opencloning 0.3.2__py3-none-any.whl → 0.3.4__py3-none-any.whl

opencloning/app_settings.py

@@ -28,6 +28,9 @@ PLANNOTATE_TIMEOUT = int(os.environ['PLANNOTATE_TIMEOUT']) if 'PLANNOTATE_TIMEOU
 if PLANNOTATE_URL is not None and not PLANNOTATE_URL.endswith('/'):
     PLANNOTATE_URL += '/'
 
+PROXY_URL = os.environ.get('PROXY_URL')
+PROXY_CERT_FILE = os.environ.get('PROXY_CERT_FILE')
+
 
 class Settings(BaseModel):
     SERVE_FRONTEND: bool
@@ -37,6 +40,9 @@ class Settings(BaseModel):
     ALLOWED_ORIGINS: list[str]
     PLANNOTATE_URL: str | None
     PLANNOTATE_TIMEOUT: int
+    PROXY_URL: str | None
+    # Must be a full path to the proxy certificate file
+    PROXY_CERT_FILE: str | None
 
 
 settings = Settings(
@@ -47,4 +53,6 @@ settings = Settings(
     ALLOWED_ORIGINS=ALLOWED_ORIGINS,
     PLANNOTATE_URL=PLANNOTATE_URL,
     PLANNOTATE_TIMEOUT=PLANNOTATE_TIMEOUT,
+    PROXY_URL=PROXY_URL,
+    PROXY_CERT_FILE=PROXY_CERT_FILE,
 )

opencloning/batch_cloning/pombe/pombe_get_primers.py

@@ -1,12 +1,12 @@
 from bs4 import BeautifulSoup
 import asyncio
-from httpx import AsyncClient, Response
 import re
 import os
 import argparse
 from Bio import SeqIO
 from Bio.Seq import Seq
 from Bio.SeqRecord import SeqRecord
+from ...http_client import get_http_client, Response
 
 default_settings_primer_design = {
     'length': 80,
@@ -25,8 +25,8 @@ default_settings_primer_design = {
 
 
 async def async_post(url, headers, data, params=None) -> Response:
-    async with AsyncClient(timeout=20.0) as client:
-        return await client.post(url, headers=headers, data=data, params=params)
+    async with get_http_client() as client:
+        return await client.post(url, headers=headers, data=data, params=params, timeout=20.0)
 
 
 async def get_primers(gene):

opencloning/bug_fixing/backend_v0_3.py

@@ -12,7 +12,6 @@ from ..pydantic_models import (
 from .._version import __version__
 import json
 import os
-from packaging import version
 import copy
 
 
@@ -96,7 +95,7 @@ def main(file_path: str):
         cs = fix_backend_v0_3(data)
 
         if cs is not None:
-            cs.backend_version = __version__ if version.parse(__version__) > version.parse('0.3') else '0.3'
+            cs.backend_version = __version__
             with open(new_file_path, 'w') as f:
                 f.write(cs.model_dump_json(indent=2, exclude_none=True))
 

opencloning/dna_functions.py

@@ -7,7 +7,6 @@ from pydna.dseq import Dseq
 from .pydantic_models import TextFileSequence, AddgeneIdSource, SequenceFileFormat, WekWikGeneIdSource, SEVASource
 from opencloning_linkml.datamodel import PlannotateAnnotationReport
 from pydna.parsers import parse as pydna_parse
-import requests
 from bs4 import BeautifulSoup
 import regex
 from Bio.SeqFeature import SimpleLocation, Location
@@ -18,7 +17,7 @@ import io
 import warnings
 from Bio.SeqIO.InsdcIO import GenBankIterator, GenBankScanner
 import re
-import httpx
+from .http_client import get_http_client, ConnectError, TimeoutException
 from .ncbi_requests import get_genbank_sequence
 
