changeset 13:c3cdca7f40a2 draft default tip

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/data_managers/data_manager_snpeff commit 225ce35e1c3514cdba7a3637eba9aee964fa85f7

--- a/data_manager/data_manager_snpEff_databases.py	Tue Mar 10 10:12:26 2026 +0000
+++ b/data_manager/data_manager_snpEff_databases.py	Fri Mar 13 13:07:48 2026 +0000
@@ -2,10 +2,24 @@
 import json
 import optparse
 import os
+import re
 import subprocess
 import sys
 
 
+def getSnpeffVersion():
+    snpeff_version = 'SnpEff ?.?'
+    args = ['snpEff', '-version']
+    try:
+        version_output = subprocess.check_output(args, shell=False).decode()
+    except subprocess.CalledProcessError as e:
+        sys.exit(e.returncode)
+    m = re.match(r'^(SnpEff)\s*(\d+\.\d+).*$', version_output)
+    if m:
+        snpeff_version = m.groups()[0] + m.groups()[1]
+    return snpeff_version
+
+
 def fetch_databases(data_manager_dict, target_directory):
     if not os.path.exists(target_directory):
         os.makedirs(target_directory)
@@ -18,6 +32,8 @@
     data_manager_dict['data_tables'] = data_manager_dict.get('data_tables', {})
     data_manager_dict['data_tables']['snpeffv_databases'] = data_manager_dict['data_tables'].get('snpeffv_databases', [])
     data_table_entries = []
+    snpeff_version = getSnpeffVersion()
+
     with open(databases_path, 'r') as fh:
         for line in fh:
             fields = line.split('\t')
@@ -29,7 +45,7 @@
                 if genome_version == '30c2c903' or fields[1].strip() == 'TestCase' or fields[1].strip().startswith('Test_'):
                     continue
                 description = fields[1].strip() + ' : ' + genome_version
-                data_table_entries.append(dict(value=genome_version, name=description))
+                data_table_entries.append(dict(key=snpeff_version + '_' + genome_version, version=snpeff_version, value=genome_version, name=description))
     data_manager_dict['data_tables']['snpeffv_databases'] = data_table_entries
     return data_manager_dict
 

--- a/data_manager/data_manager_snpEff_databases.xml	Tue Mar 10 10:12:26 2026 +0000
+++ b/data_manager/data_manager_snpEff_databases.xml	Fri Mar 13 13:07:48 2026 +0000
@@ -16,7 +16,7 @@
             <output name="out_file">
                 <assert_contents>
                     <!-- Check that a genome was added -->
-                    <has_text text="GRCh38.86" />
+                    <has_text text="ebola_zaire" />
                 </assert_contents>
             </output>
         </test>

--- a/data_manager/data_manager_snpEff_download.py	Tue Mar 10 10:12:26 2026 +0000
+++ b/data_manager/data_manager_snpEff_download.py	Fri Mar 13 13:07:48 2026 +0000
@@ -47,18 +47,14 @@
 
 def getSnpeffVersion():
     snpeff_version = 'SnpEff ?.?'
-    stderr_path = 'snpeff.err'
-    args = ['snpEff', '-h']
-    with open(stderr_path, 'w') as stderr_fh:
-        return_code = subprocess.call(args=args, shell=False, stderr=stderr_fh.fileno())
-    if return_code != 255:
-        sys.exit(return_code)
-    with open(stderr_path) as fh:
-        for line in fh:
-            m = re.match(r'^[Ss]npEff version (SnpEff)\s*(\d+\.\d+).*$', line)
-            if m:
-                snpeff_version = m.groups()[0] + m.groups()[1]
-                break
+    args = ['snpEff', '-version']
+    try:
+        version_output = subprocess.check_output(args, shell=False).decode()
+    except subprocess.CalledProcessError as e:
+        sys.exit(e.returncode)
+    m = re.match(r'^(SnpEff)\s*(\d+\.\d+).*$', version_output)
+    if m:
+        snpeff_version = m.groups()[0] + m.groups()[1]
     return snpeff_version
 
