merge: calculate number of wiggles more accurately.
[wiggle/upstream.git] / split.c
blobba2cb2687fdc8f4d121254d4b5da67c669d340f6
1 /*
2 * wiggle - apply rejected patches
4 * Copyright (C) 2003 Neil Brown <neilb@cse.unsw.edu.au>
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.
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.
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.
21 * Author: Neil Brown
22 * Email: <neilb@suse.de>
26 * Split a stream into words or lines
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).
33 * A line is any string that ends with \n
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.
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
45 #include "wiggle.h"
46 #include <stdlib.h>
47 #include <ctype.h>
48 #include <stdlib.h>
50 #include "ccan/hash/hash.h"
52 static int split_internal(char *start, char *end, int type,
53 struct elmnt *list)
55 int cnt = 0;
57 while (start < end) {
58 char *cp = start;
59 char *cp2;
60 int prefix = 0;
62 if (type == (ByWord | IgnoreBlanks))
63 while (cp < end &&
64 (*cp == ' ' || *cp == '\t')) {
65 prefix++;
66 cp++;
68 start = cp;
70 if (*cp == '\0' && cp+19 < end && cp[18] == '\n') {
71 /* special word */
72 cp += 20;
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 (isalnum(*cp) || *cp == '_') {
84 cp++;
85 while (cp < end
86 && (isalnum(*cp)
87 || *cp == '_'));
88 } else if (*cp == ' ' || *cp == '\t') {
90 cp++;
91 while (cp < end
92 && (*cp == ' '
93 || *cp == '\t'));
94 } else
95 cp++;
96 break;
98 cp2 = cp;
99 if (type == (ByWord | IgnoreBlanks) &&
100 *start && *start != '\n')
101 while (cp2 < end &&
102 (*cp2 == ' ' || *cp2 == '\t' || *cp2 == '\n')) {
103 cp2++;
104 if (cp2[-1] == '\n')
105 break;
107 if (list) {
108 list->start = start;
109 list->len = cp-start;
110 list->plen = cp2-start;
111 list->prefix = prefix;
112 if (*start)
113 list->hash = hash(start, list->len, 0);
114 else
115 list->hash = atoi(start+1);
116 list++;
118 cnt++;
119 start = cp2;
121 return cnt;
124 struct file split_stream(struct stream s, int type)
126 int cnt;
127 struct file f;
129 char *c, *end;
131 end = s.body+s.len;
132 c = s.body;
134 cnt = split_internal(c, end, type, NULL);
135 f.list = xmalloc(cnt*sizeof(struct elmnt));
137 f.elcnt = split_internal(c, end, type, f.list);
138 return f;