Movatterモバイル変換

[0]ホーム
URL:

Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

 Sign up
Appearance settings

Commitfd15dba

Browse files
committed
Fix encode(...bytea..., 'escape') so that it converts all high-bit-set byte
values into \nnn octal escape sequences. When the database encoding ismultibyte this is *necessary* to avoid generating invalidly encoded text.Even in a single-byte encoding, the old behavior seems very hazardous ---consider for example what happens if the text is transferred to anotherdatabase with a different encoding. Decoding would then yield some otherbytea value than what was encoded, which is surely undesirable. Per gripefrom Hernan Gonzalez.Backpatch to 8.3, but not further. This is a bit of a judgment call, but Imake it on these grounds: pre-8.3 we don't really have much encoding safetyanyway because of the convert() function family, and we would also have muchhigher risk of breaking existing apps that may not be expecting this behavior.8.3 is still new enough that we can probably get away with making this changein the function's behavior.
1 parentbc93919 commitfd15dba

File tree

1 file changed

+21
-16
lines changed

1 file changed

+21
-16
lines changed

‎src/backend/utils/adt/encode.c

Lines changed: 21 additions & 16 deletions
Original file line numberDiff line numberDiff line change
@@ -7,7 +7,7 @@
77
*
88
*
99
* IDENTIFICATION
10-
* $PostgreSQL: pgsql/src/backend/utils/adt/encode.c,v 1.20 2008/01/01 19:45:52 momjian Exp $
10+
* $PostgreSQL: pgsql/src/backend/utils/adt/encode.c,v 1.21 2008/02/26 02:54:08 tgl Exp $
1111
*
1212
*-------------------------------------------------------------------------
1313
*/
@@ -26,7 +26,7 @@ struct pg_encoding
2626
unsigned(*decode) (constchar*data,unsigneddlen,char*res);
2727
};
2828

29-
staticstructpg_encoding*pg_find_encoding(constchar*name);
29+
staticconststructpg_encoding*pg_find_encoding(constchar*name);
3030

3131
/*
3232
* SQL functions.
@@ -42,7 +42,7 @@ binary_encode(PG_FUNCTION_ARGS)
4242
intdatalen,
4343
resultlen,
4444
res;
45-
structpg_encoding*enc;
45+
conststructpg_encoding*enc;
4646

4747
datalen=VARSIZE(data)-VARHDRSZ;
4848

@@ -78,7 +78,7 @@ binary_decode(PG_FUNCTION_ARGS)
7878
intdatalen,
7979
resultlen,
8080
res;
81-
structpg_encoding*enc;
81+
conststructpg_encoding*enc;
8282

8383
datalen=VARSIZE(data)-VARHDRSZ;
8484

@@ -348,10 +348,13 @@ b64_dec_len(const char *src, unsigned srclen)
348348
* Minimally escape bytea to text.
349349
* De-escape text to bytea.
350350
*
351-
* Only two characters are escaped:
352-
* \0 (null) and \\ (backslash)
351+
* We must escape zero bytes and high-bit-set bytes to avoid generating
352+
* text that might be invalid in the current encoding, or that might
353+
* change to something else if passed through an encoding conversion
354+
* (leading to failing to de-escape to the original bytea value).
355+
* Also of course backslash itself has to be escaped.
353356
*
354-
* De-escapes \\ and any \### octal
357+
* De-escaping processes \\ and any \### octal
355358
*/
356359

357360
#defineVAL(CH)((CH) - '0')
@@ -366,16 +369,18 @@ esc_encode(const char *src, unsigned srclen, char *dst)
366369

367370
while (src<end)
368371
{
369-
if (*src=='\0')
372+
unsignedcharc= (unsignedchar)*src;
373+
374+
if (c=='\0'||IS_HIGHBIT_SET(c))
370375
{
371376
rp[0]='\\';
372-
rp[1]='0';
373-
rp[2]='0';
374-
rp[3]='0';
377+
rp[1]=DIG(c >>6);
378+
rp[2]=DIG((c >>3)&7);
379+
rp[3]=DIG(c&7);
375380
rp+=4;
376381
len+=4;
377382
}
378-
elseif (*src=='\\')
383+
elseif (c=='\\')
379384
{
380385
rp[0]='\\';
381386
rp[1]='\\';
@@ -384,7 +389,7 @@ esc_encode(const char *src, unsigned srclen, char *dst)
384389
}
385390
else
386391
{
387-
*rp++=*src;
392+
*rp++=c;
388393
len++;
389394
}
390395

@@ -450,7 +455,7 @@ esc_enc_len(const char *src, unsigned srclen)
450455

451456
while (src<end)
452457
{
453-
if (*src=='\0')
458+
if (*src=='\0'||IS_HIGHBIT_SET(*src))
454459
len+=4;
455460
elseif (*src=='\\')
456461
len+=2;
@@ -510,7 +515,7 @@ esc_dec_len(const char *src, unsigned srclen)
510515
* Common
511516
*/
512517

513-
staticstruct
518+
staticconststruct
514519
{
515520
constchar*name;
516521
structpg_encodingenc;
@@ -543,7 +548,7 @@ static struct
543548
}
544549
};
545550

546-
staticstructpg_encoding*
551+
staticconststructpg_encoding*
547552
pg_find_encoding(constchar*name)
548553
{
549554
inti;

0 commit comments

Comments
 (0)
[8]ページ先頭
©2009-2025 Movatter.jp