Mercurial > repos > jjohnson > query_tabular
changeset 2:ffa5e34a55c1
Uploaded
author | jjohnson |
---|---|
date | Sun, 04 Oct 2015 10:52:21 -0400 |
parents | 24f0911f75ee |
children | 125fc5d123b3 afdbc7198353 |
files | query_tabular.py query_tabular.xml |
diffstat | 2 files changed, 26 insertions(+), 12 deletions(-) [+] |
line wrap: on
line diff
--- a/query_tabular.py Sat Oct 03 09:23:08 2015 -0400 +++ b/query_tabular.py Sun Oct 04 10:52:21 2015 -0400 @@ -111,6 +111,7 @@ parser.add_option( '-s', '--sqlitedb', dest='sqlitedb', default=None, help='The SQLite Database' ) parser.add_option( '-t', '--table', dest='tables', action="append", default=[], help='Tabular file: file_path[=table_name[:column_name,...]' ) parser.add_option( '-q', '--query', dest='query', default=None, help='SQL query' ) + parser.add_option( '-Q', '--query_file', dest='query_file', default=None, help='SQL query file' ) parser.add_option( '-n', '--no_header', dest='no_header', action='store_true', default=False, help='Include a column headers line' ) parser.add_option( '-o', '--output', dest='output', default=None, help='Output file for query results' ) (options, args) = parser.parse_args() @@ -143,7 +144,16 @@ create_table(conn,path,table_name,column_names=column_names) conn.close() - if (options.query is None): + query = None + if (options.query_file != None): + with open(options.query_file,'r') as fh: + query = '' + for line in fh: + query += line + elif (options.query != None): + query = options.query + + if (query is None): try: conn = sqlite.connect(options.sqlitedb) c = conn.cursor() @@ -161,13 +171,13 @@ except Exception, exc: print >> sys.stderr, "Error: %s" % exc exit(0) - #if not sqlite.is_read_only_query(options.query): + #if not sqlite.is_read_only_query(query): # print >> sys.stderr, "Error: Must be a read only query" # exit(2) try: conn = sqlite.connect(options.sqlitedb) cur = conn.cursor() - results = cur.execute(options.query) + results = cur.execute(query) if not options.no_header: outputFile.write("#%s\n" % '\t'.join([str(col[0]) for col in cur.description])) # yield [col[0] for col in cur.description]
--- a/query_tabular.xml Sat Oct 03 09:23:08 2015 -0400 +++ b/query_tabular.xml Sun Oct 04 10:52:21 2015 -0400 @@ -6,7 +6,11 @@ <stdio> <exit_code range="1:" /> </stdio> - + <configfiles> + <configfile name="query_file"> +$sqlquery + </configfile> + </configfiles> <command interpreter="python"><![CDATA[ query_tabular.py #if $save_db @@ -27,8 +31,8 @@ #end if -t ${tbl.table}=${tname}${$col_names} #end for - #if $query: - -q "$query" + #if $sqlquery: + -Q "$query_file" $no_header -o $output #end if @@ -49,7 +53,7 @@ <validator type="regex" message="A List of separated by commas: Column names should start with a letter and may contain additional letters, digits, and underscores">^([A-Za-z]\w*)?(,([A-Za-z]\w*)?)*$</validator> </param> </repeat> - <param name="query" type="text" area="true" size="10x80" value="" optional="true" label="SQL Query"> + <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> @@ -60,10 +64,10 @@ </inputs> <outputs> <data format="sqlite" name="sqlitedb" label="sqlite"> - <filter>save_db or not (query and len(query) > 0)</filter> + <filter>save_db or not (sqlquery and len(sqlquery) > 0)</filter> </data> <data format="tabular" name="output" label="query results"> - <filter>query and len(query) > 0</filter> + <filter>sqlquery and len(sqlquery) > 0</filter> </data> </outputs> <tests> @@ -79,7 +83,7 @@ <param name="table_name" value="sales"/> <param name="col_names" value="CustomerID,Date,SaleAmount"/> </repeat> - <param name="query" 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"/> + <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> @@ -91,7 +95,7 @@ <repeat name="tables"> <param name="table" ftype="tabular" value="sales.tsv"/> </repeat> - <param name="query" 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;"/> + <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> @@ -106,7 +110,7 @@ <param name="table_name" value="mhc_summary"/> <param name="col_names" value="pos,peptide,logscore,affinity,Bind_Level,Protein,Allele"/> </repeat> - <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"/> + <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>