123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309 |
- char *rcs_lex = "$Id: lex.c,v 2.5 1994/09/22 12:44:00 lhf Exp celes $";
- /*$Log: lex.c,v $
- * Revision 2.5 1994/09/22 12:44:00 lhf
- * added support for ugly tokens
- *
- * Revision 2.4 1994/09/05 19:14:40 celes
- * escapes \' e \" em strings; correcao do escape \\
- *
- * Revision 2.3 1994/08/17 17:41:50 celes
- * Implementacao da macro 'lua_strcmp'
- *
- * Revision 2.2 1994/08/05 19:27:41 celes
- * implementacao de dois buffer de 'yytext' para evitar bug
- * no look ahead do yacc
- *
- * Revision 2.1 1994/04/15 19:00:28 celes
- * Retirar chamada da funcao lua_findsymbol associada a cada
- * token NAME. A decisao de chamar lua_findsymbol ou lua_findconstant
- * fica a cargo do modulo "lua.stx".
- *
- * Revision 1.3 1993/12/28 16:42:29 roberto
- * "include"s de string.h e stdlib.h para evitar warnings
- *
- * Revision 1.2 1993/12/22 21:39:15 celes
- * Tratamento do token $debug e $nodebug
- *
- * Revision 1.1 1993/12/22 21:15:16 roberto
- * Initial revision
- **/
- #include <ctype.h>
- #include <math.h>
- #include <stdio.h>
- #include <stdlib.h>
- #include <string.h>
- #include "opcode.h"
- #include "inout.h"
- #include "y.tab.h"
- #define lua_strcmp(a,b) (a[0]<b[0]?(-1):(a[0]>b[0]?(1):strcmp(a,b)))
- #define next() { current = input(); }
- #define save(x) { *yytextLast++ = (x); }
- #define save_and_next() { save(current); next(); }
- static int current;
- static char yytext[2][256];
- static char *yytextLast;
- static int currentText = 0;
- static Input input;
- void lua_setinput (Input fn)
- {
- current = ' ';
- input = fn;
- }
- char *lua_lasttext (void)
- {
- *yytextLast = 0;
- return yytext[currentText];
- }
- /* The reserved words must be listed in lexicographic order */
- static struct
- {
- char *name;
- int token;
- } reserved [] = {
- {"and", AND},
- {"do", DO},
- {"else", ELSE},
- {"elseif", ELSEIF},
- {"end", END},
- {"function", FUNCTION},
- {"if", IF},
- {"local", LOCAL},
- {"nil", NIL},
- {"not", NOT},
- {"or", OR},
- {"repeat", REPEAT},
- {"return", RETURN},
- {"then", THEN},
- {"until", UNTIL},
- {"while", WHILE} };
- enum
- {
- U_and=128,
- U_do,
- U_else,
- U_elseif,
- U_end,
- U_function,
- U_if,
- U_local,
- U_nil,
- U_not,
- U_or,
- U_repeat,
- U_return,
- U_then,
- U_until,
- U_while,
- U_le = '<'+128,
- U_ge = '>'+128,
- U_ne = '~'+128,
- U_sc = '.'+128
- };
- #define RESERVEDSIZE (sizeof(reserved)/sizeof(reserved[0]))
- static int findReserved (char *name)
- {
- int l = 0;
- int h = RESERVEDSIZE - 1;
- while (l <= h)
- {
- int m = (l+h)/2;
- int comp = lua_strcmp(name, reserved[m].name);
- if (comp < 0)
- h = m-1;
- else if (comp == 0)
- return reserved[m].token;
- else
- l = m+1;
- }
- return 0;
- }
- int yylex ()
- {
- currentText = !currentText;
- while (1)
- {
- yytextLast = yytext[currentText];
- #if 0
- fprintf(stderr,"'%c' %d\n",current,current);
- #endif
- switch (current)
- {
- case '\n': lua_linenumber++;
- case ' ':
- case '\t':
- next();
- continue;
- case '$':
- next();
- while (isalnum(current) || current == '_')
- save_and_next();
- *yytextLast = 0;
- if (lua_strcmp(yytext[currentText], "debug") == 0)
- {
- yylval.vInt = 1;
- return DEBUG;
- }
- else if (lua_strcmp(yytext[currentText], "nodebug") == 0)
- {
- yylval.vInt = 0;
- return DEBUG;
- }
- return WRONGTOKEN;
- case '-':
- save_and_next();
- if (current != '-') return '-';
- do { next(); } while (current != '\n' && current != 0);
