Mercurial > repos > yating-l > data_manager_fetch_reference_data

changeset 1:5349705442d0 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload
author yating-l
date Wed, 03 May 2017 16:27:19 -0400
parents 099d2508bcc3
children c4737db26737
files data_manager/fetch_reference_data.py data_manager/fetch_reference_data.xml data_manager_conf.xml fetch_reference_data.py fetch_reference_data.xml tool_data_table_conf.xml.sample
diffstat 6 files changed, 99 insertions(+), 91 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/data_manager/fetch_reference_data.py	Wed May 03 16:27:19 2017 -0400
@@ -0,0 +1,75 @@
+#!/usr/bin/env python
+# ref: https://galaxyproject.org/admin/tools/data-managers/how-to/define/
+
+import sys
+import os
+import tempfile
+import shutil
+import argparse
+import urllib2
+import tarfile
+
+from galaxy.util.json import from_json_string, to_json_string
+
+CHUNK_SIZE = 2**20 #1mb
+
+def cleanup_before_exit(tmp_dir):
+    if tmp_dir and os.path.exists(tmp_dir):
+        shutil.rmtree(tmp_dir)
+
+def stop_err(msg):
+    sys.stderr.write(msg)
+    sys.exit(1)
+
+def get_reference_id_name(params):
+    genome_id = params['param_dict']['genome_id']
+    genome_name = params['param_dict']['genome_name']
+    return genome_id, genome_name
+
+def download_from_GlimmerHMM(data_manager_dict, params, target_directory, sequence_id, sequence_name ):
+    GlimmerHMM_DOWNLOAD_URL = 'ftp://ccb.jhu.edu/pub/software/glimmerhmm/GlimmerHMM-3.0.4.tar.gz'
+    GlimmerHMM_TRAINED_DIR = os.path.join('GlimmerHMM', 'trained_dir', sequence_id)
+    with tarfile.open('GlimmerHMM-3.0.4.tar', mode='r:*') as tar:
+        subdir = [
+          tarinfo for tarinfo in tar.getmembers()
+          if sequence_id in tarinfo.name
+        ]
+        tar.extractall(members=subdir)
+    glimmerhmm_trained_target_dir = os.path.join(target_directory, sequence_id)
+    shutil.copytree(GlimmerHMM_TRAINED_DIR, glimmerhmm_trained_target_dir)
+    data_table_entry = dict(value=sequence_id, name=sequence_name, path=glimmerhmm_trained_target_dir)
+    _add_data_table_entry(data_manager_dict, data_table_entry)
+
+    cleanup_before_exit(GlimmerHMM_TRAINED_DIR)
+
+def _add_data_table_entry( data_manager_dict, data_table_entry ):
+    data_manager_dict['data_tables'] = data_manager_dict.get( 'data_tables', {} )
+    data_manager_dict['data_tables']['reference_data'] = data_manager_dict['data_tables'].get('reference_data', [])
+    data_manager_dict['data_tables']['reference_data'].append( data_table_entry )
+    return data_manager_dict
+
+REFERENCE_SOURCE_TO_DOWNLOAD = dict(glimmerhmm=download_from_GlimmerHMM)
+
+def main():
+    #Parse Command Line
+    parser = argparse.ArgumentParser()
+    args = parser.parse_args()
+
+    filename = args[0]
+
+    params = from_json_string(open(filename).read())
+    target_directory = params['output_data'][0]['extra_files_path']
+    os.mkdir(target_directory)
+    data_manager_dict = {}
+
+    sequence_id, sequence_name = get_reference_id_name(params)
+
+    #Fetch the FASTA
+    REFERENCE_SOURCE_TO_DOWNLOAD[params['param_dict']['file_path']](data_manager_dict, params, target_directory, sequence_id, sequence_name)
+
+    #save info to json file
+    open(filename, 'wb').write(to_json_string(data_manager_dict))
+
+if __name__ == "__main__":
+    main()
+
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/data_manager/fetch_reference_data.xml	Wed May 03 16:27:19 2017 -0400
@@ -0,0 +1,15 @@
+<tool id="data_manager_fetch_reference_data" name="Reference data for GlimmerHMM" version="0.0.1" tool_type="manage_data">
+    <description>fetching reference data for GlimmerHMM</description>
+    <command interpreter="python">data_manager_fetch_reference_data.py "${out_file}"</command>
+    <inputs>
+        <param name="genome_id" type="text" label="Id of the reference genome" />
+        <param name="genome_name" type="text" label="Name of the reference genome" />
+        <param name="trained_dir" type="text" value="" label="Directory of the genome file" />
+    </inputs>
+    <outputs>
+        <data name="out_file" format="data_manager_json" />
+    </outputs>
+    <help>
+        Fetch trained data (reference genome) for GlimmerHMM
+    </help>
+</tool>
\ No newline at end of file
--- a/data_manager_conf.xml	Wed May 03 16:18:10 2017 -0400
+++ b/data_manager_conf.xml	Wed May 03 16:27:19 2017 -0400
@@ -1,6 +1,6 @@
 <?xml version="1.0"?>
     <data_managers>
-        <data_manager tool_file="data_manager/fetch_reference_data.xml" id="fetch_reference_data"> 
