view query_tabular.xml @ 23:5bb148ee644a draft default tip

Deleted selected files
author jjohnson
date Mon, 17 Jul 2017 15:22:38 -0400
parents bed5018e7ae3
children
line wrap: on
line source

<tool id="query_tabular" name="Query Tabular" version="5.0.0">
    <description>using sqlite sql</description>

    <macros>
         <import>macros.xml</import>
    </macros>

    <requirements>
    </requirements>

    <command detect_errors="exit_code"><![CDATA[
        cat '$query_file' &&
        #if $add_to_database.withdb: 
            #if $save_db:
                cp '$add_to_database.withdb' '$sqlitedb' &&
            #else:
                cp '$add_to_database.withdb' '$workdb' &&
            #end if 
        #end if
        python '$__tool_directory__/query_tabular.py'
        #if $save_db
        -s '$sqlitedb'
        #else
        -s '$workdb'
        #end if
        -j '$table_json'
        #if $sqlquery:
          -Q '$query_file' 
          $no_header
          -o '$output'
        #end if
    ]]></command>
    <configfiles>
        <configfile name="query_file">
$sqlquery
        </configfile>
        <configfile name="table_json">
#import json
#set $jtbldef = dict()
#set $jtbls = []
#set $jtbldef['tables'] = $jtbls
#for $i,$tbl in enumerate($tables):
  #set $jtbl = dict()
  #set $jtbl['file_path'] = str($tbl.table)
  #if $tbl.tbl_opts.table_name:
  #set $tname = str($tbl.tbl_opts.table_name)
  #else
  #set $tname = 't' + str($i + 1) 
  #end if
  #set $jtbl['table_name'] = $tname
  ## #if $tbl.tbl_opts.sel_cols:
  ##   #set $jtbl['sel_cols'] = $tbl.tbl_opts.sel_cols el_cols
  ## #end if
  #if $tbl.tbl_opts.pkey_autoincr:
    #set $jtbl['pkey_autoincr'] = str($tbl.tbl_opts.pkey_autoincr)
  #end if
  #if $tbl.tbl_opts.col_names:
  #set $col_names = str($tbl.tbl_opts.col_names)
    #if $tbl.tbl_opts.load_named_columns:
      #set $jtbl['load_named_columns'] = True
    #end if
  #else 
  #set $col_names = ''
  #end if
  #set $jtbl['column_names'] = $col_names
  #set $idx_unique = []
  #set $idx_non = []
  #for $idx in $tbl.tbl_opts.indexes:
    #if $idx.unique:
      #silent $idx_unique.append(str($idx.index_columns))
    #else:
      #silent $idx_non.append(str($idx.index_columns))
    #end if
  #end for
  #if len($idx_unique) > 0:
    #set $jtbl['unique'] = $idx_unique
  #end if
  #if len($idx_non) > 0:
    #set $jtbl['index'] = $idx_non
  #end if
  #set $linefilters = $tbl.input_opts.linefilters
  @LINEFILTERS@
  #if $input_filters:
    #set $jtbl['filters'] = $input_filters
  #end if
  #set $jtbls += [$jtbl]
#end for
#echo $json.dumps($jtbldef)
        </configfile>
    </configfiles>
    <inputs>
        <param name="workdb" type="hidden" value="workdb.sqlite" label=""/>
        <section name="add_to_database" expanded="false" title="Add tables to an existing database">
            <param name="withdb" type="data" format="sqlite" optional="true" label="Add tables to this Database" 
               help="Make sure your added table names are not already in this database"/>
        </section>
        <repeat name="tables" title="Database Table" min="0">
            <param name="table" type="data" format="tabular" label="Tabular Dataset for Table"/>
            <section name="input_opts" expanded="false" title="Filter Dataset Input">
                <expand macro="macro_line_filters" />
            </section>
            <section name="tbl_opts" expanded="false" title="Table Options">
                <param name="table_name" type="text" value="" optional="true" label="Specify Name for Table">
                    <help>By default, tables will be named: t1,t2,...,tn (table names must be unique)</help>
                    <validator type="regex" message="Table name should start with a letter and may contain additional letters, digits, and underscores">^[A-Za-z]\w*$</validator>
                </param>
                <param name="col_names" type="text" value="" optional="true" label="Specify Column Names (comma-separated list)">
                    <help>By default, table columns will be named: c1,c2,c3,...,cn  (column names for a table must be unique)
                          You can override the default names by entering a comma -separated list of names, e.g. ',name1,,,name2' would rename the second and fifth columns.
                    </help>
                    <sanitizer sanitize="False"/>
