List of usage examples for org.apache.poi.hssf.usermodel HSSFRow getLastCellNum
@Override public short getLastCellNum()
From source file:ugh.fileformats.excel.Excelfile.java
License:Open Source License
/*************************************************************************** * Read paginiation sequences from Excel sheet and creates physical * docstruct entities (one for each page) and creates Image-instances * //from w w w. j av a 2 s.c o m * @param inSheet * single sheet of a whole excel file containing the pagination * sequences * @param pathasstring * @return true, if everthing is okay; otherwise false * @throws MetadataTypeNotAllowedException **************************************************************************/ private boolean ReadPaginationSequences(HSSFSheet inSheet, String pathasstring) throws MetadataTypeNotAllowedException { DocStruct boundbook = this.mydoc.getPhysicalDocStruct(); double oldPhysicalend = 0; // Positions of appropriate columns in the spreadsheet. int countedstartpageCol = 0; int countedendpageCol = 0; int uncountedstartpageCol = 0; int uncountedendpageCol = 0; int formatCol = 0; // Contains all pagination sequences; will be used later when reading // the hierarchy. this.allPaginations = new LinkedList<PaginationSequence>(); // Get column's names and positions from the second row in the // spreadsheet. org.apache.poi.hssf.usermodel.HSSFRow secondRow = inSheet.getRow(1); int from = secondRow.getFirstCellNum(); int to = secondRow.getLastCellNum(); for (int i = from; i < to + 1; i++) { HSSFCell currentCell = secondRow.getCell((short) (i)); if ((currentCell != null) && (currentCell.getCellType() == HSSFCell.CELL_TYPE_STRING)) { String currentValue = currentCell.getStringCellValue(); if ((currentValue != null) && (currentValue.length() >= 7) && (currentValue.substring(0, 7).equals("GSEIT_S"))) { countedstartpageCol = i; continue; } if ((currentValue != null) && (currentValue.length() >= 7) && (currentValue.substring(0, 7).equals("GSEIT_E"))) { countedendpageCol = i; continue; } if ((currentValue != null) && (currentValue.length() >= 7) && (currentValue.substring(0, 7).equals("USEIT_S"))) { uncountedstartpageCol = i; continue; } if ((currentValue != null) && (currentValue.length() >= 7) && (currentValue.substring(0, 7).equals("USEIT_E"))) { uncountedendpageCol = i; continue; } if ((currentValue != null) && (currentValue.length() >= 7) && (currentValue.substring(0, 7).equals("FRMT_S"))) { formatCol = i; continue; } } } // Now we can begin to read the pagination sequences; we'll start from // third row. for (int x = 2; x < inSheet.getPhysicalNumberOfRows(); x++) { // Each row is one pagination sequence. org.apache.poi.hssf.usermodel.HSSFRow currentRow = inSheet.getRow(x); // Get cell values. HSSFCell countedstartpagecell = currentRow.getCell((short) countedstartpageCol); HSSFCell countedendpagecell = currentRow.getCell((short) countedendpageCol); HSSFCell uncountedstartpagecell = currentRow.getCell((short) uncountedstartpageCol); HSSFCell uncountedendpagecell = currentRow.getCell((short) uncountedendpageCol); HSSFCell formatcell = currentRow.getCell((short) formatCol); // These variables are for one pagination sequence. double numpages = 0; double uncountedstartpage = 0; double uncountedendpage = 0; double countedstartpage = 0; double countedendpage = 0; String pageformat = null; // Check if we have to go out of loop, cause entries are empty. if ((countedstartpagecell == null) || (countedendpagecell == null)) { // Get out of loop; no value in start or endpage available; must // be the last one. break; } if ((countedstartpagecell.getCellType() == HSSFCell.CELL_TYPE_BLANK) || (countedendpagecell.getCellType() == HSSFCell.CELL_TYPE_BLANK)) { break; } // Get cell values. if ((countedstartpagecell != null) && (countedstartpagecell.getCellType() == HSSFCell.CELL_TYPE_NUMERIC)) { countedstartpage = countedstartpagecell.getNumericCellValue(); } else { if (countedstartpagecell != null) { System.err.println( "WARNING: value for counted page start in Pagination sequences is NOT numeric (" + x + ")"); } else { System.err.println("WARNING: value for counted page start has no value in Pagination Sequence (" + x + ")"); } } if ((countedendpagecell != null) && (countedendpagecell.getCellType() == HSSFCell.CELL_TYPE_NUMERIC)) { countedendpage = countedendpagecell.getNumericCellValue(); } else { if (countedendpagecell != null) { System.err .println("WARNING: value for counted page end in Pagination sequences is NOT numeric (" + x + ")"); } else { System.err.println("WARNING: counted endpage has no value... (" + x + ")"); } } if ((uncountedstartpagecell != null) && (uncountedstartpagecell.getCellType() == HSSFCell.CELL_TYPE_NUMERIC)) { uncountedstartpage = uncountedstartpagecell.getNumericCellValue(); } else { if ((uncountedstartpagecell != null) && (uncountedstartpagecell.getCellType() != HSSFCell.CELL_TYPE_BLANK)) { System.err.println( "WARNING: value for uncounted startpage in Pagination sequences is NOT numeric (" + x + ")"); } } if ((uncountedendpagecell != null) && (uncountedendpagecell.getCellType() == HSSFCell.CELL_TYPE_NUMERIC)) { uncountedendpage = uncountedendpagecell.getNumericCellValue(); } else { if ((uncountedendpagecell != null) && (uncountedendpagecell.getCellType() != HSSFCell.CELL_TYPE_BLANK)) { System.err .println("WARNING: value for uncounted endpage in Pagination sequences is NOT numeric (" + x + ")"); } } // Seitenformat. if ((formatcell != null) && ((formatcell.getCellType() == HSSFCell.CELL_TYPE_NUMERIC) || (formatcell.getCellType() == HSSFCell.CELL_TYPE_FORMULA))) { pageformat = "1"; } if ((formatcell != null) && (formatcell.getCellType() == HSSFCell.CELL_TYPE_STRING)) { pageformat = formatcell.getStringCellValue(); if (!pageformat.equalsIgnoreCase("R")) { System.err.println("WARNING: unknown page format - neither arabic nor roman... (" + x + ")"); } pageformat = "R"; } if ((formatcell != null) && (formatcell.getCellType() == HSSFCell.CELL_TYPE_BLANK)) { // Blank cell. pageformat = "1"; } if (formatcell == null) { // Assume that it's an arabic number, when no value was set. pageformat = "1"; } // Calculate physical start and endpages. if (((uncountedstartpage == 0) && (uncountedendpage != 0)) || ((uncountedstartpage != 0) && (uncountedendpage == 0))) { System.err.println("WARNING: uncounted start or endpage is NOT set... (" + x + ")"); continue; } if ((countedstartpage > countedendpage) || (uncountedstartpage > uncountedendpage)) { System.err.println("WARNING: startpage is larger then endpage (" + x + ")"); } if (uncountedstartpage == 0) { numpages = countedendpage - countedstartpage; } else { numpages = uncountedendpage - uncountedstartpage; } double physicalstart = oldPhysicalend + 1; double physicalend = physicalstart + numpages; oldPhysicalend = physicalend; // Create pagination sequence. PaginationSequence ps = new PaginationSequence(this.myPreferences); if ((countedstartpage == countedendpage) && (uncountedstartpage != 0) && (uncountedendpage != 0)) { // A sequence of uncounted pages. ps.logcountedstart = 0; ps.logcountedend = 0; ps.lognotcountedstart = (int) uncountedstartpage; ps.lognotcountedend = (int) uncountedendpage; ps.pageformatnumber = pageformat; } if (countedstartpage != countedendpage) { // A sequence of counted pages. if (uncountedstartpage != uncountedendpage) { System.err.println( "WARNING: counted page sequence can be may be an uncounted sequence... (" + x + ")"); } ps.logcountedstart = (int) countedstartpage; ps.logcountedend = (int) countedendpage; ps.pageformatnumber = pageformat; } ps.physicalstart = (int) physicalstart; ps.physicalend = (int) physicalend; // Convert pagination sequence to physical strucutre; get a list of // physical structures LinkedList<?> pages = ps.ConvertToPhysicalStructure(this.mydoc); this.allPaginations.add(ps); // Add number of pagination sequence necessary to calculate physical // page number in Gliederung. MetadataType seqno = new MetadataType(); seqno.setName("_PaginationNo"); for (int u = 0; u < pages.size(); u++) { DocStruct page = (DocStruct) pages.get(u); Metadata md = new Metadata(seqno); md.setValue(Integer.toString(x - 1)); try { page.addMetadata(md); // Add the single page to the uppermost physical structure // (bound book). boundbook.addChild(page); } catch (TypeNotAllowedAsChildException tnaace) { System.err.println("ERROR: ReadPaginationSequences: Can't add pages to BoundBook"); return false; } catch (MetadataTypeNotAllowedException mtnae) { System.err.println( "ERROR: ReadPaginationSequences: Can't read metadata; metadata type not allowed!"); System.err.println(" " + md.getType().getName() + " can't be added for DocStruct " + page.getType().getName()); return false; } } } // Create top physical document structure (BoundBook) if ((boundbook.getAllChildren() == null) || (boundbook.getAllChildren().size() == 0)) { System.out.println("DEBUG: rdffile.ReadPagSequence: No pages available..."); return false; } // Add page information to parent logical structure. DocStruct parent = this.mydoc.getLogicalDocStruct(); if (parent == null) { System.out.println( "ERROR: Excelfile.ReadPaginationSequences: Can't find any parent element on topmost level"); return false; } DocStructType parentType = parent.getType(); if (parentType.getAnchorClass() != null) { // It's an anchor (e.g. a periodical...) so we cannot add any // children to this but we must get the next structure entity // (child) - e.g. the volume. List<DocStruct> children = parent.getAllChildren(); if (children == null) { System.out.println("ERROR: ReadPaginationSequences: Parent is anchor but has