changeset 2:8fd5091a4091 default tip

commit

--- a/awk.xml	Sun Oct 19 15:07:18 2014 +0900
+++ b/awk.xml	Sun Oct 19 17:20:13 2014 +0900
@@ -1,5 +1,5 @@
 <!--
-  This tool is based on 'cshl_awk_tool' from Hannon Lab CSHL
+  This tool is based on 'cshl_awk_tool' from Hannon Lab, CSHL:
   http://hannonlab.cshl.edu/galaxy_unix_tools/
   Thanks. Pitagora
 -->

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/sed.xml	Sun Oct 19 17:20:13 2014 +0900
@@ -0,0 +1,104 @@
+<!--
+  This tool is based on 'cshl_sed_tool' from Hannon Lab, CSHL:
+  http://hannonlab.cshl.edu/galaxy_unix_tools/
+  Thanks. Pitagora
+-->
+<tool id="sed" name="sed">
+  <description></description>
+  <!-- NOTE
+  	  'sandbox' is a patched SED program,
+	  which blocks executing shell commands and file reading/writing.
+
+	  Hopefully, it is safe enough to allow users to execute their own SED commands
+	  -->
+  <command interpreter="sh">sed_wrapper.sh $silent $input $output '$url_paste'</command>
+  <inputs>
+    <param format="txt" name="input" type="data" label="File to process" />
+
+    <!-- Note: the parameter nane MUST BE 'url_paste' -
+         This is a hack in the galaxy library (see ./lib/galaxy/util/__init__.py line 142)
+	 If the name is 'url_paste' the string won't be sanitized, and all the non-alphanumeric characters 
+	 will be passed to the shell script -->
+    <param name="url_paste" type="text" area="true" size="5x35" label="SED Program" help="">
+      <sanitizer>
+		<valid initial="string.printable">
+		  <remove value="&apos;"/>
+		</valid>
+		<mapping initial="none">
+		  <add source="&apos;" target="__sq__"/>
+		</mapping>
+	  </sanitizer>
+    </param>
+
+    <param name="silent" type="select"  label="operation mode" help="(Same as 'sed -n', leave at 'normal' unless you know what you're doing)" > 
+      <option value="">normal</option>
+      <option value="-n">silent</option>
+    </param>
+
+  </inputs>
+  <outputs>
+    <data format="input" name="output" metadata_source="input" />
+  </outputs>
+<help>
+
+**What it does**
+
+This tool runs the unix **sed** command on the selected data file.
+
+.. class:: infomark
+
+**TIP:** This tool uses the **extended regular** expression syntax (same as running 'sed -r').
+
+
+
+**Further reading**
+
+- Short sed tutorial (http://www.linuxhowtos.org/System/sed_tutorial.htm)
+- Long sed tutorial (http://www.grymoire.com/Unix/Sed.html)
+- sed faq with good examples (http://sed.sourceforge.net/sedfaq.html)
+- sed cheat-sheet (http://www.catonmat.net/download/sed.stream.editor.cheat.sheet.pdf)
+- Collection of useful sed one-liners (http://student.northpark.edu/pemente/sed/sed1line.txt)
+
+-----
+
+**Sed commands**
+
+The most useful sed command is **s** (substitute).
+
+**Examples**
+
+- **s/hsa//**  will remove the first instance of 'hsa' in every line.
+- **s/hsa//g**  will remove all instances (beacuse of the **g**) of 'hsa' in every line.
+- **s/A{4,}/--&amp;--/g**  will find sequences of 4 or more consecutive A's, and once found, will surround them with two dashes from each side. The **&amp;** marker is a place holder for 'whatever matched the regular expression'.
+- **s/hsa-mir-([^ ]+)/short name: \\1 full name: &amp;/**  will find strings such as 'hsa-mir-43a' (the regular expression is 'hsa-mir-' followed by non-space characters) and will replace it will string such as 'short name: 43a full name: hsa-mir-43a'.  The **\\1** marker is a place holder for 'whatever matched the first parenthesis' (similar to perl's **$1**) .
+
+
+**sed's Regular Expression Syntax**
+
+The select tool searches the data for lines containing or not containing a match to the given pattern. A Regular Expression is a pattern descibing a certain amount of text. 
+
+- **( ) { } [ ] . * ? + \ ^ $** are all special characters. **\\** can be used to "escape" a special character, allowing that special character to be searched for.
+- **^** matches the beginning of a string(but not an internal line).
+- **(** .. **)** groups a particular pattern.
+- **{** n or n, or n,m **}** specifies an expected number of repetitions of the preceding pattern.
+
+  - **{n}** The preceding item is matched exactly n times.
+  - **{n,}** The preceding item ismatched n or more times. 
+  - **{n,m}** The preceding item is matched at least n times but not more than m times. 
+
+- **[** ... **]** creates a character class. Within the brackets, single characters can be placed. A dash (-) may be used to indicate a range such as **a-z**.
+- **.** Matches any single character except a newline.
+- ***** The preceding item will be matched zero or more times.
+- **?** The preceding item is optional and matched at most once.
+- **+** The preceding item will be matched one or more times.
+- **^** has two meaning:
+  - matches the beginning of a line or string. 
+  - indicates negation in a character class. For example, [^...] matches every character except the ones inside brackets.
+- **$** matches the end of a line or string.
+- **\|** Separates alternate possibilities. 
+
+
+**Note**: SED uses extended regular expression syntax, not Perl syntax. **\\d**, **\\w**, **\\s** etc. are **not** supported.
+
+</help>
+</tool>

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/sed_wrapper.sh	Sun Oct 19 17:20:13 2014 +0900
@@ -0,0 +1,38 @@
+#!/bin/sh
+
+##
+## Galaxy wrapper for SED command
+##
+
+##
+## command line arguments:
+##   input_file
+##   output_file
+##   sed-program
+##   [other parameters passed on to sed]
+
+INPUT="$1"
+OUTPUT="$2"
+PROG="$3"
+
+shift 3
+
+if [ -z "$PROG" ]; then
+	echo usage: $0 INPUTFILE OUTPUTFILE SED-PROGRAM [other sed patameters] >&2
+	exit 1
+fi
+
+if [ ! -r "$INPUT" ]; then
+	echo "error: input file ($INPUT) not found!" >&2
+	exit 1
+fi
+
+# Messages printed to STDOUT will be displayed in the "INFO" field in the galaxy dataset.
+# This way the user can tell what was the command
+echo "sed" "$@" "$PROG"
+
+#$GALAXY_TOOLS/sed/sed/sed -r --sandbox "$@" "$PROG" "$INPUT" > "$OUTPUT"
+sed -r "$@" "$PROG" "$INPUT" > "$OUTPUT"
+if (( $? ));  then exit; fi
+
+exit 0