grep.c

C语言库函数的源代码,是C语言学习参考的好文档。

/* +++Date last modified: 05-Jul-1997 */

/*
 * The  information  in  this  document  is  subject  to  change
 * without  notice  and  should not be construed as a commitment
 * by Digital Equipment Corporation or by DECUS.
 *
 * Neither Digital Equipment Corporation, DECUS, nor the authors
 * assume any responsibility for the use or reliability of  this
 * document or the described software.
 *
 *      Copyright (C) 1980, DECUS
 *
 * General permission to copy or modify, but not for profit,  is
 * hereby  granted,  provided that the above copyright notice is
 * included and reference made to  the  fact  that  reproduction
 * privileges were granted by DECUS.
 */
#include <stdio.h>
#include <stdlib.h>
#include <ctype.h>

/*
 * grep
 *
 * Runs on the Decus compiler or on vms, On vms, define as:
 *      grep :== "$disk:[account]grep"      (native)
 *      grep :== "$disk:[account]grep grep" (Decus)
 * See below for more information.
 */

char    *documentation[] = {
"grep searches a file for a given pattern.  Execute by",
"   grep [flags] regular_expression file_list\n",
"Flags are single characters preceeded by '-':",
"   -c      Only a count of matching lines is printed",
"   -f      Print file name for matching lines switch, see below",
"   -n      Each line is preceeded by its line number",
"   -v      Only print non-matching lines\n",
"The file_list is a list of files (wildcards are acceptable on RSX modes).",
"\nThe file name is normally printed if there is a file given.",
"The -f flag reverses this action (print name no file, not if more).\n",
0 };

char    *patdoc[] = {
"The regular_expression defines the pattern to search for.  Upper- and",
"lower-case are always ignored.  Blank lines never match.  The expression",
"should be quoted to prevent file-name translation.",
"x      An ordinary character (not mentioned below) matches that character.",
"'\\'    The backslash quotes any character.  \"\\$\" matches a dollar-sign.",
"'^'    A circumflex at the beginning of an expression matches the",
"       beginning of a line.",
"'$'    A dollar-sign at the end of an expression matches the end of a line.",
"'.'    A period matches any character except \"new-line\".",
"':a'   A colon matches a class of characters described by the following",
"':d'     character.  \":a\" matches any alphabetic, \":d\" matches digits,",
"':n'     \":n\" matches alphanumerics, \": \" matches spaces, tabs, and",
"': '     other control characters, such as new-line.",
"'*'    An expression followed by an asterisk matches zero or more",
"       occurrances of that expression: \"fo*\" matches \"f\", \"fo\"",
"       \"foo\", etc.",
"'+'    An expression followed by a plus sign matches one or more",
"       occurrances of that expression: \"fo+\" matches \"fo\", etc.",
"'-'    An expression followed by a minus sign optionally matches",
"       the expression.",
"'[]'   A string enclosed in square brackets matches any character in",
"       that string, but no others.  If the first character in the",
"       string is a circumflex, the expression matches any character",
"       except \"new-line\" and the characters in the string.  For",
"       example, \"[xyz]\" matches \"xx\" and \"zyx\", while \"[^xyz]\"",
"       matches \"abc\" but not \"axb\".  A range of characters may be",
"       specified by two characters separated by \"-\".  Note that,",
"       [a-z] matches alphabetics, while [z-a] never matches.",
"The concatenation of regular expressions is a regular expression.",
0};

#define LMAX    512
#define PMAX    256

#define CHAR    1
#define BOL     2
#define EOL     3
#define ANY     4
#define CLASS   5
#define NCLASS  6
#define STAR    7
#define PLUS    8
#define MINUS   9
#define ALPHA   10
#define DIGIT   11
#define NALPHA  12
#define PUNCT   13
#define RANGE   14
#define ENDPAT  15

int cflag=0, fflag=0, nflag=0, vflag=0, nfile=0, debug=0;

char *pp, lbuf[LMAX], pbuf[PMAX];

extern char *cclass(), *pmatch();


