cuekit and cuenorm: three subtitle formats, one cue stream

crates/cuekit/src/dedup.rs

@@ -0,0 +1,66 @@
+//! Collapsing the repetition automatic captioning produces.
+
+use crate::cue::Cue;
+
+/// Merge consecutive cues whose text is identical, keeping the earliest start
+/// and the latest end.
+///
+/// Automatic captioning emits a rolling window: the same line appears in cue
+/// after cue as the window slides, so a ten-minute stretch of speech can
+/// arrive as three times as many cues as there are sentences. Indexed as they
+/// come, every one of those is a separate hit for the same words at almost
+/// the same timestamp, which buries everything else in a result list.
+pub fn merge_repeats(cues: &[Cue]) -> Vec<Cue> {
+    let mut merged: Vec<Cue> = Vec::with_capacity(cues.len());
+    for cue in cues {
+        match merged.last_mut() {
+            Some(previous) if previous.text == cue.text => {
+                previous.end = previous.end.max(cue.end);
+            }
+            _ => merged.push(cue.clone()),
+        }
+    }
+    merged
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn a_repeated_line_becomes_one_cue_spanning_both() {
+        let cues = [
+            Cue::new(0.0, 2.0, "the mill stood"),
+            Cue::new(1.0, 3.0, "the mill stood"),
+            Cue::new(3.0, 4.0, "at the northern end"),
+        ];
+        let merged = merge_repeats(&cues);
+        assert_eq!(merged.len(), 2);
+        assert_eq!(merged[0].start, 0.0);
+        assert_eq!(merged[0].end, 3.0);
+        assert_eq!(merged[1].text, "at the northern end");
+    }
+
+    #[test]
+    fn a_line_that_comes_back_later_is_kept_separately() {
+        let cues = [
+            Cue::new(0.0, 1.0, "yes"),
+            Cue::new(1.0, 2.0, "no"),
+            Cue::new(2.0, 3.0, "yes"),
+        ];
+        assert_eq!(merge_repeats(&cues).len(), 3);
+    }
+
+    #[test]
+    fn an_end_that_goes_backwards_does_not_shorten_the_merged_cue() {
+        let cues = [Cue::new(0.0, 9.0, "x"), Cue::new(1.0, 2.0, "x")];
+        let merged = merge_repeats(&cues);
+        assert_eq!(merged.len(), 1);
+        assert_eq!(merged[0].end, 9.0);
+    }
+
+    #[test]
+    fn nothing_in_nothing_out() {
+        assert!(merge_repeats(&[]).is_empty());
+    }
+}