Mercurial > repos > iuc > ncbi_eutils_efetch

changeset 5:e269b3b5185b draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/ncbi_entrez_eutils commit 15bcc5104c577b4b9c761f2854fc686c07ffa9db
author iuc
date Thu, 07 Jul 2016 02:37:49 -0400
parents c26d1863f3f3
children 2ff5369b4b51
files __efetch_build_options.py ecitmatch.py efetch.py efetch.xml eutils.py eutils.pyc macros.xml test test-data/ecitmatch.results.tsv test-data/esearch.pubmed.2014-01-pnas.xml test-data/esearch.pubmed.xml test-data/esummary.tax.xml test-data/pm-tax-neighbor.xml tmp
diffstat 14 files changed, 51 insertions(+), 88 deletions(-) [+]
line wrap: on
line diff
--- a/__efetch_build_options.py	Fri Jun 10 15:03:49 2016 -0400
+++ b/__efetch_build_options.py	Thu Jul 07 02:37:49 2016 -0400
@@ -210,7 +210,7 @@
         </param>
       </when>'''
 
-FORMAT_OPTION_TPL =  '''<option value="{name_type}">{name_type_human}</option>'''
+FORMAT_OPTION_TPL = '''<option value="{name_type}">{name_type_human}</option>'''
 
 format_names = {}
 
--- a/ecitmatch.py	Fri Jun 10 15:03:49 2016 -0400
+++ b/ecitmatch.py	Thu Jul 07 02:37:49 2016 -0400
@@ -5,7 +5,7 @@
 
 if __name__ == '__main__':
     parser = argparse.ArgumentParser(description='ECitMatch', epilog='')
-    parser.add_argument('--file', help='Tabular file containing citations to search')
+    parser.add_argument('--file', type=argparse.FileType('r'), help='Tabular file containing citations to search')
 
     parser.add_argument('--key', nargs='*', help='Citation Key')
     parser.add_argument('--journal_title', nargs='*', help='Journal Title')
@@ -35,6 +35,7 @@
             })
     else:
         for line in args.file:
+            line = line.strip()
             if not line.startswith('#'):
                 tmp = line.split('\t')
                 try:
--- a/efetch.py	Fri Jun 10 15:03:49 2016 -0400
+++ b/efetch.py	Thu Jul 07 02:37:49 2016 -0400
@@ -17,8 +17,6 @@
     # Output
     parser.add_argument('--retmode', help='Retmode')
     parser.add_argument('--rettype', help='Rettype')
-    parser.add_argument('--whole', action='store_true',
-                        help='Download all records associated with query')
     args = parser.parse_args()
 
     c = eutils.Client(history_file=args.history_file, user_email=args.user_email, admin_email=args.admin_email)
@@ -34,4 +32,4 @@
         if getattr(args, attr, None) is not None:
             payload[attr] = getattr(args, attr)
 
-    c.fetch(args.db, whole=args.whole, **payload)
+    c.fetch(args.db, ftype=args.retmode, **payload)
--- a/efetch.xml	Fri Jun 10 15:03:49 2016 -0400
+++ b/efetch.xml	Thu Jul 07 02:37:49 2016 -0400
@@ -19,18 +19,15 @@
 --rettype $rettype
 
 @EMAIL_ARGUMENTS@
-$whole
-> $default]]></command>
+]]></command>
   <inputs>
     <expand macro="db"/>
     <expand macro="list_or_hist"/>
-    <param checked="false" label="Download all records associated with query" name="whole" type="boolean" truevalue="--whole" falsevalue=""/>
   </inputs>
   <outputs>
-    <data format="txt" name="default" label="NCBI EFetch Results">
-      <discover_datasets pattern="__designation__.out" ext="txt"/>
-      <expand macro="efetch_formats" />
-    </data>
+    <collection type="list" label="NCBI EFetch Results" name="output1">
+      <discover_datasets pattern="__designation_and_ext__" directory="downloads"/>
+    </collection>
   </outputs>
   <tests>
     <test>
@@ -38,7 +35,9 @@
       <param name="output_format" value="full-xml"/>
       <param name="qss" value="id_list"/>
       <param name="id_list" value="10239"/>
-      <output name="default" file="viruses.tax.xml">
+      <output name="default">
+        <discovered_dataset designation="EFetch Results Chunk 0" ftype="xml" file="viruses.tax.xml" lines_diff="2">
+        </discovered_dataset>
       </output>
     </test>
   </tests>
--- a/eutils.py	Fri Jun 10 15:03:49 2016 -0400
+++ b/eutils.py	Thu Jul 07 02:37:49 2016 -0400
@@ -43,27 +43,23 @@
     def post(self, database, **payload):
         return json.dumps(Entrez.read(Entrez.epost(database, **payload)), indent=4)
 
