Now retrieve all the syllabs and their duration from the ass file

karaUtils.py

@@ -11,18 +11,22 @@ with open(FILE, 'r') as f:
     CONTENT = f.read()
 
 LINES_KARA = re.compile(r"Comment:.*(\d+:\d{2}:\d{2}.\d{2}),(\d+:\d{2}:\d{2}.\d{2}),.*,karaoke,(.*)\n");
-print(LINES_KARA)
+
+RGX_TAGS = re.compile(r"\{\\k(\d+)\}([^\{\n\r]*)")
 
 LINES = {
-    'start': set(),
-    'end': set(),
-    'text': set()
+    'start': [],
+    'end': [],
+    'text': []
 }
 
 for line in LINES_KARA.findall(CONTENT):
-    print(line)
-    LINES['start']  = line[0]
-    LINES['end']    = line[1]
-    LINES['text']   = line[2]
+    LINES['start'].append(line[0])
+    LINES['end'].append(line[1])
+    text = []
+    for couple in RGX_TAGS.findall(line[2]):
+        text.append((couple[0], couple[1]))
+    LINES['text'].append(text)
 
-print(LINES)
+for i in range (0, len(LINES['start'])):
+    print(LINES['start'][i], LINES['end'][i], LINES['text'][i])