Joe Conway has an updated version of this he will be applying shortly. Thanks.
Joe, please make sure you CC this person once your patch is applied.
I just applied the attached patch to cvs head, and equivalent ones on the 7.3 and 7.4 stable branches. I also attached the output of Sergey's test program with the patch applied. Thanks for the nice, self-contained, test case!
Joe
Index: doc/src/sgml/datatype.sgml
===================================================================
RCS file: /cvsroot/pgsql-server/doc/src/sgml/datatype.sgml,v
retrieving revision 1.131
diff -c -r1.131 datatype.sgml
*** doc/src/sgml/datatype.sgml 16 Nov 2003 20:29:16 -0000 1.131
--- doc/src/sgml/datatype.sgml 29 Nov 2003 05:28:38 -0000
***************
*** 1076,1084 ****
strings are distinguished from characters strings by two
characteristics: First, binary strings specifically allow storing
octets of value zero and other <quote>non-printable</quote>
! octets. Second, operations on binary strings process the actual
! bytes, whereas the encoding and processing of character strings
! depends on locale settings.
</para>
<para>
--- 1076,1085 ----
strings are distinguished from characters strings by two
characteristics: First, binary strings specifically allow storing
octets of value zero and other <quote>non-printable</quote>
! octets (defined as octets outside the range 32 to 126).
! Second, operations on binary strings process the actual bytes,
! whereas the encoding and processing of character strings depends
! on locale settings.
</para>
<para>
***************
*** 1131,1144 ****
<entry><literal>\\</literal></entry>
</row>
</tbody>
</tgroup>
</table>
<para>
! Note that the result in each of the examples in <xref
linkend="datatype-binary-sqlesc"> was exactly one
! octet in length, even though the output representation of the zero
! octet and backslash are more than one character.
</para>
<para>
--- 1132,1156 ----
<entry><literal>\\</literal></entry>
</row>
+ <row>
+ <entry>0 to 31 and 127 to 255</entry>
+ <entry><quote>non-printable</quote> octets</entry>
+ <entry><literal>'\\<replaceable>xxx'</></literal> (octal value)</entry>
+ <entry><literal>SELECT '\\001'::bytea;</literal></entry>
+ <entry><literal>\001</literal></entry>
+ </row>
+
</tbody>
</tgroup>
</table>
<para>
! The requirement to escape <quote>non-printable</quote> octets actually
! varies depending on locale settings. In some instances you can get away
! with leaving them unescaped. Note that the result in each of the examples
! in <xref linkend="datatype-binary-sqlesc"> was exactly one octet in
! length, even though the output representation of the zero octet and
! backslash are more than one character.
</para>
<para>
***************
*** 1206,1212 ****
<row>
<entry>32 to 126</entry>
<entry><quote>printable</quote> octets</entry>
! <entry>ASCII representation</entry>
<entry><literal>SELECT '\\176'::bytea;</literal></entry>
<entry><literal>~</literal></entry>
</row>
--- 1218,1224 ----
<row>
<entry>32 to 126</entry>
<entry><quote>printable</quote> octets</entry>
! <entry>client character set representation</entry>
<entry><literal>SELECT '\\176'::bytea;</literal></entry>
<entry><literal>~</literal></entry>
</row>
Index: src/backend/utils/adt/varlena.c
===================================================================
RCS file: /cvsroot/pgsql-server/src/backend/utils/adt/varlena.c,v
retrieving revision 1.106
diff -c -r1.106 varlena.c
*** src/backend/utils/adt/varlena.c 25 Sep 2003 06:58:05 -0000 1.106
--- src/backend/utils/adt/varlena.c 29 Nov 2003 05:28:40 -0000
***************
*** 186,195 ****
{
if (*vp == '\\')
len += 2;
! else if (isprint((unsigned char) *vp))
! len++;
! else
len += 4;
}
rp = result = (char *) palloc(len);
vp = VARDATA(vlena);
--- 186,195 ----
{
if (*vp == '\\')
len += 2;
! else if ((unsigned char) *vp < 0x20 || (unsigned char) *vp > 0x7e)
len += 4;
+ else
+ len++;
}
rp = result = (char *) palloc(len);
vp = VARDATA(vlena);
***************
*** 200,208 ****
*rp++ = '\\';
*rp++ = '\\';
}
! else if (isprint((unsigned char) *vp))
! *rp++ = *vp;
! else
{
val = *vp;
rp[0] = '\\';
--- 200,206 ----
*rp++ = '\\';
*rp++ = '\\';
}
