upstream-extended/community/tools/text_processing/text_processing/grep.xml
1<tool id="tp_grep_tool" name="Search in textfiles" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
2 <description>(grep)</description>
3 <macros>
4 <import>macros.xml</import>
5 </macros>
6 <expand macro="creator"/>
7 <requirements>
8 <requirement type="package" version="3.11">grep</requirement>
9 <requirement type="package" version="4.9">sed</requirement><!-- for ansi2html.sh -->
10 </requirements>
11 <stdio>
12 <exit_code range="2:" level="fatal" description="grep failed" />
13 </stdio>
14 <version_command>grep --version | head -n 1</version_command>
15 <command>
16<![CDATA[
17 #if str($color) == "COLOR":
18 GREP_COLOR='1;34'
19 grep
20 --color=always
21 $regex_type
22 -A $lines_after
23 -B $lines_before
24 $invert
25 $case_sensitive
26 -- '${url_paste}'
27 '${infile}' | '$__tool_directory__/ansi2html.sh' > '${output}'
28 #else:
29 grep
30 $regex_type
31 -A $lines_after
32 -B $lines_before
33 --no-group-separator
34 $invert
35 $case_sensitive
36 -- '${url_paste}'
37 '${infile}' > '${output}'
38 #end if
39]]>
40 </command>
41 <inputs>
42 <param name="infile" format="txt" type="data" label="Select lines from" />
43
44 <param name="invert" type="select" label="that">
45 <option value="">Match</option>
46 <option value="-v">Don't Match</option>
47 </param>
48
49 <param name="regex_type" type="select" label="Type of regex">
50 <option value="-G">Basic (-G)</option>
51 <option value="-P" selected="true">Perl (-P)</option>
52 <option value="-E">Extended (egrep -E)</option>
53 </param>
54
55 <param name="url_paste" type="text" label="Regular Expression" help="See below for more details">
56 <sanitizer>
57 <valid initial="string.printable">
58 <remove value="'"/>
59 </valid>
60 </sanitizer>
61 </param>
62
63 <param name="case_sensitive" type="select" label="Match type" help="(-i)">
64 <option value="-i">case insensitive</option>
65 <option value="">case sensitive</option>
66 </param>
67 <param name="lines_before" type="integer" value="0"
68 label="Show lines preceding the matched line" help="leave it at zero unless you know what you're doing. (-B)" />
69 <param name="lines_after" type="integer" value="0"
70 label="Show lines trailing the matched line" help="leave it at zero unless you know what you're doing. (-A)" />
71 <param name="color" type="select" label="Output">
72 <option value="NOCOLOR">text file (for further processing)</option>
73 <option value="COLOR">Highlighted HTML (for easier viewing)</option>
74 </param>
75
76 </inputs>
77 <outputs>
78 <data name="output" format_source="infile" metadata_source="infile">
79 <change_format>
80 <when input="color" value="COLOR" format="html"/>
81 </change_format>
82 </data>
83 </outputs>
84 <tests>
85 <!-- grep a FASTA file for sequences with specific motif -->
86 <test>
87 <param name="infile" value="grep1.txt" />
88 <param name="case_sensitive" value="-i" />
89 <param name="regex_type" value="-P" />
90 <param name="invert" value="" />
91 <param name="url_paste" value="AA.{2}GT" />
92 <param name="lines_before" value="1" />
93 <param name="lines_after" value="0" />
94 <param name="color" value="NOCOLOR" />
95 <output name="output" file="grep_results1.txt" />
96 </test>
97 <!-- grep a FASTA file for sequences with specific motif -
98 show highlighed output -->
99 <test>
100 <param name="infile" value="grep1.txt" />
101 <param name="case_sensitive" value="-i" />
102 <param name="regex_type" value="-P" />
103 <param name="invert" value="" />
104 <param name="url_paste" value="AA.{2}GT" />
105 <param name="lines_before" value="0" />
106 <param name="lines_after" value="0" />
107 <param name="color" value="COLOR" />
108 <output name="output" file="grep_results2.html" />
109 </test>
110 <!-- tests egrep -->
111 <test>
112 <param name="infile" value="egrep1.txt" />
113 <param name="case_sensitive" value="-i" />
114 <param name="regex_type" value="-E" />
115 <param name="invert" value="" />
116 <param name="url_paste" value="[^ ]+" />
117 <param name="lines_before" value="0" />
118 <param name="lines_after" value="0" />
119 <param name="color" value="NOCOLOR" />
120 <output name="output" file="egrep_results1.txt" />
121 </test>
122 <!-- tests basic regex; + must be backslashed to match -->
123 <test>
124 <param name="infile" value="egrep1.txt" />
125 <param name="case_sensitive" value="-i" />
126 <param name="regex_type" value="-G" />
