This has been added to avoid the situation where some host ctype.h functions

return true for characters > 127.  I.e. they are allowing extended ASCII
characters through which then cause problems.  E.g. marking superscript '2' as
a number then causes the common (ch - '0') conversion to number to fail
miserably.  Likewise letters with diacritical marks can also cause problems.

If a non-ASCII character set is being used (currently only EBCDIC), it is
adjusted for.

The implementation uses a single table with a bit for each of the defined
classes.  These functions accept an int argument and fail for
values out of range or for characters outside of the ASCII set.  They will
work for both signed and unsigned character inputs.

Reviewed-by: Andy Polyakov <appro@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/4102)

1 files changed, 8 insertions, 60 deletions

diff --git a/crypto/asn1/a_mbstr.c b/crypto/asn1/a_mbstr.c
index e644fe0542..949fe6c161 100644
--- a/crypto/asn1/a_mbstr.c
+++ b/crypto/asn1/a_mbstr.c
@@ -8,7 +8,7 @@
  */
 
 #include <stdio.h>
-#include <ctype.h>
+#include "internal/ctype.h"
 #include "internal/cryptlib.h"
 #include <openssl/asn1.h>
 
@@ -22,8 +22,6 @@ static int cpy_asc(unsigned long value, void *arg);
 static int cpy_bmp(unsigned long value, void *arg);
 static int cpy_univ(unsigned long value, void *arg);
 static int cpy_utf8(unsigned long value, void *arg);
-static int is_numeric(unsigned long value);
-static int is_printable(unsigned long value);
 
 /*
  * These functions take a string in UTF8, ASCII or multibyte form and a mask
@@ -271,13 +269,15 @@ static int out_utf8(unsigned long value, void *arg)
 
 static int type_str(unsigned long value, void *arg)
 {
-    unsigned long types;
-    types = *((unsigned long *)arg);
-    if ((types & B_ASN1_NUMERICSTRING) && !is_numeric(value))
+    unsigned long types = *((unsigned long *)arg);
+    const int native = value > INT_MAX ? INT_MAX : ossl_fromascii(value);
+
+    if ((types & B_ASN1_NUMERICSTRING) && !(ossl_isdigit(native)
+                                            || native == ' '))
         types &= ~B_ASN1_NUMERICSTRING;
-    if ((types & B_ASN1_PRINTABLESTRING) && !is_printable(value))
+    if ((types & B_ASN1_PRINTABLESTRING) && !ossl_isasn1print(native))
         types &= ~B_ASN1_PRINTABLESTRING;
-    if ((types & B_ASN1_IA5STRING) && (value > 127))
+    if ((types & B_ASN1_IA5STRING) && !ossl_isascii(native))
         types &= ~B_ASN1_IA5STRING;
     if ((types & B_ASN1_T61STRING) && (value > 0xff))
         types &= ~B_ASN1_T61STRING;
@@ -341,55 +341,3 @@ static int cpy_utf8(unsigned long value, void *arg)
     *p += ret;
     return 1;
 }
-
-/* Return 1 if the character is permitted in a PrintableString */
-static int is_printable(unsigned long value)
-{
-    int ch;
-    if (value > 0x7f)
-        return 0;
-    ch = (int)value;
-    /*
-     * Note: we can't use 'isalnum' because certain accented characters may
-     * count as alphanumeric in some environments.
-     */
-#ifndef CHARSET_EBCDIC
-    if ((ch >= 'a') && (ch <= 'z'))
-        return 1;
-    if ((ch >= 'A') && (ch <= 'Z'))
-        return 1;
-    if ((ch >= '0') && (ch <= '9'))
-        return 1;
-    if ((ch == ' ') || strchr("'()+,-./:=?", ch))
-        return 1;
-#else                           /* CHARSET_EBCDIC */
-    if ((ch >= os_toascii['a']) && (ch <= os_toascii['z']))
-        return 1;
-    if ((ch >= os_toascii['A']) && (ch <= os_toascii['Z']))
-        return 1;
-    if ((ch >= os_toascii['0']) && (ch <= os_toascii['9']))
-        return 1;
-    if ((ch == os_toascii[' ']) || strchr("'()+,-./:=?", os_toebcdic[ch]))
-        return 1;
-#endif                          /* CHARSET_EBCDIC */
-    return 0;
-}
-
-/* Return 1 if the character is a digit or space */
-static int is_numeric(unsigned long value)
-{
-    int ch;
-    if (value > 0x7f)
-        return 0;
-    ch = (int)value;
-#ifndef CHARSET_EBCDIC
-    if (!isdigit(ch) && ch != ' ')
-        return 0;
-#else
-    if (ch > os_toascii['9'])
-        return 0;
-    if (ch < os_toascii['0'] && ch != os_toascii[' '])
-        return 0;
-#endif
-    return 1;
-}