Mercurial > repos > matthias > data_manager_dada2

changeset 9:facf9e6c872c draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/bernt-matthias/mb-galaxy-tools/tree/master/data_managers/data_manager_dada2 commit df2dfeb75f88b326f567cab8df4e6c4a7f2e548c
author matthias
date Tue, 15 Oct 2019 07:20:59 -0400
parents da93e6a3fe23
children
files data_manager/.data_manager.py.swp data_manager/data_manager.py
diffstat 2 files changed, 25 insertions(+), 26 deletions(-) [+]
line wrap: on
line diff
Binary file data_manager/.data_manager.py.swp has changed
--- a/data_manager/data_manager.py	Wed Jun 19 08:15:26 2019 -0400
+++ b/data_manager/data_manager.py	Tue Oct 15 07:20:59 2019 -0400
@@ -1,9 +1,6 @@
 import argparse
 import json
 import os
-import shutil
-import sys
-import zipfile
 try:
     # For Python 3.0 and later
     from urllib.request import Request, urlopen
@@ -11,14 +8,14 @@
     # Fall back to Python 2 imports
     from urllib2 import Request, urlopen
 
-DEFAULT_TAXLEVELS="Kingdom,Phylum,Class,Order,Family,Genus,Species"
+DEFAULT_TAXLEVELS = "Kingdom,Phylum,Class,Order,Family,Genus,Species"
 
 FILE2NAME = {
-    "silva_132":"Silva version 132",
-    "silva_128":"Silva version 128",
-    "rdp_16":"RDP trainset 16",
-    "rdp_14":"RDP trainset 14",
-    "greengenes_13.84":"GreenGenes version 13.84",
+    "silva_132": "Silva version 132",
+    "silva_128": "Silva version 128",
+    "rdp_16": "RDP trainset 16",
+    "rdp_14": "RDP trainset 14",
+    "greengenes_13.84": "GreenGenes version 13.84",
     "unite_8.0_fungi": "UNITE: General Fasta release 8.0 for Fungi",
     "unite_8.0_fungi_singletons": "UNITE: General Fasta release 8.0 for Fungi including global and 97% singletons",
     "RefSeq_RDP_2018_05": "NCBI RefSeq 16S rRNA database supplemented by RDP (05/2018)",
@@ -29,13 +26,13 @@
 }
 
 FILE2TAXURL = {
-    "silva_132":"https://zenodo.org/record/1172783/files/silva_nr_v132_train_set.fa.gz?download=1",
-    "silva_128":"https://zenodo.org/record/824551/files/silva_nr_v128_train_set.fa.gz?download=1",
-    "rdp_16":"https://zenodo.org/record/801828/files/rdp_train_set_16.fa.gz?download=1",
-    "rdp_14":"https://zenodo.org/record/158955/files/rdp_train_set_14.fa.gz?download=1",
+    "silva_132": "https://zenodo.org/record/1172783/files/silva_nr_v132_train_set.fa.gz?download=1",
+    "silva_128": "https://zenodo.org/record/824551/files/silva_nr_v128_train_set.fa.gz?download=1",
+    "rdp_16": "https://zenodo.org/record/801828/files/rdp_train_set_16.fa.gz?download=1",
+    "rdp_14": "https://zenodo.org/record/158955/files/rdp_train_set_14.fa.gz?download=1",
     "unite_8.0_fungi": "https://files.plutof.ut.ee/public/orig/EB/0C/EB0CCB3A871B77EA75E472D13926271076904A588D2E1C1EA5AFCF7397D48378.zip",
     "unite_8.0_fungi_singletons": "https://files.plutof.ut.ee/doi/06/A2/06A2C86256EED64085670EB0C54B7115F6DAC8F311C656A9CB33E386CFABA0D0.zip",
-    "greengenes_13.84":"https://zenodo.org/record/158955/files/gg_13_8_train_set_97.fa.gz?download=1",
+    "greengenes_13.84": "https://zenodo.org/record/158955/files/gg_13_8_train_set_97.fa.gz?download=1",
     "RefSeq_RDP_2018_05": "https://zenodo.org/record/2541239/files/RefSeq-RDP16S_v2_May2018.fa.gz?download=1",
     "gtdb_2018_11": "https://zenodo.org/record/2541239/files/GTDB_bac-arc_ssu_r86.fa.gz?download=1",
     "hitdb_1": "https://zenodo.org/record/159205/files/hitdb_v1.00.fa.gz?download=1",
@@ -44,16 +41,17 @@
 }
 
