Region::Shape::Shape(const IntRect& rect) { appendSpan(rect.y()); appendSegment(rect.x()); appendSegment(rect.maxX()); appendSpan(rect.maxY()); }
void IE_Imp_WordPerfect::insertLineBreak() { if (m_bHdrFtrOpenCount) return; // HACK UT_DEBUGMSG(("AbiWordPerfect: insertLineBreak\n")); UT_UCSChar ucs = UCS_LF; X_CheckDocumentError(appendSpan(&ucs,1)); }
void IE_Imp_WordPerfect::insertSpace() { if (m_bHdrFtrOpenCount) return; // HACK UT_DEBUGMSG(("AbiWordPerfect: insertSpace\n")); UT_UCS4Char ucs = UCS_SPACE; X_CheckDocumentError(appendSpan(&ucs,1)); }
void Region::Shape::appendSpan(int y, SegmentIterator begin, SegmentIterator end) { if (canCoalesce(begin, end)) return; appendSpan(y); m_segments.appendRange(begin, end); }
void IE_Imp_WordPerfect::insertText(const librevenge::RVNGString &text) { if (m_bHdrFtrOpenCount) return; // HACK if (text.len()) { UT_DEBUGMSG(("AbiWordPerfect: insertText\n")); UT_UCS4String ucs4(text.cstr()); X_CheckDocumentError(appendSpan(ucs4.ucs4_str(), ucs4.length())); } }
bool DocumentColorizer::project(Ref<Token> token, int i0, int i1) { while (true) { if (i0 < k1_) { int j1 = i1; if (i1 > k1_) j1 = k1_ - 1; int s0 = i0 - k0_, sn = j1 - i0; // index range of span int nl = k1_ - k0_ - 1; // text_.length(); // line length if (s0 + sn > nl) --sn; // strip newline if ((sn > 0) && (s0 < nl)) { // omit empty matches /*Ref<LanguageProvider> provider = languageManager_->languageProvider(token->definitionId()); Ref<pte::Style> style = provider->style(token->rule());*/ Ref<pte::Style> style; for (Ref<Token> candidate = token; (!style) && (candidate); candidate = candidate->parent()) { style = languageManager_->layerByDefinitionId(candidate->definition())->style(candidate->rule()); // qDebug() << "up"; } if (!style) style = document_->defaultStyle(); appendSpan(s0, sn, style, token); /*qDebug() << "token->countChildren() =" << token->countChildren(); qDebug() << "appendSpan(" << languageManager_->layerByDefinitionId(token->definition())->syntax()->name() << languageManager_->layerByDefinitionId(token->definition())->syntax()->numRules() << token->rule() << y_ << i0 << i1 << text().mid(s0, sn) << style.get() << (style == document_->defaultStyle() )<< ")";*/ } /*else { Ref<LanguageProvider> provider = languageManager_->languageProvider(token->definition()); Ref<pte::Style> style = provider->style(token->rule()); // qDebug() << "dropSpan(" << token->ruleName() << y_ << i0 << i1 << text().mid(s0, sn) << style.get() << ")"; }*/ if (k1_ < i1) { i0 = k1_; continue; } } else { if (!singleLine_) { // implicit logic HACK, needs improvment if (highlighter_) if (!highlighter_->synchronise()) { // print("\n-- yielded --\n"); return false; } } // if (stayOnLine_) // qDebug() << "nextLine(" << text_ << y_ << k0_ << k1_ << ")"; if (nextLine()) { continue; // print("\n%%:", y_); } } break; } return true; }
UT_Error IE_Imp_Hancom::_loadFile(GsfInput * input) { mDoc = GSF_INFILE(gsf_infile_msole_new (input, NULL)); if (!mDoc) return UT_IE_BOGUSDOCUMENT; GsfInput *textStream = gsf_infile_child_by_name(mDoc, "/PrvText"); if (!textStream) return UT_IE_BOGUSDOCUMENT; size_t len = gsf_input_size(textStream); UT_DEBUGMSG(("HANCOM: Text length = %zd bytes\n", len)); unsigned char* buf = new unsigned char[len]; if (!buf) { g_object_unref (G_OBJECT (textStream)); return UT_IE_NOMEMORY; } gsf_input_read(textStream, len, buf); g_object_unref (G_OBJECT (textStream)); UT_uint32 length; UT_UCS4Char* text = reinterpret_cast<UT_UCS4Char*>(UT_convert((const char *)buf, len, "UCS-2LE", UCS_INTERNAL, NULL, &length)); delete[] buf; if (!text) return UT_IE_NOMEMORY; UT_DEBUGMSG(("HANCOM: Text successfully converted.\n")); if (!appendStrux(PTX_Section, NULL)) { FREEP(text); return UT_IE_NOMEMORY; } if (!appendStrux(PTX_Block, NULL)) { FREEP(text); return UT_IE_NOMEMORY; } if (!appendSpan(text, length/4)) { FREEP(text); return UT_IE_NOMEMORY; } FREEP(text); return UT_OK; }
