Example usage for org.apache.poi.poifs.filesystem POIFSFileSystem createDocumentInputStream

List of usage examples for org.apache.poi.poifs.filesystem POIFSFileSystem createDocumentInputStream

  1. HOME
  2. Java
  3. org.apache.poi
  4. org.apache.poi.poifs.filesystem.*
  5. POIFSFileSystem
  6. createDocumentInputStream

Introduction

In this page you can find the example usage for org.apache.poi.poifs.filesystem POIFSFileSystem createDocumentInputStream.

Prototype

public DocumentInputStream createDocumentInputStream(final String documentName) throws IOException

Source Link

Document

open a document in the root entry's list of entries

Usage

From source file:com.sonicle.webtop.core.io.input.ExcelFileReader.java

License:Open Source License

public HashMap<String, String> listXlsColumnNames(File file) throws IOException, FileReaderException {
    POIFSFileSystem pfs = null;
    InputStream is = null;//  w  w w .  j  a  v a 2  s. co  m

    try {
        pfs = new POIFSFileSystem(file);
        is = pfs.createDocumentInputStream("Workbook");
        XlsColumnsProcessor processor = new XlsColumnsProcessor(is, headersRow, firstDataRow, lastDataRow,
                sheet);
        processor.process();
        return processor.columnNames;

    } finally {
        IOUtils.closeQuietly(is);
        IOUtils.closeQuietly(pfs);
    }
}

From source file:com.sonicle.webtop.core.io.input.ExcelFileReader.java

License:Open Source License

public HashMap<String, Integer> listXlsColumnIndexes(File file) throws IOException, FileReaderException {
    POIFSFileSystem pfs = null;
    InputStream is = null;//ww  w  .  j  av a 2  s  . com

    try {
        pfs = new POIFSFileSystem(file);
        is = pfs.createDocumentInputStream("Workbook");
        XlsColumnsProcessor processor = new XlsColumnsProcessor(is, headersRow, firstDataRow, lastDataRow,
                sheet);
        processor.process();
        return processor.columnIndexes;

    } finally {
        IOUtils.closeQuietly(is);
        IOUtils.closeQuietly(pfs);
    }
}

From source file:com.toolsverse.etl.metadata.excel.ExcelFileMetadata.java

License:Open Source License

@Override
public DataSet getTablesByType(InputStream inputSteam, String name, String pattern, String type)
        throws Exception {
    DataSet dataSet = new DataSet();
    dataSet.setName("tables");

    FieldDef fieldDef = new FieldDef();
    fieldDef.setName("File");
    fieldDef.setSqlDataType(Types.VARCHAR);
    dataSet.addField(fieldDef);//from  www .j  av  a2s .c  o  m

    fieldDef = new FieldDef();
    fieldDef.setName("Name");
    fieldDef.setSqlDataType(Types.VARCHAR);
    dataSet.addField(fieldDef);

    dataSet.setKeyFields("Name");

    InputStream din = null;

    try {
        POIFSFileSystem poifs = new POIFSFileSystem(inputSteam);
        din = poifs.createDocumentInputStream("Workbook");
        HSSFRequest req = new HSSFRequest();

        req.addListenerForAllRecords(new SheetReader(name, dataSet));
        HSSFEventFactory factory = new HSSFEventFactory();

        try {
            factory.processEvents(req, din);
        } catch (Exception ex) {
            if (!Utils.isParticularException(ex, SHEETS_EXTRACTED_EXCEPTION))
                throw ex;
        }
    } finally {
        if (din != null)
            din.close();
    }

    return dataSet;
}

From source file:com.toolsverse.etl.metadata.excel.ExcelFileMetadata.java

License:Open Source License

@Override
public DataSet getTablesByType(String catalog, String schema, String pattern, String type) throws Exception {
    DataSet dataSet = new DataSet();
    dataSet.setName(TABLES_DATASET_TYPE);

    FieldDef fieldDef = new FieldDef();
    fieldDef.setName("File");
    fieldDef.setSqlDataType(Types.VARCHAR);
    dataSet.addField(fieldDef);//  www  .  ja v  a  2 s .c  om

    fieldDef = new FieldDef();
    fieldDef.setName("Name");
    fieldDef.setSqlDataType(Types.VARCHAR);
    dataSet.addField(fieldDef);

    dataSet.setKeyFields("Name");

