pashko/apache-poi
1
0
Fork 0
mirror of https://github.com/apache/poi.git synced 2026-02-27 20:40:08 +08:00
Code Issues Packages Projects Releases Wiki Activity

tag r1807428 as 3.17

Browse Source 
git-svn-id: https://svn.apache.org/repos/asf/poi/tags/REL_3_17_FINAL@1807429 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Andreas Beeker 2017-09-05 22:49:42 +00:00
commit c48f56c928
10 changed files with 239 additions and 98 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
src/java/org/apache/poi/ss/formula/FormulaParser.java
View File

@ -736,7 +736,7 @@ public final class FormulaParser {
// Done reading from input stream
// Ok to return now
if (isTotalsSpec && !tbl.isHasTotalsRow()) {
if (isTotalsSpec && tbl.getTotalsRowCount() == 0) {
return new ParseNode(ErrPtg.REF_INVALID);
}
if ((isThisRow || isThisRowSpec) && (_rowIndex < startRow || endRow < _rowIndex)) {
@ -759,14 +759,14 @@ public final class FormulaParser {
if (nSpecQuantifiers == 1 && isAllSpec) {
//do nothing
} else if (isDataSpec && isHeadersSpec) {
if (tbl.isHasTotalsRow()) {
if (tbl.getTotalsRowCount() > 0) {
actualEndRow = endRow - 1;
}
} else if (isDataSpec && isTotalsSpec) {
actualStartRow = startRow + 1;
} else if (nSpecQuantifiers == 1 && isDataSpec) {
actualStartRow = startRow + 1;
if (tbl.isHasTotalsRow()) {
if (tbl.getTotalsRowCount() > 0) {
actualEndRow = endRow - 1;
}
} else if (nSpecQuantifiers == 1 && isHeadersSpec) {
@ -785,7 +785,7 @@ public final class FormulaParser {
actualEndRow = _rowIndex;
} else { // Really no special quantifiers
actualStartRow++;
if (tbl.isHasTotalsRow()) actualEndRow--;
if (tbl.getTotalsRowCount() > 0) actualEndRow--;
}
}