no child"); return false; } // Get first child as new parent. parent = children.get(0); } List<DocStruct> allpages = boundbook.getAllChildren(); for (int i = 0; i < allpages.size(); i++) { // Get single node. DocStruct currentPage = allpages.get(i); parent.addReferenceTo(currentPage, "logical_physical"); currentPage.addReferenceFrom(parent, "physical_physical"); } // Add internal metadata: start and endpage. MetadataType endpagemd = this.myPreferences.getMetadataTypeByName("_pagephysend"); Metadata mdnew = new Metadata(endpagemd); mdnew.setValue(Integer.toString(allpages.size())); try { // Add physical page number. parent.addMetadata(mdnew); } catch (MetadataTypeNotAllowedException mtnae) { System.err.println("ERROR: ReadPaginationSequences: Can't add metadata"); System.err.println( " " + mdnew.getType().getName() + " can't be added to " + parent.getType().getName()); return false; } MetadataType startpagemd = this.myPreferences.getMetadataTypeByName("_pagephysstart"); mdnew = new Metadata(startpagemd); // Physical page number begins always with 1. mdnew.setValue("1"); try { // Add physical page number. parent.addMetadata(mdnew); } catch (MetadataTypeNotAllowedException mtnae) { System.err.println("ERROR: ReadPaginationSequences: Can't add metadata"); System.err.println( " " + mdnew.getType().getName() + " can't be added to " + parent.getType().getName()); return false; } // Create imageset; every page one image. if (this.myImageset == null) { this.myImageset = new ugh.dl.FileSet(); } // NOT FINISHED // // Create File objects for images. for (int i = 0; i < allpages.size(); i++) { DocStruct currentPage = allpages.get(i); // Create new Image object and add it to myImageSet. ugh.dl.ContentFile newimage = new ugh.dl.ContentFile(); String filename = ""; ugh.dl.MetadataType MDT2 = this.myPreferences.getMetadataTypeByName("physPageNumber"); List<? extends Metadata> physpagelist = currentPage.getAllMetadataByType(MDT2); int physpage = 0; for (Metadata md : physpagelist) { try { physpage = Integer.parseInt(md.getValue()); } catch (Exception e) { System.err.println("ERROR: physical page number seems to be a non integer value!!"); return false; } } if (physpage < 100000) { filename = "000" + physpage + ".tif"; } if (physpage < 10000) { filename = "0000" + physpage + ".tif"; } if (physpage < 1000) { filename = "00000" + physpage + ".tif"; } if (physpage < 100) { filename = "000000" + physpage + ".tif"; } if (physpage < 10) { filename = "0000000" + physpage + ".tif"; } newimage.setLocation(pathasstring + "/" + filename); newimage.setMimeType("image/tiff"); // Add the file to the imageset. this.myImageset.addFile(newimage); // Add contentFile to page. currentPage.addContentFile(newimage); } this.mydoc.setPhysicalDocStruct(boundbook); this.mydoc.setFileSet(this.myImageset); return true; }
From source file:ugh.fileformats.excel.Excelfile.java
License:Open Source License
/*************************************************************************** * Reads the logical structure of a work from spreadsheet table "Gliederung" * The content is attached to the "maindocstruct", which must already be * available e.g. be reading the Bibliography first * // w w w . j a v a2s .co m * @param inSheet * of the table "Gliederung" * @return true, everything is okay; otherwise false * @throws TypeNotAllowedForParentException * @throws MetadataTypeNotAllowedException * **************************************************************************/ private boolean ReadGliederung(HSSFSheet inSheet) throws TypeNotAllowedForParentException, MetadataTypeNotAllowedException { int structtypeCol = -1; // position of structure type column int sequenceCol = -1; int levelCol = -1; int countedstartpageCol = -1; int uncountedstartpageCol = -1; int ueberlappungCol = -1; // Contains the column number for a metadata type. LinkedList<String> metadataColumn = new LinkedList<String>(); // Contains the name of a metadata type (as String). LinkedList<String> metadataType = new LinkedList<String>(); // Try to get the column-positions according to their names. org.apache.poi.hssf.usermodel.HSSFRow secondRow = inSheet.getRow(1); int from = secondRow.getFirstCellNum(); int to = secondRow.getLastCellNum(); for (int i = from; i < to + 1; i++) { HSSFCell currentCell = secondRow.getCell((short) (i)); if ((currentCell != null) && (currentCell.getCellType() == HSSFCell.CELL_TYPE_STRING)) { String currentValue = currentCell.getStringCellValue(); // Checking for length of string and comapre only the first x // chars is necessary, because OpenOffice's excel files may // contain whitespaces after the cell-content. I'm not sure, // wether only whitespaces or also other characters may occur... if ((currentValue != null) && (currentValue.length() >= 8) && (currentValue.substring(0, 