/*!
Construct encoding class
Find out which encodings the iconv on this system supports.
We try several possible names for each encoding.
If any name is successfully opened it becomes the only name for this encoding.
If no name is successfully opened the encoding is removed from the table.
*/
UT_Encoding::UT_Encoding()
{
if (s_Init) //only do this once
{
const XAP_StringSet * pSS = XAP_App::getApp()->getStringSet();
// Test all the encodings in our master table
// Build a list of only those supported by the current iconv
UT_uint32 iCheckIndex = 0;
UT_uint32 iOkayIndex = 0;
while (iCheckIndex < G_N_ELEMENTS(s_Table))
{
const gchar * szName = pSS->getValue(s_Table[iCheckIndex].id);
const gchar * szEnc;
UT_uint32 iAltIndex;
bool bFound = false;
UT_DEBUGMSG(("Encoding '%s' = ",s_Table[iCheckIndex].encs[0]));
for (iAltIndex = 0; (szEnc = s_Table[iCheckIndex].encs[iAltIndex]); ++iAltIndex)
{
UT_iconv_t iconv_handle = UT_iconv_open(szEnc,szEnc);
if (UT_iconv_isValid(iconv_handle))
{
bFound = true;
UT_iconv_close(iconv_handle);
s_Table[iOkayIndex].encs[0] = szEnc;
s_Table[iOkayIndex].encs[1] = 0;
s_Table[iOkayIndex].desc = szName;
s_Table[iOkayIndex].id = s_Table[iCheckIndex].id;
UT_DEBUGMSG(("'%s' (alias %d)\n",szEnc,iAltIndex+1));
++iOkayIndex;
break;
}
}
if (bFound == false)
{
UT_DEBUGMSG(("** Not supported **\n"));
}
++iCheckIndex;
}
s_iCount = iOkayIndex;
qsort(s_Table, s_iCount, sizeof(enc_entry), s_compareQ);
s_Init = false;
}
}
void ev_Win32Keyboard::remapKeyboard(HKL hKeyboardLayout)
{
char szCodePage[16];
if( m_iconv != UT_ICONV_INVALID )
{
UT_iconv_close( m_iconv );
m_iconv = UT_ICONV_INVALID;
}
if( hKeyboardLayout != 0 )
{
strcpy( szCodePage, "CP" );
if( GetLocaleInfo( LOWORD( hKeyboardLayout ),
LOCALE_IDEFAULTANSICODEPAGE,
&szCodePage[2],
sizeof( szCodePage ) / sizeof( szCodePage[0] ) - 2 ))
{
// Unicode locale?
// NT-based systems (at least XP) always produce unicode input irrespective of
// the ANSI locale -- see WM_CHAR on MSDN and bug 9374
//
// (It would be more efficient to do the NT test before calling
// GetLocaleInfo(), but for maintanence reasons it is better here.)
if( UT_IsWinNT() || !strcmp( szCodePage, "CP0" ) )
{
const char *szUCS2Name
= XAP_EncodingManager::get_instance()->getNativeUnicodeEncodingName();
UT_ASSERT(szUCS2Name);
m_bIsUnicodeInput = true;
strcpy( szCodePage, szUCS2Name );
}
else
m_bIsUnicodeInput = false;
UT_DEBUGMSG(("New keyboard codepage: %s\n",szCodePage));
m_iconv = UT_iconv_open( "UCS-4-INTERNAL", szCodePage );
}
m_hKeyboardLayout = hKeyboardLayout;
}
}
ev_Win32Keyboard::~ev_Win32Keyboard()
{
if( m_iconv != UT_ICONV_INVALID )
UT_iconv_close( m_iconv );
}
UT_Error IE_Imp_StarOffice::_loadFile(GsfInput * input)
{
try {
UT_DEBUGMSG(("SDW: Starting import\n"));
mOle = GSF_INFILE (gsf_infile_msole_new(input, NULL));
if (!mOle)
return UT_IE_BOGUSDOCUMENT;
// firstly, load metadata
SDWDocInfo::load(mOle, getDoc());
mDocStream = gsf_infile_child_by_name(mOle, "StarWriterDocument");
if (!mDocStream)
return UT_IE_BOGUSDOCUMENT;
gsf_off_t size = gsf_input_size(mDocStream);
if (!appendStrux(PTX_Section, PP_NOPROPS))
return UT_IE_NOMEMORY;
UT_DEBUGMSG(("SDW: Attempting to load DocHdr...\n"));
mDocHdr.load(mDocStream);
UT_DEBUGMSG(("SDW: ...success\n"));
// Ask for and verify the password
if (mDocHdr.cryptor) {
if (!mDocHdr.cryptor->SetPassword(GetPassword().c_str())) {
UT_DEBUGMSG(("SDW: Wrong password\n"));
