c_cpp C（编译器）有四个函数
Posted
tags:
篇首语：本文由小常识网(cha138.com)小编为大家整理，主要介绍了c_cpp C（编译器）有四个函数相关的知识，希望对你有一定的参考价值。
// c4.c - C in four functions
// char, int, and pointer types
// if, while, return, and expression statements
// just enough features to allow self-compilation and a bit more
// Written by Robert Swierczek
#include <stdio.h>
#include <stdlib.h>
#include <memory.h>
#include <unistd.h>
char *p, *lp, // current position in source code
*data; // data/bss pointer
int *e, *le, // current position in emitted code
*id, // currently parsed identifier
*sym, // symbol table (simple list of identifiers)
tk, // current token
ival, // current token value
ty, // current expression type
loc, // local variable offset
line, // current line number
src, // print source and assembly flag
debug; // print executed instructions
// tokens and classes (operators last and in precedence order)
enum {
Num = 128, Fun, Sys, Glo, Loc, Id,
Char, Else, Enum, If, Int, Return, Sizeof, While,
Assign, Cond, Lor, Lan, Or, Xor, And, Eq, Ne, Lt, Gt, Le, Ge, Shl, Shr, Add, Sub, Mul, Div, Mod, Inc, Dec, Brak
};
// opcodes
enum { LEA ,IMM ,JMP ,JSR ,BZ ,BNZ ,ENT ,ADJ ,LEV ,LI ,LC ,SI ,SC ,PSH ,
OR ,XOR ,AND ,EQ ,NE ,LT ,GT ,LE ,GE ,SHL ,SHR ,ADD ,SUB ,MUL ,DIV ,MOD ,
OPEN,READ,CLOS,PRTF,MALC,MSET,MCMP,EXIT };
// types
enum { CHAR, INT, PTR };
// identifier offsets (since we can't create an ident struct)
enum { Tk, Hash, Name, Class, Type, Val, HClass, HType, HVal, Idsz };
void next()
{
char *pp;
while (tk = *p) {
++p;
if (tk == '\n') {
if (src) {
printf("%d: %.*s", line, p - lp, lp);
lp = p;
while (le < e) {
printf("%8.4s", &"LEA ,IMM ,JMP ,JSR ,BZ ,BNZ ,ENT ,ADJ ,LEV ,LI ,LC ,SI ,SC ,PSH ,"
"OR ,XOR ,AND ,EQ ,NE ,LT ,GT ,LE ,GE ,SHL ,SHR ,ADD ,SUB ,MUL ,DIV ,MOD ,"
"OPEN,READ,CLOS,PRTF,MALC,MSET,MCMP,EXIT,"[*++le * 5]);
if (*le <= ADJ) printf(" %d\n", *++le); else printf("\n");
}
}
++line;
}
else if (tk == '#') {
while (*p != 0 && *p != '\n') ++p;
}
else if ((tk >= 'a' && tk <= 'z') || (tk >= 'A' && tk <= 'Z') || tk == '_') {
pp = p - 1;
while ((*p >= 'a' && *p <= 'z') || (*p >= 'A' && *p <= 'Z') || (*p >= '0' && *p <= '9') || *p == '_')
tk = tk * 147 + *p++;
tk = (tk << 6) + (p - pp);
id = sym;
while (id[Tk]) {
if (tk == id[Hash] && !memcmp((char *)id[Name], pp, p - pp)) { tk = id[Tk]; return; }
id = id + Idsz;
}
id[Name] = (int)pp;
id[Hash] = tk;
tk = id[Tk] = Id;
return;
}
else if (tk >= '0' && tk <= '9') {
if (ival = tk - '0') { while (*p >= '0' && *p <= '9') ival = ival * 10 + *p++ - '0'; }
else if (*p == 'x' || *p == 'X') {
while ((tk = *++p) && ((tk >= '0' && tk <= '9') || (tk >= 'a' && tk <= 'f') || (tk >= 'A' && tk <= 'F')))
ival = ival * 16 + (tk & 15) + (tk >= 'A' ? 9 : 0);
}
else { while (*p >= '0' && *p <= '7') ival = ival * 8 + *p++ - '0'; }
tk = Num;
return;
}
else if (tk == '/') {
if (*p == '/') {
++p;
while (*p != 0 && *p != '\n') ++p;
}
else {
tk = Div;
return;
}
}
else if (tk == '\'' || tk == '"') {
pp = data;
while (*p != 0 && *p != tk) {
if ((ival = *p++) == '\\') {
if ((ival = *p++) == 'n') ival = '\n';
}
if (tk == '"') *data++ = ival;
}
++p;
if (tk == '"') ival = (int)pp; else tk = Num;
return;
}
else if (tk == '=') { if (*p == '=') { ++p; tk = Eq; } else tk = Assign; return; }
else if (tk == '+') { if (*p == '+') { ++p; tk = Inc; } else tk = Add; return; }
else if (tk == '-') { if (*p == '-') { ++p; tk = Dec; } else tk = Sub; return; }
else if (tk == '!') { if (*p == '=') { ++p; tk = Ne; } return; }
else if (tk == '<') { if (*p == '=') { ++p; tk = Le; } else if (*p == '<') { ++p; tk = Shl; } else tk = Lt; return; }
else if (tk == '>') { if (*p == '=') { ++p; tk = Ge; } else if (*p == '>') { ++p; tk = Shr; } else tk = Gt; return; }
else if (tk == '|') { if (*p == '|') { ++p; tk = Lor; } else tk = Or; return; }
else if (tk == '&') { if (*p == '&') { ++p; tk = Lan; } else tk = And; return; }
else if (tk == '^') { tk = Xor; return; }
else if (tk == '%') { tk = Mod; return; }
else if (tk == '*') { tk = Mul; return; }
else if (tk == '[') { tk = Brak; return; }
else if (tk == '?') { tk = Cond; return; }
else if (tk == '~' || tk == ';' || tk == '{' || tk == '}' || tk == '(' || tk == ')' || tk == ']' || tk == ',' || tk == ':') return;
}
}
void expr(int lev)
{
int t, *d;
if (!tk) { printf("%d: unexpected eof in expression\n", line); exit(-1); }
else if (tk == Num) { *++e = IMM; *++e = ival; next(); ty = INT; }
else if (tk == '"') {
*++e = IMM; *++e = ival; next();
while (tk == '"') next();
data = (char *)((int)data + sizeof(int) & -sizeof(int)); ty = PTR;
}
else if (tk == Sizeof) {
next(); if (tk == '(') next(); else { printf("%d: open paren expected in sizeof\n", line); exit(-1); }
ty = INT; if (tk == Int) next(); else if (tk == Char) { next(); ty = CHAR; }
while (tk == Mul) { next(); ty = ty + PTR; }
if (tk == ')') next(); else { printf("%d: close paren expected in sizeof\n", line); exit(-1); }
*++e = IMM; *++e = (ty == CHAR) ? sizeof(char) : sizeof(int);
ty = INT;
}
else if (tk == Id) {
d = id; next();
if (tk == '(') {
next();
t = 0;
while (tk != ')') { expr(Assign); *++e = PSH; ++t; if (tk == ',') next(); }
