src/plugins/litehtml_viewer/litehtml/codepoint.cpp

   1 // Copyright (C) 2020-2021 Primate Labs Inc.
   2 // All rights reserved.
   3 //
   4 // Redistribution and use in source and binary forms, with or without
   5 // modification, are permitted provided that the following conditions are
   6 // met:
   7 //
   8 //    * Redistributions of source code must retain the above copyright
   9 // notice, this list of conditions and the following disclaimer.
  10 //    * Redistributions in binary form must reproduce the above
  11 // copyright notice, this list of conditions and the following disclaimer
  12 // in the documentation and/or other materials provided with the
  13 // distribution.
  14 //    * Neither the names of the copyright holders nor the names of their
  15 // contributors may be used to endorse or promote products derived from
  16 // this software without specific prior written permission.
  17 //
  18 // THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
  19 // "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
  20 // LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
  21 // A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
  22 // OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
  23 // SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
  24 // LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
  25 // DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
  26 // THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
  27 // (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
  28 // OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  29
  30 #include "codepoint.h"
  31
  32 #include <iostream>
  33
  34 namespace {
  35
  36 bool lookup(const uint32_t* table, char c)
  37 {
  38     return table[c >> 5] & (1 << (c & 0x1f));
  39 }
  40
  41 } // namespace
  42
  43 namespace litehtml {
  44
  45 bool is_ascii_codepoint(char c)
  46 {
  47     return (c < 128);
  48 }
  49
  50 // https://datatracker.ietf.org/doc/html/rfc3986#section-2.2
  51 bool is_url_reserved_codepoint(char c)
  52 {
  53     static const uint32_t reserved_lookup[] = {
  54         0x00000000,
  55         0xac009fda,
  56         0x28000001,
  57         0x00000000
  58     };
  59
  60     if (!is_ascii_codepoint(c)) {
  61         return false;
  62     }
  63     return lookup(reserved_lookup, c);
  64 }
  65
  66 // https://datatracker.ietf.org/doc/html/rfc3986#section-3.1
  67 bool is_url_scheme_codepoint(char c)
  68 {
  69     static const uint32_t scheme_lookup[] = {
  70         0x00000000,
  71         0x03ff6800,
  72         0x07fffffe,
  73         0x07fffffe,
  74     };
  75
  76     if (!is_ascii_codepoint(c)) {
  77         return false;
  78     }
  79     return lookup(scheme_lookup, c);
  80 }
  81
  82 } // namespace litehtml