phyks/flatisfy
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Duplicates score should be enough, removing common photos assertion

Browse Source
This commit is contained in:
nicofrand 2018-01-21 14:27:29 +01:00
parent 4870078599
commit 83d7792e4c
1 changed files with 18 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

39
flatisfy/filters/duplicates.py
View File

@ -267,27 +267,6 @@ def get_duplicate_score(flat1, flat2, photo_cache, hash_threshold):
assert flat1_phone == flat2_phone assert flat1_phone == flat2_phone
n_common_items += 10 # Counts much more than the rest n_common_items += 10 # Counts much more than the rest
# They should have at least one photo in common if there
# are some photos
if flat1.get("photos", []) and flat2.get("photos", []):
n_common_photos = find_number_common_photos(
flat1["photos"],
flat2["photos"],
photo_cache,
hash_threshold
)
assert n_common_photos > 1
min_number_photos = min(len(flat1["photos"]),
len(flat2["photos"]))
# Either all the photos are the same, or there are at least
# three common photos.
if n_common_photos == min_number_photos:
n_common_items += 15
else:
n_common_items += 5 * min(n_common_photos, 3)
# If the two flats are from the same website and have a # If the two flats are from the same website and have a
# different float part, consider they cannot be duplicates. See # different float part, consider they cannot be duplicates. See
# https://framagit.org/phyks/Flatisfy/issues/100. # https://framagit.org/phyks/Flatisfy/issues/100.
@ -302,6 +281,24 @@ def get_duplicate_score(flat1, flat2, photo_cache, hash_threshold):
) )
if both_have_float_part and both_are_from_same_backend: if both_have_float_part and both_are_from_same_backend:
assert both_have_equal_float_part assert both_have_equal_float_part
if flat1.get("photos", []) and flat2.get("photos", []):
n_common_photos = find_number_common_photos(
flat1["photos"],
flat2["photos"],
photo_cache,
hash_threshold
)
min_number_photos = min(len(flat1["photos"]),
len(flat2["photos"]))
# Either all the photos are the same, or there are at least
# three common photos.
if n_common_photos == min_number_photos:
n_common_items += 15
else:
n_common_items += 5 * min(n_common_photos, 3)
except (AssertionError, TypeError): except (AssertionError, TypeError):
# Skip and consider as not duplicates whenever the conditions # Skip and consider as not duplicates whenever the conditions
# are not met # are not met