Line data    Source code

       1             : /*
       2             :  *  Copyright (C) 2004-2025 Savoir-faire Linux Inc.
       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 <https://www.gnu.org/licenses/>.
      16             :  */
      17             : 
      18             : #include "connectivity/utf8_utils.h"
      19             : 
      20             : #include <simdutf.h>
      21             : 
      22             : #include <cassert>
      23             : 
      24             : namespace jami {
      25             : 
      26             : bool
      27       25195 : utf8_validate(std::string_view str)
      28             : {
      29       25195 :     return simdutf::validate_utf8(str.data(), str.size());
      30             : }
      31             : 
      32             : std::string
      33           2 : utf8_make_valid(std::string_view name)
      34             : {
      35           2 :     std::string sanitized;
      36           2 :     sanitized.reserve(name.size());
      37           3 :     while (!name.empty()) {
      38           3 :         const auto [err, valid_bytes] = simdutf::validate_utf8_with_errors(name.data(), name.size());
      39           3 :         if (!err) {
      40           2 :             sanitized.append(name);
      41           2 :             break;
      42             :         }
      43           1 :         sanitized.append(name.data(), valid_bytes);
      44           1 :         sanitized.append("\xEF\xBF\xBD", 3); // append '�'
      45           1 :         name.remove_prefix(valid_bytes + 1);
      46             :     }
      47           2 :     return sanitized;
      48           0 : }
      49             : 
      50             : } // namespace jami