[Libreoffice-commits] .: 5 commits - sal/Library_sal.mk sal/Library_sal_textenc.mk sal/textenc sal/util
Stephan Bergmann
sbergmann at kemper.freedesktop.org
Fri Jan 6 06:01:47 PST 2012
sal/Library_sal.mk | 5
sal/Library_sal_textenc.mk | 3
sal/textenc/context.cxx | 2
sal/textenc/context.hxx | 2
sal/textenc/convertadobe.tab | 6
sal/textenc/convertbig5hkscs.cxx | 61 --
sal/textenc/convertbig5hkscs.hxx | 6
sal/textenc/convertbig5hkscs.tab | 6
sal/textenc/converter.cxx | 38 -
sal/textenc/converter.hxx | 34 -
sal/textenc/converteuctw.cxx | 61 --
sal/textenc/converteuctw.hxx | 8
sal/textenc/converteuctw.tab | 4
sal/textenc/convertgb18030.cxx | 61 --
sal/textenc/convertgb18030.hxx | 8
sal/textenc/convertgb18030.tab | 4
sal/textenc/convertiscii.tab | 5
sal/textenc/convertiso2022cn.cxx | 67 +-
sal/textenc/convertiso2022cn.hxx | 8
sal/textenc/convertiso2022cn.tab | 5
sal/textenc/convertiso2022jp.cxx | 68 +-
sal/textenc/convertiso2022jp.hxx | 8
sal/textenc/convertiso2022jp.tab | 5
sal/textenc/convertiso2022kr.cxx | 68 +-
sal/textenc/convertiso2022kr.hxx | 8
sal/textenc/convertiso2022kr.tab | 5
sal/textenc/convertsimple.cxx | 685 ++++++++++++++++++++++
sal/textenc/convertsimple.hxx | 54 +
sal/textenc/convertsinglebytetobmpunicode.cxx | 28
sal/textenc/convertsinglebytetobmpunicode.hxx | 8
sal/textenc/handleundefinedunicodetotextchar.cxx | 193 ++++++
sal/textenc/handleundefinedunicodetotextchar.hxx | 50 +
sal/textenc/tables.cxx | 2
sal/textenc/tcvtarb1.tab | 29
sal/textenc/tcvtbyte.cxx | 692 -----------------------
sal/textenc/tcvtbyte.hxx | 55 +
sal/textenc/tcvteas1.tab | 17
sal/textenc/tcvtest1.tab | 125 ++--
sal/textenc/tcvtjp6.tab | 7
sal/textenc/tcvtkr6.tab | 4
sal/textenc/tcvtlat1.tab | 30
sal/textenc/tcvtmb.cxx | 29
sal/textenc/tcvtscn6.tab | 4
sal/textenc/tcvtsym1.tab | 4
sal/textenc/tcvttcn6.tab | 4
sal/textenc/tcvtutf7.cxx | 4
sal/textenc/tcvtutf8.cxx | 72 +-
sal/textenc/tcvtutf8.hxx | 61 ++
sal/textenc/tenchelp.cxx | 216 -------
sal/textenc/tenchelp.hxx | 86 --
sal/textenc/textenc.cxx | 30
sal/textenc/unichars.cxx | 40 -
sal/textenc/unichars.hxx | 36 -
sal/util/sal.map | 9
54 files changed, 1653 insertions(+), 1477 deletions(-)
New commits:
commit 01690f571db071781a2358bcc15581a6fa9dd86c
Author: Stephan Bergmann <sbergman at redhat.com>
Date: Fri Jan 6 15:00:19 2012 +0100
Final disentanglement between sal and sal_textenc.
diff --git a/sal/Library_sal.mk b/sal/Library_sal.mk
index c43013c..cbdbc82 100644
--- a/sal/Library_sal.mk
+++ b/sal/Library_sal.mk
@@ -121,8 +121,8 @@ $(eval $(call gb_Library_add_exception_objects,sal,\
sal/rtl/source/uuid \
sal/textenc/converter \
sal/textenc/convertsimple \
+ sal/textenc/handleundefinedunicodetotextchar \
sal/textenc/tcvtutf8 \
- sal/textenc/tenchelp \
sal/textenc/tencinfo \
sal/textenc/textcvt \
sal/textenc/textenc \
diff --git a/sal/Library_sal_textenc.mk b/sal/Library_sal_textenc.mk
index 585a485..77798d8 100644
--- a/sal/Library_sal_textenc.mk
+++ b/sal/Library_sal_textenc.mk
@@ -51,8 +51,6 @@ $(eval $(call gb_Library_add_exception_objects,sal_textenc,\
sal/textenc/tcvtbyte \
sal/textenc/tcvtmb \
sal/textenc/tcvtutf7 \
- sal/textenc/tenchelp \
- sal/textenc/unichars \
))
# vim: set noet sw=4 ts=4:
diff --git a/sal/textenc/convertsimple.cxx b/sal/textenc/convertsimple.cxx
index 24a4ad6..939aaa3 100644
--- a/sal/textenc/convertsimple.cxx
+++ b/sal/textenc/convertsimple.cxx
@@ -33,6 +33,7 @@
#include "sal/types.h"
#include "convertsimple.hxx"
+#include "handleundefinedunicodetotextchar.hxx"
#include "tenchelp.hxx"
#define IMPL_MAX_REPLACECHAR 5
@@ -657,13 +658,9 @@ sal_Size sal::detail::textenc::convertUnicodeToChar(
/* (all surrogates characters are undefined) */
if ( n == 0 )
{
- if (ImplHandleUndefinedUnicodeToTextChar(pData,
- &pSrcBuf,
- pEndSrcBuf,
- &pDestBuf,
- pEndDestBuf,
- nFlags,
- pInfo))
+ if (sal::detail::textenc::handleUndefinedUnicodeToTextChar(
+ &pSrcBuf, pEndSrcBuf, &pDestBuf, pEndDestBuf,
+ nFlags, pInfo))
continue;
else
break;
diff --git a/sal/textenc/handleundefinedunicodetotextchar.cxx b/sal/textenc/handleundefinedunicodetotextchar.cxx
new file mode 100644
index 0000000..cebe302
--- /dev/null
+++ b/sal/textenc/handleundefinedunicodetotextchar.cxx
@@ -0,0 +1,193 @@
+/* -*- Mode: C++; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 4 -*- */
+/*
+ * Version: MPL 1.1 / GPLv3+ / LGPLv3+
+ *
+ * The contents of this file are subject to the Mozilla Public License Version
+ * 1.1 (the "License"); you may not use this file except in compliance with
+ * the License or as specified alternatively below. You may obtain a copy of
+ * the License at http://www.mozilla.org/MPL/
+ *
+ * Software distributed under the License is distributed on an "AS IS" basis,
+ * WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
+ * for the specific language governing rights and limitations under the
+ * License.
+ *
+ * Major Contributor(s):
+ * [ Copyright (C) 2012 Red Hat, Inc., Stephan Bergmann <sbergman at redhat.com>
+ * (initial developer) ]
+ *
+ * All Rights Reserved.
+ *
+ * For minor contributions see the git repository.
+ *
+ * Alternatively, the contents of this file may be used under the terms of
+ * either the GNU General Public License Version 3 or later (the "GPLv3+"), or
+ * the GNU Lesser General Public License Version 3 or later (the "LGPLv3+"),
+ * in which case the provisions of the GPLv3+ or the LGPLv3+ are applicable
+ * instead of those above.
+ */
+
+#include "sal/config.h"
+
+#include "rtl/textcvt.h"
+#include "sal/types.h"
+
+#include "handleundefinedunicodetotextchar.hxx"
+#include "tenchelp.hxx"
+
+namespace {
+
+bool ImplIsUnicodeIgnoreChar(sal_Unicode c, sal_uInt32 nFlags)
+{
+ return
+ ((nFlags & RTL_UNICODETOTEXT_FLAGS_NONSPACING_IGNORE) != 0
+ && ImplIsZeroWidth(c))
+ || ((nFlags & RTL_UNICODETOTEXT_FLAGS_CONTROL_IGNORE) != 0
+ && ImplIsControlOrFormat(c))
+ || ((nFlags & RTL_UNICODETOTEXT_FLAGS_PRIVATE_IGNORE) != 0
+ && ImplIsPrivateUse(c));
+}
+
+bool ImplGetUndefinedAsciiMultiByte(sal_uInt32 nFlags,
+ char * pBuf,
+ sal_Size nMaxLen)
+{
+ if (nMaxLen == 0)
+ return false;
+ switch (nFlags & RTL_UNICODETOTEXT_FLAGS_UNDEFINED_MASK)
+ {
+ case RTL_UNICODETOTEXT_FLAGS_UNDEFINED_0:
+ *pBuf = 0x00;
+ break;
+
+ case RTL_UNICODETOTEXT_FLAGS_UNDEFINED_QUESTIONMARK:
+ default: /* RTL_UNICODETOTEXT_FLAGS_UNDEFINED_DEFAULT */
+ *pBuf = 0x3F;
+ break;
+
+ case RTL_UNICODETOTEXT_FLAGS_UNDEFINED_UNDERLINE:
+ *pBuf = 0x5F;
+ break;
+ }
+ return true;
+}
+
+bool ImplGetInvalidAsciiMultiByte(sal_uInt32 nFlags,
+ char * pBuf,
+ sal_Size nMaxLen)
+{
+ if (nMaxLen == 0)
+ return false;
+ switch (nFlags & RTL_UNICODETOTEXT_FLAGS_UNDEFINED_MASK)
+ {
+ case RTL_UNICODETOTEXT_FLAGS_INVALID_0:
+ *pBuf = 0x00;
+ break;
+
+ case RTL_UNICODETOTEXT_FLAGS_INVALID_QUESTIONMARK:
+ default: /* RTL_UNICODETOTEXT_FLAGS_INVALID_DEFAULT */
+ *pBuf = 0x3F;
+ break;
+
+ case RTL_UNICODETOTEXT_FLAGS_INVALID_UNDERLINE:
+ *pBuf = 0x5F;
+ break;
+ }
+ return true;
+}
+
+}
+
+bool sal::detail::textenc::handleUndefinedUnicodeToTextChar(
+ sal_Unicode const ** ppSrcBuf, sal_Unicode const * pEndSrcBuf,
+ char ** ppDestBuf, char const * pEndDestBuf, sal_uInt32 nFlags,
+ sal_uInt32 * pInfo)
+{
+ sal_Unicode c = **ppSrcBuf;
+
+ /* Should the private character map to one byte */
+ if ( (c >= RTL_TEXTCVT_BYTE_PRIVATE_START) && (c <= RTL_TEXTCVT_BYTE_PRIVATE_END) )
+ {
+ if ( nFlags & RTL_UNICODETOTEXT_FLAGS_PRIVATE_MAPTO0 )
+ {
+ **ppDestBuf = (char)(sal_uChar)(c-RTL_TEXTCVT_BYTE_PRIVATE_START);
+ (*ppDestBuf)++;
+ (*ppSrcBuf)++;
+ return true;
+ }
+ }
+
+ /* Should this character ignored (Private, Non Spacing, Control) */
+ if ( ImplIsUnicodeIgnoreChar( c, nFlags ) )
+ {
+ (*ppSrcBuf)++;
+ return true;
+ }
+
+ /* Surrogates Characters should result in */
+ /* one replacement character */
+ if (ImplIsHighSurrogate(c))
+ {
+ if ( *ppSrcBuf == pEndSrcBuf )
+ {
+ *pInfo |= RTL_UNICODETOTEXT_INFO_ERROR | RTL_UNICODETOTEXT_INFO_SRCBUFFERTOSMALL;
+ return false;
+ }
+
+ c = *((*ppSrcBuf)+1);
+ if (ImplIsLowSurrogate(c))
+ (*ppSrcBuf)++;
+ else
+ {
+ *pInfo |= RTL_UNICODETOTEXT_INFO_INVALID;
+ if ( (nFlags & RTL_UNICODETOTEXT_FLAGS_INVALID_MASK) == RTL_UNICODETOTEXT_FLAGS_INVALID_ERROR )
+ {
+ *pInfo |= RTL_UNICODETOTEXT_INFO_ERROR;
+ return false;
+ }
+ else if ( (nFlags & RTL_UNICODETOTEXT_FLAGS_INVALID_MASK) == RTL_UNICODETOTEXT_FLAGS_INVALID_IGNORE )
+ {
+ (*ppSrcBuf)++;
+ return true;
+ }
+ else if (ImplGetInvalidAsciiMultiByte(nFlags,
+ *ppDestBuf,
+ pEndDestBuf - *ppDestBuf))
+ {
+ ++*ppSrcBuf;
+ ++*ppDestBuf;
+ return true;
+ }
+ else
+ {
+ *pInfo |= RTL_UNICODETOTEXT_INFO_ERROR
+ | RTL_UNICODETOTEXT_INFO_DESTBUFFERTOSMALL;
+ return false;
+ }
+ }
+ }
+
+ *pInfo |= RTL_UNICODETOTEXT_INFO_UNDEFINED;
+ if ( (nFlags & RTL_UNICODETOTEXT_FLAGS_UNDEFINED_MASK) == RTL_UNICODETOTEXT_FLAGS_UNDEFINED_ERROR )
+ {
+ *pInfo |= RTL_UNICODETOTEXT_INFO_ERROR;
+ return false;
+ }
+ else if ( (nFlags & RTL_UNICODETOTEXT_FLAGS_UNDEFINED_MASK) == RTL_UNICODETOTEXT_FLAGS_UNDEFINED_IGNORE )
+ (*ppSrcBuf)++;
+ else if (ImplGetUndefinedAsciiMultiByte(nFlags,
+ *ppDestBuf,
+ pEndDestBuf - *ppDestBuf))
+ {
+ ++*ppSrcBuf;
+ ++*ppDestBuf;
+ }
+ else
+ {
+ *pInfo |= RTL_UNICODETOTEXT_INFO_ERROR
+ | RTL_UNICODETOTEXT_INFO_DESTBUFFERTOSMALL;
+ return false;
+ }
+
+ return true;
+}
diff --git a/sal/textenc/handleundefinedunicodetotextchar.hxx b/sal/textenc/handleundefinedunicodetotextchar.hxx
new file mode 100644
index 0000000..a3a3c32
--- /dev/null
+++ b/sal/textenc/handleundefinedunicodetotextchar.hxx
@@ -0,0 +1,50 @@
+/* -*- Mode: C++; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 4 -*- */
+/*
+ * Version: MPL 1.1 / GPLv3+ / LGPLv3+
+ *
+ * The contents of this file are subject to the Mozilla Public License Version
+ * 1.1 (the "License"); you may not use this file except in compliance with
+ * the License or as specified alternatively below. You may obtain a copy of
+ * the License at http://www.mozilla.org/MPL/
+ *
+ * Software distributed under the License is distributed on an "AS IS" basis,
+ * WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
+ * for the specific language governing rights and limitations under the
+ * License.
+ *
+ * Major Contributor(s):
+ * [ Copyright (C) 2012 Red Hat, Inc., Stephan Bergmann <sbergman at redhat.com>
+ * (initial developer) ]
+ *
+ * All Rights Reserved.
+ *
+ * For minor contributions see the git repository.
+ *
+ * Alternatively, the contents of this file may be used under the terms of
+ * either the GNU General Public License Version 3 or later (the "GPLv3+"), or
+ * the GNU Lesser General Public License Version 3 or later (the "LGPLv3+"),
+ * in which case the provisions of the GPLv3+ or the LGPLv3+ are applicable
+ * instead of those above.
