 1) {
+        return (TokenizeResult) {.is_valid = false, .err = LEXER_EMPTY_INPUT};
     }
 
-    *out = arr;
-    return LEXER_OK;
+    return (TokenizeResult) {.is_valid = true, .arr = arr};
 }
 
 // CURRENTLY, it only supports ints, not clear how floating
 // point is implemented but i'll figure it out
-LexerErr tokenize_number(const char *input, size_t *offset, ASTNode *out) {
-    char buf[128] = { '\0' };
+ASTNodeResult tokenize_number(const char *input, size_t *offset) {
+    char buf[64] = { '\0' };
     size_t buf_pos = 0;
     bool is_integer = true; // Will later be used to differentiate fractions
 
+    // read number
     size_t current = *offset;
     while (isdigit(input[current])) {
         buf[buf_pos] = input[current];
         
         if (buf_pos >= sizeof(buf)) {
-            return LEXER_BUF_OVERFLOW;
+            return (ASTNodeResult) {
+                .is_valid = false,
+                .err = LEXER_BUF_OVERFLOW};
         }
+
         current++;
         buf_pos++;
     }
@@ -87,35 +83,46 @@ LexerErr tokenize_number(const char *input, size_t *offset, ASTNode *out) {
     ASTNode new_node;
     if (is_integer) {
         new_node.type = NODE_INTEGER;
-        LexerErr status = string_to_integer(buf, &new_node.data.integer);
-        if (status == LEXER_OK) {
-            *out = new_node;
+        LexerI64Result status = string_to_integer(buf);
+
+
+        if (!status.is_valid) {
+            return (ASTNodeResult) {.is_valid = false, .err = status.err};
         }
+
+        new_node.data.integer = status.number;
+
         *offset = current;
-        return status;
+        return (ASTNodeResult) {.is_valid = true, .node = new_node};
     }
 
-    return LEXER_FAILED_NUMBER_CONVERSION;
+    return (ASTNodeResult) {
+        .is_valid = false,
+        .err = LEXER_FAILED_NUMBER_CONVERSION};
 }
 
-LexerErr string_to_integer(const char *buf, int64_t *number) {
+LexerI64Result string_to_integer(const char *buf) {
     int c = 0;
     int64_t count = 0;
+
     while (buf[c] != '\0') {
 
+        // Extracts number from char
         int digit = buf[c] - '0';
 
         if (count > (INT64_MAX - digit) / 10) {
-            return LEXER_INT_OVERFLOW;
+            return (LexerI64Result) {
+                .is_valid = false,
+                .err = LEXER_INT_OVERFLOW};
         }
+
         count = count * 10;
         count += digit;
         
         c++;
     }
 
-    *number = count;
-    return LEXER_OK;
+    return (LexerI64Result) {.is_valid = true, .number = count};
 }
 
 bool isoperator(int c) {
@@ -124,6 +131,10 @@ bool isoperator(int c) {
         case '-':
         case '/':
         case '*':
+        case '^':
+        case '!':
+        case '(':
+        case ')':
             return true;
         default:
             return false;
@@ -144,6 +155,18 @@ Operator char_to_operator(int c) {
         case '/':
             return OP_DIV;
             break;
+        case '^':
+            return OP_POW;
+            break;
+        case '!':
+            return OP_FACTORIAL;
+            break;
+        case '(':
+            return OP_START_PAR;
+            break;
+        case ')':
+            return OP_END_PAR;
+            break;
         default: // I mean shouldn't be used, we assume
             return -1;
     }
@@ -159,5 +182,15 @@ char operator_to_char(Operator op) {
             return '*';
         case OP_DIV:
             return '/';
+        case OP_POW:
+            return '^';
+        case OP_FACTORIAL:
+            return '!';
+        case OP_START_PAR:
+            return '(';
+        case OP_END_PAR:
+            return ')';
+        default:
+            return EOF;
     }
 }

src/main.c

@@ -1,4 +1,3 @@
-#include "arena.h"
 #include "evaluator.h"
 #include "lexer.h"
 #include "parser.h"
@@ -19,10 +18,9 @@ int main(void) {
     }
     buf[pos] = '\0';
 
-    ASTNodeArray context;
-    tokenize(buf, &context);
+    TokenizeResult tokens = tokenize(buf);
 
-    ParseResult par = parse(&context);
+    ParseResult par = parse(tokens);
     int64_t result = evaluate(par);
 
