eva-sub-cli 0.4.4__py3-none-any.whl

eva_sub_cli/__init__.py

@@ -0,0 +1,27 @@
+import os
+
+
+ROOT_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))  # This is your Project Root
+PACKAGE_DIR = os.path.dirname(os.path.abspath(__file__))
+NEXTFLOW_DIR = os.path.join(PACKAGE_DIR, 'nextflow')
+ETC_DIR = os.path.join(PACKAGE_DIR, 'etc')
+LSRI_CLIENT_ID = "aa0fcc42-096a-4f9d-b871-aceb1a97d174"
+
+SUB_CLI_CONFIG_FILE = ".eva_sub_cli_config.yml"
+
+# Environment variable
+SUBMISSION_WS_VAR = 'SUBMISSION_WS_URL'
+ENA_WEBIN_ACCOUNT_VAR = 'ENA_WEBIN_ACCOUNT'
+ENA_WEBIN_PASSWORD_VAR = 'ENA_WEBIN_PASSWORD'
+
+
+try:
+    # If setuptools_scm is installed we can get the version directly from it
+    from setuptools_scm import get_version
+    __version__ = get_version(root='..', relative_to=__file__)
+    del get_version
+except:
+    # otherwise assume that we're working in a deployed instance which should have the _version file
+    from ._version import version as __version__
+
+

eva_sub_cli/_version.py

@@ -0,0 +1,21 @@
+# file generated by setuptools-scm
+# don't change, don't track in version control
+
+__all__ = ["__version__", "__version_tuple__", "version", "version_tuple"]
+
+TYPE_CHECKING = False
+if TYPE_CHECKING:
+    from typing import Tuple
+    from typing import Union
+
+    VERSION_TUPLE = Tuple[Union[int, str], ...]
+else:
+    VERSION_TUPLE = object
+
+version: str
+__version__: str
+__version_tuple__: VERSION_TUPLE
+version_tuple: VERSION_TUPLE
+
+__version__ = version = '0.4.4'
+__version_tuple__ = version_tuple = (0, 4, 4)

eva_sub_cli/auth.py

@@ -0,0 +1,106 @@
+import json
+import os
+from functools import cached_property
+from getpass import getpass
+
+import requests
+from ebi_eva_common_pyutils.logger import AppLogger
+from urllib3.exceptions import ResponseError
+
+from eva_sub_cli import LSRI_CLIENT_ID, ENA_WEBIN_ACCOUNT_VAR, ENA_WEBIN_PASSWORD_VAR
+
+ENA_AUTH_URL = "https://www.ebi.ac.uk/ena/submit/webin/auth/token"
+LSRI_AUTH_URL = "https://www.ebi.ac.uk/eva/v1/submission/auth/lsri"
+DEVICE_AUTHORISATION_URL = "https://login.elixir-czech.org/oidc/devicecode"
+
+
+class LSRIAuth(AppLogger):
+    def __init__(self, client_id=LSRI_CLIENT_ID, device_authorization_url=DEVICE_AUTHORISATION_URL,
+                 auth_url=LSRI_AUTH_URL):
+        self.client_id = client_id
+        self.device_authorization_url = device_authorization_url
+        self.auth_url = auth_url
+
+    @cached_property
+    def token(self):
+        # Step 1: Get device code using device auth url
+        payload = {
+            'client_id': self.client_id,
+            'scope': 'openid'
+        }
+        response = requests.post(self.device_authorization_url, data=payload)
+        response.raise_for_status()
+
+        response_json = response.json()
+        device_code = response_json['device_code']
+        user_code = response_json['user_code']
+        verification_uri = response_json['verification_uri']
+        expires_in = response_json['expires_in']
+
+        # Display the user code and verification URI to the user
+        print(f'Please visit {verification_uri} and enter this user code: {user_code}')
+        # Delegate subsequent post-authentication processing (which requires LSRI client secret) to eva-submission-ws
+        # so that we can avoid storing that client secret in eva-sub-eva
+        response = requests.post(self.auth_url, timeout=expires_in,
+                                 headers={'Accept': 'application/hal+json'},
+                                 params={"deviceCode": device_code, "expiresIn": expires_in})
+        if response.status_code == 200:
+            self.info("LSRI authentication successful!")
+            return response.text
+        else:
+            raise ResponseError('LSRI Authentication Error')
+
+
+class WebinAuth(AppLogger):
+
+    def __init__(self, ena_auth_url=ENA_AUTH_URL, username=None, password=None):
+        self.ena_auth_url = ena_auth_url
+        self.cmd_line_username = username
+        self.cmd_line_password = password
+
+    @cached_property
+    def token(self):
+        self.info("ENA Webin authentication")
+        username, password = self._get_webin_username_password()
+        headers = {"accept": "*/*", "Content-Type": "application/json"}
+        data = {"authRealms": ["ENA"], "username": username, "password": password}
+        response = requests.post(self.ena_auth_url, headers=headers, data=json.dumps(data))
+
+        if response.status_code == 200:
+            self.info("Webin authentication successful!")
+            return response.text
+        else:
+            raise ResponseError('Webin Authentication Error')
+
+    def _get_webin_username_password(self):
+        username = self.cmd_line_username
+        password = self.cmd_line_password
+        if not username or not password:
+            self.debug('No username and password provided on the command line')
+            username, password = self._get_webin_username_password_from_env()
+        if not username or not password:
+            self.debug('No username and password provided in environment variables')
+            username, password = self._get_webin_username_password_from_stdin()
+        return username, password
+
+    def _get_webin_username_password_from_env(self):
+        username = os.environ.get(ENA_WEBIN_ACCOUNT_VAR)
+        password = os.environ.get(ENA_WEBIN_PASSWORD_VAR)
+        return username, password
+
+    def _get_webin_username_password_from_stdin(self):
+        username = input("Enter your ENA Webin username: ")
+        password = getpass("Enter your ENA Webin password: ")
+        return username, password
+
+
+# Global auth for the session
+auth = None
+
+
+def get_auth(username=None, password=None):
+    global auth
+    if auth:
+        return auth
+    auth = WebinAuth(username=username, password=password)
+    return auth

