Mercurial > repos > bgruening > text_processing
diff grep.xml @ 0:5314e5d6f040 draft
Imported from capsule None
author | bgruening |
---|---|
date | Thu, 29 Jan 2015 07:53:17 -0500 |
parents | |
children | 43b1f073b693 |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/grep.xml Thu Jan 29 07:53:17 2015 -0500 @@ -0,0 +1,165 @@ +<tool id="tp_grep_tool" name="Search in textfiles" version="@BASE_VERSION@.0"> + <description>(grep)</description> + <macros> + <import>macros.xml</import> + </macros> + <expand macro="requirements"> + <requirement type="package" version="2.14">gnu_grep</requirement> + <requirement type="set_environment">TP_SCRIPT_PATH</requirement> + </expand> + <version_command>grep --version | head -n 1</version_command> + <command> +<![CDATA[ + #if str($color) == "COLOR": + GREP_COLOR='1;34' + grep + --color=always + -P + -A $lines_after + -B $lines_before + $invert + $case_sensitive + -- "${url_paste}" + '${infile}' | \$TP_SCRIPT_PATH/ansi2html.sh > "${output}" + #else: + grep + -P + -A $lines_after + -B $lines_before + $invert + $case_sensitive + -- "${url_paste}" + '${infile}' | grep -v "^--$" > "${output}" + #end if + + ##grep_wrapper.sh '$infile' '$output' '$url_paste' $color -A $lines_after -B $lines_before $invert $case_sensitive +]]> + </command> + <inputs> + <param name="infile" format="txt" 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> + + <param name="url_paste" type="text" size="40" label="Regular Expression" help="See below for more details"> + <sanitizer> + <valid initial="string.printable"> + <remove value="'"/> + </valid> + </sanitizer> + </param> + + <param name="case_sensitive" type="select" label="Match type" help="(-i)"> + <option value="-i">case insensitive</option> + <option value="">case sensitive</option> + </param> + <param name="lines_before" type="integer" value="0" + label="Show lines preceding the matched line" help="leave it at zero unless you know what you're doing. (-B)" /> + <param name="lines_after" type="integer" value="0" + label="Show lines trailing the matched line" help="leave it at zero unless you know what you're doing. (-A)" /> + <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> + <outputs> + <data name="output" format_source="infile" metadata_source="infile"> + <change_format> + <when input="color" value="COLOR" format="html"/> + </change_format> + </data> + </outputs> + <tests> + <test> + <!-- grep a FASTA file for sequences with specific motif --> + <param name="infile" value="grep1.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" /> + <output name="output" file="grep_results1.txt" /> + </test> + <test> + <!-- grep a FASTA file for sequences with specific motif - + show highlighed output --> + <param name="infile" value="grep1.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="0" /> + <param name="lines_after" value="0" /> + <param name="color" value="COLOR" /> + <output name="output" file="grep_results2.html" /> + </test> + </tests> + <help> +<![CDATA[ +**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. + +@REFERENCES@ +]]> + </help> +</tool>