next();
if (d[Class] == Sys) *++e = d[Val];
else if (d[Class] == Fun) { *++e = JSR; *++e = d[Val]; }
else { printf("%d: bad function call\n", line); exit(-1); }
if (t) { *++e = ADJ; *++e = t; }
ty = d[Type];
}
else if (d[Class] == Num) { *++e = IMM; *++e = d[Val]; ty = INT; }
else {
if (d[Class] == Loc) { *++e = LEA; *++e = loc - d[Val]; }
else if (d[Class] == Glo) { *++e = IMM; *++e = d[Val]; }
else { printf("%d: undefined variable\n", line); exit(-1); }
*++e = ((ty = d[Type]) == CHAR) ? LC : LI;
}
}
else if (tk == '(') {
next();
if (tk == Int || tk == Char) {
t = (tk == Int) ? INT : CHAR; next();
while (tk == Mul) { next(); t = t + PTR; }
if (tk == ')') next(); else { printf("%d: bad cast\n", line); exit(-1); }
expr(Inc);
ty = t;
}
else {
expr(Assign);
if (tk == ')') next(); else { printf("%d: close paren expected\n", line); exit(-1); }
}
}
else if (tk == Mul) {
next(); expr(Inc);
if (ty > INT) ty = ty - PTR; else { printf("%d: bad dereference\n", line); exit(-1); }
*++e = (ty == CHAR) ? LC : LI;
}
else if (tk == And) {
next(); expr(Inc);
if (*e == LC || *e == LI) --e; else { printf("%d: bad address-of\n", line); exit(-1); }
ty = ty + PTR;
}
else if (tk == '!') { next(); expr(Inc); *++e = PSH; *++e = IMM; *++e = 0; *++e = EQ; ty = INT; }
else if (tk == '~') { next(); expr(Inc); *++e = PSH; *++e = IMM; *++e = -1; *++e = XOR; ty = INT; }
else if (tk == Add) { next(); expr(Inc); ty = INT; }
else if (tk == Sub) {
next(); *++e = IMM;
if (tk == Num) { *++e = -ival; next(); } else { *++e = -1; *++e = PSH; expr(Inc); *++e = MUL; }
ty = INT;
}
else if (tk == Inc || tk == Dec) {
t = tk; next(); expr(Inc);
if (*e == LC) { *e = PSH; *++e = LC; }
else if (*e == LI) { *e = PSH; *++e = LI; }
else { printf("%d: bad lvalue in pre-increment\n", line); exit(-1); }
*++e = PSH;
*++e = IMM; *++e = (ty > PTR) ? sizeof(int) : sizeof(char);
*++e = (t == Inc) ? ADD : SUB;
*++e = (ty == CHAR) ? SC : SI;
}
else { printf("%d: bad expression\n", line); exit(-1); }
while (tk >= lev) { // "precedence climbing" or "Top Down Operator Precedence" method
t = ty;
if (tk == Assign) {
next();
if (*e == LC || *e == LI) *e = PSH; else { printf("%d: bad lvalue in assignment\n", line); exit(-1); }
expr(Assign); *++e = ((ty = t) == CHAR) ? SC : SI;
}
else if (tk == Cond) {
next();
*++e = BZ; d = ++e;
expr(Assign);
if (tk == ':') next(); else { printf("%d: conditional missing colon\n", line); exit(-1); }
*d = (int)(e + 3); *++e = JMP; d = ++e;
expr(Cond);
*d = (int)(e + 1);
}
else if (tk == Lor) { next(); *++e = BNZ; d = ++e; expr(Lan); *d = (int)(e + 1); ty = INT; }
else if (tk == Lan) { next(); *++e = BZ; d = ++e; expr(Or); *d = (int)(e + 1); ty = INT; }
else if (tk == Or) { next(); *++e = PSH; expr(Xor); *++e = OR; ty = INT; }
else if (tk == Xor) { next(); *++e = PSH; expr(And); *++e = XOR; ty = INT; }
else if (tk == And) { next(); *++e = PSH; expr(Eq); *++e = AND; ty = INT; }
else if (tk == Eq) { next(); *++e = PSH; expr(Lt); *++e = EQ; ty = INT; }
else if (tk == Ne) { next(); *++e = PSH; expr(Lt); *++e = NE; ty = INT; }
else if (tk == Lt) { next(); *++e = PSH; expr(Shl); *++e = LT; ty = INT; }
else if (tk == Gt) { next(); *++e = PSH; expr(Shl); *++e = GT; ty = INT; }
else if (tk == Le) { next(); *++e = PSH; expr(Shl); *++e = LE; ty = INT; }
else if (tk == Ge) { next(); *++e = PSH; expr(Shl); *++e = GE; ty = INT; }
else if (tk == Shl) { next(); *++e = PSH; expr(Add); *++e = SHL; ty = INT; }
else if (tk == Shr) { next(); *++e = PSH; expr(Add); *++e = SHR; ty = INT; }
else if (tk == Add) {
next(); *++e = PSH; expr(Mul);
if ((ty = t) > PTR) { *++e = PSH; *++e = IMM; *++e = sizeof(int); *++e = MUL; }
*++e = ADD;
}
else if (tk == Sub) {
next(); *++e = PSH; expr(Mul);
if (t > PTR && t == ty) { *++e = SUB; *++e = PSH; *++e = IMM; *++e = sizeof(int); *++e = DIV; ty = INT; }
else if ((ty = t) > PTR) { *++e = PSH; *++e = IMM; *++e = sizeof(int); *++e = MUL; *++e = SUB; }
else *++e = SUB;
}
else if (tk == Mul) { next(); *++e = PSH; expr(Inc); *++e = MUL; ty = INT; }
else if (tk == Div) { next(); *++e = PSH; expr(Inc); *++e = DIV; ty = INT; }
else if (tk == Mod) { next(); *++e = PSH; expr(Inc); *++e = MOD; ty = INT; }
else if (tk == Inc || tk == Dec) {
if (*e == LC) { *e = PSH; *++e = LC; }
else if (*e == LI) { *e = PSH; *++e = LI; }
else { printf("%d: bad lvalue in post-increment\n", line); exit(-1); }
*++e = PSH; *++e = IMM; *++e = (ty > PTR) ? sizeof(int) : sizeof(char);
*++e = (tk == Inc) ? ADD : SUB;
*++e = (ty == CHAR) ? SC : SI;
*++e = PSH; *++e = IMM; *++e = (ty > PTR) ? sizeof(int) : sizeof(char);
*++e = (tk == Inc) ? SUB : ADD;
next();
}
else if (tk == Brak) {
next(); *++e = PSH; expr(Assign);
if (tk == ']') next(); else { printf("%d: close bracket expected\n", line); exit(-1); }
if (t > PTR) { *++e = PSH; *++e = IMM; *++e = sizeof(int); *++e = MUL; }
else if (t < PTR) { printf("%d: pointer type expected\n", line); exit(-1); }
*++e = ADD;
*++e = ((ty = t - PTR) == CHAR) ? LC : LI;
}
else { printf("%d: compiler error tk=%d\n", line, tk); exit(-1); }
}
}
void stmt()
{
int *a, *b;
if (tk == If) {
next();
