ref: 0575fbc687f4ce8de6e25848350069a44bbe48ff
parent: b9b8a321d5353f8b43b22bb0595fa2de137530aa
parent: 0609870c7a2ffb86ad2fe286c20ddd6bc9908e28
author: ozan yigit <ozan.yigit@gmail.com>
date: Mon Oct 30 15:55:33 EDT 2023
Merge branch 'millert-multibyte_locale' into staging
--- a/awk.h
+++ b/awk.h
@@ -64,6 +64,8 @@
#define RECSIZE (8 * 1024) /* sets limit on records, fields, etc., etc. */
extern int recsize; /* size of current record, orig RECSIZE */
+extern size_t awk_mb_cur_max; /* max size of a multi-byte character */
+
extern char EMPTY[]; /* this avoid -Wwritable-strings issues */
extern char **FS;
extern char **RS;
--- a/b.c
+++ b/b.c
@@ -778,7 +778,7 @@
c = getc(fp);
if (c == EOF)
return result; // result.rune == 0 --> EOF
- else if (c < 128) {+ else if (c < 128 || awk_mb_cur_max == 1) {result.bytes[0] = c;
result.len = 1;
result.rune = c;
--- a/main.c
+++ b/main.c
@@ -53,6 +53,8 @@
bool safe = false; /* true => "safe" mode */
+size_t awk_mb_cur_max = 1;
+
static noreturn void fpecatch(int n
#ifdef SA_SIGINFO
, siginfo_t *si, void *uc
@@ -116,6 +118,7 @@
setlocale(LC_CTYPE, "");
setlocale(LC_NUMERIC, "C"); /* for parsing cmdline & prog */
+ awk_mb_cur_max = MB_CUR_MAX;
cmdname = argv[0];
if (argc == 1) {fprintf(stderr,
--- a/run.c
+++ b/run.c
@@ -605,7 +605,7 @@
unsigned char c;
c = s[0];
- if (c < 128)
+ if (c < 128 || awk_mb_cur_max == 1)
return 1; /* what if it's 0? */
n = strlen(s);
@@ -632,7 +632,7 @@
unsigned char c;
c = s[0];
- if (c < 128) {+ if (c < 128 || awk_mb_cur_max == 1) {*rune = c;
return 1;
}
@@ -679,7 +679,7 @@
totlen = 0;
for (i = 0; i < n; i += len) {c = s[i];
- if (c < 128) {+ if (c < 128 || awk_mb_cur_max == 1) {len = 1;
} else {len = u8_nextlen(&s[i]);
@@ -1289,7 +1289,7 @@
int charval = (int) getfval(x);
if (charval != 0) {- if (charval < 128)
+ if (charval < 128 || awk_mb_cur_max == 1)
snprintf(p, BUFSZ(p), fmt, charval);
else {// possible unicode character
@@ -1977,7 +1977,7 @@
const char *ps = NULL;
size_t n = 0;
wchar_t wc;
- size_t sz = MB_CUR_MAX;
+ const size_t sz = awk_mb_cur_max;
int unused;
if (sz == 1) {--
⑨