fix: preserve numeric-only subtitle dialogue after skipped cues

backend/services/srt_parser.py

@@ -125,10 +125,11 @@ def parse_srt(content: str) -> SrtParseResult:
                 marker_lines.pop()
             marker = marker_lines[-1].strip(" \t") if marker_lines else ""
             numeric = bool(marker) and marker.isascii() and marker.isdecimal()
-            separated = len(marker_lines) > 1 and not marker_lines[-2].strip()
+            separated = len(marker_lines) > 2 and not marker_lines[-2].strip()
             expected_index = cue_index + 1 if cue_index is not None else i + 2
             expected = marker.lstrip("0") == str(expected_index)
-            if numeric and expected and (cue_index is not None or separated):
+            has_dialogue = any(line.strip() for line in marker_lines[:-1])
+            if numeric and expected and (has_dialogue or separated) and (cue_index is not None or separated):
                 body = "\n".join(marker_lines[:-1])
                 next_index = expected_index
         cue_index = next_index

tests/test_srt_parser.py

@@ -365,3 +365,9 @@ def test_skipped_cue_still_advances_numbering_state():
     result = parse_srt(text)
     assert result.skipped_cues == 1
     assert [cue["text"] for cue in result.segments] == ["First", "Third", "Fourth"]
+
+
+
+def test_numeric_only_cue_after_invalid_cue_is_not_discarded():
+    text = "1\n00:00:01,000 --> 00:00:02,000\nFirst\n\n2\n00:00:04,000 --> 00:00:03,000\nInvalid\n\n3\n00:00:05,000 --> 00:00:06,000\n4\n00:00:07,000 --> 00:00:08,000\nLast"
+    assert [cue["text"] for cue in parse_srt(text).segments] == ["First", "4", "Last"]