[v4,13/13] builtin: Process multi-byte characters in read(1)

Commit Message

Herbert Xu May 19, 2024, 5:20 a.m. UTC

Add support for multi-byte characters in read(1) by using getmbc
from the parser.

Signed-off-by: Herbert Xu <[e-mail]>
---
 src/miscbltin.c | 19 +++++++++++++------
 src/parser.c    |  2 +-
 src/parser.h    |  1 +
 3 files changed, 15 insertions(+), 7 deletions(-)

Patch

diff --git a/src/miscbltin.c b/src/miscbltin.c
index 10d256e..5aa2b24 100644
--- a/src/miscbltin.c
+++ b/src/miscbltin.c
@@ -36,15 +36,16 @@ 
  * Miscelaneous builtins.
  */
 
+#include <ctype.h>
+#include <inttypes.h>
+#include <limits.h>
+#include <stdlib.h>
 #include <sys/types.h>		/* quad_t */
 #include <sys/param.h>		/* BSD4_4 */
 #include <sys/stat.h>
 #include <sys/time.h>
 #include <sys/resource.h>
 #include <unistd.h>
-#include <stdlib.h>
-#include <ctype.h>
-#include <inttypes.h>
 
 #include "error.h"
 #include "expand.h"
@@ -151,8 +152,10 @@  readcmd(int argc, char **argv)
 	goto start;
 
 	for (;;) {
+		unsigned ml;
 		int c;
 
+		CHECKSTRSPACE((MB_LEN_MAX > 16 ? MB_LEN_MAX : 16) + 4, p);
 		c = pgetc();
 		if (c == PEOF) {
 			status = 1;
@@ -160,9 +163,14 @@  readcmd(int argc, char **argv)
 		}
 		if (c == '\0')
 			continue;
+		ml = getmbc(c, p, 0);
+		if (ml) {
+			p += ml;
+			goto record;
+		}
 		if (newloc >= startloc) {
 			if (c == '\n')
-				goto resetbs;
+				goto record;
 			goto put;
 		}
 		if (!rflag && c == '\\') {
@@ -172,13 +180,12 @@  readcmd(int argc, char **argv)
 		if (c == '\n')
 			break;
 put:
-		CHECKSTRSPACE(2, p);
 		if (strchr(qchars, c))
 			USTPUTC(CTLESC, p);
 		USTPUTC(c, p);
 
+record:
 		if (newloc >= startloc) {
-resetbs:
 			recordregion(startloc, newloc, 0);
 start:
 			startloc = p - (char *)stackblock();
diff --git a/src/parser.c b/src/parser.c
index 71d61f3..d368adc 100644
--- a/src/parser.c
+++ b/src/parser.c
@@ -883,7 +883,7 @@  static void synstack_pop(struct synstack **stack)
 	*stack = (*stack)->next;
 }
 
-static unsigned getmbc(int c, char *out, int mode)
+unsigned getmbc(int c, char *out, int mode)
 {
 	char *const start = out;
 	mbstate_t mbst = {};
diff --git a/src/parser.h b/src/parser.h
index 14bfc4f..7a9605b 100644
--- a/src/parser.h
+++ b/src/parser.h
@@ -95,6 +95,7 @@  const char *getprompt(void *);
 const char *const *findkwd(const char *);
 char *endofname(const char *);
 const char *expandstr(const char *);
+unsigned getmbc(int c, char *out, int mode);
 
 static inline int
 goodname(const char *p)