if (tk == '(') next(); else { printf("%d: open paren expected\n", line); exit(-1); }
expr(Assign);
if (tk == ')') next(); else { printf("%d: close paren expected\n", line); exit(-1); }
*++e = BZ; b = ++e;
stmt();
if (tk == Else) {
*b = (int)(e + 3); *++e = JMP; b = ++e;
next();
stmt();
}
*b = (int)(e + 1);
}
else if (tk == While) {
next();
a = e + 1;
if (tk == '(') next(); else { printf("%d: open paren expected\n", line); exit(-1); }
expr(Assign);
if (tk == ')') next(); else { printf("%d: close paren expected\n", line); exit(-1); }
*++e = BZ; b = ++e;
stmt();
*++e = JMP; *++e = (int)a;
*b = (int)(e + 1);
}
else if (tk == Return) {
next();
if (tk != ';') expr(Assign);
*++e = LEV;
if (tk == ';') next(); else { printf("%d: semicolon expected\n", line); exit(-1); }
}
else if (tk == '{') {
next();
while (tk != '}') stmt();
next();
}
else if (tk == ';') {
next();
}
else {
expr(Assign);
if (tk == ';') next(); else { printf("%d: semicolon expected\n", line); exit(-1); }
}
}
int main(int argc, char **argv)
{
int fd, bt, ty, poolsz, *idmain;
int *pc, *sp, *bp, a, cycle; // vm registers
int i, *t; // temps
--argc; ++argv;
if (argc > 0 && **argv == '-' && (*argv)[1] == 's') { src = 1; --argc; ++argv; }
if (argc > 0 && **argv == '-' && (*argv)[1] == 'd') { debug = 1; --argc; ++argv; }
if (argc < 1) { printf("usage: c4 [-s] [-d] file ...\n"); return -1; }
if ((fd = open(*argv, 0)) < 0) { printf("could not open(%s)\n", *argv); return -1; }
poolsz = 256*1024; // arbitrary size
if (!(sym = malloc(poolsz))) { printf("could not malloc(%d) symbol area\n", poolsz); return -1; }
if (!(le = e = malloc(poolsz))) { printf("could not malloc(%d) text area\n", poolsz); return -1; }
if (!(data = malloc(poolsz))) { printf("could not malloc(%d) data area\n", poolsz); return -1; }
if (!(sp = malloc(poolsz))) { printf("could not malloc(%d) stack area\n", poolsz); return -1; }
memset(sym, 0, poolsz);
memset(e, 0, poolsz);
memset(data, 0, poolsz);
p = "char else enum if int return sizeof while "
"open read close printf malloc memset memcmp exit void main";
i = Char; while (i <= While) { next(); id[Tk] = i++; } // add keywords to symbol table
i = OPEN; while (i <= EXIT) { next(); id[Class] = Sys; id[Type] = INT; id[Val] = i++; } // add library to symbol table
next(); id[Tk] = Char; // handle void type
next(); idmain = id; // keep track of main
if (!(lp = p = malloc(poolsz))) { printf("could not malloc(%d) source area\n", poolsz); return -1; }
if ((i = read(fd, p, poolsz-1)) <= 0) { printf("read() returned %d\n", i); return -1; }
p[i] = 0;
close(fd);
// parse declarations
line = 1;
next();
while (tk) {
bt = INT; // basetype
if (tk == Int) next();
else if (tk == Char) { next(); bt = CHAR; }
else if (tk == Enum) {
next();
if (tk != '{') next();
if (tk == '{') {
next();
i = 0;
while (tk != '}') {
if (tk != Id) { printf("%d: bad enum identifier %d\n", line, tk); return -1; }
next();
if (tk == Assign) {
next();
if (tk != Num) { printf("%d: bad enum initializer\n", line); return -1; }
i = ival;
next();
}
id[Class] = Num; id[Type] = INT; id[Val] = i++;
if (tk == ',') next();
}
next();
}
}
while (tk != ';' && tk != '}') {
ty = bt;
while (tk == Mul) { next(); ty = ty + PTR; }
if (tk != Id) { printf("%d: bad global declaration\n", line); return -1; }
if (id[Class]) { printf("%d: duplicate global definition\n", line); return -1; }
next();
id[Type] = ty;
if (tk == '(') { // function
id[Class] = Fun;
id[Val] = (int)(e + 1);
next(); i = 0;
while (tk != ')') {
ty = INT;
if (tk == Int) next();
else if (tk == Char) { next(); ty = CHAR; }
while (tk == Mul) { next(); ty = ty + PTR; }
if (tk != Id) { printf("%d: bad parameter declaration\n", line); return -1; }
if (id[Class] == Loc) { printf("%d: duplicate parameter definition\n", line); return -1; }
id[HClass] = id[Class]; id[Class] = Loc;
id[HType] = id[Type]; id[Type] = ty;
id[HVal] = id[Val]; id[Val] = i++;
next();
if (tk == ',') next();
}
next();
if (tk != '{') { printf("%d: bad function definition\n", line); return -1; }
loc = ++i;
next();
while (tk == Int || tk == Char) {
bt = (tk == Int) ? INT : CHAR;
next();
while (tk != ';') {
ty = bt;
while (tk == Mul) { next(); ty = ty + PTR; }
if (tk != Id) { printf("%d: bad local declaration\n", line); return -1; }
if (id[Class] == Loc) { printf("%d: duplicate local definition\n", line); return -1; }
id[HClass] = id[Class]; id[Class] = Loc;
id[HType] = id[Type]; id[Type] = ty;
id[HVal] = id[Val]; id[Val] = ++i;
next();
if (tk == ',') next();
}
next();
}
*++e = ENT; *++e = i - loc;
while (tk != '}') stmt();
*++e = LEV;
id = sym; // unwind symbol table locals
while (id[Tk]) {
if (id[Class] == Loc) {
id[Class] = id[HClass];
id[Type] = id[HType];
id[Val] = id[HVal];
}
id = id + Idsz;
}
}
else {
id[Class] = Glo;
id[Val] = (int)data;
data = data + sizeof(int);
}
if (tk == ',') next();
}
next();
}
if (!(pc = (int *)idmain[Val])) { printf("main() not defined\n"); return -1; }
if (src) return 0;
// setup stack
sp = (int *)((int)sp + poolsz);
*--sp = EXIT; // call exit if main returns
*--sp = PSH; t = sp;
*--sp = argc;
*--sp = (int)argv;
*--sp = (int)t;
// run...