 
@@ -72,7 +71,7 @@ async def get_sequences_from_file_url(
     url: str, format: SequenceFileFormat = SequenceFileFormat('genbank')
 ) -> list[Dseqrecord]:
     # TODO once pydna parse is fixed it should handle urls that point to non-gb files
-    async with httpx.AsyncClient() as client:
+    async with get_http_client() as client:
         resp = await client.get(url)
 
     if resp.status_code != 200:
@@ -83,8 +82,9 @@ async def get_sequences_from_file_url(
         return custom_file_parser(io.StringIO(resp.text), format)
 
 
-def get_sequence_from_snagene_url(url: str) -> Dseqrecord:
-    resp = requests.get(url)
+async def get_sequence_from_snapgene_url(url: str) -> Dseqrecord:
+    async with get_http_client() as client:
+        resp = await client.get(url)
     # Check that resp.content is not empty
     if len(resp.content) == 0:
         raise HTTPError(url, 404, 'invalid snapgene id', 'invalid snapgene id', None)
@@ -96,7 +96,7 @@ def get_sequence_from_snagene_url(url: str) -> Dseqrecord:
 async def request_from_addgene(source: AddgeneIdSource) -> tuple[Dseqrecord, AddgeneIdSource]:
 
     url = f'https://www.addgene.org/{source.repository_id}/sequences/'
-    async with httpx.AsyncClient() as client:
+    async with get_http_client() as client:
         resp = await client.get(url)
     if resp.status_code == 404:
         raise HTTPError(url, 404, 'wrong addgene id', 'wrong addgene id', None)
@@ -150,7 +150,7 @@ async def request_from_addgene(source: AddgeneIdSource) -> tuple[Dseqrecord, Add
 
 async def request_from_wekwikgene(source: WekWikGeneIdSource) -> tuple[Dseqrecord, WekWikGeneIdSource]:
     url = f'https://wekwikgene.wllsb.edu.cn/plasmids/{source.repository_id}'
-    async with httpx.AsyncClient() as client:
+    async with get_http_client() as client:
         resp = await client.get(url)
     if resp.status_code == 404:
         raise HTTPError(url, 404, 'invalid wekwikgene id', 'invalid wekwikgene id', None)
@@ -333,10 +333,10 @@ def custom_file_parser(
 
 async def get_sequence_from_euroscarf_url(plasmid_id: str) -> Dseqrecord:
     url = f'http://www.euroscarf.de/plasmid_details.php?accno={plasmid_id}'
-    async with httpx.AsyncClient() as client:
+    async with get_http_client() as client:
         try:
             resp = await client.get(url)
-        except httpx.ConnectError as e:
+        except ConnectError as e:
             raise HTTPError(url, 504, 'could not connect to euroscarf', 'could not connect to euroscarf', None) from e
     # I don't think this ever happens
     if resp.status_code != 200:
@@ -365,7 +365,7 @@ async def get_sequence_from_euroscarf_url(plasmid_id: str) -> Dseqrecord:
 async def annotate_with_plannotate(
     file_content: str, file_name: str, url: str, timeout: int = 20
 ) -> tuple[Dseqrecord, PlannotateAnnotationReport, str]:
-    async with httpx.AsyncClient() as client:
+    async with get_http_client() as client:
         try:
             response = await client.post(
                 url,
@@ -379,9 +379,9 @@ async def annotate_with_plannotate(
             dseqr = custom_file_parser(io.StringIO(data['gb_file']), 'genbank')[0]
             report = [PlannotateAnnotationReport.model_validate(r) for r in data['report']]
             return dseqr, report, data['version']
-        except httpx.TimeoutException as e:
+        except TimeoutException as e:
             raise HTTPError(url, 504, 'plannotate server timeout', 'plannotate server timeout', None) from e
-        except httpx.ConnectError as e:
+        except ConnectError as e:
             raise HTTPError(
                 url, 500, 'cannot connect to plannotate server', 'cannot connect to plannotate server', None
             ) from e

opencloning/endpoints/external_import.py

@@ -3,7 +3,6 @@ from pydantic import create_model
 import io
 import warnings
 import asyncio
-import httpx
 from starlette.responses import RedirectResponse
 from Bio import BiopythonParserWarning
 from typing import Annotated
@@ -31,13 +30,14 @@ from ..dna_functions import (
     request_from_addgene,
     request_from_wekwikgene,
     get_sequences_from_file_url,
-    get_sequence_from_snagene_url,
+    get_sequence_from_snapgene_url,
     custom_file_parser,
     get_sequence_from_euroscarf_url,
     get_seva_plasmid,
 )
 from .. import request_examples
 from .. import ncbi_requests
+from ..http_client import ConnectError
 
