1 /*
2 * Copyright (C) 2015 The Android Open Source Project
3 *
4 * Licensed under the Apache License, Version 2.0 (the "License");
5 * you may not use this file except in compliance with the License.
6 * You may obtain a copy of the License at
7 *
8 * http://www.apache.org/licenses/LICENSE-2.0
9 *
10 * Unless required by applicable law or agreed to in writing, software
11 * distributed under the License is distributed on an "AS IS" BASIS,
12 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13 * See the License for the specific language governing permissions and
14 * limitations under the License.
15 */
16
17 #define LOG_TAG "Minikin"
18
19 #include "LayoutUtils.h"
20
21 namespace minikin {
22
23 const uint16_t CHAR_NBSP = 0x00A0;
24
25 /*
26 * Determine whether the code unit is a word space for the purposes of
27 * justification.
28 */
isWordSpace(uint16_t code_unit)29 bool isWordSpace(uint16_t code_unit) {
30 return code_unit == ' ' || code_unit == CHAR_NBSP;
31 }
32
33 /**
34 * For the purpose of layout, a word break is a boundary with no
35 * kerning or complex script processing. This is necessarily a
36 * heuristic, but should be accurate most of the time.
37 */
isWordBreakAfter(uint16_t c)38 static bool isWordBreakAfter(uint16_t c) {
39 if (isWordSpace(c) || (c >= 0x2000 && c <= 0x200a) || c == 0x3000) {
40 // spaces
41 return true;
42 }
43 // Note: kana is not included, as sophisticated fonts may kern kana
44 return false;
45 }
46
isWordBreakBefore(uint16_t c)47 static bool isWordBreakBefore(uint16_t c) {
48 // CJK ideographs (and yijing hexagram symbols)
49 return isWordBreakAfter(c) || (c >= 0x3400 && c <= 0x9fff);
50 }
51
52 /**
53 * Return offset of previous word break. It is either < offset or == 0.
54 */
getPrevWordBreakForCache(const uint16_t * chars,size_t offset,size_t len)55 size_t getPrevWordBreakForCache(const uint16_t* chars,
56 size_t offset,
57 size_t len) {
58 if (offset == 0)
59 return 0;
60 if (offset > len)
61 offset = len;
62 if (isWordBreakBefore(chars[offset - 1])) {
63 return offset - 1;
64 }
65 for (size_t i = offset - 1; i > 0; i--) {
66 if (isWordBreakBefore(chars[i]) || isWordBreakAfter(chars[i - 1])) {
67 return i;
68 }
69 }
70 return 0;
71 }
72
73 /**
74 * Return offset of next word break. It is either > offset or == len.
75 */
getNextWordBreakForCache(const uint16_t * chars,size_t offset,size_t len)76 size_t getNextWordBreakForCache(const uint16_t* chars,
77 size_t offset,
78 size_t len) {
79 if (offset >= len)
80 return len;
81 if (isWordBreakAfter(chars[offset])) {
82 return offset + 1;
83 }
84 for (size_t i = offset + 1; i < len; i++) {
85 // No need to check isWordBreakAfter(chars[i - 1]) since it is checked
86 // in previous iteration. Note that isWordBreakBefore returns true
87 // whenever isWordBreakAfter returns true.
88 if (isWordBreakBefore(chars[i])) {
89 return i;
90 }
91 }
92 return len;
93 }
94
95 } // namespace minikin
96