1996-07-09 08:22:35 +02:00
|
|
|
/*-------------------------------------------------------------------------
|
|
|
|
*
|
1999-02-14 00:22:53 +01:00
|
|
|
* scansup.c
|
1997-09-07 07:04:48 +02:00
|
|
|
* support routines for the lex/flex scanner, used by both the normal
|
1996-07-09 08:22:35 +02:00
|
|
|
* backend as well as the bootstrap backend
|
|
|
|
*
|
2007-01-05 23:20:05 +01:00
|
|
|
* Portions Copyright (c) 1996-2007, PostgreSQL Global Development Group
|
2000-01-26 06:58:53 +01:00
|
|
|
* Portions Copyright (c) 1994, Regents of the University of California
|
1996-07-09 08:22:35 +02:00
|
|
|
*
|
|
|
|
*
|
|
|
|
* IDENTIFICATION
|
2007-01-05 23:20:05 +01:00
|
|
|
* $PostgreSQL: pgsql/src/backend/parser/scansup.c,v 1.35 2007/01/05 22:19:34 momjian Exp $
|
1996-07-09 08:22:35 +02:00
|
|
|
*
|
|
|
|
*-------------------------------------------------------------------------
|
|
|
|
*/
|
2002-09-05 02:43:07 +02:00
|
|
|
#include "postgres.h"
|
1996-08-27 09:42:29 +02:00
|
|
|
|
1996-07-09 08:22:35 +02:00
|
|
|
#include <ctype.h>
|
1997-11-26 02:14:33 +01:00
|
|
|
|
1996-07-09 08:22:35 +02:00
|
|
|
#include "parser/scansup.h"
|
2004-02-21 01:34:53 +01:00
|
|
|
#include "mb/pg_wchar.h"
|
|
|
|
|
1996-07-09 08:22:35 +02:00
|
|
|
|
|
|
|
/* ----------------
|
1997-09-07 07:04:48 +02:00
|
|
|
* scanstr
|
|
|
|
*
|
1996-07-09 08:22:35 +02:00
|
|
|
* if the string passed in has escaped codes, map the escape codes to actual
|
|
|
|
* chars
|
|
|
|
*
|
1999-09-12 00:26:47 +02:00
|
|
|
* the string returned is palloc'd and should eventually be pfree'd by the
|
|
|
|
* caller!
|
1996-07-09 08:22:35 +02:00
|
|
|
* ----------------
|
|
|
|
*/
|
|
|
|
|
1998-02-26 05:46:47 +01:00
|
|
|
char *
|
2004-02-21 01:34:53 +01:00
|
|
|
scanstr(const char *s)
|
1996-07-09 08:22:35 +02:00
|
|
|
{
|
1999-09-12 00:26:47 +02:00
|
|
|
char *newStr;
|
1997-09-08 04:41:22 +02:00
|
|
|
int len,
|
|
|
|
i,
|
|
|
|
j;
|
1996-07-09 08:22:35 +02:00
|
|
|
|
1997-09-07 07:04:48 +02:00
|
|
|
if (s == NULL || s[0] == '\0')
|
1999-09-12 00:26:47 +02:00
|
|
|
return pstrdup("");
|
1996-07-09 08:22:35 +02:00
|
|
|
|
1997-09-07 07:04:48 +02:00
|
|
|
len = strlen(s);
|
|
|
|
|
2000-04-12 19:17:23 +02:00
|
|
|
newStr = palloc(len + 1); /* string cannot get longer */
|
1999-09-12 00:26:47 +02:00
|
|
|
|
1997-09-07 07:04:48 +02:00
|
|
|
for (i = 0, j = 0; i < len; i++)
|
|
|
|
{
|
|
|
|
if (s[i] == '\'')
|
|
|
|
{
|
1999-05-25 18:15:34 +02:00
|
|
|
/*
|
2005-10-15 04:49:52 +02:00
|
|
|
* Note: if scanner is working right, unescaped quotes can only
|
|
|
|
* appear in pairs, so there should be another character.