cycle = 0;
while (1) {
i = *pc++; ++cycle;
if (debug) {
printf("%d> %.4s", cycle,
&"LEA ,IMM ,JMP ,JSR ,BZ ,BNZ ,ENT ,ADJ ,LEV ,LI ,LC ,SI ,SC ,PSH ,"
"OR ,XOR ,AND ,EQ ,NE ,LT ,GT ,LE ,GE ,SHL ,SHR ,ADD ,SUB ,MUL ,DIV ,MOD ,"
"OPEN,READ,CLOS,PRTF,MALC,MSET,MCMP,EXIT,"[i * 5]);
if (i <= ADJ) printf(" %d\n", *pc); else printf("\n");
}
if (i == LEA) a = (int)(bp + *pc++); // load local address
else if (i == IMM) a = *pc++; // load global address or immediate
else if (i == JMP) pc = (int *)*pc; // jump
else if (i == JSR) { *--sp = (int)(pc + 1); pc = (int *)*pc; } // jump to subroutine
else if (i == BZ) pc = a ? pc + 1 : (int *)*pc; // branch if zero
else if (i == BNZ) pc = a ? (int *)*pc : pc + 1; // branch if not zero
else if (i == ENT) { *--sp = (int)bp; bp = sp; sp = sp - *pc++; } // enter subroutine
else if (i == ADJ) sp = sp + *pc++; // stack adjust
else if (i == LEV) { sp = bp; bp = (int *)*sp++; pc = (int *)*sp++; } // leave subroutine
else if (i == LI) a = *(int *)a; // load int
else if (i == LC) a = *(char *)a; // load char
else if (i == SI) *(int *)*sp++ = a; // store int
else if (i == SC) a = *(char *)*sp++ = a; // store char
else if (i == PSH) *--sp = a; // push
else if (i == OR) a = *sp++ | a;
else if (i == XOR) a = *sp++ ^ a;
else if (i == AND) a = *sp++ & a;
else if (i == EQ) a = *sp++ == a;
else if (i == NE) a = *sp++ != a;
else if (i == LT) a = *sp++ < a;
else if (i == GT) a = *sp++ > a;
else if (i == LE) a = *sp++ <= a;
else if (i == GE) a = *sp++ >= a;
else if (i == SHL) a = *sp++ << a;
else if (i == SHR) a = *sp++ >> a;
else if (i == ADD) a = *sp++ + a;
else if (i == SUB) a = *sp++ - a;
else if (i == MUL) a = *sp++ * a;
else if (i == DIV) a = *sp++ / a;
else if (i == MOD) a = *sp++ % a;
else if (i == OPEN) a = open((char *)sp[1], *sp);
else if (i == READ) a = read(sp[2], (char *)sp[1], *sp);
else if (i == CLOS) a = close(*sp);
else if (i == PRTF) { t = sp + pc[1]; a = printf((char *)t[-1], t[-2], t[-3], t[-4], t[-5], t[-6]); }
else if (i == MALC) a = (int)malloc(*sp);
else if (i == MSET) a = (int)memset((char *)sp[2], sp[1], *sp);
else if (i == MCMP) a = memcmp((char *)sp[2], (char *)sp[1], *sp);
else if (i == EXIT) { printf("exit(%d) cycle = %d\n", *sp, cycle); return *sp; }
else { printf("unknown instruction = %d! cycle = %d\n", i, cycle); return -1; }
}
}
#include <stdio.h>
#include <stdlib.h>
#include <memory.h>
#include <string.h>
int debug; // print the executed instructions
int assembly; // print out the assembly and source
int token; // current token
// instructions
enum { LEA ,IMM ,JMP ,CALL,JZ ,JNZ ,ENT ,ADJ ,LEV ,LI ,LC ,SI ,SC ,PUSH,
OR ,XOR ,AND ,EQ ,NE ,LT ,GT ,LE ,GE ,SHL ,SHR ,ADD ,SUB ,MUL ,DIV ,MOD ,
OPEN,READ,CLOS,PRTF,MALC,MSET,MCMP,EXIT };
// tokens and classes (operators last and in precedence order)
// copied from c4
enum {
Num = 128, Fun, Sys, Glo, Loc, Id,
Char, Else, Enum, If, Int, Return, Sizeof, While,
Assign, Cond, Lor, Lan, Or, Xor, And, Eq, Ne, Lt, Gt, Le, Ge, Shl, Shr, Add, Sub, Mul, Div, Mod, Inc, Dec, Brak
};
// fields of identifier
enum {Token, Hash, Name, Type, Class, Value, BType, BClass, BValue, IdSize};
// types of variable/function
enum { CHAR, INT, PTR };
// type of declaration.
enum {Global, Local};
int *text, // text segment
*stack;// stack
int * old_text; // for dump text segment
char *data; // data segment
int *idmain;
char *src, *old_src; // pointer to source code string;
int poolsize; // default size of text/data/stack
int *pc, *bp, *sp, ax, cycle; // virtual machine registers
int *current_id, // current parsed ID
*symbols, // symbol table
line, // line number of source code
token_val; // value of current token (mainly for number)
int basetype; // the type of a declaration, make it global for convenience
int expr_type; // the type of an expression
// function frame
//
// 0: arg 1
// 1: arg 2
// 2: arg 3
// 3: return address
// 4: old bp pointer <- index_of_bp
// 5: local var 1
// 6: local var 2
int index_of_bp; // index of bp pointer on stack
void next() {
char *last_pos;
int hash;
while (token = *src) {
++src;
if (token == '\n') {
if (assembly) {
// print compile info
printf("%d: %.*s", line, src-old_src, old_src);
old_src = src;
while (old_text < text) {
printf("%8.4s", & "LEA ,IMM ,JMP ,CALL,JZ ,JNZ ,ENT ,ADJ ,LEV ,LI ,LC ,SI ,SC ,PUSH,"
"OR ,XOR ,AND ,EQ ,NE ,LT ,GT ,LE ,GE ,SHL ,SHR ,ADD ,SUB ,MUL ,DIV ,MOD ,"
"OPEN,READ,CLOS,PRTF,MALC,MSET,MCMP,EXIT"[*++old_text * 5]);
if (*old_text <= ADJ)
printf(" %d\n", *++old_text);
else
printf("\n");
}
}
++line;
}
else if (token == '#') {
// skip macro, because we will not support it
while (*src != 0 && *src != '\n') {
src++;
}
}
else if ((token >= 'a' && token <= 'z') || (token >= 'A' && token <= 'Z') || (token == '_')) {
// parse identifier
last_pos = src - 1;
hash = token;
while ((*src >= 'a' && *src <= 'z') || (*src >= 'A' && *src <= 'Z') || (*src >= '0' && *src <= '9') || (*src == '_')) {
hash = hash * 147 + *src;
src++;
}
// look for existing identifier, linear search
current_id = symbols;
while (current_id[Token]) {
if (current_id[Hash] == hash && !memcmp((char *)current_id[Name], last_pos, src - last_pos)) {
//found one, return
token = current_id[Token];
return;
}
current_id = current_id + IdSize;
}
// store new ID
current_id[Name] = (int)last_pos;
current_id[Hash] = hash;
token = current_id[Token] = Id;
return;
}
else if (token >= '0' && token <= '9') {
// parse number, three kinds: dec(123) hex(0x123) oct(017)
token_val = token - '0';
if (token_val) {
if (*src == 'x' || *src == 'X') {
//hex
token = *++src;
while ((token >= '0' && token <= '9') || (token >= 'a' && token <= 'f') || (token >= 'A' && token <= 'F')) {
token_val = token_val * 16 + (token & 15) + (token >= 'A' ? 9 : 0);
token = *++src;
}
} else {
// dec
while (*src >= '0' && *src <= '9') {
token_val = token_val*10 + *src++ - '0';
}
}
} else {
// oct
while (*src >= '0' && *src <= '7') {
token_val = token_val*8 + *src++ - '0';
}
}
token = Num;
return;
}
else if (token == '/') {
if (*src == '/') {
// skip comments
while (*src != 0 && *src != '\n') {
++src;
}
} else {
// divide operator
token = Div;
return;
}
}
else if (token == '"' || token == '\'') {
// parse string literal, currently, the only supported escape
// character is '\n', store the string literal into data.
