officecfg/registry/schema/org/openoffice/Office/Calc.xcs | 18 +++++-
sc/source/ui/dbgui/scuiasciiopt.cxx | 41 +++++++--------
2 files changed, 37 insertions(+), 22 deletions(-)
New commits:
commit d16535788721238a423408ba59805f4bcacc4e12
Author: Mike Kaganski <mike.kagan...@collabora.com>
AuthorDate: Wed Jun 4 19:23:30 2025 +0500
Commit: Mike Kaganski <mike.kagan...@collabora.com>
CommitDate: Sat Jun 7 12:05:07 2025 +0200
[API CHANGE] tdf#166208: New "Encoding" property for text import /
clipboard paste
The problem appeared, because the existing CharSet property was storing
the index of the selection in the encoding list box; and that meant, that
any change in the list box content (different sorting; added elements)
could suddenly make the selection wrong the next time. With introduction
of the autodetection entry into the top of the list box in tdf#152336 (in
commit 565b619d57a3b98b0826c4b49dee6606f9ae70e0), many people who had
UTF-8 selected in the dialog previously, got UTF-7 instead; and many had
not noticed the difference, thus seeing unexpected results after import.
The said commit intended to force-select autodetection for the users who
had not used the updated dialog yet; but the detection of that scenario
was flawed, and didn't work (that was discussed, and respective code was
dropped in commit ...).
This change implements that idea. I decided to ignore the stored CharSet
value; after the change, autodetection entry will be pre-selected at the
first start of the dialog. This will be a minor annoyance for users who
have already re-selected wanted encoding after previous upgrade; but it
allows to resolve the bug for people upgrading from versions prior to
25.2. Also, since new versions will not write to CharSet, it's possible
to use a shared profile between old and new versions without breaking
the encoding selection in either.
Change-Id: I59640b16f703077b6fda44a34eadf2edbe8e6bf5
Reviewed-on: https://gerrit.libreoffice.org/c/core/+/186240
Tested-by: Jenkins
Reviewed-by: Mike Kaganski <mike.kagan...@collabora.com>
diff --git a/officecfg/registry/schema/org/openoffice/Office/Calc.xcs
b/officecfg/registry/schema/org/openoffice/Office/Calc.xcs
index 5023d3c9e78e..25b272f35c64 100644
--- a/officecfg/registry/schema/org/openoffice/Office/Calc.xcs
+++ b/officecfg/registry/schema/org/openoffice/Office/Calc.xcs
@@ -1091,11 +1091,18 @@
</prop>
<prop oor:name="CharSet" oor:type="xs:int" oor:nillable="false">
<info>
- <desc>Char Set</desc>
+ <desc>Char Set (index of selected item in the dialog's list box;
obsoleted by Encoding)</desc>
<label>CharSet</label>
</info>
<value>-1</value>
</prop>
+ <prop oor:name="Encoding" oor:type="xs:short" oor:nillable="false">
+ <info>
+ <desc>Encoding (an rtl_TextEncoding value; default is "don't
know")</desc>
+ <label>Encoding</label>
+ </info>
+ <value>0</value>
+ </prop>
<prop oor:name="FixedWidthList" oor:type="xs:string"
oor:nillable="false">
<info>
<desc>Fixed Width List of separators</desc>
@@ -1201,11 +1208,18 @@
</prop>
<prop oor:name="CharSet" oor:type="xs:int" oor:nillable="false">
<info>
- <desc>Char Set</desc>
+ <desc>Char Set (index of selected item in the dialog's list box;
obsoleted by Encoding)</desc>
<label>CharSet</label>
</info>
