From 11df82023be3eadafdd1c5a52cf0a5d890c968f4 Mon Sep 17 00:00:00 2001
From: Ingo Schwarze <schwarze@cvs.openbsd.org>
Date: Sat, 19 Dec 2015 10:21:02 +0000
Subject: UTF-8 support: Let -f recognize non-ASCII blank characters and let -s
 count characters rather than bytes. OK zhuk@ bentley@

---
 usr.bin/uniq/uniq.1 | 12 ++++++++++--
 usr.bin/uniq/uniq.c | 35 ++++++++++++++++++++++++++++-------
 2 files changed, 38 insertions(+), 9 deletions(-)

(limited to 'usr.bin/uniq')

diff --git a/usr.bin/uniq/uniq.1 b/usr.bin/uniq/uniq.1
index 7858404e913..d7e275372e2 100644
--- a/usr.bin/uniq/uniq.1
+++ b/usr.bin/uniq/uniq.1
@@ -1,4 +1,4 @@
-.\"	$OpenBSD: uniq.1,v 1.17 2010/09/03 11:09:29 jmc Exp $
+.\"	$OpenBSD: uniq.1,v 1.18 2015/12/19 10:21:01 schwarze Exp $
 .\"	$NetBSD: uniq.1,v 1.5 1994/12/06 07:51:15 jtc Exp $
 .\"
 .\" Copyright (c) 1991, 1993
@@ -33,7 +33,7 @@
 .\"
 .\"     @(#)uniq.1	8.1 (Berkeley) 6/6/93
 .\"
-.Dd $Mdocdate: September 3 2010 $
+.Dd $Mdocdate: December 19 2015 $
 .Dt UNIQ 1
 .Os
 .Sh NAME
@@ -114,6 +114,14 @@ A file name of
 .Ql -
 denotes the standard input or the standard output
 .Pq depending on its position on the command line .
+.Sh ENVIRONMENT
+.Bl -tag -width LC_CTYPE
+.It Ev LC_CTYPE
+The character set
+.Xr locale 1 .
+Determines which groups of bytes are treated as characters
+and which characters are considered blank.
+.El
 .Sh EXIT STATUS
 .Ex -std uniq
 .Sh SEE ALSO
diff --git a/usr.bin/uniq/uniq.c b/usr.bin/uniq/uniq.c
index 43e462e1463..7e4d7b86a11 100644
--- a/usr.bin/uniq/uniq.c
+++ b/usr.bin/uniq/uniq.c
@@ -1,4 +1,4 @@
-/*	$OpenBSD: uniq.c,v 1.23 2015/11/02 20:25:42 mmcc Exp $	*/
+/*	$OpenBSD: uniq.c,v 1.24 2015/12/19 10:21:01 schwarze Exp $	*/
 /*	$NetBSD: uniq.c,v 1.7 1995/08/31 22:03:48 jtc Exp $	*/
 
 /*
@@ -37,10 +37,13 @@
 #include <err.h>
 #include <errno.h>
 #include <limits.h>
+#include <locale.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
 #include <unistd.h>
+#include <wchar.h>
+#include <wctype.h>
 
 #define	MAXLINELEN	(8 * 1024)
 
@@ -61,6 +64,8 @@ main(int argc, char *argv[])
 	int ch;
 	char *prevline, *thisline;
 
+	setlocale(LC_CTYPE, "");
+
 	if (pledge("stdio rpath wpath cpath", NULL) == -1)
 		err(1, "pledge");
 
@@ -176,16 +181,32 @@ show(FILE *ofp, char *str)
 char *
 skip(char *str)
 {
+	wchar_t wc;
 	int nchars, nfields;
+	int len;
+	int field_started;
 
 	for (nfields = numfields; nfields && *str; nfields--) {
-		while (isblank((unsigned char)*str))
-			str++;
-		while (*str && !isblank((unsigned char)*str))
-			str++;
+		/* Skip one field, including preceding blanks. */
+		for (field_started = 0; *str != '\0'; str += len) {
+			if ((len = mbtowc(&wc, str, MB_CUR_MAX)) == -1) {
+				(void)mbtowc(NULL, NULL, MB_CUR_MAX);
+				wc = L'?';
+				len = 1;
+			}
+			if (iswblank(wc)) {
+				if (field_started)
+					break;
+			} else
+				field_started = 1;
+		}
 	}
-	for (nchars = numchars; nchars-- && *str && *str != '\n'; ++str)
-		;
+
+	/* Skip some additional characters. */
+	for (nchars = numchars; nchars-- && *str != '\0'; str += len)
+		if ((len = mblen(str, MB_CUR_MAX)) == -1)
+			len = 1;
+
 	return (str);
 }
 
-- 
cgit v1.2.3