-    def fetch(self, db, whole=False, **payload):
-        if whole:
-            if 'id' in payload:
-                summary = self.id_summary(db, payload['id'])
-            else:
-                summary = self.history_summary(db)
+    def fetch(self, db, ftype=None, **payload):
+        os.makedirs("downloads")
 
-            count = len(summary)
-
-            payload['retmax'] = BATCH_SIZE
+        if 'id' in payload:
+            summary = self.id_summary(db, payload['id'])
+        else:
+            summary = self.history_summary(db)
 
-            # Print the first one
-            print Entrez.efetch(db, **payload).read()
-            # Then write subsequent to files for <discover datasets>
-            for i in range(BATCH_SIZE, count, BATCH_SIZE):
-                payload['retstart'] = i
-                # TODO: output multiple files??? Collection?
-                with open('%s.out' % i, 'w') as handle:
-                    handle.write(Entrez.efetch(db, **payload).read())
-        else:
-            print Entrez.efetch(db, **payload).read()
+        count = len(summary)
+        payload['retmax'] = BATCH_SIZE
+
+        # This may be bad. I'm not sure yet. I think it will be ... but UGH.
+        for i in range(0, count, BATCH_SIZE):
+            payload['retstart'] = i
+            file_path = os.path.join('downloads', 'EFetch Results Chunk %s.%s' % (i, ftype))
+            with open(file_path, 'w') as handle:
+                handle.write(Entrez.efetch(db, **payload).read())
 
     def id_summary(self, db, id_list):
         payload = {
@@ -108,7 +104,7 @@
         return Entrez.egquery(**kwargs).read()
 
     def citmatch(self, **kwargs):
-        return Entrez.ECitMatch(**kwargs).read()
+        return Entrez.ecitmatch(**kwargs).read()
 
