|
|
|
|
%top{
|
|
|
|
|
/*-------------------------------------------------------------------------
|
|
|
|
|
*
|
|
|
|
|
* bootscanner.l
|
|
|
|
|
* a lexical scanner for the bootstrap parser
|
|
|
|
|
*
|
|
|
|
|
* Portions Copyright (c) 1996-2025, PostgreSQL Global Development Group
|
|
|
|
|
* Portions Copyright (c) 1994, Regents of the University of California
|
|
|
|
|
*
|
|
|
|
|
*
|
|
|
|
|
* IDENTIFICATION
|
|
|
|
|
* src/backend/bootstrap/bootscanner.l
|
|
|
|
|
*
|
|
|
|
|
*-------------------------------------------------------------------------
|
|
|
|
|
*/
|
|
|
|
|
#include "postgres.h"
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* NB: include bootparse.h only AFTER including bootstrap.h, because bootstrap.h
|
|
|
|
|
* includes node definitions needed for YYSTYPE.
|
|
|
|
|
*/
|
|
|
|
|
#include "bootstrap/bootstrap.h"
|
|
|
|
|
#include "bootparse.h"
|
|
|
|
|
#include "utils/guc.h"
|
|
|
|
|
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
%{
|
|
|
|
|
|
|
|
|
|
/* LCOV_EXCL_START */
|
|
|
|
|
|
|
|
|
|
/* Avoid exit() on fatal scanner errors (a bit ugly -- see yy_fatal_error) */
|
|
|
|
|
#undef fprintf
|
Improve handling of ereport(ERROR) and elog(ERROR).
In commit 71450d7fd6c7cf7b3e38ac56e363bff6a681973c, we added code to inform
suitably-intelligent compilers that ereport() doesn't return if the elevel
is ERROR or higher. This patch extends that to elog(), and also fixes a
double-evaluation hazard that the previous commit created in ereport(),
as well as reducing the emitted code size.
The elog() improvement requires the compiler to support __VA_ARGS__, which
should be available in just about anything nowadays since it's required by
C99. But our minimum language baseline is still C89, so add a configure
test for that.
The previous commit assumed that ereport's elevel could be evaluated twice,
which isn't terribly safe --- there are already counterexamples in xlog.c.
On compilers that have __builtin_constant_p, we can use that to protect the
second test, since there's no possible optimization gain if the compiler
doesn't know the value of elevel. Otherwise, use a local variable inside
the macros to prevent double evaluation. The local-variable solution is
inferior because (a) it leads to useless code being emitted when elevel
isn't constant, and (b) it increases the optimization level needed for the
compiler to recognize that subsequent code is unreachable. But it seems
better than not teaching non-gcc compilers about unreachability at all.
Lastly, if the compiler has __builtin_unreachable(), we can use that
instead of abort(), resulting in a noticeable code savings since no
function call is actually emitted. However, it seems wise to do this only
in non-assert builds. In an assert build, continue to use abort(), so that
the behavior will be predictable and debuggable if the "impossible"
happens.
These changes involve making the ereport and elog macros emit do-while
statement blocks not just expressions, which forces small changes in
a few call sites.
Andres Freund, Tom Lane, Heikki Linnakangas
13 years ago
|
|
|
#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)));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
%}
|
|
|
|
|
|
|
|
|
|
%option reentrant
|
|
|
|
|
%option bison-bridge
|
|
|
|
|
%option 8bit
|
|
|
|
|
%option never-interactive
|
|
|
|
|
%option nodefault
|
|
|
|
|
%option noinput
|
|
|
|
|
%option nounput
|
|
|
|
|
%option noyywrap
|
|
|
|
|
%option noyyalloc
|
|
|
|
|
%option noyyrealloc
|
|
|
|
|
%option noyyfree
|
|
|
|
|
%option warn
|
|
|
|
|
%option prefix="boot_yy"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
id [-A-Za-z0-9_]+
|
|
|
|
|
sid \'([^']|\'\')*\'
|
|
|
|
|
|
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
8 years ago
|
|
|
/*
|
|
|
|
|
* Keyword tokens return the keyword text (as a constant string) in yylval->kw,
|
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
8 years ago
|
|
|
* 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.
|
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
8 years ago
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
%%
|
|
|
|
|
|
|
|
|
|
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; }
|
|
|
|
|
rowtype_oid { yylval->kw = "rowtype_oid"; return XROWTYPE_OID; }
|
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
8 years ago
|
|
|
|
|
|
|
|
insert { yylval->kw = "insert"; return INSERT_TUPLE; }
|
|
|
|
|
|
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
8 years ago
|
|
|
_null_ { return NULLVAL; }
|
|
|
|
|
|
|
|
|
|
"," { return COMMA; }
|
|
|
|
|
"=" { return EQUALS; }
|
|
|
|
|
"(" { return LPAREN; }
|
|
|
|
|
")" { return RPAREN; }
|
|
|
|
|
|
|
|
|
|
[\n] { yylineno++; }
|
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
8 years ago
|
|
|
[\r\t ] ;
|
|
|
|
|
|
|
|
|
|
^\#[^\n]* ; /* drop everything after "#" for comments */
|
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
8 years ago
|
|
|
|
|
|
|
|
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 = pstrdup(yytext);
|
|
|
|
|
return ID;
|
|
|
|
|
}
|
|
|
|
|
{sid} {
|
|
|
|
|
/* strip quotes and escapes */
|
|
|
|
|
yylval->str = DeescapeQuotedString(yytext);
|
|
|
|
|
return ID;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
. {
|
|
|
|
|
elog(ERROR, "syntax error at line %d: unexpected character \"%s\"", yylineno, yytext);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
%%
|
|
|
|
|
|
|
|
|
|
/* LCOV_EXCL_STOP */
|
|
|
|
|
|
|
|
|
|
void
|
|
|
|
|
boot_yyerror(yyscan_t yyscanner, const char *message)
|
|
|
|
|
{
|
|
|
|
|
struct yyguts_t *yyg = (struct yyguts_t *) yyscanner; /* needed for yylineno
|
|
|
|
|
* macro */
|
|
|
|
|
|
|
|
|
|
elog(ERROR, "%s at line %d", message, yylineno);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Interface functions to make flex use palloc() instead of malloc().
|
|
|
|
|
* It'd be better to make these static, but flex insists otherwise.
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
void *
|
|
|
|
|
yyalloc(yy_size_t size, yyscan_t yyscanner)
|
|
|
|
|
{
|
|
|
|
|
return palloc(size);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
void *
|
|
|
|
|
yyrealloc(void *ptr, yy_size_t size, yyscan_t yyscanner)
|
|
|
|
|
{
|
|
|
|
|
if (ptr)
|
|
|
|
|
return repalloc(ptr, size);
|
|
|
|
|
else
|
|
|
|
|
return palloc(size);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
void
|
|
|
|
|
yyfree(void *ptr, yyscan_t yyscanner)
|
|
|
|
|
{
|
|
|
|
|
if (ptr)
|
|
|
|
|
pfree(ptr);
|
|
|
|
|
}
|