biocypher 0.5.44__py3-none-any.whl → 0.6.1__py3-none-any.whl

biocypher/__init__.py

@@ -21,10 +21,11 @@ __all__ = [
     "log",
     "Driver",
     "BioCypher",
-    "Resource",
+    "FileDownload",
+    "APIRequest",
 ]
 
-from ._get import Resource
+from ._get import APIRequest, FileDownload
 from ._core import BioCypher
 from ._config import config, module_data
 from ._logger import log, logger, logfile

biocypher/_get.py

@@ -17,10 +17,13 @@ from __future__ import annotations
 from typing import Optional
 import shutil
 
+import requests
+
 from ._logger import logger
 
 logger.debug(f"Loading module {__name__}.")
 
+from abc import ABC
 from datetime import datetime, timedelta
 from tempfile import TemporaryDirectory
 import os
@@ -29,21 +32,22 @@ import ftplib
 
 import pooch
 
-from ._misc import to_list
+from ._misc import to_list, is_nested
 
 
-class Resource:
+class Resource(ABC):
     def __init__(
         self,
         name: str,
         url_s: str | list[str],
         lifetime: int = 0,
-        is_dir: bool = False,
     ):
         """
-        A resource is a file that can be downloaded from a URL and cached
-        locally. This class implements checks of the minimum requirements for
-        a resource, to be implemented by a biocypher adapter.
+
+        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.
@@ -52,43 +56,83 @@ class Resource:
 
             lifetime (int): The lifetime of the resource in days. If 0, the
                 resource is considered to be permanent.
-
-            is_dir (bool): Whether the resource is a directory or not.
         """
         self.name = name
         self.url_s = url_s
         self.lifetime = lifetime
+
+
+class FileDownload(Resource):
+    def __init__(
+        self,
+        name: str,
+        url_s: str | list[str],
+        lifetime: int = 0,
+        is_dir: bool = False,
+    ):
+        """
+        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.
+
+            lifetime(int): The lifetime of the File Download in days. If 0, the
+                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):
+        """
+        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.
+
+            lifetime(int): The lifetime of the API Request in days. If 0, the
+                API Request is cached indefinitely.
+
+        """
+        super().__init__(name, url_s, lifetime)
+
+
 class Downloader:
     def __init__(self, cache_dir: Optional[str] = None) -> None:
         """
-        A downloader is a collection of resources that can be downloaded
+        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.
-
-        Returns:
-            Downloader: The downloader object.
         """
         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()
 
-    # download function that accepts a resource or a list of resources
     def download(self, *resources: Resource):
         """
-        Download one or multiple resources.
+        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 or resources to download.
+            resources (Resource): The resource(s) to download or load from
+                cache.
 
         Returns:
-            str or list: The path or paths to the downloaded resource(s).
+            list[str]: The path or paths to the resource(s) that were downloaded
+                or loaded from cache.
+
         """
         paths = []
         for resource in resources:
@@ -106,16 +150,27 @@ class Downloader:
 
         Args:
             resource (Resource): The resource to download.
-
         Returns:
-            str or list: The path or paths to the downloaded resource(s).
+            list[str]: The path or paths to the downloaded resource(s).
+
+
         """
         expired = self._is_cache_expired(resource)
 
         if expired or not cache:
-            self._delete_expired_resource_cache(resource)
-            logger.info(f"Asking for download of {resource.name}.")
-            paths = self._download_resource(cache, resource)
+            self._delete_expired_cache(resource)
+            if isinstance(resource, FileDownload):
+                logger.info(f"Asking for download of resource {resource.name}.")
+                paths = self._download_files(cache, resource)
+            elif isinstance(resource, APIRequest):
+                logger.info(
+                    f"Asking for download of api request {resource.name}."
+                )
+                paths = self._download_api_request(resource)
+
+            else:
+                raise TypeError(f"Unknown resource type: {type(resource)}")
+
         else:
             paths = self.get_cached_version(resource)
         self._update_cache_record(resource)
@@ -123,13 +178,14 @@ class Downloader:
 
     def _is_cache_expired(self, resource: Resource) -> bool:
         """
-        Check if resource cache is expired.
+        Check if resource or API request cache is expired.
 