8).equals("STRCT_EL"))) { structtypeCol = i; continue; } if ((currentValue != null) && (currentValue.length() >= 5) && (currentValue.substring(0, 5).equals("LEVEL"))) { levelCol = i; continue; } if ((currentValue != null) && (currentValue.length() >= 3) && (currentValue.substring(0, 3).equals("SEQ"))) { sequenceCol = i; continue; } if ((currentValue != null) && (currentValue.length() >= 7) && (currentValue.substring(0, 7).equals("GSEIT_S"))) { countedstartpageCol = i; continue; } if ((currentValue != null) && (currentValue.length() >= 7) && (currentValue.substring(0, 7).equals("USEIT_S"))) { uncountedstartpageCol = i; continue; } if ((currentValue != null) && (currentValue.length() >= 12) && (currentValue.substring(0, 12).equals("Ueberlappung"))) { ueberlappungCol = i; continue; } // Check metadata columns; these are configurable using the // language excel:Gliederung. if (currentValue != null) { currentValue.trim(); MetadataType columnmdt = getMDTypeByName(currentValue, "ExcelGliederung"); if (columnmdt != null) { // We found a column which has a metadatatype. metadataType.add(currentValue); metadataColumn.add(Integer.toString(i)); } } } } // Now we can begin to read the contents. // // Read DocStructs. // DocStruct alllevels[] = { null, null, null, null, null, null, null, null, null, null, null, null }; int oldhierarchy = 0; // Each row is one pagination sequence. for (int x = 2; x < inSheet.getPhysicalNumberOfRows(); x++) { HSSFCell levelcell = null; HSSFCell structtypecell = null; HSSFCell sequencecell = null; HSSFCell countedstartpagecell = null; HSSFCell uncountedstartpagecell = null; HSSFCell ueberlappungcell = null; org.apache.poi.hssf.usermodel.HSSFRow currentRow = inSheet.getRow(x); if (structtypeCol > -1) { structtypecell = currentRow.getCell((short) structtypeCol); } else { System.err.println("ERROR: Can't find column 'STRCT_EL'"); return false; } if (sequenceCol > -1) { sequencecell = currentRow.getCell((short) sequenceCol); } else { System.err.println("ERROR: Can't find column 'SEQ'"); return false; } if (countedstartpageCol > -1) { countedstartpagecell = currentRow.getCell((short) countedstartpageCol); } else { System.err.println("ERROR: Can't find column 'GSEIT_S'"); return false; } if (uncountedstartpageCol > -1) { uncountedstartpagecell = currentRow.getCell((short) uncountedstartpageCol); } else { System.err.println("ERROR: Can't find column 'USEIT_S'"); return false; } if (levelCol > -1) { levelcell = currentRow.getCell((short) levelCol); } if (ueberlappungCol > -1) { ueberlappungcell = currentRow.getCell((short) ueberlappungCol); } // Get cells for metadata and store the cells in a LinkedList. LinkedList<HSSFCell> metadataCells = new LinkedList<HSSFCell>(); for (int u = 0; u < metadataColumn.size(); u++) { int column = Integer.parseInt(metadataColumn.get(u)); HSSFCell metadatacell = currentRow.getCell((short) column); metadataCells.add(metadatacell); } // Read values and create DocStruct object. int hierarchy = 0; String type = null; String overlapping = null; int sequence = 0; int countedpage = 0; int uncountedpage = 0; // Get hierarchy. // // Level-column is available. if ((levelCol > -1) && (levelcell != null)) { if (levelcell.getCellType() == HSSFCell.CELL_TYPE_NUMERIC) { hierarchy = (int) levelcell.getNumericCellValue(); } else { if (levelcell.getCellType() != HSSFCell.CELL_TYPE_BLANK) { System.err.println("ERROR: Value of hierachy is NOT numeric (1) - line " + x); } continue; } // Level information is stored in type value. } else { if ((structtypecell != null) && (structtypecell.getCellType() == HSSFCell.CELL_TYPE_STRING)) { type = structtypecell.getStringCellValue(); // Needed to read OpenOffice excel files... type = TrimString(type); } else { if ((structtypecell != null) && (structtypecell.getCellType() != HSSFCell.CELL_TYPE_BLANK)) { System.err.println( "ERROR: Unknown cell type for structure entity type (not a string) - line " + x); } continue; } // Separate level information from structtype. for (int z = 0; z < type.length(); z++) { // Position of space. int spacepos = type.indexOf(" "); String hierarchystring = type.substring(0, spacepos); hierarchy = Integer.parseInt(hierarchystring); type = type.substring(spacepos + 1); } } // Get type, but only if we don't have a type already. if ((type == null) && (structtypecell != null)) { if (structtypecell.getCellType() == HSSFCell.CELL_TYPE_STRING) { type = structtypecell.getStringCellValue(); // Needed to read OpenOffice excel files... type = TrimString(type); } else { System.err.println("ERROR: Wrong value for structure cell - line " + x); continue; } } // Get start sequence. if ((sequencecell != null) && (sequencecell.getCellType() == HSSFCell.CELL_TYPE_NUMERIC)) { sequence = (int) sequencecell.getNumericCellValue(); } else { System.err.println("ERROR: Can't find