[Babeldoc-devel] babeldoc/modules/conversion/src/com/babeldoc/conversion/flatfile ConversionUnmarsha

SourceForge Headquarters 1320 Columbia Street Suite 310 San Diego, CA 92101 +1 (858) 422-6466

Update of /cvsroot/babeldoc/babeldoc/modules/conversion/src/com/babeldoc/conversion/flatfile
In directory sc8-pr-cvs1:/tmp/cvs-serv25588/src/com/babeldoc/conversion/flatfile

Added Files:
	ConversionUnmarshaller.java FieldData.java 
	FlatFileConversionClient.java FlatFileConverter.java 
	LineSegmentData.java 
Log Message:
Lots of rearrangement of the conversion module - now using dom4j in the flatfile code - moved packages around.

--- NEW FILE: ConversionUnmarshaller.java ---
/* ====================================================================
 * The Apache Software License, Version 1.1
 *
 * Copyright (c) 2000 The Apache Software Foundation.  All rights
 * reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 *
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 *
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in
 *    the documentation and/or other materials provided with the
 *    distribution.
 *
 * 3. The end-user documentation included with the redistribution,
 *    if any, must include the following acknowledgment:
 *       "This product includes software developed by the
 *        Apache Software Foundation (http://www.apache.org/)."
 *    Alternately, this acknowledgment may appear in the software itself,
 *    if and wherever such third-party acknowledgments normally appear.
 *
 * 4. The names "Apache" and "Apache Software Foundation" must
 *    not be used to endorse or promote products derived from this
 *    software without prior written permission. For written
 *    permission, please contact ap...@ap....
 *
 * 5. Products derived from this software may not be called "Apache",
 *    nor may "Apache" appear in their name, without prior written
 *    permission of the Apache Software Foundation.
 *
 * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESSED OR IMPLIED
 * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
 * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
 * DISCLAIMED.  IN NO EVENT SHALL THE APACHE SOFTWARE FOUNDATION OR
 * ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
 * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
 * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
 * USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
 * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
 * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
 * OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 * SUCH DAMAGE.
 * ====================================================================
 *
 * This software consists of voluntary contributions made by many
 * individuals on behalf of the Apache Software Foundation.  For more
 * information on the Apache Software Foundation, please see
 * <http://www.apache.org/>.
 *
 * Portions of this software are based upon public domain software
 * originally written at the National Center for Supercomputing Applications,
 * University of Illinois, Urbana-Champaign.
 * ====================================================================
 *
 * Babeldoc:  The Universal Document Processor
 *
 * $Header: /cvsroot/babeldoc/babeldoc/modules/conversion/src/com/babeldoc/conversion/flatfile/ConversionUnmarshaller.java,v 1.1 2003/07/19 13:16:47 triphop Exp $
 * $DateTime$
 * $Author: triphop $
 *
 */
package com.babeldoc.conversion.flatfile;

/**
 * Interface that conversion unmarshallers must implement.  The definitive
 * implementation of this class is DigesterConversionUnmarshaller.  No further
 * implementations are necessary and certainly not planned.  The reason for
 * this class stems from when the old SAX based conversion unmarshaller was
 * replaced with the new digester and I needed to swap the two
 * interchangeably.
 *
 * @author bmcdonald
 * @version 1.0
 */
public interface ConversionUnmarshaller {
  /** What kind of file is this? */
  public static final int CSV_CONVERSION = 0;
  public static final int LINE_CONVERSION = 1;
  public static final int PARA_CONVERSION = 2;
  public static final int LINESEG_CONVERSION = 3;

  /**
   * Get the conversion type
   *
   * @return
   */
  public int getConversionType();

  /**
   * Get the field separator for csv fields.
   *
   * @return
   */
  public String getFieldSeparator();

  /**
   * Get the field data
   *
   * @return
   */
  public FieldData[] getFields();

  /**
   * get the interparagraph skip
   *
   * @return
   */
  public int getInterParagraphSkip();

  /**
   * get the characters to skip from the left
   *
   * @return
   */
  public int getLeftMargin();

