source: trunk/src/corelib/codecs/qiconvcodec.cpp@ 947

/****************************************************************************
**
** Copyright (C) 2011 Nokia Corporation and/or its subsidiary(-ies).
** All rights reserved.
** Contact: Nokia Corporation ([email protected])
**
** This file is part of the QtCore module of the Qt Toolkit.
**
** $QT_BEGIN_LICENSE:LGPL$
** Commercial Usage
** Licensees holding valid Qt Commercial licenses may use this file in
** accordance with the Qt Commercial License Agreement provided with the
** Software or, alternatively, in accordance with the terms contained in
** a written agreement between you and Nokia.
**
** GNU Lesser General Public License Usage
** Alternatively, this file may be used under the terms of the GNU Lesser
** General Public License version 2.1 as published by the Free Software
** Foundation and appearing in the file LICENSE.LGPL included in the
** packaging of this file.  Please review the following information to
** ensure the GNU Lesser General Public License version 2.1 requirements
** will be met: http://www.gnu.org/licenses/old-licenses/lgpl-2.1.html.
**
** In addition, as a special exception, Nokia gives you certain additional
** rights.  These rights are described in the Nokia Qt LGPL Exception
** version 1.1, included in the file LGPL_EXCEPTION.txt in this package.
**
** GNU General Public License Usage
** Alternatively, this file may be used under the terms of the GNU
** General Public License version 3.0 as published by the Free Software
** Foundation and appearing in the file LICENSE.GPL included in the
** packaging of this file.  Please review the following information to
** ensure the GNU General Public License version 3.0 requirements will be
** met: http://www.gnu.org/copyleft/gpl.html.
**
** If you have questions regarding the use of this file, please contact
** Nokia at [email protected].
** $QT_END_LICENSE$
**
****************************************************************************/

#include "qiconvcodec_p.h"
#include "qtextcodec_p.h"
#include <qlibrary.h>
#include <qdebug.h>
#include <qthreadstorage.h>

#include <errno.h>
#include <locale.h>
#include <stdio.h>
#include <dlfcn.h>

// unistd.h is needed for the _XOPEN_UNIX macro
#include <unistd.h>
#if defined(_XOPEN_UNIX) && !defined(Q_OS_QNX) && !defined(Q_OS_OSF)
#  include <langinfo.h>
#endif

#if defined(Q_OS_HPUX)
#  define NO_BOM
#  define UTF16 "ucs2"
#elif defined(Q_OS_AIX)
#  define NO_BOM
#  define UTF16 "UCS-2"
#elif defined(Q_OS_FREEBSD) || defined(Q_OS_MAC)
#  define NO_BOM
#  if Q_BYTE_ORDER == Q_BIG_ENDIAN
#    define UTF16 "UTF-16BE"
#  else
#    define UTF16 "UTF-16LE"
#  endif
#else
#  define UTF16 "UTF-16"
#endif

#if defined(Q_OS_MAC)
#ifndef GNU_LIBICONV
#define GNU_LIBICONV
#endif
typedef iconv_t (*Ptr_iconv_open) (const char*, const char*);
typedef size_t (*Ptr_iconv) (iconv_t, const char **, size_t *, char **, size_t *);
typedef int (*Ptr_iconv_close) (iconv_t);

static Ptr_iconv_open ptr_iconv_open = 0;
static Ptr_iconv ptr_iconv = 0;
static Ptr_iconv_close ptr_iconv_close = 0;
#endif

QT_BEGIN_NAMESPACE

extern bool qt_locale_initialized;

QIconvCodec::QIconvCodec()
    : utf16Codec(0)
{
    utf16Codec = QTextCodec::codecForMib(1015);
    Q_ASSERT_X(utf16Codec != 0,
               "QIconvCodec::convertToUnicode",
               "internal error, UTF-16 codec not found");
    if (!utf16Codec) {
        fprintf(stderr, "QIconvCodec::convertToUnicode: internal error, UTF-16 codec not found\n");
        utf16Codec = reinterpret_cast<QTextCodec *>(~0);
    }
#if defined(Q_OS_MAC)
    if (ptr_iconv_open == 0) {
        QLibrary libiconv(QLatin1String("/usr/lib/libiconv"));
        libiconv.setLoadHints(QLibrary::ExportExternalSymbolsHint);

        ptr_iconv_open = reinterpret_cast<Ptr_iconv_open>(libiconv.resolve("libiconv_open"));
        if (!ptr_iconv_open)
            ptr_iconv_open = reinterpret_cast<Ptr_iconv_open>(libiconv.resolve("iconv_open"));
        ptr_iconv = reinterpret_cast<Ptr_iconv>(libiconv.resolve("libiconv"));
        if (!ptr_iconv)
            ptr_iconv = reinterpret_cast<Ptr_iconv>(libiconv.resolve("iconv"));
        ptr_iconv_close = reinterpret_cast<Ptr_iconv_close>(libiconv.resolve("libiconv_close"));
        if (!ptr_iconv_close)
            ptr_iconv_close = reinterpret_cast<Ptr_iconv_close>(libiconv.resolve("iconv_close"));