+ */
+
+#ifndef INCLUDED_SAL_TEXTENC_HANDLEUNDEFINEDUNICODETOTEXTCHAR_HXX
+#define INCLUDED_SAL_TEXTENC_HANDLEUNDEFINEDUNICODETOTEXTCHAR_HXX
+
+#include "sal/config.h"
+
+#include "sal/saldllapi.h"
+#include "sal/types.h"
+
+// Internal, non-stable ABI
+
+namespace sal { namespace detail { namespace textenc {
+
+// True means "continue," false means "break:"
+bool SAL_DLLPUBLIC handleUndefinedUnicodeToTextChar(
+ sal_Unicode const ** ppSrcBuf, sal_Unicode const * pEndSrcBuf,
+ char ** ppDestBuf, char const * pEndDestBuf, sal_uInt32 nFlags,
+ sal_uInt32 * pInfo);
+
+} } }
+
+#endif
diff --git a/sal/textenc/tcvtbyte.cxx b/sal/textenc/tcvtbyte.cxx
index b8d78c5..4861daf 100644
--- a/sal/textenc/tcvtbyte.cxx
+++ b/sal/textenc/tcvtbyte.cxx
@@ -30,6 +30,7 @@
#include "rtl/textcvt.h"
+#include "handleundefinedunicodetotextchar.hxx"
#include "tcvtbyte.hxx"
#include "tenchelp.hxx"
@@ -69,7 +70,7 @@ sal_Size ImplSymbolToUnicode( const void*,
return (nDestChars - (pEndDestBuf-pDestBuf));
}
-sal_Size ImplUnicodeToSymbol( const void* pData,
+sal_Size ImplUnicodeToSymbol( const void*,
void*,
const sal_Unicode* pSrcBuf, sal_Size nSrcChars,
char* pDestBuf, sal_Size nDestBytes,
@@ -117,13 +118,9 @@ sal_Size ImplUnicodeToSymbol( const void* pData,
/* Handle undefined and surrogates characters */
/* (all surrogates characters are undefined) */
- if (!ImplHandleUndefinedUnicodeToTextChar(pData,
- &pSrcBuf,
- pEndSrcBuf,
- &pDestBuf,
- pEndDestBuf,
- nFlags,
- pInfo))
+ if (!sal::detail::textenc::handleUndefinedUnicodeToTextChar(
+ &pSrcBuf, pEndSrcBuf, &pDestBuf, pEndDestBuf, nFlags,
+ pInfo))
break;
}
}
diff --git a/sal/textenc/tcvtmb.cxx b/sal/textenc/tcvtmb.cxx
index e968bee..40bb909 100644
--- a/sal/textenc/tcvtmb.cxx
+++ b/sal/textenc/tcvtmb.cxx
@@ -30,6 +30,7 @@
#include "rtl/textcvt.h"
+#include "handleundefinedunicodetotextchar.hxx"
#include "tenchelp.hxx"
#include "unichars.hxx"
@@ -336,13 +337,9 @@ sal_Size ImplUnicodeToDBCS( const void* pData, void*,
/* Handle undefined and surrogates characters */
/* (all surrogates characters are undefined) */
- if (ImplHandleUndefinedUnicodeToTextChar(pData,
- &pSrcBuf,
- pEndSrcBuf,
- &pDestBuf,
- pEndDestBuf,
- nFlags,
- pInfo))
+ if (sal::detail::textenc::handleUndefinedUnicodeToTextChar(
+ &pSrcBuf, pEndSrcBuf, &pDestBuf, pEndDestBuf, nFlags,
+ pInfo))
continue;
else
break;
@@ -624,13 +621,9 @@ sal_Size ImplUnicodeToEUCJP( const void* pData,
/* Handle undefined and surrogates characters */
/* (all surrogates characters are undefined) */
- if (ImplHandleUndefinedUnicodeToTextChar(pData,
- &pSrcBuf,
- pEndSrcBuf,
- &pDestBuf,
- pEndDestBuf,
- nFlags,
- pInfo))
+ if (sal::detail::textenc::handleUndefinedUnicodeToTextChar(
+ &pSrcBuf, pEndSrcBuf, &pDestBuf, pEndDestBuf,
+ nFlags, pInfo))
continue;
else
break;
diff --git a/sal/textenc/tenchelp.cxx b/sal/textenc/tenchelp.cxx
deleted file mode 100644
index c76d03d..0000000
--- a/sal/textenc/tenchelp.cxx
+++ /dev/null
@@ -1,216 +0,0 @@
-/* -*- Mode: C++; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 4 -*- */
-/*************************************************************************
- *
- * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
- *
- * Copyright 2000, 2010 Oracle and/or its affiliates.
- *
- * OpenOffice.org - a multi-platform office productivity suite
- *
- * This file is part of OpenOffice.org.
- *
- * OpenOffice.org is free software: you can redistribute it and/or modify
- * it under the terms of the GNU Lesser General Public License version 3
- * only, as published by the Free Software Foundation.
- *
- * OpenOffice.org 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 Lesser General Public License version 3 for more details
- * (a copy is included in the LICENSE file that accompanied this code).
- *
- * You should have received a copy of the GNU Lesser General Public License
- * version 3 along with OpenOffice.org. If not, see
- * <http://www.openoffice.org/license.html>
- * for a copy of the LGPLv3 License.
- *
- ************************************************************************/
-
-#include "sal/config.h"
-
-#include "rtl/textcvt.h"
-#include "sal/types.h"
-
-#include "tenchelp.hxx"
-#include "unichars.hxx"
-
-static bool ImplGetUndefinedAsciiMultiByte(sal_uInt32 nFlags,
- char * pBuf,
- sal_Size nMaxLen);
-
-static bool ImplGetInvalidAsciiMultiByte(sal_uInt32 nFlags,
- char * pBuf,
- sal_Size nMaxLen);
-
-static int ImplIsUnicodeIgnoreChar(sal_Unicode c, sal_uInt32 nFlags);
-
-bool ImplGetUndefinedAsciiMultiByte(sal_uInt32 nFlags,
- char * pBuf,
- sal_Size nMaxLen)
-{
- if (nMaxLen == 0)
- return false;
- switch (nFlags & RTL_UNICODETOTEXT_FLAGS_UNDEFINED_MASK)
- {
- case RTL_UNICODETOTEXT_FLAGS_UNDEFINED_0:
- *pBuf = 0x00;
- break;
-
- case RTL_UNICODETOTEXT_FLAGS_UNDEFINED_QUESTIONMARK:
- default: /* RTL_UNICODETOTEXT_FLAGS_UNDEFINED_DEFAULT */
- *pBuf = 0x3F;
- break;
-
- case RTL_UNICODETOTEXT_FLAGS_UNDEFINED_UNDERLINE:
- *pBuf = 0x5F;
- break;
- }
- return true;
-}
-
-bool ImplGetInvalidAsciiMultiByte(sal_uInt32 nFlags,
- char * pBuf,
- sal_Size nMaxLen)
-{
- if (nMaxLen == 0)
- return false;
- switch (nFlags & RTL_UNICODETOTEXT_FLAGS_UNDEFINED_MASK)
- {
- case RTL_UNICODETOTEXT_FLAGS_INVALID_0:
- *pBuf = 0x00;
- break;
-
- case RTL_UNICODETOTEXT_FLAGS_INVALID_QUESTIONMARK:
- default: /* RTL_UNICODETOTEXT_FLAGS_INVALID_DEFAULT */
- *pBuf = 0x3F;
- break;
-
- case RTL_UNICODETOTEXT_FLAGS_INVALID_UNDERLINE:
- *pBuf = 0x5F;
- break;
- }
- return true;
-}
-
-int ImplIsUnicodeIgnoreChar( sal_Unicode c, sal_uInt32 nFlags )
-{
- return
- ((nFlags & RTL_UNICODETOTEXT_FLAGS_NONSPACING_IGNORE) != 0
- && ImplIsZeroWidth(c))
- || ((nFlags & RTL_UNICODETOTEXT_FLAGS_CONTROL_IGNORE) != 0
- && ImplIsControlOrFormat(c))
- || ((nFlags & RTL_UNICODETOTEXT_FLAGS_PRIVATE_IGNORE) != 0
- && ImplIsPrivateUse(c));
-}
-
-/* ======================================================================= */
-
-sal_Unicode ImplGetUndefinedUnicodeChar(sal_uChar cChar, sal_uInt32 nFlags)
-{
- return ((nFlags & RTL_TEXTTOUNICODE_FLAGS_UNDEFINED_MASK)
- == RTL_TEXTTOUNICODE_FLAGS_UNDEFINED_MAPTOPRIVATE) ?
- RTL_TEXTCVT_BYTE_PRIVATE_START + cChar :
- RTL_TEXTENC_UNICODE_REPLACEMENT_CHARACTER;
-}
-
-/* ----------------------------------------------------------------------- */
-
-bool
-ImplHandleUndefinedUnicodeToTextChar(void const *,
- sal_Unicode const ** ppSrcBuf,
- sal_Unicode const * pEndSrcBuf,
- char ** ppDestBuf,
- char const * pEndDestBuf,
- sal_uInt32 nFlags,
- sal_uInt32 * pInfo)
-{
- sal_Unicode c = **ppSrcBuf;
-
- /* Should the private character map to one byte */
- if ( (c >= RTL_TEXTCVT_BYTE_PRIVATE_START) && (c <= RTL_TEXTCVT_BYTE_PRIVATE_END) )
- {
- if ( nFlags & RTL_UNICODETOTEXT_FLAGS_PRIVATE_MAPTO0 )
- {
- **ppDestBuf = (char)(sal_uChar)(c-RTL_TEXTCVT_BYTE_PRIVATE_START);
- (*ppDestBuf)++;
- (*ppSrcBuf)++;
- return true;
- }
- }
-
- /* Should this character ignored (Private, Non Spacing, Control) */
- if ( ImplIsUnicodeIgnoreChar( c, nFlags ) )
- {
- (*ppSrcBuf)++;
- return true;
- }
-
- /* Surrogates Characters should result in */
- /* one replacement character */
- if (ImplIsHighSurrogate(c))
- {
- if ( *ppSrcBuf == pEndSrcBuf )
- {
- *pInfo |= RTL_UNICODETOTEXT_INFO_ERROR | RTL_UNICODETOTEXT_INFO_SRCBUFFERTOSMALL;
- return false;
- }
-
- c = *((*ppSrcBuf)+1);
- if (ImplIsLowSurrogate(c))
- (*ppSrcBuf)++;
- else
- {
- *pInfo |= RTL_UNICODETOTEXT_INFO_INVALID;
- if ( (nFlags & RTL_UNICODETOTEXT_FLAGS_INVALID_MASK) == RTL_UNICODETOTEXT_FLAGS_INVALID_ERROR )
- {
- *pInfo |= RTL_UNICODETOTEXT_INFO_ERROR;
- return false;
- }
- else if ( (nFlags & RTL_UNICODETOTEXT_FLAGS_INVALID_MASK) == RTL_UNICODETOTEXT_FLAGS_INVALID_IGNORE )
- {
- (*ppSrcBuf)++;
- return true;
- }
- else if (ImplGetInvalidAsciiMultiByte(nFlags,
- *ppDestBuf,
- pEndDestBuf - *ppDestBuf))
- {
- ++*ppSrcBuf;
- ++*ppDestBuf;
- return true;
- }
- else
- {
- *pInfo |= RTL_UNICODETOTEXT_INFO_ERROR
- | RTL_UNICODETOTEXT_INFO_DESTBUFFERTOSMALL;
- return false;
- }
- }
- }
-
- *pInfo |= RTL_UNICODETOTEXT_INFO_UNDEFINED;
- if ( (nFlags & RTL_UNICODETOTEXT_FLAGS_UNDEFINED_MASK) == RTL_UNICODETOTEXT_FLAGS_UNDEFINED_ERROR )
- {
- *pInfo |= RTL_UNICODETOTEXT_INFO_ERROR;
- return false;
- }
- else if ( (nFlags & RTL_UNICODETOTEXT_FLAGS_UNDEFINED_MASK) == RTL_UNICODETOTEXT_FLAGS_UNDEFINED_IGNORE )
- (*ppSrcBuf)++;
- else if (ImplGetUndefinedAsciiMultiByte(nFlags,
- *ppDestBuf,
- pEndDestBuf - *ppDestBuf))
- {
- ++*ppSrcBuf;
- ++*ppDestBuf;
- }
- else
- {
- *pInfo |= RTL_UNICODETOTEXT_INFO_ERROR
- | RTL_UNICODETOTEXT_INFO_DESTBUFFERTOSMALL;
- return false;
- }
-
- return true;
-}
-
-/* vim:set shiftwidth=4 softtabstop=4 expandtab: */
diff --git a/sal/textenc/tenchelp.hxx b/sal/textenc/tenchelp.hxx
index 149a543..381f26a 100644
--- a/sal/textenc/tenchelp.hxx
+++ b/sal/textenc/tenchelp.hxx
@@ -32,9 +32,12 @@
#include "sal/config.h"
#include "rtl/tencinfo.h"
+#include "rtl/textcvt.h"
#include "rtl/textenc.h"
#include "sal/types.h"
+#include "unichars.hxx"
+
#define RTL_TEXTCVT_BYTE_PRIVATE_START 0xF100
#define RTL_TEXTCVT_BYTE_PRIVATE_END 0xF1FF
@@ -199,17 +202,14 @@ struct ImplEUCJPConvertData
/* - TextConverter - HelpFunctions - */
/* --------------------------------- */
-sal_Unicode ImplGetUndefinedUnicodeChar(sal_uChar cChar, sal_uInt32 nFlags);
-
-bool
-ImplHandleUndefinedUnicodeToTextChar(void const * pData,
- sal_Unicode const ** ppSrcBuf,
- sal_Unicode const * pEndSrcBuf,
- char ** ppDestBuf,
- char const * pEndDestBuf,
- sal_uInt32 nFlags,
- sal_uInt32 * pInfo);
- /* true means 'continue,' false means 'break' */
+inline sal_Unicode ImplGetUndefinedUnicodeChar(
+ sal_uChar cChar, sal_uInt32 nFlags)
+{
+ return ((nFlags & RTL_TEXTTOUNICODE_FLAGS_UNDEFINED_MASK)
+ == RTL_TEXTTOUNICODE_FLAGS_UNDEFINED_MAPTOPRIVATE) ?
+ RTL_TEXTCVT_BYTE_PRIVATE_START + cChar :
+ RTL_TEXTENC_UNICODE_REPLACEMENT_CHARACTER;
+}
/* ----------------------------- */
/* - TextConverter - Functions - */
diff --git a/sal/textenc/unichars.cxx b/sal/textenc/unichars.cxx
index 1291fff..65ef19c 100644
--- a/sal/textenc/unichars.cxx
+++ b/sal/textenc/unichars.cxx
@@ -28,20 +28,10 @@
#include "sal/config.h"
-#include <cassert>
-
#include "sal/types.h"
#include "unichars.hxx"
-bool ImplIsNoncharacter(sal_uInt32 nUtf32)
-{
- // All code points that are noncharacters, as of Unicode 3.1.1:
- return (nUtf32 >= 0xFDD0 && nUtf32 <= 0xFDEF)
- || (nUtf32 & 0xFFFF) >= 0xFFFE
- || nUtf32 > 0x10FFFF;
-}
-
bool ImplIsControlOrFormat(sal_uInt32 nUtf32)
{
// All code points of
@@ -86,18 +76,6 @@ bool ImplIsControlOrFormat(sal_uInt32 nUtf32)
|| (nUtf32 >= 0xE0020 && nUtf32 <= 0xE007F);
}
-bool ImplIsHighSurrogate(sal_uInt32 nUtf32)
-{
- // All code points that are high-surrogates, as of Unicode 3.1.1.
