1 /* ***** BEGIN LICENSE BLOCK *****
2 * Version: MPL 1.1/GPL 2.0/LGPL 2.1
3 *
4 * Copyright (C) 2002-2017 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 #include <stdlib.h>
72 #include <string.h>
73 #include <stdio.h>
74 #include <limits>
75
76 #include "replist.hxx"
77 #include "csutil.hxx"
78
RepList(int n)79 RepList::RepList(int n) {
80 dat = (replentry**)malloc(sizeof(replentry*) * n);
81 if (dat == 0)
82 size = 0;
83 else
84 size = n;
85 pos = 0;
86 }
87
~RepList()88 RepList::~RepList() {
89 for (int i = 0; i < pos; i++) {
90 delete dat[i];
91 }
92 free(dat);
93 }
94
item(int n)95 replentry* RepList::item(int n) {
96 return dat[n];
97 }
98
find(const char * word)99 int RepList::find(const char* word) {
100 int p1 = 0;
101 int p2 = pos - 1;
102 int ret = -1;
103 while (p1 <= p2) {
104 int m = ((unsigned)p1 + (unsigned)p2) >> 1;
105 int c = strncmp(word, dat[m]->pattern.c_str(), dat[m]->pattern.size());
106 if (c < 0)
107 p2 = m - 1;
108 else if (c > 0)
109 p1 = m + 1;
110 else { // scan in the right half for a longer match
111 ret = m;
112 p1 = m + 1;
113 }
114 }
115 return ret;
116 }
117
replace(const char * word,int ind,bool atstart)118 std::string RepList::replace(const char* word, int ind, bool atstart) {
119 int type = atstart ? 1 : 0;
120 if (ind < 0)
121 return std::string();
122 if (strlen(word) == dat[ind]->pattern.size())
123 type = atstart ? 3 : 2;
124 while (type && dat[ind]->outstrings[type].empty())
125 type = (type == 2 && !atstart) ? 0 : type - 1;
126 return dat[ind]->outstrings[type];
127 }
128
add(const std::string & in_pat1,const std::string & pat2)129 int RepList::add(const std::string& in_pat1, const std::string& pat2) {
130 if (pos >= size || in_pat1.empty() || pat2.empty()) {
131 return 1;
132 }
133 // analyse word context
134 int type = 0;
135 std::string pat1(in_pat1);
136 if (pat1[0] == '_') {
137 pat1.erase(0, 1);
138 type = 1;
139 }
140 if (!pat1.empty() && pat1[pat1.size() - 1] == '_') {
141 type = type + 2;
142 pat1.erase(pat1.size() - 1);
143 }
144 mystrrep(pat1, "_", " ");
145
146 // find existing entry
147 int m = find(pat1.c_str());
148 if (m >= 0 && dat[m]->pattern == pat1) {
149 // since already used
150 dat[m]->outstrings[type] = pat2;
151 mystrrep(dat[m]->outstrings[type], "_", " ");
152 return 0;
153 }
154
155 // make a new entry if none exists
156 replentry* r = new replentry;
157 if (r == NULL)
158 return 1;
159 r->pattern = pat1;
160 r->outstrings[type] = pat2;
161 mystrrep(r->outstrings[type], "_", " ");
162 dat[pos++] = r;
163 // sort to the right place in the list
164 int i;
165 for (i = pos - 1; i > 0; i--) {
166 if (strcmp(r->pattern.c_str(), dat[i - 1]->pattern.c_str()) < 0) {
167 dat[i] = dat[i - 1];
168 } else
169 break;
170 }
171 dat[i] = r;
172 return 0;
173 }
174
conv(const std::string & in_word,std::string & dest)175 bool RepList::conv(const std::string& in_word, std::string& dest) {
176 dest.clear();
177
178 size_t wordlen = in_word.size();
179 const char* word = in_word.c_str();
180
181 bool change = false;
182 for (size_t i = 0; i < wordlen; ++i) {
183 int n = find(word + i);
184 std::string l = replace(word + i, n, i == 0);
185 if (!l.empty()) {
186 dest.append(l);
187 i += dat[n]->pattern.size() - 1;
188 change = true;
189 } else {
190 dest.push_back(word[i]);
191 }
192 }
193
194 return change;
195 }
196
197