babeldoc-devel

[Babeldoc-devel] babeldoc/modules/conversion/src/com/babeldoc/conversion/flatfile FlatFileConverter.java,1.2,1.2.4.1

[<tr...@us...>]

Update of /cvsroot/babeldoc/babeldoc/modules/conversion/src/com/babeldoc/conversion/flatfile
In directory sc8-pr-cvs1:/tmp/cvs-serv24773/modules/conversion/src/com/babeldoc/conversion/flatfile

Modified Files:
      Tag: V1-2
	FlatFileConverter.java 
Log Message:
column error in the substring

Index: FlatFileConverter.java
===================================================================
RCS file: /cvsroot/babeldoc/babeldoc/modules/conversion/src/com/babeldoc/conversion/flatfile/FlatFileConverter.java,v
retrieving revision 1.2
retrieving revision 1.2.4.1
diff -C2 -d -r1.2 -r1.2.4.1
*** FlatFileConverter.java	30 Oct 2003 00:15:56 -0000	1.2
--- FlatFileConverter.java	26 Dec 2003 18:13:59 -0000	1.2.4.1
***************
*** 1,438 ****
! 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 getChild 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 getChild 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) {
!     e.printStackTrace();
!     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-1) {
!             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) {
!       if(pairs[j]!=null) {
!         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 getChild data - first check if we can getChild all the data
!       if (end > line.length()) {
!         // can we getChild any of it?
!         if (line.length() < start) {
!           value = "";
!         }
!         // Well, we getChild 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;
!   }
! 
! }
--- 1,438 ----
! 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 getChild 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 getChild 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) {
!     e.printStackTrace();
!     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-1) {
!             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) {
!       if(pairs[j]!=null) {
!         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 getChild data - first check if we can getChild all the data
!       if (end > line.length()) {
!         // can we getChild any of it?
!         if (line.length() < start) {
!           value = "";
!         }
!         // Well, we getChild 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, 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;
!   }
! 
! }

[Babeldoc-devel] Re: PipelineDocument.toString()

[Bruce M. <br...@mc...>]

Mike,

Good to see you back.  

I completely agree with you here.  Your name looks perfect.

regards,
Bruce.

On Saturday 27 December 2003 01:20 pm, Michael Ansley wrote:
> Hi, Bruce,
>
> I noticed the discussion on the users list regarding the
> PipelineDocument.toString() method.  In the absence of other
> suggestions, I'd like to suggest that:
>
> a) toString() stay as it is, because I think that any toString() method
> should completely describe the object it's called on,
>
> b) we create a new method, say documentToString() or
> getDocumentAsString(), which contains the original toString()
> functionality.
>
> I'm disinclined to think of this as a bug, and as such, I don't see any
> reason for 1.2 to revert to the old behaviour, although others may
> disagree.  However, I would prefer to see 1.3 follow the suggestion
> outlined above.
>
> Thoughts...
>
> Any objections to me creating the new method in 1.3?  Preference for a
> name?
>
>
> MikeA

Re: [Babeldoc-devel] Re: PipelineDocument.toString()

[Dejan K. <dej...@ya...>]

The only problem I see here is that toString was used
in previous versions for getting document as String.
There are examples  in documentation where toString is
used this way. I wrote many pipelines which use
toString method for accessing content, too.
On the other hand I agree with Bruce and Mike that
toString() should return full state of object as
String - not just content. Note that currently (in 1.2
release) there is no way to access content of document
as String so whatever option we choose - it should be
implemented in 1.2 release too, not just 1.3 (1.4
stable). 

Dejan
P.S. 
I fixes few bugs in Scanner module but I have updated
only HEAD branch. I will update 1.2 branch too, and we
can start thinking about 1.2.1 bugfix release.


