biocypher 0.9.1__py3-none-any.whl → 0.9.3__py3-none-any.whl

biocypher/_get.py

@@ -1,5 +1,6 @@
-"""
-BioCypher get module. Used to download and cache data from external sources.
+"""BioCypher get module.
+
+Used to download and cache data from external sources.
 """
 
 from __future__ import annotations
@@ -30,19 +31,22 @@ class Resource(ABC):
         url_s: str | list[str],
         lifetime: int = 0,
     ):
-        """
+        """Initialize a Resource.
+
         A Resource is a file, a list of files, an API request, or a list of API
         requests, any of which can be downloaded from the given URL(s) and
         cached locally. This class implements checks of the minimum requirements
         for a resource, to be implemented by a biocypher adapter.
 
         Args:
+        ----
             name (str): The name of the resource.
 
             url_s (str | list[str]): The URL or URLs of the resource.
 
             lifetime (int): The lifetime of the resource in days. If 0, the
                 resource is considered to be permanent.
+
         """
         self.name = name
         self.url_s = url_s
@@ -57,10 +61,12 @@ class FileDownload(Resource):
         lifetime: int = 0,
         is_dir: bool = False,
     ):
-        """
+        """Initialize a FileDownload object.
+
         Represents basic information for a File Download.
 
         Args:
+        ----
             name(str): The name of the File Download.
 
             url_s(str|list[str]): The URL(s) of the File Download.
@@ -69,18 +75,20 @@ class FileDownload(Resource):
                 File Download is cached indefinitely.
 
             is_dir (bool): Whether the URL points to a directory or not.
-        """
 
+        """
         super().__init__(name, url_s, lifetime)
         self.is_dir = is_dir
 
 
 class APIRequest(Resource):
     def __init__(self, name: str, url_s: str | list[str], lifetime: int = 0):
-        """
+        """Initialize an APIRequest object.
+
         Represents basic information for an API Request.
 
         Args:
+        ----
             name(str): The name of the API Request.
 
             url_s(str|list): The URL of the API endpoint.
@@ -94,29 +102,35 @@ class APIRequest(Resource):
 
 class Downloader:
     def __init__(self, cache_dir: Optional[str] = None) -> None:
-        """
+        """Initialize the Downloader.
+
         The Downloader is a class that manages resources that can be downloaded
         and cached locally. It manages the lifetime of downloaded resources by
         keeping a JSON record of the download date of each resource.
 
         Args:
+        ----
             cache_dir (str): The directory where the resources are cached. If
                 not given, a temporary directory is created.
+
         """
         self.cache_dir = cache_dir or TemporaryDirectory().name
         self.cache_file = os.path.join(self.cache_dir, "cache.json")
         self.cache_dict = self._load_cache_dict()
 
     def download(self, *resources: Resource):
-        """
-        Download one or multiple resources. Load from cache if the resource is
-        already downloaded and the cache is not expired.
+        """Download one or multiple resources.
+
+        Load from cache if the resource is already downloaded and the cache is
+        not expired.
 
         Args:
+        ----
             resources (Resource): The resource(s) to download or load from
                 cache.
 
         Returns:
+        -------
             list[str]: The path or paths to the resource(s) that were downloaded
                 or loaded from cache.
 
@@ -132,12 +146,14 @@ class Downloader:
         return paths
 
     def _download_or_cache(self, resource: Resource, cache: bool = True):
-        """
-        Download a resource if it is not cached or exceeded its lifetime.
+        """Download a resource if it is not cached or exceeded its lifetime.
 
         Args:
+        ----
             resource (Resource): The resource to download.
+
         Returns:
+        -------
             list[str]: The path or paths to the downloaded resource(s).
 
         """
@@ -159,14 +175,16 @@ class Downloader:
         return paths
 
     def _is_cache_expired(self, resource: Resource) -> bool:
-        """
-        Check if resource or API request cache is expired.
+        """Check if resource or API request cache is expired.
 
