pybiolib 1.1.2173__py3-none-any.whl → 1.1.2180__py3-none-any.whl

biolib/_data_record/data_record.py

@@ -4,7 +4,7 @@ from datetime import datetime
 from fnmatch import fnmatch
 from pathlib import Path
 from struct import Struct
-from typing import Callable, Dict, List, Union, cast
+from typing import Callable, Dict, List, Optional, Union, cast
 
 from biolib import api, utils
 from biolib._internal import types
@@ -20,11 +20,9 @@ from biolib.biolib_binary_format import LazyLoadedFile
 from biolib.biolib_binary_format.utils import RemoteIndexableBuffer
 from biolib.biolib_errors import BioLibError
 from biolib.biolib_logging import logger
-from biolib.typing_utils import Optional as _Optional
 from biolib.utils.app_uri import parse_app_uri
 from biolib.utils.zip.remote_zip import RemoteZip
 
-
 PathFilter = Union[str, Callable[[str], bool]]
 
 
@@ -51,7 +49,7 @@ class DataRecord:
 
         return uri_parsed['app_name']
 
-    def list_files(self, path_filter: _Optional[PathFilter] = None) -> List[LazyLoadedFile]:
+    def list_files(self, path_filter: Optional[PathFilter] = None) -> List[LazyLoadedFile]:
         remote_storage_endpoint = DataRecordRemoteStorageEndpoint(
             resource_version_uuid=self._state['resource_version_uuid'],
         )
@@ -69,7 +67,7 @@ class DataRecord:
         )
         HttpClient.request(url=remote_storage_endpoint.get_remote_url(), response_path=output_path)
 
-    def download_files(self, output_dir: str, path_filter: _Optional[PathFilter] = None) -> None:
+    def download_files(self, output_dir: str, path_filter: Optional[PathFilter] = None) -> None:
         filtered_files = self.list_files(path_filter=path_filter)
 
         if len(filtered_files) == 0:
@@ -83,10 +81,10 @@ class DataRecord:
                 for chunk in file.get_data_iterator():
                     file_handle.write(chunk)
 
-    def save_files(self, output_dir: str, path_filter: _Optional[PathFilter] = None) -> None:
+    def save_files(self, output_dir: str, path_filter: Optional[PathFilter] = None) -> None:
         self.download_files(output_dir=output_dir, path_filter=path_filter)
 
-    def update(self, data_path: str, chunk_size_in_mb: _Optional[int] = None) -> None:
+    def update(self, data_path: str, chunk_size_in_mb: Optional[int] = None) -> None:
         assert os.path.isdir(data_path), f'The path "{data_path}" is not a directory.'
         BiolibApiClient.assert_is_signed_in(authenticated_action_description='push data to a Data Record')
 
@@ -108,11 +106,11 @@ class DataRecord:
             logger.info(f"Validating data record of type {data_record_type['name']}")
             for rule in data_record_type['validation_rules']:
                 logger.info(f"Validating rule {rule['type']} for {rule['path']}...")
-                if rule['type'] == "sqlite-v1":
+                if rule['type'] == 'sqlite-v1':
                     try:
                         validate_sqlite_v1(schema=rule['rule'], sqlite_file=Path(rule['path']))
                     except Exception as error:
-                        raise Exception("Data Record Validation failed") from error
+                        raise Exception('Data Record Validation failed') from error
                 else:
                     raise Exception(f"Error processing data record validation: unknown rule type {rule['type']}")
 
@@ -158,7 +156,7 @@ class DataRecord:
         return DataRecord(_internal_state=get_data_record_state_from_uri(uri))
 
     @staticmethod
-    def create(destination: str, data_path: _Optional[str] = None) -> 'DataRecord':
+    def create(destination: str, data_path: Optional[str] = None) -> 'DataRecord':
         BiolibApiClient.assert_is_signed_in(authenticated_action_description='create a Data Record')
         if data_path is not None:
             assert os.path.isdir(data_path), f'The path "{data_path}" is not a directory.'
@@ -188,7 +186,7 @@ class DataRecord:
             return DataRecord.get_by_uri(uri=data_record_info['uri'])
 
