split.c

   1 /*
   2  * wiggle - apply rejected patches
   3  *
   4  * Copyright (C) 2003 Neil Brown <neilb@cse.unsw.edu.au>
   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; if not, write to the Free Software Foundation, Inc.,
  19  *    51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
  20  *
  21  *    Author: Neil Brown
  22  *    Email: <neilb@suse.de>
  23  */
  24
  25 /*
  26  * Split a stream into words or lines
  27  *
  28  * A word is one of:
  29  *    string of [A-Za-z0-9_]
  30  *    or string of [ \t]
  31  *    or single char (i.e. punctuation and newlines).
  32  *
  33  * A line is any string that ends with \n
  34  *
  35  * As a special case to allow proper aligning of multiple chunks
  36  * in a patch, a word starting \0 will include 20 chars with a newline
  37  * second from the end.
  38  *
  39  * We make two passes through the stream.
  40  * Firstly we count the number of item so an array can be allocated,
  41  * then we store start and length of each item in the array
  42  *
  43  */
  44
  45 #include        "wiggle.h"
  46 #include        <stdlib.h>
  47 #include        <ctype.h>
  48 #include        <stdlib.h>
  49
  50 #include "ccan/hash/hash.h"
  51
  52 static int split_internal(char *start, char *end, int type,
  53                           struct elmnt *list)
  54 {
  55         int cnt = 0;
  56
  57         while (start < end) {
  58                 char *cp = start;
  59
  60                 if (*cp == '\0' && cp+19 < end && cp[18] == '\n') {
  61                         /* special word */
  62                         cp += 20;
  63                 } else
  64                         switch (type) {
  65                         case ByLine:
  66                                 while (cp < end && *cp != '\n')
  67                                         cp++;
  68                                 if (cp < end)
  69                                         cp++;
  70                                 break;
  71                         case ByWord:
  72                                 if (isalnum(*cp) || *cp == '_') {
  73                                         do
  74                                                 cp++;
  75                                         while (cp < end
  76                                                && (isalnum(*cp)
  77                                                    || *cp == '_'));
  78                                 } else if (*cp == ' ' || *cp == '\t') {
  79                                         do
  80                                                 cp++;
  81                                         while (cp < end
  82                                                && (*cp == ' '
  83                                                    || *cp == '\t'));
  84                                 } else
  85                                         cp++;
  86                                 break;
  87                         }
  88                 if (list) {
  89                         list->start = start;
  90                         list->len = cp-start;
  91                         if (*start)
  92                                 list->hash = hash(start, list->len, 0);
  93                         else
  94                                 list->hash = atoi(start+1);
  95                         list++;
  96                 }
  97                 cnt++;
  98                 start = cp;
  99         }
 100         return cnt;
 101 }
 102
 103 struct file split_stream(struct stream s, int type)
 104 {
 105         int cnt;
 106         struct file f;
 107
 108         char *c, *end;
 109
 110         end = s.body+s.len;
 111         c = s.body;
 112
 113         cnt = split_internal(c, end, type, NULL);
 114         f.list = xmalloc(cnt*sizeof(struct elmnt));
 115
 116         f.elcnt = split_internal(c, end, type, f.list);
 117         return f;
 118 }