pagination sequence for start page - line " + x); continue; } // Get counted start page. if ((countedstartpagecell != null) && (countedstartpagecell.getCellType() == HSSFCell.CELL_TYPE_NUMERIC)) { countedpage = (int) countedstartpagecell.getNumericCellValue(); } else { System.err.println( "ERROR: Can't find cell for counted startpage of cell value is not numeric - line " + x); continue; } // Get uncounted start page. if ((uncountedstartpagecell != null) && (uncountedstartpagecell.getCellType() == HSSFCell.CELL_TYPE_NUMERIC)) { uncountedpage = (int) uncountedstartpagecell.getNumericCellValue(); } else { if ((uncountedstartpagecell != null) && (uncountedstartpagecell.getCellType() != HSSFCell.CELL_TYPE_BLANK)) { System.err .println("WARNING (Gliederung): invalid value in uncountedstartpage cell - line " + x); } } // Get overlapping. if ((ueberlappungcell != null) && (ueberlappungcell.getCellType() != HSSFCell.CELL_TYPE_BLANK)) { if (ueberlappungcell.getCellType() == HSSFCell.CELL_TYPE_STRING) { overlapping = ueberlappungcell.getStringCellValue(); // Needed to read OpenOffice excel files... overlapping = TrimString(overlapping); } if (ueberlappungcell.getCellType() == HSSFCell.CELL_TYPE_NUMERIC) { overlapping = Double.toString(ueberlappungcell.getNumericCellValue()); // Needed to read OpenOffice excel files... overlapping = TrimString(overlapping); } } // Create DocStruct instance. // DocStruct newStruct = null; if (type != null) { DocStructType structType = getDSTypeByName(type, "ExcelGliederung"); if (structType == null) { System.err.println( "ERROR: Excelfile.ReadGliederung: Can't find DocStruct for type=" + type + "<"); return false; } newStruct = this.mydoc.createDocStruct(structType); } // Add metadata as title, author, identifier etc... metadata is // configurable using the language excel:Gliederung. for (int u = 0; u < metadataColumn.size(); u++) { // Gt cell. HSSFCell metadatacell = metadataCells.get(u); String mdvalue = null; if ((metadatacell != null) && (metadatacell.getCellType() != HSSFCell.CELL_TYPE_BLANK)) { if (metadatacell.getCellType() == HSSFCell.CELL_TYPE_STRING) { mdvalue = metadatacell.getStringCellValue(); } if (metadatacell.getCellType() == HSSFCell.CELL_TYPE_NUMERIC) { mdvalue = Double.toString(metadatacell.getNumericCellValue()); // Needed to read OpenOffice excel files... mdvalue = TrimString(mdvalue); } } else { // It's a blank cell - so continue with next metadata // column. continue; } if (mdvalue != null) { String metadatatypeString = metadataType.get(u); MetadataType mdtype = getMDTypeByName(metadatatypeString, "ExcelGliederung"); if (metadatatypeString.equals("Autoren")) { List<Metadata> allvalues = ReadAuthors(mdvalue); for (int j = 0; j < allvalues.size(); j++) { // Create new Metadata instance. Metadata partOfMdvalue = allvalues.get(j); // Excel spreadsheet cell as native object. partOfMdvalue.setNativeObject(metadatacell); partOfMdvalue.wasUpdated(false); try { // Addit to new DocStruct instance. if (!newStruct.addMetadata(partOfMdvalue)) { System.err.println("ERROR: Can't add metadata to new document structure - line " + x + "."); } } catch (MetadataTypeNotAllowedException mtnaae) { System.err.println("ERROR: ReadGliederung: can't add metadata - line" + x); System.err.println(" " + partOfMdvalue.getType().getName() + " can't be added to " + newStruct.getType().getName()); } // Add it to new DocStruct. partOfMdvalue.setDocStruct(newStruct); } } else { // Ccreate new Metadatainstance. Metadata md = new Metadata(mdtype); md.setValue(mdvalue); // Set the Excel-spreadsheet cell as native object. md.setNativeObject(metadatacell); md.wasUpdated(false); try { // Add it to new DocStruct instance. if (!newStruct.addMetadata(md)) { System.err.println( "ERROR: Can't add metadata to new document structure - line " + x + "."); } } catch (MetadataTypeNotAllowedException mtnae) { System.err.println("ERROR: ReadPaginationSequences: Can't add metadata - line " + x); System.err.println(" " + md.getType().getName() + " can't be added to " + newStruct.getType().getName()); } md.setDocStruct(newStruct); } } } // Add physical page numbers. PaginationSequence currentSeq = null; int physnumber = 0; for (int u = 0; u < this.allPaginations.size(); u++) { if (u == (sequence - 1)) { currentSeq = this.allPaginations.get(u); if (uncountedpage > 0) { physnumber = CalculatePhysicalNumber(currentSeq, uncountedpage); } if ((countedpage > 0) && (uncountedpage <= 0)) { physnumber = CalculatePhysicalNumber(currentSeq, countedpage); } MetadataType pagenumberPhys = this.myPreferences.getMetadataTypeByName("_pagephysstart"); Metadata mdnew = new Metadata(pagenumberPhys); mdnew.setValue(Integer.toString(physnumber)); try { // Add physical page number. newStruct.addMetadata(mdnew); } catch (MetadataTypeNotAllowedException