feat: 新增 Job Worker 系統與 API 文檔全面更新

scripts/asr_processor.py

@@ -3,17 +3,65 @@ import sys
 import json
 import os
 import argparse
+import signal
+import subprocess
 from faster_whisper import WhisperModel
 
 sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
 from redis_publisher import RedisPublisher
 
 
+def signal_handler(signum, frame):
+    print(f"ASR: Received signal {signum}, exiting...")
+    sys.exit(1)
+
+
+def has_audio_stream(video_path):
+    """Check if video file has audio stream using ffprobe."""
+    try:
+        cmd = [
+            "ffprobe",
+            "-v",
+            "error",
+            "-select_streams",
+            "a",
+            "-show_entries",
+            "stream=codec_type",
+            "-of",
+            "csv=p=0",
+            video_path,
+        ]
+        result = subprocess.run(cmd, capture_output=True, text=True, check=True)
+        return bool(result.stdout.strip())
+    except subprocess.CalledProcessError:
+        return False
+    except FileNotFoundError:
+        print("WARNING: ffprobe not found, assuming audio exists")
+        return True
+
+
 def run_asr(video_path, output_path, uuid: str = ""):
+    # Set up signal handlers
+    signal.signal(signal.SIGTERM, signal_handler)
+    signal.signal(signal.SIGINT, signal_handler)
+
     publisher = RedisPublisher(uuid) if uuid else None
     if publisher:
         publisher.info("asr", "ASR_START")
 
+    # Check for audio stream
+    if not has_audio_stream(video_path):
+        if publisher:
+            publisher.info("asr", "No audio stream detected, skipping transcription")
+        output = {"language": "", "language_probability": 0.0, "segments": []}
+        with open(output_path, "w") as f:
+            json.dump(output, f, indent=2)
+        if publisher:
+            publisher.complete("asr", "0 segments (no audio)")
+        sys.stderr.write("ASR: No audio stream, skipping transcription\n")
+        sys.stderr.flush()
+        sys.exit(0)
+
     if publisher:
         publisher.info("asr", "Loading Whisper model...")
 
@@ -53,6 +101,12 @@ def run_asr(video_path, output_path, uuid: str = ""):
     if publisher:
         publisher.complete("asr", f"{len(results)} segments")
 
+    sys.stderr.write(
+        f"ASR: Transcription complete, {len(results)} segments written to {output_path}\n"
+    )
+    sys.stderr.flush()
+    sys.exit(0)
+
 
 if __name__ == "__main__":
     parser = argparse.ArgumentParser(description="ASR Transcription")

scripts/ocr_processor.py

@@ -8,14 +8,24 @@ import sys
 import json
 import argparse
 import os
+import signal
 
 sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
 from redis_publisher import RedisPublisher
 
 
+def signal_handler(signum, frame):
+    print(f"OCR: Received signal {signum}, exiting...")
+    sys.exit(1)
+
+
 def process_ocr(video_path: str, output_path: str, uuid: str = ""):
     """Process video for OCR using EasyOCR"""
 
+    # Set up signal handlers
+    signal.signal(signal.SIGTERM, signal_handler)
+    signal.signal(signal.SIGINT, signal_handler)
+
     publisher = RedisPublisher(uuid) if uuid else None
     if publisher:
         publisher.info("ocr", "OCR_START")

scripts/pose_processor.py

@@ -8,14 +8,24 @@ import sys
 import json
 import argparse
 import os
+import signal
 
 sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
 from redis_publisher import RedisPublisher
 
 
+def signal_handler(signum, frame):
+    print(f"POSE: Received signal {signum}, exiting...")
+    sys.exit(1)
+
+
 def process_pose(video_path: str, output_path: str, uuid: str = ""):
     """Process video for pose estimation using YOLOv8 Pose"""
 
+    # Set up signal handlers
+    signal.signal(signal.SIGTERM, signal_handler)
+    signal.signal(signal.SIGINT, signal_handler)
+
     publisher = RedisPublisher(uuid) if uuid else None
     if publisher:
         publisher.info("pose", "POSE_START")