Mercurial > repos > jjohnson > query_tabular
diff query_tabular.xml @ 0:926c62f7fa09 draft
planemo upload for repository https://github.com/jj-umn/galaxytools/tree/master/query_tabular commit 9ae87502ea7c3da33ecc453872c4eb2f41ecea4a-dirty
| author | jjohnson |
|---|---|
| date | Thu, 21 Jan 2016 08:23:45 -0500 |
| parents | |
| children | c7a1a686e42b |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/query_tabular.xml Thu Jan 21 08:23:45 2016 -0500 @@ -0,0 +1,303 @@ +<tool id="query_tabular" name="Query Tabular" version="0.1.0"> + <description>using sqlite sql</description> + + <requirements> + </requirements> + <stdio> + <exit_code range="1:" /> + </stdio> + <command interpreter="python"><![CDATA[ + query_tabular.py + #if $save_db + -s $sqlitedb + #else + -s $workdb + #end if + -j $table_json + #* + ## #for $i,$tbl in enumerate($tables): + ## #if $tbl.table_name + ## #set $tname = $tbl.table_name + ## #else + ## #set $tname = 't' + str($i + 1) + ## #end if + ## #if $tbl.col_names: + ## #set $col_names = ':' + str($tbl.col_names) + ## #else + ## #set $col_names = '' + ## #end if + ## -t ${tbl.table}=${tname}${$col_names} + ## #end for + *# + #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.table_name + #set $tname = str($tbl.table_name) + #else + #set $tname = 't' + str($i + 1) + #end if + #set $jtbl['table_name'] = $tname + #if $tbl.col_names: + #set $col_names = str($tbl.col_names) + #else + #set $col_names = '' + #end if + #set $jtbl['column_names'] = $col_names + #if str($tbl.skip_lines) != '': + #set $jtbl['comment_lines'] = $tbl.skip_lines + #elif $tbl.table.metadata.comment_lines > 0: + #set $jtbl['comment_lines'] = int($tbl.table.metadata.comment_lines) + #end if + #set $jtbls += [$jtbl] +#end for +#echo $json.dumps($jtbldef) + </configfile> + </configfiles> + <inputs> + <param name="workdb" type="hidden" value="workdb.sqlite" label=""/> + <repeat name="tables" title="Add tables" min="1"> + <param name="table" type="data" format="tabular" label="Dataset"/> + <param name="table_name" type="text" value="" optional="true" label="Table name"> + <help>By default, tables will be named: t1,t2,...,tn</help> + <validator type="regex" message="Table name should start with a letter and may contain additional letters, digits, and underscores">^[A-Za-z]\w*$</validator> + </param> + <!-- + <param name="sel_cols" label="Include columns" type="data_column" multiple="true" data_ref="table" /> + --> + <param name="col_names" type="text" value="" optional="true" label="Column names"> + <help>By default, table columns will be named: c1,c2,c3,...,cn</help> + <validator type="regex" message="A List of separated by commas: Column names should start with a letter and may contain additional letters, digits, and underscores">^([A-Za-z]\w*)?(,([A-Za-z]\w*)?)*$</validator> + </param> + <param name="skip_lines" type="integer" value="" min="0" optional="true" label="Skip lines" help="Leave blank to use the datatype comment lines metadata" /> + </repeat> + <param name="sqlquery" type="text" area="true" size="10x80" value="" optional="true" label="SQL Query"> + <help>By default, tables will be named: t1,t2,...,tn</help> + <sanitizer sanitize="False"/> + <validator type="regex" message="">^(?i)\s*select\s+.*\s+from\s+.*$</validator> + </param> + <param name="no_header" type="boolean" truevalue="-n" falsevalue="" checked="False" label="Omit column headers"/> + + <param name="save_db" type="boolean" truevalue="yes" falsevalue="no" checked="false" label="Save the sqlite database"/> + </inputs> + <outputs> + <data format="sqlite" name="sqlitedb" label="sqlite db of ${on_string}"> + <filter>save_db or not (sqlquery and len(sqlquery) > 0)</filter> + </data> + <data format="tabular" name="output" label="query results on ${on_string}"> + <filter>sqlquery and len(sqlquery) > 0</filter> + </data> + </outputs> + <tests> + + <test> + <repeat name="tables"> + <param name="table" ftype="tabular" value="customers.tsv"/> + <param name="table_name" value="customers"/> + <param name="col_names" value="CustomerID,FirstName,LastName,Email,DOB,Phone"/> + </repeat> + <repeat name="tables"> + <param name="table" ftype="tabular" value="sales.tsv"/> + <param name="table_name" value="sales"/> + <param name="col_names" value="CustomerID,Date,SaleAmount"/> + </repeat> + <param name="sqlquery" value="SELECT FirstName,LastName,sum(SaleAmount) as "TotalSales" 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"/> + <param name="col_names" value=",FirstName,LastName,,DOB,"/> + </repeat> + <repeat name="tables"> + <param name="table" ftype="tabular" value="sales.tsv"/> + </repeat> + <param name="sqlquery" value="SELECT FirstName,LastName,sum(t2.c3) as "TotalSales" 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"/> + <param name="col_names" value=",FirstName,LastName,,BirthDate,"/> + </repeat> + <param name="sqlquery" value="select FirstName,LastName,re_sub('^\d{2}(\d{2})-(\d\d)-(\d\d)','\3/\2/\1',BirthDate) as "DOB" 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"/> + <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"/> + </repeat> + <repeat name="tables"> + <param name="table" ftype="tabular" value="netMHC_summary.tsv"/> + <param name="table_name" value="mhc_summary"/> + <param name="col_names" value="pos,peptide,logscore,affinity,Bind_Level,Protein,Allele"/> + </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"/> + <output name="output" file="query_results.tsv"/> + </test> + + </tests> + <help><![CDATA[ +============= +Query Tabular +============= + +**Inputs** + + Loads tabular datasets into a SQLite_ data base. + +**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. + + +For help in using SQLite_ see: http://www.sqlite.org/docs.html + +**NOTE:** input for SQLite dates input field must be in the format: *YYYY-MM-DD* for example: 2015-09-30 + +See: http://www.sqlite.org/lang_datefunc.html + +**Example** + + Given 2 tabular datasets: *customers* and *sales* + + Dataset *customers* + + Table name: "customers" + + Column names: "CustomerID,FirstName,LastName,Email,DOB,Phone" + + =========== ========== ========== ===================== ========== ============ + #CustomerID FirstName LastName Email DOB Phone + =========== ========== ========== ===================== ========== ============ + 1 John Smith John.Smith@yahoo.com 1968-02-04 626 222-2222 + 2 Steven Goldfish goldfish@fishhere.net 1974-04-04 323 455-4545 + 3 Paula Brown pb@herowndomain.org 1978-05-24 416 323-3232 + 4 James Smith jim@supergig.co.uk 1980-10-20 416 323-8888 + =========== ========== ========== ===================== ========== ============ + + Dataset *sales* + + Table name: "sales" + + Column names: "CustomerID,Date,SaleAmount" + + ============= ============ ============ + #CustomerID Date SaleAmount + ============= ============ ============ + 2 2004-05-06 100.22 + 1 2004-05-07 99.95 + 3 2004-05-07 122.95 + 3 2004-05-13 100.00 + 4 2004-05-22 555.55 + ============= ============ ============ + + The query + + :: + + SELECT FirstName,LastName,sum(SaleAmount) as "TotalSales" + FROM customers join sales on customers.CustomerID = sales.CustomerID + GROUP BY customers.CustomerID ORDER BY TotalSales DESC; + + Produces this tabular output: + + ========== ======== ========== + #FirstName LastName TotalSales + ========== ======== ========== + James Smith 555.55 + Paula Brown 222.95 + Steven Goldfish 100.22 + John Smith 99.95 + ========== ======== ========== + + + If the optional Table name and Column names inputs are not used, the query would be: + + :: + + SELECT t1.c2 as "FirstName", t1.c3 as "LastName", sum(t2.c3) as "TotalSales" + FROM t1 join t2 on t1.c1 = t2.c1 + GROUP BY t1.c1 ORDER BY TotalSales DESC; + + You can selectively name columns, e.g. on the customers input you could just name columns 2,3, and 5: + + Column names: ,FirstName,LastName,,BirthDate + + Results in the following data base table + + =========== ========== ========== ===================== ========== ============ + #c1 FirstName LastName c4 BirthDate c6 + =========== ========== ========== ===================== ========== ============ + 1 John Smith John.Smith@yahoo.com 1968-02-04 626 222-2222 + 2 Steven Goldfish goldfish@fishhere.net 1974-04-04 323 455-4545 + 3 Paula Brown pb@herowndomain.org 1978-05-24 416 323-3232 + 4 James Smith jim@supergig.co.uk 1980-10-20 416 323-8888 + =========== ========== ========== ===================== ========== ============ + + Regular_expression_ functions are included for: + + :: + + matching: re_match('pattern',column) + + SELECT t1.FirstName, t1.LastName + FROM t1 + WHERE re_match('^.*\.(net|org)$',c4) + + Results: + + =========== ========== + #FirstName LastName + =========== ========== + Steven Goldfish + Paula Brown + =========== ========== + + + :: + + searching: re_search('pattern',column) + substituting: re_sub('pattern','replacement,column) + + SELECT t1.FirstName, t1.LastName, re_sub('^\d{2}(\d{2})-(\d\d)-(\d\d)','\3/\2/\1',BirthDate) as "DOB" + FROM t1 + WHERE re_search('[hp]er',c4) + + Results: + + =========== ========== ========== + #FirstName LastName DOB + =========== ========== ========== + Steven Goldfish 04/04/74 + Paula Brown 24/05/78 + James Smith 20/10/80 + =========== ========== ========== + +.. _Regular_expression: https://docs.python.org/release/2.7/library/re.html +.. _SQLite: http://www.sqlite.org/index.html + + ]]></help> +</tool>