feat: init

core/subtitles.py

@@ -0,0 +1,49 @@
+import os
+import re
+from typing import List
+
+from .types import SubtitleEntry
+
+
+class SubtitleHandler:
+    @staticmethod
+    def parse_time(t):
+        h, m, s, ms = int(t[:2]), int(t[3:5]), int(t[6:8]), int(t[9:])
+        return h * 3600000 + m * 60000 + s * 1000 + ms
+
+    @staticmethod
+    def format_time(ms):
+        ms = max(0, ms)
+        h, r = divmod(ms, 3600000)
+        m, r = divmod(r, 60000)
+        s, ms = divmod(r, 1000)
+        return f"{h:02}:{m:02}:{s:02},{ms:03}"
+
+    @staticmethod
+    def parse_srt(filepath: str) -> List[SubtitleEntry]:
+        if not os.path.exists(filepath): return []
+        encodings = ['utf-8-sig', 'utf-8', 'latin-1']
+        content = ""
+        for enc in encodings:
+            try:
+                with open(filepath, 'r', encoding=enc) as f:
+                    content = f.read()
+                break
+            except UnicodeDecodeError:
+                continue
+
+        entries = []
+        pattern = re.compile(r'(\d+)\n(\d{2}:\d{2}:\d{2},\d{3}) --> (\d{2}:\d{2}:\d{2},\d{3})\n((?:(?!\r?\n\r?\n).)*)',
+                             re.DOTALL)
+        for match in pattern.finditer(content):
+            start = SubtitleHandler.parse_time(match.group(2))
+            end = SubtitleHandler.parse_time(match.group(3))
+            entries.append(SubtitleEntry(int(match.group(1)), start, end, match.group(4).strip()))
+        return entries
+
+    @staticmethod
+    def write_srt(filepath: str, entries: List[SubtitleEntry]):
+        with open(filepath, 'w', encoding='utf-8') as f:
+            for entry in entries:
+                f.write(
+                    f"{entry.index}\n{SubtitleHandler.format_time(entry.start_ms)} --> {SubtitleHandler.format_time(entry.end_ms)}\n{entry.raw_text}\n\n")