/* -*- Mode: C++; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 4 -*- */ /* * This file is part of the LibreOffice project. * * This Source Code Form is subject to the terms of the Mozilla Public * License, v. 2.0. If a copy of the MPL was not distributed with this * file, You can obtain one at http://mozilla.org/MPL/2.0/. * * This file incorporates work covered by the following license notice: * * Licensed to the Apache Software Foundation (ASF) under one or more * contributor license agreements. See the NOTICE file distributed * with this work for additional information regarding copyright * ownership. The ASF licenses this file to you under the Apache * License, Version 2.0 (the "License"); you may not use this file * except in compliance with the License. You may obtain a copy of * the License at http://www.apache.org/licenses/LICENSE-2.0 .
*/
class ScDocShell; class ScDocument; class ScAsciiOptions;
/** * These options control how multi-line cells are converted during export in * certain lossy formats (such as csv).
*/ struct ScExportTextOptions
{ enum NewlineConversion { ToSystem, ToSpace, None };
ScExportTextOptions( NewlineConversion eNewlineConversion = ToSystem, sal_Unicode cSeparatorConvertTo = 0, bool bAddQuotes = false ) :
meNewlineConversion( eNewlineConversion ), mcSeparatorConvertTo( cSeparatorConvertTo ), mbAddQuotes( bAddQuotes ) {}
NewlineConversion meNewlineConversion;
sal_Unicode mcSeparatorConvertTo; // Convert separator to this character bool mbAddQuotes;
};
class SAL_DLLPUBLIC_RTTI ScImportExport
{
ScDocShell* pDocSh;
ScDocument& rDoc;
std::unique_ptr<ScDocument, o3tl::default_delete<ScDocument>> pUndoDoc;
ScRange aRange;
OUString aStreamPath;
OUString aNonConvertibleChars;
OUString maFilterOptions;
sal_uInt32 nSizeLimit;
SCROW nMaxImportRow;
sal_Unicode cSep; // Separator
sal_Unicode cStr; // String Delimiter bool bFormulas; // Formula in Text? bool bIncludeFiltered; // include filtered rows? (default true) bool bAll; // no selection bool bSingle; // Single selection bool bUndo; // with Undo? bool bOverflowRow; // too many rows bool bOverflowCol; // too many columns bool bOverflowCell; // too much data for a cell bool mbApi; bool mbImportBroadcast; // whether or not to broadcast after data import. bool mbOverwriting; // Whether we could be overwriting existing values (paste). // In this case we cannot use the insert optimization, but we // do not need to broadcast after the import. bool mbIncludeBOM; // Whether to include a byte-order-mark in the output.
ScExportTextOptions mExportTextOptions;
/** ScImportExport::CountVisualWidth Count the width of string visually ( in multiple of western characters), considering CJK ideographs and CJK symbols (U+3000-U+303F) as twice the width of western characters. @param rStr the string. @param nIdx the starting index, index is incremented for each counted character. @param nMaxWidth the maximum width to count. @return the sum of the width of counted characters.
**/ static sal_Int32 CountVisualWidth(std::u16string_view rStr, sal_Int32& nIdx, sal_Int32 nMaxWidth);
/** ScImportExport::CountVisualWidth @return the sum of the visual width of the whole string.
**/ static sal_Int32 CountVisualWidth(std::u16string_view rStr);
//! only if stream is only used in own (!) memory staticvoid SetNoEndianSwap( SvStream& rStrm );
void SetSeparator( sal_Unicode c ) { cSep = c; } void SetDelimiter( sal_Unicode c ) { cStr = c; } void SetFormulas( bool b ) { bFormulas = b; } void SetIncludeFiltered( bool b ) { bIncludeFiltered = b; }
// Helper class for importing clipboard strings as streams. class ScImportStringStream : public SvMemoryStream
{ public:
ScImportStringStream(const OUString& rStr);
};
/** Read a CSV (comma separated values) data line using ReadUniOrByteStringLine().
@param bEmbeddedLineBreak If TRUE and a line-break occurs inside a field of data, a line feed LF '\n' and the next line are appended. Repeats until a line-break is not in a field. A field is determined by delimiting rFieldSeparators and optionally surrounded by a pair of cFieldQuote characters. For a line-break to be within a field, the field content MUST be surrounded by cFieldQuote characters, and the opening cFieldQuote MUST be at the very start of a line or follow right behind a field separator with no extra characters in between, with the exception of blanks contradictory to RFC 4180. Anything, including field separators and escaped quotes (by doubling them) may appear in a quoted field.
If bEmbeddedLineBreak==FALSE, nothing is parsed and the string returned is simply one ReadUniOrByteStringLine().
@param rFieldSeparators A list of characters that each may act as a field separator. If rcDetectSep was 0 and a separator is detected then it is appended to rFieldSeparators.
@param cFieldQuote The quote character used.
@param rcDetectSep If 0 then attempt to detect a possible separator if rFieldSeparators doesn't include it already. This can be necessary because of the "accept broken misquoted CSV fields" feature that tries to ignore trailing blanks after a quoted field and if no separator follows continues to add content to the field assuming the single double quote was in error. It is also necessary if the only possible separator was not selected and not included in rFieldSeparators and a line starts with a quoted field, in which case appending lines is tried until end of file. If a separator is detected it is added to rFieldSeparators and the line is reread with the new separators
@param nMaxSourceLines Maximum source lines to read and combine into one logical line for embedded new line purpose. Should be limited for the preview dialog because only non-matching separators selected otherwise would lead to trying to concatenate lines until file end. If 0 no limit other than the internal arbitrary resulting line length limit.
check Stream::good() to detect IO problems during read
@ATTENTION Note that the string returned may be truncated even inside a quoted field if some (arbitrary) maximum length was reached. There currently is no way to exactly determine the conditions, whether this was at a line end, or whether open quotes would have closed the field before the line end, as even a ReadUniOrByteStringLine() may return prematurely but the stream was positioned ahead until the real end of line. Additionally, due to character encoding conversions, string length and bytes read don't necessarily match, and resyncing to a previous position matching the string's length isn't always possible. As a result, a logical line with embedded line breaks and more than the maximum length characters will be spoiled, and a subsequent ReadCsvLine() may start under false preconditions.
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.