std::pair< PT_DocPosition, PT_DocPosition > IE_Imp_RDF::insertTextWithXMLID( const std::string& textconst, const std::string& xmlid ) { std::string text = " " + textconst + " "; PT_DocPosition startpos = getDocPos(); // FIXME /*bool bRes =*/ appendSpan( text ); PT_DocPosition endpos = getDocPos(); startpos++; endpos--; XAP_Frame* lff = XAP_App::getApp()->getLastFocussedFrame(); if(lff) { FV_View * pView = static_cast<FV_View*>( lff->getCurrentView() ); pView->selectRange( startpos, endpos ); pView->cmdInsertXMLID( xmlid ); } return std::make_pair( startpos, endpos ); }
UT_Error IE_Imp_PalmDoc::_parseFile(GsfInput * pdfp) { UT_GrowBuf gbBlock(1024); bool bEatLF = false; bool bEmptyFile = true; UT_UCSChar c; UT_UCS4Char wc; pdb_header header; doc_record0 rec0; bool bCompressed = false; int num_records, rec_num; DWord file_size, offset; gsf_input_read( pdfp, PDB_HEADER_SIZE, (guint8*)&header); if (strncmp( header.type, DOC_TYPE, sizeof(header.type) ) || strncmp( header.creator, DOC_CREATOR, sizeof(header.creator) )) { UT_DEBUGMSG(("This is not a DOC file!\n")); // Create an empty paragraph. X_ReturnNoMemIfError(appendStrux(PTX_Block, NULL)); return UT_OK; } num_records = _swap_Word( header.numRecords ) - 1; gsf_input_seek( pdfp, PDB_HEADER_SIZE, G_SEEK_SET ); GET_DWord( pdfp, offset ); gsf_input_seek( pdfp, offset, G_SEEK_SET ); gsf_input_read( pdfp, sizeof(rec0), (guint8*)&rec0); if ( _swap_Word( rec0.version ) == 2 ) bCompressed = true; gsf_input_seek( pdfp, 0, G_SEEK_END ); file_size = gsf_input_tell( pdfp ); for (rec_num = 1; rec_num <= num_records; ++rec_num ) { DWord next_offset; gsf_input_seek( pdfp, PDB_HEADER_SIZE + PDB_RECORD_HEADER_SIZE * rec_num, G_SEEK_SET); GET_DWord( pdfp, offset ); if( rec_num < num_records ) { gsf_input_seek( pdfp, PDB_HEADER_SIZE + PDB_RECORD_HEADER_SIZE * (rec_num + 1), G_SEEK_SET); GET_DWord( pdfp, next_offset ); } else next_offset = file_size; gsf_input_seek( pdfp, offset, G_SEEK_SET ); // be overly cautious here _zero_fill (m_buf->buf, BUFFER_SIZE); gsf_input_read(pdfp, next_offset - offset, m_buf->buf); m_buf->position = next_offset - offset; if ( bCompressed ) _uncompress( m_buf ); m_buf->position = 0; while ( (m_buf->position) < (m_buf->len) ) { // don't copy over null chars if (m_buf->buf[m_buf->position] == '\0') { ++m_buf->position; continue; } if( !m_Mbtowc.mbtowc( wc, m_buf->buf[m_buf->position] ) ) continue; c = static_cast<UT_UCSChar>(wc); switch (c) { case static_cast<UT_UCSChar>('\r'): case static_cast<UT_UCSChar>('\n'): if ((c == static_cast<UT_UCSChar>('\n')) && bEatLF) { bEatLF = false; break; } if (c == static_cast<UT_UCSChar>('\r')) { bEatLF = true; } // we interprete either CRLF, CR, or LF as a paragraph break. // start a paragraph and emit any text that we // have accumulated. X_ReturnNoMemIfError(appendStrux(PTX_Block, NULL)); bEmptyFile = false; if (gbBlock.getLength() > 0) { X_ReturnNoMemIfError(appendSpan(reinterpret_cast<const UT_UCSChar*>(gbBlock.getPointer(0)), gbBlock.getLength())); gbBlock.truncate(0); } break; default: bEatLF = false; X_ReturnNoMemIfError(gbBlock.ins(gbBlock.getLength(),reinterpret_cast<const UT_GrowBufElement *>(&c),1)); break; } ++m_buf->position; } } if (gbBlock.getLength() > 0 || bEmptyFile) { // if we have text left over (without final CR/LF), // or if we read an empty file, // create a paragraph and emit the text now. X_ReturnNoMemIfError(appendStrux(PTX_Block, NULL)); if (gbBlock.getLength() > 0) X_ReturnNoMemIfError(appendSpan(reinterpret_cast<const UT_UCSChar *>(gbBlock.getPointer(0)), gbBlock.getLength())); } return UT_OK; }