- return nUtf32 >= 0xD800 && nUtf32 <= 0xDBFF;
-}
-
-bool ImplIsLowSurrogate(sal_uInt32 nUtf32)
-{
- // All code points that are low-surrogates, as of Unicode 3.1.1.
- return nUtf32 >= 0xDC00 && nUtf32 <= 0xDFFF;
-}
-
bool ImplIsPrivateUse(sal_uInt32 nUtf32)
{
// All code points of
@@ -119,22 +97,4 @@ bool ImplIsZeroWidth(sal_uInt32 nUtf32)
|| nUtf32 == 0xFEFF; // ZEOR WIDTH NO-BREAK SPACE
}
-sal_uInt32 ImplGetHighSurrogate(sal_uInt32 nUtf32)
-{
- assert(nUtf32 >= 0x10000);
- return ((nUtf32 - 0x10000) >> 10) | 0xD800;
-}
-
-sal_uInt32 ImplGetLowSurrogate(sal_uInt32 nUtf32)
-{
- assert(nUtf32 >= 0x10000);
- return ((nUtf32 - 0x10000) & 0x3FF) | 0xDC00;
-}
-
-sal_uInt32 ImplCombineSurrogates(sal_uInt32 nHigh, sal_uInt32 nLow)
-{
- assert(ImplIsHighSurrogate(nHigh) && ImplIsLowSurrogate(nLow));
- return (((nHigh & 0x3FF) << 10) | (nLow & 0x3FF)) + 0x10000;
-}
-
/* vim:set shiftwidth=4 softtabstop=4 expandtab: */
diff --git a/sal/textenc/unichars.hxx b/sal/textenc/unichars.hxx
index b068fff..2b8a3d0 100644
--- a/sal/textenc/unichars.hxx
+++ b/sal/textenc/unichars.hxx
@@ -31,27 +31,51 @@
#include "sal/config.h"
+#include <cassert>
+
#include "sal/types.h"
#define RTL_TEXTENC_UNICODE_REPLACEMENT_CHARACTER 0xFFFD
-bool ImplIsNoncharacter(sal_uInt32 nUtf32);
+inline bool ImplIsNoncharacter(sal_uInt32 nUtf32)
+{
+ return (nUtf32 >= 0xFDD0 && nUtf32 <= 0xFDEF)
+ || (nUtf32 & 0xFFFF) >= 0xFFFE
+ || nUtf32 > 0x10FFFF;
+}
+ // All code points that are noncharacters, as of Unicode 3.1.1.
bool ImplIsControlOrFormat(sal_uInt32 nUtf32);
-bool ImplIsHighSurrogate(sal_uInt32 nUtf32);
+inline bool ImplIsHighSurrogate(sal_uInt32 nUtf32)
+{ return nUtf32 >= 0xD800 && nUtf32 <= 0xDBFF; }
+ // All code points that are high-surrogates, as of Unicode 3.1.1.
-bool ImplIsLowSurrogate(sal_uInt32 nUtf32);
+inline bool ImplIsLowSurrogate(sal_uInt32 nUtf32)
+{ return nUtf32 >= 0xDC00 && nUtf32 <= 0xDFFF; }
+ // All code points that are low-surrogates, as of Unicode 3.1.1.
bool ImplIsPrivateUse(sal_uInt32 nUtf32);
bool ImplIsZeroWidth(sal_uInt32 nUtf32);
-sal_uInt32 ImplGetHighSurrogate(sal_uInt32 nUtf32);
+inline sal_uInt32 ImplGetHighSurrogate(sal_uInt32 nUtf32)
+{
+ assert(nUtf32 >= 0x10000);
+ return ((nUtf32 - 0x10000) >> 10) | 0xD800;
+}
-sal_uInt32 ImplGetLowSurrogate(sal_uInt32 nUtf32);
+inline sal_uInt32 ImplGetLowSurrogate(sal_uInt32 nUtf32)
+{
+ assert(nUtf32 >= 0x10000);
+ return ((nUtf32 - 0x10000) & 0x3FF) | 0xDC00;
+}
-sal_uInt32 ImplCombineSurrogates(sal_uInt32 nHigh, sal_uInt32 nLow);
+inline sal_uInt32 ImplCombineSurrogates(sal_uInt32 nHigh, sal_uInt32 nLow)
+{
+ assert(ImplIsHighSurrogate(nHigh) && ImplIsLowSurrogate(nLow));
+ return (((nHigh & 0x3FF) << 10) | (nLow & 0x3FF)) + 0x10000;
+}
#endif
diff --git a/sal/util/sal.map b/sal/util/sal.map
index 242f4f7..fcbed28 100644
--- a/sal/util/sal.map
+++ b/sal/util/sal.map
@@ -636,10 +636,11 @@ PRIVATE_1.2 { # LibreOffice 3.5
sal_detail_logFormat;
} PRIVATE_1.1;
-PRIVATE_textenc { # LibreOffice 3.6
+PRIVATE_textenc.1 { # LibreOffice 3.6
global:
_ZN3sal6detail7textenc20convertCharToUnicodeEPKvPvPKcmPtmjPjPm;
_ZN3sal6detail7textenc20convertUnicodeToCharEPKvPvPKtmPcmjPjPm;
+ _ZN3sal6detail7textenc32handleUndefinedUnicodeToTextCharEPPKtS3_PPcPKcjPj;
_ZN3sal6detail7textenc37handleBadInputTextToUnicodeConversionEbbcjPPtS2_Pj;
_ZN3sal6detail7textenc37handleBadInputUnicodeToTextConversionEbjjPPcS2_PjPKcmPb;
};
commit 353bed10cf7d41881654b82b0a833da8dff36a69
Author: Stephan Bergmann <sbergman at redhat.com>
Date: Fri Jan 6 12:09:01 2012 +0100
Made textenc/converter cleanly usable by both sal and sal_textenc.
diff --git a/sal/Library_sal_textenc.mk b/sal/Library_sal_textenc.mk
index 27ff5c0..585a485 100644
--- a/sal/Library_sal_textenc.mk
+++ b/sal/Library_sal_textenc.mk
@@ -41,7 +41,6 @@ $(eval $(call gb_Library_add_defs,sal_textenc,\
$(eval $(call gb_Library_add_exception_objects,sal_textenc,\
sal/textenc/context \
sal/textenc/convertbig5hkscs \
- sal/textenc/converter \
sal/textenc/converteuctw \
sal/textenc/convertgb18030 \
sal/textenc/convertiso2022cn \
diff --git a/sal/textenc/convertbig5hkscs.cxx b/sal/textenc/convertbig5hkscs.cxx
index f1e1275..22bf310 100644
--- a/sal/textenc/convertbig5hkscs.cxx
+++ b/sal/textenc/convertbig5hkscs.cxx
@@ -229,19 +229,19 @@ sal_Size ImplConvertBig5HkscsToUnicode(void const * pData,
continue;
bad_input:
- switch (ImplHandleBadInputTextToUnicodeConversion(
+ switch (sal::detail::textenc::handleBadInputTextToUnicodeConversion(
bUndefined, true, 0, nFlags, &pDestBufPtr, pDestBufEnd,
&nInfo))
{
- case IMPL_BAD_INPUT_STOP:
+ case sal::detail::textenc::BAD_INPUT_STOP:
nRow = 0;
break;
- case IMPL_BAD_INPUT_CONTINUE:
+ case sal::detail::textenc::BAD_INPUT_CONTINUE:
nRow = 0;
continue;
- case IMPL_BAD_INPUT_NO_OUTPUT:
+ case sal::detail::textenc::BAD_INPUT_NO_OUTPUT:
goto no_output;
}
break;
@@ -260,16 +260,16 @@ sal_Size ImplConvertBig5HkscsToUnicode(void const * pData,
if ((nFlags & RTL_TEXTTOUNICODE_FLAGS_FLUSH) == 0)
nInfo |= RTL_TEXTTOUNICODE_INFO_SRCBUFFERTOSMALL;
else
- switch (ImplHandleBadInputTextToUnicodeConversion(
+ switch (sal::detail::textenc::handleBadInputTextToUnicodeConversion(
false, true, 0, nFlags, &pDestBufPtr, pDestBufEnd,
&nInfo))
{
- case IMPL_BAD_INPUT_STOP:
- case IMPL_BAD_INPUT_CONTINUE:
+ case sal::detail::textenc::BAD_INPUT_STOP:
+ case sal::detail::textenc::BAD_INPUT_CONTINUE:
nRow = 0;
break;
- case IMPL_BAD_INPUT_NO_OUTPUT:
+ case sal::detail::textenc::BAD_INPUT_NO_OUTPUT:
nInfo |= RTL_TEXTTOUNICODE_INFO_DESTBUFFERTOSMALL;
break;
}
@@ -434,25 +434,19 @@ sal_Size ImplConvertUnicodeToBig5Hkscs(void const * pData,
continue;
bad_input:
- switch (ImplHandleBadInputUnicodeToTextConversion(bUndefined,
- nChar,
- nFlags,
- &pDestBufPtr,
- pDestBufEnd,
- &nInfo,
- NULL,
- 0,
- NULL))
+ switch (sal::detail::textenc::handleBadInputUnicodeToTextConversion(
+ bUndefined, nChar, nFlags, &pDestBufPtr, pDestBufEnd,
+ &nInfo, NULL, 0, NULL))
{
- case IMPL_BAD_INPUT_STOP:
+ case sal::detail::textenc::BAD_INPUT_STOP:
nHighSurrogate = 0;
break;
- case IMPL_BAD_INPUT_CONTINUE:
+ case sal::detail::textenc::BAD_INPUT_CONTINUE:
nHighSurrogate = 0;
continue;
- case IMPL_BAD_INPUT_NO_OUTPUT:
+ case sal::detail::textenc::BAD_INPUT_NO_OUTPUT:
goto no_output;
}
break;
@@ -471,22 +465,16 @@ sal_Size ImplConvertUnicodeToBig5Hkscs(void const * pData,
if ((nFlags & RTL_UNICODETOTEXT_FLAGS_FLUSH) != 0)
nInfo |= RTL_UNICODETOTEXT_INFO_SRCBUFFERTOSMALL;
else
- switch (ImplHandleBadInputUnicodeToTextConversion(false,
- 0,
- nFlags,
- &pDestBufPtr,
- pDestBufEnd,
- &nInfo,
- NULL,
- 0,
- NULL))
+ switch (sal::detail::textenc::handleBadInputUnicodeToTextConversion(
+ false, 0, nFlags, &pDestBufPtr, pDestBufEnd, &nInfo,
+ NULL, 0, NULL))
{
- case IMPL_BAD_INPUT_STOP:
- case IMPL_BAD_INPUT_CONTINUE:
+ case sal::detail::textenc::BAD_INPUT_STOP:
+ case sal::detail::textenc::BAD_INPUT_CONTINUE:
nHighSurrogate = 0;
break;
- case IMPL_BAD_INPUT_NO_OUTPUT:
+ case sal::detail::textenc::BAD_INPUT_NO_OUTPUT:
nInfo |= RTL_UNICODETOTEXT_INFO_DESTBUFFERTOSMALL;
break;
}
diff --git a/sal/textenc/converter.cxx b/sal/textenc/converter.cxx
index cde368c..24ebf48 100644
--- a/sal/textenc/converter.cxx
+++ b/sal/textenc/converter.cxx
@@ -35,7 +35,8 @@
#include "tenchelp.hxx"
#include "unichars.hxx"
-ImplBadInputConversionAction ImplHandleBadInputTextToUnicodeConversion(
+sal::detail::textenc::BadInputConversionAction
+sal::detail::textenc::handleBadInputTextToUnicodeConversion(
bool bUndefined, bool bMultiByte, char cByte, sal_uInt32 nFlags,
sal_Unicode ** pDestBufPtr, sal_Unicode * pDestBufEnd, sal_uInt32 * pInfo)
{
@@ -55,22 +56,22 @@ ImplBadInputConversionAction ImplHandleBadInputTextToUnicodeConversion(
case RTL_TEXTTOUNICODE_FLAGS_MBUNDEFINED_ERROR:
case RTL_TEXTTOUNICODE_FLAGS_INVALID_ERROR:
*pInfo |= RTL_TEXTTOUNICODE_INFO_ERROR;
- return IMPL_BAD_INPUT_STOP;
+ return BAD_INPUT_STOP;
case RTL_TEXTTOUNICODE_FLAGS_UNDEFINED_IGNORE:
case RTL_TEXTTOUNICODE_FLAGS_MBUNDEFINED_IGNORE:
case RTL_TEXTTOUNICODE_FLAGS_INVALID_IGNORE:
- return IMPL_BAD_INPUT_CONTINUE;
+ return BAD_INPUT_CONTINUE;
case RTL_TEXTTOUNICODE_FLAGS_UNDEFINED_MAPTOPRIVATE:
if (*pDestBufPtr != pDestBufEnd)
{
*(*pDestBufPtr)++ = RTL_TEXTCVT_BYTE_PRIVATE_START
| ((sal_uChar) cByte);
- return IMPL_BAD_INPUT_CONTINUE;
+ return BAD_INPUT_CONTINUE;
}
else
- return IMPL_BAD_INPUT_NO_OUTPUT;
+ return BAD_INPUT_NO_OUTPUT;
default: // RTL_TEXTTOUNICODE_FLAGS_UNDEFINED_DEFAULT,
// RTL_TEXTTOUNICODE_FLAGS_MBUNDEFINED_DEFAULT,
@@ -78,23 +79,18 @@ ImplBadInputConversionAction ImplHandleBadInputTextToUnicodeConversion(
if (*pDestBufPtr != pDestBufEnd)
{
*(*pDestBufPtr)++ = RTL_TEXTENC_UNICODE_REPLACEMENT_CHARACTER;
- return IMPL_BAD_INPUT_CONTINUE;
+ return BAD_INPUT_CONTINUE;
}
else
- return IMPL_BAD_INPUT_NO_OUTPUT;
+ return BAD_INPUT_NO_OUTPUT;
}
}
-ImplBadInputConversionAction
-ImplHandleBadInputUnicodeToTextConversion(bool bUndefined,
- sal_uInt32 nUtf32,
- sal_uInt32 nFlags,
- char ** pDestBufPtr,
- char * pDestBufEnd,
- sal_uInt32 * pInfo,
- char const * pPrefix,
- sal_Size nPrefixLen,
- bool * pPrefixWritten)
+sal::detail::textenc::BadInputConversionAction
