Merge branch 'main' into metafile-rendering

Author: THausherr

CHANGES.txt

@@ -11,6 +11,14 @@ Release 4.1.0 - unreleased
      OLE2 formats (a WMF) as a THUMBNAIL embedded document, as the OOXML
      parsers do with the docProps thumbnail (TIKA-4855).
 
+   * Enum values in JSON configuration are matched case-insensitively, so
+     "no_ocr" works as well as "NO_OCR"; the server docs used the lower-case
+     form in their examples (TIKA-4859).
+
+   * The preview image of iWork '09 packages (QuickLook/Thumbnail.jpg) and of
+     iWork '18 packages (preview.jpg) is emitted as a THUMBNAIL embedded
+     document, as it already was for iWork '13 (TIKA-4854).
+
    * Raw camera formats are detected by content: RawTiffDetector tells
      Nikon NEF/NRW, Pentax PEF/PTX, Sony ARW/SRF/SR2, Samsung SRW and Adobe
      DNG from a plain TIFF by their image directory (DNGVersion, the vendor

docs/modules/ROOT/pages/migration-to-4x/migrating-tika-server-4x.adoc

@@ -67,7 +67,7 @@ POST endpoints accept multipart requests with a `file` part and optional `config
 # Parse with custom PDF parser settings (requires allowPerRequestConfig)
 curl -X POST http://localhost:9998/tika/config/json \
   -F "file=@document.pdf" \
-  -F "config={\"pdf-parser\":{\"ocr\":{\"strategy\":\"no_ocr\"}}};type=application/json"
+  -F "config={\"pdf-parser\":{\"ocr\":{\"strategy\":\"NO_OCR\"}}};type=application/json"
 ----
 
 == Breaking Changes

docs/modules/ROOT/pages/using-tika/server/index.adoc

@@ -246,7 +246,7 @@ POST with multipart for custom per-request configuration:
 ----
 curl -X POST http://localhost:9998/tika/config/json \
   -F "file=@document.pdf" \
-  -F "config={\"pdf-parser\":{\"ocr\":{\"strategy\":\"no_ocr\"}}};type=application/json"
+  -F "config={\"pdf-parser\":{\"ocr\":{\"strategy\":\"NO_OCR\"}}};type=application/json"
 ----
 
 Valid handler paths under `/tika/`: `text`, `html`, `xml`, `md`, `json` (bare `/tika` returns

tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-apple-module/src/main/java/org/apache/tika/parser/iwork/IWorkPackageParser.java

@@ -30,6 +30,7 @@
 import org.apache.commons.compress.archivers.zip.ZipArchiveInputStream;
 import org.apache.commons.compress.archivers.zip.ZipFile;
 import org.apache.commons.io.IOUtils;
+import org.apache.commons.io.input.BoundedInputStream;
 import org.apache.commons.io.input.CloseShieldInputStream;
 import org.apache.commons.io.input.UnsynchronizedByteArrayInputStream;
 import org.xml.sax.ContentHandler;
@@ -38,9 +39,12 @@
 import org.apache.tika.annotation.TikaComponent;
 import org.apache.tika.detect.XmlRootExtractor;
 import org.apache.tika.exception.TikaException;
+import org.apache.tika.extractor.EmbeddedDocumentExtractor;
+import org.apache.tika.extractor.EmbeddedDocumentUtil;
 import org.apache.tika.io.TikaInputStream;
 import org.apache.tika.metadata.HttpHeaders;
 import org.apache.tika.metadata.Metadata;
+import org.apache.tika.metadata.TikaCoreProperties;
 import org.apache.tika.mime.MediaType;
 import org.apache.tika.parser.ParseContext;
 import org.apache.tika.parser.Parser;
@@ -87,12 +91,48 @@ public Set<MediaType> getSupportedTypes(ParseContext context) {
         return supportedTypes;
     }
 