return UT_IE_PROTECTED;
}
}
// do the actual reading
char type;
bool done = false;
UT_uint32 recSize;
while (!done) {
if (gsf_input_tell(mDocStream) == size)
break;
readChar(mDocStream, type);
gsf_off_t eor;
readRecSize(mDocStream, recSize, &eor);
switch (type) {
case SWG_CONTENTS: {
gsf_off_t flagsEnd = 0;
UT_uint32 nNodes;
// sw/source/core/sw3io/sw3sectn.cxx#L129
if (mDocHdr.nVersion >= SWG_LAYFRAMES) {
UT_uint8 flags;
readFlagRec(mDocStream, flags, &flagsEnd);
}
if (mDocHdr.nVersion >= SWG_LONGIDX)
streamRead(mDocStream, nNodes);
else {
if (mDocHdr.nVersion >= SWG_LAYFRAMES) {
UT_uint16 sectidDummy;
streamRead(mDocStream, sectidDummy);
}
UT_uint16 nodes16;
streamRead(mDocStream, nodes16);
nNodes = (UT_uint32)nodes16;
}
if (flagsEnd) {
UT_ASSERT(flagsEnd >= gsf_input_tell(mDocStream));
if (gsf_input_tell(mDocStream) != flagsEnd) {
UT_DEBUGMSG(("SDW: have not read all flags\n"));
if (gsf_input_seek(mDocStream, flagsEnd, G_SEEK_SET))
return UT_IE_BOGUSDOCUMENT;
}
}
bool done2 = false;
UT_uint32 size2;
while (!done2) {
readChar(mDocStream, type);
gsf_off_t eor2;
readRecSize(mDocStream, size2, &eor2);
switch (type) {
case SWG_TEXTNODE: { // sw/source/core/sw3io/sw3nodes.cxx#L788
UT_DEBUGMSG(("SDW: Found Textnode! (start at 0x%08llX end at 0x%08llX)\n",
(long long)gsf_input_tell(mDocStream),
(long long)eor2));
UT_uint8 flags;
gsf_off_t newPos;
readFlagRec(mDocStream, flags, &newPos);
// XXX check flags
if (gsf_input_seek(mDocStream, newPos, G_SEEK_SET))
return UT_IE_BOGUSDOCUMENT;
// Read the actual text
UT_UCS4Char* str;
readByteString(mDocStream, str);
UT_UCS4String textNode(str);
free(str);
UT_DEBUGMSG(("SDW: ...length=%zu contents are: |%s|\n", textNode.length(), textNode.utf8_str()));
// now get the attributes
UT_String attrs;
UT_String pAttrs;
UT_Vector charAttributes;
while (gsf_input_tell(mDocStream) < eor2) {
char attVal;
streamRead(mDocStream, attVal);
UT_uint32 attSize;
gsf_off_t eoa; // end of attribute
readRecSize(mDocStream, attSize, &eoa);
if (attVal == SWG_ATTRIBUTE) {
TextAttr* a = new TextAttr;
streamRead(mDocStream, *a, eoa);
UT_DEBUGMSG(("SDW: ...found text-sub-node, which=0x%x, ver=0x%x, start=%u, end=%u - data:%s len:%llu data is:",
a->which, a->ver, a->start,
a->end, a->data?"Yes":"No",
(long long unsigned)a->dataLen));
#ifdef DEBUG
hexdump(a->data, a->dataLen);
putc('\n', stderr);
#endif
charAttributes.addItem(a);
}
else if (attVal == SWG_ATTRSET) {
// bah, yet another loop
UT_DEBUGMSG(("SDW: ...paragraph attributes found\n"));
while (gsf_input_tell(mDocStream) < eoa) {
// reusing attVal and attSize
streamRead(mDocStream, attVal);
gsf_off_t eoa2; // end of attribute
readRecSize(mDocStream, attSize, &eoa2);
if (attVal == SWG_ATTRIBUTE) {
TextAttr a;
streamRead(mDocStream, a, eoa2);
if (!a.attrVal.empty()) {
if (a.isPara)
UT_String_setProperty(pAttrs, a.attrName, a.attrVal);
else
UT_String_setProperty(attrs, a.attrName, a.attrVal);
}
UT_DEBUGMSG(("SDW: ......found paragraph attr, which=0x%x, ver=0x%x, start=%u, end=%u (string now %s) Data:%s Len=%lld Data:", a.which, a.ver, (a.startSet?a.start:0), (a.endSet?a.end:0), attrs.c_str(), (a.data ? "Yes" : "No"), (long long)a.dataLen));
#ifdef DEBUG
hexdump(a.data, a.dataLen);
putc('\n', stderr);
#endif
}
if (gsf_input_seek(mDocStream, eoa2, G_SEEK_SET))
return UT_IE_BOGUSDOCUMENT;
}
}
else {