         Args:
-            resource (Resource): The resource to download.
+
+            resource (Resource): The resource or API request to download.
 
         Returns:
-            bool: cache is expired or not.
+            bool: True if cache is expired, False if not.
         """
         cache_record = self._get_cache_record(resource)
         if cache_record:
@@ -142,65 +198,115 @@ class Downloader:
             expired = True
         return expired
 
-    def _delete_expired_resource_cache(self, resource: Resource):
-        resource_cache_path = self.cache_dir + "/" + resource.name
-        if os.path.exists(resource_cache_path) and os.path.isdir(
-            resource_cache_path
+    def _delete_expired_cache(self, resource: Resource):
+        cache_resource_path = self.cache_dir + "/" + resource.name
+        if os.path.exists(cache_resource_path) and os.path.isdir(
+            cache_resource_path
         ):
-            shutil.rmtree(resource_cache_path)
+            shutil.rmtree(cache_resource_path)
 
-    def _download_resource(self, cache, resource):
-        """Download a resource.
+    def _download_files(self, cache, file_download: FileDownload):
+        """
+        Download a resource given it is a file or a directory and return the
+        path.
 
         Args:
             cache (bool): Whether to cache the resource or not.
-            resource (Resource): The resource to download.
+            file_download (FileDownload): The resource to download.
 
         Returns:
-            str or list: The path or paths to the downloaded resource(s).
+            list[str]: The path or paths to the downloaded resource(s).
         """
-        if resource.is_dir:
-            files = self._get_files(resource)
-            resource.url_s = [resource.url_s + "/" + file for file in files]
-            resource.is_dir = False
-            paths = self._download_or_cache(resource, cache)
-        elif isinstance(resource.url_s, list):
+        if file_download.is_dir:
+            files = self._get_files(file_download)
+            file_download.url_s = [
+                file_download.url_s + "/" + file for file in files
+            ]
+            file_download.is_dir = False
+            paths = self._download_or_cache(file_download, cache)
+        elif isinstance(file_download.url_s, list):
             paths = []
-            for url in resource.url_s:
-                fname = url[url.rfind("/") + 1 :]
-                paths.append(
-                    self._retrieve(
-                        url=url,
-                        fname=fname,
-                        path=os.path.join(self.cache_dir, resource.name),
-                    )
+            for url in file_download.url_s:
+                fname = url[url.rfind("/") + 1 :].split("?")[0]
+                path = self._retrieve(
+                    url=url,
+                    fname=fname,
+                    path=os.path.join(self.cache_dir, file_download.name),
                 )
+                paths.append(path)
         else:
-            fname = resource.url_s[resource.url_s.rfind("/") + 1 :]
-            paths = self._retrieve(
-                url=resource.url_s,
+            paths = []
+            fname = file_download.url_s[
+                file_download.url_s.rfind("/") + 1 :
+            ].split("?")[0]
+            results = self._retrieve(
+                url=file_download.url_s,
                 fname=fname,
-                path=os.path.join(self.cache_dir, resource.name),
+                path=os.path.join(self.cache_dir, file_download.name),
             )
+            if isinstance(results, list):
+                paths.extend(results)
+            else:
+                paths.append(results)
+
         # sometimes a compressed file contains multiple files
         # TODO ask for a list of files in the archive to be used from the
         # adapter
         return paths
 
-    def get_cached_version(self, resource) -> list[str]:
+    def _download_api_request(self, api_request: APIRequest):
+        """
+        Download an API request and return the path.
+
+        Args:
+            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]
+            logger.info(
+                f"Asking for caching API of {api_request.name} {fname}."
+            )
+            response = requests.get(url=url)
+
+            if response.status_code != 200:
+                response.raise_for_status()
+            response_data = response.json()
+            api_path = os.path.join(
+                self.cache_dir, api_request.name, f"{fname}.json"
+            )
+
+            os.makedirs(os.path.dirname(api_path), exist_ok=True)
+            with open(api_path, "w") as f:
+                json.dump(response_data, f)
+                logger.info(f"Caching API request to {api_path}.")
+            paths.append(api_path)
+        return paths
+
+    def get_cached_version(self, resource: Resource) -> list[str]:
         """Get the cached version of a resource.
 