/*** Main program - parse arguments & grep *************/
main(argc, argv)
int argc;
char *argv[];
{
   register char   *p;
   register int    c, i;
   int             gotpattern;

   FILE            *f;

   if (argc <= 1)
      usage("No arguments");
   if (argc == 2 && argv[1][0] == '?' && argv[1][1] == 0) {
      help(documentation);
      help(patdoc);
      return 1;
      }
   nfile = argc-1;
   gotpattern = 0;
   for (i=1; i < argc; ++i) {
      p = argv[i];
      if (*p == '-') {
         ++p;
         while (c = *p++) {
            switch(tolower(c)) {

            case '?':
               help(documentation);
               break;

            case 'C':
            case 'c':
               ++cflag;
               break;

            case 'D':
            case 'd':
               ++debug;
               break;

            case 'F':
            case 'f':
               ++fflag;
               break;

            case 'n':
            case 'N':
               ++nflag;
               break;

            case 'v':
            case 'V':
               ++vflag;
               break;

            default:
               usage("Unknown flag");
            }
         }
         argv[i] = 0;
         --nfile;
      } else if (!gotpattern) {
         compile(p);
         argv[i] = 0;
         ++gotpattern;
         --nfile;
      }
   }
   if (!gotpattern)
      usage("No pattern");
   if (nfile == 0)
      grep(stdin, 0);
   else {
      fflag = fflag ^ (nfile > 0);
      for (i=1; i < argc; ++i) {
         if (p = argv[i]) {
            if ((f=fopen(p, "r")) == NULL)
               cant(p);
            else {
               grep(f, p);
               fclose(f);
            }
         }
      }
   }
   return EXIT_SUCCESS;
}

/*** Display a file name *******************************/
file(s)
char *s;
{
   printf("File %s:\n", s);
}

/*** Report unopenable file ****************************/
cant(s)
char *s;
{
   fprintf(stderr, "%s: cannot open\n", s);
}

/*** Give good help ************************************/
help(hp)
char **hp;
{
   register char   **dp;

   for (dp = hp; *dp; ++dp)
      printf("%s\n", *dp);
}

/*** Display usage summary *****************************/
usage(s)
char    *s;
{
   fprintf(stderr, "?GREP-E-%s\n", s);
   fprintf(stderr,
      "Usage: grep [-cfnv] pattern [file ...].  grep ? for help\n");
   exit(EXIT_FAILURE);
}

/*** Compile the pattern into global pbuf[] ************/
compile(source)
char       *source;   /* Pattern to compile */
{
   register char  *s;         /* Source string pointer     */
   register char  *lp;        /* Last pattern pointer      */
   register int   c;          /* Current character         */
   int            o;          /* Temp                      */
   char           *spp;       /* Save beginning of pattern */

   s = source;
   if (debug)
      printf("Pattern = \"%s\"\n", s);
   pp = pbuf;
   while (c = *s++) {
      /*
       * STAR, PLUS and MINUS are special.
       */
      if (c == '*' || c == '+' || c == '-') {
         if (pp == pbuf ||
              (o=pp[-1]) == BOL ||
              o == EOL ||
              o == STAR ||
              o == PLUS ||
              o == MINUS)
            badpat("Illegal occurrance op.", source, s);
         store(ENDPAT);
         store(ENDPAT);
         spp = pp;               /* Save pattern end     */
         while (--pp > lp)       /* Move pattern down    */
            *pp = pp[-1];        /* one byte             */
         *pp =   (c == '*') ? STAR :
            (c == '-') ? MINUS : PLUS;
         pp = spp;               /* Restore pattern end  */
         continue;
      }
      /*
       * All the rest.
       */
      lp = pp;         /* Remember start       */
      switch(c) {

      case '^':
         store(BOL);
         break;

      case '$':
         store(EOL);
         break;

      case '.':
         store(ANY);
         break;

      case '[':
         s = cclass(source, s);
         break;

      case ':':
         if (*s) {
            switch(tolower(c = *s++)) {