From 3fdfaaa5f36b0fb0d0918dc838c263909a8b7694 Mon Sep 17 00:00:00 2001
From: Julien Cassette <jcassette@users.noreply.github.com>
Date: Sun, 21 Nov 2021 18:41:06 +0100
Subject: [PATCH] Allow to configure which fields are used to find duplicates

---
 beets/autotag/__init__.py |  2 +-
 beets/config_default.yaml |  1 +
 beets/importer.py         | 22 ++++++++++++++++++----
 docs/changelog.rst        |  1 +
 docs/reference/config.rst | 10 ++++++++++
 5 files changed, 31 insertions(+), 5 deletions(-)

diff --git a/beets/autotag/__init__.py b/beets/autotag/__init__.py
index e62f492c6f..9169060293 100644
--- a/beets/autotag/__init__.py
+++ b/beets/autotag/__init__.py
@@ -27,7 +27,7 @@
     TrackMatch,
     Distance,
 )
-from .match import tag_item, tag_album, Proposal  # noqa
+from .match import tag_item, tag_album, current_metadata, Proposal  # noqa
 from .match import Recommendation  # noqa
 
 # Global logger.
diff --git a/beets/config_default.yaml b/beets/config_default.yaml
index 74540891e6..b59ce3297d 100644
--- a/beets/config_default.yaml
+++ b/beets/config_default.yaml
@@ -27,6 +27,7 @@ import:
     group_albums: no
     pretend: false
     search_ids: []
+    duplicate_keys: albumartist album
     duplicate_action: ask
     bell: no
     set_fields: {}
diff --git a/beets/importer.py b/beets/importer.py
index 561cedd2c6..76aa95fd8c 100644
--- a/beets/importer.py
+++ b/beets/importer.py
@@ -533,6 +533,17 @@ def chosen_ident(self):
         elif self.choice_flag is action.APPLY:
             return (self.match.info.artist, self.match.info.album)
 
+    def chosen_info(self):
+        """Returns a dictionnary of metadata about the current choice.
+        May only be called when the choice flag is ASIS or RETAG
+        (in which case the data comes from the files' current metadata)
+        or APPLY (in which case the data comes from the choice).
+        """
+        if self.choice_flag in (action.ASIS, action.RETAG):
+            return self.cur_info
+        elif self.choice_flag is action.APPLY:
+            return self.match.info
+
     def imported_items(self):
         """Return a list of Items that should be added to the library.
 
@@ -656,6 +667,8 @@ def lookup_candidates(self):
         candidate IDs are stored in self.search_ids: if present, the
         initial lookup is restricted to only those IDs.
         """
+        likelies, consensus = autotag.current_metadata(self.items)
+        self.cur_info = likelies
         artist, album, prop = \
             autotag.tag_album(self.items, search_ids=self.search_ids)
         self.cur_artist = artist
@@ -675,10 +688,11 @@ def find_duplicates(self, lib):
 
         duplicates = []
         task_paths = {i.path for i in self.items if i}
-        duplicate_query = dbcore.AndQuery((
-            dbcore.MatchQuery('albumartist', artist),
-            dbcore.MatchQuery('album', album),
-        ))
+        keys = config['import']['duplicate_keys'].as_str().split()
+        info = self.chosen_info().copy()
+        info['albumartist'] = artist
+        subqueries = [ dbcore.MatchQuery(k, info.get(k)) for k in keys ]
+        duplicate_query = dbcore.AndQuery(subqueries)
 
         for album in lib.albums(duplicate_query):
             # Check whether the album paths are all present in the task
diff --git a/docs/changelog.rst b/docs/changelog.rst
index e803b5bfa8..2ce0d35e8f 100644
--- a/docs/changelog.rst
+++ b/docs/changelog.rst
@@ -11,6 +11,7 @@ New features:
 * :doc:`/plugins/kodiupdate`: Now supports multiple kodi instances
   :bug:`4101`
 * Add the item fields ``bitrate_mode``, ``encoder_info`` and ``encoder_settings``.
+* Allow to configure which fields are used to find duplicates
 
 Bug fixes:
 
diff --git a/docs/reference/config.rst b/docs/reference/config.rst
index 642216c8f7..448eb8e60c 100644
--- a/docs/reference/config.rst
+++ b/docs/reference/config.rst
@@ -670,6 +670,16 @@ with the ``-a`` flag to the :ref:`import-cmd` command.)
 
 Default: ``yes``.
 
+.. _duplicate_keys:
+
+duplicate_keys
+~~~~~~~~~~~~~~
+
+The fields used to find duplicates in import task.
+If several items have the same value for each key, they will be considered duplicates.
+
+Default: ``albumartist album``
+
 .. _duplicate_action:
 
 duplicate_action