1 /*-
2 * SPDX-License-Identifier: BSD-2-Clause-FreeBSD
3 *
4 * Copyright (c) 2004 Tim J. Robbins.
5 * All rights reserved.
6 *
7 * Redistribution and use in source and binary forms, with or without
8 * modification, are permitted provided that the following conditions
9 * are met:
10 * 1. Redistributions of source code must retain the above copyright
11 * notice, this list of conditions and the following disclaimer.
12 * 2. Redistributions in binary form must reproduce the above copyright
13 * notice, this list of conditions and the following disclaimer in the
14 * documentation and/or other materials provided with the distribution.
15 *
16 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
17 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
18 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
19 * ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
20 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
21 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
22 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
23 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
24 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
25 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
26 * SUCH DAMAGE.
27 */
28 /*
29 * "Character map" ADT. Stores mappings between pairs of characters in a
30 * splay tree, with a lookup table cache to simplify looking up the first
31 * bunch of characters (which are presumably more common than others).
32 */
33
34 #include <sys/cdefs.h>
35 __FBSDID("$FreeBSD$");
36
37 #include <assert.h>
38 #include <limits.h>
39 #include <stdbool.h>
40 #include <stdlib.h>
41 #include <wchar.h>
42 #include "cmap.h"
43
44 static struct cmapnode *cmap_splay(struct cmapnode *, wint_t);
45
46 /*
47 * cmap_alloc --
48 * Allocate a character map.
49 */
50 struct cmap *
cmap_alloc(void)51 cmap_alloc(void)
52 {
53 struct cmap *cm;
54
55 cm = malloc(sizeof(*cm));
56 if (cm == NULL)
57 return (NULL);
58 cm->cm_root = NULL;
59 cm->cm_def = CM_DEF_SELF;
60 cm->cm_havecache = false;
61 cm->cm_min = cm->cm_max = 0;
62 return (cm);
63 }
64
65 /*
66 * cmap_add --
67 * Add a mapping from "from" to "to" to the map.
68 */
69 bool
cmap_add(struct cmap * cm,wint_t from,wint_t to)70 cmap_add(struct cmap *cm, wint_t from, wint_t to)
71 {
72 struct cmapnode *cmn, *ncmn;
73
74 cm->cm_havecache = false;
75
76 if (cm->cm_root == NULL) {
77 cmn = malloc(sizeof(*cmn));
78 if (cmn == NULL)
79 return (false);
80 cmn->cmn_from = from;
81 cmn->cmn_to = to;
82 cmn->cmn_left = cmn->cmn_right = NULL;
83 cm->cm_root = cmn;
84 cm->cm_min = cm->cm_max = from;
85 return (true);
86 }
87
88 cmn = cm->cm_root = cmap_splay(cm->cm_root, from);
89
90 if (cmn->cmn_from == from) {
91 cmn->cmn_to = to;
92 return (true);
93 }
94
95 ncmn = malloc(sizeof(*ncmn));
96 if (ncmn == NULL)
97 return (false);
98 ncmn->cmn_from = from;
99 ncmn->cmn_to = to;
100 if (from < cmn->cmn_from) {
101 ncmn->cmn_left = cmn->cmn_left;
102 ncmn->cmn_right = cmn;
103 cmn->cmn_left = NULL;
104 } else {
105 ncmn->cmn_right = cmn->cmn_right;
106 ncmn->cmn_left = cmn;
107 cmn->cmn_right = NULL;
108 }
109 if (from < cm->cm_min)
110 cm->cm_min = from;
111 if (from > cm->cm_max)
112 cm->cm_max = from;
113 cm->cm_root = ncmn;
114
115 return (true);
116 }
117
118 /*
119 * cmap_lookup_hard --
120 * Look up the mapping for a character without using the cache.
121 */
122 wint_t
cmap_lookup_hard(struct cmap * cm,wint_t ch)123 cmap_lookup_hard(struct cmap *cm, wint_t ch)
124 {
125
126 if (cm->cm_root != NULL) {
127 cm->cm_root = cmap_splay(cm->cm_root, ch);
128 if (cm->cm_root->cmn_from == ch)
129 return (cm->cm_root->cmn_to);
130 }
131 return (cm->cm_def == CM_DEF_SELF ? ch : cm->cm_def);
132 }
133
134 /*
135 * cmap_cache --
136 * Update the cache.
137 */
138 void
cmap_cache(struct cmap * cm)139 cmap_cache(struct cmap *cm)
140 {
141 wint_t ch;
142
143 for (ch = 0; ch < CM_CACHE_SIZE; ch++)
144 cm->cm_cache[ch] = cmap_lookup_hard(cm, ch);
145
146 cm->cm_havecache = true;
147 }
148
149 /*
150 * cmap_default --
151 * Change the value that characters without mappings map to, and
152 * return the old value. The special character value CM_MAP_SELF
153 * means characters map to themselves.
154 */
155 wint_t
cmap_default(struct cmap * cm,wint_t def)156 cmap_default(struct cmap *cm, wint_t def)
157 {
158 wint_t old;
159
160 old = cm->cm_def;
161 cm->cm_def = def;
162 cm->cm_havecache = false;
163 return (old);
164 }
165
166 static struct cmapnode *
cmap_splay(struct cmapnode * t,wint_t ch)167 cmap_splay(struct cmapnode *t, wint_t ch)
168 {
169 struct cmapnode N, *l, *r, *y;
170
171 /*
172 * Based on public domain code from Sleator.
173 */
174
175 assert(t != NULL);
176
177 N.cmn_left = N.cmn_right = NULL;
178 l = r = &N;
179 for (;;) {
180 if (ch < t->cmn_from) {
181 if (t->cmn_left != NULL &&
182 ch < t->cmn_left->cmn_from) {
183 y = t->cmn_left;
184 t->cmn_left = y->cmn_right;
185 y->cmn_right = t;
186 t = y;
187 }
188 if (t->cmn_left == NULL)
189 break;
190 r->cmn_left = t;
191 r = t;
192 t = t->cmn_left;
193 } else if (ch > t->cmn_from) {
194 if (t->cmn_right != NULL &&
195 ch > t->cmn_right->cmn_from) {
196 y = t->cmn_right;
197 t->cmn_right = y->cmn_left;
198 y->cmn_left = t;
199 t = y;
200 }
201 if (t->cmn_right == NULL)
202 break;
203 l->cmn_right = t;
204 l = t;
205 t = t->cmn_right;
206 } else
207 break;
208 }
209 l->cmn_right = t->cmn_left;
210 r->cmn_left = t->cmn_right;
211 t->cmn_left = N.cmn_right;
212 t->cmn_right = N.cmn_left;
213 return (t);
214 }
215