pybiolib 1.1.2173__py3-none-any.whl → 1.1.2175__py3-none-any.whl

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-1.1.2175.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pybiolib
-Version: 1.1.2173
+Version: 1.1.2175
 Summary: BioLib Python Client
 Home-page: https://github.com/biolib
 License: MIT

{pybiolib-1.1.2173.dist-info → pybiolib-1.1.2175.dist-info}/RECORD

@@ -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-1.1.2175.dist-info/LICENSE,sha256=F2h7gf8i0agDIeWoBPXDMYScvQOz02pAWkKhTGOHaaw,1067
+pybiolib-1.1.2175.dist-info/METADATA,sha256=2N5GV9P58sKVu7I1HPx2eQuP_I7igY1RIqfd1OZEQKI,1508
+pybiolib-1.1.2175.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+pybiolib-1.1.2175.dist-info/entry_points.txt,sha256=p6DyaP_2kctxegTX23WBznnrDi4mz6gx04O5uKtRDXg,42
+pybiolib-1.1.2175.dist-info/RECORD,,