From 1309450668aa571dee97f4373f9555b4fddcf1aa Mon Sep 17 00:00:00 2001 From: Fazlul Shahriar Date: Tue, 29 Oct 2019 10:04:06 -0400 Subject: awk: split record into runes for empty FS (#292) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit awk was splitting records into bytes instead of runes for empty FS. For example, this was printing only the first byte of the utf-8 encoding of é: echo é | awk 'BEGIN{FS=""}{print $1}' The change just copies how the `split` function handles runes. Originally reported by kris on twitter: https://twitter.com/p9luv/status/1180436083433201665 --- src/cmd/awk/lib.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) (limited to 'src/cmd/awk') diff --git a/src/cmd/awk/lib.c b/src/cmd/awk/lib.c index 6a6849c5..3eb30687 100644 --- a/src/cmd/awk/lib.c +++ b/src/cmd/awk/lib.c @@ -29,6 +29,7 @@ THIS SOFTWARE. #include #include #include +#include #include "awk.h" #include "y.tab.h" @@ -293,15 +294,19 @@ void fldbld(void) /* create fields from current record */ } *fr = 0; } else if ((sep = *inputFS) == 0) { /* new: FS="" => 1 char/field */ - for (i = 0; *r != 0; r++) { - char buf[2]; + int nb; + for (i = 0; *r != 0; r += nb) { + Rune rr; + char buf[UTFmax+1]; + i++; if (i > nfields) growfldtab(i); if (freeable(fldtab[i])) xfree(fldtab[i]->sval); - buf[0] = *r; - buf[1] = 0; + nb = chartorune(&rr, r); + memmove(buf, r, nb); + buf[nb] = '\0'; fldtab[i]->sval = tostring(buf); fldtab[i]->tval = FLD | STR; } -- cgit v1.2.3