Mercurial > repos > jjohnson > query_tabular

comparison query_tabular.xml @ 0:763c4f968dc6

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author jjohnson
date Thu, 01 Oct 2015 09:50:16 -0400
parents
children 24f0911f75ee
comparison
equal deleted inserted replaced
-1:000000000000 0:763c4f968dc6
1 <tool id="query_tabular" name="Query Tabular" version="0.1.0">
2 <description>using sqlite sql</description>
3
4 <requirements>
5 </requirements>
6 <stdio>
7 <exit_code range="1:" />
8 </stdio>
9
10 <command interpreter="python"><![CDATA[
11 query_tabular.py
12 #if $save_db
13 -s $sqlitedb
14 #else
15 -s $workdb
16 #end if
17 #for $i,$tbl in enumerate($tables):
18 #if $tbl.table_name
19 #set $tname = $tbl.table_name
20 #else
21 #set $tname = 't' + str($i + 1)
22 #end if
23 #if $tbl.col_names:
24 #set $col_names = ':' + str($tbl.col_names)
25 #else
26 #set $col_names = ''
27 #end if
28 -t ${tbl.table}=${tname}${$col_names}
29 #end for
30 #if $query:
31 -q "$query"
32 -o $output
33 #end if
34 ]]></command>
35 <inputs>
36 <param name="workdb" type="hidden" value="workdb.sqlite" label=""/>
37 <repeat name="tables" title="Add tables" min="1">
38 <param name="table" type="data" format="tabular" label="Dataset"/>
39 <param name="table_name" type="text" value="" optional="true" label="Table name">
40 <help>By default, tables will be named: t1,t2,...,tn</help>
41 <validator type="regex" message="Table name should start with a letter and may contain additional letters, digits, and underscores">^[A-Za-z]\w*$</validator>
42 </param>
43 <!--
44 <param name="sel_cols" label="Include columns" type="data_column" multiple="true" data_ref="table" />
45 -->
46 <param name="col_names" type="text" value="" optional="true" label="Column names">
47 <help>By default, table columns will be named: c1,c2,c3,...,cn</help>
48 <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*)?)*$</validator>
49 </param>
50 </repeat>
51 <param name="query" type="text" area="true" size="10x80" value="" optional="true" label="SQL Query">
52 <help>By default, tables will be named: t1,t2,...,tn</help>
53 <sanitizer sanitize="False"/>
54 <validator type="regex" message="">^(?i)\s*select\s+.*\s+from\s+.*$</validator>
55 </param>
56 <param name="save_db" type="boolean" truevalue="yes" falsevalue="no" checked="false" label="Save the sqlite database"/>
57 </inputs>
58 <outputs>
59 <data format="sqlite" name="sqlitedb" label="sqlite">
60 <filter>save_db or not (query and len(query) > 0)</filter>
61 </data>
62 <data format="tabular" name="output" label="query results">
63 <filter>query and len(query) > 0</filter>
64 </data>
65 </outputs>
66 <tests>
67
68 <test>
69 <repeat name="tables">
70 <param name="table" ftype="tabular" value="customers.tsv"/>
71 <param name="table_name" value="customers"/>
72 <param name="col_names" value="CustomerID,FirstName,LastName,Email,DOB,Phone"/>
73 </repeat>
74 <repeat name="tables">
75 <param name="table" ftype="tabular" value="sales.tsv"/>
76 <param name="table_name" value="sales"/>
77 <param name="col_names" value="CustomerID,Date,SaleAmount"/>
78 </repeat>
79 <param name="query" 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"/>
80 <output name="output" file="sales_results.tsv"/>
81 </test>
82
83 <test>
84 <repeat name="tables">
85 <param name="table" ftype="tabular" value="customers.tsv"/>
86 <param name="col_names" value=",FirstName,LastName,,DOB,"/>
87 </repeat>
88 <repeat name="tables">
89 <param name="table" ftype="tabular" value="sales.tsv"/>
90 </repeat>
91 <param name="query" 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;"/>
92 <output name="output" file="sales_results.tsv"/>
93 </test>
94
95 <test>
96 <repeat name="tables">
97 <param name="table" ftype="tabular" value="IEDB.tsv"/>
98 <param name="table_name" value="iedb"/>
99 <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"/>
100 </repeat>
101 <repeat name="tables">
102 <param name="table" ftype="tabular" value="netMHC_summary.tsv"/>
103 <param name="table_name" value="mhc_summary"/>
104 <param name="col_names" value="pos,peptide,logscore,affinity,Bind_Level,Protein,Allele"/>
