From 244000b5e540cace5e05edafa56e0cbae2db57d7 Mon Sep 17 00:00:00 2001
From: Derrick Gilland <dgilland@gmail.com>
Date: Wed, 1 Jul 2015 18:03:11 -0400
Subject: [PATCH] Add "is_duplicate" attribute to HashAddress and make
 HashFS.put() return HashAddress with "is_duplicate=True" when file with same
 hash already exists on disk.

Refs #1.
---
 CHANGES.rst          |  2 ++
 README.rst           |  3 +++
 hashfs/hashfs.py     | 22 +++++++++++++++++-----
 tests/test_hashfs.py | 11 +++++++++++
 4 files changed, 33 insertions(+), 5 deletions(-)

diff --git a/CHANGES.rst b/CHANGES.rst
index 8a6cded..d292dc1 100644
--- a/CHANGES.rst
+++ b/CHANGES.rst
@@ -3,6 +3,8 @@ Changelog
 
 
 - Rename private method ``HashFS.copy`` to ``HashFS._copy``.
+- Add ``is_duplicate`` attribute to ``HashAddress``.
+- Make ``HashFS.put()`` return ``HashAddress`` with ``is_duplicate=True`` when file with same hash already exists on disk.
 
 
 v0.4.0 (2015-06-03)
diff --git a/README.rst b/README.rst
index ac0aa81..aa275e3 100644
--- a/README.rst
+++ b/README.rst
@@ -104,6 +104,9 @@ Add content to the folder using either readable objects (e.g. ``StringIO``) or f
     # The path relative to fs.root.
     address.relpath
 
+    # Whether the file previously existed.
+    address.is_duplicate
+
 
 Retrieving File Address
 -----------------------
diff --git a/hashfs/hashfs.py b/hashfs/hashfs.py
index 3e6545d..dae8b7a 100644
--- a/hashfs/hashfs.py
+++ b/hashfs/hashfs.py
@@ -64,9 +64,9 @@ def put(self, file, extension=None):
 
         with closing(stream):
             id = self.computehash(stream)
-            filepath = self.copy(stream, id, extension)
+            filepath, is_duplicate = self._copy(stream, id, extension)
 
-        return HashAddress(id, self.relpath(filepath), filepath)
+        return HashAddress(id, self.relpath(filepath), filepath, is_duplicate)
 
     def _copy(self, stream, id, extension=None):
         """Copy the contents of `stream` onto disk with an optional file
@@ -77,11 +77,14 @@ def _copy(self, stream, id, extension=None):
 
         # Only copy file if it doesn't already exist.
         if not os.path.isfile(filepath):
+            is_duplicate = False
             with tmpfile(stream, self.fmode) as fname:
                 self.makepath(os.path.dirname(filepath))
                 shutil.copy(fname, filepath)
+        else:
+            is_duplicate = True
 
-        return filepath
+        return (filepath, is_duplicate)
 
     def get(self, file):
         """Return :class:`HashAdress` from given id or path. If `file` does not
@@ -329,15 +332,24 @@ def __len__(self):
         return self.count()
 
 
-class HashAddress(namedtuple('HashAddress', ['id', 'relpath', 'abspath'])):
+class HashAddress(namedtuple('HashAddress',
+                             ['id', 'relpath', 'abspath', 'is_duplicate'])):
     """File address containing file's path on disk and it's content hash ID.
 
     Attributes:
         id (str): Hash ID (hexdigest) of file contents.
         relpath (str): Relative path location to :attr:`HashFS.root`.
         abspath (str): Absoluate path location of file on disk.
+        is_duplicate (boolean, optional): Whether the hash address created was
+            a duplicate of a previously existing file. Can only be ``True``
+            after a put operation. Defaults to ``False``.
     """
-    pass
+    def __new__(cls, id, relpath, abspath, is_duplicate=False):
+        return super(HashAddress, cls).__new__(cls,
+                                               id,
+                                               relpath,
+                                               abspath,
+                                               is_duplicate)
 
 
 class Stream(object):
diff --git a/tests/test_hashfs.py b/tests/test_hashfs.py
index 1ad4f30..3a26ebc 100755
--- a/tests/test_hashfs.py
+++ b/tests/test_hashfs.py
@@ -96,6 +96,14 @@ def test_hashfs_put_file(fs, filepath):
         assert fileobj.read() == to_bytes(filepath.read())
 
 
+def test_hashfs_put_duplicate(fs, stringio):
+    address_a = fs.put(stringio)
+    address_b = fs.put(stringio)
+
+    assert not address_a.is_duplicate
+    assert address_b.is_duplicate
+
+
 @pytest.mark.parametrize('extension', [
     'txt',
     '.txt',
@@ -108,6 +116,7 @@ def test_hashfs_put_extension(fs, stringio, extension):
     assert_file_put(fs, address)
     assert os.path.sep in address.abspath
     assert os.path.splitext(address.abspath)[1].endswith(extension)
+    assert not address.is_duplicate
 
 
 def test_hashfs_put_error(fs):
@@ -121,6 +130,7 @@ def test_hashfs_address(fs, stringio):
     assert fs.root not in address.relpath
     assert os.path.join(fs.root, address.relpath) == address.abspath
     assert address.relpath.replace(os.sep, '') == address.id
+    assert not address.is_duplicate
 
 
 @pytest.mark.parametrize('extension,address_attr', [
@@ -166,6 +176,7 @@ def test_hashfs_contains(fs, stringio):
 def test_hashfs_get(fs, stringio):
     address = fs.put(stringio)
 
+    assert not address.is_duplicate
     assert fs.get(address.id) == address
     assert fs.get(address.relpath) == address
     assert fs.get(address.abspath) == address