--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tools/unix_tools/grep_tool.xml	Fri Mar 09 19:37:19 2012 -0500
@@ -0,0 +1,130 @@
+<tool id="cshl_grep_tool" name="grep">
+  <description></description>
+  <command interpreter="sh">grep_wrapper.sh $input $output '$url_paste' $color -A $lines_after -B $lines_before $invert $case_sensitive</command>
+  <inputs>
+    <param format="txt" name="input" type="data" label="Select lines from" />
+
+    <param name="invert" type="select" label="that">
+      <option value="">Match</option>
+      <option value="-v">Don't Match</option>
+    </param>
+
+    <!-- Note: the parameter ane 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" size="40" label="Regular Expression" help=""> 
+    	<validator type="expression" message="Invalid Program!">value.find('\'')==-1</validator>
+    </param>
+
+    <param name="case_sensitive" type="select"  label="Match type"> 
+      <option value="-i">case insensitive</option>
+      <option value="">case sensitive</option>
+    </param>
+
+    <param name="lines_before" type="integer"  label="Show lines preceding the matched line" help="(same as grep -B, leave it at zero unless you know what you're doing)" value="0" /> 
+    <param name="lines_after" type="integer"  label="Show lines trailing the matched line" help="(same as grep -A, leave it at zero unless you know what you're doing)" value="0" /> 
+
+    <param name="color" type="select"  label="Output"> 
+      <option value="NOCOLOR">text file (for further processing)</option>
+      <option value="COLOR">Highlighted HTML (for easier viewing)</option>
+    </param>
+
+  </inputs>
+  <tests>
+	  <test>
+		  <!-- grep a FASTA file for sequences with specific motif -->
+		  <param name="input" value="unix_grep_input1.txt" />
+		  <output name="output" file="unix_grep_output1.txt" />
+		  <param name="case_sensitive" value="case sensitive" />
+		  <param name="invert" value="" />
+		  <param name="url_paste" value="AA.{2}GT" />
+		  <param name="lines_before" value="1" />
+		  <param name="lines_after" value="0" />
+		  <param name="color" value="NOCOLOR" />
+	  </test>
+	  <test>
+		  <!-- grep a FASTA file for sequences with specific motif -
+		 	show highlighed output -->
+		  <param name="input" value="unix_grep_input1.txt" />
+		  <output name="output" file="unix_grep_output2.html" />
+		  <param name="case_sensitive" value="case sensitive" />
+		  <param name="invert" value="" />
+		  <param name="url_paste" value="AA.{2}GT" />
+		  <param name="lines_before" value="0" />
+		  <param name="lines_after" value="0" />
+		  <param name="color" value="COLOR" />
+	  </test>
+  </tests>
+  <outputs>
+	  <data format="input" name="output" metadata_source="input" >
+		<change_format>
+			<when input="color" value="COLOR" format="HTML" />
+		</change_format>
+ 	  </data>
+  </outputs>
+<help>
+
+**What it does**
+
+This tool runs the unix **grep** command on the selected data file.
+
+.. class:: infomark
+
+**TIP:** This tool uses the **perl** regular expression syntax (same as running 'grep -P'). This is **NOT** the POSIX or POSIX-extended syntax (unlike the awk/sed tools).
+
+
+**Further reading**
+
+- Wikipedia's Regular Expression page (http://en.wikipedia.org/wiki/Regular_expression)
+- Regular Expressions cheat-sheet (PDF) (http://www.addedbytes.com/cheat-sheets/download/regular-expressions-cheat-sheet-v2.pdf)
+- Grep Tutorial (http://www.panix.com/~elflord/unix/grep.html)
+
+-----
+
+**Grep Examples**
+
+- **AGC.AAT** would match lines with AGC followed by any character, followed by AAT (e.g. **AGCQAAT**, **AGCPAAT**, **AGCwAAT**)
+- **C{2,5}AGC** would match lines with 2 to 5 consecutive Cs followed by AGC
+- **TTT.{4,10}AAA** would match lines with 3 Ts, followed by 4 to 10 characters (any characeters), followed by 3 As.
+- **^chr([0-9A-Za-z])+** would match lines that begin with chromsomes, such as lines in a BED format file.
+- **(ACGT){1,5}** would match at least 1 "ACGT" and at most 5 "ACGT" consecutively.
+- **hsa|mmu** would match lines containing "hsa" or "mmu" (or both).
+ 
+-----
+
+**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. 
+
+- **( ) { } [ ] . * ? + \ ^ $** are all special characters. **\\** can be used to "escape" a special character, allowing that special character to be searched for.
+- **^** matches the beginning of a string(but not an internal line).
+- **\\d** matches a digit, same as [0-9].
+- **\\D** matches a non-digit.
+- **\\s** matches a whitespace character.
+- **\\S** matches anything BUT a whitespace.
+- **\\t** matches a tab.
+- **\\w** matches an alphanumeric character ( A to Z, 0 to 9 and underscore )
+- **\\W** matches anything but an alphanumeric character.
+- **(** .. **)** groups a particular pattern.
+- **\\Z** matches the end of a string(but not a internal line).
+- **{** n or n, or n,m **}** specifies an expected number of repetitions of the preceding pattern.
+
+  - **{n}** The preceding item is matched exactly n times.
+  - **{n,}** The preceding item ismatched n or more times. 
+  - **{n,m}** The preceding item is matched at least n times but not more than m times. 
+
+- **[** ... **]** creates a character class. Within the brackets, single characters can be placed. A dash (-) may be used to indicate a range such as **a-z**.
+- **.** Matches any single character except a newline.
+- ***** The preceding item will be matched zero or more times.
+- **?** The preceding item is optional and matched at most once.
+- **+** The preceding item will be matched one or more times.
+- **^** has two meaning:
+  - matches the beginning of a line or string. 
+  - indicates negation in a character class. For example, [^...] matches every character except the ones inside brackets.
+- **$** matches the end of a line or string.
+- **\|** Separates alternate possibilities. 
+
+
+</help>
+</tool>