2 * Copyright © 2013,2021 Ran Benita <ran234@gmail.com>
4 * Permission is hereby granted, free of charge, to any person obtaining a
5 * copy of this software and associated documentation files (the "Software"),
6 * to deal in the Software without restriction, including without limitation
7 * the rights to use, copy, modify, merge, publish, distribute, sublicense,
8 * and/or sell copies of the Software, and to permit persons to whom the
9 * Software is furnished to do so, subject to the following conditions:
11 * The above copyright notice and this permission notice (including the next
12 * paragraph) shall be included in all copies or substantial portions of the
15 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
16 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
17 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
18 * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
19 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
20 * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
21 * DEALINGS IN THE SOFTWARE.
24 #ifndef COMPOSE_COMPOSE_H
25 #define COMPOSE_COMPOSE_H
27 #include "xkbcommon/xkbcommon-compose.h"
32 * The compose table data structure is a ternary search tree.
34 * Reference: https://www.drdobbs.com/database/ternary-search-trees/184410528
35 * Visualization: https://www.cs.usfca.edu/~galles/visualization/TST.html
37 * Short example. Given these sequences:
39 * <B> <C> : "first" dead_a
40 * <B> <D> <E> : "second" dead_b
41 * <A> <F> : "third" dead_c
43 * the tree would look like:
45 * -------- [<B>]---------
48 * -- [<A>] -- [<C>] --------
58 * - [<X>] is a node for a sequence keysym <X>.
59 * - right arrows are `hikid` pointers.
60 * - left arrows are `lokid` pointers.
61 * - down arrows are `eqkid` pointers.
62 * - # is a nil pointer.
64 * The nodes are all kept in a contiguous array. Pointers are represented
65 * as integer offsets into this array. A nil pointer is represented as 0
66 * (which, helpfully, is the offset of an empty dummy node).
68 * Nodes without an eqkid are leaf nodes. Since a sequence cannot be a
69 * prefix of another, these are exactly the nodes which terminate the
70 * sequences (in a bijective manner).
72 * A leaf contains the result data of its sequence. The result keysym is
73 * contained in the node struct itself; the result UTF-8 string is a byte
74 * offset into an array of the form "\0first\0second\0third" (the initial
75 * \0 is so offset 0 points to an empty string).
78 /* 7 nodes for every potential Unicode character and then some should be
79 * enough for all purposes. */
80 #define MAX_COMPOSE_NODES (1 << 23)
85 /* Offset into xkb_compose_table::nodes or 0. */
87 /* Offset into xkb_compose_table::nodes or 0. */
98 /* Offset into xkb_compose_table::nodes or 0. */
102 /* Offset into xkb_compose_table::utf8. */
110 struct xkb_compose_table {
112 enum xkb_compose_format format;
113 enum xkb_compose_compile_flags flags;
114 struct xkb_context *ctx;
119 darray(struct compose_node) nodes;