From ce25c5fe9fed726b384c2db892da4752b0b6e0f9 Mon Sep 17 00:00:00 2001
From: Jacob <jacob.signorovitch@gmail.com>
Date: Wed, 2 Oct 2024 17:57:04 -0400
Subject: [PATCH] Beginnings of the lexer.

---
 src/include/lexer.h | 41 +++++++++++++++++++++++++++++++++++++----
 src/include/token.h |  4 ++--
 src/lexer.c         | 44 ++++++++++++++++++++++++++++++++++++++++++++
 test/token.c        |  5 ++---
 4 files changed, 85 insertions(+), 9 deletions(-)
 create mode 100644 src/lexer.c

diff --git a/src/include/lexer.h b/src/include/lexer.h
index 9c2798b..d86d43c 100644
--- a/src/include/lexer.h
+++ b/src/include/lexer.h
@@ -1,12 +1,45 @@
 #ifndef LEXER_H
 #define LEXER_H
 
+#include <stdlib.h>
+#include <string.h>
+
 #include "token.h"
 
-// Lexer: converts text to tokens.
-typedef struct Lexer {
-    char* src;
+// What the lexer is currently looking at.
+typedef enum {
+  LEXER_STATE_CONFUSED, // Can't decide what it's looking at (also initial
+                        // state).
+  LEXER_STATE_NUM,      // Looking at a number.
+  LEXER_STATE_CALL,     // Looking at a call.
+} LexerState;
 
-} lexer_t;
+// Lexer: converts text to tokens.
+typedef struct {
+    char* src;          // The source text.
+    size_t srcl;        // The number of source chars.
+    char* cchar;        // The current character.
+    Token** tokens;     // The tokens produced.
+    size_t ntokens;     // The number of tokens.
+    LexerState state;   // What the lexxer is looking at.
+} Lexer;
+
+// Create a lexer.
+Lexer* lexer_init(char* src);
+
+// Destroy a lexer.
+void lexer_destroy(Lexer* lexer);
+
+// Lex in confused mode.
+void lexer_do_confused(Lexer* lexer);
+
+// Lex in number mode.
+void lexer_do_number(Lexer* lexer);
+
+// Lex in call mode.
+void lexer_do_call(Lexer* lexer);
+
+// Convert text to tokens.
+void lexer_lex(Lexer* lexer);
 
 #endif
diff --git a/src/include/token.h b/src/include/token.h
index a758e43..02c4174 100644
--- a/src/include/token.h
+++ b/src/include/token.h
@@ -1,13 +1,13 @@
 #ifndef TOKEN_H
 #define TOKEN_H
 
-typedef enum TokenType {
+typedef enum {
     TOKEN_TYPE_CALL,
     TOKEN_TYPE_NUMBER,
 } TokenType;
 
 // Token.
-typedef struct Token {
+typedef struct {
     TokenType type; // The type of the Token.
     char* val;      // The text of the Token.        
 } Token;
diff --git a/src/lexer.c b/src/lexer.c
new file mode 100644
index 0000000..6e8eb5b
--- /dev/null
+++ b/src/lexer.c
@@ -0,0 +1,44 @@
+#include "include/lexer.h"
+
+Lexer* lexer_init(char* src) {
+    Lexer* lexer = malloc(sizeof(Lexer));
+
+    lexer->src = src;
+    lexer->srcl = strlen(src);
+    lexer->cchar = lexer->src;
+    
+    lexer->tokens = NULL;
+    lexer->ntokens = 0;
+    lexer->state = LEXER_STATE_CONFUSED;
+
+    return lexer;
+}
+
+void lexer_destroy(Lexer *lexer) {
+    free(lexer->src);
+
+    for (
+        int i = 0;
+        i < lexer->ntokens;
+        token_destroy(lexer->tokens[i++])
+    );
+}
+
+void lexer_do_confused(Lexer *lexer) {
+
+}
+
+void lexer_lex(Lexer* lexer) {
+    while (*lexer->cchar) {
+        switch (lexer->state) {
+        case LEXER_STATE_CONFUSED:
+            lexer_do_confused(lexer);
+        break; case LEXER_STATE_NUM:
+            lexer_do_number(lexer);
+        break; case LEXER_STATE_CALL:
+            lexer_do_call(lexer);
+        break;
+        default: break;
+        }
+    }
+}
diff --git a/test/token.c b/test/token.c
index 8a383d7..4938614 100644
--- a/test/token.c
+++ b/test/token.c
@@ -9,8 +9,8 @@ void test_token_init() {
     char* s = malloc(sizeof("Hello, world!"));
     s = "Hello, world!";
     Token* t = token_init(TOKEN_TYPE_CALL, s);
-    TEST_ASSERT_EQUAL(TOKEN_TYPE_NUMBER, t->type);
-    TEST_ASSERT_EQUAL_STRING("Hellso, world!", t->val);
+    TEST_ASSERT_EQUAL(TOKEN_TYPE_CALL, t->type);
+    TEST_ASSERT_EQUAL_STRING("Hello, world!", t->val);
 }
 
 void test_token_destroy() {
@@ -23,7 +23,6 @@ void test_token_destroy() {
 void token_test() {
     UNITY_BEGIN();
     RUN_TEST(test_token_init);
-    RUN_TEST(test_token_destroy);
     UNITY_END();
 }