rbbt-util 3.2.0 → 3.2.1

data/lib/rbbt/util/tsv/manipulate.rb

@@ -119,22 +119,19 @@ class TSV
       new_fields    = options[:new_fields]
 
       new = {}
-      new_key_field, new_fields = through new_key_field, new_fields do |key, values|
-        if Array === key
-          keys = key
-        else
-          keys = [key]
-        end
-
-        new_values = keys.each do |key|
-          if new[key].nil?
-            new[key] = values
-          else
-            if type == :double
-              new[key] = new[key].zip(values).collect{|v| v.flatten}
+      new_key_field, new_fields = through new_key_field, new_fields do |keys, values|
+        if Array === keys
+          keys.each do |key|
+            if new[key].nil? or not type == :double
+              new[key] = values.collect{|l| l.dup}
+            else
+              new[key] = new[key].zip(values).collect{|old_list, new_list| old_list.concat new_list}
             end
           end
+        else
+          new[keys] = values
         end
+        nil
       end
 
       new = TSV.new new

data/lib/rbbt/util/tsv/parse.rb

@@ -318,7 +318,7 @@ class TSV
 
     fields = nil if Fixnum === fields or (Array === fields and fields.select{|f| Fixnum === f}.any?)
     fields ||= other_fields
-    [data, {:key_field => key_field, :fields => fields, :type => type, :case_insensitive => case_insensitive, :namespace => namespace, :datadir => options[:datadir], :identifiers => options[:identifiers], :cast => (cast.nil? ? false : cast)}]
+    [data, {:key_field => key_field, :fields => fields, :type => type, :case_insensitive => case_insensitive, :namespace => namespace, :identifiers => options[:identifiers], :cast => (cast.nil? ? false : cast)}]
   end
 
 end

data/lib/rbbt/util/tsv/resource.rb

@@ -26,6 +26,14 @@ module Resource
       TSV.index self, options
     end
 
+    def pos_index(pos_field, options = {})
+      TSV.pos_index self, pos_field, options
+    end
+
+    def range_index(start_field, end_field, options = {})
+      TSV.range_index self, start_field, end_field, options
+    end
+
     def open(options = {})
       produce
       Open.open(self.find, options)

data/lib/rbbt/util/workflow.rb

@@ -5,12 +5,29 @@ require 'rbbt/util/misc'
 
 module WorkFlow
 
-  def self.require_workflow(path)
-    if Rbbt.etc.workflow_dir.exists?
-      require Dir.glob(File.join(Rbbt.etc.workflow_dir.read.strip, '*', path + '.rb')).first
-    else
-      require Dir.glob(File.join(Rbbt.share.workflows.find, '*', path + '.rb')).first
+  def self.require_workflow(wf_name, wf_dir = nil)
+
+    if File.exists? wf_name
+      require "./workflow.rb"
+      return
     end
+
+    wf_dir ||= case
+               when File.exists?(File.join(File.dirname(Resource.caller_lib_dir), wf_name))
+                 File.join(File.dirname(Resource.caller_lib_dir), wf_name)
+               when defined? Rbbt
+                 if Rbbt.pkg.etc.workflow_dir.exists?
+                   File.join(pkg.etc.workflow_dir.read.strip, wf_name)
+                 else
+                   Rbbt.workflows[wf_name]
+                 end
+               else
+                 File.join(ENV["HOME"], '.workflows')
+               end
+
+    wf_dir = Resource::Path.path(wf_dir)
+    $LOAD_PATH.unshift(File.join(File.dirname(wf_dir["workflow.rb"].find), 'lib'))
+    require wf_dir["workflow.rb"].find
   end
 
   def self.extended(base)
@@ -74,9 +91,9 @@ module WorkFlow
   def process_dangling
     res = [ 
       @dangling_options, 
-      Hash[*@dangling_options.zip(@dangling_option_descriptions.values_at(*@dangling_options)).flatten],
-      Hash[*@dangling_options.zip(@dangling_option_types.values_at(*@dangling_options)).flatten],
-      Hash[*@dangling_options.zip(@dangling_option_defaults.values_at(*@dangling_options)).flatten],
+      Misc.merge2hash(@dangling_options, @dangling_option_descriptions.values_at(*@dangling_options)),
+      Misc.merge2hash(@dangling_options, @dangling_option_types.values_at(*@dangling_options)),
+      Misc.merge2hash(@dangling_options, @dangling_option_defaults.values_at(*@dangling_options)),
       (@dangling_dependencies || [@last_task]).compact,
       @dangling_description,
     ]
@@ -103,6 +120,7 @@ module WorkFlow
   end
 
