1 /* 2 * Copyright (C) 2010 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_BIGRAM_DICTIONARY_H 18 #define LATINIME_BIGRAM_DICTIONARY_H 19 20 namespace latinime { 21 22 class Dictionary; 23 class BigramDictionary { 24 public: 25 BigramDictionary(const unsigned char *dict, int maxWordLength, int maxAlternatives, 26 const bool isLatestDictVersion, const bool hasBigram, Dictionary *parentDictionary); 27 int getBigrams(unsigned short *word, int length, int *codes, int codesSize, 28 unsigned short *outWords, int *frequencies, int maxWordLength, int maxBigrams, 29 int maxAlternatives); 30 ~BigramDictionary(); 31 private: 32 bool addWordBigram(unsigned short *word, int length, int frequency); 33 int getBigramAddress(int *pos, bool advance); 34 int getBigramFreq(int *pos); 35 void searchForTerminalNode(int addressLookingFor, int frequency); getFirstBitOfByte(int * pos)36 bool getFirstBitOfByte(int *pos) { return (DICT[*pos] & 0x80) > 0; } getSecondBitOfByte(int * pos)37 bool getSecondBitOfByte(int *pos) { return (DICT[*pos] & 0x40) > 0; } 38 bool checkFirstCharacter(unsigned short *word); 39 40 const unsigned char *DICT; 41 const int MAX_WORD_LENGTH; 42 const int MAX_ALTERNATIVES; 43 const bool IS_LATEST_DICT_VERSION; 44 const bool HAS_BIGRAM; 45 46 Dictionary *mParentDictionary; 47 int *mBigramFreq; 48 int mMaxBigrams; 49 unsigned short *mBigramChars; 50 int *mInputCodes; 51 int mInputLength; 52 }; 53 54 } // namespace latinime 55 56 #endif // LATINIME_BIGRAM_DICTIONARY_H 57