  /**
   * Get the line segments.
   *
   * @return
   */
  public LineSegmentData[] getLineSegments();

  /**
   * get the line separator
   *
   * @return
   */
  public String getLineSeparator();

  /**
   * Get the lines per para
   *
   * @return
   */
  public int getLinesPerPara();

  /**
   * Get the root element
   *
   * @return
   */
  public String getRootElement();

  /**
   * get the row element
   *
   * @return
   */
  public String getRowElement();

  /**
   * Get the lines to skip
   *
   * @return
   */
  public int getTopSkip();
}

--- NEW FILE: FieldData.java ---
/* ====================================================================
 * The Apache Software License, Version 1.1
 *
 * Copyright (c) 2000 The Apache Software Foundation.  All rights
 * reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 *
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 *
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in
 *    the documentation and/or other materials provided with the
 *    distribution.
 *
 * 3. The end-user documentation included with the redistribution,
 *    if any, must include the following acknowledgment:
 *       "This product includes software developed by the
 *        Apache Software Foundation (http://www.apache.org/)."
 *    Alternately, this acknowledgment may appear in the software itself,
 *    if and wherever such third-party acknowledgments normally appear.
 *
 * 4. The names "Apache" and "Apache Software Foundation" must
 *    not be used to endorse or promote products derived from this
 *    software without prior written permission. For written
 *    permission, please contact ap...@ap....
 *
 * 5. Products derived from this software may not be called "Apache",
 *    nor may "Apache" appear in their name, without prior written
 *    permission of the Apache Software Foundation.
 *
 * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESSED OR IMPLIED
 * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
 * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
 * DISCLAIMED.  IN NO EVENT SHALL THE APACHE SOFTWARE FOUNDATION OR
 * ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
 * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
 * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
 * USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
 * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
 * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
 * OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 * SUCH DAMAGE.
 * ====================================================================
 *
 * This software consists of voluntary contributions made by many
 * individuals on behalf of the Apache Software Foundation.  For more
 * information on the Apache Software Foundation, please see
 * <http://www.apache.org/>.
 *
 * Portions of this software are based upon public domain software
 * originally written at the National Center for Supercomputing Applications,
 * University of Illinois, Urbana-Champaign.
 * ====================================================================
 *
 * Babeldoc:  The Universal Document Processor
 *
 * $Header: /cvsroot/babeldoc/babeldoc/modules/conversion/src/com/babeldoc/conversion/flatfile/FieldData.java,v 1.1 2003/07/19 13:16:47 triphop Exp $
 * $DateTime$
 * $Author: triphop $
 *
 */
package com.babeldoc.conversion.flatfile;

import org.apache.commons.lang.builder.ToStringBuilder;

/**
 * Simple utility class to hold all the field data.  This is one of the two
 * main data objects in the conversion process.
 *
 * @author Bmcdonald
 * @version 1.0
 */
public class FieldData {
  public String name;
  public int column;
  public int number;
  public int row;
  public int width;

  /**
   * Useful for debugging.
   *
   * @return
   */
  public String toString() {
    return new ToStringBuilder(this).append("name", name).append("row", row)
                                    .append("column", column)
                                    .append("width", width)
                                    .append("number", number).toString();
  }
}

--- NEW FILE: FlatFileConversionClient.java ---
/* ====================================================================
 * The Apache Software License, Version 1.1
 *
 * Copyright (c) 2000 The Apache Software Foundation.  All rights
 * reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 *
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 *
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in
 *    the documentation and/or other materials provided with the
 *    distribution.
 *
 * 3. The end-user documentation included with the redistribution,
 *    if any, must include the following acknowledgment:
 *       "This product includes software developed by the
 *        Apache Software Foundation (http://www.apache.org/)."
 *    Alternately, this acknowledgment may appear in the software itself,
 *    if and wherever such third-party acknowledgments normally appear.
 *
 * 4. The names "Apache" and "Apache Software Foundation" must
 *    not be used to endorse or promote products derived from this
 *    software without prior written permission. For written
 *    permission, please contact ap...@ap....
 *
 * 5. Products derived from this software may not be called "Apache",
 *    nor may "Apache" appear in their name, without prior written
 *    permission of the Apache Software Foundation.
 *
 * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESSED OR IMPLIED
 * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
 * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
 * DISCLAIMED.  IN NO EVENT SHALL THE APACHE SOFTWARE FOUNDATION OR
 * ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
 * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
 * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
 * USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
 * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
 * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
 * OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 * SUCH DAMAGE.
 * ====================================================================
 *
 * This software consists of voluntary contributions made by many
 * individuals on behalf of the Apache Software Foundation.  For more
 * information on the Apache Software Foundation, please see
 * <http://www.apache.org/>.
 *
 * Portions of this software are based upon public domain software
 * originally written at the National Center for Supercomputing Applications,
 * University of Illinois, Urbana-Champaign.
 * ====================================================================
 *
 * Babeldoc:  The Universal Document Processor
 *
 * $Header: /cvsroot/babeldoc/babeldoc/modules/conversion/src/com/babeldoc/conversion/flatfile/FlatFileConversionClient.java,v 1.1 2003/07/19 13:16:47 triphop Exp $
 * $DateTime$
 * $Author: triphop $
 *
 */
package com.babeldoc.conversion.flatfile;

import com.babeldoc.conversion.ConversionException;
import com.babeldoc.conversion.ConversionHelper;
import com.babeldoc.conversion.flatfile.digester.DigesterConversionUnmarshaller;
import com.babeldoc.core.BabeldocCommand;
import com.babeldoc.core.I18n;
import com.babeldoc.core.LogService;
import com.babeldoc.core.ResourceLoader;
import org.apache.commons.cli.CommandLine;
import org.apache.commons.cli.OptionBuilder;
import org.apache.commons.cli.Options;
import org.dom4j.Document;

import java.io.IOException;
import java.io.InputStream;
import java.io.OutputStreamWriter;
import java.io.PrintWriter;

/**
 * <p>
 * Do conversions based on conversion xml file.  This is the entry point for
 * running xml based conversions.  The conversions xml file is converted to a
 * set of value objects by the Unmarshaller.  These classes carry the data
 * controlling the conversion process.
 * </p>
 * 
 * <p>
 * The actual conversion xml is specied by a schema xml file,
 * readme/schema/conversion.xsd
 * </p>
 *
 * @author Bmcdonald
 * @version 1.0
 */
public class FlatFileConversionClient
    extends BabeldocCommand {

  protected static final String NULL = "";
  protected ConversionUnmarshaller unmarshaller;
  private Document document;

  /**
   * Construct this object and call the super with the argument for setting up
   * the conversion client.
   *
   * @param args
   */
  public FlatFileConversionClient(String[] args) {
    super("conversion", I18n.get("conversion.009"), args);
  }

  /**
   * Main method.
   *
   * @param commandline DOCUMENT ME!
   */
  public void execute(CommandLine commandline) {
    InputStream in = null;
    InputStream conf = null;

    if (commandline.hasOption('c')) {
      String convFile = commandline.getOptionValue('c');

      try {
        conf = ResourceLoader.getResourceStream(convFile);
      } catch (IOException e) {
        LogService.getInstance().logError(I18n.get(
            "conversion.exception.io.convfile", convFile), e);

        return;
      }
    }

    if (commandline.hasOption('f')) {
      String inFile = commandline.getOptionValue('f');

      try {
        in = ResourceLoader.getResourceStream(inFile);
      } catch (IOException e) {
        LogService.getInstance().logError(I18n.get(
            "conversion.exception.io.infile", inFile), e);

        return;
      }
    }

    if ((in != null) && (conf != null)) {
      PrintWriter writer = new PrintWriter(new OutputStreamWriter(System.out));
      try {
        ConversionHelper.render(new FlatFileConverter(new DigesterConversionUnmarshaller(conf)).toXml(in),
            System.out);
      } catch (ConversionException e) {
        LogService.getInstance().logError(e);
      }
      writer.flush();
      writer.close();
    } else {
      System.err.println(I18n.get("conversion.008"));
    }
  }

  /**
   * Main
   *
   * @param args the arguments
   */
  public static void main(String[] args) {
    new FlatFileConversionClient(args);
  }

  /**
   * setup the options on the command line.
   *
   * @param options the options to access
   */
  public void setupCommandLine(Options options) {
    super.setupCommandLine(options);
    LogService.getInstance();
    options.addOption(OptionBuilder.isRequired().hasArg(true)
                                   .withDescription(I18n.get("conversion.010"))
                                   .withLongOpt("file").create('f'));
    options.addOption(OptionBuilder.isRequired().hasArg(true)
                                   .withDescription(I18n.get("conversion.011"))
                                   .withLongOpt("config").create('c'));
  }
}

--- NEW FILE: FlatFileConverter.java ---
package com.babeldoc.conversion.flatfile;

import com.babeldoc.conversion.ConversionException;
import com.babeldoc.core.I18n;
import com.babeldoc.core.NameValuePair;
import com.mindprod.csv.CSVReader;
import org.dom4j.Document;
import org.dom4j.DocumentFactory;
import org.dom4j.Element;

import java.io.*;

/**
 */
public class FlatFileConverter {
  protected ConversionUnmarshaller unmarshaller;
  private Document document;

  /**
   * Construct - this requires an unmarshaller which governs the conversion
   * of the flat file.
   *
   * @param unmarshaller
   */
  public FlatFileConverter(ConversionUnmarshaller unmarshaller) {
    this.unmarshaller = unmarshaller;
  }

  /**
   * handle csv conversions.  Watch the errors and make sure that xml start and
   * end tags get handled correctly.
   *
   * @param is the data
   */
  public Document toXml(InputStream is) {
    BufferedReader reader = new BufferedReader(new InputStreamReader(is));
    boolean carryOn = true;
    this.setUnmarshaller(unmarshaller);

    document = DocumentFactory.getInstance().createDocument();
    Element root = getDocument().addElement(getUnmarshaller().getRootElement());
    try {
      doSkipLines(reader, getUnmarshaller().getTopSkip());

      while (carryOn) {
        String[] paragraph = getParagraph(reader);

        if (paragraph == null) {
          break;
        }

        // Handle line-segments
        if (getUnmarshaller().getConversionType() == ConversionUnmarshaller.LINESEG_CONVERSION) {
          handleSegmentedLine(root, paragraph);
        } else {
          handleNonSegmented(root, paragraph);
        }

        carryOn = doSkipLines(reader, getUnmarshaller().getInterParagraphSkip());
      }
    } catch (Exception e) {
      errorComment(root, e);
    }
    return document;
  }

  /**
   * Set the unmarshaller
   *
   * @param unmarshaller the ConversionXmlUnmarshaller to use.
   */
  public void setUnmarshaller(ConversionUnmarshaller unmarshaller) {
    this.unmarshaller = unmarshaller;
  }

  /**
   * Get the unmarshaller
   *
   * @return the unmarshaller
   */
  public ConversionUnmarshaller getUnmarshaller() {
    return unmarshaller;
  }

  /**
   * Convert the data.  Depending on the setting of the type in the
   * unmarshaller the different converters get called.
   *
   * @param element the element underwhich to add the new elements (!!!)
   * @param para is the array of strings
   *
   * @throws com.babeldoc.conversion.ConversionException DOCUMENT ME!
   */
  public void convert(Element element, String[] para) throws ConversionException {
    if (getUnmarshaller().getConversionType() == ConversionUnmarshaller.CSV_CONVERSION) {
      convertCsv(element, para, getUnmarshaller().getFields());
    } else if (getUnmarshaller().getConversionType() == ConversionUnmarshaller.LINE_CONVERSION) {
      convertLine(element, para, getUnmarshaller().getFields());
    } else if (getUnmarshaller().getConversionType() == ConversionUnmarshaller.PARA_CONVERSION) {
      convertPara(element, para, getUnmarshaller().getFields());
    } else {
      throw new ConversionException(I18n.get("conversion.007"));
    }
  }