<value>-1</value>
</prop>
+ <prop oor:name="Encoding" oor:type="xs:short" oor:nillable="false">
+ <info>
+ <desc>Encoding (an rtl_TextEncoding value; default is "don't
know")</desc>
+ <label>Encoding</label>
+ </info>
+ <value>0</value>
+ </prop>
<prop oor:name="FixedWidthList" oor:type="xs:string"
oor:nillable="false">
<info>
<desc>Fixed Width List of separators</desc>
diff --git a/sc/source/ui/dbgui/scuiasciiopt.cxx
b/sc/source/ui/dbgui/scuiasciiopt.cxx
index 8370ee76fb12..95dcb676650e 100644
--- a/sc/source/ui/dbgui/scuiasciiopt.cxx
+++ b/sc/source/ui/dbgui/scuiasciiopt.cxx
@@ -81,7 +81,7 @@ constexpr OUString CSVIO_RemoveSpace = u"RemoveSpace"_ustr;
constexpr OUString CSVIO_EvaluateFormulas = u"EvaluateFormulas"_ustr;
constexpr OUString CSVIO_SeparatorType = u"SeparatorType"_ustr;
constexpr OUString CSVIO_FromRow = u"FromRow"_ustr;
-constexpr OUString CSVIO_CharSet = u"CharSet"_ustr;
+constexpr OUString CSVIO_Encoding = u"Encoding"_ustr;
constexpr OUString CSVIO_QuotedAsText = u"QuotedFieldAsText"_ustr;
constexpr OUString CSVIO_DetectSpecialNum = u"DetectSpecialNumbers"_ustr;
constexpr OUString CSVIO_DetectScientificNum = u"DetectScientificNumbers"_ustr;
@@ -160,7 +160,7 @@ static OUString lcl_GetConfigPath(ScImportAsciiCall eCall)
static void lcl_LoadSeparators(ScImportAsciiCall eCall, OUString&
rFieldSeparators, OUString& rTextSeparators,
bool& rMergeDelimiters, bool& rQuotedAsText,
bool& rDetectSpecialNum, bool& rDetectScientificNum,
- SeparatorType& rSepType, sal_Int32& rFromRow,
sal_Int32& rCharSet,
+ SeparatorType& rSepType, sal_Int32& rFromRow,
rtl_TextEncoding& rEncoding,
sal_Int32& rLanguage, bool& rSkipEmptyCells,
bool& rRemoveSpace,
bool& rEvaluateFormulas)
{
@@ -168,6 +168,8 @@ static void lcl_LoadSeparators(ScImportAsciiCall eCall,
OUString& rFieldSeparato
const Sequence<OUString> aNames = aItem.GetNodeNames({});
const Sequence<Any> aValues = aItem.GetProperties(aNames);
+ rEncoding = RTL_TEXTENCODING_DONTKNOW;
+
for (sal_Int32 i = 0; i < aNames.getLength(); ++i)
{
const OUString& name = aNames[i];
@@ -188,8 +190,8 @@ static void lcl_LoadSeparators(ScImportAsciiCall eCall,
OUString& rFieldSeparato
rEvaluateFormulas = ScUnoHelpFunctions::GetBoolFromAny(value);
else if (name == CSVIO_FromRow)
value >>= rFromRow;
- else if (name == CSVIO_CharSet)
- value >>= rCharSet;
+ else if (name == CSVIO_Encoding)
+ value >>= rEncoding;
else if (name == CSVIO_QuotedAsText)
value >>= rQuotedAsText;
else if (name == CSVIO_DetectSpecialNum)
@@ -206,7 +208,7 @@ static void lcl_LoadSeparators(ScImportAsciiCall eCall,
OUString& rFieldSeparato
static void lcl_SaveSeparators(ScImportAsciiCall eCall,
const OUString& sFieldSeparators, const OUString& sTextSeparators, bool
bMergeDelimiters, bool bQuotedAsText,
bool bDetectSpecialNum, bool bDetectScientificNum, SeparatorType rSepType,
sal_Int32 nFromRow,
- sal_Int32 nCharSet, sal_Int32 nLanguage, bool bSkipEmptyCells, bool
bRemoveSpace, bool bEvaluateFormulas)
+ rtl_TextEncoding eEncoding, sal_Int32 nLanguage, bool bSkipEmptyCells,
bool bRemoveSpace, bool bEvaluateFormulas)
{
ScLinkConfigItem aItem(lcl_GetConfigPath(eCall));
std::unordered_map<OUString, Any> properties;
@@ -227,8 +229,8 @@ static void lcl_SaveSeparators(ScImportAsciiCall eCall,