     @staticmethod
-    def fetch(uri: _Optional[str] = None, count: _Optional[int] = None) -> List['DataRecord']:
+    def fetch(uri: Optional[str] = None, count: Optional[int] = None) -> List['DataRecord']:
         max_page_size = 1_000
         params: Dict[str, Union[str, int]] = {
             'page_size': str(count or max_page_size),

biolib/_runtime/runtime.py

@@ -1,13 +1,14 @@
-from biolib import api
-from biolib._internal.runtime import BioLibRuntimeError, BioLibRuntimeNotRecognizedError, RuntimeJobDataDict
-from biolib.typing_utils import cast, Optional as _Optional
-
 import json
 import re
+from typing import Optional
+
+from biolib import api
+from biolib._internal.runtime import BioLibRuntimeError, BioLibRuntimeNotRecognizedError, RuntimeJobDataDict
+from biolib.typing_utils import cast
 
 
 class Runtime:
-    _job_data: _Optional[RuntimeJobDataDict] = None
+    _job_data: Optional[RuntimeJobDataDict] = None
 
     @staticmethod
     def check_is_environment_biolib_app() -> bool:
@@ -56,7 +57,7 @@ class Runtime:
         api.client.post(data={'note': note}, path=f'/jobs/{job_id}/notes/')
 
     @staticmethod
-    def _try_to_get_job_data() -> _Optional[RuntimeJobDataDict]:
+    def _try_to_get_job_data() -> Optional[RuntimeJobDataDict]:
         if not Runtime._job_data:
             try:
                 with open('/biolib/secrets/biolib_system_secret') as file:

biolib/runtime/__init__.py

@@ -1,4 +1,5 @@
 import warnings
+
 from biolib._runtime.runtime import Runtime as _Runtime
 
 

biolib/utils/seq_util.py

@@ -1,32 +1,26 @@
 import re
 from io import BufferedIOBase
-from biolib.typing_utils import List, Optional, Dict, Union
 
-allowed_sequence_chars = set("ABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_.")
-
-
-def find_invalid_sequence_characters(sequence):
-    invalid_chars = [char for char in sequence if char not in allowed_sequence_chars]
-    return invalid_chars
+from biolib.typing_utils import Dict, List, Optional, Union
 
 
 class SeqUtilRecord:
     def __init__(
-            self,
-            sequence: str,
-            sequence_id: str,
-            description: Optional['str'],
-            properties: Optional[Dict[str, str]] = None,
+        self,
+        sequence: str,
+        sequence_id: str,
+        description: Optional['str'],
+        properties: Optional[Dict[str, str]] = None,
     ):
         self.sequence = sequence
         self.id = sequence_id  # pylint: disable=invalid-name
         self.description = description
 
         if properties:
-            disallowed_pattern = re.compile(r"[=\[\]\n]")
+            disallowed_pattern = re.compile(r'[=\[\]\n]')
             for key, value in properties.items():
-                assert not bool(disallowed_pattern.search(key)), "Key cannot contain characters =[] and newline"
-                assert not bool(disallowed_pattern.search(value)), "Value cannot contain characters =[] and newline"
+                assert not bool(disallowed_pattern.search(key)), 'Key cannot contain characters =[] and newline'
+                assert not bool(disallowed_pattern.search(value)), 'Value cannot contain characters =[] and newline'
             self.properties = properties
         else:
             self.properties = {}
@@ -38,24 +32,24 @@ class SeqUtilRecord:
 class SeqUtil:
     @staticmethod
     def parse_fasta(
-            input_file: Union[str, BufferedIOBase, None] = None,
-            default_header: Optional[str] = None,
-            allow_any_sequence_characters: bool = False,
-            allow_empty_sequence: bool = False,
-            file_name: Optional[str] = None,
+        input_file: Union[str, BufferedIOBase, None] = None,
+        default_header: Optional[str] = None,
+        allow_any_sequence_characters: bool = False,
+        allow_empty_sequence: bool = False,
+        file_name: Optional[str] = None,
     ) -> List[SeqUtilRecord]:
         if input_file is None:
             if file_name:
                 input_file = file_name
             else:
-                raise ValueError("input_file must be a file name (str) or a BufferedIOBase object")
+                raise ValueError('input_file must be a file name (str) or a BufferedIOBase object')
         if isinstance(input_file, str):
-            with open(input_file, 'r') as file_handle:
+            with open(input_file) as file_handle:
                 data = file_handle.read().strip()
         elif isinstance(input_file, BufferedIOBase):
             data = input_file.read().decode('utf-8')
         else:
-            raise ValueError("input_file must be a file name (str) or a BufferedIOBase object")
+            raise ValueError('input_file must be a file name (str) or a BufferedIOBase object')
         if not data:
             return []
 
