int
main(void)
{
yy_extra_type yyextra;
int res;
int fd2;
for (int i = 0; i < NTIMES; ++i) {
yyscan_t scanner = scanner_init(stdin, &yyextra, ScanKeywords,
NumScanKeywords);
parser_init();
yyparse(scanner);
res = scanner_finish(scanner);
if (res < 0) {
return(res);
}
if (fseek(stdin, 0, SEEK_SET) < 0) {
return(0);
}
if (i == 0) {
if ((fd2 = open("/dev/null", O_WRONLY)) < 0) {
perror("open");
return(-1);
}
if (dup2(fd2,1) < 0) {
perror("dup2");
return(-1);
}
close(fd2);
}
}
return(0);
}
/*
* raw_parser
* Given a query in string form, do lexical and grammatical analysis.
*
* Returns a list of raw (un-analyzed) parse trees. The immediate elements
* of the list are always RawStmt nodes.
*/
List *
raw_parser(const char *str)
{
core_yyscan_t yyscanner;
base_yy_extra_type yyextra;
int yyresult;
/* initialize the flex scanner */
yyscanner = scanner_init(str, &yyextra.core_yy_extra,
ScanKeywords, NumScanKeywords);
/* base_yylex() only needs this much initialization */
yyextra.have_lookahead = false;
/* initialize the bison parser */
parser_init(&yyextra);
/* Parse! */
yyresult = base_yyparse(yyscanner);
/* Clean up (release memory) */
scanner_finish(yyscanner);
if (yyresult) /* error */
return NIL;
return yyextra.parsetree;
}
void
lexer_destroy(yyscan_t scanner)
{
void* extra = base_yyget_extra(scanner);
scanner_finish(scanner);
base_yylex_destroy(scanner);
free(extra);
}
/*
* Called after parsing is done to clean up after plpgsql_scanner_init()
*/
void
plpgsql_scanner_finish(void)
{
/* release storage */
scanner_finish(yyscanner);
/* avoid leaving any dangling pointers */
yyscanner = NULL;
scanorig = NULL;
}
/*
* pg_parse_string_token - get the value represented by a string literal
*
* Given the textual form of a SQL string literal, produce the represented
* value as a palloc'd string. It is caller's responsibility that the
* passed string does represent one single string literal.
*
* We export this function to avoid having plpgsql depend on internal details
* of the core grammar (such as the token code assigned to SCONST). Note
* that since the scanner isn't presently re-entrant, this cannot be used
* during use of the main parser/scanner.
*/
char *
pg_parse_string_token(const char *token)
{
int ctoken;
scanner_init(token);
ctoken = base_yylex();
if (ctoken != SCONST) /* caller error */
elog(ERROR, "expected string constant, got token code %d", ctoken);
scanner_finish();
return base_yylval.str;
}
/*
* raw_parser
* Given a query in string form, do lexical and grammatical analysis.
*
* Returns a list of raw (un-analyzed) parse trees.
*/
List *
raw_parser(const char *str)
{
int yyresult;
parsetree = NIL; /* in case grammar forgets to set it */
have_lookahead = false;
scanner_init(str);
parser_init();
yyresult = base_yyparse();
scanner_finish();
if (yyresult) /* error */
return NIL;
return parsetree;
}
/*
* raw_parser
* Given a query in string form, do lexical and grammatical analysis.
*
* Returns a list of raw (un-analyzed) parse trees.
*/
List *
raw_parser(const char *str)
{
char *sqlString;
core_yyscan_t yyscanner;
base_yy_extra_type yyextra;
int yyresult;
/* initialize the flex scanner */
yyscanner = scanner_init(str, &yyextra.core_yy_extra,
ScanKeywords, NumScanKeywords);
/* base_yylex() only needs this much initialization */
yyextra.have_lookahead = false;
/* initialize the bison parser */
parser_init(&yyextra);
/* Parse! */
yyresult = base_yyparse(yyscanner);
/* Clean up (release memory) */
scanner_finish(yyscanner);
if (yyresult) /* error */
return NIL;
/*
elog(WARNING, "Expression Tree: %s", nodeToString((const void *)yyextra.parsetree));
sqlString = toSQL((const void *)yyextra.parsetree);
elog(WARNING, "SQL Conversion: %s", sqlString);
*/
return yyextra.parsetree;
}
/*
* 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);
}
