Mercurial > repos > jjohnson > query_tabular

comparison query_tabular.xml @ 18:b9f797bf4f38 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author jjohnson
date Wed, 05 Jul 2017 11:51:15 -0400
parents 5b4f6cf857cf
children ab27c4bd14b9
comparison
equal deleted inserted replaced
17:c6e6e224509c 18:b9f797bf4f38
1 <tool id="query_tabular" name="Query Tabular" version="3.1.0"> 1 <tool id="query_tabular" name="Query Tabular" version="4.0.0">
2 <description>using sqlite sql</description> 2 <description>using sqlite sql</description>
3 3
4 <requirements> 4 <requirements>
5 </requirements> 5 </requirements>
6 <stdio> 6 <stdio>
92 #silent $input_filters.append($filter_dict) 92 #silent $input_filters.append($filter_dict)
93 #end if 93 #end if
94 #elif $fi.filter.filter_type == 'comment': 94 #elif $fi.filter.filter_type == 'comment':
95 #set $filter_dict = dict() 95 #set $filter_dict = dict()
96 #set $filter_dict['filter'] = 'regex' 96 #set $filter_dict['filter'] = 'regex'
97 #set $filter_dict['pattern'] = '^' + str($fi.filter.comment_char) 97 #set $filter_dict['pattern'] = '^(%s).*$' % '|'.join([chr(int(x)).replace('|','[|]') for x in (str($fi.filter.comment_char)).split(',')])
98 #set $filter_dict['action'] = 'exclude' 98 #set $filter_dict['action'] = 'exclude_match'
99 #silent $input_filters.append($filter_dict) 99 #silent $input_filters.append($filter_dict)
100 #elif $fi.filter.filter_type == 'regex': 100 #elif $fi.filter.filter_type == 'regex':
101 #set $filter_dict = dict() 101 #set $filter_dict = dict()
102 #set $filter_dict['filter'] = str($fi.filter.filter_type) 102 #set $filter_dict['filter'] = str($fi.filter.filter_type)
103 #set $filter_dict['pattern'] = str($fi.filter.regex_pattern) 103 #set $filter_dict['pattern'] = str($fi.filter.regex_pattern)
104 #set $filter_dict['action'] = str($fi.filter.regex_action) 104 #set $filter_dict['action'] = str($fi.filter.regex_action)
105 #silent $input_filters.append($filter_dict) 105 #silent $input_filters.append($filter_dict)
106 #elif $fi.filter.filter_type == 'select_columns': 106 #elif $fi.filter.filter_type == 'select_columns':
107 #set $filter_dict = dict() 107 #set $filter_dict = dict()
108 #set $filter_dict['filter'] = str($fi.filter.filter_type) 108 #set $filter_dict['filter'] = str($fi.filter.filter_type)
109 #set $filter_dict['columns'] = [int(str($ci)) for $ci in str($fi.filter.columns).split(',')] 109 #set $filter_dict['columns'] = [int(str($ci).replace('c','')) for $ci in str($fi.filter.columns).split(',')]
110 #silent $input_filters.append($filter_dict) 110 #silent $input_filters.append($filter_dict)
111 #elif $fi.filter.filter_type == 'replace': 111 #elif $fi.filter.filter_type == 'replace':
112 #set $filter_dict = dict() 112 #set $filter_dict = dict()
113 #set $filter_dict['filter'] = str($fi.filter.filter_type) 113 #set $filter_dict['filter'] = str($fi.filter.filter_type)
114 #set $filter_dict['column'] = int(str($fi.filter.column)) 114 #set $filter_dict['column'] = int(str($fi.filter.column).replace('c',''))
115 #set $filter_dict['pattern'] = str($fi.filter.regex_pattern) 115 #set $filter_dict['pattern'] = str($fi.filter.regex_pattern)
116 #set $filter_dict['replace'] = str($fi.filter.regex_replace) 116 #set $filter_dict['replace'] = str($fi.filter.regex_replace)
117 #silent $input_filters.append($filter_dict) 117 #silent $input_filters.append($filter_dict)
118 #elif str($fi.filter.filter_type).endswith('pend_line_num'): 118 #elif str($fi.filter.filter_type).endswith('pend_line_num'):
119 #set $filter_dict = dict() 119 #set $filter_dict = dict()
120 #set $filter_dict['filter'] = str($fi.filter.filter_type) 120 #set $filter_dict['filter'] = str($fi.filter.filter_type)
121 #silent $input_filters.append($filter_dict) 121 #silent $input_filters.append($filter_dict)
122 #elif str($fi.filter.filter_type).endswith('pend_text'):
123 #set $filter_dict = dict()
124 #set $filter_dict['filter'] = str($fi.filter.filter_type)
125 #set $filter_dict['column_text'] = str($fi.filter.column_text)
126 #silent $input_filters.append($filter_dict)
122 #elif $fi.filter.filter_type == 'normalize': 127 #elif $fi.filter.filter_type == 'normalize':
123 #set $filter_dict = dict() 128 #set $filter_dict = dict()
124 #set $filter_dict['filter'] = str($fi.filter.filter_type) 129 #set $filter_dict['filter'] = str($fi.filter.filter_type)
125 #set $filter_dict['columns'] = [int(str($ci)) for $ci in str($fi.filter.columns).split(',')] 130 #set $filter_dict['columns'] = [int(str($ci).replace('c','')) for $ci in str($fi.filter.columns).split(',')]