    FileInputStream fin = null;
    InputStream din = null;

    try {
        fin = new FileInputStream(catalog);
        POIFSFileSystem poifs = new POIFSFileSystem(fin);
        din = poifs.createDocumentInputStream("Workbook");
        HSSFRequest req = new HSSFRequest();

        req.addListenerForAllRecords(new SheetReader(catalog, dataSet));
        HSSFEventFactory factory = new HSSFEventFactory();

        try {
            factory.processEvents(req, din);
        } catch (Exception ex) {
            if (!Utils.isParticularException(ex, SHEETS_EXTRACTED_EXCEPTION))
                throw ex;
        }
    } finally {
        if (fin != null)
            fin.close();
        if (din != null)
            din.close();
    }

    return dataSet;
}

From source file:mj.ocraptor.extraction.tika.parser.microsoft.ooxml.AbstractOOXMLExtractor.java

License:Apache License

/**
 * Handles an embedded OLE object in the document
 *//*from  ww  w.j  a va  2 s. co  m*/
private void handleEmbeddedOLE(PackagePart part, ContentHandler handler, String rel)
        throws IOException, SAXException {
    // A POIFSFileSystem needs to be at least 3 blocks big to be valid
    // TODO: TIKA-1118 Upgrade to POI 4.0 then enable this block of code
    //        if (part.getSize() >= 0 && part.getSize() < 512*3) {
    //           // Too small, skip
    //           return;
    //        }

    // Open the POIFS (OLE2) structure and process
    POIFSFileSystem fs = new POIFSFileSystem(part.getInputStream());
    try {
        Metadata metadata = new Metadata();
        TikaInputStream stream = null;
        metadata.set(Metadata.EMBEDDED_RELATIONSHIP_ID, rel);

        DirectoryNode root = fs.getRoot();
        POIFSDocumentType type = POIFSDocumentType.detectType(root);

        if (root.hasEntry("CONTENTS") && root.hasEntry("\u0001Ole") && root.hasEntry("\u0001CompObj")
                && root.hasEntry("\u0003ObjInfo")) {
            // TIKA-704: OLE 2.0 embedded non-Office document?
            stream = TikaInputStream.get(fs.createDocumentInputStream("CONTENTS"));
            if (embeddedExtractor.shouldParseEmbedded(metadata)) {
                embeddedExtractor.parseEmbedded(stream, new EmbeddedContentHandler(handler), metadata, false);
            }
        } else if (POIFSDocumentType.OLE10_NATIVE == type) {
            // TIKA-704: OLE 1.0 embedded document
            Ole10Native ole = Ole10Native.createFromEmbeddedOleObject(fs);
            metadata.set(Metadata.RESOURCE_NAME_KEY, ole.getLabel());
            byte[] data = ole.getDataBuffer();
            if (data != null) {
                stream = TikaInputStream.get(data);
            }

            if (stream != null && embeddedExtractor.shouldParseEmbedded(metadata)) {
                embeddedExtractor.parseEmbedded(stream, new EmbeddedContentHandler(handler), metadata, false);
            }
        } else {
            handleEmbeddedFile(part, handler, rel);
        }
    } catch (FileNotFoundException e) {
        // There was no CONTENTS entry, so skip this part
    } catch (Ole10NativeException e) {
        // Could not process an OLE 1.0 entry, so skip this part
    }
}

From source file:net.sf.mmm.content.parser.impl.poi.AbstractContentParserPoi.java

License:Apache License

/**
 * {@inheritDoc}//from ww  w. ja  v  a2  s  .co m
 */
@Override
public void parse(InputStream inputStream, long filesize, ContentParserOptions options,
        MutableGenericContext context) throws Exception {

    POIFSFileSystem poiFs = new POIFSFileSystem(inputStream);
    SummaryInformation summaryInfo = (SummaryInformation) PropertySetFactory
            .create(poiFs.createDocumentInputStream(SummaryInformation.DEFAULT_STREAM_NAME));
    String title = summaryInfo.getTitle();
    if (title != null) {
        context.setVariable(VARIABLE_NAME_TITLE, title);
    }
    String author = summaryInfo.getAuthor();
    if (author != null) {
        context.setVariable(VARIABLE_NAME_CREATOR, author);
    }
    String keywords = summaryInfo.getKeywords();
    if (keywords != null) {
        context.setVariable(VARIABLE_NAME_KEYWORDS, keywords);
    }
    context.setVariable(VARIABLE_NAME_TEXT, extractText(poiFs, filesize, options));
}

