renamed self.KeepInSameDups to self.KeepInIPSPDups as it is not same dir, but ip to sp

This commit is contained in:
2021-03-25 19:52:48 +11:00
parent a6161d1fa2
commit b216d138b9

27
dups.py
View File

@@ -134,16 +134,15 @@ class Duplicates:
return False
# this stores this object into the keep from same path list (DDP: could there be more than 1)
def KeepInSameDups( self, obj ):
def KeepInIPSPDups( self, obj ):
if obj.h not in self.ip_to_sp_dups_keep:
self.ip_to_sp_dups_keep[obj.h]= obj
self.overall_dup_cnt += 1
self.overall_dup_sets += 1
return
# this stores this object into the Delete from same path list (if it is not
# already there)
def DelInSameDups( self, obj ):
def DelInIPSPDups( self, obj ):
if obj.h not in self.ip_to_sp_dups_del:
self.ip_to_sp_dups_del[obj.h]=[]
self.ip_to_sp_dups_del[obj.h].append( obj )
@@ -157,16 +156,16 @@ class Duplicates:
return
# this function takes a duplicate file (in the import path and the storage path)
# and then puts the storage path file in the keep list (self.ip_to_sp_dups_keep) via self.KeepInSameDups()
# and then puts the import path file in the delete list (self.ip_to_sp_dups_keep) via self.DelInSameDups()
# and then puts the storage path file in the keep list (self.ip_to_sp_dups_keep) via self.KeepInIPSPDups()
# and then puts the import path file in the delete list (self.ip_to_sp_dups_keep) via self.DelInIPSPDups()
def DupInImportAndStoragePath( self, row, dr1, dr2 ):
if self.InStoragePath(row.path1) and self.InImportPath(row.path2):
self.KeepInSameDups( dr1 )
self.DelInSameDups( dr2 )
self.KeepInIPSPDups( dr1 )
self.DelInIPSPDups( dr2 )
return True
if self.InStoragePath(row.path2) and self.InImportPath(row.path1):
self.KeepInSameDups( dr2 )
self.DelInSameDups( dr1 )
self.KeepInIPSPDups( dr2 )
self.DelInIPSPDups( dr1 )
return True
return False
@@ -180,9 +179,6 @@ class Duplicates:
if self.DupInImportAndStoragePath( row, dr1, dr2 ):
return
# if we are here, we have duplicates either in the storage path or in
# the import path
# if the hast is no dups_to_process, created / append
if row.hash not in self.dups_to_process:
self.dups_to_process[row.hash]=[]
@@ -208,7 +204,7 @@ class Duplicates:
return
def AddDupPath(self, hash):
# this gets complex, if this hash is also in a sahred imp / sp - then dont deal with it now, let the imp files be deleted and
# this gets complex, if this hash is also in a shared imp / sp - then dont deal with it now, let the imp files be deleted and
# the repeat check_dups validation step catch it as a cleander (potential) for still more duplicates just in sp
if hash in self.ip_to_sp_dups_keep:
return
@@ -228,14 +224,15 @@ class Duplicates:
self.preferred_path[dpr.did1]=1
if re.search( r'\d{4}/\d{8}', dpr.d2):
self.preferred_path[dpr.did2]=1
return
def SecondPass(self):
for hash in self.dups_to_process:
# more than 2 files (just ask per file) OR only 2 copies, and files are in same dir (so must be diff name, so just ask) OR content same, filename different (ask per file)
if (len(self.dups_to_process[hash]) > 2) or (self.dups_to_process[hash][0].f != self.dups_to_process[hash][1].f) or (self.dups_to_process[hash][0].d == self.dups_to_process[hash][1].d):
self.per_file_dups.append(self.dups_to_process[hash])
self.overall_dup_cnt += len(self.dups_to_process[hash])
self.overall_dup_sets += 1
self.overall_dup_cnt += len(self.dups_to_process[hash])
self.per_file_dups.append(self.dups_to_process[hash])
for el in self.dups_to_process[hash]:
if re.search( r'\d{4}/\d{8}', el.d):
self.preferred_file[hash] = el.id