mtnaae) { System.err.println("ERROR: ReadGliederung: can't add metadata "); System.err.println(" " + mdnew.getType().getName() + " can't be added to " + newStruct.getType().getName()); return false; } // Add overlapping information. MetadataType overlappingType = this.myPreferences.getMetadataTypeByName("_overlapping"); mdnew = new Metadata(overlappingType); mdnew.setValue(overlapping); try { // Add physical page number. newStruct.addMetadata(mdnew); } catch (MetadataTypeNotAllowedException mtnaae) { System.err.println("ERROR: ReadGliederung: can't add metadata "); System.err.println(" " + mdnew.getType().getName() + " can't be added to " + newStruct.getType().getName()); return false; } continue; } } // Get pagaination sequence, calculate number, add DocStruct to // tree. if (hierarchy < 0) { System.out.println("ERROR: Invalid hierarchy level (1)"); return false; } if ((oldhierarchy < hierarchy) && ((hierarchy - oldhierarchy) > 1)) { // There is a jump in hiearchy level from 1 to 3 or so; this is // an error. System.out.println("ERROR: Invalid hierarchy level (2)"); return false; } if (hierarchy == 1) { // Add it to the topmost element. DocStruct parent = this.mydoc.getLogicalDocStruct(); if (parent == null) { System.out.println("ERROR: Can't find any parent element on topmost level"); return false; } DocStructType parentType = parent.getType(); if (parentType.getAnchorClass() != null) { // It's an anchor (e.g. a periodical...) so we cannot add // any children to this but we must get the next structure // entity (child) - e.g. the volume. List<DocStruct> children = parent.getAllChildren(); if (children == null) { System.out.println("ERROR: Parent is anchor but has no child"); return false; } // Get first child as new parent. parent = children.get(0); } // Aadd this new DocStruct object to the parent. try { if (!parent.addChild(newStruct)) { System.err.println("ERROR: Can't read Gliederung; can't add child"); System.err.println(" " + newStruct.getType().getName() + " can't be added to " + parent.getType().getName()); return false; } } catch (TypeNotAllowedAsChildException tnaace) { // Type is not allowed to be added; wrong configuration. System.err.println("ERROR: Can't read Gliederung; can't add child"); System.err.println(" " + newStruct.getType().getName() + " can't be added to " + parent.getType().getName()); return false; } // Store this newStruct as the current DocStruct instance for // hierarchy level 1. alllevels[1] = newStruct; } else { DocStruct oldStruct = alllevels[hierarchy - 1]; if (oldStruct == null) { System.err.println("ERROR: ReadGliederung"); System.err.println(" Can't find any structure entity on level" + (hierarchy - 1)); return false; } try { oldStruct.addChild(newStruct); } catch (TypeNotAllowedAsChildException tnaace) { System.err.println("ERROR: ReadGliederung: Can't add child"); System.err.println(" " + newStruct.getType().getName() + " can't be added to " + oldStruct.getType().getName()); return false; } alllevels[hierarchy] = newStruct; } // Store the old value, so we can compare it with the new one in the // next row. oldhierarchy = hierarchy; // Add new DocStruct instance to LinkedList and add all other // information. this.allDocStruct.add(newStruct); this.allStructRow.add(String.valueOf(x)); this.allStructSheets.add("Gliederung"); } // Calculate physical endpages and add references for pages (DocStruct // instances). DocStruct parent = this.mydoc.getLogicalDocStruct(); if (parent == null) { System.out.println("ERROR: Can't find any parent element on topmost level"); return false; } DocStructType parentType = parent.getType(); if (parentType.getAnchorClass() != null) { // It's an anchor (e.g. a periodical...) so we cannot add any // children to this but we must get the next structure entity // (child) - e.g. the volume. List<DocStruct> children = parent.getAllChildren(); if (children == null) { System.out.println("ERROR: Parent is anchor but has no child"); return false; } // Get first child as new parent. parent = children.get(0); } // Calculates the endpages of the children - NOT of the parent we know // the parent pages already from the Pagination Sequences. CalculateEndPage(parent); return true; }
From source file:uk.ac.ebi.mnb.parser.ExcelXLSHelper.java
License:Open Source License
