Skip to content
体验新版
项目
组织
正在加载...
登录
切换导航
打开侧边栏
weixin_43355755
engine
提交
94d55255
E
engine
项目概览
weixin_43355755
/
engine
与 Fork 源项目一致
从无法访问的项目Fork
通知
1
Star
0
Fork
0
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
0
列表
看板
标记
里程碑
合并请求
0
Wiki
0
Wiki
分析
仓库
DevOps
项目成员
Pages
E
engine
项目概览
项目概览
详情
发布
仓库
仓库
文件
提交
分支
标签
贡献者
分支图
比较
Issue
0
Issue
0
列表
看板
标记
里程碑
合并请求
0
合并请求
0
Pages
分析
分析
仓库分析
DevOps
Wiki
0
Wiki
成员
成员
收起侧边栏
关闭侧边栏
动态
分支图
创建新Issue
提交
Issue看板
前往新版Gitcode,体验更适合开发者的 AI 搜索 >>
提交
94d55255
编写于
2月 24, 2016
作者:
R
Raph Levien
提交者:
Android (Google) Code Review
2月 24, 2016
浏览文件
操作
浏览文件
下载
差异文件
Merge "Suppress grapheme cluster breaks in emoji with modifiers" into nyc-dev
上级
dbf5c277
adfa580f
变更
2
隐藏空白更改
内联
并排
Showing
2 changed file
with
77 addition
and
0 deletion
+77
-0
libs/minikin/GraphemeBreak.cpp
libs/minikin/GraphemeBreak.cpp
+53
-0
tests/GraphemeBreakTests.cpp
tests/GraphemeBreakTests.cpp
+24
-0
未找到文件。
libs/minikin/GraphemeBreak.cpp
浏览文件 @
94d55255
...
...
@@ -77,6 +77,48 @@ bool isZwjEmoji(uint32_t c) {
||
c
==
0x1F5E8
);
// LEFT SPEECH BUBBLE
}
// Based on Modifiers from http://www.unicode.org/L2/L2016/16011-data-file.txt
bool
isEmojiModifier
(
uint32_t
c
)
{
return
(
0x1F3FB
<=
c
&&
c
<=
0x1F3FF
);
}
// Based on Emoji_Modifier_Base from
// http://www.unicode.org/Public/emoji/3.0/emoji-data.txt
bool
isEmojiBase
(
uint32_t
c
)
{
if
(
0x261D
<=
c
&&
c
<=
0x270D
)
{
return
(
c
==
0x261D
||
c
==
0x26F9
||
(
0x270A
<=
c
&&
c
<=
0x270D
));
}
else
if
(
0x1F385
<=
c
&&
c
<=
0x1F93E
)
{
return
(
c
==
0x1F385
||
(
0x1F3C3
<=
c
||
c
<=
0x1F3C4
)
||
(
0x1F3CA
<=
c
||
c
<=
0x1F3CB
)
||
(
0x1F442
<=
c
||
c
<=
0x1F443
)
||
(
0x1F446
<=
c
||
c
<=
0x1F450
)
||
(
0x1F466
<=
c
||
c
<=
0x1F469
)
||
c
==
0x1F46E
||
(
0x1F470
<=
c
||
c
<=
0x1F478
)
||
c
==
0x1F47C
||
(
0x1F481
<=
c
||
c
<=
0x1F483
)
||
(
0x1F485
<=
c
||
c
<=
0x1F487
)
||
c
==
0x1F4AA
||
c
==
0x1F575
||
c
==
0x1F57A
||
c
==
0x1F590
||
(
0x1F595
<=
c
||
c
<=
0x1F596
)
||
(
0x1F645
<=
c
||
c
<=
0x1F647
)
||
(
0x1F64B
<=
c
||
c
<=
0x1F64F
)
||
c
==
0x1F6A3
||
(
0x1F6B4
<=
c
||
c
<=
0x1F6B6
)
||
c
==
0x1F6C0
||
(
0x1F918
<=
c
||
c
<=
0x1F91E
)
||
c
==
0x1F926
||
c
==
0x1F930
||
(
0x1F933
<=
c
||
c
<=
0x1F939
)
||
(
0x1F93B
<=
c
||
c
<=
0x1F93E
));
}
else
{
return
false
;
}
}
bool
GraphemeBreak
::
isGraphemeBreak
(
const
uint16_t
*
buf
,
size_t
start
,
size_t
count
,
size_t
offset
)
{
// This implementation closely follows Unicode Standard Annex #29 on
...
