/* * Copyright (c) 2020, Andreas Kling * All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: * * 1. Redistributions of source code must retain the above copyright notice, this * list of conditions and the following disclaimer. * * 2. Redistributions in binary form must reproduce the above copyright notice, * this list of conditions and the following disclaimer in the documentation * and/or other materials provided with the distribution. * * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE * DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR * SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER * CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. */ #include #include #include namespace TextCodec { Latin1Decoder& latin1_decoder() { static Latin1Decoder* decoder; if (!decoder) decoder = new Latin1Decoder; return *decoder; } UTF8Decoder& utf8_decoder() { static UTF8Decoder* decoder; if (!decoder) decoder = new UTF8Decoder; return *decoder; } Decoder* decoder_for(const String& encoding) { if (encoding.equals_ignoring_case("iso-8859-1")) return &latin1_decoder(); if (encoding.equals_ignoring_case("utf-8")) return &utf8_decoder(); return nullptr; } String UTF8Decoder::to_utf8(const StringView& input) { return input; } String Latin1Decoder::to_utf8(const StringView& input) { StringBuilder builder(input.length()); for (size_t i = 0; i < input.length(); ++i) { u8 ch = input[i]; if (ch & 0x80) { builder.append(0xc0 | (ch >> 6)); builder.append(0x80 | (ch & 0x3f)); } else { builder.append(ch); } } return builder.to_string(); } }