sbase

commit 73577f10a0076dfa361776ead28621f59772154c
parent 1c462012e421df677aed06a68545467757e7453b
Author: FRIGN <dev@frign.de>
Date:   Wed, 11 Feb 2015 21:32:09 +0100

Scrap chartorunearr(), introducing utftorunestr()

Interface and function as proposed by cls.

The reasoning behind this function is that cls expressed his
interest to keep memory allocation out of libutf, which is a
very good motive.
This simplifies the function a lot and should also increase the
speed a bit, but the most important factor here is that there's
no malloc anywhere in libutf, making it a lot smaller and more
robust with a smaller attack-surface.

Look at the paste(1) and tr(1) changes for an idiomatic way to
allocate the right amount of space for the Rune-array.

Diffstat:
M
Makefile
 | 
2
+-
D
libutf/chartorunearr.c
 | 
27
---------------------------
A
libutf/utftorunestr.c
 | 
13
+++++++++++++
M
paste.c
 | 
3
++-
M
tr.c
 | 
3
++-
M
utf.h
 | 
4
++--

6 files changed, 20 insertions(+), 32 deletions(-)
diff --git a/Makefile b/Makefile
@@ -22,7 +22,7 @@ LIBUTFSRC =\
 	libutf/rune.c\
 	libutf/runetype.c\
 	libutf/utf.c\
-	libutf/chartorunearr.c\
+	libutf/utftorunestr.c\
 	libutf/fgetrune.c\
 	libutf/fputrune.c\
 	libutf/isalnumrune.c\
diff --git a/libutf/chartorunearr.c b/libutf/chartorunearr.c
@@ -1,27 +0,0 @@
-/* See LICENSE file for copyright and license details. */
-#include <stdlib.h>
-#include <string.h>
-
-#include "../util.h"
-#include "../utf.h"
-
-int
-chartorunearr(const char *str, Rune **r)
-{
-	size_t len = strlen(str), rlen, roff, ret = 1, i;
-	Rune s;
-
-	for (rlen = 0, roff = 0; roff < len && ret; rlen++) {
-		ret = charntorune(&s, str + roff, MAX(UTFmax, len - roff));
-		roff += ret;
-	}
-
-	*r = emalloc(rlen * sizeof(Rune) + 1);
-	(*r)[rlen] = 0;
-
-	for (i = 0, roff = 0; roff < len && i < rlen; i++) {
-		roff += charntorune(&(*r)[i], str + roff, MAX(UTFmax, len - roff));
-	}
-
-	return rlen;
-}
diff --git a/libutf/utftorunestr.c b/libutf/utftorunestr.c
@@ -0,0 +1,13 @@
+/* See LICENSE file for copyright and license details. */
+#include "../utf.h"
+
+int
+utftorunestr(const char *str, Rune *r)
+{
+	int i, n;
+
+	for(i = 0; (n = chartorune(&r[i], str)) && r[i]; i++)
+		str += n;
+
+	return i;
+}
diff --git a/paste.c b/paste.c
@@ -110,7 +110,8 @@ main(int argc, char *argv[])
 
 	/* populate delimiters */
 	unescape(adelim);
-	len = chartorunearr(adelim, &delim);
+	delim = emalloc((utflen(adelim) + 1) * sizeof(*delim));
+	len = utftorunestr(adelim, delim);
 
 	/* populate file list */
 	dsc = emalloc(argc * sizeof(*dsc));
diff --git a/tr.c b/tr.c
@@ -79,7 +79,8 @@ makeset(char *str, struct range **set, int (**check)(Rune))
 
 	/* rstr defines at most len ranges */
 	unescape(str);
-	len = chartorunearr(str, &rstr);
+	rstr = emalloc((utflen(str) + 1) * sizeof(*rstr));
+	len = utftorunestr(str, rstr);
 	*set = emalloc(len * sizeof(**set));
 
 	for (i = 0; i < len; i++) {
diff --git a/utf.h b/utf.h
@@ -59,9 +59,9 @@ int isxdigitrune(Rune);
 Rune tolowerrune(Rune);
 Rune toupperrune(Rune);
 
+int utftorunestr(const char*, Rune *);
+
 int fgetrune(Rune *, FILE *);
 int efgetrune(Rune *, FILE *, const char *);
 int fputrune(const Rune *, FILE *);
 int efputrune(const Rune *, FILE *, const char *);
-
-int chartorunearr(const char*, Rune **);