about summary refs log tree commit diff
path: root/inet/idna_name_classify.c
diff options
context:
space:
mode:
authorFlorian Weimer <fweimer@redhat.com>2018-05-23 15:26:19 +0200
committerFlorian Weimer <fweimer@redhat.com>2018-05-23 15:27:24 +0200
commit7f9f1ecb710eac4d65bb02785ddf288cac098323 (patch)
treeb93086996bfb5edf0221b895128ef5a6e709dead /inet/idna_name_classify.c
parent5f7b841d3aebdccc2baed27cb4b22ddb08cd7c0c (diff)
downloadglibc-7f9f1ecb710eac4d65bb02785ddf288cac098323.tar.gz
glibc-7f9f1ecb710eac4d65bb02785ddf288cac098323.tar.xz
glibc-7f9f1ecb710eac4d65bb02785ddf288cac098323.zip
Switch IDNA implementation to libidn2 [BZ #19728] [BZ #19729] [BZ #22247]
This provides an implementation of the IDNA2008 standard and fixes
CVE-2016-6261, CVE-2016-6263, CVE-2017-14062.
Diffstat (limited to 'inet/idna_name_classify.c')
-rw-r--r--inet/idna_name_classify.c75
1 files changed, 75 insertions, 0 deletions
diff --git a/inet/idna_name_classify.c b/inet/idna_name_classify.c
new file mode 100644
index 0000000000..3683e1133f
--- /dev/null
+++ b/inet/idna_name_classify.c
@@ -0,0 +1,75 @@
+/* Classify a domain name for IDNA purposes.
+   Copyright (C) 2018 Free Software Foundation, Inc.
+   This file is part of the GNU C Library.
+
+   The GNU C Library 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.
+
+   The GNU C Library 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 the GNU C Library; if not, see
+   <http://www.gnu.org/licenses/>.  */
+
+#include <errno.h>
+#include <inet/net-internal.h>
+#include <stdbool.h>
+#include <string.h>
+#include <wchar.h>
+
+enum idna_name_classification
+__idna_name_classify (const char *name)
+{
+  mbstate_t mbs;
+  memset (&mbs, 0, sizeof (mbs));
+  const char *p = name;
+  const char *end = p + strlen (p) + 1;
+  bool nonascii = false;
+  bool backslash = false;
+  while (true)
+    {
+      wchar_t wc;
+      size_t result = mbrtowc (&wc, p, end - p, &mbs);
+      if (result == 0)
+        /* NUL terminator was reached.  */
+        break;
+      else if (result == (size_t) -2)
+        /* Incomplete trailing multi-byte character.  This is an
+           encoding error becaue we received the full name.  */
+        return idna_name_encoding_error;
+      else if (result == (size_t) -1)
+        {
+          /* Other error, including EILSEQ.  */
+          if (errno == EILSEQ)
+            return idna_name_encoding_error;
+          else if (errno == ENOMEM)
+            return idna_name_memory_error;
+          else
+            return idna_name_error;
+        }
+      else
+        {
+          /* A wide character was decoded.  */
+          p += result;
+          if (wc == L'\\')
+            backslash = true;
+          else if (wc > 127)
+            nonascii = true;
+        }
+    }
+
+  if (nonascii)
+    {
+      if (backslash)
+        return idna_name_nonascii_backslash;
+      else
+        return idna_name_nonascii;
+    }
+  else
+    return idna_name_ascii;
+}