mirror of
https://github.com/postgres/postgres.git
synced 2025-11-04 20:11:56 +03:00
d809fd0008
There are a couple of places in our grammar that fail to be strict LALR(1), by requiring more than a single token of lookahead to decide what to do. Up to now we've dealt with that by using a filter between the lexer and parser that merges adjacent tokens into one in the places where two tokens of lookahead are necessary. But that creates a number of user-visible anomalies, for instance that you can't name a CTE "ordinality" because "WITH ordinality AS ..." triggers folding of WITH and ORDINALITY into one token. I realized that there's a better way. In this patch, we still do the lookahead basically as before, but we never merge the second token into the first; we replace just the first token by a special lookahead symbol when one of the lookahead pairs is seen. This requires a couple extra productions in the grammar, but it involves fewer special tokens, so that the grammar tables come out a bit smaller than before. The filter logic is no slower than before, perhaps a bit faster. I also fixed the filter logic so that when backing up after a lookahead, the current token's terminator is correctly restored; this eliminates some weird behavior in error message issuance, as is shown by the one change in existing regression test outputs. I believe that this patch entirely eliminates odd behaviors caused by lookahead for WITH. It doesn't really improve the situation for NULLS followed by FIRST/LAST unfortunately: those sequences still act like a reserved word, even though there are cases where they should be seen as two ordinary identifiers, eg "SELECT nulls first FROM ...". I experimented with additional grammar hacks but couldn't find any simple solution for that. Still, this is better than before, and it seems much more likely that we *could* somehow solve the NULLS case on the basis of this filter behavior than the previous one.
76 lines
2.2 KiB
C
76 lines
2.2 KiB
C
/*-------------------------------------------------------------------------
|
|
*
|
|
* gramparse.h
|
|
* Shared definitions for the "raw" parser (flex and bison phases only)
|
|
*
|
|
* NOTE: this file is only meant to be included in the core parsing files,
|
|
* ie, parser.c, gram.y, scan.l, and keywords.c. Definitions that are needed
|
|
* outside the core parser should be in parser.h.
|
|
*
|
|
*
|
|
* Portions Copyright (c) 1996-2015, PostgreSQL Global Development Group
|
|
* Portions Copyright (c) 1994, Regents of the University of California
|
|
*
|
|
* src/include/parser/gramparse.h
|
|
*
|
|
*-------------------------------------------------------------------------
|
|
*/
|
|
|
|
#ifndef GRAMPARSE_H
|
|
#define GRAMPARSE_H
|
|
|
|
#include "nodes/parsenodes.h"
|
|
#include "parser/scanner.h"
|
|
|
|
/*
|
|
* NB: include gram.h only AFTER including scanner.h, because scanner.h
|
|
* is what #defines YYLTYPE.
|
|
*/
|
|
#include "parser/gram.h"
|
|
|
|
/*
|
|
* The YY_EXTRA data that a flex scanner allows us to pass around. Private
|
|
* state needed for raw parsing/lexing goes here.
|
|
*/
|
|
typedef struct base_yy_extra_type
|
|
{
|
|
/*
|
|
* Fields used by the core scanner.
|
|
*/
|
|
core_yy_extra_type core_yy_extra;
|
|
|
|
/*
|
|
* State variables for base_yylex().
|
|
*/
|
|
bool have_lookahead; /* is lookahead info valid? */
|
|
int lookahead_token; /* one-token lookahead */
|
|
core_YYSTYPE lookahead_yylval; /* yylval for lookahead token */
|
|
YYLTYPE lookahead_yylloc; /* yylloc for lookahead token */
|
|
char *lookahead_end; /* end of current token */
|
|
char lookahead_hold_char; /* to be put back at *lookahead_end */
|
|
|
|
/*
|
|
* State variables that belong to the grammar.
|
|
*/
|
|
List *parsetree; /* final parse result is delivered here */
|
|
} base_yy_extra_type;
|
|
|
|
/*
|
|
* In principle we should use yyget_extra() to fetch the yyextra field
|
|
* from a yyscanner struct. However, flex always puts that field first,
|
|
* and this is sufficiently performance-critical to make it seem worth
|
|
* cheating a bit to use an inline macro.
|
|
*/
|
|
#define pg_yyget_extra(yyscanner) (*((base_yy_extra_type **) (yyscanner)))
|
|
|
|
|
|
/* from parser.c */
|
|
extern int base_yylex(YYSTYPE *lvalp, YYLTYPE *llocp,
|
|
core_yyscan_t yyscanner);
|
|
|
|
/* from gram.y */
|
|
extern void parser_init(base_yy_extra_type *yyext);
|
|
extern int base_yyparse(core_yyscan_t yyscanner);
|
|
|
|
#endif /* GRAMPARSE_H */
|