From: Yegor Kozlov Date: Wed, 1 Oct 2008 16:14:39 +0000 (+0000) Subject: iterator over sheet data in XSSFReader returns sheets in logical order, i.e. as... X-Git-Tag: ooxml_20081107~38 X-Git-Url: https://source.dussan.org/?a=commitdiff_plain;h=190f1cc40a6d74ec52661a3f16967ab1299adde3;p=poi.git iterator over sheet data in XSSFReader returns sheets in logical order, i.e. as they are defined in workbook.xml (was in physical order, as they were stored in the relationship table) git-svn-id: https://svn.apache.org/repos/asf/poi/branches/ooxml@700821 13f79535-47bb-0310-9956-ffa450edef68 --- diff --git a/src/ooxml/java/org/apache/poi/xssf/eventusermodel/XSSFReader.java b/src/ooxml/java/org/apache/poi/xssf/eventusermodel/XSSFReader.java index 181913f266..f0a84d1603 100644 --- a/src/ooxml/java/org/apache/poi/xssf/eventusermodel/XSSFReader.java +++ b/src/ooxml/java/org/apache/poi/xssf/eventusermodel/XSSFReader.java @@ -18,20 +18,24 @@ package org.apache.poi.xssf.eventusermodel; import java.io.IOException; import java.io.InputStream; -import java.util.Iterator; +import java.util.*; import org.apache.poi.xssf.model.SharedStringsTable; import org.apache.poi.xssf.model.StylesTable; import org.apache.poi.xssf.usermodel.XSSFRelation; +import org.apache.poi.POIXMLException; +import org.apache.xmlbeans.XmlException; import org.openxml4j.exceptions.InvalidFormatException; import org.openxml4j.exceptions.OpenXML4JException; import org.openxml4j.opc.Package; import org.openxml4j.opc.PackagePart; import org.openxml4j.opc.PackagePartName; import org.openxml4j.opc.PackageRelationship; -import org.openxml4j.opc.PackageRelationshipCollection; import org.openxml4j.opc.PackageRelationshipTypes; import org.openxml4j.opc.PackagingURIHelper; +import org.openxmlformats.schemas.spreadsheetml.x2006.main.CTWorkbook; +import org.openxmlformats.schemas.spreadsheetml.x2006.main.WorkbookDocument; +import org.openxmlformats.schemas.spreadsheetml.x2006.main.CTSheet; /** * This class makes it easy to get at individual parts @@ -41,127 +45,186 @@ import org.openxml4j.opc.PackagingURIHelper; * for XSSF. */ public class XSSFReader { - private Package pkg; - private PackagePart workbookPart; - - /** - * Creates a new XSSFReader, for the given package - */ - public XSSFReader(Package pkg) throws IOException, OpenXML4JException { - this.pkg = pkg; - + private Package pkg; + private PackagePart workbookPart; + + /** + * Creates a new XSSFReader, for the given package + */ + public XSSFReader(Package pkg) throws IOException, OpenXML4JException { + this.pkg = pkg; + PackageRelationship coreDocRelationship = this.pkg.getRelationshipsByType( PackageRelationshipTypes.CORE_DOCUMENT).getRelationship(0); - + // Get the part that holds the workbook workbookPart = this.pkg.getPart(coreDocRelationship); - } - - - /** - * Opens up the Shared Strings Table, parses it, and - * returns a handy object for working with - * shared strings. - */ - public SharedStringsTable getSharedStringsTable() throws IOException, InvalidFormatException { - return new SharedStringsTable(getSharedStringsData()); - } - - /** - * Opens up the Styles Table, parses it, and - * returns a handy object for working with cell styles - */ - public StylesTable getStylesTable() throws IOException, InvalidFormatException { - return new StylesTable(getStylesData()); - } - - - - /** - * Returns an InputStream to read the contents of the - * shared strings table. - */ - public InputStream getSharedStringsData() throws IOException, InvalidFormatException { - return XSSFRelation.SHARED_STRINGS.getContents(workbookPart); - } - - /** - * Returns an InputStream to read the contents of the - * styles table. - */ - public InputStream getStylesData() throws IOException, InvalidFormatException { - return XSSFRelation.STYLES.getContents(workbookPart); - } - - /** - * Returns an InputStream to read the contents of the - * main Workbook, which contains key overall data for - * the file, including sheet definitions. - */ - public InputStream getWorkbookData() throws