* Peter Eisentraut <[EMAIL PROTECTED]> [001115 10:26]:
> Larry Rosenman writes:
>
> > Ok, so what I think(?) needs to happen is the FIXME: tag needs to be
> > handled. We need to code a version of src/backend/parser/scansup.c
> > that doesn't use palloc, and also strips the apostrophes from the
> > front and end of the string? This doesn't look that hard. Do I have
> > "permission" to play with it, and submit a patch when I've got it
> > fixed?
>
> Some background information: The current
>
> name = value
>
> syntax is lexically compatible with the syntax of the SET command.
> Therefore you can't have "funny" characters in 'value' unless
> single-quoted.
I added period(.), hyphen(-), and underscore(_).
>
> Now in the context of the config file this seems overly restrictive.
> Therefore I'd agree that we relax that a bit and allow more characters to
> go into 'value' unquoted. I'm not quite sure which, but to prevent
> confusion I'd prefer no semicolons, whitespace, or equal signs, possibly
> others.
>
> This would require making 'value' a different token type from 'name',
> because the latter should not accept these characters.
done, as GUC_UNQUOTED_STRING.
>
> Additionally, the FIXME ought to be done. I'd prefer it if it accepted
> the exact same escapes and all as does the SQL parser/scanner. So it
> ought to be a copy and paste from scansup.c. I'm not excited about
> allowing double-quotes though.
Done. Added as GUC_scanstr.
Here is a patch. Comments?
Index: src/backend/utils/misc/guc-file.l
===================================================================
RCS file: /home/projects/pgsql/cvsroot/pgsql/src/backend/utils/misc/guc-file.l,v
retrieving revision 1.4
diff -c -r1.4 guc-file.l
*** src/backend/utils/misc/guc-file.l 2000/07/27 19:49:18 1.4
--- src/backend/utils/misc/guc-file.l 2000/11/15 18:13:20
***************
*** 16,21 ****
--- 16,22 ----
#include <sys/stat.h>
#include <unistd.h>
#include <errno.h>
+ #include <ctype.h>
#include "miscadmin.h"
#include "storage/fd.h"
***************
*** 32,37 ****
--- 33,39 ----
GUC_INTEGER = 3,
GUC_REAL = 4,
GUC_EQUALS = 5,
+ GUC_UNQUOTED_STRING = 6,
GUC_EOL = 99,
GUC_ERROR = 100
};
***************
*** 45,51 ****
/* prototype, so compiler is happy with our high warnings setting */
int GUC_yylex(void);
!
%}
SIGN ("-"|"+")
--- 47,53 ----
/* prototype, so compiler is happy with our high warnings setting */
int GUC_yylex(void);
! char *GUC_scanstr(char *);
%}
SIGN ("-"|"+")
***************
*** 69,76 ****
* work right. Now there are no string options, and if there were then
* the unquoted (`ID') tokens should still work. Of course this only
* affects the configuration file.
*/
! STRING \'([^'\n]|\\.)*'
%%
--- 71,83 ----
* work right. Now there are no string options, and if there were then
* the unquoted (`ID') tokens should still work. Of course this only
* affects the configuration file.
+ * LER 14NOV2000: I set it up to accept either a quoted string or a string
+ * in apostrophes. I then kill off the 1st and last characters. There is
+ * no special handling for doubled terminators or 'C' escapes.
+ * this allows most other characters to be used.
*/
! UNQUOTED_STRING {LETTER}({LETTER_OR_DIGIT}|[-._])*
! STRING (\'|\")([^'"\n]|\\.)*(\'|\")
%%
***************
*** 80,85 ****
--- 87,93 ----
{ID} return GUC_ID;
{STRING} return GUC_STRING;
+ {UNQUOTED_STRING} return GUC_UNQUOTED_STRING;
{INTEGER} return GUC_INTEGER;
{REAL} return GUC_REAL;
= return GUC_EQUALS;
***************
*** 210,220 ****
if (token == GUC_EQUALS)
token = yylex();
! if (token != GUC_ID && token != GUC_STRING && token != GUC_INTEGER
&& token != GUC_REAL)
goto parse_error;
opt_value = strdup(yytext);
if (opt_value == NULL)
goto out_of_memory;
parse_state = 2;
break;
--- 218,239 ----
if (token == GUC_EQUALS)
token = yylex();
! if (token != GUC_ID && token != GUC_STRING && token != GUC_INTEGER
&& token != GUC_REAL && token != GUC_UNQUOTED_STRING)
goto parse_error;
opt_value = strdup(yytext);
if (opt_value == NULL)
goto out_of_memory;
+ if (token == GUC_STRING)
+ {
+ /* remove the beginning and ending quote/apostrophe */
+ /* first: shift the whole shooting match down one
+ character */
+ memmove(opt_value,opt_value+1,strlen(opt_value)-1);
+ /* second: null out the 2 characters we shifted */
+ opt_value[strlen(opt_value)-2]='\0';
+ /* do the escape thing. free()'s the strdup above */
+ opt_value=GUC_scanstr(opt_value);
+ }
parse_state = 2;
break;
***************
*** 283,286 ****
--- 302,400 ----
yywrap(void)
{
return 1;
+ }
+
+ /* ----------------
+ * scanstr
+ *
+ * if the string passed in has escaped codes, map the escape codes to actual
+ * chars
+ *
+ * the string returned is palloc'd and should eventually be pfree'd by the
+ * caller!
+ * ----------------
+ */
+
+ char *
+ GUC_scanstr(char *s)
+ {
+ char *newStr;
+ int len,
+ i,
+ j;
+
+ if (s == NULL || s[0] == '\0')
+ {
+ if (s != NULL) free (s);
+ return strdup("");
+
+ }
+ len = strlen(s);
+
+ newStr = malloc(len + 1); /* string cannot get longer */
+
+ for (i = 0, j = 0; i < len; i++)
+ {
+ if (s[i] == '\'')
+ {
+
+ /*
+ * Note: if scanner is working right, unescaped quotes can
+ * only appear in pairs, so there should be another character.
+ */
+ i++;
+ newStr[j] = s[i];
+ }
+ else if (s[i] == '\\')
+ {
+ i++;
+ switch (s[i])
+ {
+ 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;
+
+ for (k = 0;
+ s[i + k] >= '0' && s[i + k]
+<= '7' && k < 3;
+ 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];
+ j++;
+ }
+ newStr[j] = '\0';
+ free(s);
+ return newStr;
}
--
Larry Rosenman http://www.lerctr.org/~ler
Phone: +1 972-414-9812 (voice) Internet: [EMAIL PROTECTED]
US Mail: 1905 Steamboat Springs Drive, Garland, TX 75044-6749
