From c113da2069b66130f67a0f27c699e1cec83588a5 Mon Sep 17 00:00:00 2001 From: Michele Calgaro Date: Sun, 30 Jun 2024 14:18:32 +0900 Subject: Rename codec nt* related files to equivalent tq*. The qrtlcodec files have been renamed into tqhebrewcodec files, for consistency with file naming used for other codecs. Signed-off-by: Michele Calgaro --- src/codecs/qjiscodec.cpp | 706 ----------------------------------------------- 1 file changed, 706 deletions(-) delete mode 100644 src/codecs/qjiscodec.cpp (limited to 'src/codecs/qjiscodec.cpp') diff --git a/src/codecs/qjiscodec.cpp b/src/codecs/qjiscodec.cpp deleted file mode 100644 index 8922209c7..000000000 --- a/src/codecs/qjiscodec.cpp +++ /dev/null @@ -1,706 +0,0 @@ -/**************************************************************************** -** -** Implementation of TQJisCodec class -** -** Created : 990225 -** -** Copyright (C) 2000-2008 Trolltech ASA. All rights reserved. -** -** This file is part of the tools module of the TQt GUI Toolkit. -** -** This file may be used under the terms of the GNU General -** Public License versions 2.0 or 3.0 as published by the Free -** Software Foundation and appearing in the files LICENSE.GPL2 -** and LICENSE.GPL3 included in the packaging of this file. -** Alternatively you may (at your option) use any later version -** of the GNU General Public License if such license has been -** publicly approved by Trolltech ASA (or its successors, if any) -** and the KDE Free TQt Foundation. -** -** Please review the following information to ensure GNU General -** Public Licensing requirements will be met: -** http://trolltech.com/products/qt/licenses/licensing/opensource/. -** If you are unsure which license is appropriate for your use, please -** review the following information: -** http://trolltech.com/products/qt/licenses/licensing/licensingoverview -** or contact the sales department at sales@trolltech.com. -** -** This file may be used under the terms of the Q Public License as -** defined by Trolltech ASA and appearing in the file LICENSE.TQPL -** included in the packaging of this file. Licensees holding valid TQt -** Commercial licenses may use this file in accordance with the TQt -** Commercial License Agreement provided with the Software. -** -** This file is provided "AS IS" with NO WARRANTY OF ANY KIND, -** INCLUDING THE WARRANTIES OF DESIGN, MERCHANTABILITY AND FITNESS FOR -** A PARTICULAR PURPOSE. Trolltech reserves all rights not granted -** herein. -** -**********************************************************************/ - -// Most of the code here was originally written by Serika Kurusugawa, -// a.k.a. Junji Takagi, and is included in TQt with the author's permission -// and the grateful thanks of the Trolltech team. - -/*! \class TQJisCodec - \reentrant - \ingroup i18n - - \brief The TQJisCodec class provides conversion to and from JIS character sets. - - More precisely, the TQJisCodec class subclasses TQTextCodec to - provide support for JIS X 0201 Latin, JIS X 0201 Kana, JIS X 0208 - and JIS X 0212. - - The environment variable UNICODEMAP_JP can be used to fine-tune - TQJisCodec, TQSjisCodec and TQEucJpCodec. The mapping names are as for - the Japanese XML working group's \link - http://www.y-adagio.com/public/standards/tr_xml_jpf/toc.htm XML - Japanese Profile\endlink, because it names and explains all the - widely used mappings. Here are brief descriptions, written by - Serika Kurusugawa: - - \list - - \i "unicode-0.9" or "unicode-0201" for Unicode style. This assumes - JISX0201 for 0x00-0x7f. (0.9 is a table version of jisx02xx mapping - used for Uniocde spec version 1.1.) - - \i "unicode-ascii" This assumes US-ASCII for 0x00-0x7f; some - chars (JISX0208 0x2140 and JISX0212 0x2237) are different from - Unicode 1.1 to avoid