writerfilter/source/rtftok/rtfdocumentimpl.cxx | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+)
New commits: commit a6516c76c01b92f7d35bfb352b63af7de42b5707 Author: Michael Stahl <michael.st...@cib.de> AuthorDate: Tue Oct 29 15:54:41 2019 +0100 Commit: Michael Stahl <michael.st...@cib.de> CommitDate: Wed Oct 30 14:44:09 2019 +0100 writerfilter: rtftok: filter control characters ... in RTFDocumentImpl::checkUnicode(); see ooo86460-1.xls [sic] for an example. There is another caller of text() in rtfdispatchdestination.cxx:311 but it turns out that buffered text was created by text() in the first place. This shouldn't be a problem for DOCX because XML 1.0 doesn't allow the bad control characters anyway so the sax parser should report an error in that case. Change-Id: Ice45e1c3c8c7db668a4cfb8364e42addea1777ce Reviewed-on: https://gerrit.libreoffice.org/81697 Reviewed-by: Michael Stahl <michael.st...@cib.de> Tested-by: Michael Stahl <michael.st...@cib.de> diff --git a/writerfilter/source/rtftok/rtfdocumentimpl.cxx b/writerfilter/source/rtftok/rtfdocumentimpl.cxx index f2873ecf97b8..a2d0d1635e7c 100644 --- a/writerfilter/source/rtftok/rtfdocumentimpl.cxx +++ b/writerfilter/source/rtftok/rtfdocumentimpl.cxx @@ -30,6 +30,7 @@ #include <tools/datetimeutils.hxx> #include <comphelper/classids.hxx> #include <comphelper/embeddedobjectcontainer.hxx> +#include <svl/lngmisc.hxx> #include <sfx2/sfxbasemodel.hxx> #include <sfx2/classificationhelper.hxx> #include <oox/mathml/import.hxx> @@ -3563,12 +3564,35 @@ bool RTFDocumentImpl::getSkipUnknown() { return m_bSkipUnknown; } void RTFDocumentImpl::setSkipUnknown(bool bSkipUnknown) { m_bSkipUnknown = bSkipUnknown; } +static auto FilterControlChars(Destination const destination, OUString const& rString) -> OUString +{ + if (destination == Destination::LEVELNUMBERS || destination == Destination::LEVELTEXT) + { // control characters are magic here! + return rString; + } + OUStringBuffer buf(rString.getLength()); + for (sal_Int32 i = 0; i < rString.getLength(); ++i) + { + sal_Unicode const ch(rString[i]); + if (!linguistic::IsControlChar(ch) || ch == '\r' || ch == '\n' || ch == '\t') + { + buf.append(ch); + } + else + { + SAL_INFO("writerfilter.rtf", "filtering control character"); + } + } + return buf.makeStringAndClear(); +} + void RTFDocumentImpl::checkUnicode(bool bUnicode, bool bHex) { if (bUnicode && !m_aUnicodeBuffer.isEmpty()) { OUString aString = m_aUnicodeBuffer.toString(); m_aUnicodeBuffer.setLength(0); + aString = FilterControlChars(m_aStates.top().getDestination(), aString); text(aString); } if (bHex && !m_aHexBuffer.isEmpty()) @@ -3579,6 +3603,7 @@ void RTFDocumentImpl::checkUnicode(bool bUnicode, bool bHex) nEncoding = RTL_TEXTENCODING_MS_1252; OUString aString = OStringToOUString(m_aHexBuffer.toString(), nEncoding); m_aHexBuffer.setLength(0); + aString = FilterControlChars(m_aStates.top().getDestination(), aString); text(aString); } } _______________________________________________ Libreoffice-commits mailing list libreoffice-comm...@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/libreoffice-commits