biocypher 0.6.2__py3-none-any.whl → 0.7.0__py3-none-any.whl

biocypher/_create.py

@@ -1,23 +1,16 @@
-#!/usr/bin/env python
-#
-# Copyright 2021, Heidelberg University Clinic
-#
-# File author(s): Sebastian Lobentanzer
-#                 ...
-#
-# Distributed under MIT licence, see the file `LICENSE`.
-#
 """
 BioCypher 'create' module. Handles the creation of BioCypher node and edge
 dataclasses.
 """
-from ._logger import logger
 
-logger.debug(f"Loading module {__name__}.")
+import os
 
+from dataclasses import dataclass, field
 from typing import Union
-from dataclasses import field, dataclass
-import os
+
+from ._logger import logger
+
+logger.debug(f"Loading module {__name__}.")
 
 __all__ = [
     "BioCypherEdge",
@@ -71,8 +64,7 @@ class BioCypherNode:
 
         if ":TYPE" in self.properties.keys():
             logger.warning(
-                "Keyword ':TYPE' is reserved for Neo4j. "
-                "Removing from properties.",
+                "Keyword ':TYPE' is reserved for Neo4j. Removing from properties.",
                 # "Renaming to 'type'."
             )
             # self.properties["type"] = self.properties[":TYPE"]
@@ -209,24 +201,21 @@ class BioCypherEdge:
 
         if ":TYPE" in self.properties.keys():
             logger.debug(
-                "Keyword ':TYPE' is reserved for Neo4j. "
-                "Removing from properties.",
+                "Keyword ':TYPE' is reserved for Neo4j. Removing from properties.",
                 # "Renaming to 'type'."
             )
             # self.properties["type"] = self.properties[":TYPE"]
             del self.properties[":TYPE"]
         elif "id" in self.properties.keys():
             logger.debug(
-                "Keyword 'id' is reserved for Neo4j. "
-                "Removing from properties.",
+                "Keyword 'id' is reserved for Neo4j. Removing from properties.",
                 # "Renaming to 'type'."
             )
             # self.properties["type"] = self.properties[":TYPE"]
             del self.properties["id"]
         elif "_ID" in self.properties.keys():
             logger.debug(
-                "Keyword '_ID' is reserved for Postgres. "
-                "Removing from properties.",
+                "Keyword '_ID' is reserved for Postgres. Removing from properties.",
                 # "Renaming to 'type'."
             )
             # self.properties["type"] = self.properties[":TYPE"]
@@ -334,20 +323,17 @@ class BioCypherRelAsNode:
     def __post_init__(self):
         if not isinstance(self.node, BioCypherNode):
             raise TypeError(
-                f"BioCypherRelAsNode.node must be a BioCypherNode, "
-                f"not {type(self.node)}.",
+                f"BioCypherRelAsNode.node must be a BioCypherNode, " f"not {type(self.node)}.",
             )
 
         if not isinstance(self.source_edge, BioCypherEdge):
             raise TypeError(
-                f"BioCypherRelAsNode.source_edge must be a BioCypherEdge, "
-                f"not {type(self.source_edge)}.",
+                f"BioCypherRelAsNode.source_edge must be a BioCypherEdge, " f"not {type(self.source_edge)}.",
             )
 
         if not isinstance(self.target_edge, BioCypherEdge):
             raise TypeError(
-                f"BioCypherRelAsNode.target_edge must be a BioCypherEdge, "
-                f"not {type(self.target_edge)}.",
+                f"BioCypherRelAsNode.target_edge must be a BioCypherEdge, " f"not {type(self.target_edge)}.",
             )
 
     def get_node(self) -> BioCypherNode:

biocypher/_deduplicate.py

@@ -1,9 +1,8 @@
+from ._create import BioCypherEdge, BioCypherNode, BioCypherRelAsNode
 from ._logger import logger
 
 logger.debug(f"Loading module {__name__}.")
 
-from ._create import BioCypherEdge, BioCypherNode, BioCypherRelAsNode
-
 
 class Deduplicator:
     """
@@ -45,9 +44,7 @@ class Deduplicator:
         if entity.get_id() in self.seen_entity_ids:
             self.duplicate_entity_ids.add(entity.get_id())
             if entity.get_label() not in self.duplicate_entity_types:
-                logger.warning(
-                    f"Duplicate node type {entity.get_label()} found. "
-                )
+                logger.warning(f"Duplicate node type {entity.get_label()} found. ")
                 self.duplicate_entity_types.add(entity.get_label())
             return True
 
@@ -69,18 +66,14 @@ class Deduplicator:
 