 

src/parser.c

@@ -1,13 +1,40 @@
 #include "parser.h"
+#include "arraylist.h"
 #include "lexer.h"
 #include "arena.h"
 #include <stdalign.h>
 #include <stdbool.h>
 #include <stdint.h>
-#include <stdlib.h>
 
+uint8_t prefix_rbp(ASTNode node) {
+    if (node.type == NODE_INTEGER) {
+        return 0;
+    }
 
-uint8_t node_lbp(ASTNode node) {
+    switch (node.data.unary.op) {
+        case OP_SUB:
+        case OP_ADD:
+            return 30;
+        default:
+            return -1;
+    }
+}
+
+uint8_t postfix_lbp(ASTNode node) {
+    if (node.type == NODE_INTEGER) {
+        return 0;
+    }
+
+    switch (node.data.unary.op) {
+        case OP_FACTORIAL:
+            return 40;
+        default:
+            // needs to be dealt with with resulttypes
+            return 255;
+    }
+}
+
+uint8_t infix_lbp(ASTNode node) {
     if (node.type == NODE_INTEGER) {
         return 0;
     }
@@ -20,12 +47,14 @@ uint8_t node_lbp(ASTNode node) {
         case OP_DIV:
         case OP_MUL:
             return 20;
+        case OP_POW:
+            return 51;
         default:
             return 0;
     }
 }
 
-uint8_t node_rbp(ASTNode node) {
+uint8_t infix_rbp(ASTNode node) {
     if (node.type == NODE_INTEGER) {
         return 0;
     }
@@ -38,49 +67,32 @@ uint8_t node_rbp(ASTNode node) {
         case OP_DIV:
         case OP_MUL:
             return 21;
+        case OP_POW:
+            return 50;
         default:
             return 0;
     }
 }
 
-ASTNode ASTNodeSlice_next(ASTNodeSlice *slice) {
-    return slice->arr->data[slice->pos++];
-}
-
-ASTNode ASTNodeSlice_peek(ASTNodeSlice *slice) {
-    return slice->arr->data[slice->pos];
-}
-
-bool ASTNodeSlice_is_valid(ASTNodeSlice *slice) {
-    if (slice->arr->len < 1) {
-        return false;
-    }
-    if (slice->pos >= slice->arr->len) {
-        return false;
-    }
-
-    return true;
-}
-
-ParseResult parse(ASTNodeArray *arr) {
-    ASTNodeSlice context = {
-        .arr = arr,
-        .pos = 0,
-    };
-    Arena arena = arena_init(sizeof(ASTNode) * arr->len).arena;
+ParseResult parse(TokenizeResult tokens) {
+    ArraySlice *context = arraylist_slice(tokens.arr, 0, arraylist_size(tokens.arr));
+    Arena arena = arena_init(sizeof(ASTNode) * arraylist_size(tokens.arr)).arena;
 
     return (ParseResult) {
+        .is_valid = true,
         .arena = arena,
-        .tree = parse_expr(&context, &arena, 0)};
+        .tree = parse_expr(context, &arena, 0)};
 }
 
-ASTNode *parse_expr(ASTNodeSlice *slice, Arena *arena, uint8_t min_bp) {
+ASTNode *parse_expr(ArraySlice *slice, Arena *arena, uint8_t min_bp) {
+    // First: Consume a first number
     arena_ensure_capacity(
         arena,
         sizeof(ASTNode),
         alignof(ASTNode)
-    );
+    ); // shouldn't fail but if it does then what a shame
 
+    // Get pointer in the arena
     ASTNode *left_side = arena_unwrap_pointer(
         arena_alloc(
             arena,
@@ -89,22 +101,90 @@ ASTNode *parse_expr(ASTNodeSlice *slice, Arena *arena, uint8_t min_bp) {
         )
     );
 
-    *left_side = ASTNodeSlice_next(slice);
+    arrayslice_next(slice, left_side);
+
+    if (left_side->type == NODE_PARENTHESIS &&
+        left_side->data.parenthesis.op == OP_START_PAR) {
+        left_side = parse_expr(slice, arena, 0);
+        // HERE CHEKC LATER if slice.next != ')'
+        ASTNode *end_par;
+        arrayslice_next(slice, &end_par);
+        if (end_par->type != NODE_PARENTHESIS ||
+            end_par->data.parenthesis.op != OP_END_PAR) {
+            // todo
+        }
+        return left_side;
+    }
+    // if is unary then take prefix bp and continue
+    // to the right, no need to allocate left side
+    // because we just did and right side
+    // WILL return a valid allocated pointer.
+    if (left_side->type == NODE_UNARY_OP) {
+        uint8_t rbp = prefix_rbp(*left_side);
+        ASTNode *righ_side = parse_expr(slice, arena, rbp);
+
+        left_side->data.unary.val = righ_side;
+    }
 
     while (true) {
-        if (!ASTNodeSlice_is_valid(slice)) {
+        // Second: Get next one and checn bp
+        if (!arrayslice_is_valid(slice)) {
             break;
         }
 