// ASSUMPTION: We assume that unordered lists will always pass a number of "0". unpredictable behaviour // may result otherwise void IE_Imp_WordPerfect::openListElement(const librevenge::RVNGPropertyList &propList) { if (m_bHdrFtrOpenCount) return; // HACK UT_DEBUGMSG(("AbiWordPerfect: openListElement\n")); UT_ASSERT(m_pCurrentListDefinition); // FIXME: ABI_LISTS_IMPORT throw an exception back to libwpd, if this fails // Paragraph properties for our list element UT_String szListID; UT_String szParentID; UT_String szLevel; UT_String_sprintf(szListID,"%d",m_pCurrentListDefinition->getListID(m_iCurrentListLevel)); if (m_iCurrentListLevel > 1) UT_String_sprintf(szParentID,"%d", m_pCurrentListDefinition->getListID((m_iCurrentListLevel-1))); else UT_String_sprintf(szParentID,"0"); UT_String_sprintf(szLevel,"%d", m_iCurrentListLevel); const gchar* listAttribs[PT_MAX_ATTRIBUTES*2 + 1]; UT_uint32 attribsCount=0; listAttribs[attribsCount++] = PT_LISTID_ATTRIBUTE_NAME; listAttribs[attribsCount++] = szListID.c_str(); listAttribs[attribsCount++] = PT_PARENTID_ATTRIBUTE_NAME; listAttribs[attribsCount++] = szParentID.c_str(); listAttribs[attribsCount++] = PT_LEVEL_ATTRIBUTE_NAME; listAttribs[attribsCount++] = szLevel.c_str(); // Now handle the Abi List properties UT_String propBuffer; UT_String tempBuffer; UT_String_sprintf(tempBuffer,"list-style:%i;", m_pCurrentListDefinition->getListType(m_iCurrentListLevel)); propBuffer += tempBuffer; #if 0 // FIXME: writing the list delimiter is kind of tricky and silly (because wordperfect wants to define // it within the document, while abi wants to (sensibly probably) define it in the list definition) // (we reset it each time but only for numbered lists) if (listDefinition->isLevelNumbered(m_iCurrentListLevel)) { UT_DEBUGMSG(("WordPerfect: Appending this list delim: %s\n", m_rightListDelim.c_str())); listDefinition->setListRightDelimText(m_iCurrentListLevel, m_rightListDelim.c_str()); X_CheckWordPerfectError(_updateDocumentListDefinition(listDefinition, m_iCurrentListLevel)); } #endif if (m_pCurrentListDefinition->getListType(m_iCurrentListLevel) == BULLETED_LIST) UT_String_sprintf(tempBuffer, "field-font:Symbol; "); else UT_String_sprintf(tempBuffer, "field-font:NULL; "); m_pCurrentListDefinition->incrementLevelNumber(m_iCurrentListLevel); propBuffer += tempBuffer; UT_String_sprintf(tempBuffer, "start-value:%i; ", 1); propBuffer += tempBuffer; UT_String_sprintf(tempBuffer, "margin-left:%.4fin; ", m_pCurrentListDefinition->getListLeftOffset(m_iCurrentListLevel) + m_pCurrentListDefinition->getListMinLabelWidth(m_iCurrentListLevel) - (propList["fo:text-indent"] ? propList["fo:text-indent"]->getDouble() : 0.0f)); propBuffer += tempBuffer; UT_String_sprintf(tempBuffer, "text-indent:%.4fin", - m_pCurrentListDefinition->getListMinLabelWidth(m_iCurrentListLevel) + (propList["fo:text-indent"] ? propList["fo:text-indent"]->getDouble() : 0.0f)); propBuffer += tempBuffer; listAttribs[attribsCount++] = PT_PROPS_ATTRIBUTE_NAME; listAttribs[attribsCount++] = propBuffer.c_str(); listAttribs[attribsCount++] = NULL; X_CheckDocumentError(appendStrux(PTX_Block, PP_std_copyProps(listAttribs))); m_bRequireBlock = false; // hang text off of a list label getDoc()->appendFmtMark(); UT_DEBUGMSG(("WordPerfect: LISTS - Appended a list tag def'n (character props)\n")); // append a list field label PP_PropertyVector fielddef = { "type", "list_label" }; X_CheckDocumentError(appendObject(PTO_Field,fielddef)); UT_DEBUGMSG(("WordPerfect: LISTS - Appended a field def'n\n")); // insert a tab UT_UCS4Char ucs = UCS_TAB; X_CheckDocumentError(appendSpan(&ucs,1)); }
