feat: add migrations, test scripts, and utility tools

- Add database migrations (006-028) for face recognition, identity, file_uuid - Add test scripts for ASR, face, search, processing - Add portal frontend (Tauri) - Add config, benchmark, and monitoring utilities - Add model checkpoints and pretrained model references
2026-04-30 15:11:53 +08:00
parent 4d75b2e251
commit b54c2def30
192 changed files with 46721 additions and 0 deletions
--- a/test_debug_hang.py
+++ b/test_debug_hang.py
@@ -0,0 +1,142 @@
+#!/usr/bin/env python3
+"""Debug the hang issue in ASR processor."""
+
+import sys
+import os
+import subprocess
+import tempfile
+import time
+import signal
+
+# Test one of the large files
+test_video = "../test_video/1636719d-c31f-78ac-f1dd-8ab0b0b36c66.mov"
+if not os.path.exists(test_video):
+    test_video = "../test_video/Old_Time_Movie_Show_-_Charade_1963.HD.mov"
+
+print(f"Testing: {test_video}")
+print(f"Size: {os.path.getsize(test_video) / (1024**3):.2f} GB")
+
+# Create temp output
+temp_dir = tempfile.mkdtemp(prefix="asr_debug_")
+output_path = os.path.join(temp_dir, "output.json")
+
+# Use debug version
+cmd = [
+    "/opt/homebrew/bin/python3.11",
+    "scripts/asr_processor_debug.py",
+    test_video,
+    output_path,
+    "--uuid",
+    "debug_test",
+]
+
+print(f"Command: {' '.join(cmd)}")
+print(f"Temp dir: {temp_dir}")
+
+# Run with timeout
+timeout = 600  # 10 minutes for debugging
+start = time.time()
+
+# Use Popen to capture real-time output
+proc = subprocess.Popen(
+    cmd,
+    stdout=subprocess.PIPE,
+    stderr=subprocess.PIPE,
+    text=True,
+    bufsize=1,  # Line buffered
+)
+
+# Read output in real-time
+stdout_lines = []
+stderr_lines = []
+
+
+def read_output():
+    """Read output from process in real-time."""
+    import select
+
+    # Set pipes to non-blocking
+    import fcntl
+    import os
+
+    fcntl.fcntl(proc.stdout, fcntl.F_SETFL, os.O_NONBLOCK)
+    fcntl.fcntl(proc.stderr, fcntl.F_SETFL, os.O_NONBLOCK)
+
+    while True:
+        # Check if process has finished
+        if proc.poll() is not None:
+            break
+
+        # Read from stdout
+        try:
+            line = proc.stdout.read()
+            if line:
+                stdout_lines.append(line)
+                sys.stdout.write(f"[STDOUT] {line}")
+                sys.stdout.flush()
+        except:
+            pass
+
+        # Read from stderr
+        try:
+            line = proc.stderr.read()
+            if line:
+                stderr_lines.append(line)
+                sys.stderr.write(f"[STDERR] {line}")
+                sys.stderr.flush()
+        except:
+            pass
+
+        time.sleep(0.1)
+
+
+# Start reading output
+import threading
+
+reader_thread = threading.Thread(target=read_output)
+reader_thread.daemon = True
+reader_thread.start()
+
+# Wait for process to complete or timeout
+try:
+    proc.wait(timeout=timeout)
+    elapsed = time.time() - start
+    success = proc.returncode == 0
+    timeout_hit = False
+except subprocess.TimeoutExpired:
+    elapsed = time.time() - start
+    success = False
+    timeout_hit = True
+    print(f"\nProcess timed out after {timeout}s, killing...")
+    proc.kill()
+    proc.wait()
+
+print(f"\nElapsed: {elapsed:.1f}s")
+print(f"Success: {success}")
+print(f"Timeout: {timeout_hit}")
+print(f"Return code: {proc.returncode}")
+
+# Check output
+if os.path.exists(output_path):
+    print(f"Output file exists: {output_path}")
+    import json
+
+    try:
+        with open(output_path, "r") as f:
+            data = json.load(f)
+        print(f"Segments: {len(data.get('segments', []))}")
+    except Exception as e:
+        print(f"Error reading output: {e}")
+else:
+    print("Output file does not exist")
+
+# Save logs
+log_file = os.path.join(temp_dir, "debug_log.txt")
+with open(log_file, "w") as f:
+    f.write("=== STDOUT ===\n")
+    f.write("".join(stdout_lines))
+    f.write("\n=== STDERR ===\n")
+    f.write("".join(stderr_lines))
+
+print(f"\nLogs saved to: {log_file}")
+print(f"Temp directory preserved: {temp_dir}")