From 2b0217184f6d88baa070e1760a59abd020d08368 Mon Sep 17 00:00:00 2001
From: Damien De Paoli <ddp@depaoli.id.au>
Date: Sun, 17 Oct 2021 12:05:48 +1100
Subject: [PATCH] optimise a move via GUI and any re-hashing, due to FS move,
 or Transform, etc. to update the last_hash_dt so we dont keep redoing the md5
 hash as ctime > last_hash_dt, but there is no new content so no new
 last_hash_dt was being modified

---
 TODO              |  3 ---
 pa_job_manager.py | 14 ++++++++------
 2 files changed, 8 insertions(+), 9 deletions(-)

diff --git a/TODO b/TODO
index 16d6bcc..4e4ba48 100644
--- a/TODO
+++ b/TODO
@@ -8,9 +8,6 @@
             FIX: BUG-69
         TEST: what if we try to move a path in settings, should not allow this?
 
-    * when we do a legitimate move of a file, update last_scanned_dt otherwise FS change is newer, and it will 're-scan'
-    * when we scan and there is no hash diff then, update last_scanned_dt otherwise FS change is newer, and it will 're-scan' continually
-
     * remember last import dir, so you can just go straight back to it
 
     * in Fullscreen mode and next/prev dropped out of FS when calling /viewlist route
diff --git a/pa_job_manager.py b/pa_job_manager.py
index 8b26b20..56a3fb4 100644
--- a/pa_job_manager.py
+++ b/pa_job_manager.py
@@ -1057,6 +1057,8 @@ def MoveFileToNewFolderInStorage(job,move_me, dst_storage_path, dst_rel_path):
         print( f"DONE change of {move_me} in_dir to {new_dir} created above" )
     session.add(move_me)
     CleanUpDirInDB(job, orig_parent_dir_e)
+    # reset last_hash_date otherwise, the move resets ctime on the FS, and so scanning sees a 'new' file
+    move_me.file_details.last_hash_date = time.time()
     AddLogForJob(job, f"{move_me.name} - (moved to {os.path.dirname(move_me.FullPathOnFS())})" )
     return
 
@@ -1337,7 +1339,7 @@ def JobTransformImage(job):
     out.save( e.FullPathOnFS() )
     print( f"JobTransformImage DONE transform: job={job.id}, id={id}, amt={amt}" )
     e.file_details.thumbnail, _ , _ = GenThumb( e.FullPathOnFS() )
-    e.file_details.hash = md5( job, e.FullPathOnFS() )
+    e.file_details.hash = md5( job, e )
     print( f"JobTransformImage DONE thumb: job={job.id}, id={id}, amt={amt}" )
     session.add(e)
     FinishJob(job, "Finished Processesing image rotation/flip")
@@ -1358,7 +1360,7 @@ def GenHashAndThumb(job, e):
         job.current_file_num+=1
         return
 
-    new_hash = md5( job, e.FullPathOnFS() )
+    new_hash = md5( job, e )
     # same hash and we already have a thumbnail-> just return
     if new_hash == e.file_details.hash and e.file_details.thumbnail:
         if DEBUG:
@@ -1372,7 +1374,6 @@ def GenHashAndThumb(job, e):
         e.file_details.thumbnail = GenVideoThumbnail( job, e.FullPathOnFS() )
     elif e.type.name == 'Unknown':
         job.current_file_num+=1
-    e.file_details.last_hash_date = time.time()
     return
 
 ####################################################################################################################################
@@ -1427,13 +1428,14 @@ def isVideo(file):
 ####################################################################################################################################
 # Returns an md5 hash of the fnames' contents 
 ####################################################################################################################################
-def md5(job, fname):
+def md5(job, e):
     hash_md5 = hashlib.md5()
-    with open(fname, "rb") as f:
+    with open(e.FullPathOnFS(), "rb") as f:
         for chunk in iter(lambda: f.read(4096), b""):
             hash_md5.update(chunk)
     hash = hash_md5.hexdigest()
-    AddLogForJob( job, "Generated md5 hash: {} for file: {}".format( hash, fname ) )
+    AddLogForJob( job, "Generated md5 hash: {} for file: {}".format( hash, e.FullPathOnFS() ) )
+    e.file_details.last_hash_date = time.time()
     return hash
 
 ####################################################################################################################################