                    <validator type="regex" message="A List of names separated by commas: Column names should start with a letter and may contain additional letters, digits, and underscores. Otherwise, the name must be eclosed in: double quotes, back quotes, or square brackets.">^([A-Za-z]\w*|"\S+[^,"]*"|`\S+[^,`]*`|[[]\S+[^,"]*[]])?(,([A-Za-z]\w*|"\S+.*"|`\S+[^,`]*`|[[]\S+[^,"]*[]])?)*$</validator>
                </param>
                <param name="load_named_columns" type="boolean" truevalue="load_named_columns" falsevalue="" checked="false" label="Only load the columns you have named into database"/>
                <param name="pkey_autoincr" type="text" value="" optional="true" label="Add an auto increment primary key column with this name"
                       help="Only creates this additional column when a name is entered. (This can not be the same name as any of the other columns in this table.)">
                        <validator type="regex" message="Column name">^([A-Za-z]\w*)?$</validator>
                </param>
                <repeat name="indexes" title="Table Index">
                    <param name="unique" type="boolean" truevalue="yes" falsevalue="no" checked="False" label="This is a unique index"/>
                    <param name="index_columns" type="text" value="" label="Index on Columns">
                        <help>Create an index on the column names: e,g, c1  or c2,c4</help>
                        <validator type="regex" message="Column name, separated by commes if more than one">^([A-Za-z]\w*|"\S+[^,"]*"|`\S+[^,`]*`|[[]\S+[^,"]*[]])(,([A-Za-z]\w*|"\S+.*"|`\S+[^,`]*`|[[]\S+[^,"]*[]])?)*$</validator>
                    </param>
                </repeat>
            </section>
        </repeat>
        <param name="save_db" type="boolean" truevalue="yes" falsevalue="no" checked="false" label="Save the sqlite database in your history"
            help="SQLite to tabular tool can run additional queries on this database"/>
        <param name="sqlquery" type="text" area="true" size="20x80" value="" optional="true" label="SQL Query to generate tabular output">
                <help>By default: tables are named: t1,t2,...,tn and columns in each table: c1,c2,...,cn</help>
                <sanitizer sanitize="False"/>
                <validator type="regex" message="">^(?ims)\s*select\s+.*\s+from\s+.*$</validator>
        </param>
        <param name="no_header" type="boolean" truevalue="-n" falsevalue="" checked="False" label="Omit column headers from tabular output"/>
    </inputs>
    <outputs>
        <data format="sqlite" name="sqlitedb" label="sqlite db of ${on_string}">
            <filter>save_db</filter>
        </data>
        <data format="tabular" name="output" label="query results on ${on_string}">
            <filter>not save_db or (sqlquery and len(sqlquery.strip()) > 0)</filter>
        </data>
    </outputs>
    <tests>
        <test>
            <repeat name="tables">
                <param name="table" ftype="tabular" value="customers.tsv"/>
                <section name="input_opts">
                    <repeat name="linefilters">
                        <conditional name="filter">
                            <param name="filter_type" value="comment"/>
                            <param name="comment_char" value="35"/>
                        </conditional>
                    </repeat>
                </section>
                <section name="tbl_opts">
                    <param name="table_name" value="customers"/>
                    <param name="col_names" value="CustomerID,FirstName,LastName,Email,DOB,Phone"/>
                </section>
            </repeat>
            <repeat name="tables">
                <param name="table" ftype="tabular" value="sales.tsv"/>
                <section name="input_opts">
                    <repeat name="linefilters">
                        <conditional name="filter">
                            <param name="filter_type" value="comment"/>
                            <param name="comment_char" value="35"/>
                        </conditional>
                    </repeat>
                </section>
                <section name="tbl_opts">
                    <param name="table_name" value="sales"/>
                    <param name="col_names" value="CustomerID,Date,SaleAmount"/>
                </section>
            </repeat>
            <param name="sqlquery" value="SELECT FirstName,LastName,sum(SaleAmount) as &quot;TotalSales&quot; FROM customers join sales on customers.CustomerID = sales.CustomerID GROUP BY customers.CustomerID ORDER BY TotalSales DESC"/>
            <output name="output" file="sales_results.tsv"/>
        </test>