! else if ((unsigned char) *vp < 0x20 || (unsigned char) *vp > 0x7e)
{
val = *vp;
rp[0] = '\\';
***************
*** 213,218 ****
--- 211,218 ----
rp[1] = DIG(val & 03);
rp += 4;
}
+ else
+ *rp++ = *vp;
}
*rp = '\0';
PG_RETURN_CSTRING(result);
Index: src/interfaces/libpq/fe-exec.c
===================================================================
RCS file: /cvsroot/pgsql-server/src/interfaces/libpq/fe-exec.c,v
retrieving revision 1.153
diff -c -r1.153 fe-exec.c
*** src/interfaces/libpq/fe-exec.c 31 Oct 2003 17:43:10 -0000 1.153
--- src/interfaces/libpq/fe-exec.c 29 Nov 2003 05:28:45 -0000
***************
*** 2261,2267 ****
* '\0' == ASCII 0 == \\000
* '\'' == ASCII 39 == \'
* '\\' == ASCII 92 == \\\\
! * anything >= 0x80 ---> \\ooo (where ooo is an octal expression)
*/
unsigned char *
PQescapeBytea(const unsigned char *bintext, size_t binlen, size_t *bytealen)
--- 2261,2268 ----
* '\0' == ASCII 0 == \\000
* '\'' == ASCII 39 == \'
* '\\' == ASCII 92 == \\\\
! * anything < 0x20, or > 0x7e ---> \\ooo
! * (where ooo is an octal expression)
*/
unsigned char *
PQescapeBytea(const unsigned char *bintext, size_t binlen, size_t *bytealen)
***************
*** 2280,2286 ****
vp = bintext;
for (i = binlen; i > 0; i--, vp++)
{
! if (*vp == 0 || *vp >= 0x80)
len += 5; /* '5' is for '\\ooo' */
else if (*vp == '\'')
len += 2;
--- 2281,2287 ----
vp = bintext;
for (i = binlen; i > 0; i--, vp++)
{
! if (*vp < 0x20 || *vp > 0x7e)
len += 5; /* '5' is for '\\ooo' */
else if (*vp == '\'')
len += 2;
***************
*** 2299,2305 ****
for (i = binlen; i > 0; i--, vp++)
{
! if (*vp == 0 || *vp >= 0x80)
{
(void) sprintf(rp, "\\\\%03o", *vp);
rp += 5;
--- 2300,2306 ----
for (i = binlen; i > 0; i--, vp++)
{
! if (*vp < 0x20 || *vp > 0x7e)
{
(void) sprintf(rp, "\\\\%03o", *vp);
rp += 5;
[EMAIL PROTECTED] misc]# psql test -c "select name, setting from pg_settings where
name like 'lc%'"
name | setting
-------------+--------------
lc_collate | ru_RU.KOI8-R
lc_ctype | ru_RU.KOI8-R
lc_messages | ru_RU.KOI8-R
lc_monetary | ru_RU.KOI8-R
lc_numeric | ru_RU.KOI8-R
lc_time | ru_RU.KOI8-R
(6 rows)
[EMAIL PROTECTED] misc]# psql -l
List of databases
Name | Owner | Encoding
-----------+----------+-----------
template0 | postgres | SQL_ASCII
template1 | postgres | SQL_ASCII
test | postgres | KOI8
(3 rows)
[EMAIL PROTECTED] misc]# ./bytea-test test test.data
Send to server:
\\000\\001\\002\\003\\004\\005\\006\\007\\010\\016\\017\\020\\021\\022\\023\\024\\025\\026\\027\\030\\031\\032\\033\\034\\035\\036\\037!"#$%&\'()*+,-./0123456789:;<=>[EMAIL
PROTECTED]|}~\\177\\200\\201\\202\\203\\204\\205\\206\\207\\210\\211\\212\\213\\214\\215\\216\\217\\220\\221\\222\\223\\224\\225\\226\\227\\230\\231\\232\\233\\234\\235\\236\\237\\240\\241\\242\\243\\244\\245\\246\\247\\250\\251\\252\\253\\254\\255\\256\\257\\260\\261\\262\\263\\264\\265\\266\\267\\270\\271\\272\\273\\274\\275\\276\\277\\300\\301\\302\\303\\304\\305\\306\\307\\310\\311\\312\\313\\314\\315\\316\\317\\320\\321\\322\\323\\324\\325\\326\\327\\330\\331\\332\\333\\334\\335\\336\\337\\340\\341\\342\\343\\344\\345\\346\\347\\350\\351\\352\\353\\354\\355\\356\\357\\360\\361\\362\\363\\364\\365\\366\\367\\370\\371\\372\\373\\374\\375\\376\\377
Recieve from server:
\000\001\002\003\004\005\006\007\010\016\017\020\021\022\023\024\025\026\027\030\031\032\033\034\035\036\037!"#$%&'()*+,-./0123456789:;<=>[EMAIL
PROTECTED]|}~\177\200\201\202\203\204\205\206\207\210\211\212\213\214\215\216\217\220\221\222\223\224\225\226\227\230\231\232\233\234\235\236\237\240\241\242\243\244\245\246\247\250\251\252\253\254\255\256\257\260\261\262\263\264\265\266\267\270\271\272\273\274\275\276\277\300\301\302\303\304\305\306\307\310\311\312\313\314\315\316\317\320\321\322\323\324\325\326\327\330\331\332\333\334\335\336\337\340\341\342\343\344\345\346\347\350\351\352\353\354\355\356\357\360\361\362\363\364\365\366\367\370\371\372\373\374\375\376\377
Test successfully done.
---------------------------(end of broadcast)---------------------------
TIP 3: if posting/reading through Usenet, please send an appropriate
subscribe-nomail command to [EMAIL PROTECTED] so that your
message can get through to the mailing list cleanly