127 <param name="invert" value="" />
128 <param name="url_paste" value="[^ ]\+" />
129 <param name="lines_before" value="0" />
130 <param name="lines_after" value="0" />
131 <param name="color" value="NOCOLOR" />
132 <output name="output" file="egrep_results1.txt" />
133 </test>
134 <!-- tests regex;matching nothing -->
135 <test>
136 <param name="infile" value="egrep1.txt" />
137 <param name="case_sensitive" value="-i" />
138 <param name="regex_type" value="-G" />
139 <param name="invert" value="" />
140 <param name="url_paste" value="not existent pattern" />
141 <param name="lines_before" value="0" />
142 <param name="lines_after" value="0" />
143 <param name="color" value="NOCOLOR" />
144 <output name="output">
145 <assert_contents>
146 <has_size value="0"/>
147 </assert_contents>
148 </output>
149 </test>
150 <!-- tests invalid regex; i.e. that we still get exit code 2 -->
151 <test expect_failure="true" expect_exit_code="2">
152 <param name="infile" value="egrep1.txt" />
153 <param name="case_sensitive" value="-i" />
154 <param name="regex_type" value="-G" />
155 <param name="invert" value="" />
156 <param name="url_paste" value="\(" />
157 <param name="lines_before" value="0" />
158 <param name="lines_after" value="0" />
159 <param name="color" value="NOCOLOR" />
160 </test>
161 </tests>
162 <help>
163<![CDATA[
164**What it does**
165
166This tool runs the unix **grep** command on the selected data file.
167
168.. class:: infomark
169
170**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).
171
172
173**Further reading**
174
175- Wikipedia's Regular Expression page (http://en.wikipedia.org/wiki/Regular_expression)
176- Regular Expressions cheat-sheet (PDF) (http://www.addedbytes.com/cheat-sheets/download/regular-expressions-cheat-sheet-v2.pdf)
177- Grep Tutorial (http://www.panix.com/~elflord/unix/grep.html)
178
179-----
180
181**Grep Examples**
182
183- **AGC.AAT** would match lines with AGC followed by any character, followed by AAT (e.g. **AGCQAAT**, **AGCPAAT**, **AGCwAAT**)
184- **C{2,5}AGC** would match lines with 2 to 5 consecutive Cs followed by AGC
185- **TTT.{4,10}AAA** would match lines with 3 Ts, followed by 4 to 10 characters (any characeters), followed by 3 As.
186- **^chr([0-9A-Za-z])+** would match lines that begin with chromsomes, such as lines in a BED format file.
187- **(ACGT){1,5}** would match at least 1 "ACGT" and at most 5 "ACGT" consecutively.
188- **hsa|mmu** would match lines containing "hsa" or "mmu" (or both).
189
190-----
191
192**Regular Expression Syntax**
193
194The 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.
195
196- **( ) { } [ ] . * ? + \ ^ $** are all special characters. **\\** can be used to "escape" a special character, allowing that special character to be searched for.
197- **^** matches the beginning of a string(but not an internal line).
198- **\\d** matches a digit, same as [0-9].
199- **\\D** matches a non-digit.
200- **\\s** matches a whitespace character.
201- **\\S** matches anything BUT a whitespace.
202- **\\t** matches a tab.
203- **\\w** matches an alphanumeric character ( A to Z, 0 to 9 and underscore )
204- **\\W** matches anything but an alphanumeric character.
205- **(** .. **)** groups a particular pattern.
206- **\\Z** matches the end of a string(but not a internal line).
207- **{** n or n, or n,m **}** specifies an expected number of repetitions of the preceding pattern.
208
209 - **{n}** The preceding item is matched exactly n times.
210 - **{n,}** The preceding item ismatched n or more times.
211 - **{n,m}** The preceding item is matched at least n times but not more than m times.
212
213- **[** ... **]** creates a character class. Within the brackets, single characters can be placed. A dash (-) may be used to indicate a range such as **a-z**.
214- **.** Matches any single character except a newline.
215- ***** The preceding item will be matched zero or more times.
216- **?** The preceding item is optional and matched at most once.
217- **+** The preceding item will be matched one or more times.
218- **^** has two meaning:
219 - matches the beginning of a line or string.
220 - indicates negation in a character class. For example, [^...] matches every character except the ones inside brackets.
221- **$** matches the end of a line or string.
222- **\|** Separates alternate possibilities.
223
224]]>
225 </help>
226 <expand macro="citations" />
227</tool>