From: Dominik Stadler Date: Wed, 5 Nov 2014 22:26:00 +0000 (+0000) Subject: github-7 - Form check box extraction with XWPFWordExtractor X-Git-Url: https://source.dussan.org/?a=commitdiff_plain;h=5f4a2a3b44ce1f534278645c9f87bafb3d166412;p=poi.git github-7 - Form check box extraction with XWPFWordExtractor git-svn-id: https://svn.apache.org/repos/asf/poi/trunk@1636990 13f79535-47bb-0310-9956-ffa450edef68 --- diff --git a/src/ooxml/java/org/apache/poi/xwpf/usermodel/XWPFRun.java b/src/ooxml/java/org/apache/poi/xwpf/usermodel/XWPFRun.java index dc09b43d46..9234d18506 100644 --- a/src/ooxml/java/org/apache/poi/xwpf/usermodel/XWPFRun.java +++ b/src/ooxml/java/org/apache/poi/xwpf/usermodel/XWPFRun.java @@ -34,42 +34,13 @@ import org.apache.xmlbeans.XmlObject; import org.apache.xmlbeans.XmlString; import org.apache.xmlbeans.XmlToken; import org.apache.xmlbeans.impl.values.XmlAnyTypeImpl; -import org.openxmlformats.schemas.drawingml.x2006.main.CTBlip; -import org.openxmlformats.schemas.drawingml.x2006.main.CTBlipFillProperties; -import org.openxmlformats.schemas.drawingml.x2006.main.CTGraphicalObject; -import org.openxmlformats.schemas.drawingml.x2006.main.CTGraphicalObjectData; -import org.openxmlformats.schemas.drawingml.x2006.main.CTNonVisualDrawingProps; -import org.openxmlformats.schemas.drawingml.x2006.main.CTNonVisualPictureProperties; -import org.openxmlformats.schemas.drawingml.x2006.main.CTPoint2D; -import org.openxmlformats.schemas.drawingml.x2006.main.CTPositiveSize2D; -import org.openxmlformats.schemas.drawingml.x2006.main.CTPresetGeometry2D; -import org.openxmlformats.schemas.drawingml.x2006.main.CTShapeProperties; -import org.openxmlformats.schemas.drawingml.x2006.main.CTTransform2D; -import org.openxmlformats.schemas.drawingml.x2006.main.STShapeType; +import org.openxmlformats.schemas.drawingml.x2006.main.*; import org.openxmlformats.schemas.drawingml.x2006.picture.CTPicture; import org.openxmlformats.schemas.drawingml.x2006.picture.CTPictureNonVisual; import org.openxmlformats.schemas.drawingml.x2006.wordprocessingDrawing.CTAnchor; import org.openxmlformats.schemas.drawingml.x2006.wordprocessingDrawing.CTInline; -import org.openxmlformats.schemas.wordprocessingml.x2006.main.CTBr; +import org.openxmlformats.schemas.wordprocessingml.x2006.main.*; import org.openxmlformats.schemas.wordprocessingml.x2006.main.CTColor; -import org.openxmlformats.schemas.wordprocessingml.x2006.main.CTDrawing; -import org.openxmlformats.schemas.wordprocessingml.x2006.main.CTEmpty; -import org.openxmlformats.schemas.wordprocessingml.x2006.main.CTFonts; -import org.openxmlformats.schemas.wordprocessingml.x2006.main.CTFtnEdnRef; -import org.openxmlformats.schemas.wordprocessingml.x2006.main.CTHpsMeasure; -import org.openxmlformats.schemas.wordprocessingml.x2006.main.CTOnOff; -import org.openxmlformats.schemas.wordprocessingml.x2006.main.CTPTab; -import org.openxmlformats.schemas.wordprocessingml.x2006.main.CTR; -import org.openxmlformats.schemas.wordprocessingml.x2006.main.CTRPr; -import org.openxmlformats.schemas.wordprocessingml.x2006.main.CTSignedHpsMeasure; -import org.openxmlformats.schemas.wordprocessingml.x2006.main.CTText; -import org.openxmlformats.schemas.wordprocessingml.x2006.main.CTUnderline; -import org.openxmlformats.schemas.wordprocessingml.x2006.main.CTVerticalAlignRun; -import org.openxmlformats.schemas.wordprocessingml.x2006.main.STBrClear; -import org.openxmlformats.schemas.wordprocessingml.x2006.main.STBrType; -import org.openxmlformats.schemas.wordprocessingml.x2006.main.STOnOff; -import org.openxmlformats.schemas.wordprocessingml.x2006.main.STUnderline; -import org.openxmlformats.schemas.wordprocessingml.x2006.main.STVerticalAlignRun; import org.w3c.dom.NodeList; import org.w3c.dom.Text; @@ -894,6 +865,22 @@ public class XWPFRun implements ISDTContents, IRunElement{ text.append(((CTText) o).getStringValue()); } } + + // Complex type evaluation (currently only for extraction of check boxes) + if(o instanceof CTFldChar) { + CTFldChar ctfldChar = ((CTFldChar)o); + if(ctfldChar.getFldCharType() == STFldCharType.BEGIN) { + if(ctfldChar.getFfData() != null) { + for(CTFFCheckBox checkBox : ctfldChar.getFfData().getCheckBoxList()) { + if(checkBox.getDefault().getVal() == STOnOff.X_1) { + text.append("|X|"); + } else { + text.append("|_|"); + } + } + } + } + } if (o instanceof CTPTab) { text.append("\t"); diff --git a/src/ooxml/testcases/org/apache/poi/xwpf/extractor/TestXWPFWordExtractor.java b/src/ooxml/testcases/org/apache/poi/xwpf/extractor/TestXWPFWordExtractor.java index d63bd642de..00408829df 100644 --- a/src/ooxml/testcases/org/apache/poi/xwpf/extractor/TestXWPFWordExtractor.java +++ b/src/ooxml/testcases/org/apache/poi/xwpf/extractor/TestXWPFWordExtractor.java @@ -397,4 +397,17 @@ public class TestXWPFWordExtractor extends TestCase { extractor.getText(); extractor.close(); } + + public void testCheckboxes() throws IOException { + XWPFDocument doc = XWPFTestDataSamples.openSampleDocument("checkboxes.docx"); + System.out.println(doc); + XWPFWordExtractor extractor = new XWPFWordExtractor(doc); + + assertEquals("This is a small test for checkboxes \nunchecked: |_| \n" + + "Or checked: |X|\n\n\n\n\n" + + "Test a checkbox within a textbox: |_| -> |X|\n\n\n" + + "In Table:\n|_|\t|X|\n\n\n" + + "In Sequence:\n|X||_||X|\n", extractor.getText()); + extractor.close(); + } } diff --git a/test-data/document/checkboxes.docx b/test-data/document/checkboxes.docx new file mode 100644 index 0000000000..c35b71598f Binary files /dev/null and b/test-data/document/checkboxes.docx differ