        Q_ASSERT_X(ptr_iconv_open && ptr_iconv && ptr_iconv_close,
        "QIconvCodec::QIconvCodec()",
        "internal error, could not resolve the iconv functions");

#       undef iconv_open
#       define iconv_open ptr_iconv_open
#       undef iconv
#       define iconv ptr_iconv
#       undef iconv_close
#       define iconv_close ptr_iconv_close
    }
#endif
}

QIconvCodec::~QIconvCodec()
{
}

QIconvCodec::IconvState::IconvState(iconv_t x)
    : buffer(array), bufferLen(sizeof array), cd(x)
{
}

QIconvCodec::IconvState::~IconvState()
{
    if (cd != reinterpret_cast<iconv_t>(-1))
        iconv_close(cd);
    if (buffer != array)
        delete[] buffer;
}

void QIconvCodec::IconvState::saveChars(const char *c, int count)
{
    if (count > bufferLen) {
        if (buffer != array)
            delete[] buffer;
        buffer = new char[bufferLen = count];
    }

    memcpy(buffer, c, count);
}

static void qIconvCodecStateFree(QTextCodec::ConverterState *state)
{
    delete reinterpret_cast<QIconvCodec::IconvState *>(state->d);
}

Q_GLOBAL_STATIC(QThreadStorage<QIconvCodec::IconvState *>, toUnicodeState)

QString QIconvCodec::convertToUnicode(const char* chars, int len, ConverterState *convState) const
{
    if (utf16Codec == reinterpret_cast<QTextCodec *>(~0))
        return QString::fromLatin1(chars, len);

    int invalidCount = 0;
    int remainingCount = 0;
    char *remainingBuffer = 0;
    IconvState **pstate;

    if (convState) {
        // stateful conversion
        pstate = reinterpret_cast<IconvState **>(&convState->d);
        if (convState->d) {
            // restore state
            remainingCount = convState->remainingChars;
            remainingBuffer = (*pstate)->buffer;
        } else {
            // first time
            convState->flags |= FreeFunction;
            QTextCodecUnalignedPointer::encode(convState->state_data, qIconvCodecStateFree);
        }
    } else {
        QThreadStorage<QIconvCodec::IconvState *> *ts = toUnicodeState();
        if (!qt_locale_initialized || !ts) {
            // we're running after the Q_GLOBAL_STATIC has been deleted
            // or before the QCoreApplication initialization
            // bad programmer, no cookie for you
            return QString::fromLatin1(chars, len);
        }

        // stateless conversion -- use thread-local data
        pstate = &toUnicodeState()->localData();
    }

    if (!*pstate) {
        // first time, create the state
        iconv_t cd = QIconvCodec::createIconv_t(UTF16, 0);
        if (cd == reinterpret_cast<iconv_t>(-1)) {
            static int reported = 0;
            if (!reported++) {
                fprintf(stderr,
                        "QIconvCodec::convertToUnicode: using Latin-1 for conversion, iconv_open failed\n");
            }
            return QString::fromLatin1(chars, len);
        }

        *pstate = new IconvState(cd);
    }

    IconvState *state = *pstate;
    size_t inBytesLeft = len;
    // best case assumption, each byte is converted into one UTF-16 character, plus 2 bytes for the BOM
#ifdef GNU_LIBICONV
    // GNU doesn't disagree with POSIX :/
    const char *inBytes = chars;
#else
    char *inBytes = const_cast<char *>(chars);
#endif

    QByteArray in;
    if (remainingCount) {
        // we have to prepend the remaining bytes from the previous conversion
        inBytesLeft += remainingCount;
        in.resize(inBytesLeft);
        inBytes = in.data();

        memcpy(in.data(), remainingBuffer, remainingCount);
        memcpy(in.data() + remainingCount, chars, len);

        remainingCount = 0;
    }