Mercurial > repos > jjohnson > query_tabular
diff query_tabular.xml @ 4:afdbc7198353 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 08:09:36 -0500 |
| parents | ffa5e34a55c1 |
| children | 727620f718c2 |
line wrap: on
line diff
--- a/query_tabular.xml Sun Oct 04 10:52:21 2015 -0400 +++ b/query_tabular.xml Thu Jan 21 08:09:36 2016 -0500 @@ -6,11 +6,6 @@ <stdio> <exit_code range="1:" /> </stdio> - <configfiles> - <configfile name="query_file"> -$sqlquery - </configfile> - </configfiles> <command interpreter="python"><![CDATA[ query_tabular.py #if $save_db @@ -18,25 +13,62 @@ #else -s $workdb #end if - #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 + -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"> @@ -52,6 +84,7 @@ <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> @@ -63,10 +96,10 @@ <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"> + <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"> + <data format="tabular" name="output" label="query results on ${on_string}"> <filter>sqlquery and len(sqlquery) > 0</filter> </data> </outputs> @@ -84,7 +117,7 @@ <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"/> + <output name="output" file="sales_results.tsv"/> </test> <test> @@ -96,7 +129,16 @@ <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"/> + <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> @@ -111,7 +153,7 @@ <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"/> + <output name="output" file="query_results.tsv"/> </test> </tests> @@ -207,7 +249,7 @@ Results in the following data base table =========== ========== ========== ===================== ========== ============ - #c1 FirstName LastName c4 BithDate c6 + #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 @@ -215,6 +257,46 @@ 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>