Removing comments with a sliding window without ne

Question

I'm trying to remove comments and strings from a c file with c code. I'll just stick to comments for the examples. I have a sliding window so I only have character n and n-1 at any given moment. I'm trying to figure out an algorithm that does not use nested whiles if possible, but I will need one while to getchar through the input. My first thought was to while through find when n=* and (n-1)=/ then while through until n=/ and (n-1)=*, but considering this has nested whiles I feel it is inefficient. I can do it this way if I have to, but I was wondering if anyone had a better solution.

Answer 1

The algorithm written with one while loop could look like this:

while ((c = getchar()) != EOF)
{
    ... // looking at the byte that was just read

    if (...) // the symbol is not inside a comment
    {
        putchar(c);
    }
}

To decide whether the input char belongs to a comment, you can use a state machine. In the following example, it has 4 states; there are also rules for traversing to next state.

int state = 0;
int next_state;
while ((c = getchar()) != EOF)
{
    switch (state)
    {
        case 0: next_state = (c == '/' ? 1 : 0); break;
        case 1: next_state = (c == '*' ? 2 : c == '/' ? 1 : 0); break;
        case 2: next_state = (c == '*' ? 3 : 2); break;
        case 3: next_state = (c == '/' ? 0 : c == '*' ? 3 : 2); break;
        default: next_state = state; // will never happen
    }

    if (state == 1 && next_state == 0)
    {
        putchar('/'); // for correct output when a slash is not followed by a star
    }
    if (state == 0 && next_state == 0)
    {
        putchar(c);
    }
    state = next_state;
}

The example above is very simple: it doesn't work correctly for /* in non-comment contexts like in C strings; it doesn't support // comments, etc.

Answer 2

Since you only wish to use two characters for the buffer and only one while loop, I would suggest a third char to track your state (whether skipping text or not). I've put together a test program for you with inline comments explaining the logic:

// Program to strip comments and strings from a C file
//
//  Build:
//     gcc -o strip-comments strip-comments.c
//
//  Test:
//     ./strip-comments strip-comments.c

#include <stdio.h>
#include <sys/types.h>
#include <sys/uio.h>
#include <fcntl.h>
#include <unistd.h>
#include <stdlib.h>

/* The following is a block of strings, and comments for testing
 * the code.
 */
/* test if three comments *//* chained together */// will be removed.
static int value = 128 /* test comment within valid code *// 2;
const char * test1 = "This is a test of \" processing"; /* testing inline comment */
const char * test2 = "this is a test of \n within strings."; // testing inline comment
// this is a the last test


int strip_c_code(FILE * in, FILE * out)
{
   char      buff[2];
   char      skipping;

   skipping = '\0';
   buff[0]  = '\0';
   buff[1]  = '\0';

   // loop through the file
   while((buff[0] =  fgetc(in)) != EOF)
   {
      // checking for start of comment or string block
      if (!(skipping))
      {
         // start skipping in "//"  comments
         if ((buff[1] == '/') && (buff[0] == '/'))
            skipping = '/';

         // start skipping in "/*"  comments
         else if ((buff[1] == '/') && (buff[0] == '*'))
            skipping = '*';

         // start skipping at start of strings, but not character assignments
         else if ( ((buff[1] != '\'') && (buff[0] == '"')) &&
                   ((buff[1] != '\\') && (buff[0] == '"')) )
         {
            fputc(buff[1], out);
            skipping = '"';
         };

         // clear buffer so that processed characters are not interpreted as
         // end of skip characters.
         if ((skipping))
         {
            buff[0] = '\0';
            buff[1] = '\0';
         };
      };

      // check for characters which terminate skip block
      switch(skipping)
      {
         // if skipping "//" comments, look for new line
         case '/':
         if (buff[1] == '\n')
            skipping = '\0';
         break;

         // if skipping "/*" comments, look for "*/" terminating string
         case '*':
         if ((buff[1] == '*') && (buff[0] == '/'))
         {
            buff[0]  = '\0';
            buff[1]  = '\0';
            skipping = '\0';
         };
         break;

         // if skipping strings, look for terminating '"' character
         case '"':
         if ((buff[1] != '\\') && (buff[0] == '"'))
         {
            skipping = '\0';
            buff[0]  = '\0';
            buff[1]  = '\0';
            fprintf(out, "NULL"); // replace string with NULL
         };
         break;

         default:
         break;
      };

      // if not skipping, write character out
      if ( (!(skipping)) && ((buff[1])) )
         fputc(buff[1], out);