void IE_Imp_XML::charData(const gchar *s, int len) { // TODO gchar is defined in the xml parser // TODO as a 'char' not as a 'unsigned char'. // TODO does this cause any problems ?? xxx_UT_DEBUGMSG(("In IE_Imp_XML::charDat, len = %d parsestate %d \n",len,m_parseState)); if(!s || !len) return; X_EatIfAlreadyError(); // xml parser keeps running until buffer consumed switch (m_parseState) { case _PS_Block: case _PS_IgnoredWordsItem: case _PS_Meta: case _PS_Revision: { UT_UCS4String buf(s,static_cast<size_t>(len),!m_bWhiteSignificant); xxx_UT_DEBUGMSG(("In IE_Imp_XML::charData buf.size %d \n",buf.size())); // flush out the buffer if (buf.size() == 0) return; switch (m_parseState) { case _PS_Block: if (!m_bWhiteSignificant && m_bStripLeading && (buf[0] == UCS_SPACE)) { if (buf.size () > 1) { X_CheckError(appendSpan (buf.ucs4_str()+1, buf.size()-1)); m_iCharCount += buf.size () - 1; } } else { X_CheckError(appendSpan (buf.ucs4_str(), buf.size())); m_iCharCount += buf.size (); } m_bStripLeading = (buf[buf.size()-1] == UCS_SPACE); return; case _PS_IgnoredWordsItem: return; case _PS_Meta: { UT_UTF8String data(s,len); getDoc()->setMetaDataProp(m_currentMetaDataName, data); return; } case _PS_Revision: // 0 is not a valid revision Id if(m_currentRevisionId) { UT_DEBUGMSG(("Doing revision \n")); X_CheckError(getDoc()->addRevision(m_currentRevisionId, buf.ucs4_str(), buf.size(), m_currentRevisionTime, m_currentRevisionVersion)); // we need to reset the revision Id in order // to be able to handle the case when there is // no character data present in our // endofelement handler m_currentRevisionId = 0; } return; default: UT_ASSERT_NOT_REACHED(); return; } } case _PS_Field: { // discard contents of the field - force recalculation // this gives us a higher chance of correcting fields // with the wrong values return; } case _PS_DataItem: { #ifdef ENABLE_RESOURCE_MANAGER XAP_ResourceManager & RM = getDoc()->resourceManager (); XAP_Resource * resource = RM.current (); if (resource == 0) break; if (!resource->bInternal) break; XAP_InternalResource * ri = dynamic_cast<XAP_InternalResource *>(resource); if (m_currentDataItemEncoded) // base64-encoded data ri->buffer (s, len, true); else // old file-format keeping MathML & SVG in CDATA section :-( { /* since SVG import was only ever a DEBUG option, and is currently disabled (why?), * since MathML was never supported except in principle, and since this CDATA stuff * (unencoded) is pretty unsafe anyway, I'm going to postpone import support * indefinitely... - fjf Aug. 19th '02 */ } #else /* ENABLE_RESOURCE_MANAGER */ #define MyIsWhite(c) (((c)==' ') || ((c)=='\t') || ((c)=='\n') || ((c)=='\r')) if (m_currentDataItemEncoded) { // DataItem data consists of Base64 encoded data with // white space added for readability. strip out any // white space and put the rest in the ByteBuf. UT_return_if_fail ((sizeof(gchar) == sizeof(UT_Byte))); UT_uint32 actualLen = m_currentDataItem.getLength(); m_currentDataItem.ins(actualLen, len); // allocate all the possibly needed memory at once const UT_Byte * ss = reinterpret_cast<const UT_Byte *>(s); const UT_Byte * ssEnd = ss + len; while (ss < ssEnd) { while ((ss < ssEnd) && MyIsWhite(*ss)) ss++; UT_uint32 k=0; while ((ss+k < ssEnd) && ( ! MyIsWhite(ss[k]))) k++; if (k > 0) { m_currentDataItem.overwrite(actualLen, ss, k); actualLen += k; } ss += k; } m_currentDataItem.truncate(actualLen); // chop off the mem we don't need after all return; } else m_currentDataItem.append(reinterpret_cast<const UT_Byte*>(s), len); #undef MyIsWhite #endif /* ENABLE_RESOURCE_MANAGER */ } default: UT_DEBUGMSG(("ie_imp_XML::charData Default just return \n")); return; } }
