# HG changeset patch # User bgruening # Date 1378395747 14400 # Node ID a4ad586d1403797e6a848ae166878c0322042905 # Parent ec66f9d90ef0862d30504c410147402b4a165344 Uploaded diff -r ec66f9d90ef0 -r a4ad586d1403 awk.xml --- a/awk.xml Thu Sep 05 04:58:21 2013 -0400 +++ b/awk.xml Thu Sep 05 11:42:27 2013 -0400 @@ -1,5 +1,5 @@ - - + + (awk) gnu_awk @@ -26,15 +26,14 @@ - + $url_paste - + **What it does** @@ -42,7 +41,10 @@ .. class:: infomark -**TIP:** This tool uses the **extended regular** expression syntax (not the perl syntax). +**TIP:** + +This tool uses the **extended regular** expression syntax (not the perl syntax). +**\\d**, **\\w**, **\\s** etc. are **not** supported. **Further reading** @@ -65,8 +67,6 @@ - - **Pattern Examples** - **$2 == "chr3"** will match lines whose second column is the string 'chr3' @@ -87,12 +87,6 @@ - - - - - - **AWK'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. @@ -118,7 +112,5 @@ - **\|** Separates alternate possibilities. -**Note**: AWK uses extended regular expression syntax, not Perl syntax. **\\d**, **\\w**, **\\s** etc. are **not** supported. - - + diff -r ec66f9d90ef0 -r a4ad586d1403 cut.xml --- a/cut.xml Thu Sep 05 04:58:21 2013 -0400 +++ b/cut.xml Thu Sep 05 11:42:27 2013 -0400 @@ -1,10 +1,10 @@ - - columns from files + + columns from a table gnu_coreutils - cut ${complement} ${cutwhat} '${list}' '${input}' > '${output}' + cut -d"${delimiter}" ${complement} ${cut_element} '${list}' '${input}' > '${output}' @@ -14,7 +14,17 @@ - + + + + + + + + + + + @@ -28,27 +38,145 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + - - - - - + + + + - - - - - + + + + - - - **What it does** @@ -68,8 +196,6 @@ **-8** - Cut from the first to the eight field/characters. - - Input Example:: fruit color price weight diff -r ec66f9d90ef0 -r a4ad586d1403 find_and_replace.xml --- a/find_and_replace.xml Thu Sep 05 04:58:21 2013 -0400 +++ b/find_and_replace.xml Thu Sep 05 11:42:27 2013 -0400 @@ -45,7 +45,7 @@ help="Select this option if the first line contains column headers. Text in the line will not be replaced. " /> - + diff -r ec66f9d90ef0 -r a4ad586d1403 grep.xml --- a/grep.xml Thu Sep 05 04:58:21 2013 -0400 +++ b/grep.xml Thu Sep 05 11:42:27 2013 -0400 @@ -6,7 +6,7 @@ UNIX_TOOLS_SCRIPT_PATH - #if $color = "COLOR": + #if $color == "COLOR": GREP_COLOR='1;34' grep --color=always -P "$@" -- "${url_paste}" '${input}' | \$UNIX_TOOLS_SCRIPT_PATH/ansi2html.sh > "${output}" #else: grep -P "$@" -- "${url_paste}" '${input}' | grep -v "^--$" > "${output}" diff -r ec66f9d90ef0 -r a4ad586d1403 head.xml --- a/head.xml Thu Sep 05 04:58:21 2013 -0400 +++ b/head.xml Thu Sep 05 11:42:27 2013 -0400 @@ -8,7 +8,7 @@ - + @@ -27,11 +27,36 @@ + + + + + + + **What it does** -This tool runs the **head** unix command, which discards lines from the end of a file. +This tool outputs specified number of lines from the **beginning** of a dataset + +----- + +**Example** + +Selecting 2 lines from this:: + + chr7 56632 56652 D17003_CTCF_R6 310 + + chr7 56736 56756 D17003_CTCF_R7 354 + + chr7 56761 56781 D17003_CTCF_R4 220 + + chr7 56772 56792 D17003_CTCF_R7 372 + + chr7 56775 56795 D17003_CTCF_R4 207 + + +will produce:: + + chr7 56632 56652 D17003_CTCF_R6 310 + + chr7 56736 56756 D17003_CTCF_R7 354 + + diff -r ec66f9d90ef0 -r a4ad586d1403 multijoin.xml --- a/multijoin.xml Thu Sep 05 04:58:21 2013 -0400 +++ b/multijoin.xml Thu Sep 05 11:42:27 2013 -0400 @@ -14,7 +14,7 @@ - + @@ -43,7 +43,7 @@ - + diff -r ec66f9d90ef0 -r a4ad586d1403 readme.rst --- a/readme.rst Thu Sep 05 04:58:21 2013 -0400 +++ b/readme.rst Thu Sep 05 11:42:27 2013 -0400 @@ -79,6 +79,8 @@ - also shuf will get a major improved performance with large files http://git.savannah.gnu.org/gitweb/?p=coreutils.git;a=commit;h=20d7bce0f7e57d9a98f0ee811e31c757e9fedfff we can remove the random feature from sort and use shuf instead - 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 diff -r ec66f9d90ef0 -r a4ad586d1403 sed.xml --- a/sed.xml Thu Sep 05 04:58:21 2013 -0400 +++ b/sed.xml Thu Sep 05 11:42:27 2013 -0400 @@ -3,24 +3,38 @@ gnu_sed - - sed --sandbox -r $silent -f '$sed_script' '$input' > '$output' - - - + + sed --sandbox -r + + #if $adv_opts.adv_opts_selector == 'advanced': + $adv_opts.silent + #end if + -f '$sed_script' '$input' > '$output' + + + - - - - - - - + + + + + + + - - - - + + + + + + + + + + + + + diff -r ec66f9d90ef0 -r a4ad586d1403 sort.xml --- a/sort.xml Thu Sep 05 04:58:21 2013 -0400 +++ b/sort.xml Thu Sep 05 11:42:27 2013 -0400 @@ -1,4 +1,5 @@ + data in ascending or descending order gnu_coreutils gnu_sed @@ -25,16 +26,11 @@ - + - - - - - + @@ -49,12 +45,46 @@ + + + + + - - + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + **What it does** diff -r ec66f9d90ef0 -r a4ad586d1403 sorted_uniq.xml --- a/sorted_uniq.xml Thu Sep 05 04:58:21 2013 -0400 +++ b/sorted_uniq.xml Thu Sep 05 11:42:27 2013 -0400 @@ -1,7 +1,8 @@ - from sorted file + assuming sorted input file gnu_coreutils + gnu_sed uniq @@ -15,17 +16,23 @@ ## feature is not yet released, it will be in the next 8.22 version ##--group=$group + + #if $count: + # count will print the count with spaces infrontof the line and + # with a space (not a tab) after the number, we need to cahnge that + | sed -e 's/ *//' -e 's/ /\t/' > $output + #end if > $output - + - - - - - + + + + +