 
 router = get_router()
@@ -262,7 +262,7 @@ async def get_from_repository_id_genbank(source: RepositoryIdSource):
         if seq_length > 100000:
             raise HTTPException(400, 'sequence is too long (max 100000 bp)')
         seq = await ncbi_requests.get_genbank_sequence(source.repository_id)
-    except httpx.ConnectError as exception:
+    except ConnectError as exception:
         raise HTTPException(504, f'Unable to connect to NCBI: {exception}')
 
     return {'sequences': [format_sequence_genbank(seq, source.output_name)], 'sources': [source.model_copy()]}
@@ -279,7 +279,7 @@ async def get_from_repository_id_addgene(source: AddgeneIdSource):
         dseq, out_source = await request_from_addgene(source)
     except HTTPError as exception:
         repository_id_http_error_handler(exception, source)
-    except httpx.ConnectError:
+    except ConnectError:
         raise HTTPException(504, 'unable to connect to Addgene')
 
     return {'sequences': [format_sequence_genbank(dseq, source.output_name)], 'sources': [out_source]}
@@ -296,7 +296,7 @@ async def get_from_repository_id_wekwikgene(source: WekWikGeneIdSource):
         dseq, out_source = await request_from_wekwikgene(source)
     except HTTPError as exception:
         repository_id_http_error_handler(exception, source)
-    except httpx.ConnectError:
+    except ConnectError:
         raise HTTPException(504, 'unable to connect to WekWikGene')
     return {'sequences': [format_sequence_genbank(dseq, source.output_name)], 'sources': [out_source]}
 
@@ -332,7 +332,7 @@ async def get_from_repository_id_snapgene(
     try:
         plasmid_set, plasmid_name = source.repository_id.split('/')
         url = f'https://www.snapgene.com/local/fetch.php?set={plasmid_set}&plasmid={plasmid_name}'
-        dseq = get_sequence_from_snagene_url(url)
+        dseq = await get_sequence_from_snapgene_url(url)
         # Unless a name is provided, we use the plasmid name from snapgene
         if source.output_name is None:
             source.output_name = plasmid_name
@@ -467,7 +467,7 @@ async def get_from_repository_id_seva(source: SEVASource):
         return {'sequences': [format_sequence_genbank(dseq, source.output_name)], 'sources': [source]}
     except HTTPError as exception:
         repository_id_http_error_handler(exception, source)
-    except httpx.ConnectError:
+    except ConnectError:
         raise HTTPException(504, 'unable to connect to SEVA')
     except Exception as exception:
         raise HTTPException(400, f'Error parsing file: {exception}')

opencloning/http_client.py

@@ -0,0 +1,53 @@
+# Response is imported into other modules from here
+from httpx import (  # noqa: F401
+    Response,
+    AsyncClient,
+    ConnectError,
+    TimeoutException,
+    AsyncHTTPTransport,
+    Request,
+    RequestError,
+)
+import ssl
+import certifi
+from .app_settings import settings
+import re
+
+white_listed_urls = {
+    r'^https://www.addgene.org/',
+    r'^https://media.addgene.org/',
+    r'^https://wekwikgene.wllsb.edu.cn',
+    r'^https://seva-plasmids.com/',
+    r'^https://api.ncbi.nlm.nih.gov/datasets/v2alpha/',
+    r'^https://eutils.ncbi.nlm.nih.gov/entrez/eutils/',
+    r'^https://www.snapgene.com/local/fetch.php',
+    r'^https://benchling.com/',
+    r'^https://raw.githubusercontent.com/manulera/annotated-igem-distribution',
+    r'^http://www.euroscarf.de/',
+}
+
+if settings.PLANNOTATE_URL:
+    white_listed_urls.add(settings.PLANNOTATE_URL)
+
+
+class WhiteListTransport(AsyncHTTPTransport):
+    async def handle_async_request(self, request: Request) -> Response:
+        if any(re.match(url, str(request.url)) for url in white_listed_urls):
+            return await super().handle_async_request(request)
+
+        raise RequestError(f'Request to {request.url} is not whitelisted')
+
+
+proxy = None
+if settings.PROXY_URL:
+    proxy = settings.PROXY_URL
+
+
+def get_http_client():
+    transport = WhiteListTransport()
+    client_ctx = None
+    if proxy is not None:
+        client_ctx = ssl.create_default_context(cafile=certifi.where())
+        if settings.PROXY_CERT_FILE:
+            client_ctx.load_verify_locations(cafile=settings.PROXY_CERT_FILE)
+    return AsyncClient(proxy=proxy, verify=client_ctx, transport=transport)

