| 1 | // SuperTux |
| 2 | // Copyright (C) 2009 Ingo Ruhnke <grumbel@gmail.com> |
| 3 | // |
| 4 | // This program is free software: you can redistribute it and/or modify |
| 5 | // it under the terms of the GNU General Public License as published by |
| 6 | // the Free Software Foundation, either version 3 of the License, or |
| 7 | // (at your option) any later version. |
| 8 | // |
| 9 | // This program is distributed in the hope that it will be useful, |
| 10 | // but WITHOUT ANY WARRANTY; without even the implied warranty of |
| 11 | // MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
| 12 | // GNU General Public License for more details. |
| 13 | // |
| 14 | // You should have received a copy of the GNU General Public License |
| 15 | // along with this program. If not, see <http://www.gnu.org/licenses/>. |
| 16 | |
| 17 | #include "util/utf8_iterator.hpp" |
| 18 | |
| 19 | #include <stdexcept> |
| 20 | |
| 21 | #include "util/log.hpp" |
| 22 | |
| 23 | namespace { |
| 24 | |
| 25 | bool has_multibyte_mark(unsigned char c); |
| 26 | uint32_t decode_utf8(const std::string& text, size_t& p); |
| 27 | |
| 28 | /** |
| 29 | * returns true if this byte matches a bitmask of 10xx.xxxx, i.e. it is the 2nd, 3rd or 4th byte of a multibyte utf8 string |
| 30 | */ |
| 31 | bool has_multibyte_mark(unsigned char c) { |
| 32 | return ((c & 0300) == 0200); |
| 33 | } |
| 34 | |
| 35 | /** |
| 36 | * gets unicode character at byte position @a p of UTF-8 encoded @a |
| 37 | * text, then advances @a p to the next character. |
| 38 | * |
| 39 | * @throws std::runtime_error if decoding fails. |
| 40 | * See unicode standard section 3.10 table 3-5 and 3-6 for details. |
| 41 | */ |
| 42 | uint32_t decode_utf8(const std::string& text, size_t& p) |
| 43 | { |
| 44 | uint32_t c1 = static_cast<unsigned char>(text[p+0]); |
| 45 | |
| 46 | if (has_multibyte_mark(static_cast<unsigned char>(c1))) { |
| 47 | throw std::runtime_error("Malformed utf-8 sequence" ); |
| 48 | } |
| 49 | |
| 50 | if ((c1 & 0200) == 0000) { |
| 51 | // 0xxx.xxxx: 1 byte sequence |
| 52 | p+=1; |
| 53 | return c1; |
| 54 | } |
| 55 | else if ((c1 & 0340) == 0300) { |
| 56 | // 110x.xxxx: 2 byte sequence |
| 57 | if (p+1 >= text.size()) throw std::range_error("Malformed utf-8 sequence" ); |
| 58 | uint32_t c2 = static_cast<unsigned char>(text[p+1]); |
| 59 | if (!has_multibyte_mark(static_cast<unsigned char>(c2))) throw std::runtime_error("Malformed utf-8 sequence" ); |
| 60 | p+=2; |
| 61 | return (c1 & 0037) << 6 | (c2 & 0077); |
| 62 | } |
| 63 | else if ((c1 & 0360) == 0340) { |
| 64 | // 1110.xxxx: 3 byte sequence |
| 65 | if (p+2 >= text.size()) throw std::range_error("Malformed utf-8 sequence" ); |
| 66 | uint32_t c2 = static_cast<unsigned char>(text[p+1]); |
| 67 | uint32_t c3 = static_cast<unsigned char>(text[p+2]); |
| 68 | if (!has_multibyte_mark(static_cast<unsigned char>(c2))) throw std::runtime_error("Malformed utf-8 sequence" ); |
| 69 | if (!has_multibyte_mark(static_cast<unsigned char>(c3))) throw std::runtime_error("Malformed utf-8 sequence" ); |
| 70 | p+=3; |
| 71 | return (c1 & 0017) << 12 | (c2 & 0077) << 6 | (c3 & 0077); |
| 72 | } |
| 73 | else if ((c1 & 0370) == 0360) { |
| 74 | // 1111.0xxx: 4 byte sequence |
| 75 | if (p+3 >= text.size()) throw std::range_error("Malformed utf-8 sequence" ); |
| 76 | uint32_t c2 = static_cast<unsigned char>(text[p+1]); |
| 77 | uint32_t c3 = static_cast<unsigned char>(text[p+2]); |
| 78 | uint32_t c4 = static_cast<unsigned char>(text[p+4]); |
| 79 | if (!has_multibyte_mark(static_cast<unsigned char>(c2))) throw std::runtime_error("Malformed utf-8 sequence" ); |
| 80 | if (!has_multibyte_mark(static_cast<unsigned char>(c3))) throw std::runtime_error("Malformed utf-8 sequence" ); |
| 81 | if (!has_multibyte_mark(static_cast<unsigned char>(c4))) throw std::runtime_error("Malformed utf-8 sequence" ); |
| 82 | p+=4; |
| 83 | return (c1 & 0007) << 18 | (c2 & 0077) << 12 | (c3 & 0077) << 6 | (c4 & 0077); |
| 84 | } |
| 85 | throw std::runtime_error("Malformed utf-8 sequence" ); |
| 86 | } |
| 87 | |
| 88 | } // namespace |
| 89 | |
| 90 | |
| 91 | UTF8Iterator::UTF8Iterator(const std::string& text_) : |
| 92 | text(text_), |
| 93 | pos(0), |
| 94 | chr() |
| 95 | { |
| 96 | try { |
| 97 | chr = decode_utf8(text, pos); |
| 98 | } catch (std::exception&) { |
| 99 | log_debug << "Malformed utf-8 sequence beginning with " << *(reinterpret_cast<const uint32_t*>(text.c_str() + pos)) << " found " << std::endl; |
| 100 | chr = 0; |
| 101 | } |
| 102 | } |
| 103 | |
| 104 | bool |
| 105 | UTF8Iterator::done() const |
| 106 | { |
| 107 | return pos > text.size(); |
| 108 | } |
| 109 | |
| 110 | UTF8Iterator& |
| 111 | UTF8Iterator::operator++() { |
| 112 | try { |
| 113 | chr = decode_utf8(text, pos); |
| 114 | } catch (std::exception&) { |
| 115 | log_debug << "Malformed utf-8 sequence beginning with " << *(reinterpret_cast<const uint32_t*>(text.c_str() + pos)) << " found " << std::endl; |
| 116 | chr = 0; |
| 117 | ++pos; |
| 118 | } |
| 119 | |
| 120 | return *this; |
| 121 | } |
| 122 | |
| 123 | uint32_t |
| 124 | UTF8Iterator::operator*() const { |
| 125 | return chr; |
| 126 | } |
| 127 | |
| 128 | /* EOF */ |
| 129 | |