   def job(task, jobname = "Default", *args)
+    raise "Task '#{ task }' unkown" if tasks[task].nil?
     tasks[task].job(jobname, *args)
   end
 

data/share/lib/R/util.R

@@ -26,7 +26,7 @@ rbbt.load.data <- function(filename, sep = "\t",  ...){
 }
 
 rbbt.tsv <- function(filename, sep = "\t", comment.char ="#", row.names=1,  ...){
-  data=read.table(file=filename, sep=sep, fill=TRUE,  as.is=TRUE, row.names= row.names, comment.char = comment.char, ...);
+  data=read.table(file=filename, sep=sep, fill=TRUE,  as.is=TRUE, quote='', row.names= row.names, comment.char = comment.char, ...);
   f = file(filename, 'r');
   headers = readLines(f, 1);
   if (length(grep("^#: ", headers)) > 0){ 
@@ -139,3 +139,73 @@ rbbt.run <- function(filename){
 }
 
 
+# UTILITIES
+
+# Addapted from http://www.phaget4.org/R/image_matrix.html
+rbbt.plot.matrix <- function(x, ...){
+    min <- min(x);
+    max <- max(x);
+    yLabels <- rownames(x);
+    xLabels <- colnames(x);
+    title <-c();
+# check for additional function arguments
+    if( length(list(...)) ){
+        Lst <- list(...);
+        if( !is.null(Lst$zlim) ){
+            min <- Lst$zlim[1];
+            max <- Lst$zlim[2];
+        }
+        if( !is.null(Lst$yLabels) ){
+            yLabels <- c(Lst$yLabels);
+        }
+        if( !is.null(Lst$xLabels) ){
+            xLabels <- c(Lst$xLabels);
+        }
+        if( !is.null(Lst$title) ){
+            title <- Lst$title;
+        }
+    }
+# check for null values
+    if( is.null(xLabels) ){
+        xLabels <- c(1:ncol(x));
+    }
+    if( is.null(yLabels) ){
+        yLabels <- c(1:nrow(x));
+    }
+
+    layout(matrix(data=c(1,2), nrow=1, ncol=2), widths=c(4,1), heights=c(1,1));
+
+# Red and green range from 0 to 1 while Blue ranges from 1 to 0
+    ColorRamp <- rgb( seq(0,1,length=256),  # Red
+                      seq(0,1,length=256),  # Green
+                      seq(1,0,length=256))  # Blue
+        ColorLevels <- seq(min, max, length=length(ColorRamp));
+
+# Reverse Y axis
+    reverse <- nrow(x) : 1;
+    yLabels <- yLabels[reverse];
+    x <- x[reverse,];
+
+# Data Map
+    par(mar = c(3,5,2.5,2));
+    image(1:length(xLabels), 1:length(yLabels), t(x), col=ColorRamp, xlab="",
+          ylab="", axes=FALSE, zlim=c(min,max));
+    if( !is.null(title) ){
+        title(main=title);
+    }
+    axis(BELOW<-1, at=1:length(xLabels), labels=xLabels, cex.axis=0.7);
+    axis(LEFT <-2, at=1:length(yLabels), labels=yLabels, las= HORIZONTAL<-1,
+         cex.axis=0.7);
+
+# Color Scale
+    par(mar = c(3,2.5,2.5,2));
+    image(1, ColorLevels,
+          matrix(data=ColorLevels, ncol=length(ColorLevels),nrow=1),
+          col=ColorRamp,
+          xlab="",ylab="",
+          xaxt="n");
+
+    layout(1);
+}
+
+

data/test/rbbt/util/test_misc.rb

@@ -142,4 +142,21 @@ This is an example file. Entries are separated by Entry
     assert_equal [1,2,3,4], Misc.merge_sorted_arrays([1,3], [2,4])
   end
 
