Merge pull request #5893 from avalonmediasystem/relax_transcript_parser

Improve handling of improperly formatted time cues in Transcript Parser
avalonmediasystem · Jul 2, 2024 · dbb0d40 · dbb0d40
2 parents 809be00 + eee3b1c
commit dbb0d40
Showing 1 changed file with 2 additions and 1 deletion.
diff --git a/lib/avalon/transcript_parser.rb b/lib/avalon/transcript_parser.rb
@@ -48,7 +48,8 @@ def normalized_text
 
     # Separate time cue and text content from a single line of timed text to facilitate result formatting of transcript searches.
     def self.extract_single_time_cue(timed_text)
-      split_text = timed_text.match(/(\d{2,}*:?\d{2}:\d{2}\.?,?\d{3} --> \d{2,}*:?\d{2}:\d{2}\.?,?\d{3})(.*)/)
+      split_text = timed_text.match(/(\d{0,}:?\d{2}:\d{2}\.?,?\d{3} --> \d{0,}:?\d{2}:\d{2}\.?,?\d{3})(.*)/)
+      return [nil, nil] if split_text.blank?
       time_cue = split_text[1].sub(',', '.').gsub(/\s-->\s/, ',')
       text = split_text[2].strip
       [time_cue, text]