commit 4399bccc5ee5a3fa69a8818e7ae265c144d33d64
author Justin Luth <justin.luth@collabora.com> Wed Dec 27 18:58:33 2023 -0500
committer Justin Luth <jluth@mail.com> Thu Dec 28 22:51:13 2023 +0100
tree 164a82ef98d6390a78d9cc1637a76c47e3d22f47
parent ba2bd49397725fd07ed36aefe2acc4d2be70c72e

tdf#158826 rtfimport: ignore page break before document starts

This avoids a 24.2 exposed bug from my
commit 016f779ee6c7f601be3ae19dc57497e63a5bf817

RTF import simply cannot be relied upon to create paragraphs
where they need to be. A side effect of fixing frames
is that spurious paragraphs can be created,
and if a frame starts the document, then an otherwise
ignored page break can be attached to the second paragraph
and thus become exposed.

This seems pretty much like the RTF implementation of
what was done for DOC and DOCX for tdf#118711.
At least it is related.

make CppunitTest_sw_rtfexport8 CPPUNIT_TEST_NAME=testTdf158826_extraCR

The following unit tests trigger this code (with no visible change)
abi10076.odt  tdf121623.rtf  tdf129513.rtf  tdf131963.docx

Change-Id: I21afa826b6f6fbb735591603a0620b8b47de517e
Reviewed-on: https://gerrit.libreoffice.org/c/core/+/161374
Tested-by: Jenkins
Reviewed-by: Justin Luth <jluth@mail.com>

sw/qa/extras/rtfexport/data/tdf158826_extraCR.rtf

diff --git a/sw/qa/extras/rtfexport/data/tdf158826_extraCR.rtf b/sw/qa/extras/rtfexport/data/tdf158826_extraCR.rtf
new file mode 100644
index 0000000..5461327
--- /dev/null
+++ b/sw/qa/extras/rtfexport/data/tdf158826_extraCR.rtf
@@ -0,0 +1,23 @@
{\rtf1

\landscape\paperh5953\paperw8391\margl720\margr720\margt432\margb1728\gutter0\ltrsect





\pagebb

\intbl

\pvpg\phpg



\posx720\posy432

\dxfrtext187\dfrmtxtx187\dfrmtxty0

\wraparound\aspalpha\aspnum

\faauto\adjustright

\rin0\lin0\absnoovrlp1\pararsid5332093\yts39





\shp





a \cell b{\cell }

\clwWidth6300\clshdrawnil \cellx6295

\clwWidth4500\clshdrawnil \cellx10795\row



}

sw/qa/extras/rtfexport/rtfexport8.cxx

diff --git a/sw/qa/extras/rtfexport/rtfexport8.cxx b/sw/qa/extras/rtfexport/rtfexport8.cxx
index 3023e51..9848d05 100644
--- a/sw/qa/extras/rtfexport/rtfexport8.cxx
+++ b/sw/qa/extras/rtfexport/rtfexport8.cxx
@@ -86,6 +86,17 @@ DECLARE_RTFEXPORT_TEST(testTdf158586_lostFrame, "tdf158586_lostFrame.rtf")
    // CPPUNIT_ASSERT_EQUAL(2, getPages());
}

DECLARE_RTFEXPORT_TEST(testTdf158826_extraCR, "tdf158826_extraCR.rtf")
{
    // Note: this is a hand-minimized sample, and very likely doesn't follow RTF { } rules...

    // The page break defined before the document content should not cause a page break
    CPPUNIT_ASSERT_EQUAL(1, getPages());

    // There is a two-column floating table [that SHOULD be getParagraphOrTable(1)]
    uno::Reference<text::XTextTable> xTable(getParagraphOrTable(2), uno::UNO_QUERY_THROW);
}

} // end of anonymous namespace
CPPUNIT_PLUGIN_IMPLEMENT();

writerfilter/source/rtftok/rtfdispatchflag.cxx

diff --git a/writerfilter/source/rtftok/rtfdispatchflag.cxx b/writerfilter/source/rtftok/rtfdispatchflag.cxx
index 72c777a..753f1c3 100644
--- a/writerfilter/source/rtftok/rtfdispatchflag.cxx
+++ b/writerfilter/source/rtftok/rtfdispatchflag.cxx
@@ -520,7 +520,9 @@ RTFError RTFDocumentImpl::dispatchFlag(RTFKeyword nKeyword)
        }
        break;
        case RTFKeyword::PAGEBB:
            nParam = NS_ooxml::LN_CT_PPrBase_pageBreakBefore;
            // ignore a page break that is defined before the document content has even started
            if (!m_bFirstRun)
                nParam = NS_ooxml::LN_CT_PPrBase_pageBreakBefore;
            break;
        default:
            break;