|
1999-02-08 00:59:59 +01:00
|
|
|
*/
|
|
|
|
i++;
|
|
|
|
newStr[j] = s[i];
|
1997-09-07 07:04:48 +02:00
|
|
|
}
|
1999-02-08 00:59:59 +01:00
|
|
|
else if (s[i] == '\\')
|
1997-09-07 07:04:48 +02:00
|
|
|
{
|
1999-02-08 00:59:59 +01:00
|
|
|
i++;
|
|
|
|
switch (s[i])
|
1997-09-07 07:04:48 +02:00
|
|
|
{
|
1999-02-08 00:59:59 +01:00
|
|
|
case 'b':
|
|
|
|
newStr[j] = '\b';
|
|
|
|
break;
|
|
|
|
case 'f':
|
|
|
|
newStr[j] = '\f';
|
|
|
|
break;
|
|
|
|
case 'n':
|
|
|
|
newStr[j] = '\n';
|
|
|
|
break;
|
|
|
|
case 'r':
|
|
|
|
newStr[j] = '\r';
|
|
|
|
break;
|
|
|
|
case 't':
|
|
|
|
newStr[j] = '\t';
|
|
|
|
break;
|
|
|
|
case '0':
|
|
|
|
case '1':
|
|
|
|
case '2':
|
|
|
|
case '3':
|
|
|
|
case '4':
|
|
|
|
case '5':
|
|
|
|
case '6':
|
|
|
|
case '7':
|
|
|
|
{
|
|
|
|
int k;
|
|
|
|
long octVal = 0;
|
1996-07-09 08:22:35 +02:00
|
|
|
|
1999-02-08 00:59:59 +01:00
|
|
|
for (k = 0;
|
1997-09-07 07:04:48 +02:00
|
|
|
s[i + k] >= '0' && s[i + k] <= '7' && k < 3;
|
1999-02-08 00:59:59 +01:00
|
|
|
k++)
|
|
|
|
octVal = (octVal << 3) + (s[i + k] - '0');
|
|
|
|
i += k - 1;
|
|
|
|
newStr[j] = ((char) octVal);
|
|
|
|
}
|
|
|
|
break;
|
|
|
|
default:
|
|
|
|
newStr[j] = s[i];
|
|
|
|
break;
|
|
|
|
} /* switch */
|
|
|
|
} /* s[i] == '\\' */
|
|
|
|
else
|
|
|
|
newStr[j] = s[i];
|
1997-09-07 07:04:48 +02:00
|
|
|
j++;
|
1996-07-09 08:22:35 +02:00
|
|
|
}
|
1997-09-07 07:04:48 +02:00
|
|
|
newStr[j] = '\0';
|
|
|
|
return newStr;
|
1996-07-09 08:22:35 +02:00
|
|
|
}
|
2004-02-21 01:34:53 +01:00
|
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
* downcase_truncate_identifier() --- do appropriate downcasing and
|
|
|
|
* truncation of an unquoted identifier. Optionally warn of truncation.
|
|
|
|
*
|
|
|
|
* Returns a palloc'd string containing the adjusted identifier.
|
|
|
|
*
|
|
|
|
* Note: in some usages the passed string is not null-terminated.
|
|
|
|
*
|
|
|
|
* Note: the API of this function is designed to allow for downcasing
|
|
|
|
* transformations that increase the string length, but we don't yet
|
|
|
|
* support that. If you want to implement it, you'll need to fix
|
|
|
|
* SplitIdentifierString() in utils/adt/varlena.c.
