pybiolib 1.2.923__py3-none-any.whl → 1.2.939__py3-none-any.whl

biolib/_internal/file_utils.py

@@ -1,3 +1,4 @@
+import hashlib
 import io
 import os
 import zipfile as zf
@@ -75,3 +76,47 @@ def get_iterable_zip_stream(files: List[str], chunk_size: int) -> Iterator[bytes
         if len(chunk) == 0:
             break
         yield chunk
+
+
+def path_to_renamed_path(path_str: str, prefix_with_slash: bool = True) -> str:
+    """
+    Normalize file paths consistently:
+    - If path contains '..' (relative path going up), convert to absolute path
+    - If relative path not containing '..', keep as is, but prepend / if prefix_with_slash=True
+    - If absolute path that is subpath of current directory, convert to relative path
+    - If absolute path not subpath of current directory, hash the folder path and keep filename
+    """
+    path = Path(path_str)
+    current_dir = Path.cwd()
+
+    if '..' in path.parts:
+        resolved_path = path.resolve()
+        try:
+            relative_path = resolved_path.relative_to(current_dir)
+            result = str(relative_path)
+        except ValueError:
+            folder_path = str(resolved_path.parent)
+            filename = resolved_path.name
+            folder_hash = hashlib.md5(folder_path.encode()).hexdigest()[:6]
+            result = f'/{folder_hash}/{filename}'
+    elif path.is_absolute():
+        try:
+            resolved_path = path.resolve()
+            relative_path = resolved_path.relative_to(current_dir)
+            result = str(relative_path)
+        except ValueError:
+            folder_path = str(path.parent)
+            filename = path.name
+            folder_hash = hashlib.md5(folder_path.encode()).hexdigest()[:6]
+            result = f'/{folder_hash}/{filename}'
+    else:
+        result = path_str
+
+    if prefix_with_slash:
+        if not result.startswith('/'):
+            return '/' + result
+        return result
+    else:
+        if result.startswith('/'):
+            return result[1:]
+        return result

biolib/app/app.py

@@ -20,6 +20,7 @@ from biolib.jobs.job import Result
 from biolib.typing_utils import Dict, Optional
 from biolib.utils.app_uri import parse_app_uri
 from biolib._runtime.runtime import Runtime
+from biolib._internal.file_utils import path_to_renamed_path
 
 
 class BioLibApp:
@@ -168,16 +169,60 @@ Example: "app.cli('--help')"
             files = []
 
         files_dict = {}
+        if isinstance(files, list):
+            for file_path in files:
+                path = Path(file_path)
+                if path.is_dir():
+                    for filename in path.rglob('*'):
+                        if filename.is_dir():
+                            continue
+                        with open(filename, 'rb') as f:
+                            relative_path = filename.relative_to(Path.cwd())
+                            files_dict[path_to_renamed_path(str(relative_path))] = f.read()
+                else:
+                    with open(path, 'rb') as f:
+                        files_dict[path_to_renamed_path(str(path))] = f.read()
+        elif isinstance(files, dict):
+            files_dict = {}
+            for key, value in files.items():
+                if not key.startswith('/'):
+                    key = '/' + key
+                files_dict[key] = value
+        else:
+            raise Exception('The given files input must be list or dict or None')
+
         for idx, arg in enumerate(args):
             if isinstance(arg, str):
                 if os.path.isfile(arg) or os.path.isdir(arg):
-                    files.append(arg)
-                    args[idx] = Path(arg).name
+                    if os.path.isfile(arg):
+                        with open(arg, 'rb') as f:
+                            files_dict[path_to_renamed_path(arg)] = f.read()
+                    elif os.path.isdir(arg):
+                        path = Path(arg)
+                        for filename in path.rglob('*'):
+                            if filename.is_dir():
+                                continue
+                            with open(filename, 'rb') as f:
+                                files_dict[path_to_renamed_path(str(filename))] = f.read()
+                    args[idx] = path_to_renamed_path(arg, prefix_with_slash=False)
 
