Home | History | Annotate | Download | only in utils 
      1 /*
      2  * Copyright (C) 2014 The Android Open Source Project
      3  *
      4  * Licensed under the Apache License, Version 2.0 (the "License");
      5  * you may not use this file except in compliance with the License.
      6  * You may obtain a copy of the License at
      7  *
      8  *      http://www.apache.org/licenses/LICENSE-2.0
      9  *
     10  * Unless required by applicable law or agreed to in writing, software
     11  * distributed under the License is distributed on an "AS IS" BASIS,
     12  * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
     13  * See the License for the specific language governing permissions and
     14  * limitations under the License.
     15  */
     16 
     17 package com.android.inputmethod.latin.utils;
     18 
     19 import android.util.Log;
     20 
     21 import com.android.inputmethod.annotations.UsedForTesting;
     22 import com.android.inputmethod.latin.NgramContext;
     23 import com.android.inputmethod.latin.common.StringUtils;
     24 import com.android.inputmethod.latin.define.DecoderSpecificConstants;
     25 import com.android.inputmethod.latin.settings.SpacingAndPunctuations;
     26 
     27 import java.util.ArrayList;
     28 import java.util.List;
     29 import java.util.Locale;
     30 
     31 // Note: this class is used as a parameter type of a native method. You should be careful when you
     32 // rename this class or field name. See BinaryDictionary#addMultipleDictionaryEntriesNative().
     33 public final class WordInputEventForPersonalization {
     34     private static final String TAG = WordInputEventForPersonalization.class.getSimpleName();
     35     private static final boolean DEBUG_TOKEN = false;
     36 
     37     public final int[] mTargetWord;
     38     public final int mPrevWordsCount;
     39     public final int[][] mPrevWordArray =
     40             new int[DecoderSpecificConstants.MAX_PREV_WORD_COUNT_FOR_N_GRAM][];
     41     public final boolean[] mIsPrevWordBeginningOfSentenceArray =
     42             new boolean[DecoderSpecificConstants.MAX_PREV_WORD_COUNT_FOR_N_GRAM];
     43     // Time stamp in seconds.
     44     public final int mTimestamp;
     45 
     46     @UsedForTesting
     47     public WordInputEventForPersonalization(final CharSequence targetWord,
     48             final NgramContext ngramContext, final int timestamp) {
     49         mTargetWord = StringUtils.toCodePointArray(targetWord);
     50         mPrevWordsCount = ngramContext.getPrevWordCount();
     51         ngramContext.outputToArray(mPrevWordArray, mIsPrevWordBeginningOfSentenceArray);
     52         mTimestamp = timestamp;
     53     }
     54 
     55     // Process a list of words and return a list of {@link WordInputEventForPersonalization}
     56     // objects.
     57     public static ArrayList<WordInputEventForPersonalization> createInputEventFrom(
     58             final List<String> tokens, final int timestamp,
     59             final SpacingAndPunctuations spacingAndPunctuations, final Locale locale) {
     60         final ArrayList<WordInputEventForPersonalization> inputEvents = new ArrayList<>();
     61         final int N = tokens.size();
     62         NgramContext ngramContext = NgramContext.EMPTY_PREV_WORDS_INFO;
     63         for (int i = 0; i < N; ++i) {
     64             final String tempWord = tokens.get(i);
     65             if (StringUtils.isEmptyStringOrWhiteSpaces(tempWord)) {
     66                 // just skip this token
     67                 if (DEBUG_TOKEN) {
     68                     Log.d(TAG, "--- isEmptyStringOrWhiteSpaces: \"" + tempWord + "\"");
     69                 }
     70                 continue;
     71             }
     72             if (!DictionaryInfoUtils.looksValidForDictionaryInsertion(
     73                     tempWord, spacingAndPunctuations)) {
     74                 if (DEBUG_TOKEN) {
     75                     Log.d(TAG, "--- not looksValidForDictionaryInsertion: \""
     76                             + tempWord + "\"");
     77                 }
     78                 // Sentence terminator found. Split.
     79                 // TODO: Detect whether the context is beginning-of-sentence.
     80                 ngramContext = NgramContext.EMPTY_PREV_WORDS_INFO;
     81                 continue;
     82             }
     83             if (DEBUG_TOKEN) {
     84                 Log.d(TAG, "--- word: \"" + tempWord + "\"");
     85             }
     86             final WordInputEventForPersonalization inputEvent =
     87                     detectWhetherVaildWordOrNotAndGetInputEvent(
     88                             ngramContext, tempWord, timestamp, locale);
     89             if (inputEvent == null) {
     90                 continue;
     91             }
     92             inputEvents.add(inputEvent);
     93             ngramContext = ngramContext.getNextNgramContext(new NgramContext.WordInfo(tempWord));
     94         }
     95         return inputEvents;
     96     }
     97 
     98     private static WordInputEventForPersonalization detectWhetherVaildWordOrNotAndGetInputEvent(
     99             final NgramContext ngramContext, final String targetWord, final int timestamp,
    100             final Locale locale) {
    101         if (locale == null) {
    102             return null;
    103         }
    104         return new WordInputEventForPersonalization(targetWord, ngramContext, timestamp);
    105     }
    106 }
    107