+sal::detail::textenc::handleBadInputUnicodeToTextConversion(
+ bool bUndefined, sal_uInt32 nUtf32, sal_uInt32 nFlags, char ** pDestBufPtr,
+ char * pDestBufEnd, sal_uInt32 * pInfo, char const * pPrefix,
+ sal_Size nPrefixLen, bool * pPrefixWritten)
{
// TODO! RTL_UNICODETOTEXT_FLAGS_UNDEFINED_REPLACE
// RTL_UNICODETOTEXT_FLAGS_UNDEFINED_REPLACESTR
@@ -129,13 +125,13 @@ ImplHandleBadInputUnicodeToTextConversion(bool bUndefined,
case RTL_UNICODETOTEXT_FLAGS_UNDEFINED_ERROR:
case RTL_UNICODETOTEXT_FLAGS_INVALID_ERROR:
*pInfo |= RTL_UNICODETOTEXT_INFO_ERROR;
- return IMPL_BAD_INPUT_STOP;
+ return BAD_INPUT_STOP;
case RTL_UNICODETOTEXT_FLAGS_UNDEFINED_IGNORE:
case RTL_UNICODETOTEXT_FLAGS_INVALID_IGNORE:
if (pPrefixWritten)
*pPrefixWritten = false;
- return IMPL_BAD_INPUT_CONTINUE;
+ return BAD_INPUT_CONTINUE;
case RTL_UNICODETOTEXT_FLAGS_UNDEFINED_0:
case RTL_UNICODETOTEXT_FLAGS_INVALID_0:
@@ -161,10 +157,10 @@ ImplHandleBadInputUnicodeToTextConversion(bool bUndefined,
*(*pDestBufPtr)++ = cReplace;
if (pPrefixWritten)
*pPrefixWritten = true;
- return IMPL_BAD_INPUT_CONTINUE;
+ return BAD_INPUT_CONTINUE;
}
else
- return IMPL_BAD_INPUT_NO_OUTPUT;
+ return BAD_INPUT_NO_OUTPUT;
}
/* vim:set shiftwidth=4 softtabstop=4 expandtab: */
diff --git a/sal/textenc/converter.hxx b/sal/textenc/converter.hxx
index 50338c2..fc69ee2 100644
--- a/sal/textenc/converter.hxx
+++ b/sal/textenc/converter.hxx
@@ -31,30 +31,32 @@
#include "sal/config.h"
+#include "sal/saldllapi.h"
#include "sal/types.h"
-enum ImplBadInputConversionAction
+// Internal, non-stable ABI
+
+namespace sal { namespace detail { namespace textenc {
+
+enum BadInputConversionAction
{
- IMPL_BAD_INPUT_STOP,
- IMPL_BAD_INPUT_CONTINUE,
- IMPL_BAD_INPUT_NO_OUTPUT
+ BAD_INPUT_STOP,
+ BAD_INPUT_CONTINUE,
+ BAD_INPUT_NO_OUTPUT
};
-ImplBadInputConversionAction
-ImplHandleBadInputTextToUnicodeConversion(
+BadInputConversionAction SAL_DLLPUBLIC
+handleBadInputTextToUnicodeConversion(
bool bUndefined, bool bMultiByte, char cByte, sal_uInt32 nFlags,
sal_Unicode ** pDestBufPtr, sal_Unicode * pDestBufEnd, sal_uInt32 * pInfo);
-ImplBadInputConversionAction
-ImplHandleBadInputUnicodeToTextConversion(bool bUndefined,
- sal_uInt32 nUtf32,
- sal_uInt32 nFlags,
- char ** pDestBufPtr,
- char * pDestBufEnd,
- sal_uInt32 * pInfo,
- char const * pPrefix,
- sal_Size nPrefixLen,
- bool * pPrefixWritten);
+BadInputConversionAction SAL_DLLPUBLIC
+handleBadInputUnicodeToTextConversion(
+ bool bUndefined, sal_uInt32 nUtf32, sal_uInt32 nFlags, char ** pDestBufPtr,
+ char * pDestBufEnd, sal_uInt32 * pInfo, char const * pPrefix,
+ sal_Size nPrefixLen, bool * pPrefixWritten);
+
+} } }
#endif
diff --git a/sal/textenc/converteuctw.cxx b/sal/textenc/converteuctw.cxx
index 09e01d8..0274fc3 100644
--- a/sal/textenc/converteuctw.cxx
+++ b/sal/textenc/converteuctw.cxx
@@ -238,19 +238,19 @@ sal_Size ImplConvertEucTwToUnicode(void const * pData,
}
bad_input:
- switch (ImplHandleBadInputTextToUnicodeConversion(
+ switch (sal::detail::textenc::handleBadInputTextToUnicodeConversion(
bUndefined, true, 0, nFlags, &pDestBufPtr, pDestBufEnd,
&nInfo))
{
- case IMPL_BAD_INPUT_STOP:
+ case sal::detail::textenc::BAD_INPUT_STOP:
eState = IMPL_EUC_TW_TO_UNICODE_STATE_0;
break;
- case IMPL_BAD_INPUT_CONTINUE:
+ case sal::detail::textenc::BAD_INPUT_CONTINUE:
eState = IMPL_EUC_TW_TO_UNICODE_STATE_0;
continue;
- case IMPL_BAD_INPUT_NO_OUTPUT:
+ case sal::detail::textenc::BAD_INPUT_NO_OUTPUT:
goto no_output;
}
break;
@@ -269,16 +269,16 @@ sal_Size ImplConvertEucTwToUnicode(void const * pData,
if ((nFlags & RTL_TEXTTOUNICODE_FLAGS_FLUSH) == 0)
nInfo |= RTL_TEXTTOUNICODE_INFO_SRCBUFFERTOSMALL;
else
- switch (ImplHandleBadInputTextToUnicodeConversion(
+ switch (sal::detail::textenc::handleBadInputTextToUnicodeConversion(
false, true, 0, nFlags, &pDestBufPtr, pDestBufEnd,
&nInfo))
{
- case IMPL_BAD_INPUT_STOP:
- case IMPL_BAD_INPUT_CONTINUE:
+ case sal::detail::textenc::BAD_INPUT_STOP:
+ case sal::detail::textenc::BAD_INPUT_CONTINUE:
eState = IMPL_EUC_TW_TO_UNICODE_STATE_0;
break;
- case IMPL_BAD_INPUT_NO_OUTPUT:
+ case sal::detail::textenc::BAD_INPUT_NO_OUTPUT:
nInfo |= RTL_TEXTTOUNICODE_INFO_DESTBUFFERTOSMALL;
break;
}
@@ -393,25 +393,19 @@ sal_Size ImplConvertUnicodeToEucTw(void const * pData,
continue;
bad_input:
- switch (ImplHandleBadInputUnicodeToTextConversion(bUndefined,
- nChar,
- nFlags,
- &pDestBufPtr,
- pDestBufEnd,
- &nInfo,
- NULL,
- 0,
- NULL))
+ switch (sal::detail::textenc::handleBadInputUnicodeToTextConversion(
+ bUndefined, nChar, nFlags, &pDestBufPtr, pDestBufEnd,
+ &nInfo, NULL, 0, NULL))
{
- case IMPL_BAD_INPUT_STOP:
+ case sal::detail::textenc::BAD_INPUT_STOP:
nHighSurrogate = 0;
break;
- case IMPL_BAD_INPUT_CONTINUE:
+ case sal::detail::textenc::BAD_INPUT_CONTINUE:
nHighSurrogate = 0;
continue;
- case IMPL_BAD_INPUT_NO_OUTPUT:
+ case sal::detail::textenc::BAD_INPUT_NO_OUTPUT:
goto no_output;
}
break;
@@ -430,22 +424,16 @@ sal_Size ImplConvertUnicodeToEucTw(void const * pData,
if ((nFlags & RTL_UNICODETOTEXT_FLAGS_FLUSH) != 0)
nInfo |= RTL_UNICODETOTEXT_INFO_SRCBUFFERTOSMALL;
else
- switch (ImplHandleBadInputUnicodeToTextConversion(false,
- 0,
- nFlags,
- &pDestBufPtr,
- pDestBufEnd,
- &nInfo,
- NULL,
- 0,
- NULL))
+ switch (sal::detail::textenc::handleBadInputUnicodeToTextConversion(
+ false, 0, nFlags, &pDestBufPtr, pDestBufEnd, &nInfo,
+ NULL, 0, NULL))
{
- case IMPL_BAD_INPUT_STOP:
- case IMPL_BAD_INPUT_CONTINUE:
+ case sal::detail::textenc::BAD_INPUT_STOP:
+ case sal::detail::textenc::BAD_INPUT_CONTINUE:
nHighSurrogate = 0;
break;
- case IMPL_BAD_INPUT_NO_OUTPUT:
+ case sal::detail::textenc::BAD_INPUT_NO_OUTPUT:
nInfo |= RTL_UNICODETOTEXT_INFO_DESTBUFFERTOSMALL;
break;
}
diff --git a/sal/textenc/convertgb18030.cxx b/sal/textenc/convertgb18030.cxx
index c2bbdc9..48d742f 100644
--- a/sal/textenc/convertgb18030.cxx
+++ b/sal/textenc/convertgb18030.cxx
@@ -230,19 +230,19 @@ sal_Size ImplConvertGb18030ToUnicode(void const * pData,
continue;
bad_input:
- switch (ImplHandleBadInputTextToUnicodeConversion(
+ switch (sal::detail::textenc::handleBadInputTextToUnicodeConversion(
bUndefined, true, 0, nFlags, &pDestBufPtr, pDestBufEnd,
&nInfo))
{
- case IMPL_BAD_INPUT_STOP:
+ case sal::detail::textenc::BAD_INPUT_STOP:
eState = IMPL_GB_18030_TO_UNICODE_STATE_0;
break;
- case IMPL_BAD_INPUT_CONTINUE:
+ case sal::detail::textenc::BAD_INPUT_CONTINUE:
eState = IMPL_GB_18030_TO_UNICODE_STATE_0;
continue;
- case IMPL_BAD_INPUT_NO_OUTPUT:
+ case sal::detail::textenc::BAD_INPUT_NO_OUTPUT:
goto no_output;
}
break;
@@ -261,16 +261,16 @@ sal_Size ImplConvertGb18030ToUnicode(void const * pData,
if ((nFlags & RTL_TEXTTOUNICODE_FLAGS_FLUSH) == 0)
nInfo |= RTL_TEXTTOUNICODE_INFO_SRCBUFFERTOSMALL;
else
- switch (ImplHandleBadInputTextToUnicodeConversion(
+ switch (sal::detail::textenc::handleBadInputTextToUnicodeConversion(
false, true, 0, nFlags, &pDestBufPtr, pDestBufEnd,
&nInfo))
{
- case IMPL_BAD_INPUT_STOP:
- case IMPL_BAD_INPUT_CONTINUE:
+ case sal::detail::textenc::BAD_INPUT_STOP:
+ case sal::detail::textenc::BAD_INPUT_CONTINUE:
eState = IMPL_GB_18030_TO_UNICODE_STATE_0;
break;
- case IMPL_BAD_INPUT_NO_OUTPUT:
+ case sal::detail::textenc::BAD_INPUT_NO_OUTPUT:
nInfo |= RTL_TEXTTOUNICODE_INFO_DESTBUFFERTOSMALL;
break;
}
@@ -408,25 +408,19 @@ sal_Size ImplConvertUnicodeToGb18030(void const * pData,
continue;
bad_input:
- switch (ImplHandleBadInputUnicodeToTextConversion(bUndefined,
- nChar,
- nFlags,
- &pDestBufPtr,
- pDestBufEnd,
- &nInfo,
- NULL,
- 0,
- NULL))
+ switch (sal::detail::textenc::handleBadInputUnicodeToTextConversion(
+ bUndefined, nChar, nFlags, &pDestBufPtr, pDestBufEnd,
+ &nInfo, NULL, 0, NULL))
{
- case IMPL_BAD_INPUT_STOP:
+ case sal::detail::textenc::BAD_INPUT_STOP:
nHighSurrogate = 0;
break;
- case IMPL_BAD_INPUT_CONTINUE:
+ case sal::detail::textenc::BAD_INPUT_CONTINUE:
nHighSurrogate = 0;
continue;
- case IMPL_BAD_INPUT_NO_OUTPUT:
+ case sal::detail::textenc::BAD_INPUT_NO_OUTPUT:
goto no_output;
}
break;
@@ -445,22 +439,16 @@ sal_Size ImplConvertUnicodeToGb18030(void const * pData,
if ((nFlags & RTL_UNICODETOTEXT_FLAGS_FLUSH) != 0)
nInfo |= RTL_UNICODETOTEXT_INFO_SRCBUFFERTOSMALL;
else
- switch (ImplHandleBadInputUnicodeToTextConversion(false,
- 0,
- nFlags,
- &pDestBufPtr,
- pDestBufEnd,
- &nInfo,
- NULL,
- 0,
- NULL))
+ switch (sal::detail::textenc::handleBadInputUnicodeToTextConversion(
+ false, 0, nFlags, &pDestBufPtr, pDestBufEnd, &nInfo,
+ NULL, 0, NULL))
{
- case IMPL_BAD_INPUT_STOP:
- case IMPL_BAD_INPUT_CONTINUE:
+ case sal::detail::textenc::BAD_INPUT_STOP:
+ case sal::detail::textenc::BAD_INPUT_CONTINUE:
nHighSurrogate = 0;
break;
- case IMPL_BAD_INPUT_NO_OUTPUT:
+ case sal::detail::textenc::BAD_INPUT_NO_OUTPUT:
nInfo |= RTL_UNICODETOTEXT_INFO_DESTBUFFERTOSMALL;
break;
}
diff --git a/sal/textenc/convertiso2022cn.cxx b/sal/textenc/convertiso2022cn.cxx
index 98b9aa1..8241c5b 100644
--- a/sal/textenc/convertiso2022cn.cxx
+++ b/sal/textenc/convertiso2022cn.cxx
@@ -362,21 +362,21 @@ sal_Size ImplConvertIso2022CnToUnicode(void const * pData,
}
bad_input:
- switch (ImplHandleBadInputTextToUnicodeConversion(
+ switch (sal::detail::textenc::handleBadInputTextToUnicodeConversion(
bUndefined, true, 0, nFlags, &pDestBufPtr, pDestBufEnd,
&nInfo))
{
- case IMPL_BAD_INPUT_STOP:
+ case sal::detail::textenc::BAD_INPUT_STOP:
eState = IMPL_ISO_2022_CN_TO_UNICODE_STATE_ASCII;
b116431 = false;
break;
- case IMPL_BAD_INPUT_CONTINUE:
+ case sal::detail::textenc::BAD_INPUT_CONTINUE:
eState = IMPL_ISO_2022_CN_TO_UNICODE_STATE_ASCII;
b116431 = false;
continue;
- case IMPL_BAD_INPUT_NO_OUTPUT:
+ case sal::detail::textenc::BAD_INPUT_NO_OUTPUT:
goto no_output;
}
break;
@@ -395,17 +395,17 @@ sal_Size ImplConvertIso2022CnToUnicode(void const * pData,
if ((nFlags & RTL_TEXTTOUNICODE_FLAGS_FLUSH) == 0)
nInfo |= RTL_TEXTTOUNICODE_INFO_SRCBUFFERTOSMALL;
else
- switch (ImplHandleBadInputTextToUnicodeConversion(
+ switch (sal::detail::textenc::handleBadInputTextToUnicodeConversion(
false, true, 0, nFlags, &pDestBufPtr, pDestBufEnd,
&nInfo))
{
- case IMPL_BAD_INPUT_STOP:
- case IMPL_BAD_INPUT_CONTINUE:
+ case sal::detail::textenc::BAD_INPUT_STOP:
+ case sal::detail::textenc::BAD_INPUT_CONTINUE:
eState = IMPL_ISO_2022_CN_TO_UNICODE_STATE_ASCII;
b116431 = false;
break;
- case IMPL_BAD_INPUT_NO_OUTPUT:
+ case sal::detail::textenc::BAD_INPUT_NO_OUTPUT:
nInfo |= RTL_TEXTTOUNICODE_INFO_DESTBUFFERTOSMALL;
break;
}
@@ -777,27 +777,21 @@ sal_Size ImplConvertUnicodeToIso2022Cn(void const * pData,
continue;
bad_input:
- switch (ImplHandleBadInputUnicodeToTextConversion(bUndefined,
- nChar,
- nFlags,
- &pDestBufPtr,
- pDestBufEnd,
- &nInfo,
- "\x0F", // SI
- bSo ? 1 : 0,
- &bWritten))
+ switch (sal::detail::textenc::handleBadInputUnicodeToTextConversion(
+ bUndefined, nChar, nFlags, &pDestBufPtr, pDestBufEnd,
+ &nInfo, "\x0F" /* SI */, bSo ? 1 : 0, &bWritten))
{
- case IMPL_BAD_INPUT_STOP:
+ case sal::detail::textenc::BAD_INPUT_STOP:
nHighSurrogate = 0;
break;
- case IMPL_BAD_INPUT_CONTINUE:
+ case sal::detail::textenc::BAD_INPUT_CONTINUE:
if (bWritten)
bSo = false;
nHighSurrogate = 0;
continue;
- case IMPL_BAD_INPUT_NO_OUTPUT:
+ case sal::detail::textenc::BAD_INPUT_NO_OUTPUT:
goto no_output;
}
break;
@@ -818,29 +812,22 @@ sal_Size ImplConvertUnicodeToIso2022Cn(void const * pData,
if ((nFlags & RTL_UNICODETOTEXT_FLAGS_FLUSH) != 0)
nInfo |= RTL_UNICODETOTEXT_INFO_SRCBUFFERTOSMALL;
else
- switch (ImplHandleBadInputUnicodeToTextConversion(
- false,
- 0,
- nFlags,
- &pDestBufPtr,
- pDestBufEnd,
- &nInfo,
- "\x0F", // SI
- bSo ? 1 : 0,
- &bWritten))
+ switch (sal::detail::textenc::handleBadInputUnicodeToTextConversion(
+ false, 0, nFlags, &pDestBufPtr, pDestBufEnd, &nInfo,
+ "\x0F" /* SI */, bSo ? 1 : 0, &bWritten))
{
- case IMPL_BAD_INPUT_STOP:
+ case sal::detail::textenc::BAD_INPUT_STOP:
nHighSurrogate = 0;
bFlush = false;
break;
- case IMPL_BAD_INPUT_CONTINUE:
+ case sal::detail::textenc::BAD_INPUT_CONTINUE:
if (bWritten)
bSo = false;
nHighSurrogate = 0;
break;
- case IMPL_BAD_INPUT_NO_OUTPUT:
+ case sal::detail::textenc::BAD_INPUT_NO_OUTPUT:
nInfo |= RTL_UNICODETOTEXT_INFO_DESTBUFFERTOSMALL;
break;
}
diff --git a/sal/textenc/convertiso2022jp.cxx b/sal/textenc/convertiso2022jp.cxx
index f40d6ad..98ede65 100644
--- a/sal/textenc/convertiso2022jp.cxx
+++ b/sal/textenc/convertiso2022jp.cxx
@@ -252,19 +252,19 @@ sal_Size ImplConvertIso2022JpToUnicode(void const * pData,
continue;
bad_input:
- switch (ImplHandleBadInputTextToUnicodeConversion(
+ switch (sal::detail::textenc::handleBadInputTextToUnicodeConversion(
bUndefined, true, 0, nFlags, &pDestBufPtr, pDestBufEnd,
&nInfo))
{
- case IMPL_BAD_INPUT_STOP:
+ case sal::detail::textenc::BAD_INPUT_STOP:
eState = IMPL_ISO_2022_JP_TO_UNICODE_STATE_ASCII;
break;
- case IMPL_BAD_INPUT_CONTINUE:
+ case sal::detail::textenc::BAD_INPUT_CONTINUE:
eState = IMPL_ISO_2022_JP_TO_UNICODE_STATE_ASCII;
continue;
- case IMPL_BAD_INPUT_NO_OUTPUT:
+ case sal::detail::textenc::BAD_INPUT_NO_OUTPUT:
goto no_output;
}
break;
@@ -283,16 +283,16 @@ sal_Size ImplConvertIso2022JpToUnicode(void const * pData,
if ((nFlags & RTL_TEXTTOUNICODE_FLAGS_FLUSH) == 0)
nInfo |= RTL_TEXTTOUNICODE_INFO_SRCBUFFERTOSMALL;
else
- switch (ImplHandleBadInputTextToUnicodeConversion(
+ switch (sal::detail::textenc::handleBadInputTextToUnicodeConversion(
false, true, 0, nFlags, &pDestBufPtr, pDestBufEnd,
&nInfo))
{
- case IMPL_BAD_INPUT_STOP:
- case IMPL_BAD_INPUT_CONTINUE:
+ case sal::detail::textenc::BAD_INPUT_STOP:
+ case sal::detail::textenc::BAD_INPUT_CONTINUE:
eState = IMPL_ISO_2022_JP_TO_UNICODE_STATE_ASCII;
break;
- case IMPL_BAD_INPUT_NO_OUTPUT:
+ case sal::detail::textenc::BAD_INPUT_NO_OUTPUT:
nInfo |= RTL_TEXTTOUNICODE_INFO_DESTBUFFERTOSMALL;
break;
}
@@ -485,28 +485,21 @@ sal_Size ImplConvertUnicodeToIso2022Jp(void const * pData,
continue;
bad_input:
- switch (ImplHandleBadInputUnicodeToTextConversion(
- bUndefined,
- nChar,
- nFlags,
- &pDestBufPtr,
- pDestBufEnd,
- &nInfo,
- "\x1B(B",
- b0208 ? 3 : 0,
- &bWritten))
+ switch (sal::detail::textenc::handleBadInputUnicodeToTextConversion(
+ bUndefined, nChar, nFlags, &pDestBufPtr, pDestBufEnd,
+ &nInfo, "\x1B(B", b0208 ? 3 : 0, &bWritten))
{
- case IMPL_BAD_INPUT_STOP:
+ case sal::detail::textenc::BAD_INPUT_STOP:
nHighSurrogate = 0;
break;
- case IMPL_BAD_INPUT_CONTINUE:
+ case sal::detail::textenc::BAD_INPUT_CONTINUE:
if (bWritten)
b0208 = false;
nHighSurrogate = 0;
continue;
- case IMPL_BAD_INPUT_NO_OUTPUT:
+ case sal::detail::textenc::BAD_INPUT_NO_OUTPUT:
goto no_output;
}
break;
@@ -527,29 +520,22 @@ sal_Size ImplConvertUnicodeToIso2022Jp(void const * pData,
if ((nFlags & RTL_UNICODETOTEXT_FLAGS_FLUSH) != 0)
nInfo |= RTL_UNICODETOTEXT_INFO_SRCBUFFERTOSMALL;
else
- switch (ImplHandleBadInputUnicodeToTextConversion(
- false,
- 0,
- nFlags,
- &pDestBufPtr,
- pDestBufEnd,
- &nInfo,
- "\x1B(B",
- b0208 ? 3 : 0,
- &bWritten))
+ switch (sal::detail::textenc::handleBadInputUnicodeToTextConversion(
+ false, 0, nFlags, &pDestBufPtr, pDestBufEnd, &nInfo,
+ "\x1B(B", b0208 ? 3 : 0, &bWritten))
{
- case IMPL_BAD_INPUT_STOP:
+ case sal::detail::textenc::BAD_INPUT_STOP:
nHighSurrogate = 0;
bFlush = false;
break;
- case IMPL_BAD_INPUT_CONTINUE:
+ case sal::detail::textenc::BAD_INPUT_CONTINUE:
if (bWritten)
b0208 = false;
nHighSurrogate = 0;
break;
- case IMPL_BAD_INPUT_NO_OUTPUT:
+ case sal::detail::textenc::BAD_INPUT_NO_OUTPUT:
nInfo |= RTL_UNICODETOTEXT_INFO_DESTBUFFERTOSMALL;
break;
}
diff --git a/sal/textenc/convertiso2022kr.cxx b/sal/textenc/convertiso2022kr.cxx
index 2e79664..d4e51ea 100644
--- a/sal/textenc/convertiso2022kr.cxx
+++ b/sal/textenc/convertiso2022kr.cxx
@@ -215,19 +215,19 @@ sal_Size ImplConvertIso2022KrToUnicode(void const * pData,
continue;
bad_input:
- switch (ImplHandleBadInputTextToUnicodeConversion(
+ switch (sal::detail::textenc::handleBadInputTextToUnicodeConversion(
bUndefined, true, 0, nFlags, &pDestBufPtr, pDestBufEnd,
&nInfo))
{
- case IMPL_BAD_INPUT_STOP:
+ case sal::detail::textenc::BAD_INPUT_STOP:
eState = IMPL_ISO_2022_KR_TO_UNICODE_STATE_ASCII;
break;
- case IMPL_BAD_INPUT_CONTINUE:
+ case sal::detail::textenc::BAD_INPUT_CONTINUE:
eState = IMPL_ISO_2022_KR_TO_UNICODE_STATE_ASCII;
continue;
- case IMPL_BAD_INPUT_NO_OUTPUT:
+ case sal::detail::textenc::BAD_INPUT_NO_OUTPUT:
goto no_output;
}
break;
@@ -246,16 +246,16 @@ sal_Size ImplConvertIso2022KrToUnicode(void const * pData,
if ((nFlags & RTL_TEXTTOUNICODE_FLAGS_FLUSH) == 0)
nInfo |= RTL_TEXTTOUNICODE_INFO_SRCBUFFERTOSMALL;
else
- switch (ImplHandleBadInputTextToUnicodeConversion(
+ switch (sal::detail::textenc::handleBadInputTextToUnicodeConversion(
false, true, 0, nFlags, &pDestBufPtr, pDestBufEnd,
&nInfo))
{
- case IMPL_BAD_INPUT_STOP:
- case IMPL_BAD_INPUT_CONTINUE:
+ case sal::detail::textenc::BAD_INPUT_STOP:
+ case sal::detail::textenc::BAD_INPUT_CONTINUE:
eState = IMPL_ISO_2022_KR_TO_UNICODE_STATE_ASCII;
break;
- case IMPL_BAD_INPUT_NO_OUTPUT:
+ case sal::detail::textenc::BAD_INPUT_NO_OUTPUT:
nInfo |= RTL_TEXTTOUNICODE_INFO_DESTBUFFERTOSMALL;
break;
}
@@ -443,28 +443,23 @@ sal_Size ImplConvertUnicodeToIso2022Kr(void const * pData,
continue;
bad_input:
- switch (ImplHandleBadInputUnicodeToTextConversion(
- bUndefined,
- nChar,
- nFlags,
- &pDestBufPtr,
- pDestBufEnd,
- &nInfo,
- "\x0F", // SI
+ switch (sal::detail::textenc::handleBadInputUnicodeToTextConversion(
+ bUndefined, nChar, nFlags, &pDestBufPtr, pDestBufEnd,
+ &nInfo, "\x0F" /* SI */,
eSet == IMPL_UNICODE_TO_ISO_2022_KR_SET_ASCII ? 0 : 1,
&bWritten))
{
- case IMPL_BAD_INPUT_STOP:
+ case sal::detail::textenc::BAD_INPUT_STOP:
nHighSurrogate = 0;
break;
- case IMPL_BAD_INPUT_CONTINUE:
+ case sal::detail::textenc::BAD_INPUT_CONTINUE:
if (bWritten)
eSet = IMPL_UNICODE_TO_ISO_2022_KR_SET_ASCII;
nHighSurrogate = 0;
continue;
- case IMPL_BAD_INPUT_NO_OUTPUT:
+ case sal::detail::textenc::BAD_INPUT_NO_OUTPUT:
goto no_output;
}
break;
@@ -485,30 +480,25 @@ sal_Size ImplConvertUnicodeToIso2022Kr(void const * pData,
if ((nFlags & RTL_UNICODETOTEXT_FLAGS_FLUSH) != 0)
nInfo |= RTL_UNICODETOTEXT_INFO_SRCBUFFERTOSMALL;
else
- switch (ImplHandleBadInputUnicodeToTextConversion(
- false,
- 0,
- nFlags,
- &pDestBufPtr,
- pDestBufEnd,
- &nInfo,
- "\x0F", // SI
- eSet == IMPL_UNICODE_TO_ISO_2022_KR_SET_ASCII ?