+  def test_intersect_sorted_arrays
+    assert_equal [2,4], Misc.intersect_sorted_arrays([1,2,3,4], [2,4])
+  end
+
+
+  def test_in_dir
+    TmpFile.with_file do |dir|
+      FileUtils.mkdir_p dir
+      Open.write(File.join(dir, 'test_file_in_dir'), 'test_file_in_dir')
+      Misc.in_dir(dir) do
+        assert Dir.glob("*").include? 'test_file_in_dir'
+      end
+      assert Dir.glob(File.join(dir, "*")).include?(File.join(dir, 'test_file_in_dir'))
+      assert(! Dir.glob("*").include?('test_file_in_dir'))
+    end
+  end
+
 end

data/test/rbbt/util/test_persistence.rb

@@ -164,6 +164,38 @@ row2   2 4 6 8
     Process.wait pid
   end
 
+  def test_persist_fwt
+    content =<<-EOF
+#: :sep=/\\s+/
+#Id    Start    End
+row1   1        10
+row2   20       30
+    EOF
+
+    TmpFile.with_file(content) do |filename|
+      fwt = Persistence.persist(filename, :Range, :fwt, :persistence_dir => Rbbt.tmp.test.persistence) do
+        fwt = TSV.new(filename).range_index("Start", "End", :persistence => false)
+        assert fwt[15].empty?
+        assert fwt[25].include? "row2"
+        fwt
+      end
+
+      assert fwt[5].include? "row1"
+      assert fwt[(5..25)].include? "row1"
+      assert fwt[(5..25)].include? "row2"
+
+      fwt = Persistence.persist(filename, :Range, :fwt, :persistence_dir => Rbbt.tmp.test.persistence) do
+        assert false
+      end
+
+      assert fwt[5].include? "row1"
+      assert fwt[(5..25)].include? "row1"
+      assert fwt[(5..25)].include? "row2"
+ 
+    end
+
+  end
+
 
 end
 

data/test/rbbt/util/test_resource.rb

@@ -67,6 +67,7 @@ class TestResource < Test::Unit::TestCase
     begin
       assert_equal "Test String", Rbbt.tmp.test_string.read
       assert_equal "Test String", Rbbt.tmp.work.foo.read
+    rescue
     ensure
       FileUtils.rm Rbbt.tmp.test_string.find if File.exists? Rbbt.tmp.test_string.find
       FileUtils.rm Rbbt.tmp.url.find if File.exists? Rbbt.tmp.url.find

data/test/rbbt/util/test_task.rb

@@ -37,6 +37,20 @@ class TestTask < Test::Unit::TestCase
     end
   end
 
+  def test_task_options_from_hash
+    TmpFile.with_file do |f|
+      task = Task.new(:test_task, nil, :name) do |name| Open.write(f, name) end
+      job = task.job(:job1, :name => "TestName")
+      assert_equal "job1" << "_" << Misc.hash2md5(:name => "TestName"), job.id
+      job.fork
+      job.join
+
+      assert File.exists? f
+      assert_equal "TestName", File.open(f).read
+    end
+  end
+
+
   def test_task_result
     task = Task.new(:test_task, nil, :name) do |name| name end
     job = task.job(:job1, "TestName")

data/test/rbbt/util/test_tc_hash.rb

@@ -54,6 +54,22 @@ class TestTCHash < Test::Unit::TestCase
     end
   end
 
+  def test_stringDoubleArraySerializer
+    TmpFile.with_file do |f|
+      t = TCHash.get f, true, TCHash::TSVSerializer
+      tsv = TSV.new({})
+      tsv["1"] = [[1],[2]]
+      tsv["2"] = [[3],[4,5]]
+      t["TSV"] = tsv
+
+      t = TCHash.get f
+      t.collect do |k,v| 
+       assert_equal [["3"],["4","5"]], t["TSV"]["2"]
+      end
+    end
+  end
+
+ 
   def test_serializer_alias
     TmpFile.with_file do |f|
       t = TCHash.get f, true, :double

