Home | History | Annotate | Download | only in utils 
      1 /*
      2  * Copyright (C) 2013, 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 #ifndef LATINIME_FORGETTING_CURVE_UTILS_H
     18 #define LATINIME_FORGETTING_CURVE_UTILS_H
     19 
     20 #include <vector>
     21 
     22 #include "defines.h"
     23 
     24 namespace latinime {
     25 
     26 class DictionaryHeaderStructurePolicy;
     27 
     28 // TODO: Check the elapsed time and decrease the probability depending on the time. Time field is
     29 // required to introduced to each terminal PtNode and bigram entry.
     30 // TODO: Quit using bigram probability to indicate the delta.
     31 class ForgettingCurveUtils {
     32  public:
     33     class TimeKeeper {
     34      public:
     35         TimeKeeper() : mCurrentTime(0) {}
     36         void setCurrentTime();
     37         int peekCurrentTime() const { return mCurrentTime; };
     38 
     39      private:
     40         DISALLOW_COPY_AND_ASSIGN(TimeKeeper);
     41 
     42         int mCurrentTime;
     43     };
     44 
     45     static const int MAX_UNIGRAM_COUNT;
     46     static const int MAX_UNIGRAM_COUNT_AFTER_GC;
     47     static const int MAX_BIGRAM_COUNT;
     48     static const int MAX_BIGRAM_COUNT_AFTER_GC;
     49 
     50     static TimeKeeper sTimeKeeper;
     51 
     52     static int getProbability(const int encodedUnigramProbability,
     53             const int encodedBigramProbability);
     54 
     55     static int getUpdatedEncodedProbability(const int originalEncodedProbability,
     56             const int newProbability);
     57 
     58     static int isValidEncodedProbability(const int encodedProbability);
     59 
     60     static int getEncodedProbabilityToSave(const int encodedProbability,
     61             const DictionaryHeaderStructurePolicy *const headerPolicy);
     62 
     63     static bool needsToDecay(const bool mindsBlockByDecay, const int unigramCount,
     64             const int bigramCount, const DictionaryHeaderStructurePolicy *const headerPolicy);
     65 
     66  private:
     67     DISALLOW_IMPLICIT_CONSTRUCTORS(ForgettingCurveUtils);
     68 
     69     class ProbabilityTable {
     70      public:
     71         ProbabilityTable();
     72 
     73         int getProbability(const int encodedProbability) const {
     74             if (encodedProbability < 0 || encodedProbability > static_cast<int>(mTable.size())) {
     75                 return NOT_A_PROBABILITY;
     76             }
     77             return mTable[encodedProbability];
     78         }
     79 
     80      private:
     81         DISALLOW_COPY_AND_ASSIGN(ProbabilityTable);
     82 
     83         std::vector<int> mTable;
     84     };
     85 
     86     static const int MAX_COMPUTED_PROBABILITY;
     87     static const int MAX_ENCODED_PROBABILITY;
     88     static const int MIN_VALID_ENCODED_PROBABILITY;
     89     static const int ENCODED_PROBABILITY_STEP;
     90     static const float MIN_PROBABILITY_TO_DECAY;
     91     static const int DECAY_INTERVAL_SECONDS;
     92 
     93     static const ProbabilityTable sProbabilityTable;
     94 
     95     static int decodeProbability(const int encodedProbability);
     96 
     97     static int backoff(const int unigramProbability);
     98 };
     99 } // namespace latinime
    100 #endif /* LATINIME_FORGETTING_CURVE_UTILS_H */
    101