public String[][] getSheetData(HSSFSheet sheet) { int maxRow = sheet.getLastRowNum() + 1; int colNumber = INTIAL_COLUMN_NUMBER; String[][] data = new String[maxRow][colNumber]; List<String> block_xy1 = new ArrayList<String>(); List<String> block_xy2 = new ArrayList<String>(); int prevLastFilledColumn = -1; int emptyRows = 0; LOGGER.info("getting sheet data"); for (int i = 0; i < maxRow; i++) { HSSFRow row = sheet.getRow(i); int lastFilledColumn = -1; if (row != null) { // convert to 1D array if (row.getLastCellNum() > 0) { String[] rowData = new String[row.getLastCellNum()]; for (int j = 0; j < row.getLastCellNum(); j++) { // check for empty rows HSSFCell cell = row.getCell(j); rowData[j] = getCellString(cell).trim(); if (rowData[j].isEmpty() == Boolean.FALSE) { lastFilledColumn = j; }/*from w ww.java 2s . c o m*/ } // resize if needed if (lastFilledColumn >= colNumber) { LOGGER.info("Sending resize row:" + i + " col:" + lastFilledColumn + " max:" + colNumber); data = resize(data, lastFilledColumn); colNumber = data[0].length; } // and copy the new data if (lastFilledColumn >= 0) { System.arraycopy(rowData, 0, data[i], 0, lastFilledColumn + 1); } } for (int j = row.getLastCellNum(); j < colNumber; j++) { if (j != -1) { data[i][j] = ""; } } if (lastFilledColumn == -1) { if (prevLastFilledColumn != -1) { // empty row block_xy2.add((i - 1) + "," + prevLastFilledColumn); } } else { if (block_xy2.size() == block_xy1.size()) { block_xy1.add(i + "," + 0); } } prevLastFilledColumn = lastFilledColumn; } emptyRows = lastFilledColumn <= 0 ? emptyRows + 1 : 0; if (emptyRows > 5) { return Arrays.copyOf(data, i - 5); } } for (int i = 0; i < block_xy2.size(); i++) { //System.out.println(block_xy1.get(i) + " to " + block_xy2.get(i)); } return data; }
From source file:uk.ac.ebi.mnb.parser.ExcelXLSHelper.java
License:Open Source License
@Override public String[][] getTableHead(Integer sheetIndex, Integer rowCount) { HSSFSheet sheet = workbook.getSheetAt(sheetIndex); Integer colCount = 0;//from ww w . ja va 2s.c o m List[] data = new List[rowCount]; for (Integer i = 0; i < rowCount; i++) { HSSFRow row = sheet.getRow(i); data[i] = new ArrayList(); for (Integer j = 0; j < row.getLastCellNum(); j++) { HSSFCell cell = row.getCell(j); if (cell != null && !cell.toString().trim().isEmpty()) { data[i].add(cell.toString()); colCount = j > colCount ? j : colCount; } else { data[i].add(""); } } } String[][] fixedData = new String[rowCount][colCount]; for (int i = 0; i < rowCount; i++) { // make sure we have the correct length while (data[i].size() < colCount) { data[i].add(""); } fixedData[i] = (String[]) data[i].subList(0, colCount).toArray(new String[0]); } return fixedData; }
From source file:uk.ac.manchester.cs.owl.semspreadsheets.model.hssf.impl.SheetHSSFImpl.java
License:BSD License
public List<Cell> getCellsWithContent() { List<Cell> cells = new ArrayList<Cell>(); int firstRow = sheet.getFirstRowNum(); int lastRow = sheet.getLastRowNum(); for (int rowIndex = firstRow; rowIndex <= lastRow; rowIndex++) { HSSFRow row = sheet.getRow(rowIndex); if (row != null) { int firstCell = row.getFirstCellNum(); int lastCell = row.getLastCellNum(); for (int cellIndex = firstCell; cellIndex <= lastCell; cellIndex++) { HSSFCell cell = row.getCell(cellIndex); boolean skip = cell == null || cell.getCellType() == HSSFCell.CELL_TYPE_BLANK || (cell.getCellType() == HSSFCell.CELL_TYPE_STRING && cell.getStringCellValue().isEmpty()); if (!skip) { cells.add(new CellHSSFImpl(hssfWorkbook, cell)); }/*from w ww. ja v a 2 s. co m*/ } } } return cells; }
From source file:utilesBD.servidoresDatos.JServerServidorDatosExcel.java
/** * Metodo que se encarga de leer los datos de un archivo en formato excel * @return Fila que contiene la informacion del archivo *///from ww w . j a v a 2 s .c o m public JFilaDatosDefecto leeLineaExcel(HSSFRow hssfRow) { JFilaDatosDefecto loLinea = new JFilaDatosDefecto(); //Me barro todos los elementos de una fila for (int i = hssfRow.getFirstCellNum(); i < hssfRow.getLastCellNum(); i++) { HSSFCell hssfCell = hssfRow.getCell(i); if (hssfCell != null) { switch (hssfCell.getCellType()) { case HSSFCell.CELL_TYPE_BOOLEAN: loLinea.addCampo(String.valueOf(hssfCell.getBooleanCellValue())); break; case HSSFCell.CELL_TYPE_FORMULA: try { loLinea.addCampo(hssfCell.getStringCellValue()); } catch (Exception e) { try { loLinea.addCampo(String.valueOf(hssfCell.getNumericCellValue())); } catch (Exception e1) { try { loLinea.addCampo(new JDateEdu(hssfCell.getDateCellValue()).toString() .replace("31/12/1899 ", "")); } catch (Exception e2) { try { loLinea.addCampo(String.valueOf(hssfCell.getBooleanCellValue())); } catch (Exception e3) { loLinea.addCampo(""); } } } } break; case HSSFCell.CELL_TYPE_NUMERIC: if (HSSFDateUtil.isCellDateFormatted(hssfCell)) { loLinea.addCampo( new JDateEdu(hssfCell.getDateCellValue()).toString().replace("31/12/1899 ", "")); } else { double ldValor = hssfCell.getNumericCellValue(); loLinea.addCampo( JFormat.msFormatearDouble(ldValor, "############.#########").replace(',', '.')); } break; case HSSFCell.CELL_TYPE_STRING: loLinea.addCampo(hssfCell.toString()); break; default: loLinea.addCampo(""); } } else { loLinea.addCampo(""); } } return loLinea; }
From source file:vone.HSSFReadWrite.java
License:Apache License
