Mercurial > repos > bgruening > text_processing

changeset 2:fc862d5bccaf draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author bgruening
date Thu, 05 Sep 2013 12:42:48 -0400
parents a4ad586d1403
children 7068d1548234
files awk.xml cut.xml find_and_replace.xml grep.xml multijoin.xml readme.rst
diffstat 6 files changed, 19 insertions(+), 17 deletions(-) [+]
line wrap: on
line diff
--- a/awk.xml	Thu Sep 05 11:42:27 2013 -0400
+++ b/awk.xml	Thu Sep 05 12:42:48 2013 -0400
@@ -1,5 +1,5 @@
-<tool id="unixtools_awk_tool" name="Data-reformatting" version="0.1.1">
-    <description>(awk)</description>
+<tool id="unixtools_awk_tool" name="Text reformatting" version="0.1.1">
+    <description>with awk</description>
     <requirements>
         <requirement type="package" version="4.1.0">gnu_awk</requirement>
     </requirements>
--- a/cut.xml	Thu Sep 05 11:42:27 2013 -0400
+++ b/cut.xml	Thu Sep 05 12:42:48 2013 -0400
@@ -4,7 +4,11 @@
         <requirement type="package" version="8.21">gnu_coreutils</requirement>
     </requirements>
     <command>
-        cut -d"${delimiter}" ${complement} ${cut_element} '${list}' '${input}' &gt; '${output}'
+        cut 
+        #if str($delimiter) != '':
+            -d"${delimiter}"
+        #end if
+        ${complement} ${cut_element} '${list}' '${input}' &gt; '${output}'
     </command>
 
     <inputs>
--- a/find_and_replace.xml	Thu Sep 05 11:42:27 2013 -0400
+++ b/find_and_replace.xml	Thu Sep 05 12:42:48 2013 -0400
@@ -1,5 +1,5 @@
-<tool id="cshl_find_and_replace" name="Find and Replace" version="0.1.1">
-    <description>text</description>
+<tool id="cshl_find_and_replace" name="Replace" version="0.1.1">
+    <description>parts of text</description>
     <command interpreter="perl">
         find_and_replace
             #if $searchwhere.choice == "column":
--- a/grep.xml	Thu Sep 05 11:42:27 2013 -0400
+++ b/grep.xml	Thu Sep 05 12:42:48 2013 -0400
@@ -5,8 +5,8 @@
         <requirement type="package" version="2.14">gnu_grep</requirement>
         <requirement type="set_environment">UNIX_TOOLS_SCRIPT_PATH</requirement>
     </requirements>
-    <command interpreter="sh">
-        #if $color == "COLOR":
+    <command>
+        #if str($color) == "COLOR":
             GREP_COLOR='1;34' grep --color=always -P "$@" -- "${url_paste}" '${input}' | \$UNIX_TOOLS_SCRIPT_PATH/ansi2html.sh > "${output}"
         #else:
             grep -P "$@" -- "${url_paste}" '${input}' | grep -v "^--$" > "${output}"
--- a/multijoin.xml	Thu Sep 05 11:42:27 2013 -0400
+++ b/multijoin.xml	Thu Sep 05 12:42:48 2013 -0400
@@ -7,6 +7,7 @@
         $ignore_dups
         $output_header
         $input_header
+        $first_filename
         #for $file in $files
             '$file.filename'
         #end for
@@ -14,21 +15,17 @@
   </command>
 
   <inputs>
-    <repeat name="files" title="file to join" min="2">
-        <param name="filename" label="Add file" type="data" format="txt" />
+
+    <param name="first_filename" label="File to join" type="data" format="txt" />
+    <repeat name="files" title="with" min="2">
+        <param name="filename" label="add additional file" type="data" format="txt" />
     </repeat>
 
     <param name="key_column" label="Common key column" type="integer"
        value="1" help="Usually gene-ID or other common value" />
 
-    <param name="value_columns" label="Column with values to preserve" type="text"
-       value="2,3,4" help="Enter comma-separated list of columns, e.g. 3,6,8">
-        <sanitizer>
-            <valid initial="string.printable">
-                <remove value="&apos;"/>
-            </valid>
-        </sanitizer>
-    </param>
+    <param name="value_columns" label="Column with values to preserve" 
+        type="data_column" data_ref="first_filename" accept_default="true" multiple="True" display="checkboxes"/>
 
     <param name="output_header" type="boolean" checked="false" truevalue="--out-header" falsevalue="" label="Add header line to the output file" help="" />
     <param name="input_header" type="boolean" checked="false" truevalue="--in-header" falsevalue="" label="Input files contain a header line (as first line)" help="" />
--- a/readme.rst	Thu Sep 05 11:42:27 2013 -0400
+++ b/readme.rst	Thu Sep 05 12:42:48 2013 -0400
@@ -81,6 +81,7 @@
 - move some advanced settings under a conditional, for example the cut tools offers to cut bytes
 - cut wrapper has some output conditional magic for interval files, that needs to be checked
 - comm wrapper, see the Galaxy default one
+- evaluate the join wrappers against the Galaxy ones, maybe we should drop them