void Region::Shape::appendSpans(const Shape& shape, SpanIterator begin, SpanIterator end) { for (SpanIterator it = begin; it != end; ++it) appendSpan(it->y, shape.segmentsBegin(it), shape.segmentsEnd(it)); }
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; } }
/*! Insert a span of text into the document \param b Buffer containing UCS text to insert Uses appropriate function for clipboard or file */ bool IE_Imp_Text::_insertSpan(UT_GrowBuf &b) { UT_uint32 iLength = b.getLength(); const UT_UCS4Char * pData = (const UT_UCS4Char *)b.getPointer(0); // handle block direction if needed ... if(pData && m_bBlockDirectionPending) { const UT_UCS4Char * p = pData; // we look for the first strong character for(UT_uint32 i = 0; i < iLength; i++, p++) { UT_BidiCharType type = UT_bidiGetCharType(*p); if(UT_BIDI_IS_STRONG(type)) { m_bBlockDirectionPending = false; // set 'dom-dir' property of the block ... const gchar * propsArray[3]; propsArray[0] = "props"; propsArray[1] = NULL; propsArray[2] = NULL; UT_String props("dom-dir:"); if(UT_BIDI_IS_RTL(type)) props += "rtl;text-align:right"; else props += "ltr;text-align:left"; propsArray[1] = props.c_str(); // we need to modify the existing formatting ... if(m_pBlock == NULL) { PL_StruxDocHandle sdh = NULL; if(getDoc()->getStruxOfTypeFromPosition(getDocPos(), PTX_Block,&sdh)) { m_pBlock = static_cast<pf_Frag_Strux *>(const_cast<void *>(sdh)); } } appendStruxFmt(m_pBlock, static_cast<const gchar **>(&propsArray[0])); // if this is the first data in the block and the first // character is LRM or RLM followed by a strong character, // then we will remove it if(m_bFirstBlockData && i==0 && iLength > 1 && (*p == UCS_LRM || *p == UCS_RLM)) { UT_BidiCharType next_type = UT_bidiGetCharType(*(p+1)); if(UT_BIDI_IS_STRONG(next_type)) { pData++; iLength--; } } break; } } } bool bRes = appendSpan (pData, iLength); b.truncate(0); m_bFirstBlockData = false; return bRes; }
bool IE_Imp_MSWrite::read_txt (int from, int to) { static const char *currcp; int fcMac, pnChar, fcFirst, cfod, fc, fcLim; unsigned char page[0x80]; UT_String properties, tmp; int dataLen = static_cast<UT_sint32>(mData.getLength()); UT_DEBUGMSG((" TXT:\n")); UT_DEBUGMSG((" from = %d\n", from)); UT_DEBUGMSG((" to = %d\n", to)); fcMac = wri_struct_value(wri_file_header, "fcMac"); pnChar = (fcMac + 127) / 128; fcFirst = 0x80; while (true) { gsf_input_seek(mFile, pnChar++ * 0x80, G_SEEK_SET); gsf_input_read(mFile, 0x80, page); fc = READ_DWORD(page); cfod = page[0x7f]; UT_DEBUGMSG((" fcFirst = %d\n", fc)); UT_DEBUGMSG((" cfod = %d\n", cfod)); if (fc != fcFirst) UT_WARNINGMSG(("read_txt: fcFirst wrong.\n")); // read all FODs (format descriptors) for (int fod = 0; fod < cfod; fod++) { int bfprop, cch, ftc, hps, fBold, fItalic, fUline, hpsPos; UT_DEBUGMSG((" CHP-FOD #%02d:\n", fod + 1)); // read a FOD (format descriptor) fcLim = READ_DWORD(page + 4 + fod * 6); bfprop = READ_WORD(page + 8 + fod * 6); UT_DEBUGMSG((" fcLim = %d\n", fcLim)); UT_DEBUGMSG((bfprop == 0xffff ? " bfprop = 0x%04X\n" : " bfprop = %d\n", bfprop)); // default CHP values ftc = 0; hps = 24; fBold = fItalic = fUline = hpsPos = 0; // if the CHP FPROPs (formatting properties) differ from the defaults, get them if (bfprop != 0xffff && bfprop + (cch = page[bfprop + 4]) < 0x80) { UT_DEBUGMSG((" cch = %d\n", cch)); if (cch >= 2) ftc = page[bfprop + 6] >> 2; if (cch >= 5) ftc |= (page[bfprop + 9] & 3) << 6; if (cch >= 3) hps = page[bfprop + 7]; if (cch >= 2) fBold = page[bfprop + 6] & 1; if (cch >= 2) fItalic = page[bfprop + 6] & 2; if (cch >= 4) fUline = page[bfprop + 8] & 1; if (cch >= 6) hpsPos = page[bfprop + 10]; } UT_DEBUGMSG((" ftc = %d\n", ftc)); UT_DEBUGMSG((" hps = %d\n", hps)); UT_DEBUGMSG((" fBold = %d\n", fBold)); UT_DEBUGMSG((" fItalic = %d\n", fItalic)); UT_DEBUGMSG((" fUline = %d\n", fUline)); UT_DEBUGMSG((" hpsPos = %d\n", hpsPos)); if (ftc >= wri_fonts_count) { UT_WARNINGMSG(("read_txt: Wrong font code.