126 #set $filter_dict['separator'] = str($fi.filter.separator) 131 #set $filter_dict['separator'] = str($fi.filter.separator)
127 #silent $input_filters.append($filter_dict) 132 #silent $input_filters.append($filter_dict)
128 #end if 133 #end if
129 #end for 134 #end for
130 #if $input_filters: 135 #if $input_filters:
152 <option value="regex">by regex expression matching</option> 157 <option value="regex">by regex expression matching</option>
153 <option value="select_columns">select columns</option> 158 <option value="select_columns">select columns</option>
154 <option value="replace">regex replace value in column</option> 159 <option value="replace">regex replace value in column</option>
155 <option value="prepend_line_num">prepend a line number column</option> 160 <option value="prepend_line_num">prepend a line number column</option>
156 <option value="append_line_num">append a line number column</option> 161 <option value="append_line_num">append a line number column</option>
162 <option value="prepend_text">prepend a column with the given text</option>
163 <option value="append_text">append a column with the given text</option>
157 <option value="normalize">normalize list columns, replicates row for each item in list</option> 164 <option value="normalize">normalize list columns, replicates row for each item in list</option>
158 </param> 165 </param>
159 <when value="skip"> 166 <when value="skip">
160 <param name="skip_lines" type="integer" value="" min="0" optional="true" label="Skip lines" 167 <param name="skip_lines" type="integer" value="" min="0" optional="true" label="Skip lines"
161 help="Leave blank to use the comment lines metadata for this dataset" /> 168 help="Leave blank to use the comment lines metadata for this dataset" />
162 </when> 169 </when>
163 <when value="comment"> 170 <when value="comment">
164 <param name="comment_char" type="text" value="#" label="Comment line starting text"> 171 <param name="comment_char" type="select" display="checkboxes" multiple="True" label="Ignore lines beginning with these characters" help="lines beginning with these are skipped">
165 <sanitizer sanitize="False"/> 172 <option value="62">&gt;</option>
173 <option value="64">@</option>
174 <option value="43">+</option>
175 <option value="60">&lt;</option>
176 <option value="42">*</option>
177 <option value="45">-</option>
178 <option value="61">=</option>
179 <option value="124">|</option>
180 <option value="63">?</option>
181 <option value="36">$</option>
182 <option value="46">.</option>
183 <option value="58">:</option>
184 <option value="38">&amp;</option>
185 <option value="37">%</option>
186 <option value="94">^</option>
187 <option value="35">&#35;</option>
188 <option value="33">!</option>
166 </param> 189 </param>
167 </when> 190 </when>
168 <when value="prepend_line_num"/> 191 <when value="prepend_line_num"/>
169 <when value="append_line_num"/> 192 <when value="append_line_num"/>
193 <when value="prepend_text">
194 <param name="column_text" type="text" value="" label="text for column">
195 </param>
196 </when>
197 <when value="append_text">
198 <param name="column_text" type="text" value="" label="text for column">
199 </param>
200 </when>
170 <when value="regex"> 201 <when value="regex">
171 <param name="regex_pattern" type="text" value="" label="regex pattern"> 202 <param name="regex_pattern" type="text" value="" label="regex pattern">
172 <sanitizer sanitize="False"/> 203 <sanitizer sanitize="False"/>
173 </param> 204 </param>
174 <param name="regex_action" type="select" label="action for regex match"> 205 <param name="regex_action" type="select" label="action for regex match">
178 <option value="include_find">include line if pattern found</option> 209 <option value="include_find">include line if pattern found</option>
179 </param> 210 </param>
180 </when> 211 </when>
181 <when value="select_columns"> 212 <when value="select_columns">
182 <param name="columns" type="text" value="" label="enter column numbers to keep" 213 <param name="columns" type="text" value="" label="enter column numbers to keep"
183 help="example: 1,4,2 (selects the first,fourth, and second columns)"> 214 help="example: 1,4,2 or c1,c4,c2(selects the first,fourth, and second columns)">
184 <validator type="regex" message="Column ordinal positions separated by commas">^([1-9]\d*)(,[1-9]\d*)*$</validator> 215 <validator type="regex" message="Column ordinal positions separated by commas">^(c?[1-9]\d*)(,c?[1-9]\d*)*$</validator>