     @classmethod
     def parse_ids(cls, id_list, id, history_file):
Binary file eutils.pyc has changed
--- a/macros.xml	Fri Jun 10 15:03:49 2016 -0400
+++ b/macros.xml	Thu Jul 07 02:37:49 2016 -0400
@@ -835,6 +835,7 @@
   </xml>
   <xml name="requirements">
     <requirements>
+      <requirement type="package" version="2.7">python</requirement>
       <requirement type="package" version="1.66">biopython</requirement>
     </requirements>
   </xml>
--- a/test	Fri Jun 10 15:03:49 2016 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,4 +0,0 @@
-{
-    "QueryKey": "1", 
-    "WebEnv": "NCID_1_29968407_130.14.22.215_9001_1465585167_557791559_0MetA0_S_MegaStore_F_1"
-}
\ No newline at end of file
--- a/test-data/ecitmatch.results.tsv	Fri Jun 10 15:03:49 2016 -0400
+++ b/test-data/ecitmatch.results.tsv	Thu Jul 07 02:37:49 2016 -0400
@@ -1,1 +1,2 @@
-proc natl acad sci u s a	1991	88	3248	mann bj	citation_1	2014248
+	1991	88	3248	mann bj	citation_1	2014248
+
--- a/test-data/esearch.pubmed.2014-01-pnas.xml	Fri Jun 10 15:03:49 2016 -0400
+++ b/test-data/esearch.pubmed.2014-01-pnas.xml	Thu Jul 07 02:37:49 2016 -0400
@@ -21,5 +21,5 @@
 <Id>24481252</Id>
 <Id>24477693</Id>
 <Id>24477692</Id>
-</IdList><TranslationSet><Translation>     <From>PNAS[ta]</From>     <To>"Proc Natl Acad Sci U S A"[Journal]</To>    </Translation></TranslationSet><TranslationStack>   <TermSet>    <Term>"Proc Natl Acad Sci U S A"[Journal]</Term>    <Field>Journal</Field>    <Count>120385</Count>    <Explode>N</Explode>   </TermSet>   <TermSet>    <Term>2014/01/01[PDAT]</Term>    <Field>PDAT</Field>    <Count>0</Count>    <Explode>N</Explode>   </TermSet>   <TermSet>    <Term>2014/02/01[PDAT]</Term>    <Field>PDAT</Field>    <Count>0</Count>    <Explode>N</Explode>   </TermSet>   <OP>RANGE</OP>   <OP>AND</OP>  </TranslationStack><QueryTranslation>"Proc Natl Acad Sci U S A"[Journal] AND 2014/01/01[PDAT] : 2014/02/01[PDAT]</QueryTranslation></eSearchResult>
+</IdList><TranslationSet><Translation>     <From>PNAS[ta]</From>     <To>"Proc Natl Acad Sci U S A"[Journal]</To>    </Translation></TranslationSet><TranslationStack>   <TermSet>    <Term>"Proc Natl Acad Sci U S A"[Journal]</Term>    <Field>Journal</Field>    <Count>124812</Count>    <Explode>N</Explode>   </TermSet>   <TermSet>    <Term>2014/01/01[PDAT]</Term>    <Field>PDAT</Field>    <Count>0</Count>    <Explode>N</Explode>   </TermSet>   <TermSet>    <Term>2014/02/01[PDAT]</Term>    <Field>PDAT</Field>    <Count>0</Count>    <Explode>N</Explode>   </TermSet>   <OP>RANGE</OP>   <OP>AND</OP>  </TranslationStack><QueryTranslation>"Proc Natl Acad Sci U S A"[Journal] AND 2014/01/01[PDAT] : 2014/02/01[PDAT]</QueryTranslation></eSearchResult>
 
--- a/test-data/esearch.pubmed.xml	Fri Jun 10 15:03:49 2016 -0400
+++ b/test-data/esearch.pubmed.xml	Thu Jul 07 02:37:49 2016 -0400
@@ -21,5 +21,5 @@
 <Id>11121066</Id>
 <Id>11121065</Id>
 <Id>11121064</Id>
-</IdList><TranslationSet><Translation>     <From>PNAS[ta]</From>     <To>"Proc Natl Acad Sci U S A"[Journal]</To>    </Translation></TranslationSet><TranslationStack>   <TermSet>    <Term>"Proc Natl Acad Sci U S A"[Journal]</Term>    <Field>Journal</Field>    <Count>120385</Count>    <Explode>N</Explode>   </TermSet>   <TermSet>    <Term>97[vi]</Term>    <Field>vi</Field>    <Count>74742</Count>    <Explode>N</Explode>   </TermSet>   <OP>AND</OP>   <OP>GROUP</OP>  </TranslationStack><QueryTranslation>"Proc Natl Acad Sci U S A"[Journal] AND 97[vi]</QueryTranslation></eSearchResult>
+</IdList><TranslationSet><Translation>     <From>PNAS[ta]</From>     <To>"Proc Natl Acad Sci U S A"[Journal]</To>    </Translation></TranslationSet><TranslationStack>   <TermSet>    <Term>"Proc Natl Acad Sci U S A"[Journal]</Term>    <Field>Journal</Field>    <Count>124812</Count>    <Explode>N</Explode>   </TermSet>   <TermSet>    <Term>97[vi]</Term>    <Field>vi</Field>    <Count>77218</Count>    <Explode>N</Explode>   </TermSet>   <OP>AND</OP>   <OP>GROUP</OP>  </TranslationStack><QueryTranslation>"Proc Natl Acad Sci U S A"[Journal] AND 97[vi]</QueryTranslation></eSearchResult>
 