-        ASTNode operator = ASTNodeSlice_peek(slice);
-        uint8_t rbp = node_rbp(operator);
-        uint8_t lbp = node_lbp(operator);
+        // Here check if not OP error
 
+        ASTNode operator;
+        // Here should chekc if is operator not some bs
+        // Third, get operator and binding powers
+        arrayslice_peek(slice, &operator);
+
+        // temporary for bad error handling
+        if (postfix_lbp(operator) != 255) {
+            if (postfix_lbp(operator) < min_bp) {
+                break;
+            }
+
+            // allocate operator
+            arrayslice_next(slice, NULL);
+            arena_ensure_capacity(
+                arena,
+                sizeof(ASTNode),
+                alignof(ASTNode));
+            ASTNode *new_node = arena_unwrap_pointer(
+                arena_alloc(
+                    arena, 
+                    sizeof(ASTNode), 
+                    alignof(ASTNode)
+                )
+            );
+            *new_node = operator;
+
+
+            new_node->data.unary.val = left_side;
+
+            left_side = new_node;
+            continue;
+        }
+
+        // check if it has infix or not, if not then error
+        uint8_t rbp = infix_rbp(operator);
+        uint8_t lbp = infix_lbp(operator);
+
+        if (rbp != 255 && lbp != 255) {
+
+            // If lbp is LESS then stop recursion,
+            // we found the next smaller binding power
+            // or the one with more precedence
             if (lbp < min_bp) {
                 break;
             }
 
-        ASTNodeSlice_next(slice);
+
+            // If NOT, then we continue wtching ahead
+            // for the next one but taking our current 
+            // concern that is rbp of the current operator
+            arrayslice_next(slice, NULL);
             ASTNode *right_side = parse_expr(slice, arena, rbp);
 
             arena_ensure_capacity(
@@ -124,11 +204,14 @@ ASTNode *parse_expr(ASTNodeSlice *slice, Arena *arena, uint8_t min_bp) {
             new_node->data.binary.right = right_side;
 
             left_side = new_node;
+
+            continue;
+        }
+
+        break;
     }
 
 
+    // Final: return left side
     return left_side;
 }
-
-
-

test/CMakeLists.txt

@@ -1,15 +1,9 @@
 find_package(cmocka REQUIRED)
 
-add_executable(test_nodeArray test_ASTNodeArray.c)
 add_executable(test_lexer test_lexer.c)
 add_executable(test_parser test_parser.c)
 add_executable(test_evaluator test_evaluator.c)
 
-target_link_libraries(test_nodeArray
-    calculator_lib
-    cmocka::cmocka
-)
-
 target_link_libraries(test_lexer
     calculator_lib
     cmocka::cmocka
@@ -25,7 +19,6 @@ target_link_libraries(test_evaluator
     cmocka::cmocka
 )
 
-add_test(NAME nodeArray_tests COMMAND test_nodeArray)
 add_test(NAME lexer_tests COMMAND test_lexer)
 add_test(NAME parser_tests COMMAND test_parser)
 add_test(NAME evaluator_tests COMMAND test_evaluator)

