from __future__ import annotations

import sys
from collections import Counter
from pathlib import Path

from rich import print


PROJECT_ROOT = Path(__file__).resolve().parents[2]

if str(PROJECT_ROOT) not in sys.path:
    sys.path.insert(0, str(PROJECT_ROOT))


from tools.rag.common import DOCUMENTS_FILE, PAGES_ROOT, ZPWIKI_ROOT, load_zpwiki_page, write_json


def scan_pages(*, wiki_root: Path | None = None, output: Path | None = None) -> list[dict]:
    pages = wiki_root / 'pages' if wiki_root is not None else PAGES_ROOT
    if not pages.exists():
        raise SystemExit(f"Neexistuje priečinok: {pages}")

    documents = []
    metadata_keys = Counter()
    categories = Counter()
    tags = Counter()
    authors = Counter()

    for file_path in sorted(pages.glob("**/README.md")):
        page = load_zpwiki_page(file_path, wiki_root=wiki_root)
        content = page.pop("content", "")

        for key in page["metadata"]:
            metadata_keys[key] += 1

        for category in page["categories"]:
            categories[category] += 1

        for tag in page["tags"]:
            tags[tag] += 1

        if page.get("author"):
            authors[str(page["author"])] += 1

        documents.append(
            {
                **page,
                "content_preview": content[:500],
                "content_length": len(content),
            }
        )

    write_json(output or DOCUMENTS_FILE, documents)
    print_summary(documents, metadata_keys, categories, tags, authors)

    return documents


def print_summary(
    documents: list[dict],
    metadata_keys: Counter,
    categories: Counter,
    tags: Counter,
    authors: Counter,
) -> None:
    print(f"[green]ZPWIKI_ROOT:[/green] {ZPWIKI_ROOT}")
    print(f"[green]Našiel som dokumentov:[/green] {len(documents)}")
    print(f"[green]Výstup uložený do:[/green] {DOCUMENTS_FILE}")

    print("\n[bold]Najčastejšie metadata kľúče:[/bold]")
    for key, count in metadata_keys.most_common(30):
        print(f"{key}: {count}")

    print("\n[bold]Najčastejšie kategórie:[/bold]")
    for key, count in categories.most_common(30):
        print(f"{key}: {count}")

    print("\n[bold]Najčastejšie tagy:[/bold]")
    for key, count in tags.most_common(40):
        print(f"{key}: {count}")

    print("\n[bold]Najčastejší autori:[/bold]")
    for key, count in authors.most_common(20):
        print(f"{key}: {count}")

    if documents:
        print("\n[bold]Ukážka prvého dokumentu:[/bold]")
        print(documents[0])


def main() -> None:
    scan_pages()


if __name__ == "__main__":
    main()