return most recent genome build for the pipeline config file.

[htsworkflow.git] / gaworkflow / util / alphanum.py

diff --git a/gaworkflow/util/alphanum.py b/gaworkflow/util/alphanum.py
new file mode 100644 (file)
index 0000000..8893bdb
--- /dev/null
+++ b/gaworkflow/util/alphanum.py
@@ -0,0 +1,61 @@
+#\r
+# The Alphanum Algorithm is an improved sorting algorithm for strings\r
+# containing numbers.  Instead of sorting numbers in ASCII order like\r
+# a standard sort, this algorithm sorts numbers in numeric order.\r
+#\r
+# The Alphanum Algorithm is discussed at http://www.DaveKoelle.com\r
+#\r
+#* Python implementation provided by Chris Hulan (chris.hulan@gmail.com)\r
+#* Distributed under same license as original\r
+#\r
+# This library is free software; you can redistribute it and/or\r
+# modify it under the terms of the GNU Lesser General Public\r
+# License as published by the Free Software Foundation; either\r
+# version 2.1 of the License, or any later version.\r
+#\r
+# This library is distributed in the hope that it will be useful,\r
+# but WITHOUT ANY WARRANTY; without even the implied warranty of\r
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU\r
+# Lesser General Public License for more details.\r
+#\r
+# You should have received a copy of the GNU Lesser General Public\r
+# License along with this library; if not, write to the Free Software\r
+# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301  USA\r
+#\r
+\r
+import re\r
+\r
+#\r
+# TODO: Make decimal points be considered in the same class as digits\r
+#\r
+\r
+def chunkify(str):\r
+       """return a list of numbers and non-numeric substrings of +str+\r
+\r
+       the numeric substrings are converted to integer, non-numeric are left as is\r
+       """\r
+       chunks = re.findall("(\d+|\D+)",str)\r
+       chunks = [re.match('\d',x) and int(x) or x for x in chunks] #convert numeric strings to numbers\r
+       return chunks\r
+\r
+def alphanum(a,b):\r
+       """breaks +a+ and +b+ into pieces and returns left-to-right comparison of the pieces\r
+\r
+       +a+ and +b+ are expected to be strings (for example file names) with numbers and non-numeric characters\r
+       Split the values into list of numbers and non numeric sub-strings and so comparison of numbers gives\r
+       Numeric sorting, comparison of non-numeric gives Lexicographic order\r
+       """\r
+       # split strings into chunks\r
+       aChunks = chunkify(a)\r
+       bChunks = chunkify(b)\r
+\r
+       return cmp(aChunks,bChunks) #built in comparison works once data is prepared\r
+\r
+\r
+\r
+if __name__ == "__main__":\r
+       unsorted = ["1000X Radonius Maximus","10X Radonius","200X Radonius","20X Radonius","20X Radonius Prime","30X Radonius","40X Radonius","Allegia 50 Clasteron","Allegia 500 Clasteron","Allegia 51 Clasteron","Allegia 51B Clasteron","Allegia 52 Clasteron","Allegia 60 Clasteron","Alpha 100","Alpha 2","Alpha 200","Alpha 2A","Alpha 2A-8000","Alpha 2A-900","Callisto Morphamax","Callisto Morphamax 500","Callisto Morphamax 5000","Callisto Morphamax 600","Callisto Morphamax 700","Callisto Morphamax 7000","Callisto Morphamax 7000 SE","Callisto Morphamax 7000 SE2","QRS-60 Intrinsia Machine","QRS-60F Intrinsia Machine","QRS-62 Intrinsia Machine","QRS-62F Intrinsia Machine","Xiph Xlater 10000","Xiph Xlater 2000","Xiph Xlater 300","Xiph Xlater 40","Xiph Xlater 5","Xiph Xlater 50","Xiph Xlater 500","Xiph Xlater 5000","Xiph Xlater 58"]\r
+       sorted = unsorted[:]\r
+       sorted.sort(alphanum)\r
+       print '+++++Sorted...++++'\r
+       print '\n'.join(sorted)\r