         Args:
-            resource (Resource): The resource to get the cached version of.
+            resource(Resource): The resource to get the cached version of.
 
         Returns:
             list[str]: The paths to the cached resource(s).
+
         """
-        cached_resource_location = os.path.join(self.cache_dir, resource.name)
-        logger.info(f"Use cached version from {cached_resource_location}.")
+        cached_location = os.path.join(self.cache_dir, resource.name)
+        logger.info(f"Use cached version from {cached_location}.")
         paths = []
-        for file in os.listdir(cached_resource_location):
-            paths.append(os.path.join(cached_resource_location, file))
+        for file in os.listdir(cached_location):
+            paths.append(os.path.join(cached_location, file))
         return paths
 
     def _retrieve(
@@ -260,23 +366,23 @@ class Downloader:
                 progressbar=True,
             )
 
-    def _get_files(self, resource: Resource):
+    def _get_files(self, file_download: FileDownload):
         """
-        Get the files contained in a directory resource.
+        Get the files contained in a directory file.
 
         Args:
-            resource (Resource): The directory resource.
+            file_download (FileDownload): The directory file.
 
         Returns:
             list: The files contained in the directory.
         """
-        if resource.url_s.startswith("ftp://"):
+        if file_download.url_s.startswith("ftp://"):
             # remove protocol
-            url = resource.url_s[6:]
+            url = file_download.url_s[6:]
             # get base url
             url = url[: url.find("/")]
             # get directory (remove initial slash as well)
-            dir = resource.url_s[7 + len(url) :]
+            dir = file_download.url_s[7 + len(url) :]
             # get files
             ftp = ftplib.FTP(url)
             ftp.login()
@@ -334,19 +440,3 @@ 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 is_nested(lst):
-    """
-    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):
-            return True
-    return False

biocypher/_metadata.py

@@ -19,7 +19,7 @@ import importlib.metadata
 
 import toml
 
-_VERSION = "0.5.44"
+_VERSION = "0.6.1"
 
 
 def get_metadata():

biocypher/_misc.py

@@ -246,3 +246,19 @@ def to_lower_sentence_case(s: str) -> str:
         return pascalcase_to_sentencecase(s)
     else:
         return s
+
+
+def is_nested(lst) -> 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):
+            return True
+    return False

{biocypher-0.5.44.dist-info → biocypher-0.6.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: biocypher
-Version: 0.5.44
+Version: 0.6.1
 Summary: A unifying framework for biomedical research knowledge graphs
 Home-page: https://github.com/biocypher/biocypher
 License: MIT

