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"); you may not
      5  * use this file except in compliance with the License. You may obtain a copy of
      6  * 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, WITHOUT
     12  * WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the
     13  * License for the specific language governing permissions and limitations under
     14  * the License.
     15  */
     16 
     17 package com.android.inputmethod.latin.utils;
     18 
     19 import com.android.inputmethod.latin.makedict.DictionaryHeader;
     20 import com.android.inputmethod.latin.makedict.NgramProperty;
     21 import com.android.inputmethod.latin.makedict.ProbabilityInfo;
     22 import com.android.inputmethod.latin.makedict.WordProperty;
     23 
     24 import java.util.HashMap;
     25 
     26 public class CombinedFormatUtils {
     27     public static final String DICTIONARY_TAG = "dictionary";
     28     public static final String BIGRAM_TAG = "bigram";
     29     public static final String NGRAM_TAG = "ngram";
     30     public static final String NGRAM_PREV_WORD_TAG = "prev_word";
     31     public static final String PROBABILITY_TAG = "f";
     32     public static final String HISTORICAL_INFO_TAG = "historicalInfo";
     33     public static final String HISTORICAL_INFO_SEPARATOR = ":";
     34     public static final String WORD_TAG = "word";
     35     public static final String BEGINNING_OF_SENTENCE_TAG = "beginning_of_sentence";
     36     public static final String NOT_A_WORD_TAG = "not_a_word";
     37     public static final String POSSIBLY_OFFENSIVE_TAG = "possibly_offensive";
     38     public static final String TRUE_VALUE = "true";
     39 
     40     public static String formatAttributeMap(final HashMap<String, String> attributeMap) {
     41         final StringBuilder builder = new StringBuilder();
     42         builder.append(DICTIONARY_TAG + "=");
     43         if (attributeMap.containsKey(DictionaryHeader.DICTIONARY_ID_KEY)) {
     44             builder.append(attributeMap.get(DictionaryHeader.DICTIONARY_ID_KEY));
     45         }
     46         for (final String key : attributeMap.keySet()) {
     47             if (key.equals(DictionaryHeader.DICTIONARY_ID_KEY)) {
     48                 continue;
     49             }
     50             final String value = attributeMap.get(key);
     51             builder.append("," + key + "=" + value);
     52         }
     53         builder.append("\n");
     54         return builder.toString();
     55     }
     56 
     57     public static String formatWordProperty(final WordProperty wordProperty) {
     58         final StringBuilder builder = new StringBuilder();
     59         builder.append(" " + WORD_TAG + "=" + wordProperty.mWord);
     60         builder.append(",");
     61         builder.append(formatProbabilityInfo(wordProperty.mProbabilityInfo));
     62         if (wordProperty.mIsBeginningOfSentence) {
     63             builder.append("," + BEGINNING_OF_SENTENCE_TAG + "=" + TRUE_VALUE);
     64         }
     65         if (wordProperty.mIsNotAWord) {
     66             builder.append("," + NOT_A_WORD_TAG + "=" + TRUE_VALUE);
     67         }
     68         if (wordProperty.mIsPossiblyOffensive) {
     69             builder.append("," + POSSIBLY_OFFENSIVE_TAG + "=" + TRUE_VALUE);
     70         }
     71         builder.append("\n");
     72         if (wordProperty.mHasNgrams) {
     73             for (final NgramProperty ngramProperty : wordProperty.mNgrams) {
     74                 builder.append(" " + NGRAM_TAG + "=" + ngramProperty.mTargetWord.mWord);
     75                 builder.append(",");
     76                 builder.append(formatProbabilityInfo(ngramProperty.mTargetWord.mProbabilityInfo));
     77                 builder.append("\n");
     78                 for (int i = 0; i < ngramProperty.mNgramContext.getPrevWordCount(); i++) {
     79                     builder.append("  " + NGRAM_PREV_WORD_TAG + "[" + i + "]="
     80                             + ngramProperty.mNgramContext.getNthPrevWord(i + 1));
     81                     if (ngramProperty.mNgramContext.isNthPrevWordBeginningOfSentence(i + 1)) {
     82                         builder.append("," + BEGINNING_OF_SENTENCE_TAG + "=true");
     83                     }
     84                     builder.append("\n");
     85                 }
     86             }
     87         }
     88         return builder.toString();
     89     }
     90 
     91     public static String formatProbabilityInfo(final ProbabilityInfo probabilityInfo) {
     92         final StringBuilder builder = new StringBuilder();
     93         builder.append(PROBABILITY_TAG + "=" + probabilityInfo.mProbability);
     94         if (probabilityInfo.hasHistoricalInfo()) {
     95             builder.append(",");
     96             builder.append(HISTORICAL_INFO_TAG + "=");
     97             builder.append(probabilityInfo.mTimestamp);
     98             builder.append(HISTORICAL_INFO_SEPARATOR);
     99             builder.append(probabilityInfo.mLevel);
    100             builder.append(HISTORICAL_INFO_SEPARATOR);
    101             builder.append(probabilityInfo.mCount);
    102         }
    103         return builder.toString();
    104     }
    105 
    106     public static boolean isLiteralTrue(final String value) {
    107         return TRUE_VALUE.equalsIgnoreCase(value);
    108     }
    109 }
    110