--- Bruce McDonald <br...@mc...> wrote:
> Mike,
> 
> Good to see you back.  
> 
> I completely agree with you here.  Your name looks
> perfect.
> 
> regards,
> Bruce.
> 
> On Saturday 27 December 2003 01:20 pm, Michael
> Ansley wrote:
> > Hi, Bruce,
> >
> > I noticed the discussion on the users list
> regarding the
> > PipelineDocument.toString() method.  In the
> absence of other
> > suggestions, I'd like to suggest that:
> >
> > a) toString() stay as it is, because I think that
> any toString() method
> > should completely describe the object it's called
> on,
> >
> > b) we create a new method, say documentToString()
> or
> > getDocumentAsString(), which contains the original
> toString()
> > functionality.
> >
> > I'm disinclined to think of this as a bug, and as
> such, I don't see any
> > reason for 1.2 to revert to the old behaviour,
> although others may
> > disagree.  However, I would prefer to see 1.3
> follow the suggestion
> > outlined above.
> >
> > Thoughts...
> >
> > Any objections to me creating the new method in
> 1.3?  Preference for a
> > name?
> >
> >
> > MikeA
> 
> 
>
-------------------------------------------------------
> This SF.net email is sponsored by: IBM Linux
> Tutorials.
> Become an expert in LINUX or just sharpen your
> skills.  Sign up for IBM's
> Free Linux Tutorials.  Learn everything from the
> bash shell to sys admin.
> Click now!
>
http://ads.osdn.com/?ad_id=1278&alloc_id=3371&op=click
> _______________________________________________
> Babeldoc-devel mailing list
> Bab...@li...
>
https://lists.sourceforge.net/lists/listinfo/babeldoc-devel


__________________________________
Do you Yahoo!?
New Yahoo! Photos - easier uploading and sharing.
http://photos.yahoo.com/

Re: [Babeldoc-devel] Re: PipelineDocument.toString()

[Michael A. <mic...@ze...>]

OK, done and committed to both branches.  The new method name is
getDocumentAsString(). =20

Cheers...


MikeA


On Sun, 2003-12-28 at 20:38, Dejan Krsmanovic wrote:
> The only problem I see here is that toString was used
> in previous versions for getting document as String.
> There are examples  in documentation where toString is
> used this way. I wrote many pipelines which use
> toString method for accessing content, too.
> On the other hand I agree with Bruce and Mike that
> toString() should return full state of object as
> String - not just content. Note that currently (in 1.2
> release) there is no way to access content of document
> as String so whatever option we choose - it should be
> implemented in 1.2 release too, not just 1.3 (1.4
> stable).=20
>=20
> Dejan
> P.S.=20
> I fixes few bugs in Scanner module but I have updated
> only HEAD branch. I will update 1.2 branch too, and we
> can start thinking about 1.2.1 bugfix release.
>=20
>=20
> --- Bruce McDonald <br...@mc...> wrote:
> > Mike,
> >=20
> > Good to see you back. =20
> >=20
> > I completely agree with you here.  Your name looks
> > perfect.
> >=20
> > regards,
> > Bruce.
> >=20
> > On Saturday 27 December 2003 01:20 pm, Michael
> > Ansley wrote:
> > > Hi, Bruce,
> > >
> > > I noticed the discussion on the users list
> > regarding the
> > > PipelineDocument.toString() method.  In the
> > absence of other
> > > suggestions, I'd like to suggest that:
> > >
> > > a) toString() stay as it is, because I think that
> > any toString() method
> > > should completely describe the object it's called
> > on,
> > >
> > > b) we create a new method, say documentToString()
> > or
> > > getDocumentAsString(), which contains the original
> > toString()
> > > functionality.
> > >
> > > I'm disinclined to think of this as a bug, and as
> > such, I don't see any
> > > reason for 1.2 to revert to the old behaviour,
> > although others may
> > > disagree.  However, I would prefer to see 1.3
> > follow the suggestion
> > > outlined above.
> > >
> > > Thoughts...
> > >
> > > Any objections to me creating the new method in
> > 1.3?  Preference for a
> > > name?
> > >
> > >
> > > MikeA
> >=20
> >=20
> >
> -------------------------------------------------------
> > This SF.net email is sponsored by: IBM Linux
> > Tutorials.
> > Become an expert in LINUX or just sharpen your
> > skills.  Sign up for IBM's
> > Free Linux Tutorials.  Learn everything from the
> > bash shell to sys admin.
> > Click now!
> >
> http://ads.osdn.com/?ad_id=3D1278&alloc_id=3D3371&op=3Dclick
> > _______________________________________________
> > Babeldoc-devel mailing list
> > Bab...@li...
> >
> https://lists.sourceforge.net/lists/listinfo/babeldoc-devel
>=20
>=20
> __________________________________
> Do you Yahoo!?
> New Yahoo! Photos - easier uploading and sharing.
> http://photos.yahoo.com/
>=20
>=20
> -------------------------------------------------------
> This SF.net email is sponsored by: IBM Linux Tutorials.
> Become an expert in LINUX or just sharpen your skills.  Sign up for IBM's
> Free Linux Tutorials.  Learn everything from the bash shell to sys admin.
> Click now! http://ads.osdn.com/?ad_id=3D1278&alloc_id=3D3371&op=3Dclick
> _______________________________________________
> Babeldoc-devel mailing list
> Bab...@li...
> https://lists.sourceforge.net/lists/listinfo/babeldoc-devel