                 # support --myarg=file.txt
                 elif os.path.isfile(arg.split('=')[-1]) or os.path.isdir(arg.split('=')[-1]):
-                    files.append(arg.split('=')[-1])
-                    args[idx] = arg.split('=')[0] + '=' + Path(arg.split('=')[-1]).name
+                    file_path = arg.split('=')[-1]
+                    if os.path.isfile(file_path):
+                        with open(file_path, 'rb') as f:
+                            files_dict[path_to_renamed_path(file_path)] = f.read()
+                    elif os.path.isdir(file_path):
+                        path = Path(file_path)
+                        for filename in path.rglob('*'):
+                            if filename.is_dir():
+                                continue
+                            with open(filename, 'rb') as f:
+                                files_dict[path_to_renamed_path(str(filename))] = f.read()
+                    args[idx] = (
+                        arg.split('=')[0] + '=' +
+                        path_to_renamed_path(file_path, prefix_with_slash=False)
+                    )
                 else:
                     pass  # a normal string arg was given
             else:
@@ -191,33 +236,6 @@ Example: "app.cli('--help')"
                 files_dict[f'/{tmp_filename}'] = file_data
                 args[idx] = tmp_filename
 
-        if isinstance(files, list):
-            for file in files:
-                path = Path(file).absolute()
-
-                # Recursively add data from files if dir
-                if path.is_dir():
-                    for filename in path.rglob('*'):
-                        if filename.is_dir():
-                            continue
-                        file = open(filename, 'rb')
-                        relative_path = '/' + path.name + '/' + '/'.join(filename.relative_to(path).parts)
-                        files_dict[relative_path] = file.read()
-                        file.close()
-
-                # Add file data
-                else:
-                    file = open(path, 'rb')
-                    path_short = '/' + path.name
-
-                    files_dict[path_short] = file.read()
-                    file.close()
-
-        elif isinstance(files, dict):
-            files_dict.update(files)
-        else:
-            raise Exception('The given files input must be list or dict or None')
-
         module_input_serialized: bytes = ModuleInput().serialize(
             stdin=stdin,
             arguments=args,

biolib/cli/run.py

@@ -48,7 +48,7 @@ def _run(local: bool, non_blocking: bool, uri: str, args: Tuple[str]) -> None:
     )
 
     if blocking:
-        job.save_files('biolib_results')
+        job.save_files('biolib_results', overwrite=True)
 
         # Write stdout and stderr if it has not been streamed (Markdown is not streamed)
         if app.version.get('stdout_render_type') == 'markdown' or not sys.stdout.isatty():

biolib/jobs/job.py

@@ -226,7 +226,7 @@ class Result:
 
         return self._cached_input_arguments
 
-    def save_input_files(self, output_dir: str) -> None:
+    def save_input_files(self, output_dir: str, overwrite: bool = False) -> None:
         logger.info('Downloading input files...')
         module_input = self._get_module_input()
 
@@ -236,7 +236,12 @@ class Result:
             # Remove leading slash of file_path
             destination_file_path = Path(output_dir) / Path(path.lstrip('/'))
             if destination_file_path.exists():
-                destination_file_path.rename(f'{destination_file_path}.biolib-renamed.{time.strftime("%Y%m%d%H%M%S")}')
+                if not overwrite:
+                    raise BioLibError(f'File {destination_file_path} already exists. Set overwrite=True to overwrite.')
+                else:
+                    destination_file_path.rename(
+                        f'{destination_file_path}.biolib-renamed.{time.strftime("%Y%m%d%H%M%S")}'
+                    )
 
             dir_path = destination_file_path.parent
             if dir_path:
@@ -252,11 +257,13 @@ class Result:
         output_dir: str,
         path_filter: Optional[PathFilter] = None,
         skip_file_if_exists: Optional[bool] = None,
+        overwrite: bool = False,
     ) -> None:
         self.result.save_files(
             output_dir=output_dir,
             path_filter=path_filter,
             skip_file_if_exists=skip_file_if_exists,
+            overwrite=overwrite,
         )
 