/** * Method main//from w w w .j a v a 2s .c o m * * Given 1 argument takes that as the filename, inputs it and dumps the cell * values/types out to sys.out.<br/> * * given 2 arguments where the second argument is the word "write" and the * first is the filename - writes out a sample (test) spreadsheet see * {@link HSSFReadWrite#testCreateSampleSheet(String)}.<br/> * * given 2 arguments where the first is an input filename and the second an * output filename (not write), attempts to fully read in the spreadsheet * and fully write it out.<br/> * * given 3 arguments where the first is an input filename and the second an * output filename (not write) and the third is "modify1", attempts to read * in the spreadsheet, deletes rows 0-24, 74-99. Changes cell at row 39, col * 3 to "MODIFIED CELL" then writes it out. Hence this is "modify test 1". * If you take the output from the write test, you'll have a valid scenario. */ @SuppressWarnings("deprecation") public static void main(String[] args) { if (args.length < 1) { System.err.println("At least one argument expected"); return; } String fileName = args[0]; try { if (args.length < 2) { HSSFWorkbook wb = HSSFReadWrite.readFile(fileName); System.out.println("Data dump:\n"); for (int k = 0; k < wb.getNumberOfSheets(); k++) { HSSFSheet sheet = wb.getSheetAt(k); int rows = sheet.getPhysicalNumberOfRows(); System.out.println("Sheet " + k + " \"" + wb.getSheetName(k) + "\" has " + rows + " row(s)."); for (int r = 0; r < rows; r++) { HSSFRow row = sheet.getRow(r); if (row == null) { continue; } // int cells = row.getPhysicalNumberOfCells(); int cells = row.getLastCellNum(); System.out.println("\nROW " + row.getRowNum() + " has " + cells + " cell(s)."); for (int c = 0; c < cells; c++) { HSSFCell cell = row.getCell(c); String value = null; if (cell == null) { System.out.println("CELL col=" + c + " VALUE= Empty"); continue; } switch (cell.getCellTypeEnum()) { case FORMULA: value = "FORMULA value=" + cell.getCellFormula(); break; case NUMERIC: value = "NUMERIC value=" + cell.getNumericCellValue(); break; case STRING: value = "STRING value=" + cell.getStringCellValue(); break; default: } System.out.println("CELL col=" + cell.getColumnIndex() + " VALUE=" + value); } } } wb.close(); } } catch (Exception e) { e.printStackTrace(); } }
From source file:ypcnv.views.impl.FileXLS.java
License:Open Source License
/** * Check whether or not the given row's cells content have all the expected * names of data fields. <br>//from w w w. jav a 2 s .c om * <br> * XLS workbooks generated by MS-Outlook while contacts export all ways have * fixed number of data fields.<br> * <br> * Obtain meta data concerning distribution of header names. * * @param headerRow * - row to be processed. * @throws FileViewException * in case check is not passed. */ private void validateHeaderNames(HSSFRow headerRow) throws FileViewException { startColumnIdx = (int) headerRow.getFirstCellNum(); /* * It's Apache POI feature - getLastCellNum gets the index of the last * cell contained in this row PLUS ONE. */ stopColumnIdx = -1 + (int) headerRow.getLastCellNum(); /* Whether quantity of fields is valid. */ int foundQuantityOfDataFields = 1 + stopColumnIdx - startColumnIdx; if (foundQuantityOfDataFields != Contact2k3.getDataFieldsQuantity() || foundQuantityOfDataFields != FileXLSMeta.NUMBER_OF_DATA_FIELDS) { String message = String.format(FileXLSMeta.ERR_MESSAGE_WRONG_FIELD_QUANTITY, ((File) address).getAbsoluteFile(), FileXLSMeta.NUMBER_OF_DATA_FIELDS); LOG.error(message); throw new FileViewException(null, "Contact2k3Xls.checkHeaderNames()", message); } /* Whether data fields names are valid. */ for (int idx = startColumnIdx; idx <= stopColumnIdx; idx++) { HSSFCell currentCell = headerRow.getCell(idx); String xlsFieldName = currentCell.getStringCellValue(); String modelDataFieldName = null; modelDataFieldName = FileXLSNames.CONTAINER_FIELD_NAMING_MAP.get(xlsFieldName); if (modelDataFieldName == null) { ArrayList<String> foreignNamesSearchResultList = new ArrayList<String>(); /* * Add one by one mappings of other localizations, or add * explicit locality flag support. */ foreignNamesSearchResultList .add(FileXLSNames.CONTAINER_FIELD_NAMING_MAP_RUS2ENGL.get(xlsFieldName)); Iterator<String> namesWereFoundListIterator = foreignNamesSearchResultList.iterator(); while (namesWereFoundListIterator.hasNext()) { String foundForeignName = namesWereFoundListIterator.next(); if (foundForeignName != null) { modelDataFieldName = FileXLSNames.CONTAINER_FIELD_NAMING_MAP.get(foundForeignName); } } } if (modelDataFieldName != null) { dataColumnsSequenceMap.put(modelDataFieldName, idx); } else { String message = String.format(FileXLSMeta.ERR_MESSAGE_WRONG_FIELD_NAME, ((File) address).getAbsoluteFile(), xlsFieldName); throw new FileViewException(null, "Contact2k3Xls.checkHeaderNames()", message); } } }