         Args:
+        ----
             resource (Resource): The resource to download.
 
         Returns:
+        -------
             bool: cache is expired or not.
+
         """
         cache_record = self._get_cache_record(resource)
         if cache_record:
@@ -182,17 +200,21 @@ class Downloader:
         if os.path.exists(cache_resource_path) and os.path.isdir(cache_resource_path):
             shutil.rmtree(cache_resource_path)
 
-    def _download_files(self, cache, file_download: FileDownload):
-        """
-        Download a resource given it is a file or a directory and return the
-        path.
+    def _download_files(self, cache, file_download: FileDownload) -> list[str]:
+        """Download a resource given it is a file or a directory.
+
+        Upon downloading, return the path(s).
 
         Args:
+        ----
             cache (bool): Whether to cache the resource or not.
+
             file_download (FileDownload): The resource to download.
 
         Returns:
+        -------
             list[str]: The path or paths to the downloaded resource(s).
+
         """
         if file_download.is_dir:
             files = self._get_files(file_download)
@@ -202,7 +224,7 @@ class Downloader:
         elif isinstance(file_download.url_s, list):
             paths = []
             for url in file_download.url_s:
-                fname = url[url.rfind("/") + 1 :].split("?")[0]
+                fname = self._trim_filename(url)
                 path = self._retrieve(
                     url=url,
                     fname=fname,
@@ -211,7 +233,7 @@ class Downloader:
                 paths.append(path)
         else:
             paths = []
-            fname = file_download.url_s[file_download.url_s.rfind("/") + 1 :].split("?")[0]
+            fname = self._trim_filename(file_download.url_s)
             results = self._retrieve(
                 url=file_download.url_s,
                 fname=fname,
@@ -227,20 +249,23 @@ class Downloader:
         # adapter
         return paths
 
-    def _download_api_request(self, api_request: APIRequest):
-        """
-        Download an API request and return the path.
+    def _download_api_request(self, api_request: APIRequest) -> list[str]:
+        """Download an API request and return the path.
 
         Args:
-            api_request(APIRequest): The API request result that is being cached.
+        ----
+            api_request(APIRequest): The API request result that is being
+                cached.
+
         Returns:
+        -------
             list[str]: The path to the cached API request.
 
         """
         urls = api_request.url_s if isinstance(api_request.url_s, list) else [api_request.url_s]
         paths = []
         for url in urls:
-            fname = url[url.rfind("/") + 1 :].rsplit(".", 1)[0]
+            fname = self._trim_filename(url)
             logger.info(f"Asking for caching API of {api_request.name} {fname}.")
             response = requests.get(url=url)
 
@@ -260,10 +285,13 @@ class Downloader:
         """Get the cached version of a resource.
 
         Args:
+        ----
             resource(Resource): The resource to get the cached version of.
 
         Returns:
+        -------
             list[str]: The paths to the cached resource(s).
+
         """
         cached_location = os.path.join(self.cache_dir, resource.name)
         logger.info(f"Use cached version from {cached_location}.")
@@ -278,17 +306,25 @@ class Downloader:
         fname: str,
         path: str,
         known_hash: str = None,
-    ):
-        """
-        Retrieve a file from a URL using Pooch. Infer type of file from
-        extension and use appropriate processor.
+    ) -> str:
+        """Retrieve a file from a URL using Pooch.
+
+        Infer type of file from extension and use appropriate processor.
 
         Args:
+        ----
             url (str): The URL to retrieve the file from.
 
             fname (str): The name of the file.
 
             path (str): The path to the file.
+
+            known_hash (str): The known hash of the file.
+
+        Returns:
+        -------
+            str: The path to the file.
+
         """
         if fname.endswith(".zip"):
             return pooch.retrieve(
@@ -329,15 +365,17 @@ class Downloader:
                 progressbar=True,
             )
 
-    def _get_files(self, file_download: FileDownload):
-        """
-        Get the files contained in a directory file.
+    def _get_files(self, file_download: FileDownload) -> list[str]:
+        """Get the files contained in a directory file.
 
