pybiolib 1.1.1566__tar.gz → 1.1.1571__tar.gz

{pybiolib-1.1.1566 → pybiolib-1.1.1571}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pybiolib
-Version: 1.1.1566
+Version: 1.1.1571
 Summary: BioLib Python Client
 Home-page: https://github.com/biolib
 License: MIT

pybiolib-1.1.1571/biolib/biolib_binary_format/remote_endpoints.py

@@ -0,0 +1,32 @@
+from datetime import datetime, timedelta
+# from urllib.parse import urlparse, parse_qs
+
+from biolib.biolib_logging import logger
+
+from biolib.biolib_api_client.biolib_job_api import BiolibJobApi
+from biolib.biolib_binary_format.utils import RemoteEndpoint
+
+
+class RemoteJobStorageResultEndpoint(RemoteEndpoint):
+    def __init__(self, job_id: str, job_auth_token: str):
+        self._job_id = job_id
+        self._job_auth_token = job_auth_token
+        self._expires_at = None
+        self._presigned_url = None
+
+    def get_remote_url(self):
+        if not self._presigned_url or datetime.utcnow() > self._expires_at:
+            self._presigned_url = BiolibJobApi.get_job_storage_download_url(
+                job_auth_token=self._job_auth_token,
+                job_uuid=self._job_id,
+                storage_type='results'
+            )
+            self._expires_at = datetime.utcnow() + timedelta(minutes=8)
+            # TODO: Use expires at from url
+            # parsed_url = urlparse(self._presigned_url)
+            # query_params = parse_qs(parsed_url.query)
+            # time_at_generation = datetime.datetime.strptime(query_params['X-Amz-Date'][0], '%Y%m%dT%H%M%SZ')
+            # self._expires_at = time_at_generation + timedelta(seconds=int(query_params['X-Amz-Expires'][0]))
+            logger.debug(f'Job "{self._job_id}" fetched presigned URL with expiry at {self._expires_at.isoformat()}')
+
+        return self._presigned_url

{pybiolib-1.1.1566 → pybiolib-1.1.1571}/biolib/utils/seq_util.py

@@ -17,7 +17,11 @@ class SeqUtilRecord:
 
 class SeqUtil:
     @staticmethod
-    def parse_fasta(file_name: str, default_header: Optional[str] = None) -> List[SeqUtilRecord]:
+    def parse_fasta(
+        file_name: str,
+        default_header: Optional[str] = None,
+        run_validation: bool = True
+    ) -> List[SeqUtilRecord]:
         with open(file_name, 'r') as file_handle:
             data = file_handle.read().strip()
 
@@ -56,9 +60,14 @@ class SeqUtil:
             sequence_id = header_line[0]
             description = sequence_data_splitted[0][len(sequence_id):].strip()
             sequence = "".join([seq.strip().upper() for seq in sequence_data_splitted[1:]])
-            invalid_sequence_characters = find_invalid_sequence_characters(sequence)
-            if len(invalid_sequence_characters) > 0:
-                raise Exception(f'Error: Invalid charater ("{invalid_sequence_characters[0]}") found in sequence.')
+
+            if run_validation:
+                invalid_sequence_characters = find_invalid_sequence_characters(sequence)
+                if len(invalid_sequence_characters) > 0:
+                    raise Exception(
+                        f'Error: Invalid character ("{invalid_sequence_characters[0]}") found in sequence {sequence_id}'
+                    )
+
             parsed_sequences.append(
                 SeqUtilRecord(sequence=sequence, sequence_id=sequence_id, description=description)
             )

{pybiolib-1.1.1566 → pybiolib-1.1.1571}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "pybiolib"
-version = "1.1.1566"
+version = "1.1.1571"
 description = "BioLib Python Client"
 readme = "README.md"
 license = "MIT"

pybiolib-1.1.1566/biolib/biolib_binary_format/remote_endpoints.py

@@ -1,30 +0,0 @@
-import datetime
-from urllib.parse import urlparse, parse_qs
-
-from biolib.biolib_logging import logger
-
-from biolib.biolib_api_client.biolib_job_api import BiolibJobApi
-from biolib.biolib_binary_format.utils import RemoteEndpoint
-
-
-class RemoteJobStorageResultEndpoint(RemoteEndpoint):
-    def __init__(self, job_id: str, job_auth_token: str):
-        self._job_id = job_id
-        self._job_auth_token = job_auth_token
-        self._expires_at = None
-        self.presigned_url = None
-
-    def get_remote_url(self):
-        if not self.presigned_url or datetime.datetime.now() > self._expires_at:
-            self.presigned_url = BiolibJobApi.get_job_storage_download_url(
-                job_auth_token=self._job_auth_token,
-                job_uuid=self._job_id,
-                storage_type='results'
-            )
-            parsed_url = urlparse(self.presigned_url)
-            query_params = parse_qs(parsed_url.query)
-            time_at_generation = datetime.datetime.strptime(query_params['X-Amz-Date'][0], '%Y%m%dT%H%M%SZ')
-            self._expires_at = time_at_generation + datetime.timedelta(seconds=int(query_params['X-Amz-Expires'][0]))
-            logger.debug(f'Job "{self._job_id}" fetched presigned URL with expiry at {self._expires_at.isoformat()}')
-
-        return self.presigned_url