magnus919_agent-skills/epub/scripts/epub-batch

#!/usr/bin/env python3
"""epub-batch — Process multiple EPUB files in batch.

Usage:
  epub-batch extract-text <glob> --output DIR [--json] [--dry-run]
  epub-batch validate <glob> [--json] [--dry-run]
  epub-batch metadata <glob> --set-author "Name" [--set-title "Title"] [--output-dir DIR] [--json] [--dry-run]
  epub-batch info <glob> [--json] [--dry-run]

Examples:
  epub-batch extract-text "books/*.epub" --output texts/
  epub-batch validate "books/*.epub" --json
  epub-batch metadata "books/*.epub" --set-author "Fixed Author" --output-dir fixed/

Dependencies: EbookLib (pip install EbookLib)
"""

import argparse
import glob
import json
import os
import subprocess
import sys
import warnings

warnings.filterwarnings("ignore")

DRY_RUN = False
JSON_OUTPUT = False
SCRIPT_DIR = os.path.dirname(os.path.abspath(__file__))


def die(msg):
    print(f"Error: {msg}", file=sys.stderr)
    sys.exit(1)


def emit(json_data, text=""):
    if JSON_OUTPUT:
        print(json.dumps(json_data, indent=2, default=str))
    else:
        print(text)


def find_epubs(pattern):
    """Expand glob pattern to list of EPUB files."""
    files = sorted(glob.glob(pattern, recursive=True))
    if not files:
        die(f"No EPUB files found matching: {pattern}")
    return [f for f in files if f.lower().endswith(".epub")]


def run_script(script_name, *args_list):
    """Run a sibling script from the scripts/ directory."""
    script_path = os.path.join(SCRIPT_DIR, script_name)
    cmd = [sys.executable, script_path] + list(args_list)
    result = subprocess.run(cmd, capture_output=True, text=True, timeout=300)
    return result


def main():
    global DRY_RUN, JSON_OUTPUT

    parser = argparse.ArgumentParser(
        description="Process multiple EPUB files in batch.",
        epilog="Examples:\n  epub-batch extract-text 'books/*.epub' --output texts/\n  epub-batch validate 'books/*.epub' --json")
    sub = parser.add_subparsers(dest="command", help="Batch operation")

    # extract-text
    p = sub.add_parser("extract-text", help="Extract text from all EPUBs")
    p.add_argument("pattern", help="Glob pattern for EPUB files")
    p.add_argument("--output", "-o", required=True, help="Output directory")
    p.add_argument("--json", action="store_true")
    p.add_argument("--dry-run", "-n", action="store_true")

    # validate
    p = sub.add_parser("validate", help="Validate all EPUBs")
    p.add_argument("pattern", help="Glob pattern for EPUB files")
    p.add_argument("--json", action="store_true")
    p.add_argument("--dry-run", "-n", action="store_true")

    # metadata
    p = sub.add_parser("metadata", help="Batch update metadata")
    p.add_argument("pattern", help="Glob pattern for EPUB files")
    p.add_argument("--set-author")
    p.add_argument("--set-title")
    p.add_argument("--output-dir", "-o", required=True, help="Output directory for updated EPUBs")
    p.add_argument("--json", action="store_true")
    p.add_argument("--dry-run", "-n", action="store_true")

    # info
    p = sub.add_parser("info", help="Dump info for all EPUBs")
    p.add_argument("pattern", help="Glob pattern for EPUB files")
    p.add_argument("--json", action="store_true")
    p.add_argument("--dry-run", "-n", action="store_true")

    args = parser.parse_args()

    if not args.command:
        parser.print_help()
        sys.exit(1)

    JSON_OUTPUT = getattr(args, "json", False)
    DRY_RUN = getattr(args, "dry_run", False)

    if DRY_RUN:
        emit({"status": "dry_run", "command": args.command, "pattern": args.pattern,
              "files_found": "unknown (dry-run)"},
             f"[dry-run] Would process EPUBs matching: {args.pattern}")
        return

    epub_files = find_epubs(args.pattern)

    results = []
    for i, epub_path in enumerate(epub_files):
        print(f"[{i+1}/{len(epub_files)}] {os.path.basename(epub_path)}", file=sys.stderr, flush=True)

        if args.command == "extract-text":
            base = os.path.splitext(os.path.basename(epub_path))[0]
            out_file = os.path.join(args.output, f"{base}.txt")
            os.makedirs(args.output, exist_ok=True)
            r = run_script("epub-text", epub_path, "--output", out_file)
            results.append({"file": epub_path, "output": out_file, "success": r.returncode == 0})

        elif args.command == "validate":
            r = run_script("epub-validate", epub_path, "--json")
            try:
                vdata = json.loads(r.stdout)
                results.append({"file": epub_path, "status": vdata.get("status", "unknown"),
                               "errors": vdata.get("errors", 0)})
            except json.JSONDecodeError:
                results.append({"file": epub_path, "status": "error", "errors": -1})

        elif args.command == "metadata":
            os.makedirs(args.output_dir, exist_ok=True)
            out_epub = os.path.join(args.output_dir, os.path.basename(epub_path))
            extra = []
            if args.set_author:
                extra += ["--author", args.set_author]
            if args.set_title:
                extra += ["--title", args.set_title]
            r = run_script("epub-edit", "metadata", epub_path, *extra, "--output", out_epub)
            results.append({"file": epub_path, "output": out_epub, "success": r.returncode == 0})

        elif args.command == "info":
            r = run_script("epub-info", epub_path, "--json")
            try:
                idata = json.loads(r.stdout)
                results.append({"file": epub_path, "title": idata.get("metadata", {}).get("title", ""),
                               "manifest_count": idata.get("manifest_count", 0)})
            except json.JSONDecodeError:
                results.append({"file": epub_path, "error": "parse failed"})

    # Summary
    success = sum(1 for r in results if r.get("success", True))
    summary = {"command": args.command, "total": len(epub_files), "results": results}
    emit(summary, f"\n{success}/{len(epub_files)} processed successfully")


if __name__ == "__main__":
    main()