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

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

@@ -1,5 +1,5 @@
 import os
-import pathlib
+from pathlib import Path
 import shutil
 import tempfile
 import zipfile
@@ -9,7 +9,6 @@
 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()
@@ -73,12 +72,12 @@
  # 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).suffix:
  continue
 
- src = os.path.join(tmpd, zipped_file)
- if os.path.exists(src):
- fname = Path(zipped_file).basename()
+ src = Path(tmpd) / zipped_file
+ if Path(src).exists():
+ fname = Path(zipped_file).name
 
  if fname.endswith(".html") or fname.endswith(".htm"):
  if mhtml:
@@ -91,7 +90,7 @@
  else:
  dst = dst_dir.joinpath(f"{book.id}_{fname}")
  try:
- Path(src).move(str(dst))
+ Path(src).rename(dst)
  except Exception as e:
  import traceback
 
@@ -102,7 +101,8 @@
  # delete temp directory and zipfile
  if Path(zippath).exists():
  os.unlink(zippath)
- Path(tmpd).rmtree_p()
+ shutil.rmtree(tmpd)
+
 
 
 def download_book(
@@ -124,7 +124,7 @@
  if "html" not in formats:
  formats.append("html")
 
- book_dir = pathlib.Path(download_cache).joinpath(str(book.id))
+ book_dir = Path(download_cache).joinpath(str(book.id))
  optimized_dir = book_dir.joinpath("optimized")
  unoptimized_dir = book_dir.joinpath("unoptimized")
  unsuccessful_formats = []
@@ -372,7 +372,7 @@
  )
 
  # ensure dir exist
- Path(download_cache).mkdir_p()
+ Path(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 = 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,

src/gutenberg2zim/export.py

@@ -1,6 +1,6 @@
 import json
 import os
-import pathlib
+from pathlib import Path
 import shutil
 import tempfile
 import traceback
@@ -11,7 +11,6 @@
 import bs4
 from bs4 import BeautifulSoup
 from jinja2 import Environment, PackageLoader
-from path import Path
 from schedule import every
 from six import text_type
 from zimscraperlib.image.transformation import resize_image
@@ -95,7 +94,7 @@
 
 
 def tmpl_path():
- return os.path.join(Path(gutenberg2zim.__file__).parent, "templates")
+ return Path(gutenberg2zim.__file__).parent / "templates"
 
 
 def get_list_of_all_languages():
@@ -105,8 +104,8 @@
 def export_illustration():
  logger.info("Adding illustration")
 
- src_illus_fpath = pathlib.Path(tmpl_path(), "favicon.png")
- tmp_illus_fpath = pathlib.Path(TMP_FOLDER_PATH, "illustration.png")
+ src_illus_fpath = Path(tmpl_path(), "favicon.png")
+ tmp_illus_fpath = Path(TMP_FOLDER_PATH, "illustration.png")
 
  shutil.copy(src_illus_fpath, tmp_illus_fpath)
 
@@ -152,18 +151,18 @@
  "datatables",
  "fonts",
  ):
- src = os.path.join(src_folder, fname)
+ src = Path(src_folder) / fname
 
  # recursively add our assets, at a path identical to position in repo
- assets_root = pathlib.Path(src)
+ assets_root = Path(src)
  if assets_root.is_file():
  Global.add_item_for(path=fname, fpath=assets_root)
  else:
  for fpath in assets_root.glob("**/*"):
  if not fpath.is_file() or fpath.name == "l10n.js":
  continue
  path = str(fpath.relative_to(src))
- Global.add_item_for(path=os.path.join(fname, path), fpath=fpath)
+ Global.add_item_for(path=str(Path(fname) / path), fpath=fpath)
 