 
@@ -101,34 +97,40 @@
     genome_path = os.path.join(data_dir, genome_version)
     snpeff_version = getSnpeffVersion()
     key = snpeff_version + '_' + genome_version
+    db_version = None
+    genomedb_name = regulationdb_name = ""
+
     if os.path.isdir(genome_path):
         for dirpath, _, files in os.walk(genome_path):
             for fname in files:
                 if fname.startswith('snpEffectPredictor'):
                     # if snpEffectPredictor.bin download succeeded
-                    name = genome_version + (' : ' + organism if organism else '')
-                    data_table_entry = dict(
-                        key=key,
-                        version=getSnpeffDbVersion(os.path.join(dirpath, fname)) or snpeff_version,
-                        value=genome_version,
-                        name=name,
-                        path=data_dir
-                    )
-                    _add_data_table_entry(data_manager_dict, 'snpeffv_genomedb', data_table_entry)
+                    genomedb_name = genome_version + (' : ' + organism if organism else '')
+                    db_version = getSnpeffDbVersion(os.path.join(dirpath, fname)) or snpeff_version
                 else:
                     m = re.match(regulation_pattern, fname)
                     if m:
-                        name = m.groups()[0]
-                        data_table_entry = dict(key=key, version=snpeff_version, genome=genome_version, value=name, name=name)
-                        _add_data_table_entry(data_manager_dict, 'snpeffv_regulationdb', data_table_entry)
-    return data_manager_dict
-
+                        regulationdb_name = m.groups()[0]
 
-def _add_data_table_entry(data_manager_dict, data_table, data_table_entry):
-    data_manager_dict['data_tables'] = data_manager_dict.get('data_tables', {})
-    data_manager_dict['data_tables'][data_table] = data_manager_dict['data_tables'].get(data_table, [])
-    data_manager_dict['data_tables'][data_table].append(data_table_entry)
-    return data_manager_dict
+        if db_version:
+            data_table_entry = dict(
+                key=key,
+                version=db_version,
+                value=genome_version,
+                name=genomedb_name,
+                path=f"snpEff/{db_version}/data"
+            )
+            data_manager_dict['data_tables']['snpeffv_genomedb'].append(data_table_entry)
+
+        if regulationdb_name:
+            data_table_entry = dict(
+                key=key,
+                version=db_version or snpeff_version,
+                genome=genome_version,
+                value=regulationdb_name,
+                name=regulationdb_name
+            )
+            data_manager_dict['data_tables']['snpeffv_regulationdb'].append(data_table_entry)
 
 
 def main():
@@ -143,7 +145,12 @@
         params = json.load(fh)
     target_directory = params['output_data'][0]['extra_files_path']
     os.mkdir(target_directory)
-    data_manager_dict = {}
+    data_manager_dict = {
+        'data_tables': {
+            'snpeffv_genomedb': [],
+            'snpeffv_regulationdb': []
+        }
+    }
 
     # Create SnpEff Reference Data
     for genome_version, organism in zip(options.genome_version.split(','), getOrganismNames(options.genome_version, options.organism).split(',')):

--- a/data_manager_conf.xml	Tue Mar 10 10:12:26 2026 +0000
+++ b/data_manager_conf.xml	Fri Mar 13 13:07:48 2026 +0000
@@ -19,9 +19,9 @@
         <column name="name" />  <!-- columns that are going to be specified by the Data Manager Tool -->
         <column name="path" output_ref="out_file" >
           <move type="directory" relativize_symlinks="True">
-            <target base="${GALAXY_DATA_MANAGER_DATA_PATH}">snpEff/v4_3/data</target>
+            <target base="${GALAXY_DATA_MANAGER_DATA_PATH}">${path}</target>
           </move>
-          <value_translation>${GALAXY_DATA_MANAGER_DATA_PATH}/snpEff/v4_3/data</value_translation>
+          <value_translation>${GALAXY_DATA_MANAGER_DATA_PATH}/${path}</value_translation>
           <value_translation type="function">abspath</value_translation>
         </column>
       </output>