pybiolib 1.2.1228__py3-none-any.whl → 1.2.1235__py3-none-any.whl

biolib/_internal/utils/__init__.py

@@ -1,5 +1,30 @@
 import time
 import uuid
+from fnmatch import fnmatch
+
+from biolib.biolib_binary_format.utils import LazyLoadedFile
+from biolib.typing_utils import Callable, List, Union, cast
+
+PathFilter = Union[str, Callable[[str], bool]]
+
+
+def filter_lazy_loaded_files(files: List[LazyLoadedFile], path_filter: PathFilter) -> List[LazyLoadedFile]:
+    if not (isinstance(path_filter, str) or callable(path_filter)):
+        raise Exception('Expected path_filter to be a string or a function')
+
+    if callable(path_filter):
+        return list(filter(lambda x: path_filter(x.path), files))  # type: ignore
+
+    glob_filter = cast(str, path_filter)
+
+    # since all file paths start with /, make sure filter does too
+    if not glob_filter.startswith('/'):
+        glob_filter = '/' + glob_filter
+
+    def _filter_function(file: LazyLoadedFile) -> bool:
+        return fnmatch(file.path, glob_filter)
+
+    return list(filter(_filter_function, files))
 
 
 def open_browser_window_from_notebook(url_to_open: str) -> None:

biolib/app/app.py

@@ -72,7 +72,7 @@ class BioLibApp:
         result_prefix: Optional[str] = None,
         timeout: Optional[int] = None,
         notify: bool = False,
-        machine_count: Optional[int] = None,
+        max_workers: Optional[int] = None,
         experiment: Optional[str] = None,
         temporary_client_secrets: Optional[Dict[str, str]] = None,
         check: bool = False,
@@ -112,7 +112,7 @@ class BioLibApp:
             override_command=override_command,
             result_prefix=result_prefix,
             timeout=timeout,
-            requested_machine_count=machine_count,
+            requested_machine_count=max_workers,
             temporary_client_secrets=temporary_client_secrets,
             api_client=self._api_client,
         )

biolib/jobs/job.py

@@ -10,7 +10,7 @@ import biolib.api.client
 from biolib import utils
 from biolib._internal.http_client import HttpClient
 from biolib._internal.tree_utils import build_tree_from_files, build_tree_str
-from biolib._internal.utils import open_browser_window_from_notebook
+from biolib._internal.utils import PathFilter, filter_lazy_loaded_files, open_browser_window_from_notebook
 from biolib.api.client import ApiClient
 from biolib.biolib_api_client import BiolibApiClient, CreatedJobDict
 from biolib.biolib_api_client.biolib_app_api import BiolibAppApi
@@ -18,11 +18,12 @@ from biolib.biolib_api_client.biolib_job_api import BiolibJobApi
 from biolib.biolib_binary_format import LazyLoadedFile, ModuleInput, ModuleInputDict, ModuleOutputV2
 from biolib.biolib_binary_format.remote_endpoints import RemoteJobStorageEndpoint
 from biolib.biolib_binary_format.stdout_and_stderr import StdoutAndStderr
+from biolib.biolib_binary_format.utils import InMemoryIndexableBuffer
 from biolib.biolib_errors import BioLibError, CloudJobFinishedError
 from biolib.biolib_logging import logger, logger_no_user_data
 from biolib.compute_node.job_worker.job_storage import JobStorage
 from biolib.compute_node.utils import SystemExceptionCodeMap, SystemExceptionCodes
-from biolib.jobs.job_result import JobResult, PathFilter
+from biolib.jobs.job_result import JobResult
 from biolib.jobs.types import CloudJobDict, CloudJobStartedDict, JobDict
 from biolib.tables import BioLibTable
 from biolib.typing_utils import Dict, List, Optional, Union, cast
@@ -187,6 +188,45 @@ class Result:
         """
         return self.result.list_output_files(path_filter=path_filter)
 
+    def list_input_files(
+        self,
+        path_filter: Optional[PathFilter] = None,
+    ) -> List[LazyLoadedFile]:
+        """List input files from the result.
+
+        Args:
+            path_filter (PathFilter, optional): Filter to apply to the input files.
+                Can be a string glob pattern or a callable that takes a path string and returns a boolean.
+
+        Returns:
+            List[LazyLoadedFile]: List of input files.
+
+        Example::
+            >>> result = biolib.get_result("result_id")
+            >>> input_files = result.list_input_files()
+            >>> # Filter files with a glob pattern
+            >>> input_files = result.list_input_files("*.txt")
+        """
+        presigned_download_url = BiolibJobApi.get_job_storage_download_url(
+            job_uuid=self.id,
+            job_auth_token=self._auth_token,
+            storage_type='input',
+        )
+        response = HttpClient.request(url=presigned_download_url)
+        module_input_serialized: bytes = response.content
+        module_input = ModuleInput(module_input_serialized).deserialize()
+
+        files = []
+        for path, data in module_input['files'].items():
+            buffer = InMemoryIndexableBuffer(data)
+            lazy_file = LazyLoadedFile(path=path, buffer=buffer, start=0, length=len(data))
+            files.append(lazy_file)
+
+        if not path_filter:
+            return files
+
+        return filter_lazy_loaded_files(files, path_filter)
+
     def get_output_file(self, filename: str) -> LazyLoadedFile:
         return self.result.get_output_file(filename=filename)
 

biolib/jobs/job_result.py

@@ -1,16 +1,14 @@
 import time
-from fnmatch import fnmatch
 from pathlib import Path
 