        <test>
            <repeat name="tables">
                <param name="table" ftype="tabular" value="customers.tsv"/>
                <section name="input_opts">
                    <repeat name="linefilters">
                        <conditional name="filter">
                            <param name="filter_type" value="comment"/>
                            <param name="comment_char" value="35"/>
                        </conditional>
                    </repeat>
                </section>
                <section name="tbl_opts">
                    <param name="col_names" value=",FirstName,LastName,,DOB,"/>
                </section>
            </repeat>
            <repeat name="tables">
                <param name="table" ftype="tabular" value="sales.tsv"/>
                <section name="input_opts">
                    <repeat name="linefilters">
                        <conditional name="filter">
                            <param name="filter_type" value="skip"/>
                            <param name="skip_lines" value="1"/>
                        </conditional>
                    </repeat>
                </section>
            </repeat>
            <param name="sqlquery" value="SELECT FirstName,LastName,sum(t2.c3) as &quot;TotalSales&quot; FROM t1 join t2 on t1.c1 = t2.c1 GROUP BY t1.c1 ORDER BY TotalSales DESC;"/>
            <output name="output" file="sales_results.tsv"/>
        </test>

        <test>
            <repeat name="tables">
                <param name="table" ftype="tabular" value="customers.tsv"/>
                <section name="input_opts">
                    <repeat name="linefilters">
                        <conditional name="filter">
                            <param name="filter_type" value="skip"/>
                            <param name="skip_lines" value="1"/>
                        </conditional>
                    </repeat>
                </section>
                <section name="tbl_opts">
                    <param name="col_names" value=",FirstName,LastName,,BirthDate,"/>
                </section>
            </repeat>
            <param name="sqlquery" value="select FirstName,LastName,re_sub('^\d{2}(\d{2})-(\d\d)-(\d\d)','\3/\2/\1',BirthDate) as &quot;DOB&quot; from t1 WHERE re_search('[hp]er',c4)"/>
            <output name="output" file="regex_results.tsv"/>
        </test>

        <test>
            <repeat name="tables">
                <param name="table" ftype="tabular" value="IEDB.tsv"/>
                <section name="input_opts">
                    <repeat name="linefilters">
                        <conditional name="filter">
                            <param name="filter_type" value="comment"/>
                            <param name="comment_char" value="35"/>
                        </conditional>
                    </repeat>
                </section>
                <section name="tbl_opts">
                    <param name="table_name" value="iedb"/>
                    <param name="col_names" value="ID,allele,seq_num,start,end,length,peptide,method,percentile_rank,ann_ic50,ann_rank,smm_ic50,smm_rank,comblib_sidney2008_score,comblib_sidney2008_rank,netmhcpan_ic50,netmhcpan_rank"/>
                </section>
            </repeat>
            <repeat name="tables">
                <param name="table" ftype="tabular" value="netMHC_summary.tsv"/>
                <section name="input_opts">
                    <repeat name="linefilters">
                        <conditional name="filter">
                            <param name="filter_type" value="skip"/>
                            <param name="skip_lines" value="1"/>
                        </conditional>
                    </repeat>
                </section>
                <section name="tbl_opts">
                    <param name="table_name" value="mhc_summary"/>
                    <param name="col_names" value="pos,peptide,logscore,affinity,Bind_Level,Protein,Allele"/>
                </section>
            </repeat>
            <param name="sqlquery" value="select iedb.ID,iedb.peptide,iedb.start,iedb.end,iedb.percentile_rank,mhc_summary.logscore,mhc_summary.affinity,mhc_summary.Bind_Level from iedb left outer join mhc_summary on iedb.peptide = mhc_summary.peptide order by affinity,Bind_Level,percentile_rank"/>
            <output name="output" file="query_results.tsv"/>
        </test>

