Update test and apply precommit

.pre-commit-config.yaml

@@ -0,0 +1,33 @@
+
+files: '\.(py|rst|sh)$'
+fail_fast: false
+
+repos:
+-   repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v3.2.0
+    hooks:
+    -   id: trailing-whitespace
+    -   id: end-of-file-fixer
+    -   id: check-yaml
+    #-   id: check-executables-have-shebangs
+    -   id: check-ast
+
+-   repo: https://github.com/pycqa/flake8
+    rev: 6.1.0
+    hooks:
+    -   id: flake8
+        args: ["-j8", "--ignore=E203,E501,W503,E722", "--max-line-length=120", "--exit-zero"]
+
+-   repo: https://github.com/psf/black
+    rev: 22.10.0
+    hooks:
+    -   id: black
+        args: ["--line-length=120"]
+        exclude: E501
+
+-   repo: https://github.com/pycqa/isort
+    rev: 5.12.0
+    hooks:
+      - id: isort
+        args: ["--profile", "black"] # solves conflicts between black and isort
+

pyproject.toml

@@ -2,14 +2,14 @@
 requires = ["poetry-core"]
 build-backend = "poetry.core.masonry.api"
 
-[tool.poetry]
+[project]
 name = "bioservices"
 version = "1.13.0"
 description = "Access to Biological Web Services from Python"
-authors = ["Thomas Cokelaer <[email protected]>"]
+authors = [{name="Thomas Cokelaer", email="[email protected]"}]
 license = "GPLv3"
-readme = ["README.rst", "LICENSE"]
-keywords = ["BioServices", "WebServices", "Biology", "BioDBNet", "ChEBI", "UniChem", "Kegg", "KEGG", "BioModels",   "EUtils", "UniProt", "PICR", "ArrayExpress", "MUSCLE", "QuickGO", "PDB", "PSICQUIC", "Blast", "BioMART", "PantherDB", "BioGRID", "MIRIAM", "BioMart", "GeneProf", "ChEMBL", "ChemSpider",  "HGNC", "PathwayCommons", "Rhea", "Ensembl"]
+readme = "README.rst"
+keywords = ["BioServices", "WebServices", "Biology", "ChEBI", "UniChem", "Kegg", "KEGG", "BioModels", "EUtils", "UniProt", "PICR", "ArrayExpress", "MUSCLE", "QuickGO", "PDB", "PSICQUIC", "Blast", "BioMART", "PantherDB", "BioGRID", "MIRIAM", "BioMart", "GeneProf", "ChEMBL", "ChemSpider",  "HGNC", "PathwayCommons", "Rhea", "Ensembl"]
 
 classifiers = [
         "Development Status :: 5 - Production/Stable",
@@ -29,8 +29,28 @@ classifiers = [
         "Topic :: Scientific/Engineering :: Information Analysis",
 ]
 
+requires-python = ">=3.8,<4.0"
+dependencies = [
+    "click (>=8.1.8,<9.0.0)",
+    "appdirs (>=1.4.4,<2.0.0)",
+    "matplotlib (<4)",
+    "easydev (>=0.13.3,<0.14.0)",
+    "tqdm (>=4.67.1,<5.0.0)",
+    "rich-click (>=1.8.5,<2.0.0)",
+    "colorlog (>=6.9.0,<7.0.0)",
+    "beautifulsoup4 (>=4.12.3,<5.0.0)",
+    "grequests (>=0.7.0,<0.8.0)",
+    "requests (>=2.32.3,<3.0.0)",
+    "lxml (>=5.3.0,<6.0.0)",
+    "requests-cache (>=1.2.1,<2.0.0)",
+    "suds-community (>=1.2.0,<2.0.0)",
+    "wrapt (>=1.17.2,<2.0.0)",
+    "xmltodict (>=0.14.2,<0.15.0)",
+    "pandas (<2.2)"
 
-[tool.poetry.scripts]
+]
+
+[project.scripts]
 bioservices = "bioservices.main:main"
 
 
@@ -42,26 +62,6 @@ Documentation =  "https://bioesrvices.readthedocs.io"
 
 
 
