suggestmgr.hxx (7744B)
1 /* ***** BEGIN LICENSE BLOCK ***** 2 * Version: MPL 1.1/GPL 2.0/LGPL 2.1 3 * 4 * Copyright (C) 2002-2022 Németh László 5 * 6 * The contents of this file are subject to the Mozilla Public License Version 7 * 1.1 (the "License"); you may not use this file except in compliance with 8 * the License. You may obtain a copy of the License at 9 * http://www.mozilla.org/MPL/ 10 * 11 * Software distributed under the License is distributed on an "AS IS" basis, 12 * WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License 13 * for the specific language governing rights and limitations under the 14 * License. 15 * 16 * Hunspell is based on MySpell which is Copyright (C) 2002 Kevin Hendricks. 17 * 18 * Contributor(s): David Einstein, Davide Prina, Giuseppe Modugno, 19 * Gianluca Turconi, Simon Brouwer, Noll János, Bíró Árpád, 20 * Goldman Eleonóra, Sarlós Tamás, Bencsáth Boldizsár, Halácsy Péter, 21 * Dvornik László, Gefferth András, Nagy Viktor, Varga Dániel, Chris Halls, 22 * Rene Engelhard, Bram Moolenaar, Dafydd Jones, Harri Pitkänen 23 * 24 * Alternatively, the contents of this file may be used under the terms of 25 * either the GNU General Public License Version 2 or later (the "GPL"), or 26 * the GNU Lesser General Public License Version 2.1 or later (the "LGPL"), 27 * in which case the provisions of the GPL or the LGPL are applicable instead 28 * of those above. If you wish to allow use of your version of this file only 29 * under the terms of either the GPL or the LGPL, and not to allow others to 30 * use your version of this file under the terms of the MPL, indicate your 31 * decision by deleting the provisions above and replace them with the notice 32 * and other provisions required by the GPL or the LGPL. If you do not delete 33 * the provisions above, a recipient may use your version of this file under 34 * the terms of any one of the MPL, the GPL or the LGPL. 35 * 36 * ***** END LICENSE BLOCK ***** */ 37 /* 38 * Copyright 2002 Kevin B. Hendricks, Stratford, Ontario, Canada 39 * And Contributors. All rights reserved. 40 * 41 * Redistribution and use in source and binary forms, with or without 42 * modification, are permitted provided that the following conditions 43 * are met: 44 * 45 * 1. Redistributions of source code must retain the above copyright 46 * notice, this list of conditions and the following disclaimer. 47 * 48 * 2. Redistributions in binary form must reproduce the above copyright 49 * notice, this list of conditions and the following disclaimer in the 50 * documentation and/or other materials provided with the distribution. 51 * 52 * 3. All modifications to the source code must be clearly marked as 53 * such. Binary redistributions based on modified source code 54 * must be clearly marked as modified versions in the documentation 55 * and/or other materials provided with the distribution. 56 * 57 * THIS SOFTWARE IS PROVIDED BY KEVIN B. HENDRICKS AND CONTRIBUTORS 58 * ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT 59 * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS 60 * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL 61 * KEVIN B. HENDRICKS OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, 62 * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, 63 * BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; 64 * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) 65 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 66 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY 67 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF 68 * SUCH DAMAGE. 