Xiaohong Yang created TIKA-4211:
-----------------------------------
Summary: Tika extractor fails to extract embedded excel from pptx
Key: TIKA-4211
URL: https://issues.apache.org/jira/browse/TIKA-4211
Project: Tika
Issue Type: Bug
Reporter: Xiaohong Yang
Attachments: config_and_sample_file.zip
We use org.apache.tika.extractor.EmbeddedDocumentExtractor to get embedded
excel from PowerPoint presentation. It works with most pptx files. But it
fails to detect the embedded excel with some pptx files.
Following is the sample code and attached is the tika-config.xml and a pptx
file that works.
We cannot provide the pptx file that does not work because it is client data.
We noticed a difference between the pptx files that work and the pptx file that
does not work:
"{*}Worksheet Object{*}" *is in the popup menu when the embedded Excel object
is right-clicked in the pptx files that work.*
"{*}Edit Data{*}" *is in the popup menu when the embedded Excel object is
right-clicked in the pptx file that does not work. This file might be created
with an old version fo PowerPoint.*
The operating system is Ubuntu 20.04. Java version is 17. Tika version is
2.9.1 and POI version is 5.2.3.
import org.apache.pdfbox.io.IOUtils;
import org.apache.poi.poifs.filesystem.DirectoryEntry;
import org.apache.poi.poifs.filesystem.DocumentEntry;
import org.apache.poi.poifs.filesystem.DocumentInputStream;
import org.apache.poi.poifs.filesystem.POIFSFileSystem;
import org.apache.tika.config.TikaConfig;
import org.apache.tika.extractor.EmbeddedDocumentExtractor;
import org.apache.tika.io.FilenameUtils;
import org.apache.tika.io.TikaInputStream;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.parser.AutoDetectParser;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.Parser;
import org.xml.sax.ContentHandler;
import org.xml.sax.SAXException;
import org.xml.sax.helpers.DefaultHandler;
import java.io.*;
import java.net.URL;
import java.nio.file.Path;
public class ExtractExcelFromPowerPoint {
private final Path pptxFile = new
File("/home/ubuntu/testdirs/testdir_pptx/sample.pptx").toPath();
private final Path outputDir = new
File("/home/ubuntu/testdirs/testdir_pptx/tika_output/").toPath();
private Parser parser;
private ParseContext context;
public static void main(String args[]) {
try {
new ExtractExcelFromPowerPoint().process();
}
catch(Exception ex) {
ex.printStackTrace();
}
}
public ExtractExcelFromPowerPoint() {
}
public void process() throws Exception {
TikaConfig config = new
TikaConfig("/home/ubuntu/testdirs/testdir_pptx/tika-config.xml");
FileEmbeddedDocumentExtractor fileEmbeddedDocumentExtractor = new
FileEmbeddedDocumentExtractor();
parser = new AutoDetectParser(config);
context = new ParseContext();
context.set(Parser.class, parser);
context.set(TikaConfig.class, config);
context.set(EmbeddedDocumentExtractor.class,
fileEmbeddedDocumentExtractor);
URL url = pptxFile.toUri().toURL();
Metadata metadata = new Metadata();
try (InputStream input = TikaInputStream.get(url, metadata)) {
ContentHandler handler = new DefaultHandler();
parser.parse(input, handler, metadata, context);
}
}
private class FileEmbeddedDocumentExtractor implements
EmbeddedDocumentExtractor {
private int count = 0;
public boolean shouldParseEmbedded(Metadata metadata) {
return true;
}
public void parseEmbedded(InputStream inputStream, ContentHandler
contentHandler, Metadata metadata,
boolean outputHtml) throws SAXException,
IOException {
String fullFileName =
metadata.get(TikaCoreProperties.RESOURCE_NAME_KEY);
if (fullFileName == null) {
fullFileName = "file" + count++;
}
String[] fileNameSplit = fullFileName.split("/");
String fileName = fileNameSplit[fileNameSplit.length - 1];
File outputFile = new File(outputDir.toFile(),
FilenameUtils.normalize(fileName));
System.out.println("Extracting '" + fileName + " to " + outputFile);
FileOutputStream os = null;
try {
os = new FileOutputStream(outputFile);
if (inputStream instanceof TikaInputStream tin) {
if (tin.getOpenContainer() instanceof DirectoryEntry) {
try(POIFSFileSystem fs = new POIFSFileSystem()){
copy((DirectoryEntry) tin.getOpenContainer(),
fs.getRoot());
fs.writeFilesystem(os);
}
} else {
IOUtils.copy(inputStream, os);
}
} else {
IOUtils.copy(inputStream, os);
}
} catch (Exception ex) {
ex.printStackTrace();
} finally {
if (os != null) {
os.flush();
os.close();
}
}
}
protected void copy(DirectoryEntry sourceDir, DirectoryEntry destDir)
throws IOException {
for (org.apache.poi.poifs.filesystem.Entry entry : sourceDir) {
if (entry instanceof DirectoryEntry) {
// Need to recurse
DirectoryEntry newDir =
destDir.createDirectory(entry.getName());
copy((DirectoryEntry) entry, newDir);
} else {
// Copy entry
try (InputStream contents = new
DocumentInputStream((DocumentEntry) entry)) {
destDir.createDocument(entry.getName(), contents);
}
}
}
}
}
}
[^config_and_sample_file.zip]
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