35
src/ooxml/java/org/apache/poi/POIXMLTypeLoader.java
View File

@ -33,6 +33,7 @@ import javax.xml.stream.XMLStreamReader;
import org.apache.poi.openxml4j.opc.PackageNamespaces;
import org.apache.poi.util.DocumentHelper;
import org.apache.poi.util.Removal;
import org.apache.xmlbeans.SchemaType;
import org.apache.xmlbeans.SchemaTypeLoader;
import org.apache.xmlbeans.XmlBeans;
@ -49,7 +50,7 @@ import org.xml.sax.SAXException;
@SuppressWarnings("deprecation")
public class POIXMLTypeLoader {
private static ThreadLocal<ClassLoader> classLoader = new ThreadLocal<ClassLoader>();
private static ThreadLocal<SchemaTypeLoader> typeLoader = new ThreadLocal<SchemaTypeLoader>();
// TODO: Do these have a good home like o.a.p.openxml4j.opc.PackageNamespaces and PackageRelationshipTypes?
// These constants should be common to all of POI and easy to use by other applications such as Tika
@ -109,20 +110,26 @@ public class POIXMLTypeLoader {
* when the user code is finalized.
*
* @param cl the classloader to be used when XmlBeans classes and definitions are looked up
* @deprecated in POI 3.17 - setting a classloader from the outside is now obsolete,
* the classloader of the SchemaType will be used
*/
@Deprecated
@Removal(version="4.0")
public static void setClassLoader(ClassLoader cl) {
classLoader.set(cl);
}
private static SchemaTypeLoader getTypeLoader() {
ClassLoader cl = classLoader.get();
return (cl == null)
? XmlBeans.getContextTypeLoader()
: XmlBeans.typeLoaderForClassLoader(cl);
private static SchemaTypeLoader getTypeLoader(SchemaType type) {
SchemaTypeLoader tl = typeLoader.get();
if (tl == null) {
ClassLoader cl = type.getClass().getClassLoader();
tl = XmlBeans.typeLoaderForClassLoader(cl);
typeLoader.set(tl);
}
return tl;
}
public static XmlObject newInstance(SchemaType type, XmlOptions options) {
return getTypeLoader().newInstance(type, getXmlOptions(options));
return getTypeLoader(type).newInstance(type, getXmlOptions(options));
}
public static XmlObject parse(String xmlText, SchemaType type, XmlOptions options) throws XmlException {
@ -154,34 +161,34 @@ public class POIXMLTypeLoader {
public static XmlObject parse(InputStream jiois, SchemaType type, XmlOptions options) throws XmlException, IOException {
try {
Document doc = DocumentHelper.readDocument(jiois);
return getTypeLoader().parse(doc.getDocumentElement(), type, getXmlOptions(options));
return getTypeLoader(type).parse(doc.getDocumentElement(), type, getXmlOptions(options));
} catch (SAXException e) {
throw new IOException("Unable to parse xml bean", e);
}
}
public static XmlObject parse(XMLStreamReader xsr, SchemaType type, XmlOptions options) throws XmlException {
return getTypeLoader().parse(xsr, type, getXmlOptions(options));
return getTypeLoader(type).parse(xsr, type, getXmlOptions(options));
}
public static XmlObject parse(Reader jior, SchemaType type, XmlOptions options) throws XmlException, IOException {
try {
Document doc = DocumentHelper.readDocument(new InputSource(jior));
return getTypeLoader().parse(doc.getDocumentElement(), type, getXmlOptions(options));
return getTypeLoader(type).parse(doc.getDocumentElement(), type, getXmlOptions(options));
} catch (SAXException e) {
throw new XmlException("Unable to parse xml bean", e);
}
}
public static XmlObject parse(Node node, SchemaType type, XmlOptions options) throws XmlException {
return getTypeLoader().parse(node, type, getXmlOptions(options));
return getTypeLoader(type).parse(node, type, getXmlOptions(options));
}
public static XmlObject parse(XMLInputStream xis, SchemaType type, XmlOptions options) throws XmlException, XMLStreamException {
return getTypeLoader().parse(xis, type, getXmlOptions(options));
return getTypeLoader(type).parse(xis, type, getXmlOptions(options));
}
public static XMLInputStream newValidatingXMLInputStream ( XMLInputStream xis, SchemaType type, XmlOptions options ) throws XmlException, XMLStreamException {
return getTypeLoader().newValidatingXMLInputStream(xis, type, getXmlOptions(options));
return getTypeLoader(type).newValidatingXMLInputStream(xis, type, getXmlOptions(options));
}
}

16
src/ooxml/java/org/apache/poi/xwpf/extractor/XWPFWordExtractor.java
View File

@ -33,6 +33,7 @@ import org.apache.poi.xwpf.usermodel.XWPFHyperlink;
import org.apache.poi.xwpf.usermodel.XWPFHyperlinkRun;
import org.apache.poi.xwpf.usermodel.XWPFParagraph;
import org.apache.poi.xwpf.usermodel.XWPFRelation;
import org.apache.poi.xwpf.usermodel.XWPFRun;
import org.apache.poi.xwpf.usermodel.XWPFSDT;
import org.apache.poi.xwpf.usermodel.XWPFSDTCell;
import org.apache.poi.xwpf.usermodel.XWPFTable;
@ -53,6 +54,7 @@ public class XWPFWordExtractor extends POIXMLTextExtractor {
private XWPFDocument document;
private boolean fetchHyperlinks = false;
private boolean concatenatePhoneticRuns = true;
public XWPFWordExtractor(OPCPackage container) throws XmlException, OpenXML4JException, IOException {
this(new XWPFDocument(container));
@ -86,6 +88,14 @@ public class XWPFWordExtractor extends POIXMLTextExtractor {
fetchHyperlinks = fetch;
}
/**
* Should we concatenate phonetic runs in extraction. Default is <code>true</code>
* @param concatenatePhoneticRuns
*/
public void setConcatenatePhoneticRuns(boolean concatenatePhoneticRuns) {
this.concatenatePhoneticRuns = concatenatePhoneticRuns;
}
public String getText() {
StringBuffer text = new StringBuffer();
XWPFHeaderFooterPolicy hfPolicy = document.getHeaderFooterPolicy();
@ -130,7 +140,11 @@ public class XWPFWordExtractor extends POIXMLTextExtractor {
for (IRunElement run : paragraph.getRuns()) {
text.append(run);
if (! concatenatePhoneticRuns && run instanceof XWPFRun) {
text.append(((XWPFRun)run).text());
} else {
text.append(run);
}
if (run instanceof XWPFHyperlinkRun && fetchHyperlinks) {
XWPFHyperlink link = ((XWPFHyperlinkRun) run).getHyperlink(document);
if (link != null)

