Update src/utils.py

src/utils.py

@@ -1,10 +1,53 @@
 # Importing the requirements
 from PIL import Image
 from decord import VideoReader, cpu
+import re
 
 
 # Maximum number of frames to use
-MAX_NUM_FRAMES = 64  # If CUDA OOM, set a smaller number
+MAX_NUM_FRAMES = 25  # If CUDA OOM, set a smaller number
+
+
+def parse_string(string, tags):
+    """
+    Extracts the content between the specified HTML tags from the given string.
+
+    Args:
+        string (str): The input string to search for the tag content.
+        tags (list): A list of HTML tags to search for.
+
+    Returns:
+        dict: A dictionary with tags as keys and lists of content as values.
+
+     Example:
+        >>> parse_string("<code>Hello, World!</code><note>Important</note>", ["code", "note"])
+        {'code': ['Hello, World!'], 'note': ['Important']}
+    """
+    results = {}
+    
+    for tag in tags:
+        pattern = rf"<{tag}>(.*?)</{tag}>"
+        matches = re.findall(pattern, string, re.DOTALL)
+        results[tag] = matches if matches else None
+
+    return results
+
+def parse_annotations(annotations_list):
+    """
+    Converts a list of annotations into a dictionary of key-value pairs.
+
+    Args:
+        annotations_list (list): A list of annotations in the format 'key: value'.
+
+    Returns:
+        dict: A dictionary with annotation keys and values.
+    """
+    annotations_dict = {}
+    for annotation in annotations_list:
+        key, value = annotation.split(': ')
+        annotations_dict[key] = int(value) 
+    return annotations_dict
+
 
 
 def encode_video(video_path):