view save_to_db.xml @ 5:f934215bdb78 draft default tip

planemo upload for repository https://github.com/brsynth commit 6ae809b563b40bcdb6be2e74fe2a84ddad5484ae

<tool id="save_to_db" name="Save Data To DB" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="21.09">
    <description>Save data to SQL DB</description>
    <macros>
        <token name="@VERSION_SUFFIX@">2</token>
        <token name="@TOOL_VERSION@">0.2.0</token>
    </macros>
    <requirements>
        <requirement type="package" version="2.2.3">pandas</requirement>
        <requirement type="package" version="2.0.40">sqlalchemy</requirement>
        <requirement type="package" version="2.9.9">psycopg2</requirement>
    </requirements>
    <command detect_errors="exit_code"><![CDATA[
        #set genbank_file_paths = ','.join([str(f) for f in $genbank_files])
        #set $file_name_mapping = ",".join(["%s:%s" % (file.file_name, file.name) for file in $genbank_files])
        python '$__tool_directory__/save_to_db.py'
            --input '$genbank_file_paths' 
            --sequence_column '$sequence_column'
            --annotation_column '$annotation_column'
            --db_uri '$db_uri' 
            --table '$table' 
            --fragment_column '$fragment_column'
            --output '$output'
            --file_name_mapping '$file_name_mapping'
            --json_conf '$json_conf'
    ]]></command>
    <inputs>
        <param name="genbank_files" type="data_collection" collection_type="list" format="genbank" label="GenBank File(s)"/>
        <param name="table" type="text" label="DB Table Name" optional="true" help="It can be extracted from JSON file -key:'JSON_table'-" />
        <param name="sequence_column" type="text" label="DB Column Contains Sequence For ganbank File" optional="true" help="It can be extracted from JSON file -key:'JSON_sequence_column'-" />
        <param name="annotation_column" type="text" label="DB Column Contains Annotation For Ganbank File" optional="true" help="It can be extracted from JSON file -key:'JSON_annotation_column'-" />
        <param name="fragment_column" type="text" label="DB IDs Column Name" optional="true" help="It can be extracted from JSON file -key:'JSON_fragment_column'-" />
        <param name="db_uri" type="text" label="DB Connection URI" help="postgresql+psycopg2://username:password@db_container_name:port/database (It can be extracted from JSON file -key:'JSON_db_uri'-)" optional="true" />
        <section name='adv' title='Advance' expanded='false'>
            <param name="json_conf" type="data" format='json' label="DB config as a json file" help="JSON file specifying the database URI, table name and the column names for annotation and sequence data" optional="true" />
        </section>
    </inputs>   
    <outputs>
        <data name="output" format="txt" label="saving report" />
    </outputs>
    <tests>
    <!--Only 1 test can be execute because the fragment will be already saved for the second test and it will return error as the fragments are present in the DB (execut ../get_db_data/testMock.py to regenerate initial DB)-->
        <!--test tool blocking from JSON -->
        <test> 
            <param name="genbank_files">
                <collection type="list">
                    <element name="p7_L7Ae-Weiss" value="p7_L7Ae-Weiss.gb" />
                    <element name="p7_gfp_sequence" value="p6_Nt-IgKLsequence.gb" />
                    <element name="p14_CMVp" value="p6_Kozak-ATG.gb" />
                    <element name="p16_bGHpolyA" value="p4_Kt-L7Ae-Weiss.gb" />
                    <element name="p18_CMVp" value="HC_Amp_ccdB.gb" />
                </collection>
            </param>
            <param name="adv|json_conf" value="test-JSON_arg_block.json" />
            <output name="output" file="test_raport.txt" ftype="txt" >
                <assert_contents>
                     <has_n_lines n="5" />
                     <has_line_matching expression="p7_L7Ae-Weiss" />
                     <has_line_matching expression="p6_Nt-IgKLsequence" />
                     <has_line_matching expression="p6_Kozak-ATG" />
                     <has_line_matching expression="p4_Kt-L7Ae-Weiss" />
                     <has_line_matching expression="HC_Amp_ccdB" />
                </assert_contents>
            </output>
        </test>
        <!--test DB config in the tool -->
        <test> 
            <param name="genbank_files">
                <collection type="list">
                    <element name="p7_L7Ae-Weiss" value="p7_L7Ae-Weiss.gb" />
                    <element name="p7_gfp_sequence" value="p6_Nt-IgKLsequence.gb" />
                    <element name="p14_CMVp" value="p6_Kozak-ATG.gb" />
                    <element name="p16_bGHpolyA" value="p4_Kt-L7Ae-Weiss.gb" />
                    <element name="p18_CMVp" value="HC_Amp_ccdB.gb" />
                </collection>
            </param>
            <param name="table" value="sample" />
            <param name="sequence_column" value="sequence" />
            <param name="annotation_column" value="annotation" />
            <param name="fragment_column" value="fragment" />
            <param name="db_uri" value="postgresql://postgres:RK17@localhost:5432/test_fragments_db" />
            <output name="output" file="test_raport.txt" ftype="txt" >
                <assert_contents>
                     <has_n_lines n="5" />
                     <has_line_matching expression="p7_L7Ae-Weiss" />
                     <has_line_matching expression="p6_Nt-IgKLsequence" />
                     <has_line_matching expression="p6_Kozak-ATG" />
                     <has_line_matching expression="p4_Kt-L7Ae-Weiss" />
                     <has_line_matching expression="HC_Amp_ccdB" />
                </assert_contents>
            </output>
        </test>
        <!--test DB config from JSON -->
        <test> 
            <param name="genbank_files">
                <collection type="list">
                    <element name="p7_L7Ae-Weiss" value="p7_L7Ae-Weiss.gb" />
                    <element name="p7_gfp_sequence" value="p6_Nt-IgKLsequence.gb" />
                    <element name="p14_CMVp" value="p6_Kozak-ATG.gb" />
                    <element name="p16_bGHpolyA" value="p4_Kt-L7Ae-Weiss.gb" />
                    <element name="p18_CMVp" value="HC_Amp_ccdB.gb" />
                </collection>
            </param>
            <param name="adv|json_conf" value="test-JSON_arg.json" />
            <output name="output" file="test_raport.txt" ftype="txt" >
                <assert_contents>
                     <has_n_lines n="5" />
                     <has_line_matching expression="p7_L7Ae-Weiss" />
                     <has_line_matching expression="p6_Nt-IgKLsequence" />
                     <has_line_matching expression="p6_Kozak-ATG" />
                     <has_line_matching expression="p4_Kt-L7Ae-Weiss" />
                     <has_line_matching expression="HC_Amp_ccdB" />
                </assert_contents>
            </output>
        </test>
    </tests>

    <help><![CDATA[
Save Data To DB
===================

Implemented a system to save GenBank (.gb) files in SQL DB, based on a connection via URI requests.
The tool is tested on a locally hosted PostgreSQL database running in a Docker container.

**Parameters**:
---------------
* **GenBank File(s)**: List of GenBaks files.
* **DB Table Name**: Name of the target table in the PostgreSQL database.
* **DB Column Contains Sequence For ganbank File**: Column storing sequence data, expected to start with "ORIGIN". 
* **DB Column Contains Annotation For Ganbank File**: Column containing annotation data, to save al part before "ORIGIN" in the .gb file.
* **DB IDs Column Name**: Column holding the unique fragment IDs.
* **DB Connection URI**: URI used to connect to the database (e.g., postgresql://user:password@host:port/DB_name).
* **DB config as a json file**: JSON file contains the DB configuration:
    - "JSON_table": will be the key to the table name.
    - "JSON_sequence_column":  will be the key to the sequence column.
    - "JSON_annotation_column":  will be the key to the annotation column.
    - "JSON_fragment_column": will be the key to the fragment column.
    - "JSON_db_uri": will be the key to the URI.
    - "execution": It is the key to execute or block the tool during a workflow ("True" or "False").
* NOTE: the JSON file can be generated using the json_db_config_generating tool. 
    ]]></help>
    <citations>
        <citation type="bibtex">
            @unpublished{save_to_db
                author = {Ramiz Khaled},
                title = {{save_to_db}},
                url = {https://github.com/brsynth/},
            }
        </citation>
    </citations>
</tool>