summaryrefslogtreecommitdiffhomepage
path: root/src/3p/chibicc/tokenize.c
diff options
context:
space:
mode:
authorMichael Smith <mikesmiffy128@gmail.com>2023-06-20 21:00:00 +0100
committerMichael Smith <mikesmiffy128@gmail.com>2023-06-20 21:00:00 +0100
commita86be4b76d96464e4bb9aa108d2c01198125084e (patch)
treeacc66325dd342582b15233ea30794378d68c7e5b /src/3p/chibicc/tokenize.c
parent9c2bb3af4358a44d71d45d05278b2f34313de0e2 (diff)
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.
Diffstat (limited to 'src/3p/chibicc/tokenize.c')
-rw-r--r--src/3p/chibicc/tokenize.c28
1 files changed, 5 insertions, 23 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);