changeset 0:0442068f5c91 draft

Uploaded
author scottx611x
date Tue, 26 Apr 2016 13:33:16 -0400
parents
children ff7e10e82d89
files data_manager_gene_annotation/data_manager/data_manager.py data_manager_gene_annotation/data_manager/gene_annotation_fetcher.xml data_manager_gene_annotation/data_manager_conf.xml data_manager_gene_annotation/tool-data/gene_annotation.loc.sample data_manager_gene_annotation/tool_data_table_conf.xml.sample
diffstat 4 files changed, 124 insertions(+), 0 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/data_manager_gene_annotation/data_manager/data_manager.py	Tue Apr 26 13:33:16 2016 -0400
@@ -0,0 +1,76 @@
+import argparse
+import datetime
+import json
+import os
+import shutil
+import sys
+import tarfile
+import urllib2
+import zipfile
+
+parser = argparse.ArgumentParser(description='Create data manager json.')
+parser.add_argument('--out', dest='output', action='store', help='JSON filename')
+parser.add_argument('--name', dest='name', action='store', default=str(datetime.date.today()), help='Data table entry unique ID')
+parser.add_argument('--url', dest='url', action='store', help='Download URL', default="http://www.scott-ouellette.com/gene_annotations/chr1-hg19_genes.gtf")
+
+args = parser.parse_args()
+
+def url_download(url, workdir):
+    if not os.path.exists(workdir):
+        os.makedirs(workdir)
+    file_path = os.path.join(workdir, 'download.dat')
+    if not os.path.exists(workdir):
+        os.makedirs(workdir)
+    src = None
+    dst = None
+    hdr = {'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.64 Safari/537.11',
+       'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
+       'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.3',
+       'Accept-Encoding': 'none',
+       'Accept-Language': 'en-US,en;q=0.8',
+       'Connection': 'keep-alive'}
+    try:
+        req = urllib2.Request(url, headers=hdr)
+        src = urllib2.urlopen(req)
+        dst = open(file_path, 'wb')
+        while True:
+            chunk = src.read(2**10)
+            if chunk:
+                dst.write(chunk)
+            else:
+                break
+    except Exception as e:
+        print e, "FUCK"
+    finally:
+        if src:
+            src.close()
+        if dst:
+            dst.close()
+    if tarfile.is_tarfile(file_path):
+        fh = tarfile.open(file_path, 'r:*')
+    elif zipfile.is_zipfile(file_path):
+        fh = zipfile.ZipFile(file_path, 'r')
+    else:
+        return
+    fh.extractall(workdir)
+    os.remove(file_path)
+
+
+def main(args):
+    workdir = os.path.join(os.getcwd(), 'gene_annotation')
+    url_download(args.url, workdir)
+    data_manager_entry = {}
+    data_manager_entry['value'] = args.name.lower()
+    data_manager_entry['name'] = args.name
+    data_manager_entry['path'] = args.output
+    data_manager_json = dict(data_tables=dict(gene_annotation=data_manager_entry))
+    params = json.loads(open(args.output).read())
+    target_directory = params['output_data'][0]['extra_files_path']
+    os.mkdir(target_directory)
+    output_path = os.path.abspath(os.path.join(os.getcwd(), 'gene_annotation'))
+    for filename in os.listdir(workdir):
+        shutil.move(os.path.join(output_path, filename), target_directory)
+    file(args.output, 'w').write(json.dumps(data_manager_json))
+
+if __name__ == '__main__':
+    main(args)
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/data_manager_gene_annotation/data_manager/gene_annotation_fetcher.xml	Tue Apr 26 13:33:16 2016 -0400
@@ -0,0 +1,25 @@
+<?xml version="1.0"?>
+<tool id="gene_annotation_fetcher_data_manager" name="Gene Annotation Fetch" tool_type="manage_data" version="1.0.0">
+    <description>gene annotation fetcher</description>
+    <stdio>
+        <exit_code description="Error" level="fatal" range="1:" />
+    </stdio>
+    <command interpreter="python">
+    <![CDATA[
+        data_manager.py --out "${out_file}"
+        #if $gene_annotation_url:
+            --url "${gene_annotation_url}"
+        #end if
+        #if $database_name:
+            --name "${database_name}"
+        #end if
+    ]]>
+    </command>
+    <inputs>
+        <param help="Enter a unique identifier, or leave blank for today's date" label="Name for this database" name="database_name" type="text" optional="True" />
+        <param label="Enter URL for gene annotation files" name="gene_annotation_url" type="text" />
+    </inputs>
+    <outputs>
+        <data format="data_manager_json" name="out_file" />
+    </outputs>
+</tool>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/data_manager_gene_annotation/data_manager_conf.xml	Tue Apr 26 13:33:16 2016 -0400
@@ -0,0 +1,15 @@
+<?xml version="1.0"?>
+<data_managers>
+
+	<data_manager tool_file="data_manager/gene_annotation_fetcher.xml" id="gene_annotation_fetcher" version="1.0.0">
+		<data_table name="gene_annotation">
+			<output>
+				<column name="value" />
+				<column name="dbkey" />
+				<column name="name" />
+				<column name="path"/>
+			</output>
+		</data_table>
+	</data_manager>
+
+</data_managers>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/data_manager_gene_annotation/tool_data_table_conf.xml.sample	Tue Apr 26 13:33:16 2016 -0400
@@ -0,0 +1,8 @@
+<?xml version="1.0"?>
+<tables>
+    <!-- Locations of gene annotation data -->
+    <table name="gene_annotation" comment_char="#">
+        <columns>value, dbkey, name, path</columns>
+        <file path="tool-data/gene_annotation.loc" />
+    </table>
+</tables>
\ No newline at end of file