Formatting

ucsinfer/__main__.py

@@ -52,7 +52,7 @@ def gather(paths, outfile):
 
     print(f"Found {len(scan_list)} files to process.")
 
-    for pair in tqdm.tqdm(scan_list, unit='files',file=sys.stderr):
+    for pair in tqdm.tqdm(scan_list, unit='files', file=sys.stderr):
         if desc := ffmpeg_description(pair[1]):
             table.writerow([pair[0], desc])
 
@@ -107,7 +107,8 @@ def evaluate(dataset, offset, limit):
 
     miss_counts = []
     for cat in cats:
-        miss_counts.append((cat, len([x for x in results \
+        miss_counts.append(
+            (cat, len([x for x in results
                        if x['catid'] == cat and x['result'] == 'MISS'])))
 
     miss_counts = sorted(miss_counts, key=lambda x: x[1])
@@ -131,7 +132,7 @@ def evaluate(dataset, offset, limit):
          f"{float(miss_counts[-1][1])/float(total):.2%}"]
     ]
 
-    print(tabulate(table, headers=['','n','pct']))
+    print(tabulate(table, headers=['', 'n', 'pct']))
 
 
 if __name__ == '__main__':

ucsinfer/inference.py

@@ -11,6 +11,7 @@ import platformdirs
 
 from sentence_transformers import SentenceTransformer
 
+
 def classify_text_ranked(text, embeddings_list, model, limit=5):
     text_embedding = model.encode(text, convert_to_numpy=True)
     embeddings = np.array([info['Embedding'] for info in embeddings_list])
@@ -32,6 +33,7 @@ class Ucs(NamedTuple):
                    subcategory=d['SubCategory'],
                    explanations=d['Explanations'], synonymns=d['Synonyms'])
 
+
 def load_ucs() -> list[Ucs]:
     FILE_ROOT_DIR = os.path.dirname(os.path.abspath(__file__))
     cats = []
@@ -43,6 +45,7 @@ def load_ucs() -> list[Ucs]:
 
     return [Ucs.from_dict(cat) for cat in cats]
 
+
 class InferenceContext:
     """
     Maintains caches and resources for UCS category inference.
@@ -108,9 +111,8 @@ class InferenceContext:
         :raises: StopIterator if CatId is not on the schedule 
         """
         i = (
-                (x.category, x.subcategory, x.explanations) \
+            (x.category, x.subcategory, x.explanations)
             for x in self.catlist if x.catid == catid
         )
 
         return next(i)
-

ucsinfer/util.py

@@ -6,6 +6,7 @@ from re import match
 
 from .inference import Ucs
 
+
 def ffmpeg_description(path: str) -> Optional[str]:
     result = subprocess.run(['ffprobe', '-show_format', '-of',
                              'json', path], capture_output=True)
@@ -65,12 +66,14 @@ def build_ucs(components: UcsNameComponents, extension: str) -> str:
     """
     Build a UCS filename
     """
-    assert components.validate(), "UcsNameComponents contains invalid characters"
+    assert components.validate(), \
+            "UcsNameComponents contains invalid characters"
 
     return ""
 
 
-def parse_ucs(rootname: str, catid_list: list[str]) -> Optional[UcsNameComponents]:
+def parse_ucs(rootname: str, 
+              catid_list: list[str]) -> Optional[UcsNameComponents]:
     """
     Parse the UCS components from a file name root.
 
@@ -79,11 +82,12 @@ def parse_ucs(rootname: str, catid_list: list[str]) -> Optional[UcsNameComponent
     :returns: the components, or `None` if the filename is not in UCS format
     """
 
-    regexp1 = r"^(?P<CatID>[A-z]+)(-(?P<UserCat>[^_]+))?_((?P<VendorCat>[^-]+)-)?(?P<FXName>[^_]+)"
+    regexp1 = r"^(?P<CatID>[A-z]+)(-(?P<UserCat>[^_]+))?_"
+    regexp2 = r"((?P<VendorCat>[^-]+)-)?(?P<FXName>[^_]+)"
+    regexp3 = r"(_(?P<CreatorID>[^_]+)(_(?P<SourceID>[^_]+)"
+    regexp4 = r"(_(?P<UserData>[^.]+))?)?)?"
 
-    regexp2 = r"(_(?P<CreatorID>[^_]+)(_(?P<SourceID>[^_]+)(_(?P<UserData>[^.]+))?)?)?"
-    
-    regexp = regexp1 + regexp2 
+    regexp = regexp1 + regexp2 + regexp3 + regexp4
 
     matches = match(regexp, rootname)