  /**
   * Skip the number of lines at the top of the file.
   *
   * @param reader DOCUMENT ME!
   * @param numToSkip DOCUMENT ME!
   *
   * @return more lines found??
   */
  protected boolean doSkipLines(BufferedReader reader, int numToSkip) {
    for (int i = 0; i < numToSkip; ++i) {
      if (readLine(reader) == null) {
        return false;
      }
    }
    return true;
  }

  /**
   * Add an error comment right here.
   *
   * @param element
   * @param e
   */
  protected void errorComment(Element element, Exception e) {
    element.addComment(e.toString());
  }
  /**
   * read the line from the input stream.
   *
   * @param reader the input stream.
   *
   * @return return null if no more lines found, else return the line.
   */
  protected static String readLine(BufferedReader reader) {
    try {
      return reader.readLine();
    } catch (Exception e) {
      return null;
    }
  }

  /**
   * Scan the  input for all the lines in a paragraph and return them
   *
   * @param reader the input stream
   *
   * @return the paragraph of lines OR NULL if lines ran out before end.
   */
  protected String[] getParagraph(BufferedReader reader) {
    String[] lines = new String[getUnmarshaller().getLinesPerPara()];

    for (int i = 0; i < lines.length; ++i) {
      String line = readLine(reader);

      if (line != null) {
        lines[i] = trimLine(line);
      } else {
        return null;
      }
    }

    return lines;
  }

  /**
   * Convert from csv format.  Simple enough.  Things to watch for:  Differing
   * number of tokens in input and configuration and if the configuration file
   * duplicate field numbers are found.
   *
   * @param row the row element to add the elements to.
   * @param para the array of lines (only one line expected)
   * @param fields DOCUMENT ME!
   *
   * @throws com.babeldoc.conversion.ConversionException DOCUMENT ME!
   */
  protected void convertCsv(Element row, String[] para, FieldData[] fields)
      throws ConversionException {
    if (para.length != 1) {
      throw new ConversionException(I18n.get("conversion.001"));
    }

    char separator = ',';
    if(this.getUnmarshaller().getFieldSeparator()!=null) {
      separator = this.getUnmarshaller().getFieldSeparator().charAt(0);
    }

    for(int l=0; l < para.length; ++l) {
      CSVReader csvreader = new CSVReader(new StringReader(para[l]),
          separator, '\"', false, true);
      if(this.getUnmarshaller().getFieldSeparator()!=null) {
      }
      String[] ltokens = new String[0];
      try {
        ltokens = csvreader.getAllFieldsInLine();
      } catch (IOException e) {
        e.printStackTrace();  //This should never happen
      }

      if (ltokens != null) {
        NameValuePair[] pairs = new NameValuePair[ltokens.length];

        for (int i = 0; i < fields.length; ++i) {
          FieldData field = fields[i];
          String name = field.name;
          int fieldNum = field.number - 1;

          // Make sure that we dont try and reference an ltoken in
          // the input stream from the field number that does not exist
          // And protect against data duplication.
          if (fieldNum > pairs.length) {
            throw new ConversionException(I18n.get("conversion.002",
                new Integer(getUnmarshaller().getFields().length),
                new Integer(ltokens.length)));
          } else if (pairs[fieldNum] != null) {
            throw new ConversionException(I18n.get("conversion.003", name));
          } else {
            pairs[fieldNum] = new NameValuePair(name, ltokens[fieldNum]);
          }
        }
        addElements(row, pairs);
      }
    }
  }

  private static void addElements(Element row, NameValuePair[] pairs) {
    for(int j = 0; j < pairs.length; ++j) {
      Element element = row.addElement(pairs[j].getName());
      element.addText(pairs[j].getValue());
    }
  }

  /**
   * Convert from lines.
   *
   * @param row the row element to add the field elements to.
   * @param para the paragraph of input data
   * @param fields the fields to extract from the input data
   *
   * @throws com.babeldoc.conversion.ConversionException DOCUMENT ME!
   */
  protected void convertLine(Element row, String[] para, FieldData[] fields)
      throws ConversionException {
    if (para.length != 1) {
      throw new ConversionException(I18n.get("conversion.004"));
    }

