from __future__ import annotations from dataclasses import dataclass import re TIME_RE = re.compile( r"(?P\d{1,2}:\d{2}:\d{2}[\.,]\d{3})\s*-->\s*" r"(?P\d{1,2}:\d{2}:\d{2}[\.,]\d{3})" ) @dataclass class SubtitleCue: start: str end: str text: str @dataclass class CleanSubtitleResult: cues: list[SubtitleCue] original_count: int cleaned_count: int duplicate_count: int empty_count: int def normalize_time(value: str) -> str: return value.replace(",", ".") def has_visible_text(rows: list[str]) -> bool: text = "".join(rows).replace(" ", "").replace("\u00a0", "").strip() return bool(text) def parse_subtitle(content: str) -> list[SubtitleCue]: cues: list[SubtitleCue] = [] current_time: tuple[str, str] | None = None text_rows: list[str] = [] def flush() -> None: nonlocal current_time, text_rows if current_time and text_rows: cues.append(SubtitleCue(current_time[0], current_time[1], "\n".join(text_rows).strip())) current_time = None text_rows = [] for raw_line in str(content or "").replace("\r", "").replace("\ufeff", "").split("\n"): row = raw_line.strip() if not row: flush() continue if row.upper().startswith("WEBVTT") or row.isdigit(): continue match = TIME_RE.search(row) if match: flush() current_time = (normalize_time(match.group("start")), normalize_time(match.group("end"))) continue if current_time: text_rows.append(row) flush() return cues def clean_english_subtitle(content: str) -> CleanSubtitleResult: parsed = parse_subtitle(content) cleaned: list[SubtitleCue] = [] seen: set[tuple[str, str, str]] = set() duplicate_count = 0 empty_count = 0 for cue in parsed: rows = cue.text.splitlines() if not has_visible_text(rows): empty_count += 1 continue key = (cue.start, cue.end, cue.text.strip()) if key in seen: duplicate_count += 1 continue seen.add(key) cleaned.append(cue) return CleanSubtitleResult( cues=cleaned, original_count=len(parsed), cleaned_count=len(cleaned), duplicate_count=duplicate_count, empty_count=empty_count, ) def build_vtt(cues: list[SubtitleCue] | list[dict[str, str]]) -> str: blocks: list[str] = [] for index, cue in enumerate(cues, 1): start = cue.start if isinstance(cue, SubtitleCue) else cue["start"] end = cue.end if isinstance(cue, SubtitleCue) else cue["end"] text = cue.text if isinstance(cue, SubtitleCue) else cue["text"] blocks.append(f"{index}\n{start} --> {end}\n{text.strip()}") return "WEBVTT\n\n" + "\n\n".join(blocks).strip() + "\n" def parse_timestamp(value: str) -> float: clean = str(value).replace(",", ".").split()[0] parts = clean.split(":") try: numbers = [float(part) for part in parts] except ValueError: return 0.0 if len(numbers) == 3: return numbers[0] * 3600 + numbers[1] * 60 + numbers[2] if len(numbers) == 2: return numbers[0] * 60 + numbers[1] return numbers[0] if numbers else 0.0 def format_timestamp(seconds: float) -> str: total_milliseconds = max(0, round((seconds or 0) * 1000)) hours = total_milliseconds // 3_600_000 minutes = (total_milliseconds % 3_600_000) // 60_000 whole_seconds = (total_milliseconds % 60_000) // 1000 milliseconds = total_milliseconds % 1000 return f"{hours:02d}:{minutes:02d}:{whole_seconds:02d}.{milliseconds:03d}"