Fix regex issues

src/ffx/helper.py

@@ -16,7 +16,21 @@ DIFF_REMOVED_KEY = 'removed'
 DIFF_CHANGED_KEY = 'changed'
 DIFF_UNCHANGED_KEY = 'unchanged'
 
-RICH_COLOR_PATTERN = '\\[[a-z_]+\\](.+)\\[\\/[a-z_]+\\]'
+FILENAME_FILTER_TRANSLATION = str.maketrans(
+    {
+        "/": "-",
+        ":": ";",
+        "*": "",
+        "'": "",
+        "?": "#",
+        "♥": "",
+        "’": "",
+    }
+)
+TMDB_FILLER_MARKERS = (" (*)", "(*)")
+TMDB_EPISODE_RANGE_SUFFIX_REGEX = re.compile(r"\(([0-9]+)[-/]([0-9]+)\)$")
+TMDB_EPISODE_PART_SUFFIX_REGEX = re.compile(r"\(([0-9]+)\)$")
+RICH_COLOR_REGEX = re.compile(r"\[[a-z_]+\](.+)\[/[a-z_]+\]")
 
 
 def dictDiff(a : dict, b : dict, ignoreKeys: list = [], removeKeys: list = []):
@@ -115,39 +129,35 @@ def filterFilename(fileName: str) -> str:
     """This filter replaces charactes from TMDB responses with characters
     less problemating when using in filenames or removes them"""
 
-    fileName = str(fileName).replace('/', '-')
-    fileName = str(fileName).replace(':', ';')
-    fileName = str(fileName).replace('*', '')
-    fileName = str(fileName).replace("'", '')
-    fileName = str(fileName).replace("?", '#')
-    fileName = str(fileName).replace('♥', '')
-    fileName = str(fileName).replace('’', '')
-
-    return fileName.strip()
+    return str(fileName).translate(FILENAME_FILTER_TRANSLATION).strip()
 
 def substituteTmdbFilename(fileName: str) -> str:
     """If chaining this method with filterFilename use this one first as the latter will destroy some patterns"""
 
-    # This indicates filler episodes in TMDB episode names
-    fileName = str(fileName).replace(' (*)', '')
-    fileName = str(fileName).replace('(*)', '')
+    normalizedFileName = str(fileName)
 
-    # This indicates the index of multi-episode files
-    episodePartMatch = re.search("\\(([0-9]+)\\)$", fileName)
+    for fillerMarker in TMDB_FILLER_MARKERS:
+        normalizedFileName = normalizedFileName.replace(fillerMarker, '')
+
+    episodeRangeMatch = TMDB_EPISODE_RANGE_SUFFIX_REGEX.search(normalizedFileName)
+    if episodeRangeMatch is not None:
+        partFirstIndex, partLastIndex = episodeRangeMatch.groups()
+        return TMDB_EPISODE_RANGE_SUFFIX_REGEX.sub(
+            f"Teil {partFirstIndex}-{partLastIndex}",
+            normalizedFileName,
+            count=1,
+        )
+
+    episodePartMatch = TMDB_EPISODE_PART_SUFFIX_REGEX.search(normalizedFileName)
     if episodePartMatch is not None:
-        partSuffix = str(episodePartMatch.group(0))
-        partIndex = episodePartMatch.groups()[0]
-        fileName = str(fileName).replace(partSuffix, f"Teil {partIndex}")
+        partIndex = episodePartMatch.group(1)
+        return TMDB_EPISODE_PART_SUFFIX_REGEX.sub(
+            f"Teil {partIndex}",
+            normalizedFileName,
+            count=1,
+        )
 
-    # Also multi-episodes with first and last episode index
-    episodePartMatch = re.search("\\(([0-9]+)[-\\/]([0-9]+)\\)$", fileName)
-    if episodePartMatch is not None:
-        partSuffix = str(episodePartMatch.group(0))
-        partFirstIndex = episodePartMatch.groups()[0]
-        partLastIndex = episodePartMatch.groups()[1]
-        fileName = str(fileName).replace(partSuffix, f"Teil {partFirstIndex}-{partLastIndex}")
-
-    return fileName
+    return normalizedFileName
 
 
 def getEpisodeFileBasename(showName,
@@ -231,7 +241,7 @@ def formatRichColor(text: str, color: str = None):
         return f"[{color}]{text}[/{color}]"
 
 def removeRichColor(text: str):
-    richColorMatch = re.search(RICH_COLOR_PATTERN, text)
+    richColorMatch = RICH_COLOR_REGEX.search(str(text))
     if richColorMatch is None:
         return text
     else: