1
0
mirror of https://github.com/postgres/postgres.git synced 2025-12-09 02:08:45 +03:00
Files
postgres/src/backend/bootstrap/bootscanner.l
Tom Lane d160882a17 Fix bootstrap parser so that its keywords are unreserved words.
Mark Dilger pointed out that the bootstrap parser does not allow
any of its keywords to appear as column values unless they're quoted,
and proposed dealing with that by quoting such values in genbki.pl.
Looking closer, though, we also have that problem with respect to table,
column, and type names appearing in the .bki file: the parser would fail
if any of those matched any of its keywords.  While so far there have
been no conflicts (that I've heard of), this seems like a booby trap
waiting to catch somebody.  Rather than clutter genbki.pl with enough
quoting logic to handle all that, let's make the bootstrap parser grow
up a little bit and treat its keywords as unreserved.

Experimentation shows that it's fairly easy to do so with the exception
of _null_, which I don't have a big problem with keeping as a reserved
word.  The only change needed is that we can't have the "close" command
take an optional table name: it has to either require or forbid the
table name to avoid shift/reduce conflicts.  genbki.pl has historically
always included the table name, so I took that option.

The implementation has bootscanner.l passing forward the string value
of each keyword, in case bootparse.y needs that.  This avoids needing to
know the precise spelling of each keyword in bootparse.y, which is good
because that's not always obvious from the token name.

Discussion: https://postgr.es/m/3024FC91-DB6D-4732-B31C-DF772DF039A0@gmail.com
2018-05-05 16:23:07 -04:00

148 lines
3.8 KiB
Plaintext

%{
/*-------------------------------------------------------------------------
*
* bootscanner.l
* a lexical scanner for the bootstrap parser
*
* Portions Copyright (c) 1996-2018, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
*
*
* IDENTIFICATION
* src/backend/bootstrap/bootscanner.l
*
*-------------------------------------------------------------------------
*/
#include "postgres.h"
#include "access/attnum.h"
#include "access/htup.h"
#include "access/itup.h"
#include "access/tupdesc.h"
#include "bootstrap/bootstrap.h"
#include "catalog/pg_am.h"
#include "catalog/pg_attribute.h"
#include "catalog/pg_class.h"
#include "nodes/nodes.h"
#include "nodes/parsenodes.h"
#include "nodes/pg_list.h"
#include "nodes/primnodes.h"
#include "parser/scansup.h"
#include "rewrite/prs2lock.h"
#include "storage/block.h"
#include "storage/fd.h"
#include "storage/itemptr.h"
#include "storage/off.h"
#include "utils/rel.h"
/* Not needed now that this file is compiled as part of bootparse. */
/* #include "bootparse.h" */
/* LCOV_EXCL_START */
/* Avoid exit() on fatal scanner errors (a bit ugly -- see yy_fatal_error) */
#undef fprintf
#define fprintf(file, fmt, msg) fprintf_to_ereport(fmt, msg)
static void
fprintf_to_ereport(const char *fmt, const char *msg)
{
ereport(ERROR, (errmsg_internal("%s", msg)));
}
static int yyline = 1; /* line number for error reporting */
%}
%option 8bit
%option never-interactive
%option nodefault
%option noinput
%option nounput
%option noyywrap
%option warn
%option prefix="boot_yy"
id [-A-Za-z0-9_]+
sid \"([^\"])*\"
/*
* Keyword tokens return the keyword text (as a constant string) in yylval.kw,
* just in case that's needed because we want to treat the keyword as an
* unreserved identifier. Note that _null_ is not treated as a keyword
* for this purpose; it's the one "reserved word" in the bootstrap syntax.
*
* Notice that all the keywords are case-sensitive, and for historical
* reasons some must be upper case.
*
* String tokens return a palloc'd string in yylval.str.
*/
%%
open { yylval.kw = "open"; return OPEN; }
close { yylval.kw = "close"; return XCLOSE; }
create { yylval.kw = "create"; return XCREATE; }
OID { yylval.kw = "OID"; return OBJ_ID; }
bootstrap { yylval.kw = "bootstrap"; return XBOOTSTRAP; }
shared_relation { yylval.kw = "shared_relation"; return XSHARED_RELATION; }
without_oids { yylval.kw = "without_oids"; return XWITHOUT_OIDS; }
rowtype_oid { yylval.kw = "rowtype_oid"; return XROWTYPE_OID; }
insert { yylval.kw = "insert"; return INSERT_TUPLE; }
_null_ { return NULLVAL; }
"," { return COMMA; }
"=" { return EQUALS; }
"(" { return LPAREN; }
")" { return RPAREN; }
[\n] { yyline++; }
[\r\t ] ;
^\#[^\n]* ; /* drop everything after "#" for comments */
declare { yylval.kw = "declare"; return XDECLARE; }
build { yylval.kw = "build"; return XBUILD; }
indices { yylval.kw = "indices"; return INDICES; }
unique { yylval.kw = "unique"; return UNIQUE; }
index { yylval.kw = "index"; return INDEX; }
on { yylval.kw = "on"; return ON; }
using { yylval.kw = "using"; return USING; }
toast { yylval.kw = "toast"; return XTOAST; }
FORCE { yylval.kw = "FORCE"; return XFORCE; }
NOT { yylval.kw = "NOT"; return XNOT; }
NULL { yylval.kw = "NULL"; return XNULL; }
{id} {
yylval.str = scanstr(yytext);
return ID;
}
{sid} {
/* leading and trailing quotes are not passed to scanstr */
yytext[strlen(yytext) - 1] = '\0';
yylval.str = scanstr(yytext+1);
yytext[strlen(yytext)] = '"'; /* restore yytext */
return ID;
}
. {
elog(ERROR, "syntax error at line %d: unexpected character \"%s\"", yyline, yytext);
}
%%
/* LCOV_EXCL_STOP */
void
yyerror(const char *message)
{
elog(ERROR, "%s at line %d", message, yyline);
}