- 0 : 1,
+ switch (sal::detail::textenc::handleBadInputUnicodeToTextConversion(
+ false, 0, nFlags, &pDestBufPtr, pDestBufEnd, &nInfo,
+ "\x0F" /* SI */,
+ (eSet == IMPL_UNICODE_TO_ISO_2022_KR_SET_ASCII
+ ? 0 : 1),
&bWritten))
{
- case IMPL_BAD_INPUT_STOP:
+ case sal::detail::textenc::BAD_INPUT_STOP:
nHighSurrogate = 0;
bFlush = false;
break;
- case IMPL_BAD_INPUT_CONTINUE:
+ case sal::detail::textenc::BAD_INPUT_CONTINUE:
if (bWritten)
eSet = IMPL_UNICODE_TO_ISO_2022_KR_SET_ASCII;
nHighSurrogate = 0;
break;
- case IMPL_BAD_INPUT_NO_OUTPUT:
+ case sal::detail::textenc::BAD_INPUT_NO_OUTPUT:
nInfo |= RTL_UNICODETOTEXT_INFO_DESTBUFFERTOSMALL;
break;
}
diff --git a/sal/textenc/convertsimple.hxx b/sal/textenc/convertsimple.hxx
index 6fb1042..3f207ea 100644
--- a/sal/textenc/convertsimple.hxx
+++ b/sal/textenc/convertsimple.hxx
@@ -35,15 +35,15 @@
#include "sal/saldllapi.h"
#include "sal/types.h"
+// Internal, non-stable ABI
+
namespace sal { namespace detail { namespace textenc {
-// internal, non-stable ABI
sal_Size SAL_DLLPUBLIC convertCharToUnicode(
void const * pData, void * pContext, char const * pSrcBuf,
sal_Size nSrcBytes, sal_Unicode * pDestBuf, sal_Size nDestChars,
sal_uInt32 nFlags, sal_uInt32 * pInfo, sal_Size * pSrcCvtBytes);
-// internal, non-stable ABI
sal_Size SAL_DLLPUBLIC convertUnicodeToChar(
void const * pData, void * pContext, sal_Unicode const * pSrcBuf,
sal_Size nSrcChars, char * pDestBuf, sal_Size nDestBytes, sal_uInt32 nFlags,
diff --git a/sal/textenc/convertsinglebytetobmpunicode.cxx b/sal/textenc/convertsinglebytetobmpunicode.cxx
index f94eed2..787dee0 100644
--- a/sal/textenc/convertsinglebytetobmpunicode.cxx
+++ b/sal/textenc/convertsinglebytetobmpunicode.cxx
@@ -64,17 +64,17 @@ sal_Size rtl_textenc_convertSingleByteToBmpUnicode(
*destBufPtr++ = c;
continue;
bad_input:
- switch (ImplHandleBadInputTextToUnicodeConversion(
+ switch (sal::detail::textenc::handleBadInputTextToUnicodeConversion(
undefined, false, b, flags, &destBufPtr, destBufEnd,
&infoFlags))
{
- case IMPL_BAD_INPUT_STOP:
+ case sal::detail::textenc::BAD_INPUT_STOP:
break;
- case IMPL_BAD_INPUT_CONTINUE:
+ case sal::detail::textenc::BAD_INPUT_CONTINUE:
continue;
- case IMPL_BAD_INPUT_NO_OUTPUT:
+ case sal::detail::textenc::BAD_INPUT_NO_OUTPUT:
goto no_output;
}
break;
@@ -152,19 +152,19 @@ sal_Size rtl_textenc_convertBmpUnicodeToSingleByte(
highSurrogate = 0;
continue;
bad_input:
- switch (ImplHandleBadInputUnicodeToTextConversion(
+ switch (sal::detail::textenc::handleBadInputUnicodeToTextConversion(
undefined, c, flags, &destBufPtr, destBufEnd, &infoFlags, 0,
0, 0))
{
- case IMPL_BAD_INPUT_STOP:
+ case sal::detail::textenc::BAD_INPUT_STOP:
highSurrogate = 0;
break;
- case IMPL_BAD_INPUT_CONTINUE:
+ case sal::detail::textenc::BAD_INPUT_CONTINUE:
highSurrogate = 0;
continue;
- case IMPL_BAD_INPUT_NO_OUTPUT:
+ case sal::detail::textenc::BAD_INPUT_NO_OUTPUT:
goto no_output;
}
break;
@@ -182,16 +182,16 @@ sal_Size rtl_textenc_convertBmpUnicodeToSingleByte(
if ((flags & RTL_UNICODETOTEXT_FLAGS_FLUSH) != 0) {
infoFlags |= RTL_UNICODETOTEXT_INFO_SRCBUFFERTOSMALL;
} else {
- switch (ImplHandleBadInputUnicodeToTextConversion(
+ switch (sal::detail::textenc::handleBadInputUnicodeToTextConversion(
false, 0, flags, &destBufPtr, destBufEnd, &infoFlags, 0,
0, 0))
{
- case IMPL_BAD_INPUT_STOP:
- case IMPL_BAD_INPUT_CONTINUE:
+ case sal::detail::textenc::BAD_INPUT_STOP:
+ case sal::detail::textenc::BAD_INPUT_CONTINUE:
highSurrogate = 0;
break;
- case IMPL_BAD_INPUT_NO_OUTPUT:
+ case sal::detail::textenc::BAD_INPUT_NO_OUTPUT:
infoFlags |= RTL_UNICODETOTEXT_INFO_DESTBUFFERTOSMALL;
break;
}
diff --git a/sal/textenc/tcvtutf8.cxx b/sal/textenc/tcvtutf8.cxx
index 1e41da2..efa0e8d 100644
--- a/sal/textenc/tcvtutf8.cxx
+++ b/sal/textenc/tcvtutf8.cxx
@@ -191,25 +191,25 @@ sal_Size ImplConvertUtf8ToUnicode(
continue;
bad_input:
- switch (ImplHandleBadInputTextToUnicodeConversion(
+ switch (sal::detail::textenc::handleBadInputTextToUnicodeConversion(
bUndefined, true, 0, nFlags, &pDestBufPtr, pDestBufEnd,
&nInfo))
{
- case IMPL_BAD_INPUT_STOP:
+ case sal::detail::textenc::BAD_INPUT_STOP:
nShift = -1;
bCheckBom = false;
if (!bConsume)
--pSrcBufPtr;
break;
- case IMPL_BAD_INPUT_CONTINUE:
+ case sal::detail::textenc::BAD_INPUT_CONTINUE:
nShift = -1;
bCheckBom = false;
if (!bConsume)
--pSrcBufPtr;
continue;
- case IMPL_BAD_INPUT_NO_OUTPUT:
+ case sal::detail::textenc::BAD_INPUT_NO_OUTPUT:
goto no_output;
}
break;
@@ -228,17 +228,17 @@ sal_Size ImplConvertUtf8ToUnicode(
if ((nFlags & RTL_TEXTTOUNICODE_FLAGS_FLUSH) == 0)
nInfo |= RTL_TEXTTOUNICODE_INFO_SRCBUFFERTOSMALL;
else
- switch (ImplHandleBadInputTextToUnicodeConversion(
+ switch (sal::detail::textenc::handleBadInputTextToUnicodeConversion(
false, true, 0, nFlags, &pDestBufPtr, pDestBufEnd,
&nInfo))
{
- case IMPL_BAD_INPUT_STOP:
- case IMPL_BAD_INPUT_CONTINUE:
+ case sal::detail::textenc::BAD_INPUT_STOP:
+ case sal::detail::textenc::BAD_INPUT_CONTINUE:
nShift = -1;
bCheckBom = false;
break;
- case IMPL_BAD_INPUT_NO_OUTPUT:
+ case sal::detail::textenc::BAD_INPUT_NO_OUTPUT:
nInfo |= RTL_TEXTTOUNICODE_INFO_DESTBUFFERTOSMALL;
break;
}
@@ -368,20 +368,19 @@ sal_Size ImplConvertUnicodeToUtf8(
continue;
bad_input:
- switch (ImplHandleBadInputUnicodeToTextConversion(false, 0, nFlags,
- &pDestBufPtr,
- pDestBufEnd, &nInfo,
- NULL, 0, NULL))
+ switch (sal::detail::textenc::handleBadInputUnicodeToTextConversion(
+ false, 0, nFlags, &pDestBufPtr, pDestBufEnd, &nInfo, NULL,
+ 0, NULL))
{
- case IMPL_BAD_INPUT_STOP:
+ case sal::detail::textenc::BAD_INPUT_STOP:
nHighSurrogate = 0;
break;
- case IMPL_BAD_INPUT_CONTINUE:
+ case sal::detail::textenc::BAD_INPUT_CONTINUE:
nHighSurrogate = 0;
continue;
- case IMPL_BAD_INPUT_NO_OUTPUT:
+ case sal::detail::textenc::BAD_INPUT_NO_OUTPUT:
goto no_output;
}
break;
@@ -400,18 +399,16 @@ sal_Size ImplConvertUnicodeToUtf8(
if ((nFlags & RTL_UNICODETOTEXT_FLAGS_FLUSH) != 0)
nInfo |= RTL_UNICODETOTEXT_INFO_SRCBUFFERTOSMALL;
else
- switch (ImplHandleBadInputUnicodeToTextConversion(false, 0, nFlags,
- &pDestBufPtr,
- pDestBufEnd,
- &nInfo, NULL, 0,
- NULL))
+ switch (sal::detail::textenc::handleBadInputUnicodeToTextConversion(
+ false, 0, nFlags, &pDestBufPtr, pDestBufEnd, &nInfo,
+ NULL, 0, NULL))
{
- case IMPL_BAD_INPUT_STOP:
- case IMPL_BAD_INPUT_CONTINUE:
+ case sal::detail::textenc::BAD_INPUT_STOP:
+ case sal::detail::textenc::BAD_INPUT_CONTINUE:
nHighSurrogate = 0;
break;
- case IMPL_BAD_INPUT_NO_OUTPUT:
+ case sal::detail::textenc::BAD_INPUT_NO_OUTPUT:
nInfo |= RTL_UNICODETOTEXT_INFO_DESTBUFFERTOSMALL;
break;
}
diff --git a/sal/util/sal.map b/sal/util/sal.map
index 2939433..242f4f7 100644
--- a/sal/util/sal.map
+++ b/sal/util/sal.map
@@ -640,6 +640,8 @@ PRIVATE_textenc { # LibreOffice 3.6
global:
_ZN3sal6detail7textenc20convertCharToUnicodeEPKvPvPKcmPtmjPjPm;
_ZN3sal6detail7textenc20convertUnicodeToCharEPKvPvPKtmPcmjPjPm;
+ _ZN3sal6detail7textenc37handleBadInputTextToUnicodeConversionEbbcjPPtS2_Pj;
+ _ZN3sal6detail7textenc37handleBadInputUnicodeToTextConversionEbjjPPcS2_PjPKcmPb;
};
# Unique libstdc++ symbols:
commit 5689b61ac9eac4d4be2d6aa378b732a5eae4784a
Author: Stephan Bergmann <sbergman at redhat.com>
Date: Fri Jan 6 11:48:13 2012 +0100
Extracted convertsimple (used by sal and sal_textenc) from tcvtbyte.
diff --git a/sal/Library_sal.mk b/sal/Library_sal.mk
index d7e65ad..c43013c 100644
--- a/sal/Library_sal.mk
+++ b/sal/Library_sal.mk
@@ -120,7 +120,7 @@ $(eval $(call gb_Library_add_exception_objects,sal,\
sal/rtl/source/ustring \
sal/rtl/source/uuid \
sal/textenc/converter \
- sal/textenc/tcvtbyte \
+ sal/textenc/convertsimple \
sal/textenc/tcvtutf8 \
sal/textenc/tenchelp \
sal/textenc/tencinfo \
diff --git a/sal/textenc/convertbig5hkscs.tab b/sal/textenc/convertbig5hkscs.tab
index bcd4748..b308515 100644
--- a/sal/textenc/convertbig5hkscs.tab
+++ b/sal/textenc/convertbig5hkscs.tab
@@ -32,8 +32,8 @@
#include "context.hxx"
#include "convertbig5hkscs.hxx"
-
#include "generate/big5hkscs2001.tab"
+#include "tenchelp.hxx"
static ImplBig5HkscsConverterData const aImplBig5HkscsConvertData
= { aImplBig5Hkscs2001ToUnicodeData,
diff --git a/sal/textenc/convertiscii.tab b/sal/textenc/convertiscii.tab
index 57e5bbd..b6506d7 100644
--- a/sal/textenc/convertiscii.tab
+++ b/sal/textenc/convertiscii.tab
@@ -32,6 +32,7 @@
#include "rtl/tencinfo.h"
#include "sal/types.h"
+#include "convertsimple.hxx"
#include "tenchelp.hxx"
/* Conversion tables for the Devanagari version of ISCII (IS 13194:1991).
@@ -97,8 +98,8 @@ static ImplByteConvertData const aImplIsciiDevanagariConvertData
static ImplTextEncodingData const aImplIsciiDevanagariTextEncodingData
= { { &aImplIsciiDevanagariConvertData,
- &ImplCharToUnicode,
- &ImplUnicodeToChar,
+ &sal::detail::textenc::convertCharToUnicode,
+ &sal::detail::textenc::convertUnicodeToChar,
NULL,
NULL,
NULL,
diff --git a/sal/textenc/convertsimple.cxx b/sal/textenc/convertsimple.cxx
new file mode 100644
index 0000000..24a4ad6
--- /dev/null
+++ b/sal/textenc/convertsimple.cxx
@@ -0,0 +1,688 @@
+/* -*- Mode: C++; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 4 -*- */
+/*
+ * Version: MPL 1.1 / GPLv3+ / LGPLv3+
+ *
+ * The contents of this file are subject to the Mozilla Public License Version
+ * 1.1 (the "License"); you may not use this file except in compliance with
+ * the License or as specified alternatively below. You may obtain a copy of
+ * the License at http://www.mozilla.org/MPL/
+ *
+ * Software distributed under the License is distributed on an "AS IS" basis,
+ * WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
+ * for the specific language governing rights and limitations under the
+ * License.
+ *
+ * Major Contributor(s):
+ * [ Copyright (C) 2012 Red Hat, Inc., Stephan Bergmann <sbergman at redhat.com>
+ * (initial developer) ]
+ *
+ * All Rights Reserved.
+ *
+ * For minor contributions see the git repository.
+ *
+ * Alternatively, the contents of this file may be used under the terms of
+ * either the GNU General Public License Version 3 or later (the "GPLv3+"), or
+ * the GNU Lesser General Public License Version 3 or later (the "LGPLv3+"),
+ * in which case the provisions of the GPLv3+ or the LGPLv3+ are applicable
+ * instead of those above.