conflict. - - \i "open-19970715-0201" ("open-0201" for convenience) or - "jisx0221-1995" for JISX0221-JISX0201 style. JIS X 0221 is JIS - version of Unicode, but a few chars (0x5c, 0x7e, 0x2140, 0x216f, - 0x2131) are different from Unicode 1.1. This is used when 0x5c is - treated as YEN SIGN. - - \i "open-19970715-ascii" ("open-ascii" for convenience) for - JISX0221-ASCII style. This is used when 0x5c is treated as REVERSE - SOLIDUS. - - \i "open-19970715-ms" ("open-ms" for convenience) or "cp932" for - Microsoft Windows style. Windows Code Page 932. Some chars (0x2140, - 0x2141, 0x2142, 0x215d, 0x2171, 0x2172) are different from Unicode - 1.1. - - \i "jdk1.1.7" for Sun's JDK style. Same as Unicode 1.1, except that - JIS 0x2140 is mapped to UFF3C. Either ASCII or JISX0201 can be used - for 0x00-0x7f. - - \endlist - - In addition, the extensions "nec-vdc", "ibm-vdc" and "udc" are - supported. - - For example, if you want to use Unicode style conversion but with - NEC's extension, set \c UNICODEMAP_JP to - \c {unicode-0.9, nec-vdc}. (You will probably - need to quote that in a shell command.) - - Most of the code here was written by Serika Kurusugawa, - a.k.a. Junji Takagi, and is included in TQt with the author's - permission and the grateful thanks of the Trolltech team. Here is - the copyright statement for that code: - - \legalese - - Copyright (C) 1999 Serika Kurusugawa. All rights reserved. - - Redistribution and use in source and binary forms, with or without - modification, are permitted provided that the following conditions - are met: - \list 1 - \i Redistributions of source code must retain the above copyright - notice, this list of conditions and the following disclaimer. - \i 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. - \endlist - - THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS "AS IS". - 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 REGENTS 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 "ntqjiscodec.h" - -#ifndef TQT_NO_BIG_CODECS - -static const uchar Esc = 0x1b; -static const uchar So = 0x0e; // Shift Out -static const uchar Si = 0x0f; // Shift In - -static const uchar ReverseSolidus = 0x5c; -static const uchar YenSign = 0x5c; -static const uchar Tilde = 0x7e; -static const uchar Overline = 0x7e; - -#define IsKana(c) (((c) >= 0xa1) && ((c) <= 0xdf)) -#define IsJisChar(c) (((c) >= 0x21) && ((c) <= 0x7e)) - -#define TQValidChar(u) ((u) ? TQChar((ushort)(u)) : TQChar::replacement) - -enum Iso2022State{ Ascii, MinState = Ascii, - JISX0201_Latin, JISX0201_Kana, - JISX0208_1978, JISX0208_1983, - JISX0212, MaxState = JISX0212, - UnknownState }; - -static const char Esc_CHARS[] = "()*+-./"; - -static const char Esc_Ascii[] = {Esc, '(', 'B', 0 }; -static const char Esc_JISX0201_Latin[] = {Esc, '(', 'J', 0 }; -static const char Esc_JISX0201_Kana[] = {Esc, '(', 'I', 0 }; -static const char Esc_JISX0208_1978[] = {Esc, '$', '@', 0 }; -static const char Esc_JISX0208_1983[] = {Esc, '$', 'B', 0 }; -static const char Esc_JISX0212[] = {Esc, '$', '(', 'D', 0 }; -static const char * const Esc_SEQ[] = { Esc_Ascii, - Esc_JISX0201_Latin, - Esc_JISX0201_Kana, - Esc_JISX0208_1978, - Esc_JISX0208_1983, - Esc_JISX0212 }; - -/*! \internal */ -TQJisCodec::TQJisCodec() : conv(TQJpUnicodeConv::newConverter(TQJpUnicodeConv::Default)) -{ -} - - -/*! \internal */ -TQJisCodec::~TQJisCodec() -{ - delete (TQJpUnicodeConv*)conv; - conv = 0; -} - - -/*! \internal */ -int TQJisCodec::mibEnum() const -{ - /* - Name: JIS_Encoding - MIBenum: 16 - Source: JIS X 0202-1991. Uses ISO 2022 escape sequences to - shift code sets as documented in JIS X 0202-1991. - Alias: csJISEncoding - */ - return 16; -} - -/*! \internal */ -TQCString TQJisCodec::fromUnicode(const TQString& uc, int& lenInOut) const -{ - int l = TQMIN((int)uc.length(),lenInOut); - TQCString result; - Iso2022State state = Ascii; - Iso2022State prev = Ascii; - for (int i=0; iunicodeToJisx0201(ch.row(), ch.cell())) != 0) { - if (j < 0x80) { - // JIS X 0201 Latin - if (state != Ascii || - ch.cell() == YenSign || ch.cell() == Overline) { - state = JISX0201_Latin; - } - } else { - // JIS X 0201 Kana - state = JISX0201_Kana; - j &= 0x7f; - } - } else if ((j = conv->unicodeToJisx0208(ch.row(), ch.cell())) != 0) { - // JIS X 0208 - state = JISX0208_1983; - } else if ((j = conv->unicodeToJisx0212(ch.row(), ch.cell())) != 0) { - // JIS X 0212 - state = JISX0212; - } else { - // Invalid - state = UnknownState; - j = '?'; - } - if (state != prev) { - if (state == UnknownState) { - result += Esc_Ascii; - } else { - result += Esc_SEQ[state - MinState]; - } - prev = state; - } - if (j < 0x0100) { - result += j & 0xff; - } else { - result += (j >> 8) & 0xff; - result += j & 0xff; - } - } - if (prev != Ascii) { - result += Esc_Ascii; - } - lenInOut = result.length(); - return result; -} - -/*! \internal */ -TQString TQJisCodec::toUnicode(const char* chars, int len) const -{ - TQString result; - Iso2022State state = Ascii, prev = Ascii; - for (int i=0; ijisx0201ToUnicode(ch); - result += TQValidChar(u); - break; - case JISX0201_Kana: - u = conv->jisx0201ToUnicode(ch | 0x80); - result += TQValidChar(u); - break; - case JISX0208_1978: - case JISX0208_1983: - if ( i < len-1 ) { - uchar c2 = chars[++i]; - u = conv->jisx0208ToUnicode(ch & 0x7f, c2 & 0x7f); - result += TQValidChar(u); - } - break; - case JISX0212: - if ( i < len-1 ) { - uchar c2 = chars[++i]; - u = conv->jisx0212ToUnicode(ch & 0x7f, c2 & 0x7f); - result += TQValidChar(u); - } - break; - default: - result += TQChar::replacement; - break; - } - } - } - return result; -} - -/*! \internal */ -const char* TQJisCodec::name() const -{ - return "JIS7"; -} - -/*! - Returns the codec's mime name. -*/ -const char* TQJisCodec::mimeName() const -{ - return "ISO-2022-JP"; -} - -/*! \internal */ -int TQJisCodec::heuristicNameMatch(const char* hint) const -{ - if ( tqstrnicmp( hint, "ISO-2022-JP", 11 ) == 0 ) - return 10000; - if ( simpleHeuristicNameMatch( "ISO-2022-JP-2", hint ) > 0 ) - return 10; - - int score = 0; - bool ja = FALSE; - if (tqstrnicmp(hint, "ja_JP", 5) == 0 || tqstrnicmp(hint, "japan", 5) == 0) { - score += 3; - ja = TRUE; - } else if (tqstrnicmp(hint, "ja", 2) == 0) { - score += 2; - ja = TRUE; - } - const char *p; - if (ja) { - p = strchr(hint, '.'); - if (p == 0) { - return score - 2; - } - p++; - } else { - p = hint; - } - if (p) { - if ((tqstricmp(p, "JIS") == 0) || - (tqstricmp(p, "JIS7") == 0) || - (simpleHeuristicNameMatch("ISO-2022-JP", p) > 0)) { - return score + 4; - } - } - return TQTextCodec::heuristicNameMatch(hint); -} - -/*! \internal */ -int TQJisCodec::heuristicContentMatch(const char* chars, int len) const -{ - int score = 0; - Iso2022State state = Ascii, prev = Ascii; - for (int i=0; ijisx0201ToUnicode(ch); - result += TQValidChar(u); - break; - case JISX0201_Kana: - u = conv->jisx0201ToUnicode(ch | 0x80); - result += TQValidChar(u); - break; - case JISX0208_1978: - case JISX0208_1983: - case JISX0212: - buf[nbuf++] = ch; - break; - default: - result += TQChar::replacement; - break; - } - break; - case 1: - switch (state) { - case JISX0208_1978: - case JISX0208_1983: - u = conv->jisx0208ToUnicode(buf[0] & 0x7f, ch & 0x7f); - result += TQValidChar(u); - break; - case JISX0212: - u = conv->jisx0212ToUnicode(buf[0] & 0x7f, ch & 0x7f); - result += TQValidChar(u); - break; - default: - result += TQChar::replacement; - break; - } - nbuf = 0; - break; - } - } - } - } - return result; - } -}; - -/*! \internal */ -TQTextDecoder* TQJisCodec::makeDecoder() const -{ - return new TQJisDecoder(conv); -} - -#endif -- cgit v1.2.3