From fc670f637d4271246691904fd649358ce2e7be59 Mon Sep 17 00:00:00 2001 From: Michael Stahl Date: Thu, 7 Sep 2017 23:01:26 +0200 Subject: svtools: HTML import: don't put lone surrogates in OUString The bytes "ed b3 b5" in fdo67610-1.doc (which, as the name indicates, is an HTML file) are converted to the lone UTF-16 surrogate "dcf5", which is inserted into SwTextNode and causes asserts later on. The actual encoding of the HTML document is probably GBK (at least VIM doesn't display any missing characters with that), but because it doesn't contain any indication of its encoding it's apparently imported as UTF-8; the ImplConvertUtf8ToUnicode() thinking a surrogate code point is valid even if the JSON-compatible mode RTL_TEXTENCODING_JAVA_UTF8 is not specified is a bit of a surprise. Change-Id: Idd788d9d461fed150171dd907439166f3075a834 --- svtools/source/svrtf/svparser.cxx | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'svtools/source/svrtf') diff --git a/svtools/source/svrtf/svparser.cxx b/svtools/source/svrtf/svparser.cxx index 541aa5276c2d..cef258f04dd2 100644 --- a/svtools/source/svrtf/svparser.cxx +++ b/svtools/source/svrtf/svparser.cxx @@ -423,7 +423,8 @@ sal_uInt32 SvParser::GetNextChar() while( 0 == nChars && !bErr ); } - if ( ! rtl::isUnicodeCodePoint( c ) ) + // Note: ImplConvertUtf8ToUnicode() may produce a surrogate! + if (!rtl::isUnicodeCodePoint(c) || rtl::isHighSurrogate(c) || rtl::isLowSurrogate(c)) c = '?' ; if( bErr ) -- cgit