Merge "Filter out control characters and non-unicode code points."
This commit is contained in:
commit
5c00bde9bc
4 changed files with 44 additions and 4 deletions
|
@ -95,6 +95,7 @@ LATIN_IME_CORE_SRC_FILES := \
|
|||
$(addprefix utils/, \
|
||||
autocorrection_threshold_utils.cpp \
|
||||
char_utils.cpp \
|
||||
jni_data_utils.cpp \
|
||||
log_utils.cpp \
|
||||
time_keeper.cpp)
|
||||
|
||||
|
|
|
@ -302,7 +302,6 @@ static jint latinime_BinaryDictionary_getNextWord(JNIEnv *env, jclass clazz,
|
|||
int wordCodePoints[outCodePointsLength];
|
||||
memset(wordCodePoints, 0, sizeof(wordCodePoints));
|
||||
const int nextToken = dictionary->getNextWordAndNextToken(token, wordCodePoints);
|
||||
env->SetIntArrayRegion(outCodePoints, 0, outCodePointsLength, wordCodePoints);
|
||||
JniDataUtils::outputCodePoints(env, outCodePoints, 0 /* start */,
|
||||
MAX_WORD_LENGTH /* maxLength */, wordCodePoints, outCodePointsLength,
|
||||
false /* needsNullTermination */);
|
||||
|
|
24
native/jni/src/utils/jni_data_utils.cpp
Normal file
24
native/jni/src/utils/jni_data_utils.cpp
Normal file
|
@ -0,0 +1,24 @@
|
|||
/*
|
||||
* Copyright (C) 2014 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 "utils/jni_data_utils.h"
|
||||
|
||||
namespace latinime {
|
||||
|
||||
const int JniDataUtils::CODE_POINT_REPLACEMENT_CHARACTER = 0xFFFD;
|
||||
const int JniDataUtils::CODE_POINT_NULL = 0;
|
||||
|
||||
} // namespace latinime
|
|
@ -23,6 +23,7 @@
|
|||
#include "jni.h"
|
||||
#include "suggest/core/policy/dictionary_header_structure_policy.h"
|
||||
#include "suggest/policyimpl/dictionary/header/header_read_write_utils.h"
|
||||
#include "utils/char_utils.h"
|
||||
|
||||
namespace latinime {
|
||||
|
||||
|
@ -69,16 +70,31 @@ class JniDataUtils {
|
|||
const int maxLength, const int *const codePoints, const int codePointCount,
|
||||
const bool needsNullTermination) {
|
||||
const int outputCodePointCount = std::min(maxLength, codePointCount);
|
||||
env->SetIntArrayRegion(intArrayToOutputCodePoints, start, outputCodePointCount, codePoints);
|
||||
int outputCodePonts[outputCodePointCount];
|
||||
for (int i = 0; i < outputCodePointCount; ++i) {
|
||||
const int codePoint = codePoints[i];
|
||||
if (!CharUtils::isInUnicodeSpace(codePoint)) {
|
||||
outputCodePonts[i] = CODE_POINT_REPLACEMENT_CHARACTER;
|
||||
} else if (codePoint >= 0x01 && codePoint <= 0x1F) {
|
||||
// Control code.
|
||||
outputCodePonts[i] = CODE_POINT_REPLACEMENT_CHARACTER;
|
||||
} else {
|
||||
outputCodePonts[i] = codePoint;
|
||||
}
|
||||
}
|
||||
env->SetIntArrayRegion(intArrayToOutputCodePoints, start, outputCodePointCount,
|
||||
outputCodePonts);
|
||||
if (needsNullTermination && outputCodePointCount < maxLength) {
|
||||
const int terminal = 0;
|
||||
env->SetIntArrayRegion(intArrayToOutputCodePoints, start + outputCodePointCount,
|
||||
1 /* len */, &terminal);
|
||||
1 /* len */, &CODE_POINT_NULL);
|
||||
}
|
||||
}
|
||||
|
||||
private:
|
||||
DISALLOW_IMPLICIT_CONSTRUCTORS(JniDataUtils);
|
||||
|
||||
static const int CODE_POINT_REPLACEMENT_CHARACTER;
|
||||
static const int CODE_POINT_NULL;
|
||||
};
|
||||
} // namespace latinime
|
||||
#endif // LATINIME_JNI_DATA_UTILS_H
|
||||
|
|
Loading…
Reference in a new issue