last_pos = data;
while (*src != 0 && *src != token) {
token_val = *src++;
if (token_val == '\\') {
// escape character
token_val = *src++;
if (token_val == 'n') {
token_val = '\n';
}
}
if (token == '"') {
*data++ = token_val;
}
}
src++;
// if it is a single character, return Num token
if (token == '"') {
token_val = (int)last_pos;
} else {
token = Num;
}
return;
}
else if (token == '=') {
// parse '==' and '='
if (*src == '=') {
src ++;
token = Eq;
} else {
token = Assign;
}
return;
}
else if (token == '+') {
// parse '+' and '++'
if (*src == '+') {
src ++;
token = Inc;
} else {
token = Add;
}
return;
}
else if (token == '-') {
// parse '-' and '--'
if (*src == '-') {
src ++;
token = Dec;
} else {
token = Sub;
}
return;
}
else if (token == '!') {
// parse '!='
if (*src == '=') {
src++;
token = Ne;
}
return;
}
else if (token == '<') {
// parse '<=', '<<' or '<'
if (*src == '=') {
src ++;
token = Le;
} else if (*src == '<') {
src ++;
token = Shl;
} else {
token = Lt;
}
return;
}
else if (token == '>') {
// parse '>=', '>>' or '>'
if (*src == '=') {
src ++;
token = Ge;
} else if (*src == '>') {
src ++;
token = Shr;
} else {
token = Gt;
}
return;
}
else if (token == '|') {
// parse '|' or '||'
if (*src == '|') {
src ++;
token = Lor;
} else {
token = Or;
}
return;
}
else if (token == '&') {
// parse '&' and '&&'
if (*src == '&') {
src ++;
token = Lan;
} else {
token = And;
}
return;
}
else if (token == '^') {
token = Xor;
return;
}
else if (token == '%') {
token = Mod;
return;
}
else if (token == '*') {
token = Mul;
return;
}
else if (token == '[') {
token = Brak;
return;
}
else if (token == '?') {
token = Cond;
return;
}
else if (token == '~' || token == ';' || token == '{' || token == '}' || token == '(' || token == ')' || token == ']' || token == ',' || token == ':') {
// directly return the character as token;
return;
}
}
}
void match(int tk) {
if (token == tk) {
next();
} else {
printf("%d: expected token: %d\n", line, tk);
exit(-1);
}
}
void expression(int level) {
// expressions have various format.
// but majorly can be divided into two parts: unit and operator
// for example `(char) *a[10] = (int *) func(b > 0 ? 10 : 20);
// `a[10]` is an unit while `*` is an operator.
// `func(...)` in total is an unit.
// so we should first parse those unit and unary operators
// and then the binary ones
//
// also the expression can be in the following types:
//
// 1. unit_unary ::= unit | unit unary_op | unary_op unit
// 2. expr ::= unit_unary (bin_op unit_unary ...)
// unit_unary()
int *id;
int tmp;
int *addr;
{
if (!token) {
printf("%d: unexpected token EOF of expression\n", line);
exit(-1);
}
if (token == Num) {
match(Num);
// emit code
*++text = IMM;
*++text = token_val;
expr_type = INT;
}
else if (token == '"') {
// continous string "abc" "abc"
// emit code
*++text = IMM;
*++text = token_val;
match('"');
// store the rest strings
while (token == '"') {
match('"');
}
// append the end of string character '\0', all the data are default
// to 0, so just move data one position forward.
data = (char *)(((int)data + sizeof(int)) & (-sizeof(int)));
expr_type = PTR;
}
else if (token == Sizeof) {
// sizeof is actually an unary operator
// now only `sizeof(int)`, `sizeof(char)` and `sizeof(*...)` are
// supported.
match(Sizeof);
match('(');
expr_type = INT;
if (token == Int) {
match(Int);
} else if (token == Char) {
match(Char);
expr_type = CHAR;
}
while (token == Mul) {
match(Mul);
expr_type = expr_type + PTR;
}
match(')');
// emit code
*++text = IMM;
*++text = (expr_type == CHAR) ? sizeof(char) : sizeof(int);
expr_type = INT;
}
else if (token == Id) {
// there are several type when occurs to Id
// but this is unit, so it can only be
// 1. function call
// 2. Enum variable
// 3. global/local variable
match(Id);
id = current_id;
if (token == '(') {
// function call
match('(');
// pass in arguments
tmp = 0; // number of arguments
while (token != ')') {
expression(Assign);
*++text = PUSH;
tmp ++;
if (token == ',') {
match(',');
}
}
match(')');
// emit code
if (id[Class] == Sys) {
// system functions
*++text = id[Value];
}
else if (id[Class] == Fun) {
// function call
*++text = CALL;
*++text = id[Value];
}
else {
printf("%d: bad function call\n", line);
exit(-1);
}
// clean the stack for arguments
if (tmp > 0) {
*++text = ADJ;
*++text = tmp;
}
expr_type = id[Type];
}
else if (id[Class] == Num) {
// enum variable
*++text = IMM;
*++text = id[Value];
expr_type = INT;
}
else {
// variable
if (id[Class] == Loc) {
*++text = LEA;
*++text = index_of_bp - id[Value];
}
else if (id[Class] == Glo) {
*++text = IMM;
*++text = id[Value];
}
else {
printf("%d: undefined variable\n", line);
exit(-1);
}
// emit code, default behaviour is to load the value of the
// address which is stored in `ax`
expr_type = id[Type];
*++text = (expr_type == Char) ? LC : LI;
}
}
else if (token == '(') {
// cast or parenthesis
match('(');
if (token == Int || token == Char) {
tmp = (token == Char) ? CHAR : INT; // cast type
match(token);
while (token == Mul) {
match(Mul);
tmp = tmp + PTR;
}
match(')');
expression(Inc); // cast has precedence as Inc(++)
expr_type = tmp;
} else {
// normal parenthesis
expression(Assign);
match(')');
}
}
else if (token == Mul) {