- continue;
- case '=':
- save_and_next();
- if (current != '=') return '=';
- else { save_and_next(); return EQ; }
- case '<':
- save_and_next();
- if (current != '=') return '<';
- else { save_and_next(); return LE; }
- case '>':
- save_and_next();
- if (current != '=') return '>';
- else { save_and_next(); return GE; }
- case '~':
- save_and_next();
- if (current != '=') return '~';
- else { save_and_next(); return NE; }
- case '"':
- case '\'':
- {
- int del = current;
- next(); /* skip the delimiter */
- while (current != del)
- {
- switch (current)
- {
- case 0:
- case '\n':
- return WRONGTOKEN;
- case '\\':
- next(); /* do not save the '\' */
- switch (current)
- {
- case 'n': save('\n'); next(); break;
- case 't': save('\t'); next(); break;
- case 'r': save('\r'); next(); break;
- case '\'': save('\''); next(); break;
- case '"': save('"'); next(); break;
- default : save(current); next(); break;
- }
- break;
- default:
- save_and_next();
- }
- }
- next(); /* skip the delimiter */
- *yytextLast = 0;
- yylval.pChar = yytext[currentText];
- return STRING;
- }
- case 'a': case 'b': case 'c': case 'd': case 'e':
- case 'f': case 'g': case 'h': case 'i': case 'j':
- case 'k': case 'l': case 'm': case 'n': case 'o':
- case 'p': case 'q': case 'r': case 's': case 't':
- case 'u': case 'v': case 'w': case 'x': case 'y':
- case 'z':
- case 'A': case 'B': case 'C': case 'D': case 'E':
- case 'F': case 'G': case 'H': case 'I': case 'J':
- case 'K': case 'L': case 'M': case 'N': case 'O':
- case 'P': case 'Q': case 'R': case 'S': case 'T':
- case 'U': case 'V': case 'W': case 'X': case 'Y':
- case 'Z':
- case '_':
- {
- int res;
- do { save_and_next(); } while (isalnum(current) || current == '_');
- *yytextLast = 0;
- res = findReserved(yytext[currentText]);
- if (res) return res;
- yylval.pChar = yytext[currentText];
- return NAME;
- }
- case '.':
- save_and_next();
- if (current == '.')
- {
- save_and_next();
- return CONC;
- }
- else if (!isdigit(current)) return '.';
- /* current is a digit: goes through to number */
- goto fraction;
- case '0': case '1': case '2': case '3': case '4':
- case '5': case '6': case '7': case '8': case '9':
- do { save_and_next(); } while (isdigit(current));
- if (current == '.') save_and_next();
- fraction: while (isdigit(current)) save_and_next();
- if (current == 'e' || current == 'E')
- {
- save_and_next();
- if (current == '+' || current == '-') save_and_next();
- if (!isdigit(current)) return WRONGTOKEN;
- do { save_and_next(); } while (isdigit(current));
- }
- *yytextLast = 0;
- yylval.vFloat = atof(yytext[currentText]);
- return NUMBER;
- case U_and: next(); return AND;
- case U_do: next(); return DO;
- case U_else: next(); return ELSE;
- case U_elseif: next(); return ELSEIF;
- case U_end: next(); return END;
- case U_function: next(); return FUNCTION;
- case U_if: next(); return IF;
- case U_local: next(); return LOCAL;
- case U_nil: next(); return NIL;
- case U_not: next(); return NOT;
- case U_or: next(); return OR;
- case U_repeat: next(); return REPEAT;
- case U_return: next(); return RETURN;
- case U_then: next(); return THEN;
- case U_until: next(); return UNTIL;
- case U_while: next(); return WHILE;
- case U_le: next(); return LE;
- case U_ge: next(); return GE;
- case U_ne: next(); return NE;
- case U_sc: next(); return CONC;
- default: /* also end of file */
- {
- save_and_next();
- return yytext[currentText][0];
- }
- }
- }
- }
|