+ */
+
+#include "sal/config.h"
+
+#include "rtl/textcvt.h"
+#include "sal/types.h"
+
+#include "convertsimple.hxx"
+#include "tenchelp.hxx"
+
+#define IMPL_MAX_REPLACECHAR 5
+
+namespace {
+
+struct ImplReplaceCharData
+{
+ sal_uInt16 mnUniChar;
+ sal_uInt16 mnReplaceChar;
+};
+
+static ImplReplaceCharData const aImplRepCharTab[] =
+{
+ { 0x00A0, 0x0020 }, /* NO-BREAK-SPACE */
+ { 0x00A1, 0x0021 }, /* INVERTED EXCLAMATION MARK */
+ { 0x00B7, 0x0045 }, /* MIDDLE DOT */
+ { 0x00BF, 0x003F }, /* INVERTED QUESTION MARK */
+ { 0x00D7, 0x002A }, /* MULTIPLIKATION SIGN */
+ { 0x00F7, 0x002F }, /* DIVISION SIGN */
+ { 0x2000, 0x0020 }, /* EN QUAD */
+ { 0x2001, 0x0020 }, /* EM QUAD */
+ { 0x2002, 0x0020 }, /* EN SPACE */
+ { 0x2003, 0x0020 }, /* EM SPACE */
+ { 0x2004, 0x0020 }, /* THREE-PER-EM SPACE */
+ { 0x2005, 0x0020 }, /* FOUR-PER-EM SPACE */
+ { 0x2006, 0x0020 }, /* SIX-PER-EM SPACE */
+ { 0x2007, 0x0020 }, /* FIGURE SPACE */
+ { 0x2008, 0x0020 }, /* PUNCTATION SPACE */
+ { 0x2009, 0x0020 }, /* THIN SPACE */
+ { 0x200A, 0x0020 }, /* HAIR SPACE */
+ { 0x2010, 0x002D }, /* HYPHEN */
+ { 0x2011, 0x002D }, /* NON-BREAKING HYPHEN */
+ { 0x2012, 0x002D }, /* FIGURE DASH */
+ { 0x2013, 0x002D }, /* EN DASH */
+ { 0x2014, 0x002D }, /* EM DASH */
+ { 0x2015, 0x002D }, /* HORIZONTAL BAR */
+ { 0x2018, 0x0027 }, /* LEFT SINGLE QUOTATION MARK */
+ { 0x2019, 0x0027 }, /* RIGHT SINGLE QUOTATION MARK */
+ { 0x201A, 0x002C }, /* SINGLE LOW-9 QUOTATION MARK */
+ { 0x201B, 0x0027 }, /* SINGLE HIGH-RESERVED-9 QUOTATION MARK */
+ { 0x201C, 0x0022 }, /* LEFT DOUBLE QUOTATION MARK */
+ { 0x201D, 0x0022 }, /* RIGHT DOUBLE QUOTATION MARK */
+ { 0x201E, 0x0022 }, /* DOUBLE LOW-9 QUOTATION MARK */
+ { 0x201F, 0x0022 }, /* DOUBLE HIGH-RESERVED-9 QUOTATION MARK */
+ { 0x2022, 0x002D }, /* BULLET */
+ { 0x2023, 0x002D }, /* TRIANGULAR BULLET */
+ { 0x2024, 0x002D }, /* ONE DOT LEADER */
+ { 0x2027, 0x002D }, /* HYPHENATION POINT */
+ { 0x2028, 0x000A }, /* LINE SEPARATOR */
+ { 0x2029, 0x000D }, /* PARAGRAPH SEPARATOR */
+ { 0x2032, 0x0027 }, /* PRIME */
+ { 0x2033, 0x0022 }, /* DOUBLE PRIME */
+ { 0x2035, 0x0027 }, /* RESERVED PRIME */
+ { 0x2036, 0x0022 }, /* RESERVED DOUBLE PRIME */
+ { 0x2039, 0x003C }, /* SINGLE LEFT-POINTING ANGLE QUOTATION MARK */
+ { 0x203A, 0x003E }, /* SINGLE RIGHT-POINTING ANGLE QUOTATION MARK */
+ { 0x2043, 0x002D }, /* HYPHEN BULLET */
+ { 0x2044, 0x002F }, /* FRACTION SLASH */
+ { 0x2160, 0x0049 }, /* ROMAN NUMERAL ONE */
+ { 0x2164, 0x0056 }, /* ROMAN NUMERAL FIVE */
+ { 0x2169, 0x0058 }, /* ROMAN NUMERAL TEN */
+ { 0x216C, 0x004C }, /* ROMAN NUMERAL FIFTY */
+ { 0x216D, 0x0043 }, /* ROMAN NUMERAL ONE HUNDRED */
+ { 0x216E, 0x0044 }, /* ROMAN NUMERAL FIVE HUNDRED */
+ { 0x216F, 0x004D }, /* ROMAN NUMERAL ONE THOUSAND */
+ { 0x2170, 0x0069 }, /* SMALL ROMAN NUMERAL ONE */
+ { 0x2174, 0x0076 }, /* SMALL ROMAN NUMERAL FIVE */
+ { 0x2179, 0x0078 }, /* SMALL ROMAN NUMERAL TEN */
+ { 0x217C, 0x006C }, /* SMALL ROMAN NUMERAL FIFTY */
+ { 0x217D, 0x0063 }, /* SMALL ROMAN NUMERAL ONE HUNDRED */
+ { 0x217E, 0x0064 }, /* SMALL ROMAN NUMERAL FIVE HUNDRED */
+ { 0x217F, 0x006D }, /* SMALL ROMAN NUMERAL ONE THOUSAND */
+ { 0x2215, 0x002F }, /* DIVISION SLASH */
+ { 0x2217, 0x002A }, /* ASTERIX OPERATOR */
+ { 0xFF00, 0x0020 }, /* FULLWIDTH ASCII FORMS */
+ { 0xFF01, 0x0021 }, /* FULLWIDTH ASCII FORMS */
+ { 0xFF02, 0x0022 }, /* FULLWIDTH ASCII FORMS*/
+ { 0xFF03, 0x0023 }, /* FULLWIDTH ASCII FORMS */
+ { 0xFF04, 0x0024 }, /* FULLWIDTH ASCII FORMS*/
+ { 0xFF05, 0x0025 }, /* FULLWIDTH ASCII FORMS */
+ { 0xFF06, 0x0026 }, /* FULLWIDTH ASCII FORMS*/
+ { 0xFF07, 0x0027 }, /* FULLWIDTH ASCII FORMS */
+ { 0xFF08, 0x0028 }, /* FULLWIDTH ASCII FORMS*/
+ { 0xFF09, 0x0029 }, /* FULLWIDTH ASCII FORMS */
+ { 0xFF0A, 0x002A }, /* FULLWIDTH ASCII FORMS*/
+ { 0xFF0B, 0x002B }, /* FULLWIDTH ASCII FORMS */
+ { 0xFF0C, 0x002C }, /* FULLWIDTH ASCII FORMS*/
+ { 0xFF0D, 0x002D }, /* FULLWIDTH ASCII FORMS */
+ { 0xFF0E, 0x002E }, /* FULLWIDTH ASCII FORMS*/
+ { 0xFF0F, 0x002F }, /* FULLWIDTH ASCII FORMS */
+ { 0xFF10, 0x0030 }, /* FULLWIDTH ASCII FORMS */
+ { 0xFF11, 0x0031 }, /* FULLWIDTH ASCII FORMS */
+ { 0xFF12, 0x0032 }, /* FULLWIDTH ASCII FORMS*/
+ { 0xFF13, 0x0033 }, /* FULLWIDTH ASCII FORMS */
+ { 0xFF14, 0x0034 }, /* FULLWIDTH ASCII FORMS*/
+ { 0xFF15, 0x0035 }, /* FULLWIDTH ASCII FORMS */
+ { 0xFF16, 0x0036 }, /* FULLWIDTH ASCII FORMS*/
+ { 0xFF17, 0x0037 }, /* FULLWIDTH ASCII FORMS */
+ { 0xFF18, 0x0038 }, /* FULLWIDTH ASCII FORMS*/
+ { 0xFF19, 0x0039 }, /* FULLWIDTH ASCII FORMS */
+ { 0xFF1A, 0x003A }, /* FULLWIDTH ASCII FORMS*/
+ { 0xFF1B, 0x003B }, /* FULLWIDTH ASCII FORMS */
+ { 0xFF1C, 0x003C }, /* FULLWIDTH ASCII FORMS*/
+ { 0xFF1D, 0x003D }, /* FULLWIDTH ASCII FORMS */
+ { 0xFF1E, 0x003E }, /* FULLWIDTH ASCII FORMS*/
+ { 0xFF1F, 0x003F }, /* FULLWIDTH ASCII FORMS */
+ { 0xFF20, 0x0040 }, /* FULLWIDTH ASCII FORMS */
+ { 0xFF21, 0x0041 }, /* FULLWIDTH ASCII FORMS */
+ { 0xFF22, 0x0042 }, /* FULLWIDTH ASCII FORMS*/
+ { 0xFF23, 0x0043 }, /* FULLWIDTH ASCII FORMS */
+ { 0xFF24, 0x0044 }, /* FULLWIDTH ASCII FORMS*/
+ { 0xFF25, 0x0045 }, /* FULLWIDTH ASCII FORMS */
+ { 0xFF26, 0x0046 }, /* FULLWIDTH ASCII FORMS*/
+ { 0xFF27, 0x0047 }, /* FULLWIDTH ASCII FORMS */
+ { 0xFF28, 0x0048 }, /* FULLWIDTH ASCII FORMS*/
+ { 0xFF29, 0x0049 }, /* FULLWIDTH ASCII FORMS */
+ { 0xFF2A, 0x004A }, /* FULLWIDTH ASCII FORMS*/
+ { 0xFF2B, 0x004B }, /* FULLWIDTH ASCII FORMS */
+ { 0xFF2C, 0x004C }, /* FULLWIDTH ASCII FORMS*/
+ { 0xFF2D, 0x004D }, /* FULLWIDTH ASCII FORMS */
+ { 0xFF2E, 0x004E }, /* FULLWIDTH ASCII FORMS*/
+ { 0xFF2F, 0x004F }, /* FULLWIDTH ASCII FORMS */
+ { 0xFF30, 0x0050 }, /* FULLWIDTH ASCII FORMS */
+ { 0xFF31, 0x0051 }, /* FULLWIDTH ASCII FORMS */
+ { 0xFF32, 0x0052 }, /* FULLWIDTH ASCII FORMS*/
+ { 0xFF33, 0x0053 }, /* FULLWIDTH ASCII FORMS */
+ { 0xFF34, 0x0054 }, /* FULLWIDTH ASCII FORMS*/
+ { 0xFF35, 0x0055 }, /* FULLWIDTH ASCII FORMS */
+ { 0xFF36, 0x0056 }, /* FULLWIDTH ASCII FORMS*/
+ { 0xFF37, 0x0057 }, /* FULLWIDTH ASCII FORMS */
+ { 0xFF38, 0x0058 }, /* FULLWIDTH ASCII FORMS*/
+ { 0xFF39, 0x0059 }, /* FULLWIDTH ASCII FORMS */
+ { 0xFF3A, 0x005A }, /* FULLWIDTH ASCII FORMS*/
+ { 0xFF3B, 0x005B }, /* FULLWIDTH ASCII FORMS */
+ { 0xFF3C, 0x005C }, /* FULLWIDTH ASCII FORMS*/
+ { 0xFF3D, 0x005D }, /* FULLWIDTH ASCII FORMS */
+ { 0xFF3E, 0x005E }, /* FULLWIDTH ASCII FORMS*/
+ { 0xFF3F, 0x005F }, /* FULLWIDTH ASCII FORMS */
+ { 0xFF40, 0x0060 }, /* FULLWIDTH ASCII FORMS */
+ { 0xFF41, 0x0061 }, /* FULLWIDTH ASCII FORMS */
+ { 0xFF42, 0x0062 }, /* FULLWIDTH ASCII FORMS*/
+ { 0xFF43, 0x0063 }, /* FULLWIDTH ASCII FORMS */
+ { 0xFF44, 0x0064 }, /* FULLWIDTH ASCII FORMS*/
+ { 0xFF45, 0x0065 }, /* FULLWIDTH ASCII FORMS */
+ { 0xFF46, 0x0066 }, /* FULLWIDTH ASCII FORMS*/
+ { 0xFF47, 0x0067 }, /* FULLWIDTH ASCII FORMS */
+ { 0xFF48, 0x0068 }, /* FULLWIDTH ASCII FORMS*/
+ { 0xFF49, 0x0069 }, /* FULLWIDTH ASCII FORMS */
+ { 0xFF4A, 0x006A }, /* FULLWIDTH ASCII FORMS*/
+ { 0xFF4B, 0x006B }, /* FULLWIDTH ASCII FORMS */
+ { 0xFF4C, 0x006C }, /* FULLWIDTH ASCII FORMS*/
+ { 0xFF4D, 0x006D }, /* FULLWIDTH ASCII FORMS */
+ { 0xFF4E, 0x006E }, /* FULLWIDTH ASCII FORMS*/
+ { 0xFF4F, 0x006F }, /* FULLWIDTH ASCII FORMS */
+ { 0xFF50, 0x0070 }, /* FULLWIDTH ASCII FORMS */
+ { 0xFF51, 0x0071 }, /* FULLWIDTH ASCII FORMS */
+ { 0xFF52, 0x0072 }, /* FULLWIDTH ASCII FORMS*/
+ { 0xFF53, 0x0073 }, /* FULLWIDTH ASCII FORMS */
+ { 0xFF54, 0x0074 }, /* FULLWIDTH ASCII FORMS*/
+ { 0xFF55, 0x0075 }, /* FULLWIDTH ASCII FORMS */
+ { 0xFF56, 0x0076 }, /* FULLWIDTH ASCII FORMS*/
+ { 0xFF57, 0x0077 }, /* FULLWIDTH ASCII FORMS */
+ { 0xFF58, 0x0078 }, /* FULLWIDTH ASCII FORMS*/
+ { 0xFF59, 0x0079 }, /* FULLWIDTH ASCII FORMS */
+ { 0xFF5A, 0x007A }, /* FULLWIDTH ASCII FORMS*/
+ { 0xFF5B, 0x007B }, /* FULLWIDTH ASCII FORMS */
+ { 0xFF5C, 0x007C }, /* FULLWIDTH ASCII FORMS*/
+ { 0xFF5D, 0x007D }, /* FULLWIDTH ASCII FORMS */
+ { 0xFF5E, 0x007E }, /* FULLWIDTH ASCII FORMS*/
+ { 0xFF5F, 0x007F }, /* FULLWIDTH ASCII FORMS */
+ { 0xFF61, 0x3002 }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF62, 0x300C }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF63, 0x300D }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF64, 0x3001 }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF65, 0x30FB }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF66, 0x30F2 }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF67, 0x30A1 }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF68, 0x30A3 }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF69, 0x30A5 }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF6A, 0x30A7 }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF6B, 0x30A9 }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF6C, 0x30E3 }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF6D, 0x30E5 }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF6E, 0x30E7 }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF6F, 0x30C3 }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF70, 0x30FC }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF71, 0x30A2 }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF72, 0x30A4 }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF73, 0x30A6 }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF74, 0x30A8 }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF75, 0x30AA }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF76, 0x30AB }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF77, 0x30AD }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF78, 0x30AF }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF79, 0x30B1 }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF7A, 0x30B3 }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF7B, 0x30B5 }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF7C, 0x30B7 }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF7D, 0x30B9 }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF7E, 0x30BB }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF7F, 0x30BD }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF80, 0x30BF }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF81, 0x30C1 }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF82, 0x30C4 }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF83, 0x30C6 }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF84, 0x30C8 }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF85, 0x30CA }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF86, 0x30CB }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF87, 0x30CC }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF88, 0x30CD }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF89, 0x30CE }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF8A, 0x30CF }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF8B, 0x30D2 }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF8C, 0x30D5 }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF8D, 0x30D8 }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF8E, 0x30DB }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF8F, 0x30DE }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF90, 0x30DF }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF91, 0x30E0 }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF92, 0x30E1 }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF93, 0x30E2 }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF94, 0x30E4 }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF95, 0x30E6 }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF96, 0x30E8 }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF97, 0x30E9 }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF98, 0x30EA }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF99, 0x30EB }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF9A, 0x30EC }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF9B, 0x30ED }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF9C, 0x30EF }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF9D, 0x30F3 }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF9E, 0x309B }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFF9F, 0x309C }, /* HALFWIDTH KATAKANA FORMS */
