video-master-adapt/batch_match_fast.py

#!/usr/bin/env python3
"""
Fast batch matching without AKAZE - uses original perceptual hash only
"""
import sys
from pathlib import Path
sys.path.insert(0, str(Path(__file__).parent / "src"))

from video_matcher.matcher import VideoMatcher
from rich.console import Console
from rich.progress import Progress, SpinnerColumn, TextColumn, BarColumn
from datetime import datetime

console = Console()

if len(sys.argv) < 2:
    console.print("[red]Usage: python batch_match_fast.py <folder_path> [output.html][/red]")
    sys.exit(1)

folder_path = Path(sys.argv[1])
output_file = sys.argv[2] if len(sys.argv) > 2 else None

if not folder_path.exists():
    console.print(f"[red]Folder not found: {folder_path}[/red]")
    sys.exit(1)

# Find all video files
VIDEO_EXTENSIONS = {'.mp4', '.mov', '.avi', '.mkv', '.webm', '.flv', '.wmv', '.m4v'}
video_files = []
for ext in VIDEO_EXTENSIONS:
    video_files.extend(folder_path.glob(f"*{ext}"))
    video_files.extend(folder_path.glob(f"*{ext.upper()}"))

if not video_files:
    console.print(f"[yellow]No video files found in {folder_path}[/yellow]")
    sys.exit(1)

console.print(f"\n[bold]Found {len(video_files)} video file(s) to process[/bold]\n")

# Initialize matcher WITHOUT AKAZE (faster)
console.print("[cyan]Using fast mode (perceptual hash only)[/cyan]")
matcher = VideoMatcher(
    use_akaze=False,  # Disable AKAZE
    use_metadata_filter=True,  # Keep metadata filtering
    enable_ai_vision=True  # Keep AI Vision
)

# Check if we have masters
masters = matcher.list_masters()
if not masters:
    console.print("[red]✗[/red] No master videos found in library.")
    console.print("Use 'python cli.py add-master' to add masters first.")
    sys.exit(1)

console.print(f"[cyan]Comparing against {len(masters)} master(s)...[/cyan]\n")

# Process each video
results = []

with Progress(
    SpinnerColumn(),
    TextColumn("[progress.description]{task.description}"),
    BarColumn(),
    TextColumn("[progress.percentage]{task.percentage:>3.0f}%"),
    console=console
) as progress:

    task = progress.add_task("[cyan]Processing adaptations...", total=len(video_files))

    for video_file in video_files:
        progress.update(task, description=f"[cyan]Processing {video_file.name}...")

        try:
            matches = matcher.match_adaptation(str(video_file))

            results.append({
                'adaptation_name': video_file.name,
                'adaptation_path': str(video_file),
                'matches': matches,
                'error': None
            })

        except Exception as e:
            console.print(f"[red]✗[/red] Error processing {video_file.name}: {e}")
            results.append({
                'adaptation_name': video_file.name,
                'adaptation_path': str(video_file),
                'matches': [],
                'error': str(e)
            })

        progress.advance(task)

# Generate output filename if not specified
if output_file is None:
    timestamp = datetime.now().strftime('%Y%m%d_%H%M%S')
    output_file = f"matching_report_fast_{timestamp}.html"

output_path = Path(output_file)

# Generate HTML report
console.print(f"\n[cyan]Generating HTML report...[/cyan]")

# Import the generation function from batch_match
sys.path.insert(0, str(Path(__file__).parent))
from batch_match import generate_html_report

generate_html_report(results, output_path, str(folder_path))

# Summary
console.print(f"\n[bold green]✓ Report generated successfully![/bold green]")
console.print(f"\n[bold]Summary:[/bold]")
console.print(f"  Total adaptations: {len(results)}")
console.print(f"  Matched: {sum(1 for r in results if r['matches'])}")
console.print(f"  No matches: {sum(1 for r in results if not r['matches'])}")
console.print(f"  Total master matches: {sum(len(r['matches']) for r in results)}")
console.print(f"\n[bold cyan]📄 Report saved to:[/bold cyan] {output_path.absolute()}")
console.print(f"\n[dim]Open in browser: file://{output_path.absolute()}[/dim]")