firka/flutter
3
0
Fork 1
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Do not allow line breaks before currency symbols

Browse Source 
Implement the change proposed in UTC document L2/16-043R
(http://www.unicode.org/L2/L2016/16043r-line-break-pr-po.txt) to make
sure we do not break between letters and currency symbols.

Bug: 24959657
Change-Id: Ia29d0e5625f84870bd910d0c6e19036d17206704
This commit is contained in:
Roozbeh Pournader
2016-03-16 15:23:20 -07:00
parent 5ccdf654f5
commit 0eaf80b016
2 changed files with 29 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
engine/src/flutter/libs/minikin/WordBreaker.cpp
View File

@@ -79,6 +79,18 @@ static bool isBreakValid(const uint16_t* buf, size_t bufEnd, size_t i) {
uint32_t next_codepoint; uint32_t next_codepoint;
size_t next_offset = i; size_t next_offset = i;
U16_NEXT(buf, next_offset, bufEnd, next_codepoint); U16_NEXT(buf, next_offset, bufEnd, next_codepoint);
// Proposed change to LB24 from http://www.unicode.org/L2/L2016/16043r-line-break-pr-po.txt
//(AL | HL) × (PR | PO)
int32_t lineBreak = u_getIntPropertyValue(codePoint, UCHAR_LINE_BREAK);
if (lineBreak == U_LB_ALPHABETIC || lineBreak == U_LB_HEBREW_LETTER) {
lineBreak = u_getIntPropertyValue(next_codepoint, UCHAR_LINE_BREAK);
if (lineBreak == U_LB_PREFIX_NUMERIC || lineBreak == U_LB_POSTFIX_NUMERIC) {
return false;
}
}
// Known emoji ZWJ sequences
if (codePoint == CHAR_ZWJ) { if (codePoint == CHAR_ZWJ) {
// Possible emoji ZWJ sequence // Possible emoji ZWJ sequence
if (next_codepoint == 0x2764 || // HEAVY BLACK HEART if (next_codepoint == 0x2764 || // HEAVY BLACK HEART
@@ -91,6 +103,7 @@ static bool isBreakValid(const uint16_t* buf, size_t bufEnd, size_t i) {
return false; return false;
} }
} }
// Proposed Rule LB30b from http://www.unicode.org/L2/L2016/16011r3-break-prop-emoji.pdf // Proposed Rule LB30b from http://www.unicode.org/L2/L2016/16011r3-break-prop-emoji.pdf
// EB x EM // EB x EM
if (isEmojiModifier(next_codepoint)) { if (isEmojiModifier(next_codepoint)) {

16
engine/src/flutter/tests/WordBreakerTests.cpp
View File

@@ -69,6 +69,22 @@ TEST_F(WordBreakerTest, softHyphen) {
EXPECT_EQ(0, breaker.breakBadness()); EXPECT_EQ(0, breaker.breakBadness());
} }
TEST_F(WordBreakerTest, postfixAndPrefix) {
uint16_t buf[] = {'U', 'S', 0x00A2, ' ', 'J', 'P', 0x00A5}; // US¢ JP¥
WordBreaker breaker;
breaker.setLocale(icu::Locale::getEnglish());
breaker.setText(buf, NELEM(buf));
EXPECT_EQ(0, breaker.current());
EXPECT_EQ(4, breaker.next()); // after CENT SIGN
EXPECT_EQ(0, breaker.wordStart()); // "US¢"
EXPECT_EQ(3, breaker.wordEnd());
EXPECT_EQ((ssize_t)NELEM(buf), breaker.next()); // end of string
EXPECT_EQ(4, breaker.wordStart()); // "JP¥"
EXPECT_EQ((ssize_t)NELEM(buf), breaker.wordEnd());
}
TEST_F(WordBreakerTest, zwjEmojiSequences) { TEST_F(WordBreakerTest, zwjEmojiSequences) {
uint16_t buf[] = { uint16_t buf[] = {
// man + zwj + heart + zwj + man // man + zwj + heart + zwj + man