test/test_ASTNodeArray.c

@@ -1,86 +0,0 @@
-#include "lexer.h"
-#include <stdarg.h>
-#include <stdbool.h>
-#include <stddef.h>
-#include <stdint.h>
-#include <setjmp.h>
-#include <cmocka.h>
-
-static void test_array_push(void **state) {
-    (void) state;
-
-    // We use 2 to force resize and checking anything wrong with malloc
-    ASTNodeArray arr = ASTNodeArray_init(2);
-    ASTNode node1 = {
-        .type = NODE_INTEGER,
-        .data = { .integer = 90 }
-    };
-
-    ASTNode node2 = {
-        .type = NODE_INTEGER,
-        .data = { .integer = 80 }
-    };
-
-    ASTNode node3 = {
-        .type = NODE_INTEGER,
-        .data = { .integer = 70 }
-    };
-
-    assert_int_equal(ASTNodeArray_push(&arr, node1), ARRAY_OK);
-    assert_int_equal(ASTNodeArray_len(&arr), 1);
-
-    assert_int_equal(ASTNodeArray_push(&arr, node2), ARRAY_OK);
-    assert_int_equal(ASTNodeArray_len(&arr), 2);
-
-    assert_int_equal(ASTNodeArray_push(&arr, node3), ARRAY_OK);
-    assert_int_equal(ASTNodeArray_len(&arr), 3);
-
-    ASTNodeArray_free(&arr);
-}
-
-static void test_array_pop(void **state) {
-    (void) state;
-
-    // Set to force desize
-    ASTNodeArray arr = ASTNodeArray_init(16);
-    ASTNode node1 = {
-        .type = NODE_INTEGER,
-        .data = { .integer = 90 }
-    };
-
-    ASTNode node2 = {
-        .type = NODE_INTEGER,
-        .data = { .integer = 80 }
-    };
-
-    ASTNode node3 = {
-        .type = NODE_INTEGER,
-        .data = { .integer = 70 }
-    };
-
-    assert_int_equal(ASTNodeArray_push(&arr, node1), ARRAY_OK);
-    assert_int_equal(ASTNodeArray_len(&arr), 1);
-
-    assert_int_equal(ASTNodeArray_push(&arr, node2), ARRAY_OK);
-    assert_int_equal(ASTNodeArray_len(&arr), 2);
-
-    assert_int_equal(ASTNodeArray_push(&arr, node3), ARRAY_OK);
-    assert_int_equal(ASTNodeArray_len(&arr), 3);
-
-    ASTNode node4;
-    assert_int_equal(ASTNodeArray_pop(&arr, 1, &node4), ARRAY_OK);
-    assert_int_equal(node4.type, NODE_INTEGER);
-    assert_int_equal(node4.data.integer, 80);
-
-    ASTNodeArray_free(&arr);
-}
-
-
-int main(void) {
-    const struct CMUnitTest tests[] = {
-        cmocka_unit_test(test_array_push),
-        cmocka_unit_test(test_array_pop),
-    };
-
-    return cmocka_run_group_tests(tests, NULL, NULL);
-}

test/test_evaluator.c

@@ -13,10 +13,8 @@ static void test_basic_evaluation(void** state) {
     (void) state;
 
     char expr[256] = "2 + 4 * 40 / 2";
-    ASTNodeArray context;
-
-    tokenize(expr, &context);
-    ParseResult result = parse(&context);
+    TokenizeResult tokens = tokenize(expr);
+    ParseResult result = parse(tokens);
     int64_t value = evaluate(result);
 
     assert_int_equal(value, 82);

test/test_lexer.c

@@ -1,3 +1,4 @@
+#include "arraylist.h"
 #include "lexer.h"
 #include <stdarg.h>
 #include <stdbool.h>
@@ -10,37 +11,37 @@ static void test_tokenize_normal_expresion(void **state) {
     (void) state;
 
     char expr[256] = "2 + 3 / 66 * 789";
-    ASTNodeArray tokens;
     ASTNode node;
+    TokenizeResult tokens = tokenize(expr);
 
-    assert_int_equal(tokenize(expr, &tokens), LEXER_OK);
-    assert_int_equal(tokens.len, 7);
+    assert_true(tokens.is_valid);
+    assert_int_equal(arraylist_size(tokens.arr), 7);
 
-    ASTNodeArray_get(&tokens, 0, &node);
+    arraylist_get(tokens.arr, 0, &node);
     assert_int_equal(node.type, NODE_INTEGER);
     assert_int_equal(node.data.integer, 2);
 
-    ASTNodeArray_get(&tokens, 1, &node);
+    arraylist_get(tokens.arr, 1, &node);
     assert_int_equal(node.type, NODE_BINARY_OP);
     assert_int_equal(node.data.binary.op, OP_ADD);
 
-    ASTNodeArray_get(&tokens, 2, &node);
+    arraylist_get(tokens.arr, 2, &node);
     assert_int_equal(node.type, NODE_INTEGER);
     assert_int_equal(node.data.integer, 3);
 
-    ASTNodeArray_get(&tokens, 3, &node);
+    arraylist_get(tokens.arr, 3, &node);
     assert_int_equal(node.type, NODE_BINARY_OP);
     assert_int_equal(node.data.binary.op, OP_DIV);
 
-    ASTNodeArray_get(&tokens, 4, &node);
+    arraylist_get(tokens.arr, 4, &node);
     assert_int_equal(node.type, NODE_INTEGER);
     assert_int_equal(node.data.integer, 66);
 