+    /**
+     * The document preview of an iWork '09 package.
+     */
+    public final static String IWORK_THUMBNAIL_ENTRY = "QuickLook/Thumbnail.jpg";
+
+    /**
+     * Bound on the preview held in memory until the content has been
+     * parsed; a real one is well under a megabyte.
+     */
+    private static final long MAX_THUMBNAIL_BYTES = 20 * 1024 * 1024;
+
     public void parse(TikaInputStream tis, ContentHandler handler, Metadata metadata,
                       ParseContext context) throws IOException, SAXException, TikaException {
         ZipArchiveInputStream zip = new ZipArchiveInputStream(tis);
         ZipArchiveEntry entry = zip.getNextEntry();
+        //the package is read as a stream, so the preview may come before the
+        //content: hold it back and emit it once the content is written, and
+        //only when the embedded document extractor wants it at all
+        EmbeddedDocumentExtractor extractor =
+                EmbeddedDocumentUtil.getEmbeddedDocumentExtractor(context);
+        Metadata thumbnailMetadata = null;
+        byte[] thumbnail = null;
+        XHTMLContentHandler xhtml = null;
 
         while (entry != null) {
+            if (IWORK_THUMBNAIL_ENTRY.equals(entry.getName()) && zip.canReadEntryData(entry)) {
+                thumbnailMetadata = thumbnailMetadata(context);
+                if (extractor.shouldParseEmbedded(thumbnailMetadata, context)) {
+                    //read one byte past the limit so an oversized entry is
+                    //recognized and skipped instead of emitted truncated
+                    thumbnail = BoundedInputStream.builder().setInputStream(zip)
+                            .setMaxCount(MAX_THUMBNAIL_BYTES + 1).get().readAllBytes();
+                    if (thumbnail.length > MAX_THUMBNAIL_BYTES) {
+                        thumbnail = null;
+                        metadata.add(TikaCoreProperties.TIKA_META_EXCEPTION_WARNING,
+                                IWORK_THUMBNAIL_ENTRY + " exceeds " + MAX_THUMBNAIL_BYTES
+                                        + " bytes and was skipped");
+                    }
+                }
+                entry = zip.getNextEntry();
+                continue;
+            }
             if (!IWORK_CONTENT_ENTRIES.contains(entry.getName())) {
                 entry = zip.getNextEntry();
                 continue;
@@ -104,7 +144,12 @@ public void parse(TikaInputStream tis, ContentHandler handler, Metadata metadata
             entryStream.reset(); // 4096 fails on github
 
             if (type != null) {
-                XHTMLContentHandler xhtml = new XHTMLContentHandler(handler, metadata, context);
+                if (xhtml == null) {
+                    //a package carries one content entry; guard against a
+                    //crafted one with several so the document is started once
+                    xhtml = new XHTMLContentHandler(handler, metadata, context);
+                    xhtml.startDocument();
+                }
                 ContentHandler contentHandler;
 
                 switch (type) {
@@ -126,19 +171,40 @@ public void parse(TikaInputStream tis, ContentHandler handler, Metadata metadata
                 }
 
                 metadata.set(HttpHeaders.CONTENT_TYPE, type.getType().toString());
-                xhtml.startDocument();
                 if (contentHandler != null) {
                     XMLReaderUtils.parseSAX(CloseShieldInputStream.wrap(entryStream),
                             contentHandler, context);
                 }
-                xhtml.endDocument();
             }
 
             entry = zip.getNextEntry();
         }
+        if (xhtml != null) {
+            if (thumbnail != null) {
+                try (TikaInputStream thumbnailStream = TikaInputStream.get(thumbnail)) {
+                    extractor.parseEmbedded(thumbnailStream, xhtml, thumbnailMetadata, context,
+                            true);
+                }
+            }
+            xhtml.endDocument();
+        }
         // Don't close the zip InputStream (TIKA-1117).
     }
 
+    /**
+     * The metadata of the document preview, a
+     * {@link TikaCoreProperties.EmbeddedResourceType#THUMBNAIL} embedded
+     * document.
+     */
+    private static Metadata thumbnailMetadata(ParseContext context) {
+        Metadata embeddedMetadata = Metadata.newInstance(context);
+        embeddedMetadata.set(TikaCoreProperties.EMBEDDED_RESOURCE_TYPE,
+                TikaCoreProperties.EmbeddedResourceType.THUMBNAIL.toString());
+        embeddedMetadata.set(TikaCoreProperties.RESOURCE_NAME_KEY, IWORK_THUMBNAIL_ENTRY);
+        embeddedMetadata.set(HttpHeaders.CONTENT_TYPE, "image/jpeg");
+        return embeddedMetadata;
+    }
+
     private IWORKDocumentType detectType(InputStream entryStream, int markLimit) throws IOException {
         byte[] bytes = new byte[markLimit];
         try {

tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-apple-module/src/main/java/org/apache/tika/parser/iwork/iwana/IWork18PackageParser.java

