Author: nick
Date: Tue Jul 2 15:11:35 2013
New Revision: 1498968
URL: http://svn.apache.org/r1498968
Log:
Patch from Tim Allison from TIKA-1130 - Extract from .docx SDT runs as well
Modified:
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/XWPFWordExtractorDecorator.java
tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java
Modified:
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/XWPFWordExtractorDecorator.java
URL:
http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/XWPFWordExtractorDecorator.java?rev=1498968&r1=1498967&r2=1498968&view=diff
==============================================================================
---
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/XWPFWordExtractorDecorator.java
(original)
+++
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/XWPFWordExtractorDecorator.java
Tue Jul 2 15:11:35 2013
@@ -28,6 +28,7 @@ import org.apache.poi.xwpf.model.XWPFHea
import org.apache.poi.xwpf.usermodel.BodyType;
import org.apache.poi.xwpf.usermodel.IBody;
import org.apache.poi.xwpf.usermodel.IBodyElement;
+import org.apache.poi.xwpf.usermodel.IRunElement;
import org.apache.poi.xwpf.usermodel.XWPFDocument;
import org.apache.poi.xwpf.usermodel.XWPFHeaderFooter;
import org.apache.poi.xwpf.usermodel.XWPFHyperlink;
@@ -36,6 +37,8 @@ import org.apache.poi.xwpf.usermodel.XWP
import org.apache.poi.xwpf.usermodel.XWPFPicture;
import org.apache.poi.xwpf.usermodel.XWPFPictureData;
import org.apache.poi.xwpf.usermodel.XWPFRun;
+import org.apache.poi.xwpf.usermodel.XWPFSDT;
+import org.apache.poi.xwpf.usermodel.XWPFSDTContent;
import org.apache.poi.xwpf.usermodel.XWPFStyle;
import org.apache.poi.xwpf.usermodel.XWPFStyles;
import org.apache.poi.xwpf.usermodel.XWPFTable;
@@ -99,9 +102,22 @@ public class XWPFWordExtractorDecorator
XWPFTable table = (XWPFTable)element;
extractTable(table, xhtml);
}
+ if (element instanceof XWPFSDT){
+ extractSDT((XWPFSDT) element, xhtml);
+ }
+
}
}
+ private void extractSDT(XWPFSDT element, XHTMLContentHandler xhtml) throws
SAXException,
+ XmlException, IOException {
+ XWPFSDTContent content = element.getContent();
+ String tag = "p";
+ xhtml.startElement(tag);
+ xhtml.characters(content.getText());
+ xhtml.endElement(tag);
+ }
+
private void extractParagraph(XWPFParagraph paragraph, XHTMLContentHandler
xhtml)
throws SAXException, XmlException, IOException {
// If this paragraph is actually a whole new section, then
@@ -183,79 +199,23 @@ public class XWPFWordExtractorDecorator
xhtml.endElement("a");
}
- // True if we are currently in the named style tag:
- boolean curBold = false;
- boolean curItalic = false;
-
- // Do the text
- for(XWPFRun run : paragraph.getRuns()) {
- if (run.isBold() != curBold) {
- if (curItalic) {
- xhtml.endElement("i");
- curItalic = false;
- }
- if (run.isBold()) {
- xhtml.startElement("b");
- } else {
- xhtml.endElement("b");
- }
- curBold = run.isBold();
- }
-
- if (run.isItalic() != curItalic) {
- if (run.isItalic()) {
- xhtml.startElement("i");
- } else {
- xhtml.endElement("i");
- }
- curItalic = run.isItalic();
- }
-
- boolean addedHREF = false;
- if(run instanceof XWPFHyperlinkRun) {
- XWPFHyperlinkRun linkRun = (XWPFHyperlinkRun)run;
- XWPFHyperlink link = linkRun.getHyperlink(document);
- if(link != null && link.getURL() != null) {
- xhtml.startElement("a", "href", link.getURL());
- addedHREF = true;
- } else if(linkRun.getAnchor() != null &&
linkRun.getAnchor().length() > 0) {
- xhtml.startElement("a", "href", "#" + linkRun.getAnchor());
- addedHREF = true;
- }
- }
-
- xhtml.characters(run.toString());
-
- // If we have any pictures, output them
- for(XWPFPicture picture : run.getEmbeddedPictures()) {
- if(paragraph.getDocument() != null) {
- XWPFPictureData data = picture.getPictureData();
- if(data != null) {
- AttributesImpl attr = new AttributesImpl();
-
- attr.addAttribute("", "src", "src", "CDATA", "embedded:" +
data.getFileName());
- attr.addAttribute("", "alt", "alt", "CDATA",
picture.getDescription());
-
- xhtml.startElement("img", attr);
- xhtml.endElement("img");
- }
- }
- }
-
- if (addedHREF) {
- xhtml.endElement("a");
+ TmpFormatting fmtg = new TmpFormatting(false, false);
+
+ // Do the iruns
+ for(IRunElement run : paragraph.getIRuns()) {
+ if (run instanceof XWPFSDT){
+ fmtg = closeStyleTags(xhtml, fmtg);
+ processSDTRun((XWPFSDT)run, xhtml);
+ //for now, we're ignoring formatting in sdt
+ //if you hit an sdt reset to false
+ fmtg.setBold(false);
+ fmtg.setItalic(false);
+ } else {
+ fmtg = processRun((XWPFRun)run, paragraph, xhtml, fmtg);
}
}
+ closeStyleTags(xhtml, fmtg);
- // Close any still open style tags
- if (curItalic) {
- xhtml.endElement("i");
- curItalic = false;
- }
- if (curBold) {
- xhtml.endElement("b");
- curBold = false;
- }