         # concatenate source and target if no id is present
         if not relationship.get_id():
-            _id = (
-                f"{relationship.get_source_id()}_{relationship.get_target_id()}"
-            )
+            _id = f"{relationship.get_source_id()}_{relationship.get_target_id()}"
         else:
             _id = relationship.get_id()
 
         if _id in self.seen_relationships[relationship.get_type()]:
             self.duplicate_relationship_ids.add(_id)
             if relationship.get_type() not in self.duplicate_relationship_types:
-                logger.warning(
-                    f"Duplicate edge type {relationship.get_type()} found. "
-                )
+                logger.warning(f"Duplicate edge type {relationship.get_type()} found. ")
                 self.duplicate_relationship_types.add(relationship.get_type())
             return True
 

biocypher/_get.py

@@ -1,38 +1,26 @@
-#!/usr/bin/env python
-
-#
-# Copyright 2021, Heidelberg University Clinic
-#
-# File author(s): Sebastian Lobentanzer
-#                 ...
-#
-# Distributed under MIT licence, see the file `LICENSE`.
-#
 """
 BioCypher get module. Used to download and cache data from external sources.
 """
 
 from __future__ import annotations
 
-from typing import Optional
+import ftplib
+import json
+import os
 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
-import json
-import ftplib
+from typing import Optional
 
 import pooch
+import requests
 
-from ._misc import to_list, is_nested
+from ._logger import logger
+from ._misc import is_nested, to_list
+
+logger.debug(f"Loading module {__name__}.")
 
 
 class Resource(ABC):
@@ -43,7 +31,6 @@ class Resource(ABC):
         lifetime: int = 0,
     ):
         """
-
         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
@@ -153,7 +140,6 @@ class Downloader:
         Returns:
             list[str]: The path or paths to the downloaded resource(s).
 
-
         """
         expired = self._is_cache_expired(resource)
 
@@ -163,14 +149,10 @@ class Downloader:
                 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}."
-                )
+                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)
@@ -181,17 +163,14 @@ class Downloader:
         Check if resource or API request cache is expired.
 
         Args:
-
-            resource (Resource): The resource or API request to download.
+            resource (Resource): The resource to download.
 
         Returns:
-            bool: True if cache is expired, False if not.
+            bool: cache is expired or not.
         """
         cache_record = self._get_cache_record(resource)
         if cache_record:
-            download_time = datetime.strptime(
-                cache_record.get("date_downloaded"), "%Y-%m-%d %H:%M:%S.%f"
-            )
+            download_time = datetime.strptime(cache_record.get("date_downloaded"), "%Y-%m-%d %H:%M:%S.%f")
             lifetime = timedelta(days=resource.lifetime)
             expired = download_time + lifetime < datetime.now()
         else:
@@ -200,9 +179,7 @@ class Downloader:
 
     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
-        ):
+        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):
@@ -219,9 +196,7 @@ class Downloader:
         """
         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.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):
@@ -236,9 +211,7 @@ class Downloader:
                 paths.append(path)
         else:
             paths = []
-            fname = file_download.url_s[
-                file_download.url_s.rfind("/") + 1 :
-            ].split("?")[0]
+            fname = file_download.url_s[file_download.url_s.rfind("/") + 1 :].split("?")[0]
             results = self._retrieve(
                 url=file_download.url_s,
                 fname=fname,
@@ -259,31 +232,22 @@ class Downloader:
         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]
-        )
+        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}."
-            )
+            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"
-            )
+            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:
@@ -300,7 +264,6 @@ class Downloader:
 
         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}.")
@@ -390,9 +353,7 @@ class Downloader:
             files = ftp.nlst()
             ftp.quit()
         else:
-            raise NotImplementedError(
-                "Only FTP directories are supported at the moment."
-            )
+            raise NotImplementedError("Only FTP directories are supported at the moment.")
 
         return files
 

biocypher/_logger.py

@@ -1,23 +1,14 @@
-#!/usr/bin/env python
-
-#
-# Copyright 2021, Heidelberg University Clinic
-#
-# File author(s): Sebastian Lobentanzer
-#                 ...
-#
-# Distributed under MIT licence, see the file `LICENSE`.
-#
 """
 Configuration of the module logger.
 """
 