UT_DEBUGMSG(("SDW: ...unknown attribute '%c' found (start=%" GSF_OFF_T_FORMAT " end=%" GSF_OFF_T_FORMAT ")\n", attVal, gsf_input_tell(mDocStream), eoa));
}
if (gsf_input_seek(mDocStream, eoa, G_SEEK_SET))
return UT_IE_BOGUSDOCUMENT;
}
PP_PropertyVector attributes = {
"props",
pAttrs.c_str()
};
// first, insert the paragraph
if (!appendStrux(PTX_Block, attributes))
return UT_IE_NOMEMORY;
UT_String pca(attrs); // character attributes for the whole paragraph
// now insert the spans of text
UT_uint32 len = textNode.length();
UT_uint32 lastInsPos = 0;
for (UT_uint32 i = 1; i < len; i++) {
bool doInsert = false; // whether there was an attribute change
for (UT_sint32 j = 0; j < charAttributes.getItemCount(); j++) {
const TextAttr* a = reinterpret_cast<const TextAttr*>(charAttributes[j]);
// clear the last attribute, if set
if (a->endSet && a->end == (i - 1)) {
if (a->isOff) {
UT_String propval = UT_String_getPropVal(pca, a->attrName);
UT_String_setProperty(attrs, a->attrName, propval);
}
else
UT_String_removeProperty(attrs, a->attrName);
}
// now set new attribute, if needed
if (a->startSet && a->start == (i - 1)) {
if (a->isPara)
UT_String_setProperty(pAttrs, a->attrName, a->attrVal);
else if (a->isOff)
UT_String_removeProperty(attrs, a->attrName);
else
UT_String_setProperty(attrs, a->attrName, a->attrVal);
}
// insert if this is the last character, or if there was a format change
if ((a->endSet && a->end == i) || (a->startSet && a->start == i))
doInsert = true;
}
if (doInsert || i == (len - 1)) {
attributes[1] = attrs.c_str();
UT_DEBUGMSG(("SDW: Going to appendFmt with %s\n", attributes[1].c_str()));
if (!appendFmt(attributes))
return UT_IE_NOMEMORY; /* leave cast alone! */
UT_DEBUGMSG(("SDW: About to insert %u-%u\n", lastInsPos, i));
size_t spanLen = i - lastInsPos;
if (i == (len - 1)) spanLen++;
UT_UCS4String span = textNode.substr(lastInsPos, spanLen);
appendSpan(span.ucs4_str(), spanLen);
lastInsPos = i;
}
}
UT_VECTOR_PURGEALL(TextAttr*, charAttributes);
break;
}
case SWG_JOBSETUP: {
// flags are apparently unused here. no idea why they are there.
gsf_off_t newpos;
UT_uint8 flags;
readFlagRec(mDocStream, flags, &newpos);
if (gsf_input_seek(mDocStream, newpos, G_SEEK_SET))
return UT_IE_BOGUSDOCUMENT;
UT_uint16 len, system;
streamRead(mDocStream, len);
streamRead(mDocStream, system);
char printerName[64];
streamRead(mDocStream, printerName, 64);
char deviceName[32], portName[32], driverName[32];
streamRead(mDocStream, deviceName, 32);
streamRead(mDocStream, portName, 32);
streamRead(mDocStream, driverName, 32);
UT_DEBUGMSG(("SDW: Jobsetup: len %u sys 0x%x printer |%.64s| device |%.32s| port |%.32s| driver |%.32s|\n", len, system, printerName, deviceName, portName, driverName));
if (system == JOBSET_FILE364_SYSTEM || system == JOBSET_FILE605_SYSTEM) {
UT_uint16 len2, system2;
streamRead(mDocStream, len2);
streamRead(mDocStream, system2);
UT_uint32 ddl; // driver data length
streamRead(mDocStream, ddl);
// now the interesting data
UT_uint16 orient; // 0=portrait 1=landscape
streamRead(mDocStream, orient);
UT_uint16 paperBin;
streamRead(mDocStream, paperBin);
UT_uint16 paperFormat;
streamRead(mDocStream, paperFormat);
UT_uint32 width, height;
streamRead(mDocStream, width);
streamRead(mDocStream, height);
UT_DEBUGMSG(("SDW: orient %u bin %u format %u width %u height %u\n", orient, paperBin, paperFormat, width, height));
// rest of the data is ignored, seems to be printer specific anyway.