opencloning/ncbi_requests.py

@@ -1,24 +1,23 @@
-import requests
 from fastapi import HTTPException
 from pydna.parsers import parse as pydna_parse
-from httpx import AsyncClient, Response
 from pydna.dseqrecord import Dseqrecord
 from .app_settings import settings
+from .http_client import get_http_client, Response
 
 headers = None if settings.NCBI_API_KEY is None else {'api_key': settings.NCBI_API_KEY}
 
 
 async def async_get(url, headers, params=None) -> Response:
-    async with AsyncClient(timeout=20.0) as client:
-        return await client.get(url, headers=headers, params=params)
+    async with get_http_client() as client:
+        return await client.get(url, headers=headers, params=params, timeout=20.0)
 
 
 # TODO: this does not return old assembly accessions, see https://github.com/ncbi/datasets/issues/380#issuecomment-2231142816
-def get_assembly_accession_from_sequence_accession(sequence_accession: str) -> list[str]:
+async def get_assembly_accession_from_sequence_accession(sequence_accession: str) -> list[str]:
     """Get the assembly accession from a sequence accession"""
 
     url = f'https://api.ncbi.nlm.nih.gov/datasets/v2alpha/genome/sequence_accession/{sequence_accession}/sequence_assemblies'
-    resp = requests.get(url, headers=headers)
+    resp = await async_get(url, headers=headers)
     data = resp.json()
     if 'accessions' in data:
         return data['accessions']

{opencloning-0.3.2.dist-info → opencloning-0.3.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: opencloning
-Version: 0.3.2
+Version: 0.3.4
 Summary: Backend of OpenCloning, a web application to generate molecular cloning strategies in json format, and share them with others.
 License: MIT
 Author: Manuel Lera-Ramirez
@@ -14,7 +14,7 @@ Classifier: Programming Language :: Python :: 3.13
 Requires-Dist: beautifulsoup4 (>=4.11.1,<5.0.0)
 Requires-Dist: biopython (==1.84)
 Requires-Dist: fastapi
-Requires-Dist: httpx (>=0.25.0,<0.26.0)
+Requires-Dist: httpx (>=0.28.1,<0.29.0)
 Requires-Dist: opencloning-linkml (==0.3.0a0)
 Requires-Dist: openpyxl (>=3.1.5,<4.0.0)
 Requires-Dist: packaging (>=25.0,<26.0)
@@ -25,7 +25,6 @@ Requires-Dist: pydna (==5.5.0)
 Requires-Dist: python-multipart
 Requires-Dist: pyyaml (>=6.0.2,<7.0.0)
 Requires-Dist: regex (>=2023.10.3,<2024.0.0)
-Requires-Dist: requests (>=2.31.0,<3.0.0)
 Requires-Dist: uvicorn
 Project-URL: Repository, https://github.com/manulera/OpenCloning_backend
 Description-Content-Type: text/markdown

