TIKA-4838: Expose the MP4 audio track codec (audio:format)

TikaMp4SoundHandler already reads the sound sample entry's format fourcc
(it uses it to detect drms/enca protected streams); expose it as a new
audio:format property (e.g. mp4a, alac, ac-3). For protected streams the
original codec is recovered from the nested frma box, with audio:has-drm
still set. Follows TIKA-4779, TIKA-4800 and TIKA-4802.

Author: dschmidt

tika-core/src/main/java/org/apache/tika/metadata/Audio.java

@@ -84,6 +84,15 @@ public interface Audio {
      */
     Property BITS_PER_SAMPLE = Property.internalInteger("audio:bits-per-sample");
 
+    /**
+     * The audio track's four-character codec identifier from the MP4/QuickTime
+     * sample description (e.g. "mp4a" for AAC, "alac", "ac-3"). For protected
+     * streams this is the original codec from the 'frma' box, with {@link #HAS_DRM}
+     * also set. Distinct from {@link XMPDM#AUDIO_COMPRESSOR}, the human-readable
+     * codec name.
+     */
+    Property FORMAT = Property.internalText("audio:format");
+
     /**
      * The raw javax.sound encoding name (e.g. "PCM_SIGNED"), as reported by {@code
      * AudioFormat#getEncoding()} (AudioParser). Distinct from {@link XMPDM#AUDIO_SAMPLE_TYPE}

tika-metadata-schema/src/main/resources/org/apache/tika/metadata/metadata-key-fields.json

@@ -13,6 +13,7 @@
   {"class":"org.apache.tika.metadata.Audio","field":"CHANNELS","key":"audio:channels"},
   {"class":"org.apache.tika.metadata.Audio","field":"DISC_COUNT","key":"audio:disc-count"},
   {"class":"org.apache.tika.metadata.Audio","field":"ENCODING","key":"audio:encoding"},
+  {"class":"org.apache.tika.metadata.Audio","field":"FORMAT","key":"audio:format"},
   {"class":"org.apache.tika.metadata.Audio","field":"HAS_DRM","key":"audio:has-drm"},
   {"class":"org.apache.tika.metadata.Audio","field":"IS_VARIABLE_BITRATE","key":"audio:is-variable-bitrate"},
   {"class":"org.apache.tika.metadata.Audio","field":"RAW_DISC_NUMBER","key":"audio:raw-disc-number"},

tika-metadata-schema/src/main/resources/org/apache/tika/metadata/metadata-keys.json

@@ -77,6 +77,7 @@
   {"key":"audio:channels","namespace":"audio","valueType":"INTEGER","cardinality":"SIMPLE","module":"tika-core"},
   {"key":"audio:disc-count","namespace":"audio","valueType":"INTEGER","cardinality":"SIMPLE","module":"tika-core"},
   {"key":"audio:encoding","namespace":"audio","valueType":"TEXT","cardinality":"SIMPLE","module":"tika-core"},
+  {"key":"audio:format","namespace":"audio","valueType":"TEXT","cardinality":"SIMPLE","module":"tika-core"},
   {"key":"audio:has-drm","namespace":"audio","valueType":"BOOLEAN","cardinality":"SIMPLE","module":"tika-core"},
   {"key":"audio:is-variable-bitrate","namespace":"audio","valueType":"BOOLEAN","cardinality":"SIMPLE","module":"tika-core"},
   {"key":"audio:raw-disc-number","namespace":"audio","valueType":"TEXT","cardinality":"SIMPLE","module":"tika-core"},

tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-audiovideo-module/src/main/java/org/apache/tika/parser/mp4/TikaMp4SoundHandler.java

@@ -70,20 +70,25 @@ private void extractFromSampleDescriptions(byte[] b) {
             }
             int end = pos + (int) size;
             String format = fourCc(b, pos + 4);
-            //protected streams replace the codec fourcc with a protected
-            //entry format: 'drms' (FairPlay) or 'enca' (ISO common encryption)
+            //sample entry: 8 byte header, 6 reserved, 2 data ref index, then
+            //version-dependent fixed sound fields before the child boxes
+            int childStart = pos + 18 <= end
+                    ? pos + soundEntrySize(EndianUtils.getUShortBE(b, pos + 16)) : end;
+            //protected streams replace the codec fourcc with a protected entry
+            //format: 'drms' (FairPlay) or 'enca' (ISO common encryption); the
+            //original codec is carried in a nested 'frma' box.
             if ("drms".equals(format) || "enca".equals(format)) {
                 tikaMetadata.set(Audio.HAS_DRM, true);
-            }
-            if (pos + 18 <= end) {
-                //sample entry: 8 byte header, 6 reserved, 2 data ref index,
-                //then version-dependent fixed sound fields before child boxes
-                int version = EndianUtils.getUShortBE(b, pos + 16);
-                int bitRate = findEsdsAverageBitRate(b, pos + soundEntrySize(version), end, 0);
-                if (bitRate > 0) {
-                    tikaMetadata.set(Audio.BITRATE, bitRate);
+                String original = findOriginalFormat(b, childStart, end, 0);
+                if (original != null) {
+                    format = original;
                 }
             }
+            tikaMetadata.set(Audio.FORMAT, format);
+            int bitRate = findEsdsAverageBitRate(b, childStart, end, 0);
+            if (bitRate > 0) {
+                tikaMetadata.set(Audio.BITRATE, bitRate);
+            }
             pos = end;
         }
     }
@@ -196,6 +201,36 @@ private static int skipDescriptorLength(byte[] b, int pos) {
         return pos + 1;
     }
 
+    /**
+     * Scans the child boxes of a protected ('drms'/'enca') sound sample entry for
+     * the 'frma' (original format) box nested in the 'sinf' protection scheme
+     * information box, and returns its codec fourcc, or null if there is none.
+     */
+    private static String findOriginalFormat(byte[] b, int pos, int end, int depth) {
+        if (depth > MAX_BOX_DEPTH) {
+            return null;
+        }
+        while (pos + 8 <= end) {
+            long size = EndianUtils.getUIntBE(b, pos);
+            if (size < 8 || size > end - pos) {
+                return null;
+            }
+            int boxEnd = pos + (int) size;
+            String type = fourCc(b, pos + 4);
+            if ("frma".equals(type) && pos + 12 <= boxEnd) {
+                return fourCc(b, pos + 8);
+            }
+            if ("sinf".equals(type)) {
+                String original = findOriginalFormat(b, pos + 8, boxEnd, depth + 1);
+                if (original != null) {
+                    return original;
+                }
+            }
+            pos = boxEnd;
+        }
+        return null;
+    }
+
     private static String fourCc(byte[] b, int pos) {
         return new String(b, pos, 4, StandardCharsets.ISO_8859_1);
     }

tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-audiovideo-module/src/test/java/org/apache/tika/parser/mp4/MP4ParserTest.java

@@ -130,6 +130,7 @@ public void testMP4ParsingAudio() throws Exception {
         assertEquals("Stereo", metadata.get(XMPDM.AUDIO_CHANNEL_TYPE));
         assertEquals("2", metadata.get(Audio.CHANNELS));
         assertEquals("16", metadata.get(Audio.BITS_PER_SAMPLE));
+        assertEquals("mp4a", metadata.get(Audio.FORMAT));
         assertEquals("M4A", metadata.get(XMPDM.AUDIO_COMPRESSOR));
         assertEquals("0.07", metadata.get(XMPDM.DURATION));