Updated the Codebase to use pathlib instead of using os.path and path.py

hatch_build.py

@@ -20,18 +20,13 @@ def initialize(self, version, build_data):
  logger.info("JS dependencies are already installed, skipping it")
  return
  subprocess.run(
- str(Path(self.root).joinpath("get_js_deps.sh")),
+ str(Path(self.root) / "get_js_deps.sh"),
  check=True,
  )
  return super().initialize(version, build_data)
 
  def deps_already_installed(self) -> bool:
  for dep in JS_DEPS:
- if (
- not Path(self.root)
- .joinpath("gutebergtozim/templates")
- .joinpath(dep)
- .exists()
- ):
+ if not Path(self.root, "gutebergtozim/templates", dep).exists():
  return False
  return True

pyproject.toml

@@ -6,7 +6,7 @@ build-backend = "hatchling.build"
 name = "gutenberg2zim"
 authors = [{ name = "Kiwix", email = "dev@kiwix.org" }]
 keywords = ["kiwix", "zim", "offline", "gutenberg"]
-requires-python = ">=3.11"
+requires-python = ">=3.11,<3.12"
 description = "Make ZIM file from Gutenberg books"
 readme = "pypi-readme.rst"
 license = { text = "GPL-3.0-or-later" }

src/gutenberg2zim/download.py

@@ -1,15 +1,14 @@
 import os
-import pathlib
 import shutil
 import tempfile
 import zipfile
 from multiprocessing.dummy import Pool
+from pathlib import Path
 from pprint import pprint as pp
 
 import apsw
 import backoff
 from kiwixstorage import KiwixStorage
-from path import Path
 
 from gutenberg2zim.constants import TMP_FOLDER, logger
 from gutenberg2zim.database import Book, BookFormat
@@ -36,15 +35,15 @@
 # return False
 
 
-def handle_zipped_epub(zippath, book, dst_dir: pathlib.Path):
+def handle_zipped_epub(zippath, book, dst_dir: Path):
  def clfn(fn):
- return os.path.join(*os.path.split(fn)[1:])
+ return Path(*Path(fn).parts[1:])
 
  def is_safe(fname):
  fname = ensure_unicode(clfn(fname))
- if Path(fname).basename() == fname:
+ if Path(fname).name == fname:
  return True
- return fname == os.path.join("images", Path(fname).splitpath()[-1])
+ return fname == Path("images") / Path(fname).name
 
  zipped_files = []
  # create temp directory to extract to
@@ -53,7 +52,7 @@
  with zipfile.ZipFile(zippath, "r") as zf:
  # check that there is no insecure data (absolute names)
  if sum([1 for n in zf.namelist() if not is_safe(ensure_unicode(n))]):
- Path(tmpd).rmtree_p()
+ shutil.rmtree(tmpd)
  return False
  # zipped_files = [clfn(fn) for fn in zf.namelist()]
  zipped_files = zf.namelist()
@@ -73,25 +72,25 @@
  # move all extracted files to proper locations
  for zipped_file in zipped_files:
  # skip folders
- if not Path(zipped_file).ext:
+ if not Path(zipped_file).is_file:
  continue
 
- src = os.path.join(tmpd, zipped_file)
- if os.path.exists(src):
- fname = Path(zipped_file).basename()
+ src = Path(tmpd) / zipped_file
+ if src.exists():
+ fname = Path(zipped_file).name
 
  if fname.endswith(".html") or fname.endswith(".htm"):
  if mhtml:
  if fname.startswith(f"{book.id}-h."):
- dst = dst_dir.joinpath(f"{book.id}.html")
+ dst = dst_dir / f"{book.id}.html"
  else:
- dst = dst_dir.joinpath(f"{book.id}_{fname}")
+ dst = dst_dir / f"{book.id}_{fname}"
  else:
- dst = dst_dir.joinpath(f"{book.id}.html")
+ dst = dst_dir / f"{book.id}.html"
  else:
- dst = dst_dir.joinpath(f"{book.id}_{fname}")
+ dst = dst_dir / f"{book.id}_{fname}"
  try:
- Path(src).move(str(dst))
+ src.rename(dst)
  except Exception as e:
  import traceback
 