eva_sub_cli/date_utils.py

@@ -0,0 +1,32 @@
+import datetime
+
+# Values coming from https://www.ebi.ac.uk/ena/browser/view/ERC000011
+not_provided_check_list = ['not provided', 'not collected', 'restricted access', 'missing: control sample',
+                           'missing: sample group', 'missing: synthetic construct', 'missing: lab stock',
+                           'missing: third party data', 'missing: data agreement established pre-2023',
+                           'missing: endangered species', 'missing: human-identifiable']
+
+
+def check_date(date):
+    return isinstance(date, datetime.date) or \
+           isinstance(date, datetime.datetime) or \
+           check_date_str_format(date) or \
+           str(date).lower() in not_provided_check_list
+
+
+def check_date_str_format(d):
+    try:
+        datetime.datetime.strptime(d, "%Y-%m-%d")
+        return True
+    except ValueError:
+        pass
+    try:
+        datetime.datetime.strptime(d, "%Y-%m")
+        return True
+    except ValueError:
+        pass
+    try:
+        datetime.datetime.strptime(d, "%Y")
+        return True
+    except ValueError:
+        return False

eva_sub_cli/etc/eva-biosamples.json

@@ -0,0 +1,174 @@
+{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "$id": "eva-biosamples.json",
+  "additionalProperties": true,
+  "definitions": {
+    "nonEmptyString": {
+      "type": "string",
+      "minLength": 1
+    }
+  },
+  "required": [
+    "name",
+    "characteristics"
+  ],
+  "title": "sample",
+  "type": "object",
+  "properties": {
+    "name": {
+      "type": "string"
+    },
+    "accession": {
+      "type": "string"
+    },
+    "characteristics": {
+      "type": "object",
+      "anyOf": [
+        {
+          "required": [
+            "organism"
+          ]
+        },
+        {
+          "required": [
+            "Organism"
+          ]
+        },
+        {
+          "required": [
+            "species"
+          ]
+        },
+        {
+          "required": [
+            "Species"
+          ]
+        }
+      ],
+      "properties": {
+        "organism": {
+          "type": "array",
+          "items": {
+            "properties": {
+              "text": {
+                "$ref": "#/definitions/nonEmptyString"
+              }
+            },
+            "required": [
+              "text"
+            ]
+          }
+        },
+        "Organism": {
+          "type": "array",
+          "items": {
+            "properties": {
+              "text": {
+                "$ref": "#/definitions/nonEmptyString"
+              }
+            },
+            "required": [
+              "text"
+            ]
+          }
+        },
+        "Species": {
+          "type": "array",
+          "items": {
+            "properties": {
+              "text": {
+                "$ref": "#/definitions/nonEmptyString"
+              }
+            },
+            "required": [
+              "text"
+            ]
+          }
+        },
+        "species": {
+          "type": "array",
+          "items": {
+            "properties": {
+              "text": {
+                "$ref": "#/definitions/nonEmptyString"
+              }
+            },
+            "required": [
+              "text"
+            ]
+          }
+        },
+        "title": {
+          "description": "The sample title is a short, preferably a single sentence, description of the sample",
+          "type": "array",
+          "items": {
+            "properties": {
+              "text": {
+                "$ref": "#/definitions/nonEmptyString"
+              }
+            },
+            "required": [
+              "text"
+            ]
+          }
+        },
+        "description": {
+          "description": "Free-text description of the sample",
+          "type": "array",
+          "items": {
+            "properties": {
+              "text": {
+                "$ref": "#/definitions/nonEmptyString"
+              }
+            },
+            "required": [
+              "text"
+            ]
+          }
+        },
+        "taxId": {
+          "description": "The Tax Id indicates the NCBI taxonomic classification (http://www.ncbi.nlm.nih.gov/taxonomy)",
+          "type": "array",
+          "items": {
+            "properties": {
+              "text": {
+                "$ref": "#/definitions/nonEmptyString"
+              }
+            },
+            "required": [
+              "text"
+            ]
+          }
+        },
+        "scientificName": {
+          "description": "The scientific name of the sequenced organism",
+          "type": "array",
+          "items": {
+            "properties": {
+              "text": {
+                "$ref": "#/definitions/nonEmptyString"
+              }
+            },
+            "required": [
+              "text"
+            ]
+          }
+        },
+        "commonName": {
+          "description": "The common name of the sequenced organism",
+          "type": "array",
+          "items": {
+            "properties": {
+              "text": {
+                "$ref": "#/definitions/nonEmptyString"
+              }
+            },
+            "required": [
+              "text"
+            ]
+          }
+        }
+      }
+    }
+  }
+}