69 */ 70 71 #ifndef SUGGESTMGR_HXX_ 72 #define SUGGESTMGR_HXX_ 73 74 #define MAX_ROOTS 100 75 #define MAX_WORDS 100 76 #define MAX_GUESS 200 77 #define MAXNGRAMSUGS 4 78 #define MAXPHONSUGS 2 79 #define MAXCOMPOUNDSUGS 3 80 81 #define NGRAM_LONGER_WORSE (1 << 0) 82 #define NGRAM_ANY_MISMATCH (1 << 1) 83 #define NGRAM_LOWERING (1 << 2) 84 #define NGRAM_WEIGHTED (1 << 3) 85 86 #include "atypes.hxx" 87 #include "affixmgr.hxx" 88 #include "hashmgr.hxx" 89 #include "langnum.hxx" 90 91 enum { LCS_UP, LCS_LEFT, LCS_UPLEFT }; 92 93 class SuggestMgr { 94 private: 95 SuggestMgr(const SuggestMgr&); 96 SuggestMgr& operator=(const SuggestMgr&); 97 98 private: 99 char* ckey; 100 size_t ckeyl; 101 std::vector<w_char> ckey_utf; 102 103 char* ctry; 104 size_t ctryl; 105 std::vector<w_char> ctry_utf; 106 bool lang_with_dash_usage; 107 108 AffixMgr* pAMgr; 109 unsigned int maxSug; 110 struct cs_info* csconv; 111 int utf8; 112 int langnum; 113 int nosplitsugs; 114 int maxngramsugs; 115 int maxcpdsugs; 116 int complexprefixes; 117 118 public: 119 SuggestMgr(const char* tryme, unsigned int maxn, AffixMgr* aptr); 120 ~SuggestMgr(); 121 122 bool suggest(std::vector<std::string>& slst, const char* word, int* onlycmpdsug); 123 void ngsuggest(std::vector<std::string>& slst, const char* word, const std::vector<HashMgr*>& rHMgr, int captype); 124 125 std::string suggest_morph(const std::string& word); 126 std::string suggest_gen(const std::vector<std::string>& pl, const std::string& pattern); 127 128 private: 129 void testsug(std::vector<std::string>& wlst, 130 const std::string& candidate, 131 int cpdsuggest, 132 int* timer, 133 clock_t* timelimit); 134 int checkword(const std::string& word, int, int*, clock_t*); 135 int check_forbidden(const char*, int); 136 137 void capchars(std::vector<std::string>&, const char*, int); 138 int replchars(std::vector<std::string>&, const char*, int); 139 int doubletwochars(std::vector<std::string>&, const char*, int); 140 int forgotchar(std::vector<std::string>&, const char*, int); 141 int swapchar(std::vector<std::string>&, const char*, int); 142 int longswapchar(std::vector<std::string>&, const char*, int); 143 int movechar(std::vector<std::string>&, const char*, int); 144 int extrachar(std::vector<std::string>&, const char*, int); 145 int badcharkey(std::vector<std::string>&, const char*, int); 146 int badchar(std::vector<std::string>&, const char*, int); 147 bool twowords(std::vector<std::string>&, const char*, int, bool); 148 149 void capchars_utf(std::vector<std::string>&, const w_char*, int wl, int); 150 int doubletwochars_utf(std::vector<std::string>&, const w_char*, int wl, int); 151 int forgotchar_utf(std::vector<std::string>&, const w_char*, int wl, int); 152 int extrachar_utf(std::vector<std::string>&, const w_char*, int wl, int); 153 int badcharkey_utf(std::vector<std::string>&, const w_char*, int wl, int); 154 int badchar_utf(std::vector<std::string>&, const w_char*, int wl, int); 155 int swapchar_utf(std::vector<std::string>&, const w_char*, int wl, int); 156 int longswapchar_utf(std::vector<std::string>&, const w_char*, int, int); 157 int movechar_utf(std::vector<std::string>&, const w_char*, int, int); 158 159 int mapchars(std::vector<std::string>&, const char*, int); 160 int map_related(const char*, 161 std::string&, 162 int, 163 std::vector<std::string>& wlst, 164 int, 165 const std::vector<mapentry>&, 166 int*, 167 clock_t*); 168 int ngram(int n, const std::vector<w_char>& su1, 169 const std::vector<w_char>& su2, int opt); 170 int ngram(int n, const std::string& s1, const std::string& s2, int opt); 171 int mystrlen(const char* word); 172 int leftcommonsubstring(const std::vector<w_char>& su1, 173 const std::vector<w_char>& su2); 174 int leftcommonsubstring(const char* s1, const char* s2); 175 int commoncharacterpositions(const char* s1, const char* s2, int* is_swap); 176 void bubblesort(char** rwd, char** rwd2, int* rsc, int n); 177 void lcs(const char* s, const char* s2, int* l1, int* l2, char** result); 178 int lcslen(const char* s, const char* s2); 179 int lcslen(const std::string& s, const std::string& s2); 180 std::string suggest_hentry_gen(hentry* rv, const char* pattern); 181 }; 182 183 #endif