...
@@ -165,6 +207,17 @@ bool GraphemeBreak::isGraphemeBreak(const uint16_t* buf, size_t start, size_t co
return
false
;
}
}
// Proposed Rule GB9c from http://www.unicode.org/L2/L2016/16011r3-break-prop-emoji.pdf
// E_Base x E_Modifier
if
(
isEmojiModifier
(
c2
))
{
if
(
c1
==
0xFE0F
&&
offset_back
>
start
)
{
// skip over emoji variation selector
U16_PREV
(
buf
,
start
,
offset_back
,
c1
);
}
if
(
isEmojiBase
(
c1
))
{
return
false
;
}
}
// Rule GB10, Any ÷ Any
return
true
;
}
...
...
tests/GraphemeBreakTests.cpp
浏览文件 @
94d55255
...
...
@@ -136,6 +136,30 @@ TEST(GraphemeBreak, tailoring) {
EXPECT_TRUE
(
IsBreak
(
"U+0628 U+200D | U+2764"
));
}
TEST
(
GraphemeBreak
,
emojiModifiers
)
{
EXPECT_FALSE
(
IsBreak
(
"U+261D | U+1F3FB"
));
// white up pointing index + modifier
EXPECT_FALSE
(
IsBreak
(
"U+270C | U+1F3FB"
));
// victory hand + modifier
EXPECT_FALSE
(
IsBreak
(
"U+1F466 | U+1F3FB"
));
// boy + modifier
EXPECT_FALSE
(
IsBreak
(
"U+1F466 | U+1F3FC"
));
// boy + modifier
EXPECT_FALSE
(
IsBreak
(
"U+1F466 | U+1F3FD"
));
// boy + modifier
EXPECT_FALSE
(
IsBreak
(
"U+1F466 | U+1F3FE"
));
// boy + modifier
EXPECT_FALSE
(
IsBreak
(
"U+1F466 | U+1F3FF"
));
// boy + modifier
EXPECT_FALSE
(
IsBreak
(
"U+1F918 | U+1F3FF"
));
// sign of the horns + modifier
EXPECT_FALSE
(
IsBreak
(
"U+1F933 | U+1F3FF"
));
// selfie (Unicode 9) + modifier
// adding emoji style variation selector doesn't affect grapheme cluster
EXPECT_TRUE
(
IsBreak
(
"U+270C U+FE0E | U+1F3FB"
));
// victory hand + text style + modifier
EXPECT_FALSE
(
IsBreak
(
"U+270C U+FE0F | U+1F3FB"
));
// heart + emoji style + modifier
// heart is not an emoji base
EXPECT_TRUE
(
IsBreak
(
"U+2764 | U+1F3FB"
));
// heart + modifier
EXPECT_TRUE
(
IsBreak
(
"U+2764 U+FE0E | U+1F3FB"
));
// heart + emoji style + modifier
EXPECT_TRUE
(
IsBreak
(
"U+2764 U+FE0F | U+1F3FB"
));
// heart + emoji style + modifier
// rat is not an emoji modifer
EXPECT_TRUE
(
IsBreak
(
"U+1F466 | U+1F400"
));
// boy + rat
}
TEST
(
GraphemeBreak
,
offsets
)
{
uint16_t
string
[]
=
{
0x0041
,
0x06DD
,
0x0045
,
0x0301
,
0x0049
,
0x0301
};
EXPECT_TRUE
(
GraphemeBreak
::
isGraphemeBreak
(
string
,
2
,
3
,
2
));
...
...
编辑
预览
Markdown
is supported
0%
请重试
或
添加新附件
.
添加附件
取消
You are about to add
0
people
to the discussion. Proceed with caution.
先完成此消息的编辑!
取消
想要评论请
注册
或
登录