         Args:
+        ----
             file_download (FileDownload): The directory file.
 
         Returns:
-            list: The files contained in the directory.
+        -------
+            list[str]: The files contained in the directory.
+
         """
         if file_download.url_s.startswith("ftp://"):
             # remove protocol
@@ -353,14 +391,25 @@ class Downloader:
             files = ftp.nlst()
             ftp.quit()
         else:
-            raise NotImplementedError("Only FTP directories are supported at the moment.")
+            msg = "Only FTP directories are supported at the moment."
+            logger.error(msg)
+            raise NotImplementedError(msg)
 
         return files
 
-    def _load_cache_dict(self):
-        """
-        Load the cache dictionary from the cache file. Create an empty cache
-        file if it does not exist.
+    def _load_cache_dict(self) -> dict:
+        """Load the cache dictionary from the cache file.
+
+        Create an empty cache file if it does not exist.
+
+        Args:
+        ----
+            None.
+
+        Returns:
+        -------
+            dict: The cache dictionary.
+
         """
         if not os.path.exists(self.cache_dir):
             logger.info(f"Creating cache directory {self.cache_dir}.")
@@ -375,24 +424,27 @@ class Downloader:
             logger.info(f"Loading cache file {self.cache_file}.")
             return json.load(f)
 
-    def _get_cache_record(self, resource: Resource):
-        """
-        Get the cache record of a resource.
+    def _get_cache_record(self, resource: Resource) -> dict:
+        """Get the cache record of a resource.
 
         Args:
+        ----
             resource (Resource): The resource to get the cache record of.
 
         Returns:
-            The cache record of the resource.
+        -------
+            dict: The cache record of the resource.
+
         """
         return self.cache_dict.get(resource.name, {})
 
-    def _update_cache_record(self, resource: Resource):
-        """
-        Update the cache record of a resource.
+    def _update_cache_record(self, resource: Resource) -> None:
+        """Update the cache record of a resource.
 
         Args:
+        ----
             resource (Resource): The resource to update the cache record of.
+
         """
         cache_record = {}
         cache_record["url"] = to_list(resource.url_s)
@@ -401,3 +453,34 @@ class Downloader:
         self.cache_dict[resource.name] = cache_record
         with open(self.cache_file, "w") as f:
             json.dump(self.cache_dict, f, default=str)
+
+    def _trim_filename(self, url: str, max_length: int = 150) -> str:
+        """Create a trimmed filename from a URL.
+
+        If the URL exceeds max_length, create a hash of the filename.
+
+        Args:
+        ----
+            url (str): The URL to generate a filename from
+            max_length (int): Maximum filename length (default: 150)
+
+        Returns:
+        -------
+            str: A valid filename derived from the URL, trimmed if necessary
+
+        """
+        # Extract the filename from the URL
+        fname = url[url.rfind("/") + 1 :]
+
+        # Remove query parameters if present
+        if "?" in fname:
+            fname = fname.split("?")[0]
+
+        if len(fname) > max_length:
+            import hashlib
+
+            fname_trimmed = hashlib.md5(fname.encode()).hexdigest()
+        else:
+            fname_trimmed = fname
+
+        return fname_trimmed

biocypher/_metadata.py

@@ -10,7 +10,7 @@ import pathlib
 
 import toml
 
-_VERSION = "0.9.1"
+_VERSION = "0.9.3"
 
 
 def get_metadata():

biocypher/_misc.py

@@ -1,22 +1,18 @@
-"""
-Handy functions for use in various places.
-"""
+"""Handy functions for use in various places."""
 
