96 lines
2.2 KiB
Python
96 lines
2.2 KiB
Python
from __future__ import annotations
|
|
|
|
import argparse
|
|
import subprocess
|
|
import sys
|
|
import time
|
|
from pathlib import Path
|
|
|
|
from rich import print
|
|
|
|
|
|
PROJECT_ROOT = Path(__file__).resolve().parents[1]
|
|
|
|
if str(PROJECT_ROOT) not in sys.path:
|
|
sys.path.insert(0, str(PROJECT_ROOT))
|
|
|
|
|
|
from scripts.build_chunks import build_chunks
|
|
from scripts.build_sqlite_index import build_database
|
|
from scripts.common import DB_FILE, ZPWIKI_ROOT
|
|
from scripts.scan_zpwiki import scan_pages
|
|
|
|
|
|
def git_pull(repo_path: Path = ZPWIKI_ROOT) -> None:
|
|
if not repo_path.exists():
|
|
raise RuntimeError(f"ZPWIKI_ROOT neexistuje: {repo_path}")
|
|
|
|
if not (repo_path / ".git").exists():
|
|
raise RuntimeError(f"Nie je to git repozitár: {repo_path}")
|
|
|
|
result = subprocess.run(
|
|
["git", "pull"],
|
|
cwd=repo_path,
|
|
text=True,
|
|
capture_output=True,
|
|
)
|
|
|
|
if result.stdout:
|
|
print(result.stdout.strip())
|
|
|
|
if result.stderr:
|
|
print(result.stderr.strip())
|
|
|
|
if result.returncode != 0:
|
|
raise RuntimeError("Git pull zlyhal")
|
|
|
|
|
|
def rebuild_index(pull_git: bool = False) -> dict:
|
|
start = time.time()
|
|
|
|
print(f"[green]ZPWIKI_ROOT:[/green] {ZPWIKI_ROOT}")
|
|
|
|
if pull_git:
|
|
git_pull()
|
|
|
|
documents = scan_pages()
|
|
chunks = build_chunks()
|
|
counts = build_database()
|
|
|
|
duration = round(time.time() - start, 2)
|
|
|
|
return {
|
|
"duration_seconds": duration,
|
|
"documents_scanned": len(documents),
|
|
"chunks_created": len(chunks),
|
|
"counts": counts,
|
|
"database_path": str(DB_FILE),
|
|
}
|
|
|
|
|
|
def main() -> None:
|
|
parser = argparse.ArgumentParser(
|
|
description="Obnoví JSON súbory a SQLite index."
|
|
)
|
|
|
|
parser.add_argument(
|
|
"--pull",
|
|
action="store_true",
|
|
help="Pred reindexovaním spustí git pull v zpwiki repozitári.",
|
|
)
|
|
|
|
args = parser.parse_args()
|
|
result = rebuild_index(pull_git=args.pull)
|
|
counts = result["counts"]
|
|
|
|
print("[green]Reindex hotový.[/green]")
|
|
print(f"Trvanie: {result['duration_seconds']} s")
|
|
print(f"Dokumentov: {counts['documents']}")
|
|
print(f"Chunkov: {counts['chunks']}")
|
|
print(f"Tag záznamov: {counts['tags']}")
|
|
print(f"Kategória záznamov: {counts['categories']}")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|