libidn: stringprep_utf8_to_ucs4 now rejects invalid UTF-8. CVE-2015-2059submit/tizen_6.0/20210204.034552accepted/tizen/6.0/unified/20210204.104932tizen_6.0accepted/tizen_6.0_unified

Backported link: http://git.savannah.gnu.org/cgit/libidn.git/commit/?id=2e97c279
(Not apply test codes)

Change-Id: If5874e9d7f9a18f8b4e0a9c4627e303635b8ca2e

5 files changed, 124 insertions, 5 deletions

diff --git a/lib/gl/Makefile.in b/lib/gl/Makefile.in
index 67c55eb..ddd6ddb 100644
--- a/lib/gl/Makefile.in
+++ b/lib/gl/Makefile.in
@@ -80,8 +80,9 @@ host_triplet = @host@
 DIST_COMMON = $(noinst_HEADERS) $(srcdir)/Makefile.am \
 	$(srcdir)/Makefile.in $(srcdir)/gnulib.mk
 @GL_COND_LIBTOOL_TRUE@am__append_1 = $(LTLIBICONV)
-@LIBUNISTRING_COMPILE_UNISTR_U8_MBTOUCR_TRUE@am__append_2 = unistr/u8-mbtoucr.c
-@LIBUNISTRING_COMPILE_UNISTR_U8_UCTOMB_TRUE@am__append_3 = unistr/u8-uctomb.c unistr/u8-uctomb-aux.c
+@LIBUNISTRING_COMPILE_UNISTR_U8_CHECK_TRUE@am__append_2 = unistr/u8-check.c
+@LIBUNISTRING_COMPILE_UNISTR_U8_MBTOUCR_TRUE@am__append_3 = unistr/u8-mbtoucr.c
+@LIBUNISTRING_COMPILE_UNISTR_U8_UCTOMB_TRUE@am__append_4 = unistr/u8-uctomb.c unistr/u8-uctomb-aux.c
 subdir = lib/gl
 ACLOCAL_M4 = $(top_srcdir)/aclocal.m4
 am__aclocal_m4_deps = $(top_srcdir)/lib/gl/m4/gnulib-comp.m4 \
@@ -168,11 +169,13 @@ am__libgnu_la_SOURCES_DIST = c-ctype.h c-ctype.c c-strcase.h \
 	c-strcasecmp.c c-strncasecmp.c gettext.h striconv.h striconv.c \
 	unistr/u8-mbtoucr.c unistr/u8-uctomb.c unistr/u8-uctomb-aux.c
 am__dirstamp = $(am__leading_dot)dirstamp
-@LIBUNISTRING_COMPILE_UNISTR_U8_MBTOUCR_TRUE@am__objects_1 = unistr/u8-mbtoucr.lo
-@LIBUNISTRING_COMPILE_UNISTR_U8_UCTOMB_TRUE@am__objects_2 = unistr/u8-uctomb.lo \
+@LIBUNISTRING_COMPILE_UNISTR_U8_CHECK_TRUE@am__objects_1 =  \
+@LIBUNISTRING_COMPILE_UNISTR_U8_CHECK_TRUE@ unistr/u8-check.lo
+@LIBUNISTRING_COMPILE_UNISTR_U8_MBTOUCR_TRUE@am__objects_2 = unistr/u8-mbtoucr.lo
+@LIBUNISTRING_COMPILE_UNISTR_U8_UCTOMB_TRUE@am__objects_3 = unistr/u8-uctomb.lo \
 @LIBUNISTRING_COMPILE_UNISTR_U8_UCTOMB_TRUE@	unistr/u8-uctomb-aux.lo
 am_libgnu_la_OBJECTS = c-ctype.lo c-strcasecmp.lo c-strncasecmp.lo \
-	striconv.lo $(am__objects_1) $(am__objects_2)
+	striconv.lo $(am__objects_1) $(am__objects_2) $(am__objects_3)
 libgnu_la_OBJECTS = $(am_libgnu_la_OBJECTS)
 AM_V_lt = $(am__v_lt_$(V))
 am__v_lt_ = $(am__v_lt_$(AM_DEFAULT_VERBOSITY))
diff --git a/lib/gl/gnulib.mk b/lib/gl/gnulib.mk
index 3722aac..da4333f 100644
--- a/lib/gl/gnulib.mk
+++ b/lib/gl/gnulib.mk
@@ -473,6 +473,14 @@ EXTRA_DIST += unistr.in.h
 
