Line data    Source code

       1              : // Copyright (C) 2020-2026 Free Software Foundation, Inc.
       2              : 
       3              : // This file is part of GCC.
       4              : 
       5              : // GCC is free software; you can redistribute it and/or modify it under
       6              : // the terms of the GNU General Public License as published by the Free
       7              : // Software Foundation; either version 3, or (at your option) any later
       8              : // version.
       9              : 
      10              : // GCC is distributed in the hope that it will be useful, but WITHOUT ANY
      11              : // WARRANTY; without even the implied warranty of MERCHANTABILITY or
      12              : // FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
      13              : // for more details.
      14              : 
      15              : // You should have received a copy of the GNU General Public License
      16              : // along with GCC; see the file COPYING3.  If not see
      17              : // <http://www.gnu.org/licenses/>.
      18              : 
      19              : #ifndef RUST_UNICODE_H
      20              : #define RUST_UNICODE_H
      21              : 
      22              : #include "optional.h"
      23              : #include "rust-system.h"
      24              : #include "rust-input-source.h"
      25              : 
      26              : namespace Rust {
      27              : 
      28       631021 : class Utf8String
      29              : {
      30              : private:
      31              :   std::vector<Codepoint> chars;
      32              : 
      33              : public:
      34              :   static tl::optional<Utf8String>
      35       315507 :   make_utf8_string (const std::string &maybe_utf8)
      36              :   {
      37       315507 :     BufferInputSource input_source = {maybe_utf8, 0};
      38       315507 :     tl::optional<std::vector<Codepoint>> chars_opt = input_source.get_chars ();
      39       315507 :     if (chars_opt.has_value ())
      40       631014 :       return {Utf8String (chars_opt.value ())};
      41              :     else
      42            0 :       return tl::nullopt;
      43       315507 :   }
      44              : 
      45       521591 :   Utf8String (const std::vector<Codepoint> codepoints) : chars ({codepoints}) {}
      46              : 
      47       206084 :   std::string as_string () const
      48              :   {
      49       206084 :     std::stringstream ss;
      50      1087196 :     for (Codepoint c : chars)
      51      1762224 :       ss << c.as_string ();
      52              : 
      53       206084 :     return ss.str ();
      54       206084 :   };
      55              : 
      56              :   // Returns characters
      57       109423 :   std::vector<Codepoint> get_chars () const { return chars; }
      58              : 
      59              :   Utf8String nfc_normalize () const;
      60              : };
      61              : 
      62              : bool is_alphabetic (uint32_t codepoint);
      63              : 
      64              : bool is_ascii_only (const std::string &str);
      65              : 
      66              : bool is_numeric (uint32_t codepoint);
      67              : 
      68              : bool is_nfc_qc_no (uint32_t codepoint);
      69              : 
      70              : bool is_nfc_qc_maybe (uint32_t codepoint);
      71              : 
      72              : enum class QuickCheckResult
      73              : {
      74              :   YES,
      75              :   NO,
      76              :   MAYBE
      77              : };
      78              : 
      79              : QuickCheckResult nfc_quick_check (const std::vector<Codepoint> &s);
      80              : 
      81              : } // namespace Rust
      82              : 
      83              : #if CHECKING_P
      84              : 
      85              : namespace selftest {
      86              : 
      87              : void rust_nfc_qc_test ();
      88              : 
      89              : void rust_utf8_normalize_test ();
      90              : 
      91              : void rust_utf8_property_test ();
      92              : 
      93              : } // namespace selftest
      94              : 
      95              : #endif // CHECKING_P
      96              : 
      97              : #endif