105 </repeat>
106 <param name="query" 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"/>
107 <output name="output" file="query_results.tsv"/>
108 </test>
109
110 </tests>
111 <help><![CDATA[
112 =============
113 Query Tabular
114 =============
115
116 **Inputs**
117
118 Loads tabular datasets into a SQLite_ data base.
119
120 **Outputs**
121
122 The results of a SQL query are output to the history as a tabular file.
123
124 The SQLite_ data base can also be saved and output as a dataset in the history.
125
126
127 For help in using SQLite_ see: http://www.sqlite.org/docs.html
128
129 **NOTE:** input for SQLite dates input field must be in the format: *YYYY-MM-DD* for example: 2015-09-30
130
131 See: http://www.sqlite.org/lang_datefunc.html
132
133 **Example**
134
135 Given 2 tabular datasets: *customers* and *sales*
136
137 Dataset *customers*
138
139 Table name: "customers"
140
141 Column names: "CustomerID,FirstName,LastName,Email,DOB,Phone"
142
143 =========== ========== ========== ===================== ========== ============
144 #CustomerID FirstName LastName Email DOB Phone
145 =========== ========== ========== ===================== ========== ============
146 1 John Smith John.Smith@yahoo.com 1968-02-04 626 222-2222
147 2 Steven Goldfish goldfish@fishhere.net 1974-04-04 323 455-4545
148 3 Paula Brown pb@herowndomain.org 1978-05-24 416 323-3232
149 4 James Smith jim@supergig.co.uk 1980-10-20 416 323-8888
150 =========== ========== ========== ===================== ========== ============
151
152 Dataset *sales*
153
154 Table name: "sales"
155
156 Column names: "CustomerID,Date,SaleAmount"
157
158 ============= ============ ============
159 #CustomerID Date SaleAmount
160 ============= ============ ============
161 2 2004-05-06 100.22
162 1 2004-05-07 99.95
163 3 2004-05-07 122.95
164 3 2004-05-13 100.00
165 4 2004-05-22 555.55
166 ============= ============ ============
167
168 The query
169
170 ::
171
172 SELECT FirstName,LastName,sum(SaleAmount) as "TotalSales"
173 FROM customers join sales on customers.CustomerID = sales.CustomerID
174 GROUP BY customers.CustomerID ORDER BY TotalSales DESC;
175
176 Produces this tabular output:
177
178 ========== ======== ==========
179 #FirstName LastName TotalSales
180 ========== ======== ==========
181 James Smith 555.55
182 Paula Brown 222.95
183 Steven Goldfish 100.22
184 John Smith 99.95
185 ========== ======== ==========
186
187
188 If the optional Table name and Column names inputs are not used, the query would be:
189
190 ::
191
192 SELECT t1.c2 as "FirstName", t1.c3 as "LastName", sum(t2.c3) as "TotalSales"
193 FROM t1 join t2 on t1.c1 = t2.c1
194 GROUP BY t1.c1 ORDER BY TotalSales DESC;
195
196 You can selectively name columns, e.g. on the customers input you could just name columns 2,3, and 5:
197
198 Column names: ,FirstName,LastName,,BirthDate
199
200 Results in the following data base table
201
202 =========== ========== ========== ===================== ========== ============
203 #c1 FirstName LastName c4 BithDate c6
204 =========== ========== ========== ===================== ========== ============
205 1 John Smith John.Smith@yahoo.com 1968-02-04 626 222-2222
206 2 Steven Goldfish goldfish@fishhere.net 1974-04-04 323 455-4545
207 3 Paula Brown pb@herowndomain.org 1978-05-24 416 323-3232
208 4 James Smith jim@supergig.co.uk 1980-10-20 416 323-8888
209 =========== ========== ========== ===================== ========== ============
210
211 .. _SQLite: http://www.sqlite.org/index.html
212
213 ]]></help>
214 </tool>