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
80 lines
2.8 KiB
C++
80 lines
2.8 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.
|
|
*/
|
|
|
|
#include <gtest/gtest.h>
|
|
#include "ICUTestBase.h"
|
|
#include "UnicodeUtils.h"
|
|
#include <minikin/WordBreaker.h>
|
|
#include <unicode/locid.h>
|
|
#include <unicode/uclean.h>
|
|
#include <unicode/udata.h>
|
|
|
|
#define LOG_TAG "Minikin"
|
|
#include <cutils/log.h>
|
|
|
|
#ifndef NELEM
|
|
#define NELEM(x) ((sizeof(x) / sizeof((x)[0])))
|
|
#endif
|
|
|
|
using namespace android;
|
|
|
|
typedef ICUTestBase WordBreakerTest;
|
|
|
|
TEST_F(WordBreakerTest, basic) {
|
|
uint16_t buf[] = {'h', 'e', 'l', 'l' ,'o', ' ', 'w', 'o', 'r', 'l', 'd'};
|
|
WordBreaker breaker;
|
|
breaker.setLocale(icu::Locale::getEnglish());
|
|
breaker.setText(buf, NELEM(buf));
|
|
EXPECT_EQ(0, breaker.current());
|
|
EXPECT_EQ(6, breaker.next()); // after "hello "
|
|
EXPECT_EQ(0, breaker.wordStart()); // "hello"
|
|
EXPECT_EQ(5, breaker.wordEnd());
|
|
EXPECT_EQ(6, breaker.current());
|
|
EXPECT_EQ((ssize_t)NELEM(buf), breaker.next()); // end
|
|
EXPECT_EQ(6, breaker.wordStart()); // "world"
|
|
EXPECT_EQ(11, breaker.wordEnd());
|
|
EXPECT_EQ(11, breaker.current());
|
|
}
|
|
|
|
TEST_F(WordBreakerTest, softHyphen) {
|
|
uint16_t buf[] = {'h', 'e', 'l', 0x00AD, 'l' ,'o', ' ', 'w', 'o', 'r', 'l', 'd'};
|
|
WordBreaker breaker;
|
|
breaker.setLocale(icu::Locale::getEnglish());
|
|
breaker.setText(buf, NELEM(buf));
|
|
EXPECT_EQ(0, breaker.current());
|
|
EXPECT_EQ(7, breaker.next()); // after "hel{SOFT HYPHEN}lo "
|
|
EXPECT_EQ(0, breaker.wordStart()); // "hel{SOFT HYPHEN}lo"
|
|
EXPECT_EQ(6, breaker.wordEnd());
|
|
EXPECT_EQ((ssize_t)NELEM(buf), breaker.next()); // end
|
|
EXPECT_EQ(7, breaker.wordStart()); // "world"
|
|
EXPECT_EQ(12, breaker.wordEnd());
|
|
}
|
|
|
|
TEST_F(WordBreakerTest, punct) {
|
|
uint16_t buf[] = {0x00A1, 0x00A1, 'h', 'e', 'l', 'l' ,'o', ',', ' ', 'w', 'o', 'r', 'l', 'd',
|
|
'!', '!'};
|
|
WordBreaker breaker;
|
|
breaker.setLocale(icu::Locale::getEnglish());
|
|
breaker.setText(buf, NELEM(buf));
|
|
EXPECT_EQ(0, breaker.current());
|
|
EXPECT_EQ(9, breaker.next()); // after "¡¡hello, "
|
|
EXPECT_EQ(2, breaker.wordStart()); // "hello"
|
|
EXPECT_EQ(7, breaker.wordEnd());
|
|
EXPECT_EQ((ssize_t)NELEM(buf), breaker.next()); // end
|
|
EXPECT_EQ(9, breaker.wordStart()); // "world"
|
|
EXPECT_EQ(14, breaker.wordEnd());
|
|
}
|