From 9d5d9f42fdf3ead35e87735f1bdf67b1a6e41215 Mon Sep 17 00:00:00 2001
From: iamkroot <kroot.patel@gmail.com>
Date: Sat, 26 Nov 2022 14:33:22 +0530
Subject: [PATCH] file_info: Use player-provided title for info

We give priority to title if it is present in title_whitelist.

Closes #169
---
 trakt_scrobbler/config_default.yaml        |  1 +
 trakt_scrobbler/file_info.py               | 22 ++++++++++++++++++++++
 trakt_scrobbler/player_monitors/monitor.py | 17 +++++++++++------
 3 files changed, 34 insertions(+), 6 deletions(-)

diff --git a/trakt_scrobbler/config_default.yaml b/trakt_scrobbler/config_default.yaml
index 864ad3c..6d8f71b 100644
--- a/trakt_scrobbler/config_default.yaml
+++ b/trakt_scrobbler/config_default.yaml
@@ -28,6 +28,7 @@ fileinfo:
 
   # if defined, only files from these directories will be scrobbled
   whitelist: []  # Keep as [] to allow all
+  title_whitelist: []  # use player-provided title instead of extracting from file path
 
   exclude_patterns: []  # ignore files matching these regex patterns
 
diff --git a/trakt_scrobbler/file_info.py b/trakt_scrobbler/file_info.py
index ecc1279..cdb9b76 100644
--- a/trakt_scrobbler/file_info.py
+++ b/trakt_scrobbler/file_info.py
@@ -11,6 +11,7 @@
 
 cfg = config["fileinfo"]
 whitelist = cfg["whitelist"].get(confuse.StrSeq())
+title_whitelist: list = cfg["title_whitelist"].get(confuse.Sequence(RegexPat()))
 regexes: dict = cfg['include_regexes'].get({
     "movie": confuse.Sequence(RegexPat()),
     "episode": confuse.Sequence(RegexPat()),
@@ -68,6 +69,16 @@ def whitelist_file(file_path: str, is_url=False, return_path=False) -> Union[boo
     return False
 
 
+def whitelist_title(title: str, return_entry=False) -> Union[bool, str]:
+    """Check if the given title string matches any entry in title_whitelist"""
+    for pattern in title_whitelist:
+        match = pattern.search(title)
+        if match:
+            logger.debug(f"Matched title whitelist entry {pattern!r}")
+            return pattern if return_entry else True
+    return False
+
+
 def exclude_file(file_path: str) -> bool:
     for pattern in exclude_patterns:
         if pattern.match(file_path):
@@ -133,8 +144,19 @@ def get_media_info(file_path: str):
 
 @lru_cache(maxsize=None)
 def get_media_info_from_title(title: str):
+    if not whitelist_title(title):
+        logger.info("Title not in whitelist.")
+        return None
+    # TODO: Do we want to have separate config key for title_exclude?
+    if exclude_file(title):
+        logger.info("Ignoring title.")
+        return None
+
+    # we don't allow custom regexes on titles
     guess = use_guessit(title)
     logger.debug(f"Title Guess: {guess}")
+    # TODO: perform mediainfo_remap on this guess
+    # maybe provide "match.playertitle" property for matching?
     return cleanup_guess(guess)
 
 
diff --git a/trakt_scrobbler/player_monitors/monitor.py b/trakt_scrobbler/player_monitors/monitor.py
index a7d6415..7c54072 100644
--- a/trakt_scrobbler/player_monitors/monitor.py
+++ b/trakt_scrobbler/player_monitors/monitor.py
@@ -159,12 +159,17 @@ def parse_status(status):
         ) or not status.get('duration'):
             return {}
 
-        if 'filepath' in status:
-            media_info = get_media_info(status['filepath'])
-            if 'title' in status:
-                title_info = get_media_info_from_title(status['title'])
-        else:
-            media_info = status['media_info']
+        media_info = None
+        if 'title' in status:
+            # give first priority to title from media player
+            # will be used if it is present in title_whitelist config
+            media_info = get_media_info_from_title(status['title'])
+
+        if media_info is None:
+            if 'filepath' in status:
+                media_info = get_media_info(status['filepath'])
+            else:
+                media_info = status['media_info']
 
         if media_info is None:
             return {}