From source file:net.sf.mmm.content.parser.impl.poi.ContentParserPpt.java

License:Apache License

/**
 * {@inheritDoc}// w ww. j a v a  2  s  .  c  o  m
 */
@Override
protected String extractText(POIFSFileSystem poiFs, long filesize, ContentParserOptions options)
        throws Exception {

    // PowerPointExtractor pptExtractor = new PowerPointExtractor(poiFs);
    // return pptExtractor.getText();

    DocumentInputStream docStream = poiFs.createDocumentInputStream(POIFS_POWERPOINT_DOC);

    int length = docStream.available();
    int maximumBufferSize = options.getMaximumBufferSize();
    if (maximumBufferSize < length) {
        length = maximumBufferSize;
    }
    int capacity = length / 10;
    StringBuffer textBuffer = new StringBuffer(capacity);
    byte[] buffer = new byte[length];
    docStream.read(buffer);
    docStream.close();
    extractRecursive(buffer, 0, length, textBuffer);
    return textBuffer.toString();
}

From source file:net.sf.mmm.content.parser.impl.poi.ContentParserXls.java

License:Apache License

/**
 * {@inheritDoc}/*  www .j a v a  2s.  c  om*/
 */
@Override
protected String extractText(POIFSFileSystem poiFs, long filesize, ContentParserOptions options)
        throws Exception {

    int maxBufferSize = options.getMaximumBufferSize();
    int maxCharSize = maxBufferSize / 2;
    InputStream documentInputStream = poiFs.createDocumentInputStream(POIFS_EXCEL_DOC);
    // actually there seems no smart guess for the initial capacity of
    // textBuffer
    // the text length can have any ration to documentInputStream.available()
    // the only possibility would be to create the string buffer in the listener
    // from the size of the SSTRecord. In this case stable code is better than
    // saving a tiny percent of performance...
    StringBuilder textBuffer = new StringBuilder(1024);
    try {
        HSSFRequest req = new HSSFRequest();
        req.addListenerForAllRecords(new ExcelListener(textBuffer, maxCharSize));
        HSSFEventFactory factory = new HSSFEventFactory();
        factory.processEvents(req, documentInputStream);
    } finally {
        documentInputStream.close();
    }
    return textBuffer.toString();
}

From source file:no.trank.openpipe.parse.ms.POIUtils.java

License:Apache License

/**
 * Fetches the \005SummaryInformation and \005DocumentSummaryInformation streams from the poi
 * file system and exctracts all properties of primitive type, String or Date.
 * /* w ww  . j  a v  a 2 s .  co  m*/
 * @param fs the poi filesystem 
 * @return the properties
 */
public static Map<String, String> getProperties(POIFSFileSystem fs) {
    Map<String, String> map = new HashMap<String, String>();

    try {
        InputStream stream = fs.createDocumentInputStream(SummaryInformation.DEFAULT_STREAM_NAME);
        addProperties(map, PropertySetFactory.create(stream));
    } catch (Exception e) {
        // ignore
    }

    try {
        InputStream stream = fs.createDocumentInputStream(DocumentSummaryInformation.DEFAULT_STREAM_NAME);
        addProperties(map, PropertySetFactory.create(stream));
    } catch (Exception e) {
        // ignore
    }

    return map;
}

From source file:org.apache.nutch.parse.msword.WordExtractor.java

License:Apache License

/**
 * Gets the text from a Word document./*from www .ja v a 2 s .  co  m*/
 *
 * @param in The InputStream representing the Word file.
 */
protected String extractText(InputStream in) throws Exception {

    ArrayList text = new ArrayList();
    POIFSFileSystem fsys = new POIFSFileSystem(in);

