Apache
/
poi
mirror of https://github.com/apache/poi.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

simplify table converting; fix bug that prevents table from AIOOB-Tap.doc to be converted 

git-svn-id: https://svn.apache.org/repos/asf/poi/trunk@1142872 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Sergey Vladimirov 2011-07-05 01:44:29 +00:00
parent 34cae0eb4e
commit c5d30dcfea
4 changed files with 20 additions and 108 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
src/scratchpad/src/org/apache/poi/hwpf/converter/AbstractWordConverter.java
View File

@ -16,9 +16,7 @@
==================================================================== */
package org.apache.poi.hwpf.converter;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
@ -32,7 +30,6 @@ import org.apache.poi.hwpf.usermodel.Picture;
import org.apache.poi.hwpf.usermodel.Range;
import org.apache.poi.hwpf.usermodel.Section;
import org.apache.poi.hwpf.usermodel.Table;
import org.apache.poi.hwpf.usermodel.TableIterator;
import org.apache.poi.util.POILogFactory;
import org.apache.poi.util.POILogger;
import org.w3c.dom.Document;
@ -233,14 +230,6 @@ public abstract class AbstractWordConverter
protected void processSectionParagraphes( HWPFDocumentCore wordDocument,
Element flow, Range range, int currentTableLevel )
{
final Map<Integer, Table> allTables = new HashMap<Integer, Table>();
for ( TableIterator tableIterator = AbstractWordUtils.newTableIterator(
range, currentTableLevel + 1 ); tableIterator.hasNext(); )
{
Table next = tableIterator.next();
allTables.put( Integer.valueOf( next.getStartOffset() ), next );
}
final ListTables listTables = wordDocument.getListTables();
int currentListInfo = 0;
@ -249,18 +238,14 @@ public abstract class AbstractWordConverter
{
Paragraph paragraph = range.getParagraph( p );
if ( allTables.containsKey( Integer.valueOf( paragraph
.getStartOffset() ) ) )
{
Table table = allTables.get( Integer.valueOf( paragraph
.getStartOffset() ) );
processTable( wordDocument, flow, table, currentTableLevel + 1 );
continue;
}
if ( paragraph.isInTable()
&& paragraph.getTableLevel() != currentTableLevel )
{
Table table = range.getTable( paragraph );
processTable( wordDocument, flow, table );
p += table.numParagraphs();
p--;
continue;
}
@ -311,7 +296,7 @@ public abstract class AbstractWordConverter
}
protected abstract void processTable( HWPFDocumentCore wordDocument,
Element flow, Table table, int newTableLevel );
Element flow, Table table );
protected int tryField( HWPFDocumentCore wordDocument, Paragraph paragraph,
int currentTableLevel, List<CharacterRun> characterRuns,

86
src/scratchpad/src/org/apache/poi/hwpf/converter/WordToFoConverter.java
View File

