TIKA-4870: Parse AVIF, do not only detect it

CHANGES.txt

@@ -1,5 +1,9 @@
 Release 4.1.0 - unreleased
 
+   * AVIF images are parsed rather than only detected: HeifParser accepts
+     image/avif, which is the same ISO-BMFF container, so dimensions, EXIF
+     and XMP come out of it the way they do for HEIC (TIKA-4870).
+
    * The video of a Google/Android motion photo, appended after the image and
      described by the Motion Photo or MicroVideo XMP, is emitted as an
      ATTACHMENT embedded document named after what the file declares it to

tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-image-module/src/main/java/org/apache/tika/parser/image/HeifParser.java

@@ -21,6 +21,7 @@
 import java.io.InputStream;
 import java.nio.file.Files;
 import java.util.Arrays;
+import java.util.Collections;
 import java.util.HashSet;
 import java.util.Set;
 
@@ -39,9 +40,10 @@
 @TikaComponent
 public class HeifParser extends AbstractImageParser {
 
-    private static final Set<MediaType> SUPPORTED_TYPES = new HashSet<>(
-            Arrays.asList(MediaType.image("heif"), MediaType.image("heif-sequence"),
-                    MediaType.image("heic"), MediaType.image("heic-sequence")));
+    private static final Set<MediaType> SUPPORTED_TYPES = Collections.unmodifiableSet(
+            new HashSet<>(Arrays.asList(MediaType.image("heif"), MediaType.image("heif-sequence"),
+                    MediaType.image("heic"), MediaType.image("heic-sequence"),
+                    MediaType.image("avif"))));
 
     @Override
     public Set<MediaType> getSupportedTypes(ParseContext context) {

tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-image-module/src/test/java/org/apache/tika/parser/image/HeifParserTest.java

@@ -26,6 +26,7 @@
 import org.apache.tika.metadata.Geographic;
 import org.apache.tika.metadata.HttpHeaders;
 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;
@@ -84,4 +85,25 @@ public void testAppleLivePhotoMakerNote() throws Exception {
         }
     }
 
+    /*
+        testAVIF_XMP.avif is a 32x32 gradient encoded with libavif through
+        ImageMagick, with an XMP packet attached: AVIF is the same ISO-BMFF
+        container, so the same parser reads it (TIKA-4870).
+     */
+    @Test
+    public void testAvif() throws Exception {
+        Metadata metadata = new Metadata();
+        try (TikaInputStream tis = getResourceAsStream("/test-documents/testAVIF_XMP.avif")) {
+            parser.parse(tis, new DefaultHandler(), metadata, new ParseContext());
+
+            assertEquals("image/avif", metadata.get(HttpHeaders.CONTENT_TYPE));
+            assertEquals("avif", metadata.get(ImageMetadataExtractor.UNKNOWN_IMG_NS + "Major Brand"));
+            assertEquals("32 pixels", metadata.get(ImageMetadataExtractor.UNKNOWN_IMG_NS + "Width"));
+            assertEquals("32 pixels", metadata.get(ImageMetadataExtractor.UNKNOWN_IMG_NS + "Height"));
+            //the XMP item is found through meta/iinf/iloc, as it is for HEIC
+            assertEquals("AVIF XMP Title", metadata.get(TikaCoreProperties.TITLE));
+            assertEquals("Jane Photographer", metadata.get(TikaCoreProperties.CREATOR));
+        }
+    }
+
 }