changeset 354:ec0d6d58e043

uptools/libcoding: UTF-8 input conversion to 8859-1 implemented
author Mychaela Falconia <falcon@freecalypso.org>
date Mon, 05 Feb 2018 19:01:27 +0000
parents 3bcc56883b17
children 8fee530f7850
files uptools/libcoding/Makefile uptools/libcoding/utf8_decode.c
diffstat 2 files changed, 30 insertions(+), 1 deletions(-) [+]
line wrap: on
line diff
--- a/uptools/libcoding/Makefile	Mon Feb 05 17:35:49 2018 +0000
+++ b/uptools/libcoding/Makefile	Mon Feb 05 19:01:27 2018 +0000
@@ -2,7 +2,7 @@
 CFLAGS=	-O2
 OBJS=	alpha_addr.o decode_helpers.o grokdcs.o gsm7_decode.o \
 	gsm7_decode_tables.o gsm7_unpack.o gsmtime.o hexdecode.o hexdump.o \
-	number_decode.o scaddr.o ucs2_decode.o
+	number_decode.o scaddr.o ucs2_decode.o utf8_decode.o
 LIB=	libcoding.a
 
 all:	${LIB}
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/uptools/libcoding/utf8_decode.c	Mon Feb 05 19:01:27 2018 +0000
@@ -0,0 +1,29 @@
+/*
+ * This library module implements a function that converts text input
+ * from UTF-8 to ISO 8859-1, rejecting any input Unicode characters
+ * that aren't in the 8859-1 range.  The conversion in done in place.
+ */
+
+#include <sys/types.h>
+
+utf8_to_latin1(buf)
+	u_char *buf;
+{
+	u_char *ip = buf, *op = buf;
+	int c, c2;
+
+	while (c = *ip++) {
+		if (c < 0x80) {
+			*op++ = c;
+			continue;
+		}
+		if (c != 0xC2 && c != 0xC3)
+			return(-1);
+		c2 = *ip++;
+		if (c2 < 0x80 || c2 > 0xBF)
+			return(-1);
+		*op++ = ((c & 3) << 6) | (c2 & 0x3F);
+	}
+	*op = '\0';
+	return(0);
+}