diff options
author | Underground78 <underground78@users.sourceforge.net> | 2012-10-07 23:36:00 +0400 |
---|---|---|
committer | Underground78 <underground78@users.sourceforge.net> | 2012-10-14 21:40:36 +0400 |
commit | 7cb86ad153e6c6409a49cd1f9546aaa7411c514a (patch) | |
tree | 7fa46d18b702361faa6cae400c47aa976a5d77a6 /include | |
parent | 6c0b8b6774334272c16106f9d0919d15bf2b8b3a (diff) |
External subtitles: add support for UTF-8 without BOM.
Change the default subtitle encoding to UTF-8 and fallback to ANSI if invalid UTF8 characters are found while reading the file.
The file Utf8.h is borrowed from Notepad++ source code. Thanks to Francois-R. Boyer.
This commit fixes ticket #439.
Diffstat (limited to 'include')
-rw-r--r-- | include/Utf8.h | 57 |
1 files changed, 57 insertions, 0 deletions
diff --git a/include/Utf8.h b/include/Utf8.h new file mode 100644 index 000000000..eed48df37 --- /dev/null +++ b/include/Utf8.h @@ -0,0 +1,57 @@ +// Simple functions to test UTF-8 characters. +// Copyright (C)2010 Francois-R.Boyer@PolyMtl.ca +// First version 2010-08 +// +// Written for notepad++, and distributed under same license: +// This program is free software; you can redistribute it and/or +// modify it under the terms of the GNU General Public License +// as published by the Free Software Foundation; either +// version 2 of the License, or (at your option) any later version. + +// This program is distributed in the hope that it will be useful, +// but WITHOUT ANY WARRANTY; without even the implied warranty of +// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +// GNU General Public License for more details. + +// You should have received a copy of the GNU General Public License +// along with this program; if not, write to the Free Software +// Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. + +#pragma once + +namespace Utf8 { // could be a static class, instead of a namespace, if it needs private members + // basic classification of UTF-8 bytes + inline static bool isSingleByte(unsigned char c) { return c < 0x80; } + inline static bool isPartOfMultibyte(unsigned char c) { return c >= 0x80; } + inline static bool isFirstOfMultibyte(unsigned char c) { return c >= 0xC2 && c < 0xF5; } // 0xF5 to 0xFD are defined by UTF-8, but are not currently valid Unicode + inline static bool isContinuation(unsigned char c) { return (c & 0xC0) == 0x80; } + inline static bool isValid(unsigned char c) { return c < 0xC0 || isFirstOfMultibyte(c); } // validates a byte, out of context + + // number of continuation bytes for a given valid first character (0 for single byte characters) + inline static int continuationBytes(unsigned char c) { + static const char _len[] = { 1,1,2,3 }; + return (c < 0xC0) ? 0 : _len[(c & 0x30) >> 4]; + } + + // validates a full character + inline static bool isValid(const unsigned char* buf, int buflen) { + if(isSingleByte(buf[0])) return true; // single byte is valid + if(!isFirstOfMultibyte(buf[0])) return false; // not single byte, nor valid multi-byte first byte + int charContinuationBytes = continuationBytes(buf[0]); + if(buflen < charContinuationBytes+1) return false; // character does not fit in buffer + for(int i = charContinuationBytes; i>0; --i) + if(!isContinuation(*(++buf))) return false; // not enough continuation bytes + return true; // the character is valid (if there are too many continuation bytes, it is the next character that will be invalid) + } + + // rewinds to the first byte of a multi-byte character for any valid UTF-8 (and will not rewind too much on any other input) + inline static int characterStart(const unsigned char* buf, int startingIndex) { + int charContinuationBytes = 0; + while(charContinuationBytes < startingIndex // rewind past start of buffer? + && charContinuationBytes < 5 // UTF-8 support up to 5 continuation bytes (but valid sequences currently do not have more than 3) + && isContinuation(buf[startingIndex-charContinuationBytes]) + ) + ++charContinuationBytes; + return startingIndex-charContinuationBytes; + } +}; |