Updated

apps/pyMetadata/app.py

@@ -150,12 +150,14 @@ class MessageHandlerThread(threading.Thread):
                 baseName = messageData["sanitizedName"]
                 title = messageData["title"]
 
+                eventId = self.message.value["eventId"]
+
                 logger.info("Searching for %s", title)
-                result = self.get_metadata(title)
+                result = self.get_metadata(title, eventId)
                 if (result is None):
                     logger.info("No result for %s", title)
                     logger.info("Searching for %s", baseName)
-                    result = self.get_metadata(baseName)
+                    result = self.get_metadata(baseName, eventId)
 
                 producerMessage = self.compose_message(referenceId=self.message.value["referenceId"], result=result)
 
@@ -175,7 +177,7 @@ class MessageHandlerThread(threading.Thread):
         else:
             logger.warn("No status present for %s", self.message.value)
 
-    def get_metadata(self, name: str) -> Optional[DataResult]:
+    def get_metadata(self, name: str, evnetId: str) -> Optional[DataResult]:
         result = None
         logger.info("Checking cache for offloading")
         cache_result = ResultCache.get(name)
@@ -185,7 +187,7 @@ class MessageHandlerThread(threading.Thread):
         else:
             logger.info("Not in cache: %s", name)
             logger.info("Searching in sources for information about %s", name)
-            result: Optional[DataResult] = UseSource(title=name).select_result()
+            result: Optional[DataResult] = UseSource(title=name, eventId=evnetId).select_result()
             if (result.status == "COMPLETED"):
                 logger.info("Storing response for %s in in-memory cache", name)
                 ResultCache.add(name, result)

apps/pyMetadata/sources/select.py

@@ -7,6 +7,7 @@ from .imdb import metadata as ImdbMetadata
 from .mal import metadata as MalMetadata
 from fuzzywuzzy import fuzz
 from unidecode import unidecode
+import json
 
 
 logger = logging.getLogger(__name__)
@@ -23,7 +24,8 @@ class DataAndScore:
 
 class UseSource():
     title: str
-    def __init__(self, title) -> None:
+    evnetId: str
+    def __init__(self, title, eventId) -> None:
         self.title = title
 
     def __perform_search(self, title)-> List[WeightedData]:
@@ -63,13 +65,21 @@ class UseSource():
         scored = self.__calculate_score(title=self.title, weightData=weightResult)
         scored.sort(key=lambda x: x.score, reverse=True)
 
+        try:
+            jsr = json.dumps(scored, indent=4)
+            with open(f"./logs/{self.evnetId}.json", "w", encoding="utf-8") as f:
+                f.write(jsr)
+        except:
+            logger.info("Couldn't dump log..")
+
+
         try:
             titles: List[str] = []
             for wd in weightResult:
                 titles.append(wd.result.data.title)
                 titles.extend(wd.result.data.altTitle)
-            joinedTitles = "\n\t".join(titles)
-            logger.info(f"Title {self.title} gave the result: {joinedTitles} \nTitle selected: \n\t{scored[0].result.data.title}\n")
+            joinedTitles = "\n\t" + "\n\t".join(titles)
+            logger.info(f"[Title]: {self.title} gave the result: {joinedTitles} \nTitle selected: \n\t{scored[0].result.data.title}\n")
         except:
             pass
 

dockerfiles/Python

@@ -14,6 +14,8 @@ RUN pip3 install -r ./requirements.txt
 # Kopier resten av prosjektfilene
 COPY ./apps/${MODULE_NAME}/ .
 
+RUN mkdir ./apps/logs
+
 # Start applikasjonen
 CMD ["python3", "-u", "app.py"]
 

shared/common/src/main/kotlin/no/iktdev/mediaprocessing/shared/common/parsing/FileNameParser.kt

@@ -81,8 +81,10 @@ class FileNameParser(val fileName: String) {
     /**
      *
      */
-    fun removeResolutionAndTags(text: String): String {
-        return Regex("(.*?)(?=\\d+[pk]\\b)").replace(text, " ")
+    fun removeResolutionAndTags(input: String): String {
+        var text = Regex("(?i)(\\d+[pk]\\b|(hd|uhd))", RegexOption.IGNORE_CASE).replace(input, " ")
+        text = Regex("(?i)(\\s(bluray|laserdisc|dvd|web))", RegexOption.IGNORE_CASE).replace(text, " ")
+        return text
     }