libcruft-util/string.cpp

197 lines
5.3 KiB
C++
Raw Normal View History

2011-08-12 00:25:59 +10:00
/*
2015-04-13 18:05:28 +10:00
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
2011-08-12 00:25:59 +10:00
*
2015-04-13 18:05:28 +10:00
* http://www.apache.org/licenses/LICENSE-2.0
2011-08-12 00:25:59 +10:00
*
2015-04-13 18:05:28 +10:00
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
2011-08-12 00:25:59 +10:00
*
* Copyright 2011-2017 Danny Robson <danny@nerdcruft.net>
2011-08-12 00:25:59 +10:00
*/
#include "./string.hpp"
2011-08-12 00:25:59 +10:00
#include "./debug.hpp"
#include <cstring>
#include <codecvt>
#include <locale>
2013-08-05 16:41:20 +10:00
2016-03-17 18:13:19 +11:00
using util::tokeniser;
///////////////////////////////////////////////////////////////////////////////
std::string
util::to_utf8 (const wchar_t *src)
{
using convert_t = std::codecvt_utf8<wchar_t>;
std::wstring_convert<convert_t,wchar_t> converter;
return converter.to_bytes (src);
}
//-----------------------------------------------------------------------------
std::string
util::to_utf8 (const std::wstring &src)
{
return to_utf8 (src.c_str ());
}
2016-03-17 18:13:19 +11:00
///////////////////////////////////////////////////////////////////////////////
2011-08-12 00:25:59 +10:00
// TODO: Horribly inefficient, but God help you if you're relying on this
// being efficient in the first place.
bool
strbegins (const char *restrict str,
const char *restrict prefix) {
return 0 == strncmp (prefix, str, strlen (prefix));
}
2016-03-17 18:13:19 +11:00
///////////////////////////////////////////////////////////////////////////////
2016-03-18 11:08:12 +11:00
template <typename Iterator>
tokeniser<Iterator>::tokeniser (Iterator _first,
Iterator _last,
value_type _separator):
m_range (_first, _last),
2016-03-17 18:13:19 +11:00
m_separator (_separator)
{ }
2016-03-18 11:08:12 +11:00
///////////////////////////////////////////////////////////////////////////////
template <typename Iterator>
typename tokeniser<Iterator>::iterator
tokeniser<Iterator>::cbegin (void) const
2016-03-17 18:13:19 +11:00
{
return iterator (
2016-03-18 11:08:12 +11:00
m_range,
2016-03-17 18:13:19 +11:00
m_separator
);
}
//-----------------------------------------------------------------------------
2016-03-18 11:08:12 +11:00
template <typename Iterator>
typename tokeniser<Iterator>::iterator
tokeniser<Iterator>::cend (void) const
2016-03-17 18:13:19 +11:00
{
return iterator (
2016-03-18 11:08:12 +11:00
{m_range.cend (), m_range.cend ()},
2016-03-17 18:13:19 +11:00
m_separator
);
}
2016-03-21 14:20:04 +11:00
//-----------------------------------------------------------------------------
template <typename Iterator>
typename tokeniser<Iterator>::iterator
tokeniser<Iterator>::begin (void) const
{
return cbegin ();
}
//-----------------------------------------------------------------------------
template <typename Iterator>
typename tokeniser<Iterator>::iterator
tokeniser<Iterator>::end (void) const
{
return cend ();
}
2016-03-17 18:13:19 +11:00
///////////////////////////////////////////////////////////////////////////////
2016-03-18 11:08:12 +11:00
template <typename Iterator>
tokeniser<Iterator>::iterator::iterator (range_type _range, value_type _separator):
2016-03-17 18:13:19 +11:00
m_separator (_separator),
m_range (_range.cbegin (),
std::find (_range.cbegin (),
_range.cend (),
_separator)),
m_end (_range.cend ())
{ }
//-----------------------------------------------------------------------------
2016-03-18 11:08:12 +11:00
template <typename Iterator>
typename tokeniser<Iterator>::iterator
tokeniser<Iterator>::iterator::operator++ (int)
2016-03-17 18:13:19 +11:00
{
iterator res(*this);
++*this;
return res;
}
//-----------------------------------------------------------------------------
2016-03-18 11:08:12 +11:00
template <typename Iterator>
typename tokeniser<Iterator>::iterator&
tokeniser<Iterator>::iterator::operator++ (void)&
2016-03-17 18:13:19 +11:00
{
auto newend = m_range.cend ();
if (newend != m_end) {
CHECK_EQ (*m_range.cend (), m_separator);
newend++;
}
m_range = {
newend,
std::find (newend, m_end, m_separator)
};
return *this;
}
//-----------------------------------------------------------------------------
2016-03-18 11:08:12 +11:00
template <typename Iterator>
typename tokeniser<Iterator>::range_type
tokeniser<Iterator>::iterator::operator* (void) const
2016-03-17 18:13:19 +11:00
{
return m_range;
}
//-----------------------------------------------------------------------------
2016-03-18 11:08:12 +11:00
template <typename Iterator>
2016-03-17 18:13:19 +11:00
bool
2016-03-18 11:08:12 +11:00
tokeniser<Iterator>::iterator::operator== (const iterator &rhs) const
2016-03-17 18:13:19 +11:00
{
return m_range == rhs.m_range && m_separator == rhs.m_separator;
}
2016-03-18 11:08:12 +11:00
//-----------------------------------------------------------------------------
template <typename Iterator>
bool
tokeniser<Iterator>::iterator::operator!= (const iterator &rhs) const
{
return !(*this == rhs);
}
///////////////////////////////////////////////////////////////////////////////
tokeniser<std::string::const_iterator>
util::make_tokeniser (const std::string &value, std::string::value_type separator)
{
return tokeniser<std::string::const_iterator> (value.cbegin (), value.cend (), separator);
}
//-----------------------------------------------------------------------------
tokeniser<const char*>
util::make_tokeniser (const char *str, char separator)
{
return tokeniser<const char*> (str, str + strlen (str), separator);
}
///////////////////////////////////////////////////////////////////////////////
template struct util::tokeniser<std::string::const_iterator>;
template struct util::tokeniser<const char*>;