Path: utzoo!attcan!uunet!cs.utexas.edu!mailrus!ncar!mephisto!mcnc!duke!romeo!drh
From: drh@romeo.cs.duke.edu (D. Richard Hipp)
Newsgroups: comp.lang.c
Subject: Re: C obfuscator (Obfuscator code attached)
Message-ID: <19858@duke.cs.duke.edu>
Date: 29 May 90 13:24:27 GMT
Sender: news@duke.cs.duke.edu
Reply-To: drh@duke.cs.edu
Lines: 51

The program below reads a C program from standard input, strips away all
unnecessary white space and writes the results to standard output.  The
result is a program which has been obfuscated.

Unfortunately, this technique is probably not adequate for a secure
source code distribution, since "cb" will unravel everything into a
nicely indented program again.  To make things really incomprehensible,
one needs to change local identifiers to weird strings like "__X__88s",
rewrite control structures as goto's, insert "red herring" code, and
so forth.  Such radical changes will require a complete parse of the
input program, however, and this is more than I want to tackle right now.

BTW: the program obfuscates itself without error, but I can still almost
promise you that it has bugs.  Use with care.

-------------------------------- Cut Here -----------------------------------
#include <stdio.h>
#include <string.h>
#include <ctype.h>
typedef enum{WHITE,ID,STRING,OP,NL}tokentype;int putx(x)char*x;{static 
int ccnt=0;if(x==0){if(ccnt)printf("\n");ccnt=0;}else{ccnt+=strlen(x);if(
ccnt>70&&isalnum(*x)){printf("\n");ccnt=0;}printf("%s",x);}}int convert(t,
x)tokentype t;char*x;{static int state=1;switch(state){case 1:putx(x);
if(t==NL)state=6;if(t==ID)state=2;break;case 2:if(t==WHITE){state=3;}
else if(t==NL){state=7;}else{putx(x);if(t==ID)state=2;else state=1;}break;
case 3:if(t==ID){putx(" ");putx(x);state=2;}else{putx(x);if(t==WHITE)state=
3;else if(t==NL)state=7;else state=1;}break;case 4:printf("%s",x);if(t==
WHITE)printf(" ");if(t==NL){printf("\n");state=6;}else if(t==OP&&*x=='\\'){
state=5;}break;case 5:printf("%s",x);if(t==WHITE)printf(" ");if(t==NL)
printf("\n");if(t==OP&&*x=='\\'){state=5;}else{state=4;}break;case 6:if(t==
OP&&*x=='#'){putx(0);printf("#");state=4;}else{putx(x);if(t==ID)state=2;
else if(t==NL)state=6;else state=1;}break;case 7:if(t==ID){putx(" ");putx(
x);state=2;}else if(t==OP&&*x=='#'){putx(0);printf("#");state=4;}else{
putx(x);if(t==WHITE)state=3;else if(t==NL)state=7;else state=1;}break;}}
#define LINESIZE 500
int tokenize(fp)FILE*fp;{char line[LINESIZE];register char*cp,c;int 
incomment=0;char*start;tokentype t;while(fgets(line,LINESIZE,fp)){for(cp=line;(
c=*cp)!=0;){if(incomment){char pc;start=cp;do{pc=c;c=*++cp;}while(c!=0&&(
c!='/'||pc!='*'));if(c!=0){incomment=0;c=*++cp;}else{break;}}if(c==' '||
c=='\t'){do c=*++cp;while(c==' '||c=='\t');convert(WHITE,"");}start=cp;
if(isalpha(c)||c=='_'){do c=*++cp;while(isalnum(c)||c=='_');t=ID;}else 
if(c=='0'){if(cp[1]=='x'||cp[1]=='X'){cp++;do c=*++cp;while(isxdigit(c));}
else{do c=*++cp;while(isdigit(c)&&c!='8'&&c!='9');}t=ID;}else if(isdigit(c)){
do c=*++cp;while(isdigit(c));if(c=='.'){cp++;do c=*++cp;while(isdigit(c));}
if(c=='e'||c=='E'){c=*++cp;if(c=='+'||c=='-')c=*++cp;while(isdigit(c))c=*++
cp;}t=ID;}else if(c=='"'){do{c=*++cp;if(c=='\\'){cp+=2;c=*cp;}}while(c!=
0&&c!='"');if(c)cp++;t=STRING;}else if(c=='\''){do{c=*++cp;if(c=='\\'){
cp+=2;c=*cp;}}while(c!=0&&c!='\'');if(c)cp++;t=STRING;}else if(c=='/'&&
cp[1]=='*'){incomment=1;cp++;}else if(c=='\n'){cp++;t=NL;start=cp;}else{
if(c!=0)cp++;t=OP;}if(!incomment&&start<cp){c=*cp;*cp=0;convert(t,start);*
cp=c;}}convert(NL,"");}return 1;}main(){tokenize(stdin);putx(0);}