      // shift new character to old character position
      buff[1] = buff[0];
   };

   // verify that the comment or string was terminated properly
   if ((skipping))
   {
      fprintf(stderr, "Unterminated comment or string\n");
      return(-1);
   };

   // write last character
   fputc(buff[1], out);

   return(0);
}


int main(int argc, char * argv[])
{
   FILE * fs;

   if (argc != 2)
   {
      fprintf(stderr, "Usage: %s <filename>\n", argv[0]);
      return(1);
   };

   if ((fs = fopen(argv[1], "r")) == NULL)
   {
      perror("fopen()");
      return(1);
   };

   strip_c_code(fs, stdout);

   fclose(fs);

   return(0);
}

/* end of source file */

I've also posted this code on Github to make it easier to download and compile:

https://gist.github.com/syzdek/5417109

Answer 3

Doing this correctly is more complicated than one may at first think, as ably pointed out by the other comments here. I would strongly recommend writing a table-driven FSM, using a state transition diagram to get the transitions right. Trying to do anything more than a few states with case statements is horribly error-prone IMO.

Here's a diagram in dot/graphviz format from which you could probably directly code a state table. Note that I haven't tested this at all, so YMMV.

The semantics of the diagram are that when you see <ch>, it is a fall-though if none of the other input in that state match. End of file is an error in any state except S0, and so is any character not explicitly listed, or <ch>. Every character scanned is printed except when in a comment (S4 and S5), and when detecting a start comment (S1). You will have to buffer characters when detecting a start comment, and print them if it's a false start, otherwise throw them away when sure it's really a comment.

In the dot diagram, sq is a single quote ', dq is a double quote ".

digraph state_machine {
    rankdir=LR;
    size="8,5";

    node [shape=doublecircle]; S0 /* init */;
    node [shape=circle];

    S0  /* init */      -> S1  /* begin_cmt */ [label = "'/'"];
    S0  /* init */      -> S2  /* in_str */    [label = dq];
    S0  /* init */      -> S3  /* in_ch */     [label = sq];
    S0  /* init */      -> S0  /* init */      [label = "<ch>"];
    S1  /* begin_cmt */ -> S4  /* in_slc */    [label = "'/'"];
    S1  /* begin_cmt */ -> S5  /* in_mlc */    [label = "'*'"];
    S1  /* begin_cmt */ -> S0  /* init */      [label = "<ch>"];
    S1  /* begin_cmt */ -> S1  /* begin_cmt */ [label = "'\\n'"]; // handle "/\n/" and "/\n*"
    S2  /* in_str */    -> S0  /* init */      [label = "'\\'"];
    S2  /* in_str */    -> S6  /* str_esc */   [label = "'\\'"];
    S2  /* in_str */    -> S2  /* in_str */    [label = "<ch>"];
    S3  /* in_ch */     -> S0  /* init */      [label = sq];
    S4  /* in_slc */    -> S4  /* in_slc */    [label = "<ch>"];
    S4  /* in_slc */    -> S0  /* init */      [label = "'\\n'"];
    S5  /* in_mlc */    -> S7  /* end_mlc */   [label = "'*'"];
    S5  /* in_mlc */    -> S5  /* in_mlc */    [label = "<ch>"];
    S7  /* end_mlc */   -> S7  /* end_mlc */   [label = "'*'|'\\n'"];
    S7  /* end_mlc */   -> S0  /* init */      [label = "'/'"];
    S7  /* end_mlc */   -> S5  /* in_mlc */    [label = "<ch>"];
    S6  /* str_esc */   -> S8  /* oct */       [label = "[0-3]"];
    S6  /* str_esc */   -> S9  /* hex */       [label = "'x'"];
    S6  /* str_esc */   -> S2  /* in_str */    [label = "<ch>"];
    S8  /* oct */       -> S10 /* o1 */        [label = "[0-7]"];
    S10 /* o1 */        -> S2  /* in_str */    [label = "[0-7]"];
    S9  /* hex */       -> S11 /* h1 */        [label = hex];
    S11 /* h1 */        -> S2  /* in_str */    [label = hex];
    S3  /* in_ch */     -> S12 /* ch_esc */    [label = "'\\'"];
    S3  /* in_ch */     -> S13 /* out_ch */    [label = "<ch>"];
    S13 /* out_ch */    -> S0  /* init */      [label = sq];
    S12 /* ch_esc */    -> S3  /* in_ch */     [label = sq];
    S12 /* ch_esc */    -> S12 /* ch_esc */    [label = "<ch>"];
}