avformat/matroskaenc: Make output more deterministic

Using random values for TrackUID and FileUID (as happens when the
AVFMT_FLAG_BITEXACT flag is not set) has the obvious downside of making
the output indeterministic. This commit mitigates this by writing the
potentially random values with a fixed size of eight byte, even if their
actual values would fit into less than eight bytes. This ensures that
even in non-bitexact mode, the differences between two files generated
with the same settings are restricted to a few bytes in the header.
(Namely the SegmentUID, the TrackUIDs (in Tracks as well as when
referencing them via TagTrackUID), the FileUIDs (in Attachments as
well as in TagAttachmentUID) as well as the CRC-32 checksums of the
Info, Tracks, Attachments and Tags level-1-elements.) Without this
patch, there might be an offset/a size difference between two such
files.

The FATE-tests had to be updated because the fixed-sized UIDs are also
used in bitexact mode.

Signed-off-by: Andreas Rheinhardt <andreas.rheinhardt@gmail.com>

1 files changed, 13 insertions, 3 deletions

diff --git a/libavformat/matroskaenc.c b/libavformat/matroskaenc.c
index cfa5c09282..7df7526b02 100644
--- a/libavformat/matroskaenc.c
+++ b/libavformat/matroskaenc.c
@@ -224,6 +224,16 @@ static void put_ebml_num(AVIOContext *pb, uint64_t num, int bytes)
         avio_w8(pb, (uint8_t)(num >> i * 8));
 }
 
+/**
+ * Write a (random) UID with fixed size to make the output more deterministic
+ */
+static void put_ebml_uid(AVIOContext *pb, uint32_t elementid, uint64_t uid)
+{
+    put_ebml_id(pb, elementid);
+    put_ebml_num(pb, 8, 0);
+    avio_wb64(pb, uid);
+}
+
 static void put_ebml_uint(AVIOContext *pb, uint32_t elementid, uint64_t val)
 {
     int i, bytes = 1;
@@ -1102,7 +1112,7 @@ static int mkv_write_track(AVFormatContext *s, MatroskaMuxContext *mkv,
     track = start_ebml_master(pb, MATROSKA_ID_TRACKENTRY, 0);
     put_ebml_uint (pb, MATROSKA_ID_TRACKNUMBER,
                    mkv->is_dash ? mkv->dash_track_number : i + 1);
-    put_ebml_uint (pb, MATROSKA_ID_TRACKUID, mkv->tracks[i].uid);
+    put_ebml_uid  (pb, MATROSKA_ID_TRACKUID, mkv->tracks[i].uid);
     put_ebml_uint (pb, MATROSKA_ID_TRACKFLAGLACING , 0);    // no lacing (yet)
 
     if ((tag = av_dict_get(st->metadata, "title", NULL, 0)))
@@ -1483,7 +1493,7 @@ static int mkv_write_tag_targets(AVFormatContext *s, uint32_t elementid,
     *tag    = start_ebml_master(pb, MATROSKA_ID_TAG,        0);
     targets = start_ebml_master(pb, MATROSKA_ID_TAGTARGETS, 0);
     if (elementid)
-        put_ebml_uint(pb, elementid, uid);
+        put_ebml_uid(pb, elementid, uid);
     end_ebml_master(pb, targets);
     return 0;
 }
@@ -1682,7 +1692,7 @@ static int mkv_write_attachments(AVFormatContext *s)
 
         put_ebml_string(dyn_cp, MATROSKA_ID_FILEMIMETYPE, mimetype);
         put_ebml_binary(dyn_cp, MATROSKA_ID_FILEDATA, st->codecpar->extradata, st->codecpar->extradata_size);
-        put_ebml_uint(dyn_cp, MATROSKA_ID_FILEUID, track->uid);
+        put_ebml_uid(dyn_cp, MATROSKA_ID_FILEUID, track->uid);
         end_ebml_master(dyn_cp, attached_file);
     }
     end_ebml_master_crc32(pb, &dyn_cp, mkv, MATROSKA_ID_ATTACHMENTS, 0, 0);