Customize / Harmonize publisher + other small fixes

ChangeLog

@@ -8,6 +8,17 @@ as of 2.0.0.
 
 ## [Unreleased]
 
+### Added
+- `Publisher` ZIM metadata can now be customized at CLI (#210)
+
+### Changed
+- `Publisher` ZIM metadata default value is changed to `openZIM` intead of `Kiwix` (#210)
+
+### Fixed
+- Do not fail if temporary directory already exists (#207)
+- Typo in `Scraper` ZIM metadata (#212)
+- Adapt to hatchling v1.19.0 which mandates packages setting (#211)
+
 ## [2.1.0] - 2023-08-18
 
 ### Changed

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" }
@@ -69,6 +69,9 @@ exclude = ["/.github"]
 path = "hatch_build.py"
 dependencies = ["zimscraperlib==3.1.1"]
 
+[tool.hatch.build.targets.wheel]
+packages = ["src/gutenberg2zim"]
+
 [tool.hatch.envs.default]
 features = ["dev"]
 

src/gutenberg2zim/entrypoint.py

@@ -22,7 +22,7 @@
     """[--prepare] [--parse] [--download] [--export] [--dev] """
     """[--zim] [--complete] [-m ONE_LANG_ONE_ZIM_FOLDER] """
     """[--title-search] [--bookshelves] [--optimization-cache S3URL] """
-    """[--stats-filename STATS_FILENAME]"""
+    """[--stats-filename STATS_FILENAME] [--publisher ZIM_PUBLISHER]"""
     """
 
 -h --help                       Display this help message
@@ -63,6 +63,7 @@
 --use-any-optimized-version     Try to use any optimized version found on """
     """optimization cache
 --stats-filename=<filename>  Path to store the progress JSON file to
+--publisher=<zim_publisher>     Custom Publisher in ZIM Metadata (openZIM otherwise)
 
 This script is used to produce a ZIM file (and any intermediate state)
 of Gutenberg repository using a mirror."""
@@ -102,6 +103,7 @@ def main():
     optimization_cache = arguments.get("--optimization-cache") or None
     use_any_optimized_version = arguments.get("--use-any-optimized-version", False)
     stats_filename = arguments.get("--stats-filename") or None
+    publisher = arguments.get("--publisher") or "openZIM"
 
     s3_storage = None
     if optimization_cache:
@@ -111,7 +113,7 @@ def main():
         logger.info("S3 Credentials OK. Continuing ... ")
 
     # create tmp dir
-    TMP_FOLDER_PATH.mkdir(parents=True)
+    TMP_FOLDER_PATH.mkdir(parents=True, exist_ok=True)
 
     languages = [
         x.strip().lower()
@@ -224,4 +226,5 @@ def f(x):
                 title=zim_title,
                 description=zim_desc,
                 stats_filename=stats_filename,
+                publisher=publisher,
             )

src/gutenberg2zim/shared.py

@@ -32,7 +32,7 @@ def inc_progress():
             Global.progress += 1
 
     @staticmethod
-    def setup(filename, language, title, description, name):
+    def setup(filename, language, title, description, name, publisher):
         Global.creator = Creator(
             filename=filename,
             main_path="Home.html",
@@ -41,10 +41,10 @@ def setup(filename, language, title, description, name):
             title=title,
             description=description,
             creator="gutenberg.org",  # type: ignore
-            publisher="Kiwix",  # type: ignore
+            publisher=publisher,  # type: ignore
             name=name,
             tags="_category:gutenberg;gutenberg",  # type: ignore
-            scraper=f"gutengergtozim-{VERSION}",  # type: ignore
+            scraper=f"gutenberg2zim-{VERSION}",  # type: ignore
             date=date.today(),  # type: ignore
         ).config_verbose(True)
 

src/gutenberg2zim/zim.py

@@ -28,6 +28,7 @@ def build_zimfile(
     title,
     description,
     stats_filename,
+    publisher,
 ):
     # actual list of languages with books sorted by most used
     nb = fn.COUNT(Book.language).alias("nb")
@@ -76,6 +77,7 @@ def build_zimfile(
         title=title,
         description=description,
         name=project_id,
+        publisher=publisher,
     )
 
     Global.start()