Attached is a small patch to $SUBJECT.
In master, only single-byte characters are allowed as an escape. Of
course, with the patch it must still be a single character, but it may
be multi-byte.
Regards,
Jeff Davis
*** a/src/backend/utils/adt/regexp.c
--- b/src/backend/utils/adt/regexp.c
***************
*** 688,698 **** similar_escape(PG_FUNCTION_ARGS)
elen = VARSIZE_ANY_EXHDR(esc_text);
if (elen == 0)
e = NULL; /* no escape character */
! else if (elen != 1)
! ereport(ERROR,
! (errcode(ERRCODE_INVALID_ESCAPE_SEQUENCE),
! errmsg("invalid escape string"),
! errhint("Escape string must be empty or one character.")));
}
/*----------
--- 688,704 ----
elen = VARSIZE_ANY_EXHDR(esc_text);
if (elen == 0)
e = NULL; /* no escape character */
! else
! {
! int escape_mblen = pg_verify_mbstr_len(GetDatabaseEncoding(), e,
! elen, false);
!
! if (escape_mblen > 1)
! ereport(ERROR,
! (errcode(ERRCODE_INVALID_ESCAPE_SEQUENCE),
! errmsg("invalid escape string"),
! errhint("Escape string must be empty or one character.")));
! }
}
/*----------
***************
*** 722,781 **** similar_escape(PG_FUNCTION_ARGS)
while (plen > 0)
{
! char pchar = *p;
! if (afterescape)
{
! if (pchar == '"' && !incharclass) /* for SUBSTRING patterns */
! *r++ = ((nquotes++ % 2) == 0) ? '(' : ')';
! else
{
*r++ = '\\';
*r++ = pchar;
}
! afterescape = false;
! }
! else if (e && pchar == *e)
! {
! /* SQL99 escape character; do not send to output */
! afterescape = true;
}
! else if (incharclass)
{
! if (pchar == '\\')
*r++ = '\\';
! *r++ = pchar;
! if (pchar == ']')
! incharclass = false;
! }
! else if (pchar == '[')
! {
! *r++ = pchar;
! incharclass = true;
! }
! else if (pchar == '%')
! {
! *r++ = '.';
! *r++ = '*';
! }
! else if (pchar == '_')
! *r++ = '.';
! else if (pchar == '(')
! {
! /* convert to non-capturing parenthesis */
! *r++ = '(';
! *r++ = '?';
! *r++ = ':';
! }
! else if (pchar == '\\' || pchar == '.' ||
! pchar == '^' || pchar == '$')
! {
! *r++ = '\\';
! *r++ = pchar;
}
- else
- *r++ = pchar;
- p++, plen--;
}
*r++ = ')';
--- 728,816 ----
while (plen > 0)
{
! char pchar = *p;
! int mblen = pg_encoding_verifymb(GetDatabaseEncoding(), p, plen);
!
! Assert(mblen > 0);
! if (mblen == 1)
{
! if (afterescape)
! {
! if (pchar == '"' && !incharclass) /* for SUBSTRING patterns */
! *r++ = ((nquotes++ % 2) == 0) ? '(' : ')';
! else
! {
! *r++ = '\\';
! *r++ = pchar;
! }
! afterescape = false;
! }
! else if (e && pchar == *e)
! {
! /* SQL99 escape character; do not send to output */
! afterescape = true;
! }
! else if (incharclass)
! {
! if (pchar == '\\')
! *r++ = '\\';
! *r++ = pchar;
! if (pchar == ']')
! incharclass = false;
! }
! else if (pchar == '[')
! {
! *r++ = pchar;
! incharclass = true;
! }
! else if (pchar == '%')
! {
! *r++ = '.';
! *r++ = '*';
! }
! else if (pchar == '_')
! *r++ = '.';
! else if (pchar == '(')
! {
! /* convert to non-capturing parenthesis */
! *r++ = '(';
! *r++ = '?';
! *r++ = ':';
! }
! else if (pchar == '\\' || pchar == '.' ||
! pchar == '^' || pchar == '$')
{
*r++ = '\\';
*r++ = pchar;
}
! else
! *r++ = pchar;
! p++, plen--;
}
! else
{
! if (afterescape)
! {
*r++ = '\\';
! memcpy(r, p, mblen);
! r += mblen;
! afterescape = false;
! }
! else if (e && elen == mblen && memcmp(e, p, mblen) == 0)
! {
! /* SQL99 escape character; do not send to output */
! afterescape = true;
! }
! else
! {
! memcpy(r, p, mblen);
! r += mblen;
! }
!
! p += mblen;
! plen -= mblen;
}
}
*r++ = ')';
--
Sent via pgsql-hackers mailing list ([email protected])
To make changes to your subscription:
http://www.postgresql.org/mailpref/pgsql-hackers