/*
* Internal yylex function. This wraps the core lexer and adds one feature:
* a token pushback stack. We also make a couple of trivial single-token
* translations from what the core lexer does to what we want, in particular
* interfacing from the core_YYSTYPE to YYSTYPE union.
*/
static int
internal_yylex(TokenAuxData *auxdata)
{
int token;
const char *yytext;
if (num_pushbacks > 0)
{
num_pushbacks--;
token = pushback_token[num_pushbacks];
*auxdata = pushback_auxdata[num_pushbacks];
}
else
{
token = core_yylex(&auxdata->lval.core_yystype,
&auxdata->lloc,
yyscanner);
/* remember the length of yytext before it gets changed */
yytext = core_yy.scanbuf + auxdata->lloc;
auxdata->leng = strlen(yytext);
/* Check for << >> and #, which the core considers operators */
if (token == Op)
{
if (strcmp(auxdata->lval.str, "<<") == 0)
token = LESS_LESS;
else if (strcmp(auxdata->lval.str, ">>") == 0)
token = GREATER_GREATER;
else if (strcmp(auxdata->lval.str, "#") == 0)
token = '#';
}
/* The core returns PARAM as ival, but we treat it like IDENT */
else if (token == PARAM)
{
auxdata->lval.str = pstrdup(yytext);
}
}
return token;
}
/*
* norm_yylex: core_yylex with replacing some tokens.
*/
static int
norm_yylex(char *str, core_YYSTYPE *yylval, YYLTYPE *yylloc, core_yyscan_t yyscanner)
{
int tok;
PG_TRY();
{
tok = core_yylex(yylval, yylloc, yyscanner);
}
PG_CATCH();
{
/*
* Error might occur during parsing quoted tokens that chopped
* halfway. Just ignore the rest of this query even if there might
* be other reasons for parsing to fail.
*/
FlushErrorState();
return -1;
}
PG_END_TRY();
/*
* '?' alone is assumed to be an IDENT. If there's a real
* operator '?', this should be confused but there's hardly be.
*/
if (tok == Op && str[*yylloc] == '?' &&
strchr(OPCHARS, str[*yylloc + 1]) == NULL)
tok = SCONST;
/*
* Replace tokens with '=' if the operator is consists of two or
* more opchars only. Assuming that opchars do not compose a token
* with non-opchars, check the first char only is sufficient.
*/
if (tok == Op && strchr(OPCHARS, str[*yylloc]) != NULL)
tok = '=';
return tok;
}
/*
* 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;
}
/*
* Given a valid SQL string and an array of constant-location records,
* fill in the textual lengths of those constants.
*
* The constants may use any allowed constant syntax, such as float literals,
* bit-strings, single-quoted strings and dollar-quoted strings. This is
* accomplished by using the public API for the core scanner.
*
* It is the caller's job to ensure that the string is a valid SQL statement
* with constants at the indicated locations. Since in practice the string
* has already been parsed, and the locations that the caller provides will
* have originated from within the authoritative parser, this should not be
* a problem.
*
* Duplicate constant pointers are possible, and will have their lengths
* marked as '-1', so that they are later ignored. (Actually, we assume the
* lengths were initialized as -1 to start with, and don't change them here.)
*
* N.B. There is an assumption that a '-' character at a Const location begins
* a negative numeric constant. This precludes there ever being another
* reason for a constant to start with a '-'.
*/
static void
fill_in_constant_lengths(pgssConstLocations *jstate, const char *query)
{
pgssLocationLen *locs;
core_yyscan_t yyscanner;
core_yy_extra_type yyextra;
core_YYSTYPE yylval;
YYLTYPE yylloc;
int last_loc = -1;
int i;
/*
* Sort the records by location so that we can process them in order while
* scanning the query text.
*/
if (jstate->clocations_count > 1)
qsort(jstate->clocations, jstate->clocations_count,
sizeof(pgssLocationLen), comp_location);
locs = jstate->clocations;
/* initialize the flex scanner --- should match raw_parser() */
yyscanner = scanner_init(query,
&yyextra,
ScanKeywords,
NumScanKeywords);
/* Search for each constant, in sequence */
for (i = 0; i < jstate->clocations_count; i++)
{
int loc = locs[i].location;
int tok;
Assert(loc >= 0);
if (loc <= last_loc)
continue; /* Duplicate constant, ignore */
/* Lex tokens until we find the desired constant */
for (;;)
{
tok = core_yylex(&yylval, &yylloc, yyscanner);
/* We should not hit end-of-string, but if we do, behave sanely */
if (tok == 0)
break; /* out of inner for-loop */
/*
* We should find the token position exactly, but if we somehow
* run past it, work with that.
*/
if (yylloc >= loc)
{
if (query[loc] == '-')
{
/*
* It's a negative value - this is the one and only case
* where we replace more than a single token.
*
* Do not compensate for the core system's special-case
* adjustment of location to that of the leading '-'
* operator in the event of a negative constant. It is
* also useful for our purposes to start from the minus
* symbol. In this way, queries like "select * from foo
* where bar = 1" and "select * from foo where bar = -2"
* will have identical normalized query strings.
*/
tok = core_yylex(&yylval, &yylloc, yyscanner);
if (tok == 0)
break; /* out of inner for-loop */
}
/*
* We now rely on the assumption that flex has placed a zero
* byte after the text of the current token in scanbuf.
*/
locs[i].length = (int) strlen(yyextra.scanbuf + loc);
/* Quoted string with Unicode escapes
*
* The lexer consumes trailing whitespace in order to find UESCAPE, but if there
* is no UESCAPE it has still consumed it - don't include it in constant length.
*/
if (locs[i].length > 4 && /* U&'' */
(yyextra.scanbuf[loc] == 'u' || yyextra.scanbuf[loc] == 'U') &&
yyextra.scanbuf[loc + 1] == '&' && yyextra.scanbuf[loc + 2] == '\'')
{
int j = locs[i].length - 1; /* Skip the \0 */
for (; j >= 0 && scanner_isspace(yyextra.scanbuf[loc + j]); j--) {}
locs[i].length = j + 1; /* Count the \0 */
}
break; /* out of inner for-loop */
}
}
/* If we hit end-of-string, give up, leaving remaining lengths -1 */
if (tok == 0)
break;
last_loc = loc;
}
scanner_finish(yyscanner);
}
/*
* 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;
}
