pybiolib 1.2.71__py3-none-any.whl → 1.2.99.dev1__py3-none-any.whl

biolib/utils/seq_util.py

@@ -1,7 +1,7 @@
 import re
-from io import BufferedIOBase
+from io import BufferedIOBase, TextIOWrapper
 
-from biolib.typing_utils import Dict, List, Optional, Union
+from biolib.typing_utils import Dict, List, Optional, Union, Iterator
 
 
 class SeqUtilRecord:
@@ -37,67 +37,75 @@ class SeqUtil:
         allow_any_sequence_characters: bool = False,
         allow_empty_sequence: bool = True,
         file_name: Optional[str] = None,
-    ) -> List[SeqUtilRecord]:
+) -> Iterator[SeqUtilRecord]:
+        def process_and_yield_record(header: str, sequence_lines: list):
+            sequence = ''.join(sequence_lines)
+            sequence_id = header.split()[0]
+            if not allow_any_sequence_characters:
+                invalid_sequence_characters = SeqUtil._find_invalid_sequence_characters(sequence)
+                if invalid_sequence_characters:
+                    raise Exception(
+                        f'Error: Invalid character ("{invalid_sequence_characters[0]}") found in sequence {sequence_id}'
+                    )
+            if not allow_empty_sequence and not sequence:
+                raise Exception(f'Error: No sequence found for fasta entry {sequence_id}')
+            yield SeqUtilRecord(
+                sequence=sequence,
+                sequence_id=sequence_id,
+                description=header[len(sequence_id):].strip()
+            )
+
+        def line_generator_from_buffered_io_base(file_handle: BufferedIOBase) -> Iterator[str]:
+            """Generates lines from a BufferedIOBase handle, decoding UTF-8."""
+            for line in file_handle:
+                yield line.decode('utf-8')
+
+        def line_generator_from_text_io_wrapper(file_handle: TextIOWrapper) -> Iterator[str]:
+            """Generates lines from a TextIOWrapper handle, decoding UTF-8."""
+            for line in file_handle:
+                yield line
+
         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')
+
+        file_handle = None
         if isinstance(input_file, str):
-            with open(input_file) as file_handle:
-                data = file_handle.read().strip()
+            file_handle = open(input_file, "r")
+            line_iterator = line_generator_from_text_io_wrapper(file_handle)
         elif isinstance(input_file, BufferedIOBase):
-            data = input_file.read().decode('utf-8')
+            line_iterator = line_generator_from_buffered_io_base(input_file)
         else:
             raise ValueError('input_file must be a file name (str) or a BufferedIOBase object')
-        if not data:
-            return []
-
-        if '>' not in data:
-            if default_header:
-                lines_with_header = []
-                for index, line in enumerate(data.split('\n')):
-                    index_string = str(index + 1) if index > 0 else ''
-                    lines_with_header.append(f'>{default_header}{index_string}\n{line}')
-
-                data = '\n'.join(lines_with_header)
-            else:
-                raise Exception(f'No header line found in FASTA file "{file_name}"')
-
-        splitted = []
-        tmp_data = ''
-        for line in data.splitlines():
-            if line.startswith('>'):
-                if tmp_data:
-                    splitted.append(tmp_data)
-                tmp_data = line[1:].strip() + '\n'
-            else:
-                if line.strip():
-                    tmp_data += line.strip() + '\n'
-
-        if tmp_data:
-            splitted.append(tmp_data)
-
-        parsed_sequences = []
-        for sequence_data in splitted:
-            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() for seq in sequence_data_splitted[1:]])
-
-            if not allow_any_sequence_characters:
-                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}')
-
-            parsed_sequences.append(SeqUtilRecord(sequence=sequence, sequence_id=sequence_id, description=description))
 
-        return parsed_sequences
+        header = None
+        sequence_lines: list[str] = []
+
+        try:
+            for line_number, line in enumerate(line_iterator):
+                line = line.strip()
+                if line.startswith('>'):
+                    if header is not None:
+                        yield from process_and_yield_record(header, sequence_lines)
+
+                    header = line[1:].strip()
+                    sequence_lines = []
+                else:
+                    if header is None:
+                        if default_header:
+                            yield from process_and_yield_record(f"{default_header}{line_number}", [line])
+                        else:
+                            raise Exception(f'No header line found in FASTA file "{file_name}"')
+                    else:
+                        sequence_lines.append(line)
+
+            if header is not None:
+                yield from process_and_yield_record(header, sequence_lines)
+        finally:
+            if file_handle:
+                file_handle.close()
 
     @staticmethod
     def write_records_to_fasta(file_name: str, records: List[SeqUtilRecord]) -> None:

{pybiolib-1.2.71.dist-info → pybiolib-1.2.99.dev1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pybiolib
-Version: 1.2.71
+Version: 1.2.99.dev1
 Summary: BioLib Python Client
 Home-page: https://github.com/biolib
 License: MIT

{pybiolib-1.2.71.dist-info → pybiolib-1.2.99.dev1.dist-info}/RECORD

@@ -117,10 +117,10 @@ 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=ZQFcaE37B2dtucN2zDjOmdya_X0ITc1zBFZJNQY13XA,5183
+biolib/utils/seq_util.py,sha256=fBJoGIkmqNqFebLIwSzxifXzkkUdBOepDYknBsks7Qw,5660
 biolib/utils/zip/remote_zip.py,sha256=0wErYlxir5921agfFeV1xVjf29l9VNgGQvNlWOlj2Yc,23232
-pybiolib-1.2.71.dist-info/LICENSE,sha256=F2h7gf8i0agDIeWoBPXDMYScvQOz02pAWkKhTGOHaaw,1067
-pybiolib-1.2.71.dist-info/METADATA,sha256=Fz8X4xfMgIOj-MyEF8-h8YkSZ0ZSHhi_uJtv56ikYvk,1506
-pybiolib-1.2.71.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-pybiolib-1.2.71.dist-info/entry_points.txt,sha256=p6DyaP_2kctxegTX23WBznnrDi4mz6gx04O5uKtRDXg,42
-pybiolib-1.2.71.dist-info/RECORD,,
+pybiolib-1.2.99.dev1.dist-info/LICENSE,sha256=F2h7gf8i0agDIeWoBPXDMYScvQOz02pAWkKhTGOHaaw,1067
+pybiolib-1.2.99.dev1.dist-info/METADATA,sha256=FoK4QVbKuqHAXomf4Ezk2tGYhvl5MdeMyJqDOPSlhP0,1511
+pybiolib-1.2.99.dev1.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+pybiolib-1.2.99.dev1.dist-info/entry_points.txt,sha256=p6DyaP_2kctxegTX23WBznnrDi4mz6gx04O5uKtRDXg,42
+pybiolib-1.2.99.dev1.dist-info/RECORD,,