+        <data_manager tool_file="data_manager/fetch_reference_data.xml" id="data_manager_fetch_reference_data"> 
             <data_table name="glimmer_hmm_trained_dir">
                 <output>
                     <column name="value" />
--- a/fetch_reference_data.py	Wed May 03 16:18:10 2017 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,75 +0,0 @@
-#!/usr/bin/env python
-# ref: https://galaxyproject.org/admin/tools/data-managers/how-to/define/
-
-import sys
-import os
-import tempfile
-import shutil
-import argparse
-import urllib2
-import tarfile
-
-from galaxy.util.json import from_json_string, to_json_string
-
-CHUNK_SIZE = 2**20 #1mb
-
-def cleanup_before_exit(tmp_dir):
-    if tmp_dir and os.path.exists(tmp_dir):
-        shutil.rmtree(tmp_dir)
-
-def stop_err(msg):
-    sys.stderr.write(msg)
-    sys.exit(1)
-
-def get_reference_id_name(params):
-    genome_id = params['param_dict']['genome_id']
-    genome_name = params['param_dict']['genome_name']
-    return genome_id, genome_name
-
-def download_from_GlimmerHMM(data_manager_dict, params, target_directory, sequence_id, sequence_name ):
-    GlimmerHMM_DOWNLOAD_URL = 'ftp://ccb.jhu.edu/pub/software/glimmerhmm/GlimmerHMM-3.0.4.tar.gz'
-    GlimmerHMM_TRAINED_DIR = os.path.join('GlimmerHMM', 'trained_dir', sequence_id)
-    with tarfile.open('GlimmerHMM-3.0.4.tar', mode='r:*') as tar:
-        subdir = [
-          tarinfo for tarinfo in tar.getmembers()
-          if sequence_id in tarinfo.name
-        ]
-        tar.extractall(members=subdir)
-    glimmerhmm_trained_target_dir = os.path.join(target_directory, sequence_id)
-    shutil.copytree(GlimmerHMM_TRAINED_DIR, glimmerhmm_trained_target_dir)
-    data_table_entry = dict(value=sequence_id, name=sequence_name, path=glimmerhmm_trained_target_dir)
-    _add_data_table_entry(data_manager_dict, data_table_entry)
-
-    cleanup_before_exit(GlimmerHMM_TRAINED_DIR)
-
-def _add_data_table_entry( data_manager_dict, data_table_entry ):
-    data_manager_dict['data_tables'] = data_manager_dict.get( 'data_tables', {} )
-    data_manager_dict['data_tables']['reference_data'] = data_manager_dict['data_tables'].get('reference_data', [])
-    data_manager_dict['data_tables']['reference_data'].append( data_table_entry )
-    return data_manager_dict
-
-REFERENCE_SOURCE_TO_DOWNLOAD = dict(glimmerhmm=download_from_GlimmerHMM)
-
-def main():
-    #Parse Command Line
-    parser = argparse.ArgumentParser()
-    args = parser.parse_args()
-
-    filename = args[0]
-
-    params = from_json_string(open(filename).read())
-    target_directory = params['output_data'][0]['extra_files_path']
-    os.mkdir(target_directory)
-    data_manager_dict = {}
-
-    sequence_id, sequence_name = get_reference_id_name(params)
-
-    #Fetch the FASTA
-    REFERENCE_SOURCE_TO_DOWNLOAD[params['param_dict']['file_path']](data_manager_dict, params, target_directory, sequence_id, sequence_name)
-
-    #save info to json file
-    open(filename, 'wb').write(to_json_string(data_manager_dict))
-
-if __name__ == "__main__":
-    main()
-
--- a/fetch_reference_data.xml	Wed May 03 16:18:10 2017 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,15 +0,0 @@
-<tool id="data_manager_fetch_reference_data" name="Reference data for GlimmerHMM" version="0.0.1" tool_type="manage_data">
-    <description>fetching reference data for GlimmerHMM</description>
-    <command interpreter="python">data_manager_fetch_reference_data.py "${out_file}"</command>
-    <inputs>
-        <param name="genome_id" type="text" label="Id of the reference genome" />
-        <param name="genome_name" type="text" label="Name of the reference genome" />
-        <param name="trained_dir" type="text" value="" label="Directory of the genome file" />
-    </inputs>
-    <outputs>
-        <data name="out_file" format="data_manager_json" />
-    </outputs>
-    <help>
-        Fetch trained data (reference genome) for GlimmerHMM
-    </help>
-</tool>
\ No newline at end of file
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_data_table_conf.xml.sample	Wed May 03 16:27:19 2017 -0400
@@ -0,0 +1,8 @@
+<!-- Use the file tool_data_table_conf.xml.oldlocstyle if you don't want to update your loc files as changed in revision 4550:535d276c92bc-->
+<tables>
+    <!-- glimmer_hmm trained_dir -->
+    <table name="glimmer_hmm_trained_dir" comment_char="#">
+        <columns>value, name, path</columns>
+        <file path="tool-data/glimmer_hmm.loc" />
+    </table>
+</tables>