    String line = para[0];
    NameValuePair[] pairs = new NameValuePair[fields.length];

    for (int i = 0; i < fields.length; ++i) {
      FieldData field = fields[i];
      String name = field.name;
      int start = field.column - 1;
      int width = field.width;
      int end = start + width;

      // Check overruns.
      String value = null;

      // Handle negative starts bug: 741190 ]
      if (start < 0) {
        start = 0;
      }

      // Ok get data - first check if we can get all the data
      if (end > line.length()) {
        // can we get any of it?
        if (line.length() < start) {
          value = "";
        }
        // Well, we get what we can.
        else {
          value = line.substring(start);
        }
      } else {
        value = line.substring(start, end);
      }

      pairs[i] = new NameValuePair(name, value);
    }
    addElements(row, pairs);
  }

  /**
   * Convert from para.  Things to watch are that the field does not exceed the
   * current line length or the number of rows.  Other than that this is a
   * simple piece of code.
   *
   * @param rowElement the row element to which to add the field elements
   * @param para the paragraph of input
   * @param fields DOCUMENT ME!
   *
   * @throws com.babeldoc.conversion.ConversionException DOCUMENT ME!
   */
  protected void convertPara(Element rowElement, String[] para, FieldData[] fields)
      throws ConversionException {
    NameValuePair[] pairs = new NameValuePair[fields.length];

    for (int i = 0; i < fields.length; ++i) {
      FieldData field = fields[i];
      String name = field.name;
      int row = field.row - 1;
      int start = field.column - 1;
      int width = field.width;
      int end = start + width;

      // Check overruns.
      if (row > para.length) {
        throw new ConversionException(I18n.get("conversion.005", name));
      } else if (end > para[row].length()) {
        throw new ConversionException(I18n.get("conversion.006", name));
      }

      String value = para[row].substring(start, end);
      pairs[i] = new NameValuePair(name, value);
    }

    addElements(rowElement, pairs);
  }

  /**
   * Trim the left margin from the line.
   *
   * @param input the line to trim
   *
   * @return the trimmed line
   */
  protected String trimLine(String input) {
    int leftMargin = unmarshaller.getLeftMargin();

    if (leftMargin == 0) {
      return input;
    } else if (leftMargin >= input.length()) {
      return null;
    } else {
      return input.substring(leftMargin);
    }
  }

  /**
   * Handle a line segment.
   *
   * @param startElement add a line segment
   * @param lineSegment
   */
  private Element handleLineSegmentElement(Element startElement, LineSegmentData lineSegment) {
    if (lineSegment.startGroup != null) {
      startElement = startElement.addElement(lineSegment.startGroup);
    }
    return startElement.addElement(lineSegment.name);
  }

  /**
   * Handle non-segmented paragraph
   *
   * @param root the root element
   * @param paragraph the paragraph
   */
  private void handleNonSegmented(Element root, String[] paragraph) {
    Element rowElement = root.addElement(getUnmarshaller().getRowElement());

    try {
      convert(rowElement, paragraph);
    } catch (ConversionException ce) {
      errorComment(rowElement, ce);
    }
  }

  /**
   * Handle segmentline paragraph
   *
   * @param element element to start doing this segmented line
   * @param para the paragraph
   */
  private void handleSegmentedLine(Element element, String[] para) {
    String line = para[0];
    int numSegments = getUnmarshaller().getLineSegments().length;

    for (int i = 0; i < numSegments; ++i) {
      LineSegmentData lineSegment = getUnmarshaller().getLineSegments()[i];
      int column = lineSegment.column - 1;
      int width = lineSegment.width;
      String value = lineSegment.value;

      if ((line.length() > (column + width)) &&
            line.substring(column, width).equals(value)) {
        Element segmentElement = handleLineSegmentElement(element, lineSegment);

        try {
          handlineLineSegmentElementData(segmentElement, lineSegment, para);

          break;
        } catch (Exception e) {
          errorComment(segmentElement, e);
        } finally {
        }
      }
    }
  }

  /**
   * Handle the two kinds of line segments...
   *
   * @param lineSegment
   * @param para
   *
   * @throws com.babeldoc.conversion.ConversionException
   */
  private void handlineLineSegmentElementData(Element element, LineSegmentData lineSegment,
    String[] para) throws ConversionException {
    FieldData[] fields = lineSegment.fields;

    if (lineSegment.conversionType == ConversionUnmarshaller.CSV_CONVERSION) {
      convertCsv(element, para, fields);
    } else if (lineSegment.conversionType == ConversionUnmarshaller.LINE_CONVERSION) {
      convertLine(element, para, fields);
    } else {
      throw new ConversionException(I18n.get("conversion.007"));
    }
  }

  public Document getDocument() {
    return document;
  }

  public void setDocument(Document document) {
    this.document = document;
  }

}

--- NEW FILE: LineSegmentData.java ---
/* ====================================================================
 * The Apache Software License, Version 1.1
 *
 * Copyright (c) 2000 The Apache Software Foundation.  All rights
 * reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 *
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 *
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in
 *    the documentation and/or other materials provided with the
 *    distribution.
 *
 * 3. The end-user documentation included with the redistribution,
 *    if any, must include the following acknowledgment:
 *       "This product includes software developed by the
 *        Apache Software Foundation (http://www.apache.org/)."
 *    Alternately, this acknowledgment may appear in the software itself,
 *    if and wherever such third-party acknowledgments normally appear.
 *
 * 4. The names "Apache" and "Apache Software Foundation" must
 *    not be used to endorse or promote products derived from this
 *    software without prior written permission. For written
 *    permission, please contact ap...@ap....
 *
 * 5. Products derived from this software may not be called "Apache",
 *    nor may "Apache" appear in their name, without prior written
 *    permission of the Apache Software Foundation.
 *
 * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESSED OR IMPLIED
 * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
 * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
 * DISCLAIMED.  IN NO EVENT SHALL THE APACHE SOFTWARE FOUNDATION OR
 * ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
 * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
 * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
 * USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
 * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
 * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
 * OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 * SUCH DAMAGE.
 * ====================================================================
 *
 * This software consists of voluntary contributions made by many
 * individuals on behalf of the Apache Software Foundation.  For more
 * information on the Apache Software Foundation, please see
 * <http://www.apache.org/>.
 *
 * Portions of this software are based upon public domain software
 * originally written at the National Center for Supercomputing Applications,
 * University of Illinois, Urbana-Champaign.
 * ====================================================================
 *
 * Babeldoc:  The Universal Document Processor
 *
 * $Header: /cvsroot/babeldoc/babeldoc/modules/conversion/src/com/babeldoc/conversion/flatfile/LineSegmentData.java,v 1.1 2003/07/19 13:16:47 triphop Exp $
 * $DateTime$
 * $Author: triphop $
 *
 */
package com.babeldoc.conversion.flatfile;

import org.apache.commons.lang.builder.ToStringBuilder;

/**
 * Hold the configuration for each of the line segments.  This one of the two
 * main data objects in the conversion process.
 *
 * @author Bmcdonald
 * @version 1.0
 */
public class LineSegmentData {
  public String endGroup;
  public String name;
  public String startGroup;
  public String value;
  public FieldData[] fields;
  public int column;
  public int conversionType;
  public int width;

  /**
   * toXml to a string
   *
   * @return string
   */
  public String toString() {
    return new ToStringBuilder(this).append("name", name)
                                    .append("column", column)
                                    .append("width", width)
                                    .append("conversionType", conversionType)
                                    .append("value", value)
                                    .append("startGroup", startGroup)
                                    .append("endGroup", endGroup)
                                    .append("fields", fields).toString();
  }
}

[Babeldoc-devel] babeldoc/modules/conversion/src/com/babeldoc/conversion/flatfile ConversionUnmarsha

[Babeldoc-devel] babeldoc/modules/conversion/src/com/babeldoc/conversion/flatfile ConversionUnmarshaller.java,NONE,1.1 FieldData.java,NONE,1.1 FlatFileConversionClient.java,NONE,1.1 FlatFileConverter.java,NONE,1.1 LineSegmentData.java,NONE,1.1