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 justification.
27 */
isWordSpace(uint16_t code_unit)28 bool isWordSpace(uint16_t code_unit) {
29 return code_unit == ' ' || code_unit == CHAR_NBSP;
30 }
31
32 /**
33 * For the purpose of layout, a word break is a boundary with no
34 * kerning or complex script processing. This is necessarily a
35 * heuristic, but should be accurate most of the time.
36 */
isWordBreakAfter(uint16_t c)37 static bool isWordBreakAfter(uint16_t c) {
38 if (isWordSpace(c) || (c >= 0x2000 && c <= 0x200a) || c == 0x3000) {
39 // spaces
40 return true;
41 }
42 // Note: kana is not included, as sophisticated fonts may kern kana
43 return false;
44 }
45
isWordBreakBefore(uint16_t c)46 static bool isWordBreakBefore(uint16_t c) {
47 // CJK ideographs (and yijing hexagram symbols)
48 return isWordBreakAfter(c) || (c >= 0x3400 && c <= 0x9fff);
49 }
50
51 /**
52 * Return offset of previous word break. It is either < offset or == 0.
53 */
getPrevWordBreakForCache(const uint16_t * chars,size_t offset,size_t len)54 size_t getPrevWordBreakForCache(
55 const uint16_t* chars, size_t offset, size_t len) {
56 if (offset == 0) return 0;
57 if (offset > len) offset = len;
58 if (isWordBreakBefore(chars[offset - 1])) {
59 return offset - 1;
60 }
61 for (size_t i = offset - 1; i > 0; i--) {
62 if (isWordBreakBefore(chars[i]) || isWordBreakAfter(chars[i - 1])) {
63 return i;
64 }
65 }
66 return 0;
67 }
68
69 /**
70 * Return offset of next word break. It is either > offset or == len.
71 */
getNextWordBreakForCache(const uint16_t * chars,size_t offset,size_t len)72 size_t getNextWordBreakForCache(
73 const uint16_t* chars, size_t offset, size_t len) {
74 if (offset >= len) return len;
75 if (isWordBreakAfter(chars[offset])) {
76 return offset + 1;
77 }
78 for (size_t i = offset + 1; i < len; i++) {
79 // No need to check isWordBreakAfter(chars[i - 1]) since it is checked
80 // in previous iteration. Note that isWordBreakBefore returns true
81 // whenever isWordBreakAfter returns true.
82 if (isWordBreakBefore(chars[i])) {
83 return i;
84 }
85 }
86 return len;
87 }
88
89 } // namespace minikin
90