Re: [Babeldoc-devel] Re: PipelineDocument.toString()

[Dejan K. <dej...@nb...>]

I would suggest using some shorter name. Something like getContents() as
Mitch Christensen proposed. Note that this method will mostly be used in
pipeline configurations and I would prefer using:

blah.blah=${document.contents}

then

blah.blah=${document.documentAsString}



Dejan

>OK, done and committed to both branches. The new method name is

>getDocumentAsString().

Re: [Babeldoc-devel] Re: PipelineDocument.toString()

[Michael A. <mic...@ze...>]

Fine, I'll make the change.

On Mon, 2003-12-29 at 08:13, Dejan Krsmanovic wrote:
> I would suggest using some shorter name. Something like getContents() as
> Mitch Christensen proposed. Note that this method will mostly be used in
> pipeline configurations and I would prefer using:
>=20
> blah.blah=3D${document.contents}
>=20
> then
>=20
> blah.blah=3D${document.documentAsString}
>=20
>=20
>=20
> Dejan
>=20
> >OK, done and committed to both branches. The new method name is
>=20
> >getDocumentAsString().
>=20
>=20
>=20
>=20
>=20
>=20
> -------------------------------------------------------
> This SF.net email is sponsored by: IBM Linux Tutorials.
> Become an expert in LINUX or just sharpen your skills.  Sign up for IBM's
> Free Linux Tutorials.  Learn everything from the bash shell to sys admin.
> Click now! http://ads.osdn.com/?ad_id=3D1278&alloc_id=3D3371&op=3Dclick
> _______________________________________________
> Babeldoc-devel mailing list
> Bab...@li...
> https://lists.sourceforge.net/lists/listinfo/babeldoc-devel

Re: [Babeldoc-devel] Re: PipelineDocument.toString()

[Bruce M. <br...@mc...>]

Dejan,

Haha - too late for the 1.2.1 - I did that on December 26!!!  Get those fixes 
in for 1.2.2.

I think that Mike is going to implement the changes in 1.3 - can you do it in 
1.2 also?  That would be great.

regards,
Bruce.

