ordering methods for duplicates

files/file_list.py

@@ -37,6 +37,10 @@ def setup_options():
                       help="Depth of summarization for --du.")
     parser.add_argument("--dup",action="store_true",dest="duplicate",default=False,
                      help="Return a list of duplicate files, based on hashes. This option will flip the 'Add new files' option. [%(default)s]")
+    parser.add_argument("--dup-order",action="store",dest="duplicate_order",default='path',
+        help = "Order duplicates by a method. (length = path str length)",
+        choices = ('age','length','file','path')
+    )
     parser.add_argument("--haschanges",action="store_true",dest="haschanges",default=False,
                       help="Do not change anything, return True and exit code 1 if DB needs update. Exit code 0 if all intact.")
     parser.add_argument("--hasdeletions",action="store_true",dest="hasdeletions",default=False,
@@ -67,6 +71,7 @@ def setup_options():
     options.sqlpath=os.path.dirname(os.path.realpath(options.sqlfile))
     return options
 
+
 def add_recurse(options):
     conn=sqlite3.connect(options.sqlfile)
     conn.text_factory=str
@@ -101,6 +106,7 @@ def add_recurse(options):
     sys.stdout.write("\n")
     return
 
+
 def add_single(conn,filename,change=False,hash=None,minsize=0,fullfile=False):
     try:
         fsize=os.path.getsize(filename)
@@ -130,6 +136,7 @@ def add_single(conn,filename,change=False,hash=None,minsize=0,fullfile=False):
     sys.stdout.write('\r')
     return
 
+
 def checkdb(options):
     needle=options.search
     if len(needle)==0:
@@ -192,6 +199,7 @@ def clean_dirs(dirs):
             dirs.remove(s)
     return dirs
 
+
 def clean_syms(files,path):
     nonsyms=[]
     for f in files:
@@ -220,6 +228,7 @@ def createdb(options):
     conn.commit()
     return
 
+
 def delete_nonexisting(sqlfile,options):
     conn=sqlite3.connect(sqlfile)
     conn.text_factory=str
@@ -240,6 +249,7 @@ def delete_nonexisting(sqlfile,options):
     conn.commit()
     return
 
+
 def disk_used(options):
     conn=sqlite3.connect(options.sqlfile)
     conn.text_factory=str
@@ -266,13 +276,15 @@ def disk_used(options):
                          humanize_size(entry[0]).rjust(8),
                          entry[1]]))
 
+
 def filename_join(path,name,options):
     filename=os.path.realpath(os.path.join(path,name))
     if options.relative:
         return os.path.relpath(filename, options.sqlpath)
     return filename
 
-def find_duplicates(sqlfile):
+
+def find_duplicates(sqlfile, order):
     conn=sqlite3.connect(sqlfile)
     conn.text_factory=str
     db=conn.cursor()
@@ -285,7 +297,7 @@ def find_duplicates(sqlfile):
         flist=[]
         for row in dbh:
             flist.append(row)
-        flist.sort(key=lambda file: file[0])
+        sort_by_method(flist, order)
         duphash.append((hash, flist))
     duphash.sort(key=lambda file: file[1][0])
     return duphash
@@ -317,6 +329,7 @@ def get_folder_contents(db,path):
             files.append(base)
     return files
 
+
 def get_md5(filename,fullfile=False):
     ''' returns content based hash, only first 50Mb is read, unless user wants the whole file '''
     fsize=os.path.getsize(filename)
@@ -360,6 +373,7 @@ def has_changes_deleted(db,exit=True):
                 deleted.append(row[0])
     return deleted
 
+
 def has_changes_additions(db,options,exit=True):
     added=[]
     changed=[]
@@ -402,6 +416,7 @@ def humanize_date(date):
         return ''
     return datetime.datetime.fromtimestamp(int(date)).strftime('%Y-%m-%d %H:%M:%S')
 
+
 def humanize_size(size,precision=1):
     if size==None:
         return 'nan'
@@ -414,11 +429,13 @@ def humanize_size(size,precision=1):
         defPrecision=precision
     return "%.*f%s"%(defPrecision,size,suffixes[suffixIndex])
 
+
 def is_listed(db,filename):
     db.execute("SELECT COUNT(*) FROM list where file == ?",(filename,))
     count=db.fetchall()
     return count[0][0]>0
 
+
 def matchdb(sqlfile,needle,helper):
     needle=needle.lower()
     import difflib as dl
@@ -441,20 +458,27 @@ def matchdb(sqlfile,needle,helper):
             best_match=row[0]
     print(best_match)
 
-def print_structure(files):
+def print_duplicates(files):
     for hash in files:
         #print(hash[0])
         i=1
         for f in hash[1]:
-            print "%(i)d: %(x)d:%(f)s " % {'i':i, 'f':f[0], 'x':f[1]}
+            print("%(i)d|%(s)s|%(d)s|%(f)s " % {
+                'i':i,
+                'f':f[0],
+                'd': humanize_date(f[2]),
+                's': humanize_size(f[1])
+            })
             i+=1
     return
 
+
 def print_stderr(s):
     sys.stderr.write(s)
     sys.stderr.write("\n")
     sys.stderr.flush()
 
+
 def searchdb(sqlfile,needle):
     needle=['%'+i+'%' for i in needle]
     like_query=' OR '.join(['file LIKE ?' for i in needle])
@@ -465,6 +489,18 @@ def searchdb(sqlfile,needle):
     for row in db:
         print(row[0])
 
+
+def sort_by_method(flist, order):
+    if order == 'path':
+        flist.sort(key=lambda file: file[0])
+    if order == 'file':
+        flist.sort(key=lambda file: os.path.basename(file[0]))
+    if order == 'age':
+        flist.sort(key=lambda file: file[2])
+    if order == 'length':
+        flist.sort(key=lambda file: len(file[0]))
+
+
 def stored_options(options):
     try:
         conn=sqlite3.connect(options.sqlfile)
@@ -483,6 +519,7 @@ def stored_options(options):
 
     return options
 
+
 def main():
     options=setup_options();
 
@@ -513,8 +550,8 @@ def main():
         print('Adding '+options.startpath+' entries...')
         add_recurse(options)
     if options.duplicate:
-        files=find_duplicates(options.sqlfile)
-        print_structure(files)
+        files=find_duplicates(options.sqlfile, options.duplicate_order)
+        print_duplicates(files)
 
     sys.exit(0)