move package back to eutils (not biocommons.eutils) as with 0.6.0

Author: Reece Hart

docs/conf.py

@@ -14,7 +14,7 @@
 
 import sphinx_rtd_theme
 
-from biocommons import eutils
+import eutils
 
 # If extensions (or modules to document with autodoc) are in another directory,
 # add these directories to sys.path here. If the directory is relative to the

sbin/eutils-shell

@@ -2,48 +2,61 @@
 
 import gzip
 import logging
-import os
+from pathlib import Path
 
 import lxml.etree as le
 
-from biocommons.eutils import Client
+from eutils import Client
+from eutils._internal.xmlfacades.entrezgeneset import EntrezgeneSet
 
 # new style
-from biocommons.eutils._internal.xmlfacades.esearchresult import ESearchResult
-from biocommons.eutils._internal.xmlfacades.entrezgeneset import EntrezgeneSet
+from eutils._internal.xmlfacades.esearchresult import ESearchResult
 
 logging.basicConfig(level=logging.DEBUG)
-
-data_dir = os.path.join(os.path.dirname(os.path.realpath(__file__)),'..','tests','data')
+data_dir = Path(__file__).resolve().parent.parent / "tests" / "data"
 ec = Client()
 
 
 if True:
-    xml = gzip.open(os.path.join(data_dir,'esearch.fcgi?term=hart%20rk[author].xml.gz')).read()
+    with gzip.open(data_dir / "esearch.fcgi?term=hart%20rk[author].xml.gz") as f:
+        xml = f.read()
     doc = le.XML(xml)
     esr = ESearchResult(doc)
 
 
 if False:
-    xml = gzip.open(os.path.join(data_dir,'entrezgeneset.xml.gz')).read()
-    doc = lxml.etree.XML(xml)
+    with gzip.open(data_dir / "entrezgeneset.xml.gz") as f:
+        xml = f.read()
+    doc = le.XML(xml)
     egs = EntrezgeneSet(doc)
 
-    print("{} genes in EntrezgeneSet".format(len(egs.entrezgenes)))
+    print(f"{len(egs.entrezgenes)} genes in EntrezgeneSet")
     for eg in egs:
-        print("\t".join(map(str,[eg.gene_id,eg.maploc,eg.hgnc,
-                                eg.summary[:30] + "..." if eg.summary else None])))
+        print(
+            "\t".join(
+                map(
+                    str,
+                    [
+                        eg.gene_id,
+                        eg.maploc,
+                        eg.hgnc,
+                        eg.summary[:30] + "..." if eg.summary else None,
+                    ],
+                )
+            )
+        )
 
 if False:
-    esr = ec.esearch(db='gene',term='tumor necrosis factor')
-    egs = ec.efetch(db='gene',id=esr.ids[0])
+    esr = ec.esearch(db="gene", term="tumor necrosis factor")
+    egs = ec.efetch(db="gene", id=esr.ids[0])
     eg = egs.entrezgenes[0]
 
 if False:
-    esr = ec.esearch(db='nuccore',term='NM_000533.3')
-    gbset = ec.efetch(db='nuccore',id=esr.ids[0])
+    esr = ec.esearch(db="nuccore", term="NM_000533.3")
+    gbset = ec.efetch(db="nuccore", id=esr.ids[0])
     gbseq = gbset.gbseqs[0]
 
 
-import IPython; IPython.embed()
+import IPython  # noqa: E402
 
+IPython.embed()

sbin/test-script

@@ -6,32 +6,35 @@ This script queries NCBI for human gene records in Entrez.
 
 """
 
-import csv
-import logging
 import lxml.etree as le
 import requests
-import sys
-import time
 
-from biocommons.eutils._internal.xmlfacades.entrezgeneset import EntrezgeneSet
+from eutils._internal.xmlfacades.entrezgeneset import EntrezgeneSet
 
-eutils_base_url = 'https://eutils.ncbi.nlm.nih.gov/entrez/eutils'
+eutils_base_url = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils"
 retmax_request = 250
 
+
 def fetch_gene(hgnc):
     # search for all human genes, saving history at NCBI
-    esearch_url = eutils_base_url+"/esearch.fcgi?db=gene&usehistory=y&retmax=0&term=human[orgn] AND alive[property] AND {hgnc}[PREF]".format(hgnc=hgnc)
-    r1 = requests.get(esearch_url)
+    esearch_url = (
+        eutils_base_url
+        + f"/esearch.fcgi?db=gene&usehistory=y&retmax=0&term=human[orgn] AND alive[property] AND {hgnc}[PREF]"
+    )
+    r1 = requests.get(esearch_url, timeout=10)
     r1_x = le.XML(r1.content)
-    webenv_key = r1_x.find('WebEnv').text
-    query_key = r1_x.find('QueryKey').text
-    count = int(r1_x.find('Count').text)
-    assert count == 1, "hgnc {} returned {} hits".format(hgnc,count)
-
-    efetch_url = eutils_base_url+"/efetch.fcgi?db=gene&usehistory=&retmode=XML&WebEnv={}&query_key={}&retmax={}".format(webenv_key,query_key,retmax_request)
-    r2 = requests.get(efetch_url + "&retstart=" + str(0))
+    webenv_key = r1_x.find("WebEnv").text
+    query_key = r1_x.find("QueryKey").text
+    count = int(r1_x.find("Count").text)
+    assert count == 1, f"hgnc {hgnc} returned {count} hits"  # noqa: S101
+
+    efetch_url = (
+        eutils_base_url
+        + f"/efetch.fcgi?db=gene&usehistory=&retmode=XML&WebEnv={webenv_key}&query_key={query_key}&retmax={retmax_request}"
+    )
+    r2 = requests.get(efetch_url + "&retstart=" + str(0), timeout=10)
     egs = EntrezgeneSet(le.XML(r2.content))
-    assert len(egs.entrezgenes) == 1, "more than one entrezgene entry in efetch reply"
+    assert len(egs.entrezgenes) == 1, "more than one entrezgene entry in efetch reply"  # noqa: S101
 
     return egs.entrezgenes[0]