 ## end   gnulib module unistr/base
 
+## begin gnulib module unistr/u8-check
+
+if LIBUNISTRING_COMPILE_UNISTR_U8_CHECK
+libgnu_la_SOURCES += unistr/u8-check.c
+endif
+
+## end   gnulib module unistr/u8-check
+
 ## begin gnulib module unistr/u8-mbtoucr
 
 if LIBUNISTRING_COMPILE_UNISTR_U8_MBTOUCR
diff --git a/lib/gl/m4/gnulib-cache.m4 b/lib/gl/m4/gnulib-cache.m4
index 4b88a60..9f45b54 100644
--- a/lib/gl/m4/gnulib-cache.m4
+++ b/lib/gl/m4/gnulib-cache.m4
@@ -39,6 +39,7 @@ gl_MODULES([
   stdint
   striconv
   strverscmp
+  unistr/u8-check
 ])
 gl_AVOID([iconv-h-tests string-tests wchar-tests])
 gl_SOURCE_BASE([lib/gl])
diff --git a/lib/gl/m4/gnulib-comp.m4 b/lib/gl/m4/gnulib-comp.m4
index 62cb1b2..c4832ac 100644
--- a/lib/gl/m4/gnulib-comp.m4
+++ b/lib/gl/m4/gnulib-comp.m4
@@ -168,6 +168,7 @@ if test $HAVE_STRVERSCMP = 0; then
 fi
 gl_STRING_MODULE_INDICATOR([strverscmp])
 gl_LIBUNISTRING_LIBHEADER([0.9.2], [unistr.h])
+gl_LIBUNISTRING_MODULE([0.9], [unistr/u8-check])
 gl_MODULE_INDICATOR([unistr/u8-mbtoucr])
 gl_LIBUNISTRING_MODULE([0.9], [unistr/u8-mbtoucr])
 gl_MODULE_INDICATOR([unistr/u8-uctomb])
@@ -393,6 +394,7 @@ AC_DEFUN([lgl_FILE_LIST], [
   lib/string.in.h
   lib/strverscmp.c
   lib/unistr.in.h
+  lib/unistr/u8-check.c
   lib/unistr/u8-mbtoucr.c
   lib/unistr/u8-uctomb-aux.c
   lib/unistr/u8-uctomb.c
diff --git a/lib/gl/unistr/u8-check.c b/lib/gl/unistr/u8-check.c
new file mode 100644
index 0000000..0e87f11
--- /dev/null
+++ b/lib/gl/unistr/u8-check.c
@@ -0,0 +1,105 @@
+/* Check UTF-8 string.
+   Copyright (C) 2002, 2006-2007, 2009-2015 Free Software Foundation, Inc.
+   Written by Bruno Haible <bruno@clisp.org>, 2002.
+
+   This program is free software: you can redistribute it and/or modify it
+   under the terms of the GNU Lesser General Public License as published
+   by the Free Software Foundation; either version 2.1 of the License, or
+   (at your option) any later version.
+
+   This program is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+   Lesser General Public License for more details.
+
+   You should have received a copy of the GNU Lesser General Public License
+   along with this program.  If not, see <http://www.gnu.org/licenses/>.  */
+
+#include <config.h>
+
+/* Specification.  */
+#include "unistr.h"
+
+const uint8_t *
+u8_check (const uint8_t *s, size_t n)
+{
+  const uint8_t *s_end = s + n;
+
+  while (s < s_end)
+    {
+      /* Keep in sync with unistr.h and u8-mbtouc-aux.c.  */
+      uint8_t c = *s;
+
+      if (c < 0x80)
+        {
+          s++;
+          continue;
+        }
+      if (c >= 0xc2)
+        {
+          if (c < 0xe0)
+            {
+              if (s + 2 <= s_end
+                  && (s[1] ^ 0x80) < 0x40)
+                {
+                  s += 2;
+                  continue;
+                }
+            }
+          else if (c < 0xf0)
+            {
+              if (s + 3 <= s_end
+                  && (s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40
+                  && (c >= 0xe1 || s[1] >= 0xa0)
+                  && (c != 0xed || s[1] < 0xa0))
+                {
+                  s += 3;
+                  continue;
+                }
+            }
+          else if (c < 0xf8)
+            {
+              if (s + 4 <= s_end
+                  && (s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40
+                  && (s[3] ^ 0x80) < 0x40
+                  && (c >= 0xf1 || s[1] >= 0x90)
+#if 1
+                  && (c < 0xf4 || (c == 0xf4 && s[1] < 0x90))
+#endif
+                 )
+                {
+                  s += 4;
+                  continue;
+                }
+            }
+#if 0
+          else if (c < 0xfc)
+            {
+              if (s + 5 <= s_end
+                  && (s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40
+                  && (s[3] ^ 0x80) < 0x40 && (s[4] ^ 0x80) < 0x40
+                  && (c >= 0xf9 || s[1] >= 0x88))
+                {
+                  s += 5;
+                  continue;
+                }
+            }
+          else if (c < 0xfe)
+            {
+              if (s + 6 <= s_end
+                  && (s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40
+                  && (s[3] ^ 0x80) < 0x40 && (s[4] ^ 0x80) < 0x40
+                  && (s[5] ^ 0x80) < 0x40
+                  && (c >= 0xfd || s[1] >= 0x84))
+                {
+                  s += 6;
+                  continue;
+                }
+            }
+#endif
+        }
+      /* invalid or incomplete multibyte character */
+      return s;
+    }
+  return NULL;
+}