github.com/roboticscm/goman@v0.0.0-20210203095141-87c07b4a0a55/src/lib9/tokenize.c (about)

     1  // +build !plan9
     2  
     3  /*
     4  Inferno lib9/tokenize.c
     5  http://code.google.com/p/inferno-os/source/browse/lib9/tokenize.c
     6  
     7  	Copyright © 1994-1999 Lucent Technologies Inc.  All rights reserved.
     8  	Revisions Copyright © 2000-2007 Vita Nuova Holdings Limited (www.vitanuova.com).  All rights reserved.
     9  
    10  Permission is hereby granted, free of charge, to any person obtaining a copy
    11  of this software and associated documentation files (the "Software"), to deal
    12  in the Software without restriction, including without limitation the rights
    13  to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
    14  copies of the Software, and to permit persons to whom the Software is
    15  furnished to do so, subject to the following conditions:
    16  
    17  The above copyright notice and this permission notice shall be included in
    18  all copies or substantial portions of the Software.
    19  
    20  THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
    21  IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
    22  FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL THE
    23  AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
    24  LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
    25  OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
    26  THE SOFTWARE.
    27  */
    28  
    29  #include <u.h>
    30  #include <libc.h>
    31  
    32  static char qsep[] = " \t\r\n";
    33  
    34  static char*
    35  qtoken(char *s, char *sep)
    36  {
    37  	int quoting;
    38  	char *t;
    39  
    40  	quoting = 0;
    41  	t = s;	/* s is output string, t is input string */
    42  	while(*t!='\0' && (quoting || utfrune(sep, (Rune)*t)==nil)){
    43  		if(*t != '\''){
    44  			*s++ = *t++;
    45  			continue;
    46  		}
    47  		/* *t is a quote */
    48  		if(!quoting){
    49  			quoting = 1;
    50  			t++;
    51  			continue;
    52  		}
    53  		/* quoting and we're on a quote */
    54  		if(t[1] != '\''){
    55  			/* end of quoted section; absorb closing quote */
    56  			t++;
    57  			quoting = 0;
    58  			continue;
    59  		}
    60  		/* doubled quote; fold one quote into two */
    61  		t++;
    62  		*s++ = *t++;
    63  	}
    64  	if(*s != '\0'){
    65  		*s = '\0';
    66  		if(t == s)
    67  			t++;
    68  	}
    69  	return t;
    70  }
    71  
    72  static char*
    73  etoken(char *t, char *sep)
    74  {
    75  	int quoting;
    76  
    77  	/* move to end of next token */
    78  	quoting = 0;
    79  	while(*t!='\0' && (quoting || utfrune(sep, (Rune)*t)==nil)){
    80  		if(*t != '\''){
    81  			t++;
    82  			continue;
    83  		}
    84  		/* *t is a quote */
    85  		if(!quoting){
    86  			quoting = 1;
    87  			t++;
    88  			continue;
    89  		}
    90  		/* quoting and we're on a quote */
    91  		if(t[1] != '\''){
    92  			/* end of quoted section; absorb closing quote */
    93  			t++;
    94  			quoting = 0;
    95  			continue;
    96  		}
    97  		/* doubled quote; fold one quote into two */
    98  		t += 2;
    99  	}
   100  	return t;
   101  }
   102  
   103  int
   104  gettokens(char *s, char **args, int maxargs, char *sep)
   105  {
   106  	int nargs;
   107  
   108  	for(nargs=0; nargs<maxargs; nargs++){
   109  		while(*s!='\0' && utfrune(sep, (Rune)*s)!=nil)
   110  			*s++ = '\0';
   111  		if(*s == '\0')
   112  			break;
   113  		args[nargs] = s;
   114  		s = etoken(s, sep);
   115  	}
   116  
   117  	return nargs;
   118  }
   119  
   120  int
   121  tokenize(char *s, char **args, int maxargs)
   122  {
   123  	int nargs;
   124  
   125  	for(nargs=0; nargs<maxargs; nargs++){
   126  		while(*s!='\0' && utfrune(qsep, (Rune)*s)!=nil)
   127  			s++;
   128  		if(*s == '\0')
   129  			break;
   130  		args[nargs] = s;
   131  		s = qtoken(s, qsep);
   132  	}
   133  
   134  	return nargs;
   135  }