Add encoding='utf-8' to all subprocess.run calls with text=True

Co-authored-by: meizhong986 <148393222+meizhong986@users.noreply.github.com>

Author: Copilot

whisperjav/main.py

@@ -430,6 +430,7 @@ def process_files_sync(media_files: List[Dict], args: argparse.Namespace, resolv
                                 cmd,
                                 capture_output=True,
                                 text=True,
+                                encoding='utf-8',
                                 timeout=600
                             )
                         else:
@@ -439,6 +440,7 @@ def process_files_sync(media_files: List[Dict], args: argparse.Namespace, resolv
                                 stdout=subprocess.PIPE,
                                 stderr=None,
                                 text=True,
+                                encoding='utf-8',
                                 timeout=600
                             )
 
@@ -595,6 +597,7 @@ def progress_callback(message: Dict):
                                         cmd,
                                         capture_output=True,
                                         text=True,
+                                        encoding='utf-8',
                                         timeout=600
                                     )
                                 else:
@@ -604,6 +607,7 @@ def progress_callback(message: Dict):
                                         stdout=subprocess.PIPE,
                                         stderr=None,
                                         text=True,
+                                        encoding='utf-8',
                                         timeout=600
                                     )
 

whisperjav/modules/audio_extraction.py

@@ -61,7 +61,7 @@ def extract(self, input_file: Union[str, Path], output_path: Union[str, Path]) -
             result = subprocess.run(cmd, 
                                   capture_output=True, 
                                   text=True, 
-                                  check=True)
+                                  encoding='utf-8', check=True)
 
             # Get duration
             duration = self._get_audio_duration(output_path)
@@ -83,7 +83,7 @@ def _get_audio_duration(self, audio_file: Path) -> float:
             "-"
         ]
 
-        result = subprocess.run(cmd, capture_output=True, text=True)
+        result = subprocess.run(cmd, capture_output=True, text=True, encoding='utf-8')
 
         # Parse duration from FFmpeg output
         for line in result.stderr.split('\n'):

whisperjav/modules/media_discovery.py

@@ -143,7 +143,7 @@ def _get_ffprobe_info(self, file_path: str) -> Optional[Dict]:
                 file_path
             ]
 
-            result = subprocess.run(cmd, capture_output=True, text=True, check=True)
+            result = subprocess.run(cmd, capture_output=True, text=True, encoding='utf-8', check=True)
             data = json.loads(result.stdout)
 
             info = {}

whisperjav/utils/preflight_check.py

@@ -247,6 +247,7 @@ def _check_ffmpeg(self):
                     ['ffmpeg', '-version'],
                     capture_output=True,
                     text=True,
+                    encoding='utf-8',
                     timeout=5
                 )
                 version_line = result.stdout.split('\n')[0]