+ { 0xFFA0, 0x3164 }, /* HALFWIDTH HANGUL FORMS */
+ { 0xFFA1, 0x3131 }, /* HALFWIDTH HANGUL FORMS */
+ { 0xFFA2, 0x3132 }, /* HALFWIDTH HANGUL FORMS */
+ { 0xFFA3, 0x3133 }, /* HALFWIDTH HANGUL FORMS */
+ { 0xFFA4, 0x3134 }, /* HALFWIDTH HANGUL FORMS */
+ { 0xFFA5, 0x3135 }, /* HALFWIDTH HANGUL FORMS */
+ { 0xFFA6, 0x3136 }, /* HALFWIDTH HANGUL FORMS */
+ { 0xFFA7, 0x3137 }, /* HALFWIDTH HANGUL FORMS */
+ { 0xFFA8, 0x3138 }, /* HALFWIDTH HANGUL FORMS */
+ { 0xFFA9, 0x3139 }, /* HALFWIDTH HANGUL FORMS */
+ { 0xFFAA, 0x313A }, /* HALFWIDTH HANGUL FORMS */
+ { 0xFFAB, 0x313B }, /* HALFWIDTH HANGUL FORMS */
+ { 0xFFAC, 0x313C }, /* HALFWIDTH HANGUL FORMS */
+ { 0xFFAD, 0x313D }, /* HALFWIDTH HANGUL FORMS */
+ { 0xFFAE, 0x313E }, /* HALFWIDTH HANGUL FORMS */
+ { 0xFFAF, 0x313F }, /* HALFWIDTH HANGUL FORMS */
+ { 0xFFB0, 0x3140 }, /* HALFWIDTH HANGUL FORMS */
+ { 0xFFB1, 0x3141 }, /* HALFWIDTH HANGUL FORMS */
+ { 0xFFB2, 0x3142 }, /* HALFWIDTH HANGUL FORMS */
+ { 0xFFB3, 0x3143 }, /* HALFWIDTH HANGUL FORMS */
+ { 0xFFB4, 0x3144 }, /* HALFWIDTH HANGUL FORMS */
+ { 0xFFB5, 0x3145 }, /* HALFWIDTH HANGUL FORMS */
+ { 0xFFB6, 0x3146 }, /* HALFWIDTH HANGUL FORMS */
+ { 0xFFB7, 0x3147 }, /* HALFWIDTH HANGUL FORMS */
+ { 0xFFB8, 0x3148 }, /* HALFWIDTH HANGUL FORMS */
+ { 0xFFB9, 0x3149 }, /* HALFWIDTH HANGUL FORMS */
+ { 0xFFBA, 0x314A }, /* HALFWIDTH HANGUL FORMS */
+ { 0xFFBB, 0x314B }, /* HALFWIDTH HANGUL FORMS */
+ { 0xFFBC, 0x314C }, /* HALFWIDTH HANGUL FORMS */
+ { 0xFFBD, 0x314D }, /* HALFWIDTH HANGUL FORMS */
+ { 0xFFBE, 0x314E }, /* HALFWIDTH HANGUL FORMS */
+ { 0xFFC2, 0x314F }, /* HALFWIDTH HANGUL FORMS */
+ { 0xFFC3, 0x3150 }, /* HALFWIDTH HANGUL FORMS */
+ { 0xFFC4, 0x3151 }, /* HALFWIDTH HANGUL FORMS */
+ { 0xFFC5, 0x3152 }, /* HALFWIDTH HANGUL FORMS */
+ { 0xFFC6, 0x3153 }, /* HALFWIDTH HANGUL FORMS */
+ { 0xFFC7, 0x3154 }, /* HALFWIDTH HANGUL FORMS */
+ { 0xFFCA, 0x3155 }, /* HALFWIDTH HANGUL FORMS */
+ { 0xFFCB, 0x3156 }, /* HALFWIDTH HANGUL FORMS */
+ { 0xFFCC, 0x3157 }, /* HALFWIDTH HANGUL FORMS */
+ { 0xFFCD, 0x3158 }, /* HALFWIDTH HANGUL FORMS */
+ { 0xFFCE, 0x3159 }, /* HALFWIDTH HANGUL FORMS */
+ { 0xFFCF, 0x315A }, /* HALFWIDTH HANGUL FORMS */
+ { 0xFFD2, 0x315B }, /* HALFWIDTH HANGUL FORMS */
+ { 0xFFD3, 0x315C }, /* HALFWIDTH HANGUL FORMS */
+ { 0xFFD4, 0x315D }, /* HALFWIDTH HANGUL FORMS */
+ { 0xFFD5, 0x315E }, /* HALFWIDTH HANGUL FORMS */
+ { 0xFFD6, 0x315F }, /* HALFWIDTH HANGUL FORMS */
+ { 0xFFD7, 0x3160 }, /* HALFWIDTH HANGUL FORMS */
+ { 0xFFDA, 0x3161 }, /* HALFWIDTH HANGUL FORMS */
+ { 0xFFDB, 0x3162 }, /* HALFWIDTH HANGUL FORMS */
+ { 0xFFDC, 0x3163 }, /* HALFWIDTH HANGUL FORMS */
+ { 0xFFE0, 0x00A2 }, /* FULLWIDTH CENT SIGN */
+ { 0xFFE1, 0x00A3 }, /* FULLWIDTH POUND SIGN */
+ { 0xFFE2, 0x00AC }, /* FULLWIDTH NOT SIGN */
+ { 0xFFE3, 0x00AF }, /* FULLWIDTH MACRON */
+ { 0xFFE4, 0x00A6 }, /* FULLWIDTH BROKEN BAR */
+ { 0xFFE5, 0x00A5 }, /* FULLWIDTH YEN SIGN */
+ { 0xFFE6, 0x20A9 }, /* FULLWIDTH WON SIGN */
+ { 0xFFE8, 0x2502 }, /* HALFWIDTH FORMS LIGHT VERTICAL */
+ { 0xFFE9, 0x2190 }, /* HALFWIDTH LEFTWARDS ARROW */
+ { 0xFFEA, 0x2191 }, /* HALFWIDTH UPWARDS ARROW */
+ { 0xFFEB, 0x2192 }, /* HALFWIDTH RIGHTWARDS ARROW */
+ { 0xFFEC, 0x2193 }, /* HALFWIDTH DOWNWARDS ARROW */
+ { 0xFFED, 0x25A0 }, /* HALFWIDTH BLACK SQUARE */
+ { 0xFFEE, 0x25CB }, /* HALFWIDTH WHITE CIRCLE */
+ { 0xFFFD, 0x003F } /* REPLACEMENT CHARACTER */
+};
+
+sal_uInt16 ImplGetReplaceChar( sal_Unicode c )
+{
+ sal_uInt16 nLow;
+ sal_uInt16 nHigh;
+ sal_uInt16 nMid;
+ sal_uInt16 nCompareChar;
+ const ImplReplaceCharData* pCharData;
+
+ nLow = 0;
+ nHigh = (sizeof( aImplRepCharTab )/sizeof( ImplReplaceCharData ))-1;
+ do
+ {
+ nMid = (nLow+nHigh)/2;
+ pCharData = aImplRepCharTab+nMid;
+ nCompareChar = pCharData->mnUniChar;
+ if ( c < nCompareChar )
+ {
+ if ( !nMid )
+ break;
+ nHigh = nMid-1;
+ }
+ else
+ {
+ if ( c > nCompareChar )
+ nLow = nMid+1;
+ else
+ return pCharData->mnReplaceChar;
+ }
+ }
+ while ( nLow <= nHigh );
+
+ return 0;
+}
+
+struct ImplReplaceCharStrData
+{
+ sal_uInt16 mnUniChar;
+ sal_uInt16 maReplaceChars[IMPL_MAX_REPLACECHAR];
+};
+
+static ImplReplaceCharStrData const aImplRepCharStrTab[] =
+{
+ { 0x00A9, { 0x0028, 0x0063, 0x0029, 0x0000, 0x0000 } }, /* COPYRIGHT SIGN */
+ { 0x00AB, { 0x003C, 0x003C, 0x0000, 0x0000, 0x0000 } }, /* LEFT-POINTING-DOUBLE ANGLE QUOTATION MARK */
+ { 0x0AE0, { 0x0028, 0x0072, 0x0029, 0x0000, 0x0000 } }, /* REGISTERED SIGN */
+ { 0x00BB, { 0x003E, 0x003E, 0x0000, 0x0000, 0x0000 } }, /* RIGHT-POINTING-DOUBLE ANGLE QUOTATION MARK */
+ { 0x00BC, { 0x0031, 0x002F, 0x0034, 0x0000, 0x0000 } }, /* VULGAR FRACTION ONE QUARTER */
+ { 0x00BD, { 0x0031, 0x002F, 0x0032, 0x0000, 0x0000 } }, /* VULGAR FRACTION ONE HALF */
+ { 0x00BE, { 0x0033, 0x002F, 0x0034, 0x0000, 0x0000 } }, /* VULGAR FRACTION THREE QUARTERS */
+ { 0x00C6, { 0x0041, 0x0045, 0x0000, 0x0000, 0x0000 } }, /* LATIN CAPITAL LETTER AE */
+ { 0x00E6, { 0x0061, 0x0065, 0x0000, 0x0000, 0x0000 } }, /* LATIN SMALL LETTER AE */
+ { 0x0152, { 0x004F, 0x0045, 0x0000, 0x0000, 0x0000 } }, /* LATIN CAPITAL LIGATURE OE */
+ { 0x0153, { 0x006F, 0x0065, 0x0000, 0x0000, 0x0000 } }, /* LATIN SMALL LIGATURE OE */
+ { 0x2025, { 0x002E, 0x002E, 0x0000, 0x0000, 0x0000 } }, /* TWO DOT LEADER */
+ { 0x2026, { 0x002E, 0x002E, 0x002E, 0x0000, 0x0000 } }, /* HORIZONTAL ELLIPSES */
+ { 0x2034, { 0x0027, 0x0027, 0x0027, 0x0000, 0x0000 } }, /* TRIPPLE PRIME */
+ { 0x2037, { 0x0027, 0x0027, 0x0027, 0x0000, 0x0000 } }, /* RESERVED TRIPPLE PRIME */
+ { 0x20AC, { 0x0045, 0x0055, 0x0052, 0x0000, 0x0000 } }, /* EURO SIGN */
+ { 0x2122, { 0x0028, 0x0074, 0x006D, 0x0029, 0x0000 } }, /* TRADE MARK SIGN */
+ { 0x2153, { 0x0031, 0x002F, 0x0033, 0x0000, 0x0000 } }, /* VULGAR FRACTION ONE THIRD */
+ { 0x2154, { 0x0032, 0x002F, 0x0033, 0x0000, 0x0000 } }, /* VULGAR FRACTION TWO THIRD */
+ { 0x2155, { 0x0031, 0x002F, 0x0035, 0x0000, 0x0000 } }, /* VULGAR FRACTION ONE FIFTH */
+ { 0x2156, { 0x0032, 0x002F, 0x0035, 0x0000, 0x0000 } }, /* VULGAR FRACTION TWO FIFTH */
+ { 0x2157, { 0x0033, 0x002F, 0x0035, 0x0000, 0x0000 } }, /* VULGAR FRACTION THREE FIFTH */
+ { 0x2158, { 0x0034, 0x002F, 0x0035, 0x0000, 0x0000 } }, /* VULGAR FRACTION FOUR FIFTH */
+ { 0x2159, { 0x0031, 0x002F, 0x0036, 0x0000, 0x0000 } }, /* VULGAR FRACTION ONE SIXTH */
+ { 0x215A, { 0x0035, 0x002F, 0x0036, 0x0000, 0x0000 } }, /* VULGAR FRACTION FIVE SIXTH */
+ { 0x215B, { 0x0031, 0x002F, 0x0038, 0x0000, 0x0000 } }, /* VULGAR FRACTION ONE EIGHTH */
+ { 0x215C, { 0x0033, 0x002F, 0x0038, 0x0000, 0x0000 } }, /* VULGAR FRACTION THREE EIGHTH */
+ { 0x215D, { 0x0035, 0x002F, 0x0038, 0x0000, 0x0000 } }, /* VULGAR FRACTION FIVE EIGHTH */
+ { 0x215E, { 0x0037, 0x002F, 0x0038, 0x0000, 0x0000 } }, /* VULGAR FRACTION SEVEN EIGHTH */
+ { 0x215F, { 0x0031, 0x002F, 0x0000, 0x0000, 0x0000 } }, /* FRACTION NUMERATOR ONE */
+ { 0x2161, { 0x0049, 0x0049, 0x0000, 0x0000, 0x0000 } }, /* ROMAN NUMERAL TWO */
+ { 0x2162, { 0x0049, 0x0049, 0x0049, 0x0000, 0x0000 } }, /* ROMAN NUMERAL THREE */
+ { 0x2163, { 0x0049, 0x0056, 0x0000, 0x0000, 0x0000 } }, /* ROMAN NUMERAL FOUR */
+ { 0x2165, { 0x0056, 0x0049, 0x0000, 0x0000, 0x0000 } }, /* ROMAN NUMERAL SIX */
+ { 0x2166, { 0x0056, 0x0049, 0x0049, 0x0000, 0x0000 } }, /* ROMAN NUMERAL SEVEN */
+ { 0x2168, { 0x0056, 0x0049, 0x0049, 0x0049, 0x0000 } }, /* ROMAN NUMERAL EIGHT */
+ { 0x2169, { 0x0049, 0x0058, 0x0000, 0x0000, 0x0000 } }, /* ROMAN NUMERAL NINE */
+ { 0x216A, { 0x0058, 0x0049, 0x0000, 0x0000, 0x0000 } }, /* ROMAN NUMERAL ELEVEN */
+ { 0x216B, { 0x0058, 0x0049, 0x0049, 0x0000, 0x0000 } }, /* ROMAN NUMERAL TWELVE */
+ { 0x2171, { 0x0069, 0x0069, 0x0000, 0x0000, 0x0000 } }, /* SMALL ROMAN NUMERAL TWO */
+ { 0x2172, { 0x0069, 0x0069, 0x0069, 0x0000, 0x0000 } }, /* SMALL ROMAN NUMERAL THREE */
+ { 0x2173, { 0x0069, 0x0076, 0x0000, 0x0000, 0x0000 } }, /* SMALL ROMAN NUMERAL FOUR */
+ { 0x2175, { 0x0076, 0x0069, 0x0000, 0x0000, 0x0000 } }, /* SMALL ROMAN NUMERAL SIX */
+ { 0x2176, { 0x0076, 0x0069, 0x0069, 0x0000, 0x0000 } }, /* SMALL ROMAN NUMERAL SEVEN */
+ { 0x2178, { 0x0076, 0x0069, 0x0069, 0x0069, 0x0000 } }, /* SMALL ROMAN NUMERAL EIGHT */
+ { 0x2179, { 0x0069, 0x0078, 0x0000, 0x0000, 0x0000 } }, /* SMALL ROMAN NUMERAL NINE */
+ { 0x217A, { 0x0078, 0x0069, 0x0000, 0x0000, 0x0000 } }, /* SMALL ROMAN NUMERAL ELEVEN */
+ { 0x217B, { 0x0058, 0x0069, 0x0069, 0x0000, 0x0000 } } /* SMALL ROMAN NUMERAL TWELVE */
+};
+
+const sal_uInt16* ImplGetReplaceString( sal_Unicode c )
+{
+ sal_uInt16 nLow;
+ sal_uInt16 nHigh;
+ sal_uInt16 nMid;
+ sal_uInt16 nCompareChar;
+ const ImplReplaceCharStrData* pCharData;
+
+ nLow = 0;
+ nHigh = (sizeof( aImplRepCharStrTab )/sizeof( ImplReplaceCharStrData ))-1;
+ do
+ {
+ nMid = (nLow+nHigh)/2;
+ pCharData = aImplRepCharStrTab+nMid;
+ nCompareChar = pCharData->mnUniChar;
+ if ( c < nCompareChar )
+ {
+ if ( !nMid )
+ break;
+ nHigh = nMid-1;
+ }
+ else
+ {
+ if ( c > nCompareChar )
+ nLow = nMid+1;
+ else
+ return pCharData->maReplaceChars;
+ }
+ }
+ while ( nLow <= nHigh );
+
+ return 0;
+}
+
+// Writes 0--2 characters to dest:
+static int ImplConvertUnicodeCharToChar(
+ const ImplByteConvertData* pConvertData, sal_Unicode c, char * dest )
+{
+ const ImplUniCharTabData* pToCharExTab;
+
+ if ( c < 0x80 )
+ {
+ dest[0] = static_cast< char >(c);
+ return 1;
+ }
+ if ( (c >= pConvertData->mnToCharStart1) && (c <= pConvertData->mnToCharEnd1) )
+ {
+ dest[0] = static_cast< char >(pConvertData->mpToCharTab1[c-pConvertData->mnToCharStart1]);
+ if ( dest[0] != 0 )
+ return 1;
+ }
+ else if ( (c >= pConvertData->mnToCharStart2) && (c <= pConvertData->mnToCharEnd2) )
+ {
+ dest[0] = static_cast< char >(pConvertData->mpToCharTab2[c-pConvertData->mnToCharStart2]);
+ if ( dest[0] != 0 )
+ return 1;
+ }
+ pToCharExTab = pConvertData->mpToCharExTab;
+ if ( pToCharExTab )
+ {
+ sal_uInt16 nLow;
+ sal_uInt16 nHigh;
... etc. - the rest is truncated
More information about the Libreoffice-commits
mailing list