/*
* Intermediate filter between parser and core lexer (core_yylex in scan.l).
*
* This filter is needed because in some cases the standard SQL grammar
* requires more than one token lookahead. We reduce these cases to one-token
* lookahead by replacing tokens here, in order to keep the grammar LALR(1).
*
* Using a filter is simpler than trying to recognize multiword tokens
* directly in scan.l, because we'd have to allow for comments between the
* words. Furthermore it's not clear how to do that without re-introducing
* scanner backtrack, which would cost more performance than this filter
* layer does.
*
* The filter also provides a convenient place to translate between
* the core_YYSTYPE and YYSTYPE representations (which are really the
* same thing anyway, but notationally they're different).
*/
int
base_yylex(YYSTYPE *lvalp, YYLTYPE *llocp, core_yyscan_t yyscanner)
{
base_yy_extra_type *yyextra = pg_yyget_extra(yyscanner);
int cur_token;
int next_token;
int cur_token_length;
YYLTYPE cur_yylloc;
/* Get next token --- we might already have it */
if (yyextra->have_lookahead)
{
cur_token = yyextra->lookahead_token;
lvalp->core_yystype = yyextra->lookahead_yylval;
*llocp = yyextra->lookahead_yylloc;
*(yyextra->lookahead_end) = yyextra->lookahead_hold_char;
yyextra->have_lookahead = false;
}
else
cur_token = core_yylex(&(lvalp->core_yystype), llocp, yyscanner);
/*
* If this token isn't one that requires lookahead, just return it. If it
* does, determine the token length. (We could get that via strlen(), but
* since we have such a small set of possibilities, hardwiring seems
* feasible and more efficient.)
*/
switch (cur_token)
{
case NOT:
cur_token_length = 3;
break;
case NULLS_P:
cur_token_length = 5;
break;
case WITH:
cur_token_length = 4;
break;
default:
return cur_token;
}
/*
* Identify end+1 of current token. core_yylex() has temporarily stored a
* '\0' here, and will undo that when we call it again. We need to redo
* it to fully revert the lookahead call for error reporting purposes.
*/
yyextra->lookahead_end = yyextra->core_yy_extra.scanbuf +
*llocp + cur_token_length;
Assert(*(yyextra->lookahead_end) == '\0');
/*
* Save and restore *llocp around the call. It might look like we could
* avoid this by just passing &lookahead_yylloc to core_yylex(), but that
* does not work because flex actually holds onto the last-passed pointer
* internally, and will use that for error reporting. We need any error
* reports to point to the current token, not the next one.
*/
cur_yylloc = *llocp;
/* Get next token, saving outputs into lookahead variables */
next_token = core_yylex(&(yyextra->lookahead_yylval), llocp, yyscanner);
yyextra->lookahead_token = next_token;
yyextra->lookahead_yylloc = *llocp;
*llocp = cur_yylloc;
/* Now revert the un-truncation of the current token */
yyextra->lookahead_hold_char = *(yyextra->lookahead_end);
*(yyextra->lookahead_end) = '\0';
yyextra->have_lookahead = true;
/* Replace cur_token if needed, based on lookahead */
switch (cur_token)
{
case NOT:
/* Replace NOT by NOT_LA if it's followed by BETWEEN, IN, etc */
switch (next_token)
{
case BETWEEN:
case IN_P:
case LIKE:
case ILIKE:
case SIMILAR:
cur_token = NOT_LA;
break;
}
break;
case NULLS_P:
/* Replace NULLS_P by NULLS_LA if it's followed by FIRST or LAST */
switch (next_token)
{
case FIRST_P:
case LAST_P:
cur_token = NULLS_LA;
break;
}
break;
case WITH:
/* Replace WITH by WITH_LA if it's followed by TIME or ORDINALITY */
switch (next_token)
{
case TIME:
case ORDINALITY:
cur_token = WITH_LA;
break;
}
break;
}
return cur_token;
}
/*
* Intermediate filter between parser and core lexer (core_yylex in scan.l).
*
* The filter is needed because in some cases the standard SQL grammar
* requires more than one token lookahead. We reduce these cases to one-token
* lookahead by combining tokens here, in order to keep the grammar LALR(1).
*
* Using a filter is simpler than trying to recognize multiword tokens
* directly in scan.l, because we'd have to allow for comments between the
* words. Furthermore it's not clear how to do it without re-introducing
* scanner backtrack, which would cost more performance than this filter
* layer does.
*
* The filter also provides a convenient place to translate between
* the core_YYSTYPE and YYSTYPE representations (which are really the
* same thing anyway, but notationally they're different).
*/
int
base_yylex(YYSTYPE *lvalp, YYLTYPE *llocp, core_yyscan_t yyscanner)
{
base_yy_extra_type *yyextra = pg_yyget_extra(yyscanner);
int cur_token;
int next_token;
core_YYSTYPE cur_yylval;
YYLTYPE cur_yylloc;
/* Get next token --- we might already have it */
if (yyextra->have_lookahead)
{
cur_token = yyextra->lookahead_token;
lvalp->core_yystype = yyextra->lookahead_yylval;
*llocp = yyextra->lookahead_yylloc;
yyextra->have_lookahead = false;
}
else
cur_token = core_yylex(&(lvalp->core_yystype), llocp, yyscanner);
/* Do we need to look ahead for a possible multiword token? */
switch (cur_token)
{
case NULLS_P:
/*
* NULLS FIRST and NULLS LAST must be reduced to one token
*/
cur_yylval = lvalp->core_yystype;
cur_yylloc = *llocp;
next_token = core_yylex(&(lvalp->core_yystype), llocp, yyscanner);
switch (next_token)
{
case FIRST_P:
cur_token = NULLS_FIRST;
break;
case LAST_P:
cur_token = NULLS_LAST;
break;
default:
/* save the lookahead token for next time */
yyextra->lookahead_token = next_token;
yyextra->lookahead_yylval = lvalp->core_yystype;
yyextra->lookahead_yylloc = *llocp;
yyextra->have_lookahead = true;
/* and back up the output info to cur_token */
lvalp->core_yystype = cur_yylval;
*llocp = cur_yylloc;
break;
}
break;
case WITH:
/*
* WITH TIME must be reduced to one token
*/
cur_yylval = lvalp->core_yystype;
cur_yylloc = *llocp;
next_token = core_yylex(&(lvalp->core_yystype), llocp, yyscanner);
switch (next_token)
{
case TIME:
cur_token = WITH_TIME;
break;
default:
/* save the lookahead token for next time */
yyextra->lookahead_token = next_token;
yyextra->lookahead_yylval = lvalp->core_yystype;
yyextra->lookahead_yylloc = *llocp;
yyextra->have_lookahead = true;
/* and back up the output info to cur_token */
lvalp->core_yystype = cur_yylval;
*llocp = cur_yylloc;
break;
}
break;
default:
break;
}
return cur_token;
}