@@ -25,22 +25,28 @@
 import java.util.zip.ZipEntry;
 import java.util.zip.ZipInputStream;
 
+import org.apache.commons.compress.archivers.zip.ZipArchiveEntry;
 import org.apache.commons.compress.archivers.zip.ZipFile;
+import org.apache.commons.io.input.CloseShieldInputStream;
 import org.xml.sax.ContentHandler;
 import org.xml.sax.SAXException;
 
 import org.apache.tika.annotation.TikaComponent;
 import org.apache.tika.exception.TikaException;
+import org.apache.tika.extractor.EmbeddedDocumentExtractor;
+import org.apache.tika.extractor.EmbeddedDocumentUtil;
 import org.apache.tika.io.TikaInputStream;
 import org.apache.tika.metadata.HttpHeaders;
 import org.apache.tika.metadata.Metadata;
+import org.apache.tika.metadata.TikaCoreProperties;
 import org.apache.tika.mime.MediaType;
 import org.apache.tika.parser.ParseContext;
 import org.apache.tika.parser.Parser;
+import org.apache.tika.sax.XHTMLContentHandler;
 
 /**
- * For now, this parser isn't even registered.  It contains
- * code that will detect the newer 2018 .keynote, .numbers, .pages files.
+ * Detects the newer 2018 .keynote, .numbers, .pages files and emits their
+ * preview image as a thumbnail; the content itself is not parsed yet.
  */
 @TikaComponent
 public class IWork18PackageParser implements Parser {
@@ -67,32 +73,74 @@ public void parse(TikaInputStream tis, ContentHandler handler, Metadata metadata
             zipFile = (ZipFile) container;
         } else if (tis.hasFile()) {
             zipFile = ZipFile.builder().setFile(tis.getFile()).get();
+            //closed with the stream, as the zip container detector does it
+            tis.setOpenContainer(zipFile);
         } else {
             zipStream = new ZipInputStream(tis);
         }
 
-        // For now, just detect
+        // Detect the type, and emit the document preview as the thumbnail;
+        // the content itself is not parsed yet
+        XHTMLContentHandler xhtml = new XHTMLContentHandler(handler, metadata, context);
+        xhtml.startDocument();
         MediaType type = null;
         if (zipFile != null) {
-            Enumeration<? extends ZipEntry> entries = zipFile.getEntries();
+            Enumeration<? extends ZipArchiveEntry> entries = zipFile.getEntries();
             while (entries.hasMoreElements()) {
-                ZipEntry entry = entries.nextElement();
+                ZipArchiveEntry entry = entries.nextElement();
                 if (type == null) {
                     type = IWork18DocumentType.detectIfPossible(entry);
                 }
+                if (isPreview(entry) && zipFile.canReadEntryData(entry)) {
+                    try (TikaInputStream previewStream =
+                                 TikaInputStream.get(zipFile.getInputStream(entry))) {
+                        handleThumbnail(entry, previewStream, xhtml, context);
+                    }
+                }
             }
         } else {
             ZipEntry entry = zipStream.getNextEntry();
             while (entry != null) {
                 if (type == null) {
                     type = IWork18DocumentType.detectIfPossible(entry);
                 }
+                if (isPreview(entry)) {
+                    try (TikaInputStream previewStream =
+                                 TikaInputStream.get(CloseShieldInputStream.wrap(zipStream))) {
+                        handleThumbnail(entry, previewStream, xhtml, context);
+                    }
+                }
                 entry = zipStream.getNextEntry();
             }
         }
         if (type != null) {
             metadata.set(HttpHeaders.CONTENT_TYPE, type.toString());
         }
+        xhtml.endDocument();
+    }
+
+    /**
+     * The document preview, {@code preview.jpg} inside the package's
+     * document directory (e.g. {@code Presentation.key/preview.jpg}).
+     */
+    private static boolean isPreview(ZipEntry entry) {
+        String name = entry.getName();
+        return name.equals("preview.jpg") || name.endsWith("/preview.jpg");
+    }
+
+    private static void handleThumbnail(ZipEntry entry, TikaInputStream previewStream,
+                                        XHTMLContentHandler xhtml, ParseContext context)
+            throws IOException, SAXException {
+        EmbeddedDocumentExtractor extractor =
+                EmbeddedDocumentUtil.getEmbeddedDocumentExtractor(context);
+        Metadata embeddedMetadata = Metadata.newInstance(context);
+        embeddedMetadata.set(TikaCoreProperties.EMBEDDED_RESOURCE_TYPE,
+                TikaCoreProperties.EmbeddedResourceType.THUMBNAIL.toString());
+        embeddedMetadata.set(TikaCoreProperties.RESOURCE_NAME_KEY, entry.getName());
+        embeddedMetadata.set(HttpHeaders.CONTENT_TYPE, "image/jpeg");
+        if (extractor.shouldParseEmbedded(embeddedMetadata, context)) {
+            extractor.parseEmbedded(previewStream, xhtml, embeddedMetadata, context, true);
+        }
     }
 
