diff --git a/swh/lister/julia/__init__.py b/swh/lister/julia/__init__.py index ed9c8584d5523e844d54951a76161af42247db09..8388c0a2d26f78da7e7767b14a677df8cd29caed 100644 --- a/swh/lister/julia/__init__.py +++ b/swh/lister/julia/__init__.py @@ -24,8 +24,8 @@ packaged releases using the Github release system. As of July 2023 `Julia General registry`_ list 9714 packages names. -Origins retrieving strategy ---------------------------- +Origins retrieval strategy +-------------------------- To build a list of origins we clone the `Julia General registry`_ Git repository, then read the `Registry.toml`_ file to get the path to packages directories. diff --git a/swh/lister/julia/lister.py b/swh/lister/julia/lister.py index 4e445fb37dacc212cbc277c36d63b363dfc73123..ccfa9faf61545a578d92e747d5b5a7bfb95b450e 100644 --- a/swh/lister/julia/lister.py +++ b/swh/lister/julia/lister.py @@ -64,9 +64,9 @@ class JuliaLister(StatelessLister[JuliaListerPage]): def get_pages(self) -> Iterator[JuliaListerPage]: """Yield an iterator which returns 'page' - It uses the api endpoint provided by `https://registry.julia.io/packages` - to get a list of package names with an origin url that corresponds to Git - repository. + To build a list of origins the `Julia General registry` Git + repository is cloned to get a `Registry.toml` file, an index file of + packages directories. There is only one page that list all origins urls. """ @@ -76,7 +76,11 @@ class JuliaLister(StatelessLister[JuliaListerPage]): yield registry["packages"].items() def get_origins_from_page(self, page: JuliaListerPage) -> Iterator[ListedOrigin]: - """Iterate on all pages and yield ListedOrigin instances""" + """Iterate on all pages and yield ListedOrigin instances + + Each directory of the Git repository have a `Package.toml` file from + where we get the Git repository url for each package. + """ assert self.lister_obj.id is not None assert self.REPO_PATH.exists()