|
|
|
|
*/
|
|
|
|
char *
|
|
|
|
downcase_truncate_identifier(const char *ident, int len, bool warn)
|
|
|
|
{
|
|
|
|
char *result;
|
|
|
|
int i;
|
|
|
|
|
|
|
|
result = palloc(len + 1);
|
2004-08-29 07:07:03 +02:00
|
|
|
|
2004-02-21 01:34:53 +01:00
|
|
|
/*
|
2005-10-15 04:49:52 +02:00
|
|
|
* SQL99 specifies Unicode-aware case normalization, which we don't yet
|
|
|
|
* have the infrastructure for. Instead we use tolower() to provide a
|
|
|
|
* locale-aware translation. However, there are some locales where this
|
|
|
|
* is not right either (eg, Turkish may do strange things with 'i' and
|
|
|
|
* 'I'). Our current compromise is to use tolower() for characters with
|
|
|
|
* the high bit set, and use an ASCII-only downcasing for 7-bit
|
|
|
|
* characters.
|
2004-02-21 01:34:53 +01:00
|
|
|
*/
|
|
|
|
for (i = 0; i < len; i++)
|
|
|
|
{
|
2004-08-29 07:07:03 +02:00
|
|
|
unsigned char ch = (unsigned char) ident[i];
|
2004-02-21 01:34:53 +01:00
|
|
|
|
|
|
|
if (ch >= 'A' && ch <= 'Z')
|
|
|
|
ch += 'a' - 'A';
|
2005-12-25 03:14:19 +01:00
|
|
|
else if (IS_HIGHBIT_SET(ch) && isupper(ch))
|
2004-02-21 01:34:53 +01:00
|
|
|
ch = tolower(ch);
|
|
|
|
result[i] = (char) ch;
|
|
|
|
}
|
|
|
|
result[i] = '\0';
|
|
|
|
|
|
|
|
if (i >= NAMEDATALEN)
|
|
|
|
truncate_identifier(result, i, warn);
|
|
|
|
|
|
|
|
return result;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* truncate_identifier() --- truncate an identifier to NAMEDATALEN-1 bytes.
|
|
|
|
*
|
|
|
|
* The given string is modified in-place, if necessary. A warning is
|
|
|
|
* issued if requested.
|
|
|
|
*
|
|
|
|
* We require the caller to pass in the string length since this saves a
|
|
|
|
* strlen() call in some common usages.
|
|
|
|
*/
|
|
|
|
void
|
|
|
|
truncate_identifier(char *ident, int len, bool warn)
|
|
|
|
{
|
|
|
|
if (len >= NAMEDATALEN)
|
|
|
|
{
|
2004-08-29 07:07:03 +02:00
|
|
|
len = pg_mbcliplen(ident, len, NAMEDATALEN - 1);
|
2004-02-21 01:34:53 +01:00
|
|
|
if (warn)
|
|
|
|
ereport(NOTICE,
|
|
|
|
(errcode(ERRCODE_NAME_TOO_LONG),
|
2005-10-15 04:49:52 +02:00
|
|
|
errmsg("identifier \"%s\" will be truncated to \"%.*s\"",
|
|
|
|
ident, len, ident)));
|
2004-02-21 01:34:53 +01:00
|
|
|
ident[len] = '\0';
|
|
|
|
}
|
|
|
|
}
|
2006-09-22 23:39:58 +02:00
|
|
|
|
|
|
|
/*
|
|
|
|
* scanner_isspace() --- return TRUE if flex scanner considers char whitespace
|
|
|
|
*
|
|
|
|
* This should be used instead of the potentially locale-dependent isspace()
|
|
|
|
* function when it's important to match the lexer's behavior.
|
|
|
|
*
|
|
|
|
* In principle we might need similar functions for isalnum etc, but for the
|
|
|
|
* moment only isspace seems needed.
|
|
|
|
*/
|
|
|
|
bool
|
|
|
|
scanner_isspace(char ch)
|
|
|
|
{
|
|
|
|
/* This must match scan.l's list of {space} characters */
|
|
|
|
/* and plpgsql's scan.l as well */
|
|
|
|
if (ch == ' ' ||
|
|
|
|
ch == '\t' ||
|
|
|
|
ch == '\n' ||
|
|
|
|
ch == '\r' ||
|
|
|
|
ch == '\f')
|
|
|
|
return true;
|
|
|
|
return false;
|
|
|
|
}
|