mighty

commit 15fb7b2e5a110528b4024e56c1c1e9d2ff384889
parent 84e387d0bffde1310a9549d791792c9fccb4fa93
Author: citbl <citbl@citbl.org>
Date:   Wed, 20 May 2026 20:31:20 +1000

wip

Diffstat:
A
mtcc/.clangd
 | 
15
+++++++++++++++
M
mtcc/.gitignore
 | 
1
+
M
mtcc/src/lexer.c
 | 
85
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
M
mtcc/src/lexer.h
 | 
5
++---
M
mtcc/src/main.c
 | 
4
++--
M
mtcc/src/token.h
 | 
6
+++---

6 files changed, 105 insertions(+), 11 deletions(-)
diff --git a/mtcc/.clangd b/mtcc/.clangd
@@ -0,0 +1,15 @@
+CompileFlags:
+  Add: [
+    -Wall,
+    -Wextra,
+    -Wpedantic,
+    -Wshadow,
+    -Wpointer-arith,
+    -Wcast-qual,
+    -Wcast-align,
+    -Wstrict-prototypes,
+    -Wmissing-prototypes,
+    -xc,
+    -std=c17,
+    -g,
+    ]
diff --git a/mtcc/.gitignore b/mtcc/.gitignore
@@ -1,2 +1,3 @@
 .DS_Store
 *.dSYM
+mtcc
diff --git a/mtcc/src/lexer.c b/mtcc/src/lexer.c
@@ -1,10 +1,58 @@
+#include <stdbool.h>
+
 #include "lexer.h"
 #include "string.h"
 
+static bool is__(const char c);
+static bool is_alpha(const char c);
+static bool is_digit(const char c);
+static bool is_space(const char c);
+static bool is_alpha_numeric(const char c);
+static bool is_dot(const char c);
+
 void lexer_lex(lexer_t *lexer) {
-    size_t len = strnlen(lexer->source, lexer->source_len);
-    while (lexer->pos < len) {
-        char c = lexer->source[lexer->pos++];
+    size_t len = strnlen(lexer->src, lexer->src_len);
+    const char *src = lexer->src;
+    char c, cx;
+    size_t i = 0;
+    size_t col = 1;
+    size_t line = 1;
+    size_t start = 0;
+    size_t start_col = 0;
+
+    while (i < len) {
+        c = lexer->src[i];
+
+        if (is_space(c)) {
+            if (c == '\n') {
+                i++;
+                col = 1;
+            } else {
+                col++;
+            }
+            i++;
+        }
+
+        start = i;
+        start_col = col;
+
+        if (is_alpha(c) || is__(c)) {
+            while (i < len && (is_alpha_numeric(src[i]) || is__(src[i]))) {
+                i++;
+                col++;
+            }
+        }
+
+        cx = (i < len) ? lexer->src[i] : '\0';
+
+        if (c == '/' && cx == '/') {
+            while (i < len && src[i] != '\n') {
+                i++;
+                col++;
+            }
+            continue;
+        }
+
         switch (c) {
             case '\n':
             case '\t':
@@ -14,3 +62,34 @@ void lexer_lex(lexer_t *lexer) {
         }
     }
 }
+
+static bool is_space(const char c) {
+    return c == ' ' | c == '\t' | c == '\r' | c == '\n';
+}
+
+static bool is__(const char c) {
+    return c == '_';
+}
+
+static bool is_alpha(const char c) {
+    return (c >= 'a' && c <= 'z') || (c >= 'A' && c <= 'Z');
+}
+
+static bool is_digit(const char c) {
+    return (c >= '0' && c <= '9');
+}
+
+static bool is_alpha_numeric(const char c) {
+    return is_alpha(c) || is_digit(c);
+}
+
+static bool is_dot(const char c) {
+    return c == '.';
+}
+
+static const char *TYPES[] = {
+    /*[TOKEN_IDENT] = "ident/type",
+    [TOKEN_LPAREN] = "open paren",
+    [TOKEN_RPAREN] = "close paren",
+    [TOKEN_LBRACE] = "open brace",*/
+};
diff --git a/mtcc/src/lexer.h b/mtcc/src/lexer.h
@@ -3,12 +3,11 @@
 
 typedef struct lexer_t {
     const char *filename;
-    const char *source;
-    size_t source_len;
+    const char *src;
+    size_t src_len;
     token_t *tokens;
     size_t tok_len;
     size_t tok_cap;
-    size_t pos;
 } lexer_t;
 
 void lexer_lex(lexer_t *lexer);
diff --git a/mtcc/src/main.c b/mtcc/src/main.c
@@ -17,8 +17,8 @@ int main(int argc, char **argv) {
     file = read_file(filename);
     lexer = (lexer_t){
         .filename = filename,
-        .source = file.contents,
-        .source_len = file.len,
+        .src = file.contents,
+        .src_len = file.len,
     };
 
     lexer_lex(&lexer);
diff --git a/mtcc/src/token.h b/mtcc/src/token.h
@@ -10,9 +10,9 @@ typedef struct {
     token_type_t token_type;
 
     struct {
-        char *filename;
-        size_t line;
-        size_t col;
+        const char *filename;
+        size_t line, col;
+        size_t start, stop;
     } span_t;
 
 } token_t;