\n")); ftc = wri_fonts_count - 1; } if (from < fcLim && to >= fcFirst) { UT_LocaleTransactor lt(LC_NUMERIC, "C"); UT_String_sprintf(properties, "font-weight:%s", fBold ? "bold" : "normal"); if (hps != 24) { UT_String_sprintf(tmp, "; font-size:%dpt", hps / 2); properties += tmp; } if (fItalic) properties += "; font-style:italic"; if (fUline) properties += "; text-decoration:underline"; if (hpsPos) { UT_String_sprintf(tmp, "; text-position:%s", hpsPos < 128 ? "superscript" : "subscript"); properties += tmp; } if (wri_fonts_count) { UT_String_sprintf(tmp, "; font-family:%s", wri_fonts[ftc].name); properties += tmp; } if (wri_fonts[ftc].codepage != currcp /*sic!*/) { set_codepage(wri_fonts[ftc].codepage); currcp = wri_fonts[ftc].codepage; } mText.clear(); UT_DEBUGMSG((" Text: ")); while (fcFirst <= from && from < fcLim && from <= to && from - 0x80 < dataLen) translate_char(*mData.getPointer(from++ - 0x80), mText); UT_DEBUGMSG(("\n")); // new attributes, only if there was text if (mText.size() > 0) { const gchar *attributes[5]; const UT_UCS4Char *text = mText.ucs4_str(), *p = text; size_t txtLen; UT_DEBUGMSG((" Conv: %s\n", mText.utf8_str())); attributes[0] = PT_PROPS_ATTRIBUTE_NAME; attributes[1] = properties.c_str(); attributes[2] = NULL; appendFmt(attributes); // check for page number (should only be in header or footer) while (*p && *p != (UT_UCS4Char) 0x01) p++; if (*p) { if (p - text) appendSpan(text, p - text); attributes[2] = PT_TYPE_ATTRIBUTE_NAME; attributes[3] = "page_number"; attributes[4] = NULL; appendObject(PTO_Field, attributes); txtLen = mText.size() - (p - text) - 1; p++; } else { txtLen = mText.size(); p = text; } if (txtLen) appendSpan(p, txtLen); } } fcFirst = fcLim; if (fcLim >= fcMac || fcFirst > to) { UT_DEBUGMSG((" CHP-FODs end, fcLim (%d) >= fcMac (%d) or fcFirst (%d) > to (%d)\n", fcLim, fcMac, fcFirst, to)); return true; } } }
/*! * Read all Psion paragraphs and add them to the document. */ UT_Error IE_Imp_Psion::readParagraphs(const psiconv_text_and_layout psiontext, const psiconv_word_styles_section style_sec) // psiconv_list embobjlst) { unsigned int i,inline_nr; int loc; psiconv_paragraph paragraph; psiconv_in_line_layout in_line; UT_UCS4String text; psiconv_word_style style; const gchar *stylename; UT_Error res; // Iterate through all paragraphs for (i=0; i < psiconv_list_length(psiontext); i++) { UT_DEBUGMSG(("PSION: Importing paragraph %d\n",i)); if (!(paragraph = (psiconv_paragraph) psiconv_list_get(psiontext,i))) { // Something is really wrong... UT_ASSERT(paragraph != NULL); return UT_IE_IMPORTERROR; } // Determine the style name; set it to Normal if it is not available if (!style_sec || !(style = psiconv_get_style(style_sec,paragraph->base_style)) || (!style->name) || !(stylename = prepare_style_name(style->name))) stylename = (const gchar *) strdup("Normal"); if (!stylename) return UT_IE_NOMEMORY; UT_DEBUGMSG(("PSION: paragraph %d: style %s\n",i,stylename)); // Add all paragraph attributes to the document if ((res = applyParagraphAttributes(paragraph->base_paragraph,stylename))) return res; // Iterate through all Psion inlines. These contain the character // layout information, together with the number of characters they // apply to. loc = 0; for(inline_nr=0; inline_nr < psiconv_list_length(paragraph->in_lines); inline_nr++) { UT_DEBUGMSG(("Psion: paragraph %d inline %d\n",i,inline_nr)); if (!