     def get_status(self) -> str:

biolib/jobs/job_result.py

@@ -39,6 +39,7 @@ class JobResult:
         output_dir: str,
         path_filter: Optional[PathFilter] = None,
         skip_file_if_exists: Optional[bool] = None,
+        overwrite: bool = False,
     ) -> None:
         module_output = self._get_module_output()
         output_files = module_output.get_files()
@@ -68,6 +69,8 @@ class JobResult:
                 if skip_file_if_exists:
                     print(f'Skipping {destination_file_path} as a file with that name already exists locally.')
                     continue
+                elif not overwrite:
+                    raise BioLibError(f'File {destination_file_path} already exists. Set overwrite=True to overwrite.')
                 else:
                     destination_file_path.rename(
                         f'{destination_file_path}.biolib-renamed.{time.strftime("%Y%m%d%H%M%S")}'

{pybiolib-1.2.923.dist-info → pybiolib-1.2.939.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: pybiolib
-Version: 1.2.923
+Version: 1.2.939
 Summary: BioLib Python Client
 License: MIT
 Keywords: biolib

{pybiolib-1.2.923.dist-info → pybiolib-1.2.939.dist-info}/RECORD

@@ -7,7 +7,7 @@ biolib/_internal/data_record/data_record.py,sha256=SD3-tKQY2RZv9ZSVNUhd2ISDYV64F
 biolib/_internal/data_record/push_data.py,sha256=-L3a_7zZzDCXabBu3O4lWPMAMeBbeRPTrBlEM-_5SCI,2693
 biolib/_internal/data_record/remote_storage_endpoint.py,sha256=eCptuZ4DMAPnaNCVDvpWXwXGI6Jac9U1N5dqU8Cj95Q,1732
 biolib/_internal/errors.py,sha256=AokI6Dvaa22B__LTfSZUVdDsm0ye7lgBFv_aD9O_kbs,163
-biolib/_internal/file_utils.py,sha256=4jT6j7bB21c0JNn5BfnyWQib_zt0CVtJ_TiOFOStRcE,2604
+biolib/_internal/file_utils.py,sha256=u_fD4aAWpLtvPlvcnz_iP4cRsFBjfnE6MWJUFPbTQHQ,4276
 biolib/_internal/fuse_mount/__init__.py,sha256=B_tM6RM2dBw-vbpoHJC4X3tOAaN1H2RDvqYJOw3xFwg,55
 biolib/_internal/fuse_mount/experiment_fuse_mount.py,sha256=08aUdEq_bvqLBft_gSLjOClKDy5sBnMts1RfJf7AP_U,7012
 biolib/_internal/http_client.py,sha256=9-3HG6LnLwJfrwjCeFj5XigHVH8Dzz6Dpr58IjQJHDo,6221
@@ -56,7 +56,7 @@ biolib/_session/session.py,sha256=US1Y1jfFIAm86-Lq3C7nCXpZXUJXXBVBkND9djMNYxI,16
 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=7AD0S1ih_drWbWXFKixGXyOKwQurt3ecND4m0Vb-Aik,10554
+biolib/app/app.py,sha256=E4PuwMWiWujQQzHQcq7MfVEZV-q6uKAbwBLr0ZPY5Dk,11825
 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
@@ -91,7 +91,7 @@ biolib/cli/download_container.py,sha256=HIZVHOPmslGE5M2Dsp9r2cCkAEJx__vcsDz5Wt5L