        <test>
            <section name="add_to_database">
                <param name="withdb" ftype="sqlite" value="testdb.sqlite"/>
            </section>
            <repeat name="tables">
                <param name="table" ftype="tabular" value="pets.tsv"/>
                <section name="input_opts">
                    <repeat name="linefilters">
                        <conditional name="filter">
                            <param name="filter_type" value="regex"/>
                            <param name="regex_pattern" value="^\d+"/>
                            <param name="regex_action" value="include_find"/>
                        </conditional>
                    </repeat>
                    <repeat name="linefilters">
                        <conditional name="filter">
                            <param name="filter_type" value="comment"/>
                            <param name="comment_char" value="35"/>
                        </conditional>
                    </repeat>
                    <repeat name="linefilters">
                        <conditional name="filter">
                            <param name="filter_type" value="append_line_num"/>
                        </conditional>
                    </repeat>
                    <repeat name="linefilters">
                        <conditional name="filter">
                            <param name="filter_type" value="select_columns"/>
                            <param name="columns" value="7,2,3,4,1"/>
                        </conditional>
                    </repeat>
                    <repeat name="linefilters">
                        <conditional name="filter">
                            <param name="filter_type" value="replace"/>
                            <param name="column" value="c4"/>
                            <param name="regex_pattern" value="(\d+)/(\d+)/(\d+)"/>
                            <param name="regex_replace" value="19\3-\2-\1"/>
                        </conditional>
                    </repeat>
                </section>
                <section name="tbl_opts">
                    <param name="table_name" value="people"/>
                    <param name="col_names" value="id,first,last,dob,pets"/>
                </section>
            </repeat>
            <param name="sqlquery" value="SELECT people.id,first,last,pets,quote FROM people JOIN contacts ON people.first = contacts.first_name"/>
            <output name="output" file="add_to_db_results.tsv"/>
        </test>

        <test>
            <repeat name="tables">
                <param name="table" ftype="tabular" value="pets.tsv"/>
                <section name="input_opts">
                    <repeat name="linefilters">
                        <conditional name="filter">
                            <param name="filter_type" value="regex"/>
                            <param name="regex_pattern" value="^\d+"/>
                            <param name="regex_action" value="include_find"/>
                        </conditional>
                    </repeat>
                    <repeat name="linefilters">
                        <conditional name="filter">
                            <param name="filter_type" value="comment"/>
                            <param name="comment_char" value="35"/>
                        </conditional>
                    </repeat>
                    <repeat name="linefilters">
                        <conditional name="filter">
                            <param name="filter_type" value="append_line_num"/>
                        </conditional>
                    </repeat>
                    <repeat name="linefilters">
                        <conditional name="filter">
                            <param name="filter_type" value="select_columns"/>
                            <param name="columns" value="7,2,3,4,1"/>
                        </conditional>
                    </repeat>
                    <repeat name="linefilters">
                        <conditional name="filter">
                            <param name="filter_type" value="replace"/>
                            <param name="column" value="c4"/>
                            <param name="regex_pattern" value="(\d+)/(\d+)/(\d+)"/>
                            <param name="regex_replace" value="19\3-\2-\1"/>
                        </conditional>
                    </repeat>
                </section>
                <section name="tbl_opts">
                    <param name="table_name" value="people"/>
                    <param name="col_names" value="id,first,last,dob,pets"/>
                </section>
            </repeat>
            <repeat name="tables">
                <param name="table" ftype="tabular" value="pets.tsv"/>
                <section name="input_opts">
                    <repeat name="linefilters">
                        <conditional name="filter">
                            <param name="filter_type" value="regex"/>
                            <param name="regex_pattern" value="^\d+"/>
                            <param name="regex_action" value="include_find"/>
                        </conditional>
                    </repeat>
                    <repeat name="linefilters">
                        <conditional name="filter">
                            <param name="filter_type" value="append_line_num"/>
                        </conditional>
                    </repeat>
                    <repeat name="linefilters">
                        <conditional name="filter">
                            <param name="filter_type" value="select_columns"/>
                            <param name="columns" value="c7,c5,c6"/>
                        </conditional>
                    </repeat>
                    <repeat name="linefilters">
                        <conditional name="filter">
                            <param name="filter_type" value="normalize"/>
                            <param name="columns" value="c2,c3"/>
                            <param name="separator" value=","/>
                        </conditional>
                    </repeat>
                </section>
                <section name="tbl_opts">
                    <param name="table_name" value="pet"/>
                    <param name="col_names" value="id,name,animal"/>
                </section>
            </repeat>
            <param name="sqlquery" value="SELECT people.id,first,last,dob,name,animal,pets FROM people JOIN pet ON people.id = pet.id WHERE animal = 'cat'"/>
            <output name="output" file="pet_normalized_query_results.tsv"/>
        </test>

    </tests>
    <help><![CDATA[
=============
Query Tabular
=============

**Inputs**

  Loads tabular datasets into a SQLite_ data base.  