174
src/ooxml/java/org/apache/poi/xwpf/usermodel/XWPFRun.java
View File

@ -68,6 +68,8 @@ 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.CTRuby;
import org.openxmlformats.schemas.wordprocessingml.x2006.main.CTRubyContent;
import org.openxmlformats.schemas.wordprocessingml.x2006.main.CTSignedHpsMeasure;
import org.openxmlformats.schemas.wordprocessingml.x2006.main.CTSignedTwipsMeasure;
import org.openxmlformats.schemas.wordprocessingml.x2006.main.CTText;
@ -1042,10 +1044,15 @@ public class XWPFRun implements ISDTContents, IRunElement, CharacterRun {
}
/**
* Returns the string version of the text
* Returns the string version of the text and the phonetic string
*/
public String toString() {
return text();
String phonetic = getPhonetic();
if (phonetic.length() > 0) {
return text() +" ("+phonetic.toString()+")";
} else {
return text();
}
}
/**
@ -1061,71 +1068,136 @@ public class XWPFRun implements ISDTContents, IRunElement, CharacterRun {
c.selectPath("./*");
while (c.toNextSelection()) {
XmlObject o = c.getObject();
if (o instanceof CTText) {
if (o instanceof CTRuby) {
handleRuby(o, text, false);
continue;
}
_getText(o, text);
}
c.dispose();
return text.toString();
}
/**
*
* @return the phonetic (ruby) string associated with this run or an empty String if none exists
*/
public String getPhonetic() {
StringBuffer text = new StringBuffer();
// Grab the text and tabs of the text run
// Do so in a way that preserves the ordering
XmlCursor c = run.newCursor();
c.selectPath("./*");
while (c.toNextSelection()) {
XmlObject o = c.getObject();
if (o instanceof CTRuby) {
handleRuby(o, text, true);
}
}
// Any picture text?
if (pictureText != null && pictureText.length() > 0) {
text.append("\n").append(pictureText).append("\n");
}
c.dispose();
return text.toString();
}
/**
*
* @param rubyObj rubyobject
* @param text buffer to which to append the content
* @param extractPhonetic extract the phonetic (rt) component or the base component
*/
private void handleRuby(XmlObject rubyObj, StringBuffer text, boolean extractPhonetic) {
XmlCursor c = rubyObj.newCursor();
//according to the spec, a ruby object
//has the phonetic (rt) first, then the actual text (base)
//second.
c.selectPath(".//*");
boolean inRT = false;
boolean inBase = false;
while (c.toNextSelection()) {
XmlObject o = c.getObject();
if (o instanceof CTRubyContent) {
String tagName = o.getDomNode().getNodeName();
// Field Codes (w:instrText, defined in spec sec. 17.16.23)
// come up as instances of CTText, but we don't want them
// in the normal text output
if (!"w:instrText".equals(tagName)) {
text.append(((CTText) o).getStringValue());
if ("w:rt".equals(tagName)) {
inRT = true;
} else if ("w:rubyBase".equals(tagName)) {
inRT = false;
inBase = true;
}
} else {
if (extractPhonetic && inRT) {
_getText(o, text);
} else if (! extractPhonetic && inBase) {
_getText(o, text);
}
}
}
c.dispose();
}
// 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() != null && checkBox.getDefault().getVal() == STOnOff.X_1) {
text.append("|X|");
} else {
text.append("|_|");
}
private void _getText(XmlObject o, StringBuffer text) {
if (o instanceof CTText) {
String tagName = o.getDomNode().getNodeName();
// Field Codes (w:instrText, defined in spec sec. 17.16.23)
// come up as instances of CTText, but we don't want them
// in the normal text output
if (!"w:instrText".equals(tagName)) {
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() != null && checkBox.getDefault().getVal() == STOnOff.X_1) {
text.append("|X|");
} else {
text.append("|_|");
}
}
}
}
}
if (o instanceof CTPTab) {
if (o instanceof CTPTab) {
text.append("\t");
}
if (o instanceof CTBr) {
text.append("\n");
}
if (o instanceof CTEmpty) {
// Some inline text elements get returned not as
// themselves, but as CTEmpty, owing to some odd
// definitions around line 5642 of the XSDs
// This bit works around it, and replicates the above
// rules for that case
String tagName = o.getDomNode().getNodeName();
if ("w:tab".equals(tagName) || "tab".equals(tagName)) {
text.append("\t");
}
if (o instanceof CTBr) {
if ("w:br".equals(tagName) || "br".equals(tagName)) {
text.append("\n");
}
if (o instanceof CTEmpty) {
// Some inline text elements get returned not as
// themselves, but as CTEmpty, owing to some odd
// definitions around line 5642 of the XSDs
// This bit works around it, and replicates the above
// rules for that case
String tagName = o.getDomNode().getNodeName();
if ("w:tab".equals(tagName) || "tab".equals(tagName)) {
text.append("\t");
}
if ("w:br".equals(tagName) || "br".equals(tagName)) {
text.append("\n");
}
if ("w:cr".equals(tagName) || "cr".equals(tagName)) {
text.append("\n");
}
}
if (o instanceof CTFtnEdnRef) {
CTFtnEdnRef ftn = (CTFtnEdnRef) o;
String footnoteRef = ftn.getDomNode().getLocalName().equals("footnoteReference") ?
"[footnoteRef:" + ftn.getId().intValue() + "]" : "[endnoteRef:" + ftn.getId().intValue() + "]";
text.append(footnoteRef);
if ("w:cr".equals(tagName) || "cr".equals(tagName)) {
text.append("\n");
}
}
c.dispose();
// Any picture text?
if (pictureText != null && pictureText.length() > 0) {
text.append("\n").append(pictureText);
if (o instanceof CTFtnEdnRef) {
CTFtnEdnRef ftn = (CTFtnEdnRef) o;
String footnoteRef = ftn.getDomNode().getLocalName().equals("footnoteReference") ?
"[footnoteRef:" + ftn.getId().intValue() + "]" : "[endnoteRef:" + ftn.getId().intValue() + "]";
text.append(footnoteRef);
}
return text.toString();
}
/**

