Repository 'data_manager_fetch_ncbi_taxonomy'
hg clone https://toolshed.g2.bx.psu.edu/repos/devteam/data_manager_fetch_ncbi_taxonomy

Changeset 0:fafcd2f5db36 (2015-10-08)
Next changeset 1:926847693e4d (2017-04-04)
Commit message:
planemo upload for repository https://github.com/galaxyproject/tools-devteam/blob/master/data_managers/data_manager_fetch_ncbi_taxonomy/ commit 220e70acb66016873732b193b3ac20ae48083f0b-dirty
added:
data_manager/data_manager.py
data_manager/ncbi_taxonomy_fetcher.xml
data_manager_conf.xml
tool-data/ncbi_taxonomy.loc.sample
tool_data_table_conf.xml.sample
b
diff -r 000000000000 -r fafcd2f5db36 data_manager/data_manager.py
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/data_manager/data_manager.py Thu Oct 08 12:14:42 2015 -0400
[
@@ -0,0 +1,68 @@
+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', default='ftp://ftp.ncbi.nih.gov/pub/taxonomy/taxdump.tar.gz', help='Download URL')
+
+args = parser.parse_args()
+
+def url_download(url, workdir):
+    file_path = os.path.join(workdir, 'download.dat')
+    if not os.path.exists(workdir):
+        os.makedirs(workdir)
+    src = None
+    dst = None
+    try:
+        req = urllib2.Request(url)
+        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, e:
+        print >>sys.stderr, str(e)
+    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(), 'taxonomy')
+    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'] = '.'
+    data_manager_json = dict(data_tables=dict(ncbi_taxonomy=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(), 'taxonomy'))
+    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)
b
diff -r 000000000000 -r fafcd2f5db36 data_manager/ncbi_taxonomy_fetcher.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/data_manager/ncbi_taxonomy_fetcher.xml Thu Oct 08 12:14:42 2015 -0400
[
@@ -0,0 +1,25 @@
+<?xml version="1.0"?>
+<tool id="ncbi_taxonomy_fetcher" name="NCBI" tool_type="manage_data" version="1.0.0">
+    <description>taxonomy downloader</description>
+    <stdio>
+        <exit_code description="Error" level="fatal" range="1:" />
+    </stdio>
+    <command interpreter="python">
+    <![CDATA[
+        data_manager.py --out "${out_file}"
+        #if $taxonomy_url:
+            --url "${taxonomy_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 taxonomy files" name="taxonomy_url" type="text" />
+    </inputs>
+    <outputs>
+        <data format="data_manager_json" name="out_file" />
+    </outputs>
+</tool>
b
diff -r 000000000000 -r fafcd2f5db36 data_manager_conf.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/data_manager_conf.xml Thu Oct 08 12:14:42 2015 -0400
b
@@ -0,0 +1,18 @@
+<?xml version="1.0"?>
+<data_managers>
+    <data_manager tool_file="data_manager/ncbi_taxonomy_fetcher.xml" id="ncbi_taxonomy_fetcher" version="1.0.0">
+        <data_table name="ncbi_taxonomy">
+            <output>
+                <column name="value" />
+                <column name="name" />
+                <column name="path" output_ref="out_file">
+                    <move type="directory" relativize_symlinks="True">
+                        <target base="${GALAXY_DATA_MANAGER_DATA_PATH}">ncbi_taxonomy/${value}</target>
+                    </move>
+                    <value_translation>${GALAXY_DATA_MANAGER_DATA_PATH}/ncbi_taxonomy/${value}</value_translation>
+                    <value_translation type="function">abspath</value_translation>
+                </column>
+            </output>
+        </data_table>
+    </data_manager>
+</data_managers>
b
diff -r 000000000000 -r fafcd2f5db36 tool_data_table_conf.xml.sample
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_data_table_conf.xml.sample Thu Oct 08 12:14:42 2015 -0400
b
@@ -0,0 +1,8 @@
+<?xml version="1.0"?>
+<tables>
+    <!-- Locations of taxonomy data downloaded from NCBI -->
+    <table name="ncbi_taxonomy" comment_char="#">
+        <columns>value, name, path</columns>
+        <file path="tool-data/ncbi_taxonomy.loc" />
+    </table>
+</tables>