 __all__ = ["get_logger", "log", "logfile"]
 
-from datetime import datetime
+import logging
 import os
 import pydoc
-import logging
+
+from datetime import datetime
 
 from biocypher import _config
 from biocypher._metadata import __version__
@@ -63,10 +54,7 @@ def get_logger(name: str = "biocypher") -> logging.Logger:
         log_to_disk = _config.config("biocypher").get("log_to_disk")
 
         if log_to_disk:
-            logdir = (
-                _config.config("biocypher").get("log_directory")
-                or "biocypher-log"
-            )
+            logdir = _config.config("biocypher").get("log_directory") or "biocypher-log"
             os.makedirs(logdir, exist_ok=True)
             logfile = os.path.join(logdir, f"biocypher-{date_time}.log")
 

biocypher/_mapping.py

@@ -1,20 +1,7 @@
-#!/usr/bin/env python
-
-#
-# Copyright 2021, Heidelberg University Clinic
-#
-# File author(s): Sebastian Lobentanzer
-#                 ...
-#
-# Distributed under MIT licence, see the file `LICENSE`.
-#
 """
 BioCypher 'mapping' module. Handles the mapping of user-defined schema to the
 underlying ontology.
 """
-from ._logger import logger
-
-logger.debug(f"Loading module {__name__}.")
 
 from typing import Optional
 from urllib.request import urlopen
@@ -22,7 +9,9 @@ from urllib.request import urlopen
 import yaml
 
 from . import _misc
-from ._config import config as _config
+from ._logger import logger
+
+logger.debug(f"Loading module {__name__}.")
 
 
 class OntologyMapping:
@@ -151,9 +140,7 @@ class OntologyMapping:
                 if parent_props:
                     v["properties"].update(parent_props)
 
-                parent_excl_props = self.schema[parent].get(
-                    "exclude_properties", {}
-                )
+                parent_excl_props = self.schema[parent].get("exclude_properties", {})
                 if parent_excl_props:
                     v["exclude_properties"].update(parent_excl_props)
 

biocypher/_metadata.py

@@ -1,25 +1,16 @@
-#!/usr/bin/env python
-#
-# Copyright 2021, Heidelberg University Clinic
-#
-# File author(s): Sebastian Lobentanzer
-#                 ...
-#
-# Distributed under MIT licence, see the file `LICENSE`.
-#
 """
 Package metadata (version, authors, etc).
 """
 
 __all__ = ["get_metadata"]
 
+import importlib.metadata
 import os
 import pathlib
-import importlib.metadata
 
 import toml
 
-_VERSION = "0.6.2"
+_VERSION = "0.7.0"
 
 
 def get_metadata():
@@ -52,10 +43,7 @@ def get_metadata():
 
     if not meta:
         try:
-            meta = {
-                k.lower(): v
-                for k, v in importlib.metadata.metadata(here.name).items()
-            }
+            meta = {k.lower(): v for k, v in importlib.metadata.metadata(here.name).items()}
 
         except importlib.metadata.PackageNotFoundError:
             pass

biocypher/_misc.py

@@ -1,36 +1,29 @@
-#!/usr/bin/env python
-
-#
-# Copyright 2021, Heidelberg University Clinic
-#
-# File author(s): Sebastian Lobentanzer
-#                 ...
-#
-# Distributed under MIT licence, see the file `LICENSE`.
-#
 """
 Handy functions for use in various places.
 """
-from ._logger import logger
 
-logger.debug(f"Loading module {__name__}.")
+import re
 
+from collections.abc import Iterable
 from typing import (
     Any,
-    Union,
-    Mapping,
-    KeysView,
     Generator,
     ItemsView,
+    KeysView,
+    Mapping,
+    Union,
     ValuesView,
 )
-from collections.abc import Iterable
-import re
 
-from treelib import Tree
 import networkx as nx
 import stringcase
 
+from treelib import Tree
+
+from ._logger import logger
+
+logger.debug(f"Loading module {__name__}.")
+
 __all__ = ["LIST_LIKE", "SIMPLE_TYPES", "ensure_iterable", "to_list"]
 
 SIMPLE_TYPES = (
@@ -110,9 +103,7 @@ def _get_inheritance_tree(inheritance_graph: Union[dict, nx.Graph]) -> dict:
     if isinstance(inheritance_graph, nx.Graph):
         inheritance_tree = nx.to_dict_of_lists(inheritance_graph)
 
-        multiple_parents_present = _multiple_inheritance_present(
-            inheritance_tree
-        )
+        multiple_parents_present = _multiple_inheritance_present(inheritance_tree)
         if multiple_parents_present:
             logger.warning(
                 "The ontology contains multiple inheritance (one child node "
@@ -143,17 +134,12 @@ 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}."
-            )
+            raise ValueError("Inheritance tree cannot have more than one root node. " f"Found {len(root)}: {root}.")
     else:
         root = root[0]
     if not root:
         # find key whose value is None
-        root = list(inheritance_tree.keys())[
-            list(inheritance_tree.values()).index(None)
-        ]
+        root = list(inheritance_tree.keys())[list(inheritance_tree.values()).index(None)]
     return classes, root