 FILE2SPECIESURL = {
-    "silva_132":"https://zenodo.org/record/1172783/files/silva_species_assignment_v132.fa.gz?download=1",
-    "silva_128":"https://zenodo.org/record/824551/files/silva_species_assignment_v128.fa.gz?download=1",
-    "rdp_16":"https://zenodo.org/record/801828/files/rdp_species_assignment_16.fa.gz?download=1",
-    "rdp_14":"https://zenodo.org/record/158955/files/rdp_species_assignment_14.fa.gz?download=1"
+    "silva_132": "https://zenodo.org/record/1172783/files/silva_species_assignment_v132.fa.gz?download=1",
+    "silva_128": "https://zenodo.org/record/824551/files/silva_species_assignment_v128.fa.gz?download=1",
+    "rdp_16": "https://zenodo.org/record/801828/files/rdp_species_assignment_16.fa.gz?download=1",
+    "rdp_14": "https://zenodo.org/record/158955/files/rdp_species_assignment_14.fa.gz?download=1"
 }
 
 FILE2TAXLEVELS = {
     "PR2_4.11.1": "Kingdom,Supergroup,Division,Class,Order,Family,Genus,Species"
 }
 
+
 def url_download(url, fname, workdir):
     """
     download url to workdir/fname
@@ -77,7 +75,7 @@
         if src:
             src.close()
 
-    #special treatment of UNITE DBs: they are zip files containing two fasta (xyz.fasta and developer/xyz.fasta)
+#   special treatment of UNITE DBs: they are zip files containing two fasta (xyz.fasta and developer/xyz.fasta)
     if fname.startswith("unite"):
         import glob
         import gzip
@@ -88,9 +86,9 @@
         zip_ref.extractall(workdir)
         zip_ref.close()
         # gzip top level fasta file
-        fastas = glob.glob("%s/*fasta"%workdir)
+        fastas = glob.glob("%s/*fasta" % workdir)
         if len(fastas) != 1:
-            msg = "UNITE download %s contained %d fasta file(s): %s"%(url, len(fastas), " ".join(fastas))
+            msg = "UNITE download %s contained %d fasta file(s): %s" % (url, len(fastas), " ".join(fastas))
             raise Exception(msg)
         with open(fastas[0], 'rb') as f_in:
             with gzip.open(file_path, 'wb') as f_out:
@@ -104,27 +102,28 @@
 
     workdir = params['output_data'][0]['extra_files_path']
     os.mkdir(workdir)
-    url_download( FILE2TAXURL[dataset], dataset+".taxonomy", workdir)
+    url_download( FILE2TAXURL[dataset], dataset + ".taxonomy", workdir)
 
-    data_manager_json = {"data_tables":{}}
+    data_manager_json = {"data_tables": {}}
     data_manager_entry = {}
     data_manager_entry['value'] = dataset
     data_manager_entry['name'] = FILE2NAME[dataset]
-    data_manager_entry['path'] = dataset+".taxonomy"
+    data_manager_entry['path'] = dataset + ".taxonomy"
     data_manager_entry['taxlevels'] = FILE2TAXLEVELS.get(dataset, DEFAULT_TAXLEVELS)
     data_manager_json["data_tables"]["dada2_taxonomy"] = data_manager_entry
 
     if FILE2SPECIESURL.get(dataset, False ):
-        url_download( FILE2SPECIESURL[dataset], dataset+".species", workdir)
+        url_download( FILE2SPECIESURL[dataset], dataset + ".species", workdir)
         data_manager_entry = {}
         data_manager_entry['value'] = dataset
         data_manager_entry['name'] = FILE2NAME[dataset]
-        data_manager_entry['path'] = dataset+".species"
+        data_manager_entry['path'] = dataset + ".species"
         data_manager_json["data_tables"]["dada2_species"] = data_manager_entry
 
     with file(outjson, 'w') as jf:
         jf.write(json.dumps(data_manager_json))
 
+
 if __name__ == '__main__':
     parser = argparse.ArgumentParser(description='Create data manager json.')
     parser.add_argument('--out', action='store', help='JSON filename')