Mercurial > repos > iuc > data_manager_fetch_gene_annotation
changeset 0:6b2ba2f88c2e draft default tip
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/data_managers/data_manager_fetch_gene_annotation/ commit 8652f36a3a3838dca989426961561e81432acf4f
| author | iuc |
|---|---|
| date | Tue, 04 Apr 2017 17:50:05 -0400 |
| parents | |
| children | |
| files | data_manager/data_manager.py data_manager/gene_annotation_fetcher.xml data_manager_conf.xml tool-data/gene_annotation.loc.sample tool_data_table_conf.xml.sample |
| diffstat | 4 files changed, 131 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/data_manager/data_manager.py Tue Apr 04 17:50:05 2017 -0400 @@ -0,0 +1,74 @@ +import argparse +import datetime +import json +import os +import sys +import uuid + +import requests +from requests.exceptions import ContentDecodingError + + +def url_download(url): + """Attempt to download gene annotation file from a given url + :param url: full url to gene annotation file + :type url: str. + :returns: name of downloaded gene annotation file + :raises: ContentDecodingError, IOError + """ + response = requests.get(url=url, stream=True) + + # Generate file_name + file_name = response.url.split("/")[-1] + + block_size = 10 * 1024 * 1024 # 10MB chunked download + with open(file_name, 'w+') as f: + try: + # Good to note here that requests' iter_content() will + # automatically handle decoding "gzip" and "deflate" encoding + # formats + for buf in response.iter_content(block_size): + f.write(buf) + except (ContentDecodingError, IOError) as e: + sys.stderr.write("Error occured downloading reference file: %s" + % e) + os.remove(file_name) + + return file_name + + +def main(): + 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=uuid.uuid4(), help='Data table entry unique ID' + ) + parser.add_argument('--url', dest='url', action='store', + help='Url to download gtf file from') + + args = parser.parse_args() + + work_dir = os.getcwd() + + # Attempt to download gene annotation file from given url + gene_annotation_file_name = url_download(args.url) + + # Update Data Manager JSON and write to file + data_manager_entry = { + 'data_tables': { + 'gff_gene_annotations': { + 'value': str(datetime.datetime.now()), + 'dbkey': str(args.name), + 'name': gene_annotation_file_name, + 'path': os.path.join(work_dir, gene_annotation_file_name) + } + } + } + + with open(os.path.join(args.output), "w+") as f: + f.write(json.dumps(data_manager_entry)) + + +if __name__ == '__main__': + main()
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/data_manager/gene_annotation_fetcher.xml Tue Apr 04 17:50:05 2017 -0400 @@ -0,0 +1,27 @@ +<?xml version="1.0"?> +<tool id="gene_annotation_fetcher_data_manager" name="Gene Annotation Fetch" tool_type="manage_data" version="1.0.1"> + <description>gene annotation fetcher</description> + <requirements> + <requirement type="package" version="2.13.0">requests</requirement> + </requirements> + <command detect_errors="exit_code"> + <![CDATA[ + python '$__tool_directory__/data_manager.py' --out '${out_file}' + #if $gene_annotation_url: + --url '${gene_annotation_url}' + #end if + #if $database_name: + --name '${database_name}' + #end if + ]]> + </command> + <inputs> + <param name="database_name" type="text" optional="true" label="Name for this database" help="Enter a unique identifier, or leave blank for today's date" /> + <param name="gene_annotation_url" type="text" label="Enter URL for gene annotation files" /> + </inputs> + <outputs> + <data format="data_manager_json" name="out_file" /> + </outputs> + <help> + </help> +</tool>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/data_manager_conf.xml Tue Apr 04 17:50:05 2017 -0400 @@ -0,0 +1,22 @@ +<?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="gff_gene_annotations"> + <output> + <column name="value" /> + <column name="dbkey" /> + <column name="name" /> + <column name="path" output_ref="out_file" > + <move type="file"> + <source>${path}</source> + <target base="${GALAXY_DATA_MANAGER_DATA_PATH}">${dbkey}/seq/${path}</target> + </move> + <value_translation>${GALAXY_DATA_MANAGER_DATA_PATH}/${dbkey}/seq/${path}</value_translation> + <value_translation type="function">abspath</value_translation> + </column> + </output> + </data_table> + </data_manager> + +</data_managers>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool_data_table_conf.xml.sample Tue Apr 04 17:50:05 2017 -0400 @@ -0,0 +1,8 @@ +<?xml version="1.0"?> +<tables> + <!-- Locations of gene annotation data --> + <table name="gff_gene_annotations" comment_char="#"> + <columns>value, name, path</columns> + <file path="tool-data/gene_annotation.loc" /> + </table> +</tables> \ No newline at end of file