(in_line = (psiconv_in_line_layout) psiconv_list_get(paragraph->in_lines,inline_nr))) { // Something is really wrong... UT_ASSERT(in_line != NULL); return UT_IE_IMPORTERROR; } // This may be an object, which needs special handling. // Objects have layout associated with them, but we will ignore // it. I am not sure how it would apply anyway. We will also ignore // all text. It should just be a single character \016, which is the // object marker. if (in_line->object) { if ((res = insertObject(in_line))) return res; } else { // Put all characters belonging to the current inline into text text.clear(); if ((res = prepareCharacters(paragraph->text + loc,in_line->length, text))) return res; // Yes, text may be empty! if (text.length()) { // Add the character layout and the text itself to the document if ((res = applyCharacterAttributes(in_line->layout))) return res; if (!(appendSpan((text.ucs4_str()),text.length()))) return UT_IE_IMPORTERROR; } } loc += in_line->length; } // There may be text left after iterating through all inlines. // This remaining text gets the paragraph base_character layout. if (loc < psiconv_unicode_strlen(paragraph->text)) { // Get the remaining characters into text text.clear(); if ((res = prepareCharacters(paragraph->text+loc, psiconv_unicode_strlen(paragraph->text - loc),text))) return res; // Yes, text may be empty! if (text.length()) { // Add the character layout and the text itself to the document. if ((res = applyCharacterAttributes(paragraph->base_character))) return res; if (!appendSpan(text.ucs4_str(),text.length())) return UT_IE_IMPORTERROR; } } } return UT_OK; }
/*! * Get all paragraph-related attributes and add them to the document. * * It does an appendStrux setting the current paragraph attributes and opening * a new paragraph. Several special cases are handled here too, mostly for * bullets. */ UT_Error IE_Imp_Psion::applyParagraphAttributes(const psiconv_paragraph_layout layout, const gchar *stylename) { UT_return_val_if_fail(layout != NULL, true /* perhaps should be false, but we want loading to proceed */); UT_UTF8String props; UT_Error res; // Get all attributes into prop if ((res = getParagraphAttributes(layout,props))) return UT_IE_IMPORTERROR; // HACK: Handle bullets // This is really, really ugly. // We can not really select the bullet symbol to use, so we do not even // try and just use always the plain round bullet. // Indent magic is done in getParagraphAttributes. if (layout->bullet->on) { props += ";list-style:Bullet List;field-font:Symbol"; // We need to generate the list once, but only if we actually // have a bullet somewhere. Nasty. The attributes are mostly // black magickish... if (!list) { list = true; const PP_PropertyVector propsArray = { "id", global_listid, "parentid", "0", "type", "5", "start-value", "0", "list-delim", "%L", "list-decimal", "NULL" }; getDoc()->appendList(propsArray); } } // Prepare the properties for this paragraph strux UT_DEBUGMSG(("PSION: Paragraph: %s\n",props.utf8_str())); PP_PropertyVector propsArray = { "props", props.utf8_str(), "style", stylename }; // Bullets need the listid too. if (layout->bullet->on) { propsArray.push_back("listid"); propsArray.push_back(global_listid); } if (!(appendStrux(PTX_Block, propsArray))) { return UT_IE_IMPORTERROR; } // HACK: there is no real setting to do this. Yet. if (layout->on_next_page) { UT_UCSChar ucs = UCS_FF; if (!(appendSpan(&ucs,1))) return UT_IE_IMPORTERROR; } // We need to append a field and some other stuff... if (layout->bullet->on) { propsArray.resize(2); propsArray.push_back("type"); propsArray.push_back("list_label"); if (!(appendObject(PTO_Field,propsArray))) return UT_IE_IMPORTERROR; // In some cases, but not in all, we need a tab after the bullet. // See the Psiconv docs for the (ugly) details. if ((!layout->bullet->indent && (layout->indent_first > 0)) || layout->bullet->indent) { UT_UCSChar uc = (UT_UCSChar) UCS_TAB; if (!(appendSpan(&uc,1))) return UT_IE_IMPORTERROR; } } return UT_OK; }
