You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tika.apache.org by ta...@apache.org on 2026/05/13 16:44:13 UTC
(tika) branch haystack-poi-embedded-filenames created (now 1d6a8d79b6)
This is an automated email from the ASF dual-hosted git repository.
tballison pushed a change to branch haystack-poi-embedded-filenames
in repository https://gitbox.apache.org/repos/asf/tika.git
at 1d6a8d79b6 embedded file names and pagination in hslf
This branch includes the following new commits:
new 1d6a8d79b6 embedded file names and pagination in hslf
The 1 revisions listed above as "new" are entirely new to this
repository and will be described in separate emails. The revisions
listed as "add" were already present in the repository and have only
been added to this reference.
(tika) 01/01: embedded file names and pagination in hslf
Posted by ta...@apache.org.
This is an automated email from the ASF dual-hosted git repository.
tballison pushed a commit to branch haystack-poi-embedded-filenames
in repository https://gitbox.apache.org/repos/asf/tika.git
commit 1d6a8d79b67e563c51f9cf132237001211f583be
Author: tballison <ti...@elastic.co>
AuthorDate: Wed May 13 12:43:59 2026 -0400
embedded file names and pagination in hslf
---
.../parser/microsoft/AbstractPOIFSExtractor.java | 22 +++++++++++--
.../tika/parser/microsoft/HSLFExtractor.java | 36 ++++++++++++++++++++++
2 files changed, 55 insertions(+), 3 deletions(-)
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/AbstractPOIFSExtractor.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/AbstractPOIFSExtractor.java
index 37267b6644..6bb79a16c0 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/AbstractPOIFSExtractor.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/AbstractPOIFSExtractor.java
@@ -21,6 +21,7 @@ import java.io.IOException;
import java.io.InputStream;
import java.nio.charset.StandardCharsets;
import java.util.Iterator;
+import java.util.Locale;
import org.apache.commons.io.output.UnsynchronizedByteArrayOutputStream;
import org.apache.poi.hpsf.ClassID;
@@ -213,7 +214,7 @@ abstract class AbstractPOIFSExtractor {
metadata.set(TikaCoreProperties.RESOURCE_NAME_KEY, name);
} else {
metadata.set(TikaCoreProperties.RESOURCE_NAME_KEY,
- name + '.' + type.getExtension());
+ appendExtensionIfMissing(name, type.getExtension()));
metadata.set(TikaCoreProperties.RESOURCE_NAME_EXTENSION_INFERRED, true);
}
}
@@ -225,7 +226,7 @@ abstract class AbstractPOIFSExtractor {
metadata.set(TikaCoreProperties.RESOURCE_NAME_KEY, rName);
} else {
metadata.set(TikaCoreProperties.RESOURCE_NAME_KEY,
- rName + '.' + type.getExtension());
+ appendExtensionIfMissing(rName, type.getExtension()));
metadata.set(TikaCoreProperties.RESOURCE_NAME_EXTENSION_INFERRED, true);
}
}
@@ -320,7 +321,7 @@ abstract class AbstractPOIFSExtractor {
// Record what we can do about it
metadata.set(Metadata.CONTENT_TYPE, mediaType.toString());
- metadata.set(TikaCoreProperties.RESOURCE_NAME_KEY, rName + extension);
+ metadata.set(TikaCoreProperties.RESOURCE_NAME_KEY, appendExtensionIfMissing(rName, extension));
metadata.set(TikaCoreProperties.RESOURCE_NAME_EXTENSION_INFERRED, true);
metadata.set(Metadata.CONTENT_LENGTH, Integer.toString(length));
parseEmbedded(parentDir, tis, xhtml, metadata, outputHtml);
@@ -416,6 +417,21 @@ abstract class AbstractPOIFSExtractor {
}
+ /**
+ * Appends {@code ext} to {@code name} only when {@code name} does not already end with it
+ * (case-insensitive). {@code ext} may or may not have a leading dot.
