Tighten up SJIS byte sequence check. Now we reject invalid SJIS byte

sequence such as "0x95 0x27". Patches from Akio Ishida.

diff --git a/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c b/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c
index ee460b621ba424d2d8691188879ceb93b87da252..a8e90ddf81910cee22746205b665d82a59db2c39 100644 (file)
--- a/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c
+++ b/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c
@@ -6,7 +6,7 @@
  * Portions Copyright (c) 1994, Regents of the University of California
  *
  * IDENTIFICATION
- *       $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c,v 1.9.4.1 2005/06/11 02:46:16 ishii Exp $
+ *       $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c,v 1.9.4.2 2006/03/04 11:54:02 ishii Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -22,6 +22,9 @@
 #define PGSJISALTCODE 0x81ac
 #define PGEUCALTCODE 0xa2ae
 
+#define ISSJISHEAD(c) ((c >= 0x81 && c <= 0x9f) || (c >= 0xe0 && c <= 0xef))
+#define ISSJISTAIL(c) ((c >= 0x40 && c <= 0x7e) || (c >= 0x80 && c <= 0xfc))
+
 /*
  * conversion table between SJIS UDC (IBM kanji) and EUC_JP
  */
@@ -192,6 +195,11 @@ sjis2mic(unsigned char *sjis, unsigned char *p, int len)
                         * JIS X0208, X0212, user defined extended characters
                         */
                        c2 = *sjis++;
+                       if (!ISSJISHEAD(c1) || !ISSJISTAIL(c2))
+                               ereport(ERROR,
+                                               (errcode(ERRCODE_CHARACTER_NOT_IN_REPERTOIRE),
+                                       errmsg("invalid byte sequence for encoding \"SJIS\": 0x%02x%02x",
+                                                   c1, c2)));
                        k = (c1 << 8) + c2;
 /* Eiji Tokuya patched begin */
                        if (k >= 0xed40 && k < 0xf040)