185 </param> 216 </param>
186 </when> 217 </when>
187 <when value="replace"> 218 <when value="replace">
188 <param name="column" type="data_column" data_ref="table" label="Column to replace text" 219 <param name="column" type="text" value="" label="enter column number to replace"
189 help=""/> 220 help="example: 1 or c1 (selects the first column)">
221 <validator type="regex" message="Column ordinal position separated by commas">^(c?[1-9]\d*)$</validator>
222 </param>
190 <param name="regex_pattern" type="text" value="" label="regex pattern"> 223 <param name="regex_pattern" type="text" value="" label="regex pattern">
191 <sanitizer sanitize="False"/> 224 <sanitizer sanitize="False"/>
192 </param> 225 </param>
193 <param name="regex_replace" type="text" value="" label="replacement expression"> 226 <param name="regex_replace" type="text" value="" label="replacement expression">
194 <sanitizer sanitize="False"/> 227 <sanitizer sanitize="False"/>
195 </param> 228 </param>
196 </when> 229 </when>
197 <when value="normalize"> 230 <when value="normalize">
198 <param name="columns" type="data_column" data_ref="table" multiple="True" label="Columns to split" 231 <param name="columns" type="text" value="" label="enter column numbers to normalize">
199 help="If multiple columns are selected, they should have the same length and separator on each line"/> 232 <help><![CDATA[
233 example: 2,4 or c2,c4 (selects the second, and fourth columns)
234 If multiple columns are selected, they should have the same length and separator on each line
235 ]]></help>
236 <validator type="regex" message="Column ordinal positions separated by commas">^(c?[1-9]\d*)(,c?[1-9]\d*)*$</validator>
237 </param>
200 <param name="separator" type="text" value="," label="List item delimiter in column"> 238 <param name="separator" type="text" value="," label="List item delimiter in column">
201 <sanitizer sanitize="False"/> 239 <sanitizer sanitize="False"/>
202 <validator type="regex" message="Anything but TAB or Newline">^[^\t\n\r\f\v]+$</validator> 240 <validator type="regex" message="Anything but TAB or Newline">^[^\t\n\r\f\v]+$</validator>
203 </param> 241 </param>
204 </when> 242 </when>
298 </repeat> 336 </repeat>
299 <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"/> 337 <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"/>
300 <output name="output" file="query_results.tsv"/> 338 <output name="output" file="query_results.tsv"/>
301 </test> 339 </test>
302 340
341 <test>
342 <repeat name="tables">
343 <param name="table" ftype="tabular" value="pets.tsv"/>
344 <repeat name="linefilters">
345 <param name="filter_type" value="comment"/>
346 <param name="comment_char" value="35"/>
347 </repeat>
348 <repeat name="linefilters">
349 <param name="filter_type" value="append_line_num"/>
350 </repeat>
351 <repeat name="linefilters">
352 <param name="filter_type" value="select_columns"/>
353 <param name="columns" value="7,2,3,4,1"/>
354 </repeat>
355 <repeat name="linefilters">
356 <param name="filter_type" value="replace"/>
357 <param name="column" value="c4"/>
358 <param name="regex_pattern" value="(\d+)/(\d+)/(\d+)"/>
359 <param name="regex_replace" value="19\3-\2-\1"/>
360 </repeat>
361 <param name="table_name" value="people"/>
362 <param name="col_names" value="id,first,last,dob,pets"/>
363
364 </repeat>
365 <repeat name="tables">
366 <param name="table" ftype="tabular" value="pets.tsv"/>
367 <repeat name="linefilters">
368 <param name="filter_type" value="comment"/>
369 <param name="comment_char" value="35"/>
370 </repeat>
371 <repeat name="linefilters">
372 <param name="filter_type" value="append_line_num"/>
373 </repeat>
374 <repeat name="linefilters">
375 <param name="filter_type" value="select_columns"/>
376 <param name="columns" value="c7,c5,c6"/>
377 </repeat>
378 <repeat name="linefilters">
379 <param name="filter_type" value="normalize"/>
380 <param name="columns" value="c2,c3"/>
381 <param name="separator" value=","/>
382 </repeat>
383 <param name="table_name" value="pet"/>
384 <param name="col_names" value="id,name,animal"/>
385 </repeat>
386 <param name="sqlquery" value="SELECT people.id,first,last,dob,name,animal,pets FROM people JOIN pet ON people.id = pet.id WHERE animal = 'cat'"/>
387 <output name="output" file="pet_normalized_query_results.tsv"/>
388 </test>
389
303 </tests> 390 </tests>
304 <help><![CDATA[ 391 <help><![CDATA[
305 ============= 392 =============
306 Query Tabular 393 Query Tabular
307 ============= 394 =============