// Now do any comments for the paragraph
XWPFCommentsDecorator comments = new XWPFCommentsDecorator(paragraph,
null);
@@ -282,6 +242,89 @@ public class XWPFWordExtractorDecorator
}
}
+ private TmpFormatting closeStyleTags(XHTMLContentHandler xhtml,
+ TmpFormatting fmtg) throws SAXException {
+ // Close any still open style tags
+ if (fmtg.isItalic()) {
+ xhtml.endElement("i");
+ fmtg.setItalic(false);
+ }
+ if (fmtg.isBold()) {
+ xhtml.endElement("b");
+ fmtg.setBold(false);
+ }
+ return fmtg;
+ }
+
+ private TmpFormatting processRun(XWPFRun run, XWPFParagraph paragraph,
+ XHTMLContentHandler xhtml, TmpFormatting tfmtg)
+ throws SAXException, XmlException, IOException{
+ // True if we are currently in the named style tag:
+ if (run.isBold() != tfmtg.isBold()) {
+ if (tfmtg.isItalic()) {
+ xhtml.endElement("i");
+ tfmtg.setItalic(false);
+ }
+ if (run.isBold()) {
+ xhtml.startElement("b");
+ } else {
+ xhtml.endElement("b");
+ }
+ tfmtg.setBold(run.isBold());
+ }
+
+ if (run.isItalic() != tfmtg.isItalic()) {
+ if (run.isItalic()) {
+ xhtml.startElement("i");
+ } else {
+ xhtml.endElement("i");
+ }
+ tfmtg.setItalic(run.isItalic());
+ }
+
+ boolean addedHREF = false;
+ if(run instanceof XWPFHyperlinkRun) {
+ XWPFHyperlinkRun linkRun = (XWPFHyperlinkRun)run;
+ XWPFHyperlink link = linkRun.getHyperlink(document);
+ if(link != null && link.getURL() != null) {
+ xhtml.startElement("a", "href", link.getURL());
+ addedHREF = true;
+ } else if(linkRun.getAnchor() != null &&
linkRun.getAnchor().length() > 0) {
+ xhtml.startElement("a", "href", "#" + linkRun.getAnchor());
+ addedHREF = true;
+ }
+ }
+
+ xhtml.characters(run.toString());
+
+ // If we have any pictures, output them
+ for(XWPFPicture picture : run.getEmbeddedPictures()) {
+ if(paragraph.getDocument() != null) {
+ XWPFPictureData data = picture.getPictureData();
+ if(data != null) {
+ AttributesImpl attr = new AttributesImpl();
+
+ attr.addAttribute("", "src", "src", "CDATA", "embedded:" +
data.getFileName());
+ attr.addAttribute("", "alt", "alt", "CDATA",
picture.getDescription());
+
+ xhtml.startElement("img", attr);
+ xhtml.endElement("img");
+ }
+ }
+ }
+
+ if (addedHREF) {
+ xhtml.endElement("a");
+ }
+
+ return tfmtg;
+ }
+
+ private void processSDTRun(XWPFSDT run, XHTMLContentHandler xhtml)
+ throws SAXException, XmlException, IOException{
+ xhtml.characters(run.getContent().getText());
+ }
+
private void extractTable(XWPFTable table, XHTMLContentHandler xhtml)
throws SAXException, XmlException, IOException {
xhtml.startElement("table");
@@ -333,12 +376,15 @@ public class XWPFWordExtractorDecorator
}
private void extractHeaderText(XHTMLContentHandler xhtml, XWPFHeaderFooter
header) throws SAXException, XmlException, IOException {
- for(XWPFParagraph p : header.getParagraphs()) {
- extractParagraph(p, xhtml);
- }
- for(XWPFTable table : header.getTables()) {
- extractTable(table, xhtml);
+ for (IBodyElement e : header.getBodyElements()){
+ if (e instanceof XWPFParagraph){
+ extractParagraph((XWPFParagraph)e, xhtml);
+ } else if (e instanceof XWPFTable){
+ extractTable((XWPFTable)e, xhtml);
+ } else if (e instanceof XWPFSDT){
+ extractSDT((XWPFSDT)e, xhtml);
+ }
}
}
@@ -352,4 +398,27 @@ public class XWPFWordExtractorDecorator
parts.add( document.getPackagePart() );
return parts;
}
+
+ private class TmpFormatting{
+ private boolean bold = false;
+ private boolean italic = false;
+ private TmpFormatting(boolean bold, boolean italic){
+ this.bold = bold;
+ this.italic = italic;
+ }
+ public boolean isBold() {
+ return bold;
+ }
+ public void setBold(boolean bold) {
+ this.bold = bold;
+ }
+ public boolean isItalic() {
+ return italic;
+ }
+ public void setItalic(boolean italic) {
+ this.italic = italic;
+ }
+
+ }
+
}
Modified:
tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java
URL:
http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java?rev=1498968&r1=1498967&r2=1498968&view=diff
==============================================================================
---
tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java
(original)
+++
tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java
Tue Jul 2 15:11:35 2013
@@ -970,10 +970,8 @@ public class OOXMLParserTest extends Tik
/**
* Test for missing text described in
* <a href="https://issues.apache.org/jira/browse/TIKA-1130";>TIKA-1130</a>.
- *
- * @throws Exception
*/
- public void disabledTestMissingText() throws Exception { // TODO: Enable
test once POI has been updated.
+ public void testMissingText() throws Exception {
Metadata metadata = new Metadata();
ContentHandler handler = new BodyContentHandler();
ParseContext context = new ParseContext();
@@ -990,4 +988,4 @@ public class OOXMLParserTest extends Tik
input.close();
}
}
- }
+}