@@ -102,12 +101,12 @@
  # delete temp directory and zipfile
  if Path(zippath).exists():
  os.unlink(zippath)
- Path(tmpd).rmtree_p()
+ shutil.rmtree(tmpd)
 
 
 def download_book(
  book: Book,
- download_cache: str,
+ download_cache: Path,
  formats: list[str],
  *,
  force: bool,
@@ -124,13 +123,14 @@
  if "html" not in formats:
  formats.append("html")
 
- book_dir = pathlib.Path(download_cache).joinpath(str(book.id))
- optimized_dir = book_dir.joinpath("optimized")
- unoptimized_dir = book_dir.joinpath("unoptimized")
+ book_dir = download_cache / str(book.id)
+ optimized_dir = book_dir / "optimized"
+ unoptimized_dir = book_dir / "unoptimized"
  unsuccessful_formats = []
+
  for book_format in formats:
- unoptimized_fpath = unoptimized_dir.joinpath(fname_for(book, book_format))
- optimized_fpath = optimized_dir.joinpath(archive_name_for(book, book_format))
+ unoptimized_fpath = unoptimized_dir / fname_for(book, book_format)
+ optimized_fpath = optimized_dir / archive_name_for(book, book_format)
 
  # check if already downloaded
  if (unoptimized_fpath.exists() or optimized_fpath.exists()) and not force:
@@ -233,7 +233,7 @@
 
  # HTML files are *sometime* available as ZIP files
  if url.endswith(".zip"):
- zpath = unoptimized_dir.joinpath(f"{fname_for(book, book_format)}.zip")
+ zpath = unoptimized_dir / f"{fname_for(book, book_format)}.zip"
 
  etag = get_etag_from_url(url)
  if s3_storage:
@@ -329,10 +329,9 @@
  etag = get_etag_from_url(url)
  downloaded_from_cache = False
  cover = f"{book.id}_cover_image.jpg"
- if (
- book_dir.joinpath("optimized").joinpath(cover).exists()
- or book_dir.joinpath("unoptimized").joinpath(cover).exists()
- ):
+ if (book_dir / "optimized" / cover).exists() or (
+ book_dir / "unoptimized" / cover
+ ).exists():
  logger.debug(f"Cover already exists for book #{book.id}")
  return
  if s3_storage:
@@ -343,21 +342,21 @@
  book=book,
  etag=etag,
  book_format="cover",
- dest_dir=book_dir.joinpath("optimized"),
+ dest_dir=book_dir / "optimized",
  s3_storage=s3_storage,
  optimizer_version=optimizer_version,
  )
  if not downloaded_from_cache:
  logger.debug(f"Downloading {url}")
- if download_file(url, book_dir.joinpath("unoptimized").joinpath(cover)):
+ if download_file(url, book_dir / "unoptimized" / cover):
  book.cover_etag = etag
  book.save()
  else:
  logger.debug(f"No Book Cover found for Book #{book.id}")
 
 
 def download_all_books(
- download_cache: str,
+ download_cache: Path,
  concurrency: int,
  languages: list[str],
  formats: list[str],
@@ -372,7 +371,7 @@
  )
 
  # ensure dir exist
- Path(download_cache).mkdir_p()
+ download_cache.mkdir(parents=True, exist_ok=True)
 
  def backoff_busy_error_hdlr(details):
  logger.warning(

src/gutenberg2zim/entrypoint.py

@@ -1,8 +1,7 @@
-import os
 import sys
+from pathlib import Path
 
 from docopt import docopt
-from path import Path
 
 from gutenberg2zim.checkdeps import check_dependencies
 from gutenberg2zim.constants import TMP_FOLDER_PATH, VERSION, logger
@@ -90,7 +89,7 @@
  arguments.get("--rdf-url")
  or "http://www.gutenberg.org/cache/epub/feeds/rdf-files.tar.bz2"
  )
- dl_cache = arguments.get("--dl-folder") or os.path.join("dl-cache")
+ dl_cache = Path(arguments.get("--dl-folder") or "dl-cache")
  books_csv = arguments.get("--books") or ""
  zim_title = arguments.get("--zim-title")
  zim_desc = arguments.get("--zim-desc")
@@ -209,7 +208,7 @@
  if do_zim:
  logger.info("BUILDING ZIM dynamically")
  build_zimfile(
- output_folder=Path(one_lang_one_zim_folder or ".").abspath(),
+ output_folder=Path(one_lang_one_zim_folder or ".").resolve(),
  download_cache=dl_cache,
  concurrency=concurrency,
  languages=zim_lang,