1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
|
// Copyright (c) 2014-2023, The Monero Project
//
// All rights reserved.
//
// Redistribution and use in source and binary forms, with or without modification, are
// permitted provided that the following conditions are met:
//
// 1. Redistributions of source code must retain the above copyright notice, this list of
// conditions and the following disclaimer.
//
// 2. Redistributions in binary form must reproduce the above copyright notice, this list
// of conditions and the following disclaimer in the documentation and/or other
// materials provided with the distribution.
//
// 3. Neither the name of the copyright holder nor the names of its contributors may be
// used to endorse or promote products derived from this software without specific
// prior written permission.
//
// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND ANY
// EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
// MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL
// THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
// PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
// INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
// STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF
// THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
/*!
* \file language_base.h
*
* \brief Language Base class for Polymorphism.
*/
#ifndef LANGUAGE_BASE_H
#define LANGUAGE_BASE_H
#include <vector>
#include <unordered_map>
#include <string>
#include <boost/algorithm/string.hpp>
#include "misc_log_ex.h"
#include "fnv1.h"
#include "common/utf8.h"
/*!
* \namespace Language
* \brief Mnemonic language related namespace.
*/
namespace Language
{
/*!
* \brief Returns a string made of (at most) the first count characters in s.
* Assumes well formedness. No check is made for this.
* \param s The string from which to return the first count characters.
* \param count How many characters to return.
* \return A string consisting of the first count characters in s.
*/
template<typename T>
inline T utf8prefix(const T &s, size_t count)
{
T prefix = "";
size_t avail = s.size();
const char *ptr = s.data();
while (count-- && avail--)
{
prefix += *ptr++;
while (avail && ((*ptr) & 0xc0) == 0x80)
{
prefix += *ptr++;
--avail;
}
}
return prefix;
}
struct WordHash
{
std::size_t operator()(const epee::wipeable_string &s) const
{
const epee::wipeable_string sc = tools::utf8canonical(s, [](wint_t c) -> wint_t { return std::towlower(c); });
return epee::fnv::FNV1a(sc.data(), sc.size());
}
};
struct WordEqual
{
bool operator()(const epee::wipeable_string &s0, const epee::wipeable_string &s1) const
{
const epee::wipeable_string s0c = tools::utf8canonical(s0, [](wint_t c) -> wint_t { return std::towlower(c); });
const epee::wipeable_string s1c = tools::utf8canonical(s1, [](wint_t c) -> wint_t { return std::towlower(c); });
return s0c == s1c;
}
};
/*!
* \class Base
* \brief A base language class which all languages have to inherit from for
* Polymorphism.
*/
class Base
{
protected:
enum {
ALLOW_SHORT_WORDS = 1<<0,
ALLOW_DUPLICATE_PREFIXES = 1<<1,
};
enum {
NWORDS = 1626
};
std::vector<std::string> word_list; /*!< A pointer to the array of words */
std::unordered_map<epee::wipeable_string, uint32_t, WordHash, WordEqual> word_map; /*!< hash table to find word's index */
std::unordered_map<epee::wipeable_string, uint32_t, WordHash, WordEqual> trimmed_word_map; /*!< hash table to find word's trimmed index */
std::string language_name; /*!< Name of language */
std::string english_language_name; /*!< Name of language */
uint32_t unique_prefix_length; /*!< Number of unique starting characters to trim the wordlist to when matching */
/*!
* \brief Populates the word maps after the list is ready.
*/
void populate_maps(uint32_t flags = 0)
{
int ii;
std::vector<std::string>::const_iterator it;
if (word_list.size () != NWORDS)
throw std::runtime_error("Wrong word list length for " + language_name);
for (it = word_list.begin(), ii = 0; it != word_list.end(); it++, ii++)
{
word_map[*it] = ii;
if ((*it).size() < unique_prefix_length)
{
if (flags & ALLOW_SHORT_WORDS)
MINFO(language_name << " word '" << *it << "' is shorter than its prefix length, " << unique_prefix_length);
else
throw std::runtime_error("Too short word in " + language_name + " word list: " + *it);
}
epee::wipeable_string trimmed;
if (it->length() > unique_prefix_length)
{
trimmed = utf8prefix(*it, unique_prefix_length);
}
else
{
trimmed = *it;
}
if (trimmed_word_map.find(trimmed) != trimmed_word_map.end())
{
if (flags & ALLOW_DUPLICATE_PREFIXES)
MWARNING("Duplicate prefix in " << language_name << " word list: " << std::string(trimmed.data(), trimmed.size()));
else
throw std::runtime_error("Duplicate prefix in " + language_name + " word list: " + std::string(trimmed.data(), trimmed.size()));
}
trimmed_word_map[trimmed] = ii;
}
}
public:
Base(const char *language_name, const char *english_language_name, const std::vector<std::string> &words, uint32_t prefix_length):
word_list(words),
unique_prefix_length(prefix_length),
language_name(language_name),
english_language_name(english_language_name)
{
}
virtual ~Base()
{
}
void set_words(const char * const words[])
{
word_list.resize(NWORDS);
for (size_t i = 0; i < NWORDS; ++i)
word_list[i] = words[i];
}
/*!
* \brief Returns a pointer to the word list.
* \return A pointer to the word list.
*/
const std::vector<std::string>& get_word_list() const
{
return word_list;
}
/*!
* \brief Returns a pointer to the word map.
* \return A pointer to the word map.
*/
const std::unordered_map<epee::wipeable_string, uint32_t, WordHash, WordEqual>& get_word_map() const
{
return word_map;
}
/*!
* \brief Returns a pointer to the trimmed word map.
* \return A pointer to the trimmed word map.
*/
const std::unordered_map<epee::wipeable_string, uint32_t, WordHash, WordEqual>& get_trimmed_word_map() const
{
return trimmed_word_map;
}
/*!
* \brief Returns the name of the language.
* \return Name of the language.
*/
const std::string &get_language_name() const
{
return language_name;
}
/*!
* \brief Returns the name of the language in English.
* \return Name of the language.
*/
const std::string &get_english_language_name() const
{
return english_language_name;
}
/*!
* \brief Returns the number of unique starting characters to be used for matching.
* \return Number of unique starting characters.
*/
uint32_t get_unique_prefix_length() const
{
return unique_prefix_length;
}
};
}
#endif
|
