filter-repo: report on and record LFS objects we find

After finding and tracking LFS objects orphaned by the rewrite as done
in the last few commits, report on and record these objects as well.

Signed-off-by: Elijah Newren <newren@gmail.com>

Author: newren

Documentation/git-filter-repo.txt

@@ -512,6 +512,21 @@ have been made public and shared from the previous rewrite, then the next
 filter-repo run should not be considered a continuation of the previous
 filtering run.
 
+Original LFS Objects
+~~~~~~~~~~~~~~~~~~~~
+
+When running with the --sensitive-data-removal flag, and LFS is in use by the
+repository, the `$GIT_DIR/filter-repo/original_lfs_objects` contains a list of
+LFS objects referenced by the repository before the rewrite, in sorted order.
+
+Orphaned LFS Objects
+~~~~~~~~~~~~~~~~~~~~
+
+When running with the --sensitive-data-removal flag, and LFS is in use by the
+repository, the `$GIT_DIR/filter-repo/orphaned_lfs_objects` contains a list of
+LFS objects that used to be referenced by the repository but no longer are after
+git-filter-repo has run.  Objects appear in sorted order.
+
 [[FRESHCLONE]]
 FRESH CLONE SAFETY CHECK AND --FORCE
 ------------------------------------

git-filter-repo

@@ -4656,6 +4656,27 @@ class RepoFilter(object):
 
     return commit_renames, ref_maps, first_changes
 
+  def _handle_lfs_metadata(self, metadata_dir):
+    if self._lfs_object_tracker is None:
+      print("NOTE: LFS object orphaning not checked (LFS not in use)")
+      return
+
+    with open(os.path.join(metadata_dir, b'original_lfs_objects'), 'bw') as f:
+      for obj in sorted(self._lfs_object_tracker.source_objects.objects):
+        f.write(obj+b"\n")
+
+    orphaned_lfs_path = os.path.join(metadata_dir, b'orphaned_lfs_objects')
+    msg = textwrap.dedent(_(f"""\
+      NOTE: There were LFS Objects Orphaned by this rewrite recorded in
+            {decode(orphaned_lfs_path)}."""))
+    with open(orphaned_lfs_path, 'bw') as f:
+      differences = self._lfs_object_tracker.source_objects.objects - \
+                    self._lfs_object_tracker.target_objects.objects
+      for obj in sorted(differences):
+        f.write(obj+b"\n")
+      if differences:
+        print(msg)
+
   def _record_metadata(self, metadata_dir, orig_refs):
     self._flush_renames()
     commit_renames, ref_maps, first_changes = \
@@ -4671,6 +4692,7 @@ class RepoFilter(object):
       with open(os.path.join(metadata_dir, b'sensitive_data_removal'), 'bw') as f:
         pass # Write nothing; we only need the file created
 
+      self._handle_lfs_metadata(metadata_dir)
       print("") # Add a blank line after important rewrite information
 
     with open(os.path.join(metadata_dir, b'commit-map'), 'bw') as f:

t/t9393-filter-repo-rerun.sh

@@ -643,7 +643,7 @@ test_expect_success 'sdr: handling local-only changes' '
 # attempting to smudge them, which would just result in an error.
 export GIT_LFS_SKIP_SMUDGE=1
 
-test_expect_failure 'lfs: not in use, no files to process' '
+test_expect_success 'lfs: not in use, no files to process' '
 	test_create_repo no_lfs_files_to_process &&
 	(
 		cd no_lfs_files_to_process &&
@@ -666,7 +666,7 @@ test_expect_failure 'lfs: not in use, no files to process' '
 	)
 '
 
-test_expect_failure 'lfs: no files orphaned' '
+test_expect_success 'lfs: no files orphaned' '
 	test_create_repo no_lfs_files_orphaned &&
 	(
 		cd no_lfs_files_orphaned &&
@@ -677,7 +677,7 @@ test_expect_failure 'lfs: no files orphaned' '
 		                --invert-paths --force >output &&
 
 		! grep "NOTE:.*LFS not in use" output &&
-		! grep "NOTE:.*LFS objects orphaned by this rewrite" output &&
+		! grep "NOTE:.*LFS Objects Orphaned by this rewrite" output &&
 
 		cat <<-EOF >expect &&
 		sha256:aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
@@ -701,7 +701,7 @@ test_expect_failure 'lfs: orphaning across multiple runs' '
 		git filter-repo --sensitive-data-removal --path LB --path LD \
 		                --invert-paths --force >output &&
 
-		grep "NOTE:.*LFS objects orphaned by this rewrite" output &&
+		grep "NOTE:.*LFS Objects Orphaned by this rewrite" output &&
 
 		cat <<-EOF >orig_expect &&
 		sha256:aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
@@ -738,7 +738,7 @@ test_expect_failure 'lfs: orphaning across multiple runs with blob callback' '
 		                --invert-paths --blob-callback pass \
 		                --force >output &&
 
-		grep "NOTE:.*LFS objects orphaned by this rewrite" output &&
+		grep "NOTE:.*LFS Objects Orphaned by this rewrite" output &&
 
 		cat <<-EOF >orig_expect &&
 		sha256:aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa