split.c

   1 /*
   2  * wiggle - apply rejected patches
   3  *
   4  * Copyright (C) 2003-2013 Neil Brown <neilb@suse.de>
   5  *
   6  *
   7  *    This program is free software; you can redistribute it and/or modify
   8  *    it under the terms of the GNU General Public License as published by
   9  *    the Free Software Foundation; either version 2 of the License, or
  10  *    (at your option) any later version.
  11  *
  12  *    This program is distributed in the hope that it will be useful,
  13  *    but WITHOUT ANY WARRANTY; without even the implied warranty of
  14  *    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  15  *    GNU General Public License for more details.
  16  *
  17  *    You should have received a copy of the GNU General Public License
  18  *    along with this program.
  19  *
  20  *    Author: Neil Brown
  21  *    Email: <neilb@suse.de>
  22  */
  23
  24 /*
  25  * Split a stream into words or lines
  26  *
  27  * A word is one of:
  28  *    string of [A-Za-z0-9_]
  29  *    or string of [ \t]
  30  *    or single char (i.e. punctuation and newlines).
  31  *
  32  * A line is any string that ends with \n
  33  *
  34  * As a special case to allow proper aligning of multiple chunks
  35  * in a patch, a word starting \0 will include 20+ chars with a newline
  36  * second from the end.
  37  *
  38  * We make two passes through the stream.
  39  * Firstly we count the number of item so an array can be allocated,
  40  * then we store start and length of each item in the array
  41  *
  42  */
  43
  44 #include        "wiggle.h"
  45 #include        <stdlib.h>
  46 #include        <ctype.h>
  47 #include        <stdlib.h>
  48
  49 #include "ccan/hash/hash.h"
  50
  51 static int split_internal(char *start, char *end, int type,
  52                           struct elmnt *list)
  53 {
  54         int cnt = 0;
  55
  56         while (start < end) {
  57                 char *cp = start;
  58                 char *cp2;
  59                 int prefix = 0;
  60
  61                 if ((type & ByWord) && (type & IgnoreBlanks))
  62                         while (cp < end &&
  63                                (*cp == ' ' || *cp == '\t')) {
  64                                 prefix++;
  65                                 cp++;
  66                         }
  67                 start = cp;
  68
  69                 if (*cp == '\0' && cp+19 < end) {
  70                         /* special word */
  71                         cp += 19;
  72                         cp += strlen(cp) + 1;
  73                 } else
  74                         switch (type & ByMask) {
  75                         case ByLine:
  76                                 while (cp < end && *cp != '\n')
  77                                         cp++;
  78                                 if (cp < end)
  79                                         cp++;
  80                                 break;
  81                         case ByWord:
  82                                 if (*cp == ' ' || *cp == '\t') {
  83                                         do
  84                                                 cp++;
  85                                         while (cp < end
  86                                                && (*cp == ' '
  87                                                    || *cp == '\t'));
  88                                 } else if ((type & WholeWord) ||
  89                                            isalnum(*cp) || *cp == '_') {
  90                                         do
  91                                                 cp++;
  92                                         while (cp < end
  93                                                && (((type & WholeWord)
  94                                                     && *cp != ' ' && *cp != '\t'
  95                                                     && *cp != '\n')
  96                                                    || isalnum(*cp)
  97                                                    || *cp == '_'));
  98                                 } else
  99                                         cp++;
 100                                 break;
 101                         }
 102                 cp2 = cp;
 103                 if ((type & ByWord) && (type & IgnoreBlanks) &&
 104                     *start && *start != '\n')
 105                         while (cp2 < end &&
 106                                (*cp2 == ' ' || *cp2 == '\t' || *cp2 == '\n')) {
 107                                 cp2++;
 108                                 if (cp2[-1] == '\n')
 109                                         break;
 110                         }
 111                 if (list) {
 112                         list->start = start;
 113                         list->len = cp-start;
 114                         list->plen = cp2-start;
 115                         list->prefix = prefix;
 116                         if (*start)
 117                                 list->hash = hash(start, list->len, 0);
 118                         else
 119                                 list->hash = atoi(start+1);
 120                         list++;
 121                 }
 122                 cnt++;
 123                 start = cp2;
 124         }
 125         return cnt;
 126 }
 127
 128 struct file split_stream(struct stream s, int type)
 129 {
 130         int cnt;
 131         struct file f;
 132         char *c, *end;
 133
 134         if (!s.body) {
 135                 f.list = NULL;
 136                 f.elcnt = 0;
 137                 return f;
 138         }
 139         end = s.body+s.len;
 140         c = s.body;
 141
 142         cnt = split_internal(c, end, type, NULL);
 143         f.list = xmalloc(cnt*sizeof(struct elmnt));
 144
 145         f.elcnt = split_internal(c, end, type, f.list);
 146         return f;
 147 }