{opencloning-0.3.2.dist-info → opencloning-0.3.4.dist-info}/RECORD

@@ -1,7 +1,7 @@
 opencloning/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 opencloning/_version.py,sha256=6QbWXLSZypjtWL_CwJFHH4dzMRK3AUH4B0YudzvGz9s,200
 opencloning/api_config_utils.py,sha256=inAXPGYNDz-DuEoSqitImj0Vv5TpQSbMZH9D3dQb5P0,4319
-opencloning/app_settings.py,sha256=x5ddkaoyWE76fa4CdwIv-aDfg1eyZr6qTQwfKJB4mCo,1785
+opencloning/app_settings.py,sha256=MScy0le1Dn00rxqDkpeoBLWwjWQTyzHBQ-MqSDdmoe4,2054
 opencloning/assembly2.py,sha256=_UdQCnjc2wmWoeVT9NKwXcYUAEBrBT0OSBNMbGYAIL8,57041
 opencloning/batch_cloning/EBIC/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 opencloning/batch_cloning/EBIC/barcode.gb,sha256=G6kP6MuY23S-n3xg16LQaTasFtYFqik5eEgcooZ9ATM,815
@@ -15,36 +15,37 @@ opencloning/batch_cloning/pombe/index.html,sha256=3YchoKGpcKDfvTOW1Rdih4PkbZIkMj
 opencloning/batch_cloning/pombe/pombe_all.sh,sha256=0yvDdBaIdt2RsIrvnjgn5L3KtYBToq3Rl8-X8RFHibE,364
 opencloning/batch_cloning/pombe/pombe_clone.py,sha256=OY6yOlBK-9OAmHu3HUhP50mIXvyR0HJg1_2OjBFifV8,8123
 opencloning/batch_cloning/pombe/pombe_gather.py,sha256=qI-biMZGLxVDV-vOf3sT6bS1BawtTihZNcSYNlnnEi8,2432
-opencloning/batch_cloning/pombe/pombe_get_primers.py,sha256=1RbR_8YGhSrmeIVDOpUprdwLXazn1tsEPI_PL0RuWrk,3949
+opencloning/batch_cloning/pombe/pombe_get_primers.py,sha256=nrn6V4_l8FWWfqS4WU3qPt95KwzvCXxETh8E-zWbRhM,3968
 opencloning/batch_cloning/pombe/pombe_summary.py,sha256=W9DLpnCuwK7w2DhHLu60N7L6jquuYubD3ZRFwdhNPVw,4033
 opencloning/batch_cloning/ziqiang_et_al2024/__init__.py,sha256=zZUbj3uMzd9rKMXi5s9LQ1yUg7sccdS0f_4kpw7SQlk,7584
 opencloning/batch_cloning/ziqiang_et_al2024/index.html,sha256=EDncANDhhQkhi5FjnnAP6liHkG5srf4_Y46IrnMUG5g,4607
 opencloning/batch_cloning/ziqiang_et_al2024/ziqiang_et_al2024.json,sha256=d-7oXbxoKhMKLz4FJ2OGDdedWTisoaRqLAh1NZnScBg,157189
 opencloning/bug_fixing/README.md,sha256=fGf_4HPTZ2TjGfIOZzw8IAD78-N-RnBrX8mz14wjXEQ,4237
 opencloning/bug_fixing/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-opencloning/bug_fixing/backend_v0_3.py,sha256=ubfDN-IEwj-dW1Qgy3ozrkXcUIXwXvZcxJHrVanR_Ws,4213
+opencloning/bug_fixing/backend_v0_3.py,sha256=BTnqCXYIcOShut0WfwH6tDjJ1fecAHFHVSDTOKJgUZw,4119
 opencloning/cre_lox.py,sha256=x_OVYzfaLJH5eVyp05_I9YNycT606UL683AswhQ-gjU,4294
-opencloning/dna_functions.py,sha256=ivepJM2wRTIW0ArSiQ5s-XuqBd69giEQijaWXXGT64E,16536
+opencloning/dna_functions.py,sha256=WvEiKuZEzy3mXjIkOMv4Ymej6xQ3gm4mymM8JCgvE_o,16611