// Use A4, Portrait by default
PP_PropertyVector attributes = {
"pagetype", "a4", // A4/Letter/...
"orientation", "portrait",
"width", "210",
"height", "297",
"units", "mm"
};
const char* sdwPaperToAbi[] = {
"A3",
"A4",
"A5",
"B4",
"B5",
"Letter",
"Legal",
"Tabloid/Ledger",
"Custom"
};
if (paperFormat < sizeof(sdwPaperToAbi)/sizeof(*sdwPaperToAbi)) {
attributes[1] = sdwPaperToAbi[paperFormat];
}
const char* sdwOrientToAbi[] = {
"portrait",
"landscape"
};
if (orient < sizeof(sdwOrientToAbi)/sizeof(*sdwOrientToAbi)) {
attributes[3] = sdwOrientToAbi[orient];
}
attributes[5] = UT_std_string_sprintf("%f", static_cast<double>(width)/100);
attributes[7] = UT_std_string_sprintf("%f", static_cast<double>(height)/100);
getDoc()->setPageSizeFromFile(attributes);
}
break;
}
case SWG_EOF:
done2 = true;
break;
default:
UT_DEBUGMSG(("SDW: SWG_CONTENT: Skipping %u bytes for record type '%c' (starting at 0x%08llX)\n",
size2, type,
(long long)gsf_input_tell(mDocStream)));
}
if (gsf_input_seek(mDocStream, eor2, G_SEEK_SET))
return UT_IE_BOGUSDOCUMENT;
}
break;
}
case SWG_STRINGPOOL:
{
if (mDocHdr.nVersion <= SWG_POOLIDS) {
UT_ASSERT_HARMLESS(UT_NOT_IMPLEMENTED);
break;
}
UT_uint8 encoding;
streamRead(mDocStream, encoding);
UT_iconv_t cd = findConverter(encoding);
if (!UT_iconv_isValid(cd))
throw UT_IE_IMPORTERROR;
UT_uint16 count;
streamRead(mDocStream, count);
while (count--) {
UT_uint16 id;
streamRead(mDocStream, id);
char* str;
UT_uint16 len;
::readByteString(mDocStream, str, &len);
if (id == IDX_NOCONV_FF) {
UT_ASSERT_HARMLESS(UT_NOT_IMPLEMENTED);
}
// FIXME: find a way to not have to copy and free
// the result of UT_convert_cd.... --hub
UT_DEBUGMSG(("SDW: StringPool: found 0x%04x <-> %.*s\n", id, len, str));
UT_UCS4Char* convertedString = reinterpret_cast<UT_UCS4Char*>(UT_convert_cd(str, len + 1, cd, NULL, NULL));
mStringPool.insert(stringpool_map::value_type(id, convertedString));
FREEP(convertedString);
delete [] str;
}
UT_iconv_close(cd);
break;
}
case SWG_COMMENT: // skip over comments
break;
case SWG_EOF:
done = true;
break;
default:
UT_DEBUGMSG(("SDW: Skipping %u bytes for record type '%c' (starting at 0x%08llX)\n", recSize, type, (long long)gsf_input_tell(mDocStream)));
}
// Seek to the end of the record, in case it wasn't read completely
if (gsf_input_seek(mDocStream, eor, G_SEEK_SET))
return UT_IE_BOGUSDOCUMENT;
}
UT_DEBUGMSG(("SDW: Done\n"));
return UT_OK;
}
catch(UT_Error e) {
UT_DEBUGMSG(("SDW: error %d\n", e));
return e;
}
catch(...) {
UT_DEBUGMSG(("SDW: Unknown error\n"));
return UT_IE_BOGUSDOCUMENT;
}
}
