satok | 3008825 | 2010-12-01 21:22:15 +0900 | [diff] [blame] | 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_UNIGRAM_DICTIONARY_H |
| 18 | #define LATINIME_UNIGRAM_DICTIONARY_H |
| 19 | |
satok | e808e43 | 2010-12-02 14:53:24 +0900 | [diff] [blame] | 20 | #include "defines.h" |
| 21 | |
satok | 3008825 | 2010-12-01 21:22:15 +0900 | [diff] [blame] | 22 | namespace latinime { |
| 23 | |
satok | 3008825 | 2010-12-01 21:22:15 +0900 | [diff] [blame] | 24 | class UnigramDictionary { |
| 25 | public: |
satok | e808e43 | 2010-12-02 14:53:24 +0900 | [diff] [blame] | 26 | UnigramDictionary(const unsigned char *dict, int typedLetterMultipler, int fullWordMultiplier, |
satok | 18c28f4 | 2010-12-02 18:11:54 +0900 | [diff] [blame] | 27 | int maxWordLength, int maxWords, int maxAlternatives, const bool isLatestDictVersion); |
satok | 3008825 | 2010-12-01 21:22:15 +0900 | [diff] [blame] | 28 | int getSuggestions(int *codes, int codesSize, unsigned short *outWords, int *frequencies, |
| 29 | int *nextLetters, int nextLettersSize); |
satok | 3008825 | 2010-12-01 21:22:15 +0900 | [diff] [blame] | 30 | ~UnigramDictionary(); |
| 31 | |
| 32 | private: |
| 33 | void initSuggestions(int *codes, int codesSize, unsigned short *outWords, int *frequencies); |
satok | 18c28f4 | 2010-12-02 18:11:54 +0900 | [diff] [blame] | 34 | int getSuggestionCandidates(int inputLength, int skipPos, int *nextLetters, |
| 35 | int nextLettersSize); |
satok | 3008825 | 2010-12-01 21:22:15 +0900 | [diff] [blame] | 36 | void getVersionNumber(); |
| 37 | bool checkIfDictVersionIsLatest(); |
| 38 | int getAddress(int *pos); |
satok | 3008825 | 2010-12-01 21:22:15 +0900 | [diff] [blame] | 39 | int getFreq(int *pos); |
satok | 3008825 | 2010-12-01 21:22:15 +0900 | [diff] [blame] | 40 | int wideStrLen(unsigned short *str); |
satok | 3008825 | 2010-12-01 21:22:15 +0900 | [diff] [blame] | 41 | bool sameAsTyped(unsigned short *word, int length); |
satok | 3008825 | 2010-12-01 21:22:15 +0900 | [diff] [blame] | 42 | bool addWord(unsigned short *word, int length, int frequency); |
satok | 3008825 | 2010-12-01 21:22:15 +0900 | [diff] [blame] | 43 | unsigned short toLowerCase(unsigned short c); |
satok | 6831926 | 2010-12-03 19:38:08 +0900 | [diff] [blame] | 44 | void getWordsRec(const int childrenCount, const int pos, const int depth, const int maxDepth, |
| 45 | const bool traverseAllNodes, const int snr, const int inputIndex, const int diffs, |
| 46 | const int skipPos, int *nextLetters, const int nextLettersSize); |
| 47 | void getWords(const int initialPos, const int inputLength, const int skipPos, int *nextLetters, |
| 48 | const int nextLettersSize); |
satok | 3008825 | 2010-12-01 21:22:15 +0900 | [diff] [blame] | 49 | void registerNextLetter(unsigned short c, int *nextLetters, int nextLettersSize); |
satok | 715514d | 2010-12-02 20:19:59 +0900 | [diff] [blame] | 50 | void onTerminalWhenUserTypedLengthIsGreaterThanInputLength(unsigned short *word, |
| 51 | const int mInputLength, const int depth, const int snr, int *nextLetters, |
| 52 | const int nextLettersSize, const int skipPos, const int freq); |
satok | 715514d | 2010-12-02 20:19:59 +0900 | [diff] [blame] | 53 | void onTerminalWhenUserTypedLengthIsSameAsInputLength(unsigned short *word, const int depth, |
| 54 | const int snr, const int skipPos, const int freq, const int addedWeight); |
satok | 28bd03b | 2010-12-03 16:39:16 +0900 | [diff] [blame] | 55 | bool needsToSkipCurrentNode(const unsigned short c, |
satok | 6831926 | 2010-12-03 19:38:08 +0900 | [diff] [blame] | 56 | const int inputIndex, const int skipPos, const int depth); |
satok | 28bd03b | 2010-12-03 16:39:16 +0900 | [diff] [blame] | 57 | int getMatchedProximityId(const int *currentChars, const unsigned short lowerC, |
| 58 | const unsigned short c, const int skipPos); |
| 59 | |
satok | e808e43 | 2010-12-02 14:53:24 +0900 | [diff] [blame] | 60 | const unsigned char *DICT; |
satok | 3008825 | 2010-12-01 21:22:15 +0900 | [diff] [blame] | 61 | const int MAX_WORDS; |
| 62 | const int MAX_WORD_LENGTH; |
| 63 | const int MAX_ALTERNATIVES; |
satok | e808e43 | 2010-12-02 14:53:24 +0900 | [diff] [blame] | 64 | const bool IS_LATEST_DICT_VERSION; |
satok | 18c28f4 | 2010-12-02 18:11:54 +0900 | [diff] [blame] | 65 | const int TYPED_LETTER_MULTIPLIER; |
| 66 | const int FULL_WORD_MULTIPLIER; |
satok | 3008825 | 2010-12-01 21:22:15 +0900 | [diff] [blame] | 67 | |
satok | 3008825 | 2010-12-01 21:22:15 +0900 | [diff] [blame] | 68 | int *mFrequencies; |
satok | 3008825 | 2010-12-01 21:22:15 +0900 | [diff] [blame] | 69 | unsigned short *mOutputChars; |
satok | 3008825 | 2010-12-01 21:22:15 +0900 | [diff] [blame] | 70 | int *mInputCodes; |
| 71 | int mInputLength; |
satok | 715514d | 2010-12-02 20:19:59 +0900 | [diff] [blame] | 72 | // MAX_WORD_LENGTH_INTERNAL must be bigger than MAX_WORD_LENGTH |
| 73 | unsigned short mWord[MAX_WORD_LENGTH_INTERNAL]; |
satok | 3008825 | 2010-12-01 21:22:15 +0900 | [diff] [blame] | 74 | int mMaxEditDistance; |
satok | 3008825 | 2010-12-01 21:22:15 +0900 | [diff] [blame] | 75 | }; |
| 76 | |
| 77 | // ---------------------------------------------------------------------------- |
| 78 | |
| 79 | }; // namespace latinime |
| 80 | |
| 81 | #endif // LATINIME_UNIGRAM_DICTIONARY_H |