// dereference *<addr>
match(Mul);
expression(Inc); // dereference has the same precedence as Inc(++)
if (expr_type >= PTR) {
expr_type = expr_type - PTR;
} else {
printf("%d: bad dereference\n", line);
exit(-1);
}
*++text = (expr_type == CHAR) ? LC : LI;
}
else if (token == And) {
// get the address of
match(And);
expression(Inc); // get the address of
if (*text == LC || *text == LI) {
text --;
} else {
printf("%d: bad address of\n", line);
exit(-1);
}
expr_type = expr_type + PTR;
}
else if (token == '!') {
// not
match('!');
expression(Inc);
// emit code, use <expr> == 0
*++text = PUSH;
*++text = IMM;
*++text = 0;
*++text = EQ;
expr_type = INT;
}
else if (token == '~') {
// bitwise not
match('~');
expression(Inc);
// emit code, use <expr> XOR -1
*++text = PUSH;
*++text = IMM;
*++text = -1;
*++text = XOR;
expr_type = INT;
}
else if (token == Add) {
// +var, do nothing
match(Add);
expression(Inc);
expr_type = INT;
}
else if (token == Sub) {
// -var
match(Sub);
if (token == Num) {
*++text = IMM;
*++text = -token_val;
match(Num);
} else {
*++text = IMM;
*++text = -1;
*++text = PUSH;
expression(Inc);
*++text = MUL;
}
expr_type = INT;
}
else if (token == Inc || token == Dec) {
tmp = token;
match(token);
expression(Inc);
if (*text == LC) {
*text = PUSH; // to duplicate the address
*++text = LC;
} else if (*text == LI) {
*text = PUSH;
*++text = LI;
} else {
printf("%d: bad lvalue of pre-increment\n", line);
exit(-1);
}
*++text = PUSH;
*++text = IMM;
*++text = (expr_type > PTR) ? sizeof(int) : sizeof(char);
*++text = (tmp == Inc) ? ADD : SUB;
*++text = (expr_type == CHAR) ? SC : SI;
}
else {
printf("%d: bad expression\n", line);
exit(-1);
}
}
// binary operator and postfix operators.
{
while (token >= level) {
// handle according to current operator's precedence
tmp = expr_type;
if (token == Assign) {
// var = expr;
match(Assign);
if (*text == LC || *text == LI) {
*text = PUSH; // save the lvalue's pointer
} else {
printf("%d: bad lvalue in assignment\n", line);
exit(-1);
}
expression(Assign);
expr_type = tmp;
*++text = (expr_type == CHAR) ? SC : SI;
}
else if (token == Cond) {
// expr ? a : b;
match(Cond);
*++text = JZ;
addr = ++text;
expression(Assign);
if (token == ':') {
match(':');
} else {
printf("%d: missing colon in conditional\n", line);
exit(-1);
}
*addr = (int)(text + 3);
*++text = JMP;
addr = ++text;
expression(Cond);
*addr = (int)(text + 1);
}
else if (token == Lor) {
// logic or
match(Lor);
*++text = JNZ;
addr = ++text;
expression(Lan);
*addr = (int)(text + 1);
expr_type = INT;
}
else if (token == Lan) {
// logic and
match(Lan);
*++text = JZ;
addr = ++text;
expression(Or);
*addr = (int)(text + 1);
expr_type = INT;
}
else if (token == Or) {
// bitwise or
match(Or);
*++text = PUSH;
expression(Xor);
*++text = OR;
expr_type = INT;
}
else if (token == Xor) {
// bitwise xor
match(Xor);
*++text = PUSH;
expression(And);
*++text = XOR;
expr_type = INT;
}
else if (token == And) {
// bitwise and
match(And);
*++text = PUSH;
expression(Eq);
*++text = AND;
expr_type = INT;
}
else if (token == Eq) {
// equal ==
match(Eq);
*++text = PUSH;
expression(Ne);
*++text = EQ;
expr_type = INT;
}
else if (token == Ne) {
// not equal !=
match(Ne);
*++text = PUSH;
expression(Lt);
*++text = NE;
expr_type = INT;
}
else if (token == Lt) {
// less than
match(Lt);
*++text = PUSH;
expression(Shl);
*++text = LT;
expr_type = INT;
}
else if (token == Gt) {
// greater than
match(Gt);
*++text = PUSH;
expression(Shl);
*++text = GT;
expr_type = INT;
}
else if (token == Le) {
// less than or equal to
match(Le);
*++text = PUSH;
expression(Shl);
*++text = LE;
expr_type = INT;
}
else if (token == Ge) {
// greater than or equal to
match(Ge);
*++text = PUSH;
expression(Shl);
*++text = GE;
expr_type = INT;
}
else if (token == Shl) {
// shift left
match(Shl);
*++text = PUSH;
expression(Add);
*++text = SHL;
expr_type = INT;
}
else if (token == Shr) {
// shift right
match(Shr);
*++text = PUSH;
expression(Add);
*++text = SHR;
expr_type = INT;
}
else if (token == Add) {
// add
match(Add);
*++text = PUSH;
expression(Mul);
expr_type = tmp;
if (expr_type > PTR) {
// pointer type, and not `char *`
*++text = PUSH;
*++text = IMM;
*++text = sizeof(int);
*++text = MUL;
}
*++text = ADD;
}
else if (token == Sub) {
// sub
match(Sub);
*++text = PUSH;
expression(Mul);
if (tmp > PTR && tmp == expr_type) {
// pointer subtraction
*++text = SUB;
*++text = PUSH;
*++text = IMM;
*++text = sizeof(int);
*++text = DIV;
expr_type = INT;
} else if (tmp > PTR) {
// pointer movement
*++text = PUSH;
*++text = IMM;
*++text = sizeof(int);
*++text = MUL;
*++text = SUB;
expr_type = tmp;
} else {
// numeral subtraction
*++text = SUB;
expr_type = tmp;
}
}
else if (token == Mul) {
// multiply
match(Mul);
*++text = PUSH;
expression(Inc);
*++text = MUL;
expr_type = tmp;
}
else if (token == Div) {
// divide
match(Div);
*++text = PUSH;
expression(Inc);
*++text = DIV;
expr_type = tmp;
}
else if (token == Mod) {
// Modulo
match(Mod);
*++text = PUSH;
expression(Inc);
*++text = MOD;
expr_type = tmp;
}
else if (token == Inc || token == Dec) {
// postfix inc(++) and dec(--)
// we will increase the value to the variable and decrease it
// on `ax` to get its original value.
