misc / tRIP - beginnings/work in progress

lyric_search/utils.py

@@ -111,8 +111,19 @@ class DataUtils:
     """
 
     def __init__(self) -> None:
-        self.lrc_regex = regex.compile(
-            r"\[([0-9]{2}:[0-9]{2})\.[0-9]{1,3}\](\s(.*)){0,}"
+        self.lrc_regex = regex.compile(         # capture mm:ss and optional .xxx, then the lyric text
+            r"""
+            \[                 # literal “[”
+            (                # 1st (and only) capture group:
+                [0-9]{2}       #   two-digit minutes
+                :[0-9]{2}      #   colon + two-digit seconds
+                (?:\.[0-9]{1,3})?  #   optional decimal part, e.g. .123
+            )
+            \]                 # literal “]”
+            \s*                # optional whitespace
+            (.*)               # capture the rest of the line as words
+            """,
+            regex.VERBOSE,
         )
         self.scrub_regex_1: Pattern = regex.compile(r"(\[.*?\])(\s){0,}(\:){0,1}")
         self.scrub_regex_2: Pattern = regex.compile(
@@ -161,7 +172,7 @@ class DataUtils:
             )
             _timetag = reg_helper[0]
             if not reg_helper[1].strip():
-                _words = "♪"
+                continue
             else:
                 _words = reg_helper[1].strip()
             lrc_out.append(