+from biolib._internal.utils import PathFilter, filter_lazy_loaded_files
 from biolib.biolib_binary_format import ModuleOutputV2
 from biolib.biolib_binary_format.remote_endpoints import RemoteJobStorageEndpoint
 from biolib.biolib_binary_format.remote_stream_seeker import StreamSeeker
 from biolib.biolib_binary_format.utils import LazyLoadedFile, RemoteIndexableBuffer
 from biolib.biolib_errors import BioLibError
 from biolib.biolib_logging import logger
-from biolib.typing_utils import Callable, List, Optional, Union, cast
-
-PathFilter = Union[str, Callable[[str], bool]]
+from biolib.typing_utils import List, Optional
 
 
 class JobResult:
@@ -43,7 +41,7 @@ class JobResult:
     ) -> None:
         module_output = self._get_module_output()
         output_files = module_output.get_files()
-        filtered_output_files = self._get_filtered_files(output_files, path_filter) if path_filter else output_files
+        filtered_output_files = filter_lazy_loaded_files(output_files, path_filter) if path_filter else output_files
 
         if len(filtered_output_files) == 0:
             logger.debug('No output files to save')
@@ -100,7 +98,7 @@ class JobResult:
 
     def get_output_file(self, filename) -> LazyLoadedFile:
         files = self._get_module_output().get_files()
-        filtered_files = self._get_filtered_files(files, path_filter=filename)
+        filtered_files = filter_lazy_loaded_files(files, path_filter=filename)
         if not filtered_files:
             raise BioLibError(f'File {filename} not found in results.')
 
@@ -114,26 +112,7 @@ class JobResult:
         if not path_filter:
             return files
 
-        return self._get_filtered_files(files, path_filter)
-
-    @staticmethod
-    def _get_filtered_files(files: List[LazyLoadedFile], path_filter: PathFilter) -> List[LazyLoadedFile]:
-        if not (isinstance(path_filter, str) or callable(path_filter)):
-            raise Exception('Expected path_filter to be a string or a function')
-
-        if callable(path_filter):
-            return list(filter(lambda x: path_filter(x.path), files))  # type: ignore
-
-        glob_filter = cast(str, path_filter)
-
-        # since all file paths start with /, make sure filter does too
-        if not glob_filter.startswith('/'):
-            glob_filter = '/' + glob_filter
-
-        def _filter_function(file: LazyLoadedFile) -> bool:
-            return fnmatch(file.path, glob_filter)
-
-        return list(filter(_filter_function, files))
+        return filter_lazy_loaded_files(files, path_filter)
 
     def _get_module_output(self) -> ModuleOutputV2:
         if self._module_output is None:

{pybiolib-1.2.1228.dist-info → pybiolib-1.2.1235.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pybiolib
-Version: 1.2.1228
+Version: 1.2.1235
 Summary: BioLib Python Client
 License: MIT
 License-File: LICENSE