On Sunday 28 December 2003 03:38 pm, Dejan Krsmanovic wrote:
> The only problem I see here is that toString was used
> in previous versions for getting document as String.
> There are examples  in documentation where toString is
> used this way. I wrote many pipelines which use
> toString method for accessing content, too.
> On the other hand I agree with Bruce and Mike that
> toString() should return full state of object as
> String - not just content. Note that currently (in 1.2
> release) there is no way to access content of document
> as String so whatever option we choose - it should be
> implemented in 1.2 release too, not just 1.3 (1.4
> stable).
>
> Dejan
> P.S.
> I fixes few bugs in Scanner module but I have updated
> only HEAD branch. I will update 1.2 branch too, and we
> can start thinking about 1.2.1 bugfix release.
>
> --- Bruce McDonald <br...@mc...> wrote:
> > Mike,
> >
> > Good to see you back.
> >
> > I completely agree with you here.  Your name looks
> > perfect.
> >
> > regards,
> > Bruce.
> >
> > On Saturday 27 December 2003 01:20 pm, Michael
> >
> > Ansley wrote:
> > > Hi, Bruce,
> > >
> > > I noticed the discussion on the users list
> >
> > regarding the
> >
> > > PipelineDocument.toString() method.  In the
> >
> > absence of other
> >
> > > suggestions, I'd like to suggest that:
> > >
> > > a) toString() stay as it is, because I think that
> >
> > any toString() method
> >
> > > should completely describe the object it's called
> >
> > on,
> >
> > > b) we create a new method, say documentToString()
> >
> > or
> >
> > > getDocumentAsString(), which contains the original
> >
> > toString()
> >
> > > functionality.
> > >
> > > I'm disinclined to think of this as a bug, and as
> >
> > such, I don't see any
> >
> > > reason for 1.2 to revert to the old behaviour,
> >
> > although others may
> >
> > > disagree.  However, I would prefer to see 1.3
> >
> > follow the suggestion
> >
> > > outlined above.
> > >
> > > Thoughts...
> > >
> > > Any objections to me creating the new method in
> >
> > 1.3?  Preference for a
> >
> > > name?
> > >
> > >
> > > MikeA
>
> -------------------------------------------------------
>
> > This SF.net email is sponsored by: IBM Linux
> > Tutorials.
> > Become an expert in LINUX or just sharpen your
> > skills.  Sign up for IBM's
> > Free Linux Tutorials.  Learn everything from the
> > bash shell to sys admin.
> > Click now!
>
> http://ads.osdn.com/?ad_id=1278&alloc_id=3371&op=click
>
> > _______________________________________________
> > Babeldoc-devel mailing list
> > Bab...@li...
>
> https://lists.sourceforge.net/lists/listinfo/babeldoc-devel
>
>
> __________________________________
> Do you Yahoo!?
> New Yahoo! Photos - easier uploading and sharing.
> http://photos.yahoo.com/
>
>
> -------------------------------------------------------
> This SF.net email is sponsored by: IBM Linux Tutorials.
> Become an expert in LINUX or just sharpen your skills.  Sign up for IBM's
> Free Linux Tutorials.  Learn everything from the bash shell to sys admin.
> Click now! http://ads.osdn.com/?ad_id=1278&alloc_id=3371&op=click
> _______________________________________________
> Babeldoc-devel mailing list
> Bab...@li...
> https://lists.sourceforge.net/lists/listinfo/babeldoc-devel

Re: [Babeldoc-devel] Re: PipelineDocument.toString()

[Bruce M. <br...@mc...>]

Dejan:
I kinda liked getDocumentAsString but its not a big deal.

All:

What do you think of the observer pattern classes I emailed to the list some 
time back for the configuration classes? 

regards,
Bruce.

On Monday 29 December 2003 03:13 am, Dejan Krsmanovic wrote:
> I would suggest using some shorter name. Something like getContents() as
> Mitch Christensen proposed. Note that this method will mostly be used in
> pipeline configurations and I would prefer using:
>
> blah.blah=${document.contents}
>
> then
>
> blah.blah=${document.documentAsString}
>
>
>
> Dejan
>
> >OK, done and committed to both branches. The new method name is
> >
> >getDocumentAsString().
>
> -------------------------------------------------------
> This SF.net email is sponsored by: IBM Linux Tutorials.
> Become an expert in LINUX or just sharpen your skills.  Sign up for IBM's
> Free Linux Tutorials.  Learn everything from the bash shell to sys admin.
> Click now! http://ads.osdn.com/?ad_id=1278&alloc_id=3371&op=click
> _______________________________________________
> Babeldoc-devel mailing list
> Bab...@li...
> https://lists.sourceforge.net/lists/listinfo/babeldoc-devel

Re: [Babeldoc-devel] Re: PipelineDocument.toString()

[Dejan K. <dej...@nb...>]

IMO, document is consisted of contents and attributes. So I think that
method name getContents or maybe getContentsAsString (since content can be
binary) is better. But as you said - it is not a big deal. I'll need to
change some of my pipelines anyway since I've used toString() there!

