From 2fc01f7cad3f0df92aa08b22072ee51f3b1b9db4 Mon Sep 17 00:00:00 2001
From: Lars Wirzenius <liw@liw.fi>
Date: Sun, 25 Apr 2010 06:15:25 +1200
Subject: Only report hardlinks as duplicates if there's another identical file
 as well.

If foo and bar are hardlinks to the same inode, and foobar is a file
with the same content, report all three. However, if there is no foobar
to be reported, do not report anything.
---
 dupfiles | 3 +++
 testit   | 2 +-
 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/dupfiles b/dupfiles
index ea52d7f..dd0364a 100755
--- a/dupfiles
+++ b/dupfiles
@@ -84,6 +84,9 @@ class DuplicateFileFinder(object):
 
         result = []
         for size, tuples in self.by_size.iteritems():
+            if len(set((dev, ino) for dev, ino, pathname in tuples)) == 1:
+                # All duplicates are hardlinks to the same inode. Skip.
+                continue
             by_checksum = dict()
             for dev, ino, pathname in tuples:
                 checksum = self.file_checksum(pathname)
diff --git a/testit b/testit
index b1bdc9f..59f2659 100755
--- a/testit
+++ b/testit
@@ -92,7 +92,7 @@ class TwoHardlinksToSameContent(TestCase):
     def setUp(self):
         self.create('foo', 'foo')
         self.hardlink('foo', 'bar')
-        self.identical = ['foo', 'bar']
+        self.identical = []
 
 
 class TwoHardlinksToSameContentPlusSecondIdenticalCopy(TestCase):
-- 
cgit v1.2.1