mirror of
https://github.com/flutter/flutter.git
synced 2026-02-20 02:29:02 +08:00
57b6dae989
Implement a WordBreaker that defines our concept of valid word boundaries, customizing the ICU behavior. Currently, we suppress line breaks at soft hyphens (these are handled specially). Also, the new WordBreaker class has methods that determine the start and end of the word (punctuation stripped) for the purpose of hyphenation. This patch, in its current form, doesn't handle email addresses and URLs specially, but the WordBreaker class is the correct place to do so. Also, special case handling of hyphens and dashes is still done in LineBreaker, but all of that should be moved to WordBreaker. Bug: 20126487 Bug: 20566159 Change-Id: I492cbad963f9b74a2915f010dad46bb91f97b2fe
111 lines
3.0 KiB
C++
111 lines
3.0 KiB
C++
/*
|
|
* Copyright (C) 2015 The Android Open Source Project
|
|
*
|
|
* Licensed under the Apache License, Version 2.0 (the "License");
|
|
* you may not use this file except in compliance with the License.
|
|
* You may obtain a copy of the License at
|
|
*
|
|
* http://www.apache.org/licenses/LICENSE-2.0
|
|
*
|
|
* Unless required by applicable law or agreed to in writing, software
|
|
* distributed under the License is distributed on an "AS IS" BASIS,
|
|
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
* See the License for the specific language governing permissions and
|
|
* limitations under the License.
|
|
*/
|
|
|
|
#define LOG_TAG "Minikin"
|
|
#include <cutils/log.h>
|
|
|
|
#include "minikin/WordBreaker.h"
|
|
|
|
#include <unicode/uchar.h>
|
|
#include <unicode/utf16.h>
|
|
|
|
namespace android {
|
|
|
|
const uint32_t CHAR_SOFT_HYPHEN = 0x00AD;
|
|
|
|
void WordBreaker::setLocale(const icu::Locale& locale) {
|
|
UErrorCode status = U_ZERO_ERROR;
|
|
mBreakIterator.reset(icu::BreakIterator::createLineInstance(locale, status));
|
|
// TODO: handle failure status
|
|
if (mText != nullptr) {
|
|
mBreakIterator->setText(&mUText, status);
|
|
}
|
|
mIteratorWasReset = true;
|
|
}
|
|
|
|
void WordBreaker::setText(const uint16_t* data, size_t size) {
|
|
mText = data;
|
|
mTextSize = size;
|
|
mIteratorWasReset = false;
|
|
mLast = 0;
|
|
mCurrent = 0;
|
|
UErrorCode status = U_ZERO_ERROR;
|
|
utext_openUChars(&mUText, data, size, &status);
|
|
mBreakIterator->setText(&mUText, status);
|
|
mBreakIterator->first();
|
|
}
|
|
|
|
ssize_t WordBreaker::current() const {
|
|
return mCurrent;
|
|
}
|
|
|
|
ssize_t WordBreaker::next() {
|
|
int32_t result;
|
|
mLast = mCurrent;
|
|
do {
|
|
if (mIteratorWasReset) {
|
|
result = mBreakIterator->following(mCurrent);
|
|
mIteratorWasReset = false;
|
|
} else {
|
|
result = mBreakIterator->next();
|
|
}
|
|
} while (result != icu::BreakIterator::DONE && (size_t)result != mTextSize
|
|
&& mText[result - 1] == CHAR_SOFT_HYPHEN);
|
|
mCurrent = (ssize_t)result;
|
|
return mCurrent;
|
|
}
|
|
|
|
ssize_t WordBreaker::wordStart() const {
|
|
ssize_t result = mLast;
|
|
while (result < mCurrent) {
|
|
UChar32 c;
|
|
ssize_t ix = result;
|
|
U16_NEXT(mText, ix, mCurrent, c);
|
|
int32_t lb = u_getIntPropertyValue(c, UCHAR_LINE_BREAK);
|
|
// strip leading punctuation, defined as OP and QU line breaking classes,
|
|
// see UAX #14
|
|
if (!(lb == U_LB_OPEN_PUNCTUATION || lb == U_LB_QUOTATION)) {
|
|
break;
|
|
}
|
|
result = ix;
|
|
}
|
|
return result;
|
|
}
|
|
|
|
ssize_t WordBreaker::wordEnd() const {
|
|
ssize_t result = mCurrent;
|
|
while (result > mLast) {
|
|
UChar32 c;
|
|
ssize_t ix = result;
|
|
U16_PREV(mText, mLast, ix, c);
|
|
int32_t gc_mask = U_GET_GC_MASK(c);
|
|
// strip trailing space and punctuation
|
|
if ((gc_mask & (U_GC_ZS_MASK | U_GC_P_MASK)) == 0) {
|
|
break;
|
|
}
|
|
result = ix;
|
|
}
|
|
return result;
|
|
}
|
|
|
|
void WordBreaker::finish() {
|
|
mText = nullptr;
|
|
// Note: calling utext_close multiply is safe
|
|
utext_close(&mUText);
|
|
}
|
|
|
|
} // namespace android
|