naming.hpp

Go to the documentation of this file.

//This file is part of Bertini 2.
//
//bertini2/naming.hpp is free software: you can redistribute it and/or modify
//it under the terms of the GNU General Public License as published by
//the Free Software Foundation, either version 3 of the License, or
//(at your option) any later version.
//
//bertini2/naming.hpp is distributed in the hope that it will be useful,
//but WITHOUT ANY WARRANTY; without even the implied warranty of
//MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
//GNU General Public License for more details.
//
//You should have received a copy of the GNU General Public License
//along with bertini2/naming.hpp.  If not, see <http://www.gnu.org/licenses/>.
//
// Copyright(C) Bertini2 Development Team
//
// See <http://www.gnu.org/licenses/> for a copy of the license,
// as well as COPYING.  Bertini2 is provided with permitted
// additional terms in the b2/licenses/ directory.
 

 
#pragma once
 
#include <string>
#include <stdexcept>
 
#include <boost/regex/pending/unicode_iterator.hpp>
#include <boost/spirit/home/support/char_encoding/unicode.hpp>
 
namespace bertini {
 
namespace detail {

inline bool IsEmojiBase(char32_t cp)
{
    return (cp >= 0x1F000 && cp <= 0x1FAFF)   // emoticons, pictographs, transport, supplemental & extended-A (incl. skin tones, regional indicators)
        || (cp >= 0x2600  && cp <= 0x27BF)    // miscellaneous symbols + dingbats (☀ ❤ ✨ ✅ ...)
        || (cp >= 0x2B00  && cp <= 0x2BFF);   // miscellaneous symbols and arrows (⭐ ⬅ ...)
}

inline bool IsEmojiGlue(char32_t cp)
{
    return cp == 0x200D              // ZERO WIDTH JOINER (👩‍👩‍👧)
        || cp == 0xFE0E || cp == 0xFE0F  // variation selectors 15 / 16 (❤️)
        || cp == 0x20E3;            // combining enclosing keycap
    // skin-tone modifiers (U+1F3FB..FF) and regional indicators (U+1F1E6..FF) are
    // already covered by IsEmojiBase, so they continue a name via that predicate.
}
 
} // namespace detail

inline bool IsIdentStart(char32_t cp)
{
    return boost::spirit::char_encoding::unicode::isalpha(cp)
        || detail::IsEmojiBase(cp);
}

inline bool IsIdentCont(char32_t cp)
{
    return boost::spirit::char_encoding::unicode::isalnum(cp)
        || cp == U'[' || cp == U']' || cp == U'_'
        || detail::IsEmojiBase(cp) || detail::IsEmojiGlue(cp);
}

inline bool IsValidVariableName(std::string const& s)
{
    if (s.empty())
        return false;
    try
    {
        boost::u8_to_u32_iterator<std::string::const_iterator> it(s.begin(), s.begin(), s.end());
        boost::u8_to_u32_iterator<std::string::const_iterator> end(s.end(), s.begin(), s.end());
        if (it == end || !IsIdentStart(*it))
            return false;
        for (++it; it != end; ++it)
            if (!IsIdentCont(*it))
                return false;
        return true;
    }
    catch (...)
    {
        return false; // malformed UTF-8
    }
}

inline void ThrowIfInvalidVariableName(std::string const& s)
{
    if (!IsValidVariableName(s))
        throw std::runtime_error(
            "invalid variable name \"" + s + "\": a name must be a nonempty identifier -- "
            "it starts with a letter (ASCII or Unicode, e.g. x or \xCE\xA9) and continues with "
            "letters, digits, or [ ] _ .  Expressions, operators, whitespace, and leading "
            "digits are not allowed.");
}
 
} // namespace bertini