/* * Intermediate filter between parser and base lexer (base_yylex in scan.l). * * The filter is needed because in some cases SQL92 requires more than one * token lookahead. We reduce these cases to one-token lookahead by combining * tokens here, in order to keep the grammar LR(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 ... */ int yylex(void) { int cur_token; /* Get next token --- we might already have it */ if (have_lookahead) { cur_token = lookahead_token; have_lookahead = false; } else cur_token = base_yylex(); /* Do we need to look ahead for a possible multiword token? */ switch (cur_token) { case UNION: /* UNION JOIN must be reduced to a single UNIONJOIN token */ lookahead_token = base_yylex(); if (lookahead_token == JOIN) cur_token = UNIONJOIN; else have_lookahead = true; break; default: break; } return cur_token; }
/* * 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; }
/* * Intermediate filter between parser and base lexer (base_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. */ int filtered_base_yylex(void) { int cur_token; int next_token; YYSTYPE cur_yylval; YYLTYPE cur_yylloc; /* Get next token --- we might already have it */ if (have_lookahead) { cur_token = lookahead_token; base_yylval = lookahead_yylval; base_yylloc = lookahead_yylloc; have_lookahead = false; } else cur_token = base_yylex(); /* 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 = base_yylval; cur_yylloc = base_yylloc; next_token = base_yylex(); 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 */ lookahead_token = next_token; lookahead_yylval = base_yylval; lookahead_yylloc = base_yylloc; have_lookahead = true; /* and back up the output info to cur_token */ base_yylval = cur_yylval; base_yylloc = cur_yylloc; break; } break; case WITH: /* * WITH TIME, CASCADED, LOCAL, or CHECK must be reduced to one token * * XXX an alternative way is to recognize just WITH_TIME and put * the ugliness into the datetime datatype productions instead of * WITH CHECK OPTION. However that requires promoting WITH to a * fully reserved word. If we ever have to do that anyway * (perhaps for SQL99 recursive queries), come back and simplify * this code. */ cur_yylval = base_yylval; cur_yylloc = base_yylloc; next_token = base_yylex(); switch (next_token) { case TIME: cur_token = WITH_TIME; break; case CASCADED: cur_token = WITH_CASCADED; break; case LOCAL: cur_token = WITH_LOCAL; break; case CHECK: cur_token = WITH_CHECK; break; default: /* save the lookahead token for next time */ lookahead_token = next_token; lookahead_yylval = base_yylval; lookahead_yylloc = base_yylloc; have_lookahead = true; /* and back up the output info to cur_token */ base_yylval = cur_yylval; base_yylloc = cur_yylloc; break; } break; default: break; } return cur_token; }