Witnessed a JunitTest_chart2_unoapi failure where (deep within Idle::Timeout)
chart::impl::ModelState::update is apparently called with a null xModel.  All
the code called from there appears to be careful to handle a null xModel, except
for chart::TitleHelper::getTitle, which---presumably by accident---stopped doing
so with 401f01ca "use ChartModel instead of
XModel in a few places."

Change-Id: I5788b5e41a6d68fe193cb214d736ee54c4c581d7

by moving work done in dtor to an explicit method

Change-Id: I99b3843819ea78f2a91a2784ae0243430dacb3d9

Change-Id: I59e5ede0c0cfb10f4196d79ae762132ae4ecb9bb

The only valid non-txtnode return value for the SwPosition is the
unmodified initial value (hopefully).

Change-Id: Ib5789455576a20848dd7f0542bd520aa04040b90

The primary benefit of this is that it's no longer necessary to manually
downcast to each and every subclass in sw.

Change-Id: I5742d5744836eef192eef2d4f7ad180da67eb914

Change-Id: Icc2b80cfdcb3ff6a8a4fa8d1fb30a8ce9c865c95

Fallout of 72b9dd27 String to OUString
conversion.

Change-Id: I89a90da11790efba9e8ce4c9464dfca50b08c3ce

Change-Id: I2a6b4ba10d303a6a4ce5bc4582e68a73c2ae331e

Change-Id: I60d5f4929168163e755934ccaf07d227e702948f

Change-Id: Ia4c8920ce2ce44286c5042d4b5dbeaa41fe355cc

Change-Id: I8a2785e90dae7edacb6dfb3e4362e5fb6a981b0e

Change-Id: I1dac5542d711133f30fb4e61590a19bd2beccf53

Change-Id: Iaefde6a2fbe1b37f31435217c9f57d611d255b11

Change-Id: Ida354ee41b4158716ab39a92f009fa7c9a2ce21f
Reviewed-on: https://gerrit.libreoffice.org/13919Tested-by: Andras Timar <andras.timar@collabora.com>
Reviewed-by: Andras Timar <andras.timar@collabora.com>

anchor to the page instead

Change-Id: Ib7931fdd1c70e809ec442aeac125879980e20ec9

1 press return in an empty writer doc a few times
2 insert a stock 2x2 table
4 enter A1 and change format->character to hidden
A1
3 draw a rectangle above A1 so it'll get anchored to paragraph above table
5 draw rectangle anchor into A1

Change-Id: I2b0631908843150fae48f7e387a98e91cf90423d

Change-Id: I68654a5fa4cbb7403c00b103e2be5929ccb516a2

regression from

commit 10e77ab3
Author: Thorsten Behrens <thb@documentfoundation.org>
Date:   Sun Nov 2 22:37:32 2014 +0100

    coverity#1242508: swapped arguments

rename the variables to indicate which are source and
which are dest indexes and that the aNewBitmap
argument is always, and assert that it must be, of
equivalent rotated source to the Bitmap which has
ImplConvolutionPass called on it.

Change-Id: If9715b9f29655da66c6981c0f7cab3d89c528ed7

Change-Id: I5a95556b2a9975af150aeb65d6f363f643349a49

not entirely sure when this stopped working, but our contempory code is riddled
with asserts and throws for negative sizes so rework this to explicitly mirror
the preview rather than try the no longer working technique

Change-Id: Ie90283cad2797ab1c37848469b007dc01a2c9d75

Change-Id: I91745c868310b301e86cf9b5d6607ae362e2b945

Change-Id: I399bf576fe89283f839842959f06b8fe83f13b2b

Change-Id: Ifa143e5a8f0e8254fbd324032951517d3a30c4c8

If there is a SAXParseException, OOXMLDocumentImpl::resolve() should not
ignore it, because if it occurs in a substream some end tag handlers may
not have been run and the DomainMapper may be in an inconsistent state,
so continuing to parse the outer document is probably not a good idea.

Also add some exception mangling so sfx2 can present a useful error
dialog.

Change-Id: I169ba6db25f2ae264af08a64edf76a6bf6757f85

Change-Id: I9891269a765ace15497a3cd3b1729be941bc3c1b

Change-Id: I1cd932ae520ba20eff8ef447614e91e1cc2032f8

Change-Id: I1811dead8f104a445bfee9282a60ecedeca872ed

lp502369-3.doc contains several StgEntry that are invalid and have type
0 (STG_EMPTY).  Not sure if sot Storage::FillInfoList() should filter
these out.

Change-Id: I493cbb346723a3be4f8bc93de1030e68c1216b50

Change-Id: Ie4ecb334666587d25b94d8bf2b1a9fe60d03d232

Change-Id: I53ad45fef0e17ce15a500959206b9b042e550e49

It is only called from sc/qa/unit/opencl-test.cxx anyway, and there it is
presumably intended to make OpenCL be used whenever at all possible, with no
requirements on which opcodes are used in a formula or the size of the formula
group.

Change-Id: Ib8a28dfa15794374e849aa1cdcc5288ef8aa017e

Change-Id: Ia9af98d580a694c2b8c5dae213d443d94c143091

(and its later fixup)

This reverts commits
 e8a68c1f
 e60b5899

It was a work-around for the real underlying issue, which was that the
result of dbaccess::ResultSet::isFirst() et al were clobbered by moves
made by its clones.

The BrowseBox has two different cursors:
1) One for data to edit (which is kept on the current/active row)
2) One for data to *paint*
The second is a clone of the first.

The real underlying issue is fixed by:

  commit d7c9a1d9
  Author: Lionel Elie Mamane <lionel@mamane.lu>
  Date:   Thu Jan 22 10:49:42 2015 +0100

      fdo#88475 RowSetBase: reposition cache before interrogating it

      Change-Id: I28d62673fdf10ee6507d38bb7c79c08e4b40902f

Change-Id: Ib4516eec5e47d95d53dbb5002f7258514c93f2c9

This fixes a regression introduced by "fdo#88551 no need to update content from field when activating grid cell"
that when switching from design mode to normal mode
before one moved row at least once, the current cell (inevitably of the first row)
was always displayed empty.
Before, the update was done by the activation event (which was too often), so now we need to do it once at initialisation.
Not sure if using updateFromModel instead of UpdateFromField makes a difference. Hope not. Else need to change that.

Change-Id: I878dea0f91b370a4f83c3c1a3ed185a51ac9f0b7

Change-Id: I6024352f9d7c68d8075d90b5954ec3ba662a06f0

Even when called with _bMoved==false, that is when inserting row or when asked to move to the position we are already in.

Change-Id: Icff5a18638f7e850db4678cdf82021f56f135d1f

Change-Id: Ide3f05cc66353787acb33b33340577624f25a8bc

This partially reverts:

  commit d20232a7
  Author: Lionel Elie Mamane <lionel@mamane.lu>
  Date:   Thu Dec 6 13:22:06 2012 +0100

      Don't force refresh when higher up code did not request it

      Change-Id: I0f415c96fc05c1d776d14885751aef020c42f4ae

which did not take into account that the cache is shared with the
clones.

Finish the above commit more deeply, that is
more aggressively avoid moving the cache if we don't need to:
when we merely reposition the cache in case another RowSet(Clone)
has moved it, no need to force a move and by that to force a refresh.

Change-Id: I28d62673fdf10ee6507d38bb7c79c08e4b40902f

Change-Id: I87744f86d1413973709a46a58ebc03a39bce842c