if (*text == LI) {
*text = PUSH;
*++text = LI;
}
else if (*text == LC) {
*text = PUSH;
*++text = LC;
}
else {
printf("%d: bad value in increment\n", line);
exit(-1);
}
*++text = PUSH;
*++text = IMM;
*++text = (expr_type > PTR) ? sizeof(int) : sizeof(char);
*++text = (token == Inc) ? ADD : SUB;
*++text = (expr_type == CHAR) ? SC : SI;
*++text = PUSH;
*++text = IMM;
*++text = (expr_type > PTR) ? sizeof(int) : sizeof(char);
*++text = (token == Inc) ? SUB : ADD;
match(token);
}
else if (token == Brak) {
// array access var[xx]
match(Brak);
*++text = PUSH;
expression(Assign);
match(']');
if (tmp > PTR) {
// pointer, `not char *`
*++text = PUSH;
*++text = IMM;
*++text = sizeof(int);
*++text = MUL;
}
else if (tmp < PTR) {
printf("%d: pointer type expected\n", line);
exit(-1);
}
expr_type = tmp - PTR;
*++text = ADD;
*++text = (expr_type == CHAR) ? LC : LI;
}
else {
printf("%d: compiler error, token = %d\n", line, token);
exit(-1);
}
}
}
}
void statement() {
// there are 8 kinds of statements here:
// 1. if (...) <statement> [else <statement>]
// 2. while (...) <statement>
// 3. { <statement> }
// 4. return xxx;
// 5. <empty statement>;
// 6. expression; (expression end with semicolon)
int *a, *b; // bess for branch control
if (token == If) {
// if (...) <statement> [else <statement>]
//
// if (...) <cond>
// JZ a
// <statement> <statement>
// else: JMP b
// a:
// <statement> <statement>
// b: b:
//
//
match(If);
match('(');
expression(Assign); // parse condition
match(')');
// emit code for if
*++text = JZ;
b = ++text;
statement(); // parse statement
if (token == Else) { // parse else
match(Else);
// emit code for JMP B
*b = (int)(text + 3);
*++text = JMP;
b = ++text;
statement();
}
*b = (int)(text + 1);
}
else if (token == While) {
//
// a: a:
// while (<cond>) <cond>
// JZ b
// <statement> <statement>
// JMP a
// b: b:
match(While);
a = text + 1;
match('(');
expression(Assign);
match(')');
*++text = JZ;
b = ++text;
statement();
*++text = JMP;
*++text = (int)a;
*b = (int)(text + 1);
}
else if (token == '{') {
// { <statement> ... }
match('{');
while (token != '}') {
statement();
}
match('}');
}
else if (token == Return) {
// return [expression];
match(Return);
if (token != ';') {
expression(Assign);
}
match(';');
// emit code for return
*++text = LEV;
}
else if (token == ';') {
// empty statement
match(';');
}
else {
// a = b; or function_call();
expression(Assign);
match(';');
}
}
void enum_declaration() {
// parse enum [id] { a = 1, b = 3, ...}
int i;
i = 0;
while (token != '}') {
if (token != Id) {
printf("%d: bad enum identifier %d\n", line, token);
exit(-1);
}
next();
if (token == Assign) {
// like {a=10}
next();
if (token != Num) {
printf("%d: bad enum initializer\n", line);
exit(-1);
}
i = token_val;
next();
}
current_id[Class] = Num;
current_id[Type] = INT;
current_id[Value] = i++;
if (token == ',') {
next();
}
}
}
void function_parameter() {
int type;
int params;
params = 0;
while (token != ')') {
// int name, ...
type = INT;
if (token == Int) {
match(Int);
} else if (token == Char) {
type = CHAR;
match(Char);
}
// pointer type
while (token == Mul) {
match(Mul);
type = type + PTR;
}
// parameter name
if (token != Id) {
printf("%d: bad parameter declaration\n", line);
exit(-1);
}
if (current_id[Class] == Loc) {
printf("%d: duplicate parameter declaration\n", line);
exit(-1);
}
match(Id);
// store the local variable
current_id[BClass] = current_id[Class]; current_id[Class] = Loc;
current_id[BType] = current_id[Type]; current_id[Type] = type;
current_id[BValue] = current_id[Value]; current_id[Value] = params++; // index of current parameter
if (token == ',') {
match(',');
}
}
index_of_bp = params+1;
}
void function_body() {
// type func_name (...) {...}
// -->| |<--
// ... {
// 1. local declarations
// 2. statements
// }
int pos_local; // position of local variables on the stack.
int type;
pos_local = index_of_bp;
while (token == Int || token == Char) {
// local variable declaration, just like global ones.
basetype = (token == Int) ? INT : CHAR;
match(token);
while (token != ';') {
type = basetype;
while (token == Mul) {
match(Mul);
type = type + PTR;
}
if (token != Id) {
// invalid declaration
printf("%d: bad local declaration\n", line);
exit(-1);
}
if (current_id[Class]) {
// identifier exists
printf("%d: duplicate local declaration\n", line);
exit(-1);
}
match(Id);
// store the local variable
current_id[BClass] = current_id[Class]; current_id[Class] = Loc;
current_id[BType] = current_id[Type]; current_id[Type] = type;
current_id[BValue] = current_id[Value]; current_id[Value] = ++pos_local; // index of current parameter
if (token == ',') {
match(',');
}
}
match(';');
}
// save the stack size for local variables
*++text = ENT;
*++text = pos_local - index_of_bp;
// statements
while (token != '}') {
statement();
}
// emit code for leaving the sub function
*++text = LEV;
}
void function_declaration() {
// type func_name (...) {...}
// | this part
match('(');
function_parameter();
match(')');
match('{');
function_body();
//match('}');
// unwind local variable declarations for all local variables.
current_id = symbols;
while (current_id[Token]) {
if (current_id[Class] == Loc) {
current_id[Class] = current_id[BClass];
current_id[Type] = current_id[BType];
current_id[Value] = current_id[BValue];
}
current_id = current_id + IdSize;
}
}
void global_declaration() {
// int [*]id [; | (...) {...}]
int type; // tmp, actual type for variable
int i; // tmp
basetype = INT;
// parse enum, this should be treated alone.
if (token == Enum) {
// enum [id] { a = 10, b = 20, ... }
match(Enum);
if (token != '{') {
match(Id); // skip the [id] part
}
if (token == '{') {
// parse the assign part
match('{');
enum_declaration();
match('}');
}
match(';');
return;
}
// parse type information
if (token == Int) {
match(Int);
}
else if (token == Char) {
match(Char);
basetype = CHAR;
}
// parse the comma seperated variable declaration.
