aboutsummaryrefslogtreecommitdiffstats
path: root/crypto/asn1/a_utf8.c
diff options
context:
space:
mode:
authorDr. Stephen Henson <steve@openssl.org>1999-09-04 17:19:55 +0000
committerDr. Stephen Henson <steve@openssl.org>1999-09-04 17:19:55 +0000
commitaef838fc957afefc4d49a360f1ab77b14595f27c (patch)
treeee95048ee99db1b62be8baf7710b8fb19c6e49b2 /crypto/asn1/a_utf8.c
parentb74ba295da96a0aebefd52161629230329265c68 (diff)
downloadopenssl-aef838fc957afefc4d49a360f1ab77b14595f27c.tar.gz
New UTF8 utility functions to parse/generate UTF8 strings.
Diffstat (limited to 'crypto/asn1/a_utf8.c')
-rw-r--r--crypto/asn1/a_utf8.c149
1 files changed, 149 insertions, 0 deletions
diff --git a/crypto/asn1/a_utf8.c b/crypto/asn1/a_utf8.c
index 4a8a92e9e4..6179bd09a3 100644
--- a/crypto/asn1/a_utf8.c
+++ b/crypto/asn1/a_utf8.c
@@ -81,3 +81,152 @@ ASN1_UTF8STRING *d2i_ASN1_UTF8STRING(ASN1_UTF8STRING **a, unsigned char **pp,
return(ret);
}
+
+/* UTF8 utilities */
+
+/* This parses a UTF8 string one character at a time. It is passed a pointer
+ * to the string and the length of the string. It sets 'value' to the value of
+ * the current character. It returns the number of characters read or a
+ * negative error code:
+ * -1 = string too short
+ * -2 = illegal character
+ * -3 = subsequent characters not of the form 10xxxxxx
+ * -4 = character encoded incorrectly (not minimal length).
+ */
+
+int UTF8_getc(unsigned char *str, int len, unsigned long *val)
+{
+ unsigned char *p;
+ unsigned long value;
+ int ret;
+ if(len <= 0) return 0;
+ p = str;
+
+ /* Check syntax and work out the encoded value (if correct) */
+ if((*p & 0x80) == 0) {
+ value = *p++ & 0x7f;
+ ret = 1;
+ } else if((*p & 0xe0) == 0xc0) {
+ if(len < 2) return -1;
+ if((p[1] & 0xc0) != 0x80) return -3;
+ value = (*p++ & 0x1f) << 6;
+ value |= *p++ & 0x3f;
+ if(value < 0x80) return -4;
+ ret = 2;
+ } else if((*p & 0xf0) == 0xe0) {
+ if(len < 3) return -1;
+ if( ((p[1] & 0xc0) != 0x80)
+ || ((p[2] & 0xc0) != 0x80) ) return -3;
+ value = (*p++ & 0xf) << 12;
+ value |= (*p++ & 0x3f) << 6;
+ value |= *p++ & 0x3f;
+ if(value < 0x800) return -4;
+ ret = 3;
+ } else if((*p & 0xf8) == 0xf0) {
+ if(len < 4) return -1;
+ if( ((p[1] & 0xc0) != 0x80)
+ || ((p[2] & 0xc0) != 0x80)
+ || ((p[3] & 0xc0) != 0x80) ) return -3;
+ value = (*p++ & 0x7) << 18;
+ value |= (*p++ & 0x3f) << 12;
+ value |= (*p++ & 0x3f) << 6;
+ value |= *p++ & 0x3f;
+ if(value < 0x10000) return -4;
+ ret = 4;
+ } else if((*p & 0xfc) == 0xf8) {
+ if(len < 5) return -1;
+ if( ((p[1] & 0xc0) != 0x80)
+ || ((p[2] & 0xc0) != 0x80)
+ || ((p[3] & 0xc0) != 0x80)
+ || ((p[4] & 0xc0) != 0x80) ) return -3;
+ value = (*p++ & 0x3) << 24;
+ value |= (*p++ & 0x3f) << 18;
+ value |= (*p++ & 0x3f) << 12;
+ value |= (*p++ & 0x3f) << 6;
+ value |= *p++ & 0x3f;
+ if(value < 0x200000) return -4;
+ ret = 5;
+ } else if((*p & 0xfe) == 0xfc) {
+ if(len < 6) return -1;
+ if( ((p[1] & 0xc0) != 0x80)
+ || ((p[2] & 0xc0) != 0x80)
+ || ((p[3] & 0xc0) != 0x80)
+ || ((p[4] & 0xc0) != 0x80)
+ || ((p[5] & 0xc0) != 0x80) ) return -3;
+ value = (*p++ & 0x1) << 30;
+ value |= (*p++ & 0x3f) << 24;
+ value |= (*p++ & 0x3f) << 18;
+ value |= (*p++ & 0x3f) << 12;
+ value |= (*p++ & 0x3f) << 6;
+ value |= *p++ & 0x3f;
+ if(value < 0x4000000) return -4;
+ ret = 6;
+ } else return -2;
+ *val = value;
+ return ret;
+}
+
+/* This takes a character 'value' and writes the UTF8 encoded value in
+ * 'str' where 'str' is a buffer containing 'len' characters. Returns
+ * the number of characters written or -1 if 'len' is too small. 'str' can
+ * be set to NULL in which case it just returns the number of characters.
+ * It will need at most 6 characters.
+ */
+
+int UTF8_putc(unsigned char *str, int len, unsigned long value)
+{
+ if(!str) len = 6; /* Maximum we will need */
+ else if(len <= 0) return -1;
+ if(value < 0x80) {
+ if(str) *str = value;
+ return 1;
+ }
+ if(value < 0x800) {
+ if(len < 2) return -1;
+ if(str) {
+ *str++ = ((value >> 6) & 0x1f) | 0xc0;
+ *str = (value & 0x3f) | 0x80;
+ }
+ return 2;
+ }
+ if(value < 0x10000) {
+ if(len < 3) return -1;
+ if(str) {
+ *str++ = ((value >> 12) & 0xf) | 0xe0;
+ *str++ = ((value >> 6) & 0x3f) | 0x80;
+ *str = (value & 0x3f) | 0x80;
+ }
+ return 3;
+ }
+ if(value < 0x200000) {
+ if(len < 4) return -1;
+ if(str) {
+ *str++ = ((value >> 18) & 0x7) | 0xf0;
+ *str++ = ((value >> 12) & 0x3f) | 0x80;
+ *str++ = ((value >> 6) & 0x3f) | 0x80;
+ *str = (value & 0x3f) | 0x80;
+ }
+ return 4;
+ }
+ if(value < 0x4000000) {
+ if(len < 5) return -1;
+ if(str) {
+ *str++ = ((value >> 24) & 0x3) | 0xf8;
+ *str++ = ((value >> 18) & 0x3f) | 0x80;
+ *str++ = ((value >> 12) & 0x3f) | 0x80;
+ *str++ = ((value >> 6) & 0x3f) | 0x80;
+ *str = (value & 0x3f) | 0x80;
+ }
+ return 5;
+ }
+ if(len < 6) return -1;
+ if(str) {
+ *str++ = ((value >> 30) & 0x1) | 0xfc;
+ *str++ = ((value >> 24) & 0x3f) | 0x80;
+ *str++ = ((value >> 18) & 0x3f) | 0x80;
+ *str++ = ((value >> 12) & 0x3f) | 0x80;
+ *str++ = ((value >> 6) & 0x3f) | 0x80;
+ *str = (value & 0x3f) | 0x80;
+ }
+ return 6;
+}