data/test/rbbt/util/tsv/test_accessor.rb

@@ -146,6 +146,5 @@ row2 A B C
     end
   end
 
-
 end
 

data/test/rbbt/util/tsv/test_filters.rb

@@ -135,7 +135,33 @@ row2    A    B
     end
   end
 
+  def test_delete
+    content =<<-EOF
+#ID ValueA ValueB Comment
+row1 a b c
+row2 A B C
+    EOF
+
+    TmpFile.with_file(content) do |filename|
+      tsv = TSV.new(File.open(filename), :double, :sep => /\s/)
+      assert_equal 2, tsv.keys.length
+      tsv.delete "row2"
+      assert_equal 1, tsv.keys.length
+
+      tsv = TSV.new(File.open(filename), :double, :sep => /\s/)
+      tsv.filter
+      tsv.add_filter "field:ValueA", ["A"]
 
+      assert_equal 1, tsv.keys.length
+      assert_equal ["row2"], tsv.keys
+
+      tsv.delete "row2"
+      assert_equal 0, tsv.keys.length
+
+      tsv.pop_filter
+      assert_equal ["row1"], tsv.keys
+    end
+  end
 
 end
 

data/test/rbbt/util/tsv/test_index.rb

@@ -128,7 +128,39 @@ row2    A    B
     tsv
   end
 
-  def test_sorted_index
+  def test_pos_index
+    content =<<-EOF
+#Id	ValueA    ValueB    Pos
+row1    a|aa|aaa    b    0|10
+row2    A    B    30
+    EOF
+
+    TmpFile.with_file(content) do |filename|
+      tsv = TSV.new(File.open(filename), :double, :sep => /\s+/)
+      index = tsv.pos_index("Pos")
+      assert_equal ["row1"], index[10]
+    end
+  end
+
+
+  def test_range_index
+    content =<<-EOF
+#Id	ValueA    ValueB    Pos1    Pos2
+row1    a|aa|aaa    b    0|10    10|30
+row2    A    B    30   35
+    EOF
+
+    TmpFile.with_file(content) do |filename|
+      tsv = TSV.new(File.open(filename), :double, :sep => /\s+/)
+      index = tsv.pos_index("Pos1")
+      assert_equal ["row1"], index[10]
+
+      index = tsv.range_index("Pos1", "Pos2")
+      assert_equal ["row1"], index[20]
+    end
+  end
+
+  def test_range_index2
     data =<<-EOF
 #ID:Range
 #:012345678901234567890
@@ -142,7 +174,7 @@ g:         ____
     EOF
     TmpFile.with_file(data) do |datafile|
       tsv = load_data(datafile)
-      f   = tsv.sorted_index
+      f   = tsv.range_index("Start", "End")
 
       assert_equal %w(), f[0].sort
       assert_equal %w(b), f[1].sort
@@ -153,35 +185,55 @@ g:         ____
     end
   end
 
-  def test_pos_index
-    content =<<-EOF
-#Id	ValueA    ValueB    Pos
-row1    a|aa|aaa    b    0|10
-row2    A    B    30
+  def test_range_index_persistent
+    data =<<-EOF
+#ID:Range
+#:012345678901234567890
+a:   ______
+b: ______
+c:    _______
+d:  ____
+e:    ______
+f:             ___
+g:         ____
     EOF
-
-    TmpFile.with_file(content) do |filename|
-      tsv = TSV.new(File.open(filename), :double, :sep => /\s+/)
-      index = tsv.pos_index("Pos", :memory, true)
-      assert_equal ["row1"], index[10]
+    TmpFile.with_file(data) do |datafile|
+      TmpFile.with_file(load_data(datafile)) do |tsvfile|
+        f = TSV.range_index(tsvfile, "Start", "End", :persistence => true)
+
+        assert_equal %w(), f[0].sort
+        assert_equal %w(b), f[1].sort
+        assert_equal %w(), f[20].sort
+        assert_equal %w(), f[(20..100)].sort
+        assert_equal %w(a b d), f[3].sort
+        assert_equal %w(a b c d e), f[(3..4)].sort
+      end
     end
   end
 
-
-  def test_range_index
-    content =<<-EOF
-#Id	ValueA    ValueB    Pos1    Pos2
-row1    a|aa|aaa    b    0|10    10|30
-row2    A    B    30   35
+  def test_range_index_persistent_with_filter
+    data =<<-EOF