     public enum IWork18DocumentType {

tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-apple-module/src/test/java/org/apache/tika/parser/iwork/IWorkParserTest.java

@@ -55,6 +55,48 @@ public void setUp() {
         iWorkParser = new IWorkPackageParser();
     }
 
+    /**
+     * The QuickLook preview of a Pages '09 package is the document's
+     * THUMBNAIL embedded document, emitted after the content.
+     */
+    @Test
+    public void testPagesThumbnail() throws Exception {
+        List<Metadata> metadataList = getRecursiveMetadata("testPages.pages");
+        assertEquals(2, metadataList.size());
+        assertEquals("application/vnd.apple.pages",
+                metadataList.get(0).get(HttpHeaders.CONTENT_TYPE));
+        Metadata thumbnail = metadataList.get(1);
+        assertEquals("QuickLook/Thumbnail.jpg", thumbnail.get(TikaCoreProperties.RESOURCE_NAME_KEY));
+        assertEquals("image/jpeg", thumbnail.get(HttpHeaders.CONTENT_TYPE));
+        assertEquals(TikaCoreProperties.EmbeddedResourceType.THUMBNAIL.toString(),
+                thumbnail.get(TikaCoreProperties.EMBEDDED_RESOURCE_TYPE));
+    }
+
+    @Test
+    public void testNumbersThumbnail() throws Exception {
+        List<Metadata> metadataList = getRecursiveMetadata("testNumbers.numbers");
+        assertEquals(2, metadataList.size());
+        Metadata thumbnail = metadataList.get(1);
+        assertEquals("QuickLook/Thumbnail.jpg", thumbnail.get(TikaCoreProperties.RESOURCE_NAME_KEY));
+        assertEquals("image/jpeg", thumbnail.get(HttpHeaders.CONTENT_TYPE));
+        assertEquals(TikaCoreProperties.EmbeddedResourceType.THUMBNAIL.toString(),
+                thumbnail.get(TikaCoreProperties.EMBEDDED_RESOURCE_TYPE));
+    }
+
+    /**
+     * Keynote '09 also carries per-slide thumbnails under thumbs/; only the
+     * QuickLook document preview is the thumbnail
+     */
+    @Test
+    public void testKeynoteThumbnail() throws Exception {
+        List<Metadata> metadataList = getRecursiveMetadata("testKeynote.key");
+        assertEquals(2, metadataList.size());
+        assertEquals("QuickLook/Thumbnail.jpg",
+                metadataList.get(1).get(TikaCoreProperties.RESOURCE_NAME_KEY));
+        assertEquals(TikaCoreProperties.EmbeddedResourceType.THUMBNAIL.toString(),
+                metadataList.get(1).get(TikaCoreProperties.EMBEDDED_RESOURCE_TYPE));
+    }
+
     /**
      * Check the given InputStream is not closed by the Parser (TIKA-1117).
      *