properties[name] <<= static_cast<sal_Int16>(rSepType);
else if (name == CSVIO_FromRow)
properties[name] <<= nFromRow;
- else if (name == CSVIO_CharSet)
- properties[name] <<= nCharSet;
+ else if (name == CSVIO_Encoding)
+ properties[name] <<= eEncoding;
else if (name == CSVIO_QuotedAsText)
properties[name] <<= bQuotedAsText;
else if (name == CSVIO_DetectSpecialNum)
@@ -325,12 +327,12 @@ ScImportAsciiDlg::ScImportAsciiDlg(weld::Window* pParent,
std::u16string_view aD
bool bSkipEmptyCells = true;
bool bRemoveSpace = false;
sal_Int32 nFromRow = 1;
- sal_Int32 nCharSet = -1;
+ rtl_TextEncoding eEncoding = RTL_TEXTENCODING_DONTKNOW;
sal_Int32 nLanguage = 0;
lcl_LoadSeparators ( meCall, sFieldSeparators, sTextSeparators,
bMergeDelimiters,
bQuotedFieldAsText, bDetectSpecialNum,
bDetectScientificNum, eSepType, nFromRow,
- nCharSet, nLanguage, bSkipEmptyCells, bRemoveSpace,
bEvaluateFormulas);
+ eEncoding, nLanguage, bSkipEmptyCells, bRemoveSpace,
bEvaluateFormulas);
maFieldSeparators = sFieldSeparators;
@@ -367,10 +369,6 @@ ScImportAsciiDlg::ScImportAsciiDlg(weld::Window* pParent,
std::u16string_view aD
else
mxRbDetectSep->set_active(true);
- // Clipboard is always Unicode, else rely on default/config.
- rtl_TextEncoding ePreselectUnicode = (meCall == SC_IMPORTFILE ?
- RTL_TEXTENCODING_DONTKNOW : RTL_TEXTENCODING_UNICODE);
-
// Detect character set only once and then use it for "Detect" option.
SvStreamEndian eEndian;
SfxObjectShell::DetectCharSet(*mpDatStream, meDetectedCharSet, eEndian);
@@ -425,12 +423,13 @@ ScImportAsciiDlg::ScImportAsciiDlg(weld::Window* pParent,
std::u16string_view aD
// Insert one for detecting charset.
mxLbCharSet->InsertTextEncoding( RTL_TEXTENCODING_USER_DETECTED, "- " +
ScResId( SCSTR_AUTOMATIC ) + " -" );
- if (ePreselectUnicode != RTL_TEXTENCODING_DONTKNOW)
- mxLbCharSet->SelectTextEncoding( ePreselectUnicode );
- else if (nCharSet >= 0)
- mxLbCharSet->set_active(nCharSet);
- else
- mxLbCharSet->SelectTextEncoding(RTL_TEXTENCODING_USER_DETECTED);
+ // Clipboard is always Unicode, and TextToColumns doesn't use encoding.
+ if (meCall != SC_IMPORTFILE)
+ eEncoding = RTL_TEXTENCODING_UNICODE;
+ else if (eEncoding == RTL_TEXTENCODING_DONTKNOW)
+ eEncoding = RTL_TEXTENCODING_USER_DETECTED;
+
+ mxLbCharSet->SelectTextEncoding(eEncoding);
SetSelectedCharSet();
mxLbCharSet->connect_changed( LINK( this, ScImportAsciiDlg, CharSetHdl ) );
@@ -476,6 +475,8 @@ ScImportAsciiDlg::ScImportAsciiDlg(weld::Window* pParent,
std::u16string_view aD
if (meCall == SC_TEXTTOCOLUMNS)
{
+ m_xBuilder->weld_frame(u"frame1"_ustr)->hide(); // the whole "Import"
section
+
mxFtCharSet->set_sensitive(false);
mxLbCharSet->set_sensitive(false);
mxFtCustomLang->set_sensitive(false);
@@ -622,7 +623,7 @@ void ScImportAsciiDlg::SaveParameters()
mxCkbQuotedAsText->get_active(),
mxCkbDetectNumber->get_active(), mxCkbDetectScientificNumber->get_active(),
mxRbFixed->get_active() ? FIXED :
(mxRbDetectSep->get_active() ? DETECT_SEPARATOR : SEPARATOR),
mxNfRow->get_value(),
- mxLbCharSet->get_active(),
+ mxLbCharSet->GetSelectTextEncoding(),
static_cast<sal_uInt16>(mxLbCustomLang->get_active_id()),
mxCkbSkipEmptyCells->get_active(),
mxCkbRemoveSpace->get_active(),
mxCkbEvaluateFormulas->get_active());