 import re
 
-from collections.abc import Iterable
-from typing import (
-    Any,
+from collections.abc import (
     Generator,
     ItemsView,
+    Iterable,
     KeysView,
     Mapping,
-    Union,
     ValuesView,
 )
+from typing import Any
 
 import networkx as nx
-import stringcase
 
 from treelib import Tree
 
@@ -48,10 +44,7 @@ LIST_LIKE = (
 
 
 def to_list(value: Any) -> list:
-    """
-    Ensures that ``value`` is a list.
-    """
-
+    """Ensure that ``value`` is a list."""
     if isinstance(value, LIST_LIKE):
         value = list(value)
 
@@ -62,17 +55,12 @@ def to_list(value: Any) -> list:
 
 
 def ensure_iterable(value: Any) -> Iterable:
-    """
-    Returns iterables, except strings, wraps simple types into tuple.
-    """
-
+    """Return iterables, except strings, wrap simple types into tuple."""
     return value if isinstance(value, LIST_LIKE) else (value,)
 
 
-def create_tree_visualisation(inheritance_graph: Union[dict, nx.Graph]) -> Tree:
-    """
-    Creates a visualisation of the inheritance tree using treelib.
-    """
+def create_tree_visualisation(inheritance_graph: dict | nx.Graph) -> Tree:
+    """Create a visualisation of the inheritance tree using treelib."""
     inheritance_tree = _get_inheritance_tree(inheritance_graph)
     classes, root = _find_root_node(inheritance_tree)
 
@@ -91,38 +79,42 @@ def create_tree_visualisation(inheritance_graph: Union[dict, nx.Graph]) -> Tree:
     return tree
 
 
-def _get_inheritance_tree(inheritance_graph: Union[dict, nx.Graph]) -> dict:
-    """Transforms an inheritance_graph into an inheritance_tree.
+def _get_inheritance_tree(inheritance_graph: dict | nx.Graph) -> dict | None:
+    """Transform an inheritance_graph into an inheritance_tree.
 
     Args:
+    ----
         inheritance_graph: A dict or nx.Graph representing the inheritance graph.
 
     Returns:
+    -------
         A dict representing the inheritance tree.
+
     """
     if isinstance(inheritance_graph, nx.Graph):
         inheritance_tree = nx.to_dict_of_lists(inheritance_graph)
 
         multiple_parents_present = _multiple_inheritance_present(inheritance_tree)
         if multiple_parents_present:
-            logger.warning(
+            msg = (
                 "The ontology contains multiple inheritance (one child node "
                 "has multiple parent nodes). This is not visualized in the "
                 "following hierarchy tree (the child node is only added once). "
                 "If you wish to browse all relationships of the parsed "
                 "ontologies, write a graphml file to disk using "
-                "`to_disk = <directory>` and view this file."
+                "`to_disk = <directory>` and view this file.",
             )
-
+            logger.warning(msg)
         # unlist values
         inheritance_tree = {k: v[0] for k, v in inheritance_tree.items() if v}
         return inheritance_tree
     elif not _multiple_inheritance_present(inheritance_graph):
         return inheritance_graph
+    return None  # Explicit return for the case when neither condition is met
 
 
 def _multiple_inheritance_present(inheritance_tree: dict) -> bool:
-    """Checks if multiple inheritance is present in the inheritance_tree."""
+    """Check if multiple inheritance is present in the inheritance_tree."""
     return any(len(value) > 1 for value in inheritance_tree.values())
 
 
@@ -134,7 +126,9 @@ def _find_root_node(inheritance_tree: dict) -> tuple[set, str]:
         if "entity" in root:
             root = "entity"  # TODO: default: good standard?
         else:
-            raise ValueError("Inheritance tree cannot have more than one root node. " f"Found {len(root)}: {root}.")
+            msg = f"Inheritance tree cannot have more than one root node. Found {len(root)}: {root}."
+            logger.error(msg)
+            raise ValueError(msg)
     else:
         root = root[0]
     if not root:
@@ -158,53 +152,62 @@ def from_pascal(s: str, sep: str = " ") -> str:
 
 
 def pascalcase_to_sentencecase(s: str) -> str:
-    """
-    Convert PascalCase to sentence case.
+    """Convert PascalCase to sentence case.
 