while (token != ';' && token != '}') {
type = basetype;
// parse pointer type, note that there may exist `int ****x;`
while (token == Mul) {
match(Mul);
type = type + PTR;
}
if (token != Id) {
// invalid declaration
printf("%d: bad global declaration\n", line);
exit(-1);
}
if (current_id[Class]) {
// identifier exists
printf("%d: duplicate global declaration\n", line);
exit(-1);
}
match(Id);
current_id[Type] = type;
if (token == '(') {
current_id[Class] = Fun;
current_id[Value] = (int)(text + 1); // the memory address of function
function_declaration();
} else {
// variable declaration
current_id[Class] = Glo; // global variable
current_id[Value] = (int)data; // assign memory address
data = data + sizeof(int);
}
if (token == ',') {
match(',');
}
}
next();
}
void program() {
// get next token
next();
while (token > 0) {
global_declaration();
}
}
int eval() {
int op, *tmp;
cycle = 0;
while (1) {
cycle ++;
op = *pc++; // get next operation code
// print debug info
if (debug) {
printf("%d> %.4s", cycle,
& "LEA ,IMM ,JMP ,CALL,JZ ,JNZ ,ENT ,ADJ ,LEV ,LI ,LC ,SI ,SC ,PUSH,"
"OR ,XOR ,AND ,EQ ,NE ,LT ,GT ,LE ,GE ,SHL ,SHR ,ADD ,SUB ,MUL ,DIV ,MOD ,"
"OPEN,READ,CLOS,PRTF,MALC,MSET,MCMP,EXIT"[op * 5]);
if (op <= ADJ)
printf(" %d\n", *pc);
else
printf("\n");
}
if (op == IMM) {ax = *pc++;} // load immediate value to ax
else if (op == LC) {ax = *(char *)ax;} // load character to ax, address in ax
else if (op == LI) {ax = *(int *)ax;} // load integer to ax, address in ax
else if (op == SC) {ax = *(char *)*sp++ = ax;} // save character to address, value in ax, address on stack
else if (op == SI) {*(int *)*sp++ = ax;} // save integer to address, value in ax, address on stack
else if (op == PUSH) {*--sp = ax;} // push the value of ax onto the stack
else if (op == JMP) {pc = (int *)*pc;} // jump to the address
else if (op == JZ) {pc = ax ? pc + 1 : (int *)*pc;} // jump if ax is zero
else if (op == JNZ) {pc = ax ? (int *)*pc : pc + 1;} // jump if ax is zero
else if (op == CALL) {*--sp = (int)(pc+1); pc = (int *)*pc;} // call subroutine
//else if (op == RET) {pc = (int *)*sp++;} // return from subroutine;
else if (op == ENT) {*--sp = (int)bp; bp = sp; sp = sp - *pc++;} // make new stack frame
else if (op == ADJ) {sp = sp + *pc++;} // add esp, <size>
else if (op == LEV) {sp = bp; bp = (int *)*sp++; pc = (int *)*sp++;} // restore call frame and PC
else if (op == LEA) {ax = (int)(bp + *pc++);} // load address for arguments.
else if (op == OR) ax = *sp++ | ax;
else if (op == XOR) ax = *sp++ ^ ax;
else if (op == AND) ax = *sp++ & ax;
else if (op == EQ) ax = *sp++ == ax;
else if (op == NE) ax = *sp++ != ax;
else if (op == LT) ax = *sp++ < ax;
else if (op == LE) ax = *sp++ <= ax;
else if (op == GT) ax = *sp++ > ax;
else if (op == GE) ax = *sp++ >= ax;
else if (op == SHL) ax = *sp++ << ax;
else if (op == SHR) ax = *sp++ >> ax;
else if (op == ADD) ax = *sp++ + ax;
else if (op == SUB) ax = *sp++ - ax;
else if (op == MUL) ax = *sp++ * ax;
else if (op == DIV) ax = *sp++ / ax;
else if (op == MOD) ax = *sp++ % ax;
else if (op == EXIT) { printf("exit(%d)", *sp); return *sp;}
else if (op == OPEN) { ax = open((char *)sp[1], sp[0]); }
else if (op == CLOS) { ax = close(*sp);}
else if (op == READ) { ax = read(sp[2], (char *)sp[1], *sp); }
else if (op == PRTF) { tmp = sp + pc[1]; ax = printf((char *)tmp[-1], tmp[-2], tmp[-3], tmp[-4], tmp[-5], tmp[-6]); }
else if (op == MALC) { ax = (int)malloc(*sp);}
else if (op == MSET) { ax = (int)memset((char *)sp[2], sp[1], *sp);}
else if (op == MCMP) { ax = memcmp((char *)sp[2], (char *)sp[1], *sp);}
else {
printf("unknown instruction:%d\n", op);
return -1;
}
}
}
int main(int argc, char **argv)
{
int i, fd;
int *tmp;
argc--;
argv++;
// parse arguments
if (argc > 0 && **argv == '-' && (*argv)[1] == 's') {
assembly = 1;
--argc;
++argv;
}
if (argc > 0 && **argv == '-' && (*argv)[1] == 'd') {
debug = 1;
--argc;
++argv;
}
if (argc < 1) {
printf("usage: xc [-s] [-d] file ...\n");
return -1;
}
if ((fd = open(*argv, 0)) < 0) {
printf("could not open(%s)\n", *argv);
return -1;
}
poolsize = 256 * 1024; // arbitrary size
line = 1;
// allocate memory
if (!(text = malloc(poolsize))) {
printf("could not malloc(%d) for text area\n", poolsize);
return -1;
}
if (!(data = malloc(poolsize))) {
printf("could not malloc(%d) for data area\n", poolsize);
return -1;
}
if (!(stack = malloc(poolsize))) {
printf("could not malloc(%d) for stack area\n", poolsize);
return -1;
}
if (!(symbols = malloc(poolsize))) {
printf("could not malloc(%d) for symbol table\n", poolsize);
return -1;
}
memset(text, 0, poolsize);
memset(data, 0, poolsize);
memset(stack, 0, poolsize);
memset(symbols, 0, poolsize);
old_text = text;
src = "char else enum if int return sizeof while "
"open read close printf malloc memset memcmp exit void main";
// add keywords to symbol table
i = Char;
while (i <= While) {
next();
current_id[Token] = i++;
}
// add library to symbol table
i = OPEN;
while (i <= EXIT) {
next();
current_id[Class] = Sys;
current_id[Type] = INT;
current_id[Value] = i++;
}
next(); current_id[Token] = Char; // handle void type
next(); idmain = current_id; // keep track of main
if (!(src = old_src = malloc(poolsize))) {
printf("could not malloc(%d) for source area\n", poolsize);
return -1;
}
// read the source file
if ((i = read(fd, src, poolsize-1)) <= 0) {
printf("read() returned %d\n", i);
return -1;
}
src[i] = 0; // add EOF character
close(fd);
program();
if (!(pc = (int *)idmain[Value])) {
printf("main() not defined\n");
return -1;
}
// dump_text();
if (assembly) {
// only for compile
return 0;
}
// setup stack
sp = (int *)((int)stack + poolsize);
*--sp = EXIT; // call exit if main returns
*--sp = PUSH; tmp = sp;
*--sp = argc;
*--sp = (int)argv;
*--sp = (int)tmp;
return eval();
}以上是关于c_cpp C（编译器）有四个函数的主要内容，如果未能解决你的问题，请参考以下文章
js编写函数寻找水仙花数 三位数各位数字的立方和恰巧是该数本身，100到999之间有四个这样的数
c_cpp 一个加载着色器文件，编译和链接到着色器程序的函数。