@@ -71,9 +65,9 @@ class SeqUtil:
                 raise Exception(f'No header line found in FASTA file "{file_name}"')
 
         splitted = []
-        tmp_data = ""
+        tmp_data = ''
         for line in data.splitlines():
-            if line.startswith(">"):
+            if line.startswith('>'):
                 if tmp_data:
                     splitted.append(tmp_data)
                 tmp_data = line[1:].strip() + '\n'
@@ -89,23 +83,20 @@ class SeqUtil:
             sequence_data_splitted = sequence_data.strip().split('\n')
             header_line = sequence_data_splitted[0].split()
             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:]])
+            description = sequence_data_splitted[0][len(sequence_id) :].strip()
+            sequence = ''.join([seq.strip() for seq in sequence_data_splitted[1:]])
 
             if not allow_any_sequence_characters:
-                invalid_sequence_characters = find_invalid_sequence_characters(sequence)
+                invalid_sequence_characters = SeqUtil._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}'
                     )
             if not allow_empty_sequence and len(sequence) == 0:
-                raise Exception(
-                    f'Error: No sequence found for fasta entry {sequence_id}'
-                )
+                raise Exception(f'Error: No sequence found for fasta entry {sequence_id}')
+
+            parsed_sequences.append(SeqUtilRecord(sequence=sequence, sequence_id=sequence_id, description=description))
 
-            parsed_sequences.append(
-                SeqUtilRecord(sequence=sequence, sequence_id=sequence_id, description=description)
-            )
         return parsed_sequences
 
     @staticmethod
@@ -116,5 +107,17 @@ class SeqUtil:
                 if record.properties:
                     for key, value in record.properties.items():
                         optional_description += f' [{key}={value}]'
-                sequence = '\n'.join(record.sequence[i:i + 80] for i in range(0, len(record.sequence), 80))
+                sequence = '\n'.join(record.sequence[i : i + 80] for i in range(0, len(record.sequence), 80))
                 file_handle.write(f'>{record.id}{optional_description}\n{sequence}\n')
+
+    @staticmethod
+    def _find_invalid_sequence_characters(sequence: str) -> List[str]:
+        allowed_sequence_chars = set('abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_.')
+        invalid_chars = [char for char in sequence if char not in allowed_sequence_chars]
+        return invalid_chars
+
+    @staticmethod
+    def _find_invalid_sequence_id_characters(sequence: str) -> List[str]:
+        allowed_chars = set('abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_.:*#')
+        invalid_chars = [char for char in sequence if char not in allowed_chars]
+        return invalid_chars

{pybiolib-1.1.2173.dist-info → pybiolib-1.1.2180.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pybiolib
-Version: 1.1.2173
+Version: 1.1.2180
 Summary: BioLib Python Client
 Home-page: https://github.com/biolib
 License: MIT