  # export homepage
  tpl_path = "Home.html"
@@ -273,7 +272,7 @@
  def dlb(b):
  export_book(
  b,
- book_dir=pathlib.Path(download_cache).joinpath(str(b.id)),
+ book_dir=Path(download_cache).joinpath(str(b.id)),
  formats=formats,
  books=books,
  project_id=project_id,
@@ -711,23 +710,23 @@
 
  remove_cover = False
  for fname in zipped_files:
- fnp = os.path.join(tmpd, fname)
- if Path(fname).ext in (".png", ".jpeg", ".jpg", ".gif"):
+ fnp = Path(tmpd) / fname
+ if Path(fname).suffix in (".png", ".jpeg", ".jpg", ".gif"):
  # special case to remove ugly cover
  if fname.endswith("cover.jpg") and is_bad_cover(fnp):
  zipped_files.remove(fname)
  remove_cover = True
  else:
- optimize_image(pathlib.Path(fnp), pathlib.Path(fnp), force=True)
+ optimize_image(Path(fnp), Path(fnp), force=True)
 
- if Path(fname).ext in (".htm", ".html"):
+ if Path(fname).suffix in (".htm", ".html"):
  html_content, _ = read_file(fnp)
  html = update_html_for_static(
  book=book, html_content=html_content, formats=formats, epub=True
  )
  save_bs_output(html, fnp, UTF8)
 
- if Path(fname).ext == ".ncx":
+ if Path(fname).suffix == ".ncx":
  pattern = "*** START: FULL LICENSE ***"
  ncx, _ = read_file(fnp)
  soup = BeautifulSoup(ncx, "lxml-xml")
@@ -744,11 +743,15 @@
  # delete {id}/cover.jpg if exist and update {id}/content.opf
  if remove_cover:
  # remove cover
- Path(os.path.join(tmpd, text_type(book.id), "cover.jpg")).unlink_p()
+ file_path = Path(tmpd) / text_type(book.id) / "cover.jpg"
+ try:
+ file_path.unlink()
+ except FileNotFoundError:
+ pass
 
  soup = None
- opff = os.path.join(tmpd, text_type(book.id), "content.opf")
- if os.path.exists(opff):
+ opff = Path(tmpd) / text_type(book.id) / "content.opf"
+ if Path(opff).exists():
  opff_content, _ = read_file(opff)
  soup = BeautifulSoup(opff_content, "lxml-xml")
 
@@ -761,7 +764,7 @@
  # bundle epub as zip
  zip_epub(epub_fpath=dst, root_folder=tmpd, fpaths=zipped_files)
 
- Path(tmpd).rmtree_p()
+ shutil.rmtree(tmpd)
 
  def handle_companion_file(
  fname,
@@ -821,7 +824,7 @@
  as_ext=".zip",
  )
  else:
- Path(tmp_epub.name).move(str(dst))
+ tmp_epub.rename(Path(dst) / tmp_epub.name)
  Global.add_item_for(path=dstfname, fpath=dst)
  if s3_storage:
  upload_to_cache(

src/gutenberg2zim/rdf.py

@@ -1,8 +1,7 @@
 import os
-import pathlib
 import re
 import tarfile
-
+from pathlib import Path
 import peewee
 from bs4 import BeautifulSoup
 
@@ -18,7 +17,7 @@
 
 def get_rdf_fpath():
  fname = "rdf-files.tar.bz2"
- fpath = pathlib.Path(fname).resolve()
+ fpath = Path(fname).resolve()
  return fpath
 
 
@@ -38,7 +37,7 @@
  rdf_tarfile = tarfile.open(name=rdf_path, mode="r|bz2")
 
  for rdf_member in rdf_tarfile:
- rdf_member_path = pathlib.Path(rdf_member.name)
+ rdf_member_path = Path(rdf_member.name)
 
  # skip books outside of requested list
  if (
@@ -297,9 +296,10 @@
  nums = [f"{i:0=5d}" for i in range(21000, 40000)]
  for num in nums:
  print(num) # noqa: T201
- curd = os.path.dirname(os.path.realpath(__file__))
- rdf = os.path.join(curd, "..", "rdf-files", num, "pg" + num + ".rdf")
- if os.path.isfile(rdf):
+ curd = Path(__file__).resolve().parent
+ rdf = curd.parent / "rdf-files" / num / f"pg{num}.rdf"
+
+ if rdf.is_file():
  data = ""
  with open(rdf) as f:
  data = f.read()