 opencloning/dna_utils.py,sha256=uv97aO04dbk3NnqbN6GlnwOu0MOpK88rl2np2QcEQ4Y,6301
 opencloning/ebic/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 opencloning/ebic/primer_design.py,sha256=gPZTF9w5SV7WGgnefp_HBM831y0z73M1Kb0QUPnbfIM,2270
 opencloning/ebic/primer_design_settings.py,sha256=OnFsuh0QCvplUEPXLZouzRo9R7rm4nLbcd2LkDCiIDM,1896
 opencloning/endpoints/annotation.py,sha256=3rlIXeNQzoqPD9lJUEBGLGxvlhUCTcfkqno814A8P0U,2283
 opencloning/endpoints/assembly.py,sha256=MMwvlyM2NHnT04Pp7LdKQRvahq0itdqTtZx3OQhOswc,20980
-opencloning/endpoints/external_import.py,sha256=xU-ZL503pJW1M08gxXTULaLgp9jHc_dBVrcyMRjNmow,18178
+opencloning/endpoints/external_import.py,sha256=i2hAKSYi2IIdglmDhDhWmBzHbhn6A9A8ybbj4nmhROM,18188
 opencloning/endpoints/no_assembly.py,sha256=NY6rhEDCNoZVn6Xk81cen2n-FkMr7ierfxM8G0npbQs,4722
 opencloning/endpoints/no_input.py,sha256=DuqKD3Ph3a44ZxPMEzZv1nwD5xlxYsN7YyxXcfjSUFc,3844
 opencloning/endpoints/other.py,sha256=7YBXU5UrVCjEjOjdYWw-0sASXn3MhWVZYwDYSZD4C9E,3452
 opencloning/endpoints/primer_design.py,sha256=3eiQ7MwgeLoAuXFUMNF-DzjzwH_eJGCjd4s32CjxIic,12717
 opencloning/gateway.py,sha256=pFB3gsCQL715kOFOP1NQOOsQqrkWuQe5qXk4IunF5SA,8486
 opencloning/get_router.py,sha256=l2DXaTbeL2tDqlnVMlcewutzt1sjaHlxku1X9HVUwJk,252
+opencloning/http_client.py,sha256=nepAAJXA9Wtehjeex3PuQRbUlB0kbhxSOPqzcg7gMtY,1624
 opencloning/main.py,sha256=l9PrPBMtGMEWxAPiPWR15Qv2oDNnRoNd8H8E3bZW6Do,3750
-opencloning/ncbi_requests.py,sha256=JrFc-Ugr1r1F4LqsdpJZEiERj7ZemvZSgiIltl2Chx8,5547
+opencloning/ncbi_requests.py,sha256=b8ow9TDpXbyYk_0HeK-7RXWwwZGrhH-MylSNc3_tH0I,5557
 opencloning/primer_design.py,sha256=nqCmYIZ7UvU4CQwVGJwX7T5LTHwt3-51_ZcTZZAgT_Y,9175
 opencloning/pydantic_models.py,sha256=lMO78M4MwDgzTEGz9qzsaADwAFXagWK4qGsF1K1hLZw,18865
 opencloning/request_examples.py,sha256=QAsJxVaq5tHwlPB404IiJ9WC6SA7iNY7XnJm63BWT_E,2944
 opencloning/utils.py,sha256=0Lvw1h1AsUJTK2b9mNzYVi_DBeWmWCFA5dIPl_gERcI,1479
-opencloning-0.3.2.dist-info/LICENSE,sha256=VSdVE1f8axjIh6gvo9ZZygJdTVkRFMcwCW_hvjOHC_w,1058
-opencloning-0.3.2.dist-info/METADATA,sha256=Aw5-DxzqZaSzvhHH_7cnS9FPdbspRiq8I3c-YVavggU,9083
-opencloning-0.3.2.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
-opencloning-0.3.2.dist-info/RECORD,,
+opencloning-0.3.4.dist-info/LICENSE,sha256=VSdVE1f8axjIh6gvo9ZZygJdTVkRFMcwCW_hvjOHC_w,1058
+opencloning-0.3.4.dist-info/METADATA,sha256=beszv-cKQj-br6Zcn9kW_v-PiaHe-MIOJ6PUZ7atBPs,9041
+opencloning-0.3.4.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
+opencloning-0.3.4.dist-info/RECORD,,