{pybiolib-1.1.2173.dist-info → pybiolib-1.1.2180.dist-info}/RECORD

@@ -1,7 +1,7 @@
 LICENSE,sha256=F2h7gf8i0agDIeWoBPXDMYScvQOz02pAWkKhTGOHaaw,1067
 README.md,sha256=_IH7pxFiqy2bIAmaVeA-iVTyUwWRjMIlfgtUbYTtmls,368
 biolib/__init__.py,sha256=_tThyzISH81yS9KXP_X3qEiKXmsIp5XOBcJIODfLVnc,4338
-biolib/_data_record/data_record.py,sha256=XC3BsxnmA20odM7r4dsRHNnwYqhYp054f4BNkA5J5dA,12685
+biolib/_data_record/data_record.py,sha256=6PD-jBgWU2Cc4PwT-hLNPTFZygb4r0LBL617U-1eijE,12633
 biolib/_internal/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 biolib/_internal/data_record/__init__.py,sha256=fGdME6JGRU_2VxpJbYpGXYndjN-feUkmKY4fuMyq3cg,76
 biolib/_internal/data_record/data_record.py,sha256=YmaAABR57goDCE8-rKb2j0FPMSbDtRPCm_HhT3mM074,4299
@@ -23,7 +23,7 @@ biolib/_internal/types/experiment.py,sha256=D94iBdn2nS92lRW-TOs1a2WKXJD5ZtmzL4yp
 biolib/_internal/types/resource.py,sha256=G-vPkZoe4Um6FPxsQZtRzAlbSW5sDW4NFkbjn21I3V4,372
 biolib/_internal/types/typing.py,sha256=D4EKKEe7kDx0K6lJi-H_XLtk-8w6nu2fdqn9bvzI-Xo,288
 biolib/_internal/utils/__init__.py,sha256=p5vsIFyu-zYqBgdSMfwW9NC_jk7rXvvCbV4Bzd3As7c,630
-biolib/_runtime/runtime.py,sha256=zy9HrE4X5hBqm8doUHkckyflquSBDSXV3REhT2MQGas,2767
+biolib/_runtime/runtime.py,sha256=daYxzIpRoW4k-HJFu2BMXeylYSlCXn3-SqdSriCFnKw,2770
 biolib/api/__init__.py,sha256=mQ4u8FijqyLzjYMezMUUbbBGNB3iFmkNdjXnWPZ7Jlw,138
 biolib/api/client.py,sha256=9MD1qI52BnRC_QSydFGjyFquwFw0R9dkDfUrjUouuHQ,3490
 biolib/app/__init__.py,sha256=cdPtcfb_U-bxb9iSL4fCEq2rpD9OjkyY4W-Zw60B0LI,37
@@ -102,7 +102,7 @@ biolib/jobs/__init__.py,sha256=aIb2H2DHjQbM2Bs-dysFijhwFcL58Blp0Co0gimED3w,32
 biolib/jobs/job.py,sha256=OfG8cLd3AjGjiMWRlJRZdVVbLsRWSX-OM5nxJhR6mPQ,19136
 biolib/jobs/job_result.py,sha256=rALHiKYNaC9lHi_JJqBob1RubzNLwG9Z386kwRJjd2M,5885
 biolib/jobs/types.py,sha256=qhadtH2KDC2WUOOqPiwke0YgtQY4FtuB71Stekq1k48,970
-biolib/runtime/__init__.py,sha256=Fg2ZIAmUegurLKagpBNfRgLcOwR2VZSmXQpb-ryRwI0,505
+biolib/runtime/__init__.py,sha256=MlRepA11n2H-3plB5rzWyyHK2JmP6PiaP3i6x3vt0mg,506
 biolib/sdk/__init__.py,sha256=qJ_V_Edxolzi4VBQCrvem5lYIkJ0FVH3VZepSDuXjTc,1895
 biolib/tables.py,sha256=acH7VjwAbadLo8P84FSnKEZxCTVsF5rEg9VPuxElNs8,872
 biolib/templates/__init__.py,sha256=Yx62sSyDCDesRQDQgmbDsLpfgEh93fWE8r9u4g2azXk,36
@@ -114,10 +114,10 @@ biolib/utils/__init__.py,sha256=fwjciJyJicvYyZcVTzfDBgD0SKY13DeXqvTeG4qZIy8,5548
 biolib/utils/app_uri.py,sha256=Yq_-_VGugQhMMo6mM5f0G9yNlLkr0WK4j0Nrf3FE4xQ,2171
 biolib/utils/cache_state.py,sha256=u256F37QSRIVwqKlbnCyzAX4EMI-kl6Dwu6qwj-Qmag,3100
 biolib/utils/multipart_uploader.py,sha256=XvGP1I8tQuKhAH-QugPRoEsCi9qvbRk-DVBs5PNwwJo,8452
-biolib/utils/seq_util.py,sha256=jC5WhH63FTD7SLFJbxQGA2hOt9NTwq9zHl_BEec1Z0c,4907
+biolib/utils/seq_util.py,sha256=WieuQ2RvV4QSJFUAMRVyvKXFs3YanFAmjh-CFIaQmQk,5184
 biolib/utils/zip/remote_zip.py,sha256=0wErYlxir5921agfFeV1xVjf29l9VNgGQvNlWOlj2Yc,23232
-pybiolib-1.1.2173.dist-info/LICENSE,sha256=F2h7gf8i0agDIeWoBPXDMYScvQOz02pAWkKhTGOHaaw,1067
-pybiolib-1.1.2173.dist-info/METADATA,sha256=vA4sMu0c3kO4Z5PTqIziK4BRlsjEKNe-lVtJ26RzVag,1508
-pybiolib-1.1.2173.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-pybiolib-1.1.2173.dist-info/entry_points.txt,sha256=p6DyaP_2kctxegTX23WBznnrDi4mz6gx04O5uKtRDXg,42
-pybiolib-1.1.2173.dist-info/RECORD,,
+pybiolib-1.1.2180.dist-info/LICENSE,sha256=F2h7gf8i0agDIeWoBPXDMYScvQOz02pAWkKhTGOHaaw,1067
+pybiolib-1.1.2180.dist-info/METADATA,sha256=icX35ySYzpvqGrHM6Sy4NJ9tGCVWpP6U1qga8I3jgtc,1508
+pybiolib-1.1.2180.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+pybiolib-1.1.2180.dist-info/entry_points.txt,sha256=p6DyaP_2kctxegTX23WBznnrDi4mz6gx04O5uKtRDXg,42
+pybiolib-1.1.2180.dist-info/RECORD,,