+ */
+ private static String appendExtensionIfMissing(String name, String ext) {
+ if (StringUtils.isBlank(ext)) {
+ return name;
+ }
+ String dotExt = ext.startsWith(".") ? ext : "." + ext;
+ if (name.toLowerCase(Locale.ROOT).endsWith(dotExt.toLowerCase(Locale.ROOT))) {
+ return name;
+ }
+ return name + dotExt;
+ }
+
public static String tryToGetMsgTitle(DirectoryEntry node, String defaultVal) {
for (String entryName : new String[] {"__substg1.0_0037001F", "__substg1.0_0E1D001F", "__substg1.0_0070001F"} ) {
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/HSLFExtractor.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/HSLFExtractor.java
index e2f10977bc..95232fba3d 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/HSLFExtractor.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/HSLFExtractor.java
@@ -19,8 +19,10 @@ package org.apache.tika.parser.microsoft;
import java.io.IOException;
import java.io.InputStream;
import java.util.ArrayList;
+import java.util.HashMap;
import java.util.HashSet;
import java.util.List;
+import java.util.Map;
import java.util.Set;
import org.apache.poi.common.usermodel.Hyperlink;
@@ -37,6 +39,7 @@ import org.apache.poi.hslf.usermodel.HSLFNotes;
import org.apache.poi.hslf.usermodel.HSLFObjectData;
import org.apache.poi.hslf.usermodel.HSLFObjectShape;
import org.apache.poi.hslf.usermodel.HSLFPictureData;
+import org.apache.poi.hslf.usermodel.HSLFPictureShape;
import org.apache.poi.hslf.usermodel.HSLFShape;
import org.apache.poi.hslf.usermodel.HSLFSlide;
import org.apache.poi.hslf.usermodel.HSLFSlideShow;
@@ -61,6 +64,7 @@ import org.apache.tika.io.TikaInputStream;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.Office;
import org.apache.tika.metadata.TikaCoreProperties;
+import org.apache.tika.metadata.TikaPagedText;
import org.apache.tika.mime.MediaType;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.sax.XHTMLContentHandler;
@@ -553,6 +557,12 @@ public class HSLFExtractor extends AbstractPOIFSExtractor {
private void handleSlideEmbeddedPictures(HSLFSlideShow slideshow, XHTMLContentHandler xhtml)
throws TikaException, SAXException, IOException {
+ // Build picture-index → slide numbers map so each image carries its page number
+ Map<Integer, Set<Integer>> picToSlides = new HashMap<>();
+ for (HSLFSlide slide : slideshow.getSlides()) {
+ collectPictureSlides(slide, slide.getSlideNumber(), picToSlides);
+ }
+
for (HSLFPictureData pic : slideshow.getPictureData()) {
String mediaType;
@@ -585,12 +595,38 @@ public class HSLFExtractor extends AbstractPOIFSExtractor {
pic.getIndex(), mediaType);
Metadata picMetadata = Metadata.newInstance(context);
picMetadata.set(TikaCoreProperties.RESOURCE_NAME_EXTENSION_INFERRED, true);
+ Set<Integer> slideNums = picToSlides.get(pic.getIndex());
+ if (slideNums != null && slideNums.size() == 1) {
+ picMetadata.set(TikaPagedText.PAGE_NUMBER, slideNums.iterator().next());
+ }
handleEmbeddedResource(picIs, picMetadata, picName, null,
null, mediaType, xhtml, false);
}
}
}
+ /**
+ * Walks all shapes in {@code container} and records, for each
+ * {@link HSLFPictureShape}, the 1-based slide number in {@code picToSlides}.
+ */
+ private void collectPictureSlides(ShapeContainer container, int slideNum,
+ Map<Integer, Set<Integer>> picToSlides) {
+ List<HSLFShape> shapes = getShapes(container);
+ if (shapes == null) {
+ return;
+ }
+ for (HSLFShape shape : shapes) {
+ if (shape instanceof HSLFPictureShape) {
+ HSLFPictureData pd = ((HSLFPictureShape) shape).getPictureData();
+ if (pd != null) {
+ picToSlides.computeIfAbsent(pd.getIndex(), k -> new HashSet<>()).add(slideNum);
+ }
+ } else if (shape instanceof HSLFGroupShape) {
+ collectPictureSlides((HSLFGroupShape) shape, slideNum, picToSlides);
+ }
+ }
+ }
+
private void handleSlideEmbeddedResources(ShapeContainer shapeContainer,
XHTMLContentHandler xhtml)
throws TikaException, SAXException {