{biocypher-0.5.44.dist-info → biocypher-0.6.1.dist-info}/RECORD

@@ -1,4 +1,4 @@
-biocypher/__init__.py,sha256=ejNY53vH_pE3ZbIN8G_ZBYxxPG9aERovRLD0XhDvt4k,942
+biocypher/__init__.py,sha256=-vr7dGUv6QK7f_i9mmUK5WpMsZuFPflUEFC4oElJTCA,980
 biocypher/_config/__init__.py,sha256=fFHRFYxE2MtDAQWL6upe--MJ1vw3Z8CwIPhF2gW8cRU,3698
 biocypher/_config/biocypher_config.yaml,sha256=pusj0IjJM3uWRcm0N7U7mb1IX257HCV2reZV3YKFCk0,3037
 biocypher/_config/test_config.yaml,sha256=Np8jeS5_EP6HHOvMKb7B_Tkyqd5YaYlYz_DVsXypt-A,119
@@ -8,11 +8,11 @@ biocypher/_config/test_schema_config_extended.yaml,sha256=wn3A76142hhjnImhMF6ROD
 biocypher/_core.py,sha256=m4o4Szv2xY2gl3PnNAA9m7Gg5Sgd8iR9THv3RDyZlQ8,22618
 biocypher/_create.py,sha256=vpUchUdEpWupZi1LgFLxAWMtqoBwnWbP7PwEDUCBS4A,10202
 biocypher/_deduplicate.py,sha256=BBvfpXzu6L5YDY5FdtXxnf8YlsbJpbCE8RdUoKsm0n0,4949
-biocypher/_get.py,sha256=3Kpky3blfNf1JwxKWLsZxTU2aTP_C4sUe8OpiyYj63I,10810
+biocypher/_get.py,sha256=1FHs4n2R2k7OVWtVe7euF2J5WpsUXsFAmnpdSYuhLvY,13817
 biocypher/_logger.py,sha256=NGXe3hZA79WSujfOgpcxHBf8N2QAfrmvM1LFDpsGK2U,3185
 biocypher/_mapping.py,sha256=ERSNH2Bg19145KytxbFE4BInPaiP-LWW7osOBot29Eo,9304
-biocypher/_metadata.py,sha256=HTVcugUBYLbM1r3SEl-J9hiNGlPqic1zqXtMlLyTwH8,1658
-biocypher/_misc.py,sha256=18EG2Bei3RnyWXDWc3qtZaT3gybvXI8opi0HvSaF7Lg,6066
+biocypher/_metadata.py,sha256=E4Ei48t7ZASflo58HSMUoLe8WlQnNt0d5w-68FantVA,1657
+biocypher/_misc.py,sha256=oKNfmj9mUKDYtmx-R6FCZxRa7AOut3VKZZm16KFimyY,6363
 biocypher/_ontology.py,sha256=G5k-bnzvPZUqhLPxtoOPFa4OSQ4JpufgozVakLTjwLg,31789
 biocypher/_translate.py,sha256=JafvhtVaFSpruRfYh9BzjVbvDF1Mhg7LLKMDZHWkRjg,16496
 biocypher/output/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -33,7 +33,7 @@ biocypher/output/write/relational/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeR
 biocypher/output/write/relational/_csv.py,sha256=eyAtmwfCNYnuVbkpd0rUoo9KgG2KPgopZVA3X97tRLU,2919
 biocypher/output/write/relational/_postgresql.py,sha256=6sABZaELzmV7a2aUy2iRksf28WFsc3EA9mdQ2mShPeM,11959
 biocypher/output/write/relational/_sqlite.py,sha256=ozElhca1YCYq8R-VFh-LDsnPBaXVJm2cvEboBK2LVVY,2073
-biocypher-0.5.44.dist-info/LICENSE,sha256=SjUaQkq671iQUZOxEUpC4jvJxXOlfSiHTTueyz9kXJM,1065
-biocypher-0.5.44.dist-info/METADATA,sha256=_a0l4S_OPALMmrpEhbKWuwtPcSzWRursqJKMEAkrZaw,10642
-biocypher-0.5.44.dist-info/WHEEL,sha256=Zb28QaM1gQi8f4VCBhsUklF61CTlNYfs9YAZn-TOGFk,88
-biocypher-0.5.44.dist-info/RECORD,,
+biocypher-0.6.1.dist-info/LICENSE,sha256=SjUaQkq671iQUZOxEUpC4jvJxXOlfSiHTTueyz9kXJM,1065
+biocypher-0.6.1.dist-info/METADATA,sha256=WR311EH67e8M_0wNaHbo88a7zU2Tl4y681GyI1fC4xY,10641
+biocypher-0.6.1.dist-info/WHEEL,sha256=Zb28QaM1gQi8f4VCBhsUklF61CTlNYfs9YAZn-TOGFk,88
+biocypher-0.6.1.dist-info/RECORD,,