79
src/ooxml/testcases/org/apache/poi/TestPOIXMLDocument.java
View File

@ -28,6 +28,7 @@ import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.lang.Thread.UncaughtExceptionHandler;
import java.lang.reflect.InvocationTargetException;
import java.util.ArrayList;
import java.util.HashMap;
@ -40,6 +41,7 @@ import org.apache.poi.openxml4j.exceptions.OpenXML4JRuntimeException;
import org.apache.poi.openxml4j.opc.OPCPackage;
import org.apache.poi.openxml4j.opc.PackagePart;
import org.apache.poi.openxml4j.opc.PackageRelationshipTypes;
import org.apache.poi.util.IOUtils;
import org.apache.poi.util.NullOutputStream;
import org.apache.poi.util.PackageHelper;
import org.apache.poi.util.TempFile;
@ -321,38 +323,61 @@ public final class TestPOIXMLDocument {
}
}
@Test(expected=IllegalStateException.class)
public void testOSGIClassLoadingAsIs() throws IOException {
@Test
public void testOSGIClassLoading() {
// the schema type loader is cached per thread in POIXMLTypeLoader.
// So create a new Thread and change the context class loader (which would normally be used)
// to not contain the OOXML classes
Runnable run = new Runnable() {
public void run() {
InputStream is = POIDataSamples.getSlideShowInstance().openResourceAsStream("table_test.pptx");
XMLSlideShow ppt = null;
try {
ppt = new XMLSlideShow(is);
ppt.getSlides().get(0).getShapes();
} catch (IOException e) {
fail("failed to load XMLSlideShow");
} finally {
IOUtils.closeQuietly(ppt);
IOUtils.closeQuietly(is);
}
}
};
Thread thread = Thread.currentThread();
ClassLoader cl = thread.getContextClassLoader();
InputStream is = POIDataSamples.getSlideShowInstance().openResourceAsStream("table_test.pptx");
try {
thread.setContextClassLoader(cl.getParent());
XMLSlideShow ppt = new XMLSlideShow(is);
ppt.getSlides().get(0).getShapes();
ppt.close();
} finally {
thread.setContextClassLoader(cl);
is.close();
UncaughtHandler uh = new UncaughtHandler();
// check schema type loading and check if we could run in an OOM
Thread ta[] = new Thread[30];
for (int j=0; j<10; j++) {
for (int i=0; i<ta.length; i++) {
ta[i] = new Thread(run);
ta[i].setContextClassLoader(cl.getParent());
ta[i].setUncaughtExceptionHandler(uh);
ta[i].start();
}
for (int i=0; i<ta.length; i++) {
try {
ta[i].join();
} catch (InterruptedException e) {
fail("failed to join thread");
}
}
}
assertFalse(uh.hasException());
}
@Test
public void testOSGIClassLoadingFixed() throws IOException {
Thread thread = Thread.currentThread();
ClassLoader cl = thread.getContextClassLoader();
InputStream is = POIDataSamples.getSlideShowInstance().openResourceAsStream("table_test.pptx");
try {
thread.setContextClassLoader(cl.getParent());
POIXMLTypeLoader.setClassLoader(cl);
XMLSlideShow ppt = new XMLSlideShow(is);
ppt.getSlides().get(0).getShapes();
ppt.close();
} finally {
thread.setContextClassLoader(cl);
POIXMLTypeLoader.setClassLoader(null);
is.close();
private static class UncaughtHandler implements UncaughtExceptionHandler {
Throwable e;
public synchronized void uncaughtException(Thread t, Throwable e) {
this.e = e;
}
public synchronized boolean hasException() {
return e != null;
}
}

11
src/ooxml/testcases/org/apache/poi/xssf/usermodel/TestXSSFFormulaEvaluation.java
View File

@ -694,4 +694,15 @@ public final class TestXSSFFormulaEvaluation extends BaseTestFormulaEvaluator {
assertSame(cell, same);
wb.close();
}
@Test
public void testBug61468() {
Workbook wb = XSSFTestDataSamples.openSampleWorkbook("simple-monthly-budget.xlsx");
FormulaEvaluator evaluator = wb.getCreationHelper().createFormulaEvaluator();
Cell cell = wb.getSheetAt(0).getRow(8).getCell(4);
assertEquals(3750, cell.getNumericCellValue(), 0.001);
CellValue value = evaluator.evaluate(cell);
assertEquals(3750, value.getNumberValue(), 0.001);
}
}

2
src/ooxml/testcases/org/apache/poi/xssf/usermodel/TestXSSFTable.java
View File

@ -163,7 +163,7 @@ public final class TestXSSFTable {
public void isHasTotalsRow() throws IOException {
XSSFWorkbook wb = XSSFTestDataSamples.openSampleWorkbook("StructuredReferences.xlsx");
XSSFTable table = wb.getTable("\\_Prime.1");
assertFalse(table.isHasTotalsRow());
assertFalse(table.getTotalsRowCount() > 0);
wb.close();
}

12
src/ooxml/testcases/org/apache/poi/xwpf/extractor/TestXWPFWordExtractor.java
View File

@ -421,4 +421,16 @@ public class TestXWPFWordExtractor extends TestCase {
extractor.getText());
extractor.close();
}
public void testPhonetic() throws IOException {
XWPFDocument doc = XWPFTestDataSamples.openSampleDocument("61470.docx");
XWPFWordExtractor extractor = new XWPFWordExtractor(doc);
//expect: baseText (phoneticText)
assertEquals("\u6771\u4EAC (\u3068\u3046\u304D\u3087\u3046)", extractor.getText().trim());
extractor.close();
extractor = new XWPFWordExtractor(doc);
extractor.setConcatenatePhoneticRuns(false);
assertEquals("\u6771\u4EAC", extractor.getText().trim());
}
}

BIN
test-data/document/61470.docx Normal file
View File

Binary file not shown.

BIN
test-data/spreadsheet/simple-monthly-budget.xlsx Normal file
View File

Binary file not shown.