Mercurial > repos > iuc > query_tabular
changeset 10:2e8f945f7285 draft
"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/query_tabular commit 67db58361546009a77b2cbd140967fbc634d425b"
| author | iuc |
|---|---|
| date | Thu, 24 Sep 2020 11:26:46 +0000 |
| parents | a3aab6045663 |
| children | 83069b38aa85 |
| files | load_db.py query_tabular.xml test-data/netMHC_summary_out1.tsv test-data/netMHC_summary_out2.tsv |
| diffstat | 4 files changed, 80 insertions(+), 10 deletions(-) [+] |
line wrap: on
line diff
--- a/load_db.py Sat Sep 12 01:22:05 2020 +0000 +++ b/load_db.py Thu Sep 24 11:26:46 2020 +0000 @@ -189,6 +189,9 @@ if linenum == 0 and firstlinenames: col_names = [get_valid_column_name(name) or 'c%d' % (i + 1) for i, name in enumerate(fields)] + # guarantee col_types in case of empty data + while len(col_types) < len(fields): + col_types.append(None) continue if linenum > max_lines: break @@ -210,23 +213,30 @@ if not col_names: col_names = ['c%d' % i for i in range(1, len(col_types) + 1)] if column_names: + cnames = [cn.strip() for cn in column_names.split(',')] if load_named_columns: col_idx = [] - cnames = [] - for i, cname in enumerate( - [cn.strip() for cn in column_names.split(',')]): + colnames = [] + for i, cname in enumerate(cnames): + # guarantee col_types in case of empty data + if i >= len(col_types): + col_types.append('TEXT') if cname != '': col_idx.append(i) - cnames.append(cname) + colnames.append(cname) col_types = [col_types[i] for i in col_idx] - col_names = cnames + col_names = colnames else: - for i, cname in enumerate( - [cn.strip() for cn in column_names.split(',')]): - if cname and i < len(col_names): - col_names[i] = cname + if col_names: + for i, cname in enumerate(cnames): + if cname and i < len(col_names): + col_names[i] = cname + else: + col_names = [x if x else 'c%d' % (i) for i, x in enumerate(cnames)] col_def = [] for i, col_name in enumerate(col_names): + if i >= len(col_types): + col_types.append('TEXT') col_def.append('%s %s' % (col_names[i], col_types[i])) return col_names, col_types, col_def, col_idx
--- a/query_tabular.xml Sat Sep 12 01:22:05 2020 +0000 +++ b/query_tabular.xml Thu Sep 24 11:26:46 2020 +0000 @@ -1,4 +1,4 @@ -<tool id="query_tabular" name="Query Tabular" version="3.1.0"> +<tool id="query_tabular" name="Query Tabular" version="3.1.1"> <description>using sqlite sql</description> <macros> @@ -528,6 +528,57 @@ <output name="output1" file="psm_dbmod_output1.tsv" compare="re_match"/> </test> + <test> + <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="regex"/> + <param name="regex_pattern" value="peptide"/> + <param name="regex_action" value="include_find"/> + </conditional> + </repeat> + </section> + <section name="tbl_opts"> + <param name="table_name" value="epitope"/> + <param name="column_names_from_first_line" value="True"/> + </section> + </repeat> + <param name="sqlquery" value="SELECT * FROM epitope"/> + <conditional name="query_result"> + <param name="header" value="yes"/> + <param name="header_prefix" value=""/> + </conditional> + <output name="output" file="netMHC_summary_out1.tsv" ftype="tabular"/> + </test> + + <test> + <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="regex"/> + <param name="regex_pattern" value="NOT TO BE FOUND"/> + <param name="regex_action" value="include_find"/> + </conditional> + </repeat> + </section> + <section name="tbl_opts"> + <param name="table_name" value="epitope"/> + <param name="column_names_from_first_line" value="False"/> + <param name="col_names" value="pos,peptide,logscore,,,,Allele"/> + </section> + </repeat> + <param name="sqlquery" value="SELECT pos,peptide,logscore,Allele FROM epitope"/> + <conditional name="query_result"> + <param name="header" value="yes"/> + <param name="header_prefix" value=""/> + </conditional> + <output name="output" file="netMHC_summary_out2.tsv" ftype="tabular"/> + </test> + </tests> <help><![CDATA[ ============= @@ -540,6 +591,13 @@ 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. + **NOTE:** If there are no data rows in an input tabular dataset, query_tabular will fail unless: + + - There is a row header line in the dataset and **Use first line as column names** is selected + - **Specify Column Names** is used to provide column names + + in which case an empty table will be created with those columns + @LINEFILTERS_HELP@