IOException, InvalidFormatException { - return workbookPart.getInputStream(); - } - - /** - * Returns an InputStream to read the contents of the - * specified Sheet. - * @param relId The relationId of the sheet, from a r:id on the workbook - */ - public InputStream getSheet(String relId) throws IOException, InvalidFormatException { + } + + + /** + * Opens up the Shared Strings Table, parses it, and + * returns a handy object for working with + * shared strings. + */ + public SharedStringsTable getSharedStringsTable() throws IOException, InvalidFormatException { + return new SharedStringsTable(getSharedStringsData()); + } + + /** + * Opens up the Styles Table, parses it, and + * returns a handy object for working with cell styles + */ + public StylesTable getStylesTable() throws IOException, InvalidFormatException { + return new StylesTable(getStylesData()); + } + + + + /** + * Returns an InputStream to read the contents of the + * shared strings table. + */ + public InputStream getSharedStringsData() throws IOException, InvalidFormatException { + return XSSFRelation.SHARED_STRINGS.getContents(workbookPart); + } + + /** + * Returns an InputStream to read the contents of the + * styles table. + */ + public InputStream getStylesData() throws IOException, InvalidFormatException { + return XSSFRelation.STYLES.getContents(workbookPart); + } + + /** + * Returns an InputStream to read the contents of the + * main Workbook, which contains key overall data for + * the file, including sheet definitions. + */ + public InputStream getWorkbookData() throws IOException, InvalidFormatException { + return workbookPart.getInputStream(); + } + + /** + * Returns an InputStream to read the contents of the + * specified Sheet. + * @param relId The relationId of the sheet, from a r:id on the workbook + */ + public InputStream getSheet(String relId) throws IOException, InvalidFormatException { PackageRelationship rel = workbookPart.getRelationship(relId); if(rel == null) { - throw new IllegalArgumentException("No Sheet found with r:id " + relId); + throw new IllegalArgumentException("No Sheet found with r:id " + relId); } - + PackagePartName relName = PackagingURIHelper.createPartName(rel.getTargetURI()); PackagePart sheet = pkg.getPart(relName); if(sheet == null) { - throw new IllegalArgumentException("No data found for Sheet with r:id " + relId); + throw new IllegalArgumentException("No data found for Sheet with r:id " + relId); } return sheet.getInputStream(); - } - - /** - * Returns an Iterator which will let you get at all the - * different Sheets in turn. - * Each sheet's InputStream is only opened when fetched - * from the Iterator. It's up to you to close the - * InputStreams when done with each one. - */ - public Iterator getSheetsData() throws IOException, InvalidFormatException { - return new SheetDataIterator(); - } - - private class SheetDataIterator implements Iterator { - private Iterator sheetRels; - private SheetDataIterator() throws IOException, InvalidFormatException { - // Find all the sheets - PackageRelationshipCollection sheets = - workbookPart.getRelationshipsByType( - XSSFRelation.WORKSHEET.getRelation() - ); - sheetRels = sheets.iterator(); - } - - public boolean hasNext() { - return sheetRels.hasNext(); - } - - public InputStream next() { - PackageRelationship sheet = sheetRels.next(); - try { - PackagePartName relName = PackagingURIHelper.createPartName(sheet.getTargetURI()); - PackagePart sheetPkg = pkg.getPart(relName); - return sheetPkg.getInputStream(); - } catch(IOException e) { - throw new RuntimeException(e); - } catch(InvalidFormatException ife) { - throw new RuntimeException(ife); - } - } - - public void remove() { - throw new IllegalStateException("Not supported"); - } - } + } + + /** + * Returns an Iterator which will let you get at all the + * different Sheets in turn. + * Each sheet's InputStream is only opened when fetched + * from the Iterator. It's up to you to close the + * InputStreams when done with each one. + */ + public Iterator getSheetsData() throws IOException, InvalidFormatException { + return new SheetIterator(workbookPart); + } + + /** + * Iterator over sheet data. + */ + public static class SheetIterator implements Iterator { + + /** + * Maps relId and the corresponding PackagePart + */ + private Map sheetMap; + + /** + * Current CTSheet bean + */ + private CTSheet ctSheet; + + /** + * Iterator over CTSheet objects, returns sheets in logical order. + * We can't rely on the Ooxml4J's relationship iterator because it returns objects in physical order, + * i.e. as they are stored in the underlying package + */ + private Iterator sheetIterator; + + /** + * Construct a new SheetIterator + * + * @param wb package part holding workbook.xml + */ + private SheetIterator(PackagePart wb) throws IOException { + + /** + * The order of sheets is defined by the order of CTSheet elements in workbook.xml + */ + try { + //step 1. Map sheet's relationship Id and the corresponding PackagePart + sheetMap = new HashMap(); + for(PackageRelationship rel : wb.getRelationships()){ + if(rel.getRelationshipType().equals(XSSFRelation.WORKSHEET.getRelation())){ + PackagePartName relName = PackagingURIHelper.createPartName(rel.getTargetURI()); + sheetMap.put(rel.getId(), wb.getPackage().getPart(relName)); + } + } + //step 2. Read array of CTSheet elements, wrap it in a ArayList and construct an iterator + //Note, using XMLBeans might be expensive, consider refactoring to use SAX or a plain regexp search + CTWorkbook wbBean = WorkbookDocument.Factory.parse(wb.getInputStream()).getWorkbook(); + sheetIterator = Arrays.asList(wbBean.getSheets().getSheetArray()).iterator(); + } catch (InvalidFormatException e){ + throw new POIXMLException(e); + } catch (XmlException e){ + throw new POIXMLException(e); + } + } + + /** + * Returns true if the iteration has more elements. + * + * @return true if the iterator has more elements. + */ + public boolean hasNext() { + return sheetIterator.hasNext(); + } + + /** + * Returns input stream of the next sheet in the iteration + * + * @return input stream of the next sheet in the iteration + */ + public InputStream next() { + ctSheet = sheetIterator.next(); + + String sheetId = ctSheet.getId(); + try { + PackagePart sheetPkg = sheetMap.get(sheetId); + return sheetPkg.getInputStream(); + } catch(IOException e) { + throw new POIXMLException(e); + } + } + + /** + * Returns name of the current sheet + * + * @return name of the current sheet + */ + public String getSheetName() { + return ctSheet.getName(); + } + + public void remove() { + throw new IllegalStateException("Not supported"); + } + } } diff --git a/src/ooxml/testcases/org/apache/poi/xssf/eventusermodel/TestXSSFReader.java b/src/ooxml/testcases/org/apache/poi/xssf/eventusermodel/TestXSSFReader.java index 8ba59de434..5a552df4f6 100644 --- a/src/ooxml/testcases/org/apache/poi/xssf/eventusermodel/TestXSSFReader.java +++ b/src/ooxml/testcases/org/apache/poi/xssf/eventusermodel/TestXSSFReader.java @@ -109,4 +109,30 @@ public class TestXSSFReader extends TestCase { } assertEquals(3, count); } + + /** + * Check that the sheet iterator returns sheets in the logical order + * (as they are defined in the workbook.xml) + */ + public void testOrderOfSheets() throws Exception { + File f = new File(dirName, "reordered_sheets.xlsx"); + Package pkg = Package.open(f.toString()); + + XSSFReader r = new XSSFReader(pkg); + + String[] sheetNames = {"Sheet4", "Sheet2", "Sheet3", "Sheet1"}; + XSSFReader.SheetIterator it = (XSSFReader.SheetIterator)r.getSheetsData(); + + int count = 0; + while(it.hasNext()) { + InputStream inp = it.next(); + assertNotNull(inp); + inp.close(); + + assertEquals(sheetNames[count], it.getSheetName()); + count++; + } + assertEquals(4, count); + + } } diff --git a/src/testcases/org/apache/poi/hssf/data/reordered_sheets.xlsx b/src/testcases/org/apache/poi/hssf/data/reordered_sheets.xlsx new file mode 100755 index 0000000000..f46f59b032 Binary files /dev/null and b/src/testcases/org/apache/poi/hssf/data/reordered_sheets.xlsx differ