Dejan

----- Original Message ----- 
From: "Bruce McDonald" <br...@mc...>
To: "Dejan Krsmanovic" <dej...@nb...>; "Babeldoc Developer List"
<bab...@li...>
Sent: Monday, December 29, 2003 2:08 PM
Subject: Re: [Babeldoc-devel] Re: PipelineDocument.toString()


> Dejan:
> I kinda liked getDocumentAsString but its not a big deal.
>
> All:
>
> What do you think of the observer pattern classes I emailed to the list
some
> time back for the configuration classes?
>
> regards,
> Bruce.
>
> On Monday 29 December 2003 03:13 am, Dejan Krsmanovic wrote:
> > I would suggest using some shorter name. Something like getContents() as
> > Mitch Christensen proposed. Note that this method will mostly be used in
> > pipeline configurations and I would prefer using:
> >
> > blah.blah=${document.contents}
> >
> > then
> >
> > blah.blah=${document.documentAsString}
> >
> >
> >
> > Dejan
> >
> > >OK, done and committed to both branches. The new method name is
> > >
> > >getDocumentAsString().
> >
> > -------------------------------------------------------
> > This SF.net email is sponsored by: IBM Linux Tutorials.
> > Become an expert in LINUX or just sharpen your skills.  Sign up for
IBM's
> > Free Linux Tutorials.  Learn everything from the bash shell to sys
admin.
> > Click now! http://ads.osdn.com/?ad_id=1278&alloc_id=3371&op=click
> > _______________________________________________
> > Babeldoc-devel mailing list
> > Bab...@li...
> > https://lists.sourceforge.net/lists/listinfo/babeldoc-devel

[Babeldoc-devel] Observer pattern

[Dejan K. <dej...@nb...>]

Unfortunately, I was pretty bussy when you sent that mail, so I haven't time
to examine the code. I even don't have that mail here....
Anyway, I haven't problems with issues you have tried to solve with that
code so I guess I cannot help you a lot.

Dejan

> All:
>
> What do you think of the observer pattern classes I emailed to the list
some
> time back for the configuration classes?
>

Re: [Babeldoc-devel] Re: PipelineDocument.toString()

[Michael A. <mic...@ze...>]

Hi, Bruce,

I haven't yet put it into my working set.  I'll probably get a chance as
soon as I'm back from Cape Town.  In fact, I'm going to have to do it
then, because I need it soon after that.

Cheers...


MikeA



On Mon, 2003-12-29 at 13:08, Bruce McDonald wrote:
> Dejan:
> I kinda liked getDocumentAsString but its not a big deal.
>=20
> All:
>=20
> What do you think of the observer pattern classes I emailed to the list s=
ome=20
> time back for the configuration classes?=20
>=20
> regards,
> Bruce.
>=20
> On Monday 29 December 2003 03:13 am, Dejan Krsmanovic wrote:
> > I would suggest using some shorter name. Something like getContents() a=
s
> > Mitch Christensen proposed. Note that this method will mostly be used i=
n
> > pipeline configurations and I would prefer using:
> >
> > blah.blah=3D${document.contents}
> >
> > then
> >
> > blah.blah=3D${document.documentAsString}
> >
> >
> >
> > Dejan
> >
> > >OK, done and committed to both branches. The new method name is
> > >
> > >getDocumentAsString().
> >
> > -------------------------------------------------------
> > This SF.net email is sponsored by: IBM Linux Tutorials.
> > Become an expert in LINUX or just sharpen your skills.  Sign up for IBM=
's
> > Free Linux Tutorials.  Learn everything from the bash shell to sys admi=
n.
> > Click now! http://ads.osdn.com/?ad_id=3D1278&alloc_id=3D3371&op=3Dclick
> > _______________________________________________
> > Babeldoc-devel mailing list
> > Bab...@li...
> > https://lists.sourceforge.net/lists/listinfo/babeldoc-devel
>=20
>=20
> -------------------------------------------------------
> This SF.net email is sponsored by: IBM Linux Tutorials.
> Become an expert in LINUX or just sharpen your skills.  Sign up for IBM's
> Free Linux Tutorials.  Learn everything from the bash shell to sys admin.
> Click now! http://ads.osdn.com/?ad_id=3D1278&alloc_id=3D3371&op=3Dclick
> _______________________________________________
> Babeldoc-devel mailing list
> Bab...@li...
> https://lists.sourceforge.net/lists/listinfo/babeldoc-devel