jasder
/
antlr
1
0
Fork 1
Code Issues Pull Requests Releases 1 Wiki Activity

EmojiDefault and TextDefault

This commit is contained in:
Ben Hamilton 2017-03-08 17:05:31 -08:00
parent b467dc8015
commit c71b7d2f18
3 changed files with 48 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
doc/lexer-rules.md
View File

@ -66,6 +66,14 @@ Match that character or sequence of characters. E.g., ’while’ or ’=’.</t
<p>As a shortcut for <tt>\p{Block=Latin_1_Supplement}</tt>, you can refer to blocks using <a href="http://www.unicode.org/Public/UCD/latest/ucd/Blocks.txt">Unicode block names</a> prefixed with <tt>In</tt> and with spaces changed to <tt>_</tt>. For example: <tt>\p{InLatin_1_Supplement}</tt>, <tt>\p{InYijing_Hexagram_Symbols}</tt>, and <tt>\p{InAncient_Greek_Numbers}</tt>.</p>
<p>A few extra properties are supported:</p>
<ul>
<li><tt>\p{Extended_Pictographic}</tt> (see <a href="http://unicode.org/reports/tr35/">UTS #35</a>)</li>
<li><tt>\p{EmojiPresentation=EmojiDefault}</tt> (code points which have colorful emoji-style presentation by default but which can also be displayed text-style)</li>
<li><tt>\p{EmojiPresentation=TextDefault}</tt> (code points which have black-and-white text-style presentation by default but which can also be displayed emoji-style)</li>
<li><tt>\p{EmojiPresentation=Text}</tt> (code points which have only black-and-white text-style and lack a colorful emoji-style presentation)</li>
</ul>
<p>Property names are <b>case-insensitive</b>, and <tt>_</tt> and <tt>-</tt> are treated identically</p>
<p>Here are a few examples:</p>

22
tool-testsuite/test/org/antlr/v4/test/tool/TestUnicodeData.java
View File

@ -176,6 +176,28 @@ public class TestUnicodeData {
UnicodeData.getPropertyCodePoints("Extended_Pictographic").contains('0'));
}
@Test
public void emojiPresentation() {
assertTrue(
"U+1F4A9 PILE OF POO is in EmojiPresentation=EmojiDefault",
UnicodeData.getPropertyCodePoints("EmojiPresentation=EmojiDefault").contains(0x1F4A9));
assertFalse(
"0 is not in EmojiPresentation=EmojiDefault",
UnicodeData.getPropertyCodePoints("EmojiPresentation=EmojiDefault").contains('0'));
assertFalse(
"A is not in EmojiPresentation=EmojiDefault",
UnicodeData.getPropertyCodePoints("EmojiPresentation=EmojiDefault").contains('A'));
assertFalse(
"U+1F4A9 PILE OF POO is not in EmojiPresentation=TextDefault",
UnicodeData.getPropertyCodePoints("EmojiPresentation=TextDefault").contains(0x1F4A9));
assertTrue(
"0 is in EmojiPresentation=TextDefault",
UnicodeData.getPropertyCodePoints("EmojiPresentation=TextDefault").contains('0'));
assertFalse(
"A is not in EmojiPresentation=TextDefault",
UnicodeData.getPropertyCodePoints("EmojiPresentation=TextDefault").contains('A'));
}
@Test
public void testPropertyCaseInsensitivity() {
assertTrue(UnicodeData.getPropertyCodePoints("l").contains('x'));

18
tool/src/org/antlr/v4/unicode/UnicodeDataTemplateController.java
View File

@ -76,6 +76,7 @@ public abstract class UnicodeDataTemplateController {
addUnicodeBinaryPropertyCodesToCodePointRanges(propertyCodePointRanges);
addUnicodeIntPropertyCodesToCodePointRanges(propertyCodePointRanges);
addTR35ExtendedPictographicPropertyCodesToCodePointRanges(propertyCodePointRanges);
addEmojiPresentationPropertyCodesToCodePointRanges(propertyCodePointRanges);
Map<String, String> propertyAliases = new LinkedHashMap<>();
addUnicodeCategoryCodesToNames(propertyAliases);
@ -349,6 +350,23 @@ public abstract class UnicodeDataTemplateController {
propertyCodePointRanges.put("EmojiNRK", emojiNRKIntervalSet);
}
private static void addEmojiPresentationPropertyCodesToCodePointRanges(Map<String, IntervalSet> propertyCodePointRanges) {
UnicodeSet emojiDefaultUnicodeSet = new UnicodeSet("[[\\p{Emoji=Yes}]&[\\p{Emoji_Presentation=Yes}]]");
IntervalSet emojiDefaultIntervalSet = new IntervalSet();
addUnicodeSetToIntervalSet(emojiDefaultUnicodeSet, emojiDefaultIntervalSet);
propertyCodePointRanges.put("EmojiPresentation=EmojiDefault", emojiDefaultIntervalSet);
UnicodeSet textDefaultUnicodeSet = new UnicodeSet("[[\\p{Emoji=Yes}]&[\\p{Emoji_Presentation=No}]]");
IntervalSet textDefaultIntervalSet = new IntervalSet();
addUnicodeSetToIntervalSet(textDefaultUnicodeSet, textDefaultIntervalSet);
propertyCodePointRanges.put("EmojiPresentation=TextDefault", textDefaultIntervalSet);
UnicodeSet textUnicodeSet = new UnicodeSet("[\\p{Emoji=No}]");
IntervalSet textIntervalSet = new IntervalSet();
addUnicodeSetToIntervalSet(textUnicodeSet, textIntervalSet);
propertyCodePointRanges.put("EmojiPresentation=Text", textIntervalSet);
}
private static void addIntPropertyAliases(int property, String namePrefix, Map<String, String> propertyAliases) {
String propertyName = getShortPropertyName(property);
for (int propertyValue = UCharacter.getIntPropertyMinValue(property);