 biolib/cli/init.py,sha256=OMYIltLJfF8q9VAvzDwNG0-1VixDkFGEN1ic2VhrW7c,4583
 biolib/cli/lfs.py,sha256=z2qHUwink85mv9yDgifbVKkVwuyknGhMDTfly_gLKJM,4151
 biolib/cli/push.py,sha256=J8BswMYVeTacZBHbm4K4a2XbS_I8kvfgRZLoby2wi3I,1695
-biolib/cli/run.py,sha256=MCo0ZqW2pHBxOoCI3i5gAx5D0auW9fmxHqkAF4TRhms,2134
+biolib/cli/run.py,sha256=RAAXbIx8Bi-4fNkEoz2ODJ0fEtyS7VxD3dkc2fVZwjY,2150
 biolib/cli/runtime.py,sha256=Xv-nrma5xX8NidWcvbUKcUvuN5TCarZa4A8mPVmF-z0,361
 biolib/cli/sdk.py,sha256=XisJwTft4QDB_99eGDlz-WBqqRwIqkVg7HyvxWtOG8w,471
 biolib/cli/start.py,sha256=rg8VVY8rboFhf1iQo3zE3WA5oh_R1VWWfYJEO1gMReY,1737
@@ -129,8 +129,8 @@ biolib/compute_node/webserver/worker_thread.py,sha256=7uD9yQPhePYvP2HCJ27EeZ_h6p
 biolib/experiments/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 biolib/experiments/experiment.py,sha256=gY1-d7FgVrcQO3YzOJ0mHS6j7z7rl5XzXEuk7dFi1gU,10460
 biolib/jobs/__init__.py,sha256=aIb2H2DHjQbM2Bs-dysFijhwFcL58Blp0Co0gimED3w,32
-biolib/jobs/job.py,sha256=INQuNpEpe8rQPWBWeDFRjcAd-i4U6hF63FAsJ0BkJ_Y,27086
-biolib/jobs/job_result.py,sha256=rALHiKYNaC9lHi_JJqBob1RubzNLwG9Z386kwRJjd2M,5885
+biolib/jobs/job.py,sha256=B9v-dq9li0v9gDfmyyZOnCk-kN0vYPYxoybHWQsCkPg,27403
+biolib/jobs/job_result.py,sha256=L__GA5dNSDFHoQpAG2xb-tNqp_p4fQl53bAmlcvAt6M,6074
 biolib/jobs/types.py,sha256=ezvaoTANsWazK6PmfpYcqezdfjP7MNBEBfqIZGoZhz8,997
 biolib/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 biolib/runtime/__init__.py,sha256=MlRepA11n2H-3plB5rzWyyHK2JmP6PiaP3i6x3vt0mg,506
@@ -145,8 +145,8 @@ 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=Ozk0blGtPur_D9MwShD02r_mphyQmgZkx-lOHOwnlIM,6730
 biolib/utils/zip/remote_zip.py,sha256=0wErYlxir5921agfFeV1xVjf29l9VNgGQvNlWOlj2Yc,23232
-pybiolib-1.2.923.dist-info/LICENSE,sha256=F2h7gf8i0agDIeWoBPXDMYScvQOz02pAWkKhTGOHaaw,1067
-pybiolib-1.2.923.dist-info/METADATA,sha256=_6O5_T5lbKG9bEy2PBkthT5GWj6KyGyCGJMd337P_eI,1570
-pybiolib-1.2.923.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
-pybiolib-1.2.923.dist-info/entry_points.txt,sha256=p6DyaP_2kctxegTX23WBznnrDi4mz6gx04O5uKtRDXg,42
-pybiolib-1.2.923.dist-info/RECORD,,
+pybiolib-1.2.939.dist-info/LICENSE,sha256=F2h7gf8i0agDIeWoBPXDMYScvQOz02pAWkKhTGOHaaw,1067
+pybiolib-1.2.939.dist-info/METADATA,sha256=kPWSZXEhVmT-z_Wq2qmHvnhfksdAhH4eu8vOwxah3lU,1570
+pybiolib-1.2.939.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
+pybiolib-1.2.939.dist-info/entry_points.txt,sha256=p6DyaP_2kctxegTX23WBznnrDi4mz6gx04O5uKtRDXg,42
+pybiolib-1.2.939.dist-info/RECORD,,