     Args:
+    ----
         s: Input string in PascalCase
 
     Returns:
+    -------
         string in sentence case form
+
     """
     return from_pascal(s, sep=" ")
 
 
 def snakecase_to_sentencecase(s: str) -> str:
-    """
-    Convert snake_case to sentence case.
+    """Convert snake_case to sentence case.
 
     Args:
+    ----
         s: Input string in snake_case
 
     Returns:
+    -------
         string in sentence case form
+
     """
-    return stringcase.sentencecase(s).lower()
+    return " ".join(word.lower() for word in s.split("_"))
 
 
 def sentencecase_to_snakecase(s: str) -> str:
-    """
-    Convert sentence case to snake_case.
+    """Convert sentence case to snake_case.
 
     Args:
+    ----
         s: Input string in sentence case
 
     Returns:
+    -------
         string in snake_case form
+
     """
-    return stringcase.snakecase(s).lower()
+    return "_".join(s.lower().split())
 
 
 def sentencecase_to_pascalcase(s: str, sep: str = r"\s") -> str:
-    """
-    Convert sentence case to PascalCase.
+    """Convert sentence case to PascalCase.
 
     Args:
+    ----
         s: Input string in sentence case
+        sep: Separator for the words in the input string
 
     Returns:
+    -------
         string in PascalCase form
+
     """
     return re.sub(
         r"(?:^|[" + sep + "])([a-zA-Z])",
@@ -214,15 +217,18 @@ def sentencecase_to_pascalcase(s: str, sep: str = r"\s") -> str:
 
 
 def to_lower_sentence_case(s: str) -> str:
-    """
-    Convert any string to lower sentence case. Works with snake_case,
-    PascalCase, and sentence case.
+    """Convert any string to lower sentence case.
+
+    Works with snake_case, PascalCase, and sentence case.
 
     Args:
+    ----
         s: Input string
 
     Returns:
+    -------
         string in lower sentence case form
+
     """
     if "_" in s:
         return snakecase_to_sentencecase(s)
@@ -234,15 +240,17 @@ def to_lower_sentence_case(s: str) -> str:
         return s
 
 
-def is_nested(lst) -> bool:
-    """
-    Check if a list is nested.
+def is_nested(lst: list) -> bool:
+    """Check if a list is nested.
 
     Args:
+    ----
         lst (list): The list to check.
 
     Returns:
+    -------
         bool: True if the list is nested, False otherwise.
+
     """
     for item in lst:
         if isinstance(item, list):

{biocypher-0.9.1.dist-info → biocypher-0.9.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: biocypher
-Version: 0.9.1
+Version: 0.9.3
 Summary: A unifying framework for biomedical research knowledge graphs
 Home-page: https://github.com/biocypher/biocypher
 License: MIT
@@ -27,7 +27,6 @@ Requires-Dist: networkx (>=3.0,<4.0)
 Requires-Dist: pandas (>=2.0.1,<3.0.0)
 Requires-Dist: pooch (>=1.7.0,<2.0.0)
 Requires-Dist: rdflib (>=6.2.0,<7.0.0)
-Requires-Dist: stringcase (>=1.2.0,<2.0.0)
 Requires-Dist: tqdm (>=4.65.0,<5.0.0)
 Requires-Dist: treelib (==1.6.4)
 Project-URL: Bug Tracker, https://github.com/biocypher/biocypher/issues