    // load our POIFS document streams.
    DocumentEntry headerProps = (DocumentEntry) fsys.getRoot().getEntry("WordDocument");
    DocumentInputStream din = fsys.createDocumentInputStream("WordDocument");
    byte[] header = new byte[headerProps.getSize()];

    din.read(header);
    din.close();

    int info = LittleEndian.getShort(header, 0xa);
    if ((info & 0x4) != 0) {
        throw new FastSavedException("Fast-saved files are unsupported at this time");
    }
    if ((info & 0x100) != 0) {
        throw new PasswordProtectedException("This document is password protected");
    }

    // determine the version of Word this document came from.
    int nFib = LittleEndian.getShort(header, 0x2);
    switch (nFib) {
    case 101:
    case 102:
    case 103:
    case 104:
        // this is a Word 6.0 doc send it to the extractor for that version.
        Word6Extractor oldExtractor = new Word6Extractor();
        return oldExtractor.extractText(header);
    }

    //Get the information we need from the header
    boolean useTable1 = (info & 0x200) != 0;

    //get the location of the piece table
    int complexOffset = LittleEndian.getInt(header, 0x1a2);

    // determine which table stream we must use.
    String tableName = null;
    if (useTable1) {
        tableName = "1Table";
    } else {
        tableName = "0Table";
    }

    DocumentEntry table = (DocumentEntry) fsys.getRoot().getEntry(tableName);
    byte[] tableStream = new byte[table.getSize()];

    din = fsys.createDocumentInputStream(tableName);

    din.read(tableStream);
    din.close();

    int chpOffset = LittleEndian.getInt(header, 0xfa);
    int chpSize = LittleEndian.getInt(header, 0xfe);
    int fcMin = LittleEndian.getInt(header, 0x18);
    CHPBinTable cbt = new CHPBinTable(header, tableStream, chpOffset, chpSize, fcMin);

    // load our text pieces and our character runs
    ComplexFileTable cft = new ComplexFileTable(header, tableStream, complexOffset, fcMin);
    TextPieceTable tpt = cft.getTextPieceTable();
    List textPieces = tpt.getTextPieces();

    // make the POIFS objects available for garbage collection
    din = null;
    fsys = null;
    table = null;
    headerProps = null;

    List textRuns = cbt.getTextRuns();
    Iterator runIt = textRuns.iterator();
    Iterator textIt = textPieces.iterator();

    TextPiece currentPiece = (TextPiece) textIt.next();
    int currentTextStart = currentPiece.getStart();
    int currentTextEnd = currentPiece.getEnd();

    WordTextBuffer finalTextBuf = new WordTextBuffer();

    // iterate through all text runs extract the text only if they haven't been
    // deleted
    while (runIt.hasNext()) {
        CHPX chpx = (CHPX) runIt.next();
        boolean deleted = isDeleted(chpx.getGrpprl());
        if (deleted) {
            continue;
        }

        int runStart = chpx.getStart();
        int runEnd = chpx.getEnd();

        while (runStart >= currentTextEnd) {
            currentPiece = (TextPiece) textIt.next();
            currentTextStart = currentPiece.getStart();
            currentTextEnd = currentPiece.getEnd();
        }

        if (runEnd < currentTextEnd) {
            String str = currentPiece.substring(runStart - currentTextStart, runEnd - currentTextStart);
            finalTextBuf.append(str);
        } else if (runEnd > currentTextEnd) {
            while (runEnd > currentTextEnd) {
                String str = currentPiece.substring(runStart - currentTextStart,
                        currentTextEnd - currentTextStart);
                finalTextBuf.append(str);
                if (textIt.hasNext()) {
                    currentPiece = (TextPiece) textIt.next();
                    currentTextStart = currentPiece.getStart();
                    runStart = currentTextStart;
                    currentTextEnd = currentPiece.getEnd();
                } else {
                    return finalTextBuf.toString();
                }
            }
            String str = currentPiece.substring(0, runEnd - currentTextStart);
            finalTextBuf.append(str);
        } else {
            String str = currentPiece.substring(runStart - currentTextStart, runEnd - currentTextStart);
            if (textIt.hasNext()) {
                currentPiece = (TextPiece) textIt.next();
                currentTextStart = currentPiece.getStart();
                currentTextEnd = currentPiece.getEnd();
            }
            finalTextBuf.append(str);
        }
    }
    return finalTextBuf.toString();
}