void IE_Imp_WordPerfect::openParagraph(const librevenge::RVNGPropertyList &propList) { if (m_bHdrFtrOpenCount) return; // HACK UT_DEBUGMSG(("AbiWordPerfect: openParagraph()\n")); // for now, we always append these options float marginTop = 0.0f, marginBottom = 0.0f; float marginLeft = 0.0f, marginRight = 0.0f, textIndent = 0.0f; if (propList["fo:margin-top"]) marginTop = propList["fo:margin-top"]->getDouble(); if (propList["fo:margin-bottom"]) marginBottom = propList["fo:margin-bottom"]->getDouble(); if (propList["fo:margin-left"]) marginLeft = propList["fo:margin-left"]->getDouble(); if (propList["fo:margin-right"]) marginRight = propList["fo:margin-right"]->getDouble(); if (propList["fo:text-indent"]) textIndent = propList["fo:text-indent"]->getDouble(); m_topMargin = marginTop; m_bottomMargin = marginBottom; m_leftMarginOffset = marginLeft; m_rightMarginOffset = marginRight; m_textIndent = textIndent; UT_String propBuffer; propBuffer += "text-align:"; if (propList["fo:text-align"]) { // AbiWord follows xsl:fo, except here, for some reason.. if (propList["fo:text-align"]->getStr() == "end") propBuffer += "right"; else propBuffer += propList["fo:text-align"]->getStr().cstr(); } else propBuffer += "left"; float lineSpacing = 1.0f; if (propList["fo:line-height"]) lineSpacing = propList["fo:line-height"]->getDouble(); UT_String tmpBuffer; UT_String_sprintf(tmpBuffer, "; margin-top:%dpt; margin-bottom:%dpt; margin-left:%.4fin; margin-right:%.4fin; text-indent:%.4fin; line-height:%.4f", (int)(m_topMargin*72), (int)(m_bottomMargin*72), m_leftMarginOffset, m_rightMarginOffset, m_textIndent, lineSpacing); propBuffer += tmpBuffer; const librevenge::RVNGPropertyListVector *tabStops = propList.child("style:tab-stops"); if (tabStops && tabStops->count()) // Append the tabstop information { propBuffer += "; tabstops:"; tmpBuffer = ""; librevenge::RVNGPropertyListVector::Iter i(*tabStops); for (i.rewind(); i.next();) { propBuffer += tmpBuffer; if (i()["style:position"]) { UT_String_sprintf(tmpBuffer, "%.4fin", i()["style:position"]->getDouble()); propBuffer += tmpBuffer; } if (i()["style:type"]) if (i()["style:type"]->getStr() == "right") propBuffer += "/R"; else if (i()["style:type"]->getStr() == "center") propBuffer += "/C"; else if (i()["style:type"]->getStr() == "char") propBuffer += "/D"; else propBuffer += "/L"; else // Left aligned is default propBuffer += "/L"; if (i()["style:leader-text"]) if (i()["style:leader-text"]->getStr() == "-") propBuffer += "2"; else if (i()["style:leader-text"]->getStr() == "_") propBuffer += "3"; else // default to dot leader if the given leader is dot or is not supported by AbiWord propBuffer += "1"; else propBuffer += "0"; tmpBuffer = ","; } } UT_DEBUGMSG(("AbiWordPerfect: Appending paragraph properties: %s\n", propBuffer.c_str())); const PP_PropertyVector propsArray = { "props", propBuffer.c_str() }; X_CheckDocumentError(appendStrux(PTX_Block, propsArray)); m_bRequireBlock = false; if (propList["fo:break-before"]) { if (strcmp(propList["fo:break-before"]->getStr().cstr(), "page") == 0) { UT_UCS4Char ucs = UCS_FF; X_CheckDocumentError(appendSpan(&ucs,1)); } else if (strcmp(propList["fo:break-before"]->getStr().cstr(), "column") == 0) { UT_UCS4Char ucs = UCS_VTAB; X_CheckDocumentError(appendSpan(&ucs,1)); } } }