@ -18,9 +18,7 @@ package org.apache.poi.hwpf.converter;
import java.io.File;
import java.io.FileWriter;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
import java.util.Stack;
import javax.xml.parsers.DocumentBuilderFactory;
@ -32,17 +30,13 @@ import javax.xml.transform.stream.StreamResult;
import org.apache.poi.hwpf.HWPFDocument;
import org.apache.poi.hwpf.HWPFDocumentCore;
import org.apache.poi.hwpf.model.ListFormatOverride;
import org.apache.poi.hwpf.model.ListTables;
import org.apache.poi.hwpf.usermodel.CharacterRun;
import org.apache.poi.hwpf.usermodel.Paragraph;
import org.apache.poi.hwpf.usermodel.Picture;
import org.apache.poi.hwpf.usermodel.Range;
import org.apache.poi.hwpf.usermodel.Section;
import org.apache.poi.hwpf.usermodel.SectionProperties;
import org.apache.poi.hwpf.usermodel.Table;
import org.apache.poi.hwpf.usermodel.TableCell;
import org.apache.poi.hwpf.usermodel.TableIterator;
import org.apache.poi.hwpf.usermodel.TableRow;
import org.apache.poi.util.POILogFactory;
import org.apache.poi.util.POILogger;
@ -374,85 +368,11 @@ public class WordToFoConverter extends AbstractWordConverter
Element flow = foDocumentFacade.addFlowToPageSequence( pageSequence,
"xsl-region-body" );
processSectionParagraphes( wordDocument, flow, section, 0 );
}
protected void processSectionParagraphes( HWPFDocument wordDocument,
Element flow, Range range, int currentTableLevel )
{
final Map<Integer, Table> allTables = new HashMap<Integer, Table>();
for ( TableIterator tableIterator = WordToFoUtils.newTableIterator(
range, currentTableLevel + 1 ); tableIterator.hasNext(); )
{
Table next = tableIterator.next();
allTables.put( Integer.valueOf( next.getStartOffset() ), next );
}
final ListTables listTables = wordDocument.getListTables();
int currentListInfo = 0;
final int paragraphs = range.numParagraphs();
for ( int p = 0; p < paragraphs; p++ )
{
Paragraph paragraph = range.getParagraph( p );
if ( allTables.containsKey( Integer.valueOf( paragraph
.getStartOffset() ) ) )
{
Table table = allTables.get( Integer.valueOf( paragraph
.getStartOffset() ) );
processTable( wordDocument, flow, table, currentTableLevel + 1 );
continue;
}
if ( paragraph.isInTable()
&& paragraph.getTableLevel() != currentTableLevel )
{
continue;
}
if ( paragraph.getIlfo() != currentListInfo )
{
currentListInfo = paragraph.getIlfo();
}
if ( currentListInfo != 0 )
{
if ( listTables != null )
{
final ListFormatOverride listFormatOverride = listTables
.getOverride( paragraph.getIlfo() );
String label = WordToFoUtils.getBulletText( listTables,
paragraph, listFormatOverride.getLsid() );
processParagraph( wordDocument, flow, currentTableLevel,
paragraph, label );
}
else
{
logger.log( POILogger.WARN,
"Paragraph #" + paragraph.getStartOffset() + "-"
+ paragraph.getEndOffset()
+ " has reference to list structure #"
+ currentListInfo
+ ", but listTables not defined in file" );
processParagraph( wordDocument, flow, currentTableLevel,
paragraph, WordToFoUtils.EMPTY );
}
}
else
{
processParagraph( wordDocument, flow, currentTableLevel,
paragraph, WordToFoUtils.EMPTY );
}
}
processSectionParagraphes( wordDocument, flow, section, Integer.MIN_VALUE );
}
protected void processTable( HWPFDocumentCore wordDocument, Element flow,
Table table, int thisTableLevel )
Table table )
{
Element tableHeader = foDocumentFacade.createTableHeader();
Element tableBody = foDocumentFacade.createTableBody();
@ -532,7 +452,7 @@ public class WordToFoConverter extends AbstractWordConverter
}
processSectionParagraphes( wordDocument, tableCellElement,
tableCell, thisTableLevel );
tableCell, table.getTableLevel() );
if ( !tableCellElement.hasChildNodes() )
{

8
src/scratchpad/src/org/apache/poi/hwpf/converter/WordToHtmlConverter.java
View File

@ -326,7 +326,7 @@ public class WordToHtmlConverter extends AbstractWordConverter
div.setAttribute( "style", getSectionStyle( section ) );
htmlDocumentFacade.body.appendChild( div );
processSectionParagraphes( wordDocument, div, section, 0 );
processSectionParagraphes( wordDocument, div, section, Integer.MIN_VALUE );
}
@Override
@ -337,11 +337,11 @@ public class WordToHtmlConverter extends AbstractWordConverter
getSectionStyle( section ) );
processSectionParagraphes( wordDocument, htmlDocumentFacade.body,
section, 0 );
section, Integer.MIN_VALUE );
}
protected void processTable( HWPFDocumentCore hwpfDocument, Element flow,
Table table, int thisTableLevel )
Table table )
{
Element tableHeader = htmlDocumentFacade.createTableHeader();
Element tableBody = htmlDocumentFacade.createTableBody();
@ -429,7 +429,7 @@ public class WordToHtmlConverter extends AbstractWordConverter
}
processSectionParagraphes( hwpfDocument, tableCellElement,
tableCell, thisTableLevel );
tableCell, table.getTableLevel() );
if ( !tableCellElement.hasChildNodes() )
{

7
src/scratchpad/testcases/org/apache/poi/hwpf/converter/TestWordToHtmlConverter.java
View File

@ -77,6 +77,13 @@ public class TestWordToHtmlConverter extends TestCase
.contains( "<!--Image link to '0.emf' can be here-->" ) );
}
public void testAIOOBTap() throws Exception
{
String result = getHtmlText( "AIOOB-Tap.doc" );
assertTrue( result.substring( 0, 2000 ).contains( "<table>" ) );
}
public void testHyperlink() throws Exception
{
String result = getHtmlText( "hyperlink.doc" );