-[tool.poetry.dependencies]
-python = "^3.8"
-appdirs = "^1.4.4"
-click = "^8.1.7"
-easydev = "^0.12.1"
-matplotlib = "<4"
-tqdm = "^4.66.1"
-rich-click = "^1.7.2"
-beautifulsoup4 = "^4.12.3"
-colorlog = "^6.8.2"
-grequests = "^0.7.0"
-requests = "^2.31.0"
-pandas = ">=0.21.1"
-lxml = "^5.1.0"
-xmltodict = "^0.13.0"
-wrapt = "^1.16.0"
-requests-cache = "^1.1.1"
-suds-community = "^1.1.2"
-
-
 [tool.poetry.group.dev.dependencies]
 pytest = "^8"
 pytest-cov = "^4.1.0"

src/bioservices/biomart.py

@@ -33,10 +33,10 @@
 
 .. note:: SOAP and REST are available. We use REST for the wrapping.
 """
-from io import StringIO
-from bioservices import REST, BioServicesError
 from functools import wraps
-from bioservices import logger
+from io import StringIO
+
+from bioservices import REST, BioServicesError, logger
 
 logger.name = __name__
 import pandas as pd
@@ -359,8 +359,9 @@ def filters(self, dataset):
             scrofa,Taeniopygia guttata ,Xenopus tropicalis]
 
         """
-        if dataset not in [x for k in self.valid_attributes.keys() for x in self.valid_attributes[k]]:
-            raise ValueError("provided dataset (%s) is not found. see valid_attributes" % dataset)
+        valid_attributes = sorted([x for k in self.valid_attributes.keys() for x in self.valid_attributes[k]])
+        if dataset not in valid_attributes:
+            raise ValueError(f"provided dataset ({dataset}) is not found. see valid_attributes {valid_attributes}")
         ret = self.http_get("?type=filters&dataset=%s" % dataset, frmt="txt")
         ret = [x for x in ret.split("\n") if len(x)]
         results = {}

src/bioservices/ensembl.py

@@ -32,8 +32,8 @@
 
 
 """
-from bioservices.services import REST
 from bioservices import logger
+from bioservices.services import REST
 
 logger.name = __name__
 
@@ -189,13 +189,13 @@ def get_genetree_by_member_symbol(
     def get_genetree_by_member_id(
         self,
         identifier,
+        species,
         frmt="json",
         aligned=False,
         db_type="core",
         object_type=None,
         nh_format="simple",
         sequence="protein",
-        species="homo_sapiens",
         compara="multi",
     ):
         """Retrieves a gene tree containing the gene identified by a symbol
@@ -211,7 +211,7 @@ def get_genetree_by_member_id(
 
         :
 
-            get_genetree_by_member_id('ENSG00000157764', frmt='phyloxml')
+            get_genetree_by_member_id('ENSG00000157764', 'human', frmt='phyloxml')
 
 
         """
@@ -222,7 +222,7 @@ def get_genetree_by_member_id(
         self.check_sequence(sequence)
 
         res = self.services.http_get(
-            "genetree/member/id/" + identifier,
+            f"genetree/member/id/{species}/{identifier}",
             frmt=frmt,
             headers=self.services.get_headers(content=frmt),
             params={
@@ -356,23 +356,23 @@ def get_alignment_by_region(
         )
         return res
 
-    def get_homology_by_id(
+    def get_homology_by_species_and_id(
         self,
         identifier,
+        species,
         frmt="json",
         aligned=True,
         compara="multi",
         format=None,
         sequence=None,
-        species=None,
         target_species=None,
         target_taxon=None,
         type="all",
     ):
         """Retrieves homology information (orthologs) by Ensembl gene id"""
         self._check_frmt(frmt, ["xml"])
         res = self.services.http_get(
-            "homology/id/{0}".format(identifier),
+            f"homology/id/{species}/{identifier}",
             frmt=frmt,
             headers=self.services.get_headers(content=frmt),
             params={
@@ -381,7 +381,6 @@ def get_homology_by_id(
                 "compara": compara,
                 "format": format,
                 "sequence": sequence,
-                "species": species,
                 "target_species": target_species,
                 "target_taxon": target_taxon,
                 "type": type,

src/bioservices/ncbiblast.py

@@ -36,8 +36,8 @@
 import sys
 import time
 
-from bioservices.services import REST
 from bioservices import logger
+from bioservices.services import REST
 
 logger.name = __name__
 
@@ -346,7 +346,7 @@ def get_result_types(self, jobid):
         """
         if self.get_status(jobid) != "FINISHED":
             self.services.logging.warning("waiting for the job to be finished. May take a while")
-            self.wait(jobid, verbose=False)
+            self.wait(jobid)
         url = "resulttypes/" + jobid
         res = self.services.http_get(
             url,