From 2f32c928d6cae60b532b498d72897a7fabe135e3 Mon Sep 17 00:00:00 2001
From: me <me@alloca.space>
Date: Sun, 11 Jan 2026 10:58:05 +0200
Subject: [PATCH] lex: parse tab and exit, add comments

---
 first-interpreter/src/lex.c | 27 +++++++++++++++++++++++++--
 1 file changed, 25 insertions(+), 2 deletions(-)

diff --git a/first-interpreter/src/lex.c b/first-interpreter/src/lex.c
index 7218460..fab6ed0 100644
--- a/first-interpreter/src/lex.c
+++ b/first-interpreter/src/lex.c
@@ -6,56 +6,74 @@ int is_identifier_char(char);
 int is_numeric(char);
 
 TokenArray lex(char* txt, unsigned length) {
+    // The index for the input.
     unsigned txt_index = 0;
+
+    // We'll put tokens we lexed successfully here.
     Token* tokens = (Token*)malloc(length * sizeof(Token));
+    // Where to put the next token in tokens.
     unsigned tokens_index = 0;
+
     while (txt_index < length && txt[txt_index] != '\0') {
         switch (txt[txt_index]) {
+        // Ignore spaces, tabs and newlines
         case ' ': {
             ++txt_index;
             break;
         }
+        case '\t': {
+            ++txt_index;
+            break;
+        }
         case '\n': {
             ++txt_index;
             break;
         }
+        // EQUALS
         case '=': {
             tokens[tokens_index] = (Token){ .tag = EQUALS, .data.integer = 0, };
             ++tokens_index;
             ++txt_index;
             break;
         }
+        // COMMA
         case ',': {
             tokens[tokens_index] = (Token){ .tag = COMMA, .data.integer = 0, };
             ++tokens_index;
             ++txt_index;
             break;
         }
+        // OPENPAREN
         case '(': {
             tokens[tokens_index] = (Token){ .tag = OPENPAREN, .data.integer = 0, };
             ++tokens_index;
             ++txt_index;
             break;
         }
+        // CLOSEPAREN
         case ')': {
             tokens[tokens_index] = (Token){ .tag = CLOSEPAREN, .data.integer = 0, };
             ++tokens_index;
             ++txt_index;
             break;
         }
+        // OPENCURLY
         case '{': {
             tokens[tokens_index] = (Token){ .tag = OPENCURLY, .data.integer = 0, };
             ++tokens_index;
             ++txt_index;
             break;
         }
+        // CLOSECURLY
         case '}': {
             tokens[tokens_index] = (Token){ .tag = CLOSECURLY, .data.integer = 0, };
             ++tokens_index;
             ++txt_index;
             break;
         }
+        // Complex cases and errors.
         default: {
+            // Identifiers.
             if (is_identifier_char(txt[txt_index])) {
                 char* word = malloc(128);
                 unsigned word_index = 0;
@@ -66,7 +84,9 @@ TokenArray lex(char* txt, unsigned length) {
                 }
                 tokens[tokens_index] = (Token){ .tag = IDENTIFIER, .data.identifier = word, };
                 ++tokens_index;
-            } else if (is_numeric(txt[txt_index])) {
+            }
+            // Integers.
+			else if (is_numeric(txt[txt_index])) {
 
                 char word[9] = { '\0' };
                 unsigned word_index = 0;
@@ -78,8 +98,11 @@ TokenArray lex(char* txt, unsigned length) {
                 int integer = atoi(word);
                 tokens[tokens_index] = (Token){ .tag = INTEGER, .data.integer = integer, };
                 ++tokens_index;
-            } else {
+            }
+            // Not a token.
+			else {
                 fprintf(stderr, "unexpected character '%c'", txt[txt_index]);
+				exit(1);
             }
         }
         }