-    ASTNodeArray_get(&tokens, 5, &node);
+    arraylist_get(tokens.arr, 5, &node);
     assert_int_equal(node.type, NODE_BINARY_OP);
     assert_int_equal(node.data.binary.op, OP_MUL);
 
-    ASTNodeArray_get(&tokens, 6, &node);
+    arraylist_get(tokens.arr, 6, &node);
     assert_int_equal(node.type, NODE_INTEGER);
     assert_int_equal(node.data.integer, 789);
 }
@@ -49,28 +50,20 @@ static void test_tokenize_unrecognized_symbol(void **state) {
     (void) state;
 
     char expr[256] = " 2 j 3 / 66 } 789";
-    ASTNodeArray tokens = {
-        .len = 0,
-        .cap = 0,
-    };
+    TokenizeResult tokens = tokenize(expr);
 
-    assert_int_equal(tokenize(expr, &tokens), LEXER_NOT_RECOGNIZED_SYMBOL);
-    assert_int_equal(tokens.len, 0);
-    assert_int_equal(tokens.cap, 0);
+    assert_false(tokens.is_valid);
+    assert_uint_equal(tokens.err, LEXER_NOT_RECOGNIZED_SYMBOL);
 }
 
 static void test_tokenize_wrong_sintax(void **state) {
     (void) state;
 
     char expr[256] = "2 3 / 66 789";
-    ASTNodeArray tokens = {
-        .len = 0,
-        .cap = 0,
-    };
+    TokenizeResult tokens = tokenize(expr);
 
-    assert_int_equal(tokenize(expr, &tokens), LEXER_WRONG_SYNTAX);
-    assert_int_equal(tokens.len, 0);
-    assert_int_equal(tokens.cap, 0);
+    assert_false(tokens.is_valid);
+    assert_uint_equal(tokens.err, LEXER_WRONG_SYNTAX);
 }
 
 static void test_string_to_number_normal(void **state) {
@@ -78,23 +71,24 @@ static void test_string_to_number_normal(void **state) {
 
     char num[16] = "2333t55";
     size_t offset = 0;
-    ASTNode result;
+    ASTNodeResult result = tokenize_number(num, &offset);
 
-    assert_int_equal(tokenize_number(num, &offset, &result), LEXER_OK);
+    assert_true(result.is_valid);
 
     assert_int_equal(offset, 4); // equal to t position in string
-    assert_int_equal(result.type, NODE_INTEGER);
-    assert_int_equal(result.data.integer, 2333);
+    assert_int_equal(result.node.type, NODE_INTEGER);
+    assert_int_equal(result.node.data.integer, 2333);
 }
 
 static void test_string_to_number_overflow(void **state) {
     (void) state;
 
-    // Number is INT64_MAX but with a extra 8 at the end
-    char num[32] = "92233720368547758078yy7";
+    // Number is INT64_MAX but with a extra 899 at the end
+    char num[32] = "92233720368547758079";
     size_t offset = 0;
-    ASTNode result;
-    assert_int_equal(tokenize_number(num, &offset, &result), LEXER_INT_OVERFLOW);
+    ASTNodeResult result = tokenize_number(num, &offset);
+    assert_false(result.is_valid);
+    assert_uint_equal(result.err, LEXER_INT_OVERFLOW);
     // Technically it can trigger a buf overflow error but obvioulsy 
     // it will trigger int overflow error first
 }

test/test_parser.c

@@ -1,4 +1,5 @@
 #include "arena.h"
+#include "arraylist.h"
 #include "lexer.h"
 #include "parser.h"
 #include <stdarg.h>
@@ -12,13 +13,12 @@ static void test_parsing_basic_expression(void **state) {
     (void) state;
 
     char expr[256] = "2 + 3 / 66 * 789";
-    ASTNodeArray tokens;
-    ASTNode node;
+    TokenizeResult tokens = tokenize(expr);
 
-    assert_int_equal(tokenize(expr, &tokens), LEXER_OK);
-    assert_int_equal(tokens.len, 7);
+    assert_true(tokens.is_valid);
+    assert_int_equal(arraylist_size(tokens.arr), 7);
 
-    ParseResult result = parse(&tokens);
+    ParseResult result = parse(tokens);
     // Assert head is +
     assert_int_equal(result.tree->type, NODE_BINARY_OP);
     assert_int_equal(result.tree->data.binary.op, OP_ADD);