{biocypher-0.9.1.dist-info → biocypher-0.9.3.dist-info}/RECORD

@@ -8,11 +8,11 @@ biocypher/_config/test_schema_config_extended.yaml,sha256=wn3A76142hhjnImhMF6ROD
 biocypher/_core.py,sha256=S8frW62bc0V9M6gwU5l_D2ESa-7xwbOTffRuPqbIbT0,27382
 biocypher/_create.py,sha256=QsvXrwEQ8k0uNXvCG06UKejvw-QsJwzSaumrBjx9n1k,9884
 biocypher/_deduplicate.py,sha256=rtglcaLRaVzNjLtaPwTGP8VvCM4PHYQ5CZ-cm32CrKQ,4840
-biocypher/_get.py,sha256=2kjiBFu_onGUhgOpV7IMfGX67jyY1rpHg_GWncEUdrc,13278
+biocypher/_get.py,sha256=BDNnvw6Xbz_Lq0ekU1Y60J4DI1zQKiZugJV6zGnWPsI,14873
 biocypher/_logger.py,sha256=y9dh3SPJOCWXnkFSYSK7aj_-pB7zlAkNCf43Dp1lt74,2941
 biocypher/_mapping.py,sha256=ntspG2C_NaQODhWTBFk0CDvolkOCjtqlQ9E-NkJAuTg,9030
-biocypher/_metadata.py,sha256=Eop3cijNQBsHWeOO8zbBmN_2ICJutZziDPvWppV474M,1415
-biocypher/_misc.py,sha256=N8aDg8j3EEcKf9ZRqzSNruUEUK4RixCy1vQ1V4maGxk,6079
+biocypher/_metadata.py,sha256=Z8vZYEjGXUNfcRhLpWBawExiESXuhhhIH7pxsbZYejU,1415
+biocypher/_misc.py,sha256=YzlY7zwa0mim9QFg9HwXErkJFIH3cvLrbgjF8tKOIT8,6353
 biocypher/_ontology.py,sha256=lipZxU3aj6zrTbBrJZmCW6IRCuz-KQG3AfbYCVq6aFE,33133
 biocypher/_translate.py,sha256=9E19eLRL0VnxxDuiNhZ5vu54XyKXnfLuBhCgNcL9yAE,17000
 biocypher/output/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -38,7 +38,7 @@ biocypher/output/write/relational/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeR
 biocypher/output/write/relational/_csv.py,sha256=m0BSQXts88Qu5AEvoIgnwRz54ia38g4VN3PaA3LCYM8,2807
 biocypher/output/write/relational/_postgresql.py,sha256=RckQJBiuwvDmHAyXxS8zCavYqDecHHWW_piofurokfQ,11965
 biocypher/output/write/relational/_sqlite.py,sha256=BuGWOeeNA83lbUvjpkzqcR9_baWLsbfmLXBKe4O1EPE,2105
-biocypher-0.9.1.dist-info/LICENSE,sha256=oejgxuxyjSnyPw3YPloz6-dCBB_nYizJ4jDQnr-xZUU,1082
-biocypher-0.9.1.dist-info/METADATA,sha256=Qjy-T-iNXAn0wye7-NbLivn7ZPz80ZrOu8utum7_4vk,10643
-biocypher-0.9.1.dist-info/WHEEL,sha256=FMvqSimYX_P7y0a7UY-_Mc83r5zkBZsCYPm7Lr0Bsq4,88
-biocypher-0.9.1.dist-info/RECORD,,
+biocypher-0.9.3.dist-info/LICENSE,sha256=oejgxuxyjSnyPw3YPloz6-dCBB_nYizJ4jDQnr-xZUU,1082
+biocypher-0.9.3.dist-info/METADATA,sha256=5V08qJIN2n5vsedgGbk-ChO0OjrNxR5hJRvM4YEPSfo,10600
+biocypher-0.9.3.dist-info/WHEEL,sha256=FMvqSimYX_P7y0a7UY-_Mc83r5zkBZsCYPm7Lr0Bsq4,88
+biocypher-0.9.3.dist-info/RECORD,,