From a86be4b76d96464e4bb9aa108d2c01198125084e Mon Sep 17 00:00:00 2001
From: Michael Smith <mikesmiffy128@gmail.com>
Date: Tue, 20 Jun 2023 21:00:00 +0100
Subject: Tweak feature sorting and fix a chibicc bug

That sorting function was a bit wonky, so make it just a little bit
wonky instead. chibicc would produce confusing lex errors if given a
stray single quote somewhere, so make it give non-confusing errors.

Also get rid of canonicalize_newline() because it's unnecessary for SST
so long as Windows Git isn't left in its default misconfigured state.
---
 src/3p/chibicc/tokenize.c | 28 +++++-----------------------
 src/build/codegen.c       | 12 ++++++------
 2 files changed, 11 insertions(+), 29 deletions(-)

diff --git a/src/3p/chibicc/tokenize.c b/src/3p/chibicc/tokenize.c
index 3b15df9..b13edd5 100644
--- a/src/3p/chibicc/tokenize.c
+++ b/src/3p/chibicc/tokenize.c
@@ -330,9 +330,11 @@ static Token *read_char_literal(char *start, char *quote, Type *ty) {
   else
     c = decode_utf8(&p, p);
 
-  char *end = strchr(p, '\'');
-  if (!end)
-    error_at(p, "unclosed char literal");
+  char *end = p;
+  for (; *end != '\''; ++end) {
+    if (!*end || *end == '\n')
+      error_at(p, "unclosed char literal");
+  }
 
   Token *tok = new_token(TK_NUM, start, end + 1);
   tok->val = c;
@@ -691,25 +693,6 @@ File *new_file(char *name, int file_no, char *contents) {
   return file;
 }
 
-// Replaces \r or \r\n with \n.
-static void canonicalize_newline(char *p) {
-  int i = 0, j = 0;
-
-  while (p[i]) {
-    if (p[i] == '\r' && p[i + 1] == '\n') {
-      i += 2;
-      p[j++] = '\n';
-    } else if (p[i] == '\r') {
-      i++;
-      p[j++] = '\n';
-    } else {
-      p[j++] = p[i++];
-    }
-  }
-
-  p[j] = '\0';
-}
-
 // Removes backslashes followed by a newline.
 static void remove_backslash_newline(char *p) {
   int i = 0, j = 0;
@@ -781,7 +764,6 @@ static void convert_universal_chars(char *p) {
 
 // NOTE modified API from upstream
 Token *tokenize_buf(const char *name, char *p) {
-  canonicalize_newline(p);
   remove_backslash_newline(p);
   convert_universal_chars(p);
 
diff --git a/src/build/codegen.c b/src/build/codegen.c
index bf3ae1e..e24a096 100644
--- a/src/build/codegen.c
+++ b/src/build/codegen.c
@@ -81,14 +81,14 @@ static inline int cmp_feature(struct feature *e, const char *s) {
 }
 static inline int cmp_feature_bydesc(struct feature *e, const char *s) {
 	for (const char *p = e->desc; ; ++p, ++s) {
-		// longer string first
-		if (!*s) return !!*p; else if (!*p) return -1;
+		// shortest string first
+		if (!*p) return !!*s; if (!*s) return -1;
 		// case insensitive sort where possible
-		if (tolower(*p) > tolower(*s)) return 1;
-		if (tolower(*p) < tolower(*s)) return -1;
+		if (tolower((uchar)*p) > tolower((uchar)*s)) return 1;
+		if (tolower((uchar)*p) < tolower((uchar)*s)) return -1;
 		// prioritise upper-case if same letter
-		if (isupper(*p) && islower(*s)) return 1;
-		if (islower(*p) && isupper(*s)) return -1;
+		if (isupper((uchar)*p) && islower((uchar)*s)) return 1;
+		if (islower((uchar)*p) && isupper((uchar)*s)) return -1;
 	}
 	return 0;
 }
-- 
cgit v1.2.3