--- a/test-data/esummary.tax.xml	Fri Jun 10 15:03:49 2016 -0400
+++ b/test-data/esummary.tax.xml	Thu Jul 07 02:37:49 2016 -0400
@@ -1,5 +1,5 @@
 <?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE eSummaryResult PUBLIC "-//NLM//DTD esummary v1 20060131//EN" "http://eutils.ncbi.nlm.nih.gov/eutils/dtd/20060131/esummary-v1.dtd">
+<!DOCTYPE eSummaryResult PUBLIC "-//NLM//DTD esummary v1 20041029//EN" "http://eutils.ncbi.nlm.nih.gov/eutils/dtd/20041029/esummary-v1.dtd">
 <eSummaryResult>
 <DocSum>
 	<Id>10239</Id>
--- a/test-data/pm-tax-neighbor.xml	Fri Jun 10 15:03:49 2016 -0400
+++ b/test-data/pm-tax-neighbor.xml	Thu Jul 07 02:37:49 2016 -0400
@@ -1,24 +1,24 @@
-<?xml version="1.0"?>
-<!DOCTYPE eLinkResult PUBLIC "-//NLM//DTD eLinkResult, 23 November 2010//EN" "http://www.ncbi.nlm.nih.gov/entrez/query/DTD/eLink_101123.dtd">
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE eLinkResult PUBLIC "-//NLM//DTD elink 20101123//EN" "http://eutils.ncbi.nlm.nih.gov/eutils/dtd/20101123/elink.dtd">
 <eLinkResult>
 
-	<LinkSet>
-		<DbFrom>taxonomy</DbFrom>
-		<IdList>
-			<Id>510899</Id>
-		</IdList>
-		
-		<LinkSetDb>
-			<DbTo>pubmed</DbTo>
-			<LinkName>taxonomy_pubmed_entrez</LinkName>
-			
-				<Link>
+  <LinkSet>
+    <DbFrom>taxonomy</DbFrom>
+    <IdList>
+      <Id>510899</Id>
+    </IdList>
+    
+    <LinkSetDb>
+      <DbTo>pubmed</DbTo>
+      <LinkName>taxonomy_pubmed_entrez</LinkName>
+      
+        <Link>
 				<Id>22241621</Id>
 			</Link>
-			
-		</LinkSetDb>
-		
-		
-	</LinkSet>
+      
+    </LinkSetDb>
+    
+    
+  </LinkSet>
 </eLinkResult>
 
--- a/tmp	Fri Jun 10 15:03:49 2016 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,29 +0,0 @@
-<?xml version="1.0"?>
-<!DOCTYPE TaxaSet PUBLIC "-//NLM//DTD Taxon, 14th January 2002//EN" "http://www.ncbi.nlm.nih.gov/entrez/query/DTD/taxon.dtd">
-<TaxaSet><Taxon>
-    <TaxId>10239</TaxId>
-    <ScientificName>Viruses</ScientificName>
-    <OtherNames>
-        <BlastName>viruses</BlastName>
-        <Synonym>Vira</Synonym>
-        <Synonym>Viridae</Synonym>
-    </OtherNames>
-    <ParentTaxId>1</ParentTaxId>
-    <Rank>superkingdom</Rank>
-    <Division>Viruses</Division>
-    <GeneticCode>
-        <GCId>1</GCId>
-        <GCName>Standard</GCName>
-    </GeneticCode>
-    <MitoGeneticCode>
-        <MGCId>0</MGCId>
-        <MGCName>Unspecified</MGCName>
-    </MitoGeneticCode>
-    <Lineage/>
-    <CreateDate>1995/02/27 09:24:00</CreateDate>
-    <UpdateDate>2010/11/23 11:40:11</UpdateDate>
-    <PubDate>1993/04/20 01:00:00</PubDate>
-</Taxon>
-
-</TaxaSet>
-