  An existing SQLite_ data base can be used as input, and any selected tabular datasets will be added as new tables in that data base.


@LINEFILTERS_HELP@


**Outputs**

  The results of a SQL query are output to the history as a tabular file.

  The SQLite_ data base can also be saved and output as a dataset in the history.  

    *(The* **SQLite to tabular** *tool can run additional queries on this database.)*


@QUERY_HELP@

@LINEFILTERS_HELP_EXAMPLE@


  Table name: pets

  Table columns: Pets,FirstName,LastName,Birthdate,PetNames,PetType,line_num,entry_num,row_num

  Query: SELECT * FROM pets 

  Result:

     ======  ==========  ========  ==========  =========  ========  =========  ==========  ========
     #Pets   FirstName   LastName  BirthDate   PetNames   PetType   line_num   entry_num    row_num
     ======  ==========  ========  ==========  =========  ========  =========  ==========  ========
     2       Paula       Brown     1978-05-24  Rex        dog              3           1         1
     2       Paula       Brown     1978-05-24  Fluff      cat              3           1         2
     1       Steven      Jones     1974-04-04  Allie      cat              4           2         3
     0       Jane        Doe       1978-05-24                              5           3         4
     1       James       Smith     1980-10-20  Spot                        6           4         5          
     ======  ==========  ========  ==========  =========  ========  =========  ==========  ======== 


**Normalizing by Line Filtering into 2 Tables** 

*Relational database opertions work with single-valued column entries.  
To apply relational operations to tabular files that contain fields with lists of values,
we need to "normalize" those fields, duplicating lines for each item in the list.  
In this example we create 2 tables, one for single-valued fields and a second with list-valued fields normalized.  
Becauce we add a line number first for each table, we can join the 2 tables on the line number column.*
https://en.wikipedia.org/wiki/First_normal_form 

    *People Table*

      ::
  
        Filter 1 - by regex expression matching [include]: '^\d+' (include lines that start with a number) 
        Filter 2 - append a line number column:
        Filter 3 - regex replace value in column[4]: '(\d+)/(\d+)/(\d+)' '19\3-\2-\1' (convert dates to sqlite format) 
        Filter 4 - select columns 7,2,3,4,1

      Table: People
      Columns: id,FirstName,LastName,DOB,Pets

      ==  =========  ========   ==========  ====
      id  FirstName  LastName   DOB         Pets
      ==  =========  ========   ==========  ====
      1     Paula      Brown    1978-05-24  2
      2     Steven     Jones    1974-04-04  1
      3     Jane       Doe      1978-05-24  0
      4     James      Smith    1980-10-20  1
      ==  =========  ========   ==========  ====


    *Pet Table*

      :: 

        Filter 1 - by regex expression matching [include]: '^\d+' (include lines that start with a number) 
        Filter 2 - append a line number column:
        Filter 3 - by regex expression matching [exclude]: '^0\t' (exclude lines with no pets)
        Filter 4 - normalize list columns[5,6]:
        Filter 5 - select columns 7,5,6

      Table: Pet
      Columns: id,PetName,PetType

      ==  ========  ========
      id  PetName   PetType 
      ==  ========  ========
      1   Rex       dog     
      1   Fluff     cat     
      2   Allie     cat     
      4   Spot              
      ==  ========  ========


    Query: SELECT FirstName,LastName,PetName FROM People JOIN Pet ON People.id = Pet.id WHERE PetType = 'cat';     

    Result:

     =========  ========  ========
     FirstName  LastName  PetName 
     =========  ========  ========
     Paula      Brown     Fluff   
     Steven     Jones     Allie   
     =========  ========  ========


    ]]></help>
</tool>