2017-02-21 18:38:18 +01:00
|
|
|
// Copyright (c) 2014-2017, The Monero Project
|
2014-10-05 12:42:40 +02:00
|
|
|
//
|
|
|
|
// 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.
|
|
|
|
|
2014-10-02 18:05:27 +02:00
|
|
|
/*!
|
|
|
|
* \file language_base.h
|
|
|
|
*
|
|
|
|
* \brief Language Base class for Polymorphism.
|
|
|
|
*/
|
|
|
|
|
2014-10-02 17:44:29 +02:00
|
|
|
#ifndef LANGUAGE_BASE_H
|
|
|
|
#define LANGUAGE_BASE_H
|
|
|
|
|
|
|
|
#include <vector>
|
|
|
|
#include <unordered_map>
|
|
|
|
#include <string>
|
|
|
|
|
2014-10-02 18:05:27 +02:00
|
|
|
/*!
|
|
|
|
* \namespace Language
|
|
|
|
* \brief Mnemonic language related namespace.
|
|
|
|
*/
|
2014-10-02 17:44:29 +02:00
|
|
|
namespace Language
|
|
|
|
{
|
2015-06-21 12:28:16 +02:00
|
|
|
/*!
|
|
|
|
* \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.
|
|
|
|
*/
|
2015-06-23 04:13:00 +02:00
|
|
|
inline std::string utf8prefix(const std::string &s, size_t count)
|
2015-06-21 12:28:16 +02:00
|
|
|
{
|
|
|
|
std::string prefix = "";
|
|
|
|
const char *ptr = s.c_str();
|
|
|
|
while (count-- && *ptr)
|
|
|
|
{
|
|
|
|
prefix += *ptr++;
|
|
|
|
while (((*ptr) & 0xc0) == 0x80)
|
|
|
|
prefix += *ptr++;
|
|
|
|
}
|
|
|
|
return prefix;
|
|
|
|
}
|
|
|
|
|
2014-10-03 12:55:44 +02:00
|
|
|
/*!
|
|
|
|
* \class Base
|
|
|
|
* \brief A base language class which all languages have to inherit from for
|
|
|
|
* Polymorphism.
|
|
|
|
*/
|
|
|
|
class Base
|
|
|
|
{
|
|
|
|
protected:
|
|
|
|
std::vector<std::string> *word_list; /*!< A pointer to the array of words */
|
|
|
|
std::unordered_map<std::string, uint32_t> *word_map; /*!< hash table to find word's index */
|
|
|
|
std::unordered_map<std::string, uint32_t> *trimmed_word_map; /*!< hash table to find word's trimmed index */
|
|
|
|
std::string language_name; /*!< Name of language */
|
2014-10-07 09:19:36 +02:00
|
|
|
uint32_t unique_prefix_length; /*!< Number of unique starting characters to trim the wordlist to when matching */
|
2014-10-03 12:55:44 +02:00
|
|
|
/*!
|
|
|
|
* \brief Populates the word maps after the list is ready.
|
|
|
|
*/
|
|
|
|
void populate_maps()
|
|
|
|
{
|
|
|
|
int ii;
|
|
|
|
std::vector<std::string>::iterator it;
|
|
|
|
for (it = word_list->begin(), ii = 0; it != word_list->end(); it++, ii++)
|
|
|
|
{
|
|
|
|
(*word_map)[*it] = ii;
|
|
|
|
if (it->length() > unique_prefix_length)
|
|
|
|
{
|
2015-06-21 12:28:16 +02:00
|
|
|
(*trimmed_word_map)[utf8prefix(*it, unique_prefix_length)] = ii;
|
2014-10-03 12:55:44 +02:00
|
|
|
}
|
|
|
|
else
|
|
|
|
{
|
|
|
|
(*trimmed_word_map)[*it] = ii;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
public:
|
|
|
|
Base()
|
|
|
|
{
|
|
|
|
word_list = new std::vector<std::string>;
|
|
|
|
word_map = new std::unordered_map<std::string, uint32_t>;
|
|
|
|
trimmed_word_map = new std::unordered_map<std::string, uint32_t>;
|
2014-10-07 09:19:36 +02:00
|
|
|
unique_prefix_length = 4;
|
2014-10-03 12:55:44 +02:00
|
|
|
}
|
2016-12-10 13:39:25 +01:00
|
|
|
virtual ~Base()
|
|
|
|
{
|
|
|
|
delete word_list;
|
|
|
|
delete word_map;
|
|
|
|
delete trimmed_word_map;
|
|
|
|
}
|
2014-10-03 12:55:44 +02:00
|
|
|
/*!
|
|
|
|
* \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<std::string, uint32_t>& 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<std::string, uint32_t>& get_trimmed_word_map() const
|
|
|
|
{
|
|
|
|
return *trimmed_word_map;
|
|
|
|
}
|
|
|
|
/*!
|
|
|
|
* \brief Returns the name of the language.
|
|
|
|
* \return Name of the language.
|
|
|
|
*/
|
|
|
|
std::string get_language_name() const
|
|
|
|
{
|
|
|
|
return language_name;
|
|
|
|
}
|
2014-10-05 12:42:40 +02:00
|
|
|
/*!
|
|
|
|
* \brief Returns the number of unique starting characters to be used for matching.
|
|
|
|
* \return Number of unique starting characters.
|
|
|
|
*/
|
2014-10-07 09:19:36 +02:00
|
|
|
uint32_t get_unique_prefix_length() const
|
2014-10-05 12:42:40 +02:00
|
|
|
{
|
2014-10-07 09:19:36 +02:00
|
|
|
return unique_prefix_length;
|
2014-10-05 12:42:40 +02:00
|
|
|
}
|
2014-10-03 12:55:44 +02:00
|
|
|
};
|
2014-10-02 17:44:29 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
#endif
|