{pybiolib-1.2.1228.dist-info → pybiolib-1.2.1235.dist-info}/RECORD

@@ -59,14 +59,14 @@ biolib/_internal/types/resource_version.py,sha256=cU0YFHqxO-wX_Y6CoeK0Iei61gFwVo
 biolib/_internal/types/result.py,sha256=MesSTBXCkaw8HydXgHf1OKGVLzsxhZ1KV5z4w-VI-0M,231
 biolib/_internal/types/typing.py,sha256=qrsk8hHcGEbDpU1QQFzHAKnhQxkMe7uJ6pxHeAnfv1Y,414
 biolib/_internal/types/user.py,sha256=5_hYG0jrdGxynCCWXGaHZCAlVcRKBqMIEA2EBGrnpiE,439
-biolib/_internal/utils/__init__.py,sha256=p5vsIFyu-zYqBgdSMfwW9NC_jk7rXvvCbV4Bzd3As7c,630
+biolib/_internal/utils/__init__.py,sha256=xp1I-lVnu5owV1CW53jiPEZLKmqqHiPUDfauYDfJ7iQ,1540
 biolib/_internal/utils/multinode.py,sha256=N7kR49xD1PdkMVlxxzRiSYHfgi9MG-kLCwemcY1rojg,8323
 biolib/_runtime/runtime.py,sha256=vRJ0YFSGYVHWULam_fnS2EHmNEm_qkrJXWdsy0n8JDA,5857
 biolib/_session/session.py,sha256=US1Y1jfFIAm86-Lq3C7nCXpZXUJXXBVBkND9djMNYxI,1649
 biolib/api/__init__.py,sha256=mQ4u8FijqyLzjYMezMUUbbBGNB3iFmkNdjXnWPZ7Jlw,138
 biolib/api/client.py,sha256=2GpKE7QrPgyPdgJgrV7XnZByIJf1n26UCy3aoaHBs1M,7881
 biolib/app/__init__.py,sha256=cdPtcfb_U-bxb9iSL4fCEq2rpD9OjkyY4W-Zw60B0LI,37
-biolib/app/app.py,sha256=FGGi4jfjHpku3n60ZNJFKjEfLkrlwo1vqGdRO9nsrMw,11886
+biolib/app/app.py,sha256=Jc2PwNsZDKca9NxvasI_yrnb0q_S9PrJ94lva-y2Zpc,11882
 biolib/app/search_apps.py,sha256=K4a41f5XIWth2BWI7OffASgIsD0ko8elCax8YL2igaY,1470
 biolib/biolib_api_client/__init__.py,sha256=E5EMa19wJoblwSdQPYrxc_BtIeRsAuO0L_jQweWw-Yk,182
 biolib/biolib_api_client/api_client.py,sha256=IONzXeFCHl4wuct6fqOC_7NiTv_zFy6ys0hsAtvLzTA,7578
@@ -141,8 +141,8 @@ biolib/compute_node/webserver/worker_thread.py,sha256=7uD9yQPhePYvP2HCJ27EeZ_h6p
 biolib/experiments/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 biolib/experiments/experiment.py,sha256=4g1xMYmfp5yzSOdwjf3pUUULF9QjqBJb4uQ25FHrFrk,13688
 biolib/jobs/__init__.py,sha256=aIb2H2DHjQbM2Bs-dysFijhwFcL58Blp0Co0gimED3w,32
-biolib/jobs/job.py,sha256=AsWSnhDHNMz5_7pSsAfUYZx-34zahTDXLzhstSvLFiI,27394
-biolib/jobs/job_result.py,sha256=3uE_oj567-yGLr4UEFAf9CsM5lcEcjK8XE8v-CJKz8Q,6065
+biolib/jobs/job.py,sha256=7giHZfDt1lux8Nl2BZKwtVNaLr-vCcwFYZ28Cs_tZN0,28957
+biolib/jobs/job_result.py,sha256=_xqQu9z9BqPQrU6tjqKPuKlQDt5W0Zw5xiQvzEBkDyE,5266
 biolib/jobs/types.py,sha256=ezvaoTANsWazK6PmfpYcqezdfjP7MNBEBfqIZGoZhz8,997
 biolib/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 biolib/runtime/__init__.py,sha256=MlRepA11n2H-3plB5rzWyyHK2JmP6PiaP3i6x3vt0mg,506
@@ -157,8 +157,8 @@ biolib/utils/cache_state.py,sha256=u256F37QSRIVwqKlbnCyzAX4EMI-kl6Dwu6qwj-Qmag,3
 biolib/utils/multipart_uploader.py,sha256=XvGP1I8tQuKhAH-QugPRoEsCi9qvbRk-DVBs5PNwwJo,8452
 biolib/utils/seq_util.py,sha256=rImaghQGuIqTVWks6b9P2yKuN34uePUYPUFW_Wyoa4A,6737
 biolib/utils/zip/remote_zip.py,sha256=0wErYlxir5921agfFeV1xVjf29l9VNgGQvNlWOlj2Yc,23232
-pybiolib-1.2.1228.dist-info/METADATA,sha256=jD07Dls__RR6S-_Svx_bR-Ip4rVpbPtpLo2_lpIoycU,1644
-pybiolib-1.2.1228.dist-info/WHEEL,sha256=zp0Cn7JsFoX2ATtOhtaFYIiE2rmFAD4OcMhtUki8W3U,88
-pybiolib-1.2.1228.dist-info/entry_points.txt,sha256=p6DyaP_2kctxegTX23WBznnrDi4mz6gx04O5uKtRDXg,42
-pybiolib-1.2.1228.dist-info/licenses/LICENSE,sha256=F2h7gf8i0agDIeWoBPXDMYScvQOz02pAWkKhTGOHaaw,1067
-pybiolib-1.2.1228.dist-info/RECORD,,
+pybiolib-1.2.1235.dist-info/METADATA,sha256=BfK36P1WXe47dq0raBjDfGe46dGTtqQmMma7Ms8Vf_o,1644
+pybiolib-1.2.1235.dist-info/WHEEL,sha256=zp0Cn7JsFoX2ATtOhtaFYIiE2rmFAD4OcMhtUki8W3U,88
+pybiolib-1.2.1235.dist-info/entry_points.txt,sha256=p6DyaP_2kctxegTX23WBznnrDi4mz6gx04O5uKtRDXg,42
+pybiolib-1.2.1235.dist-info/licenses/LICENSE,sha256=F2h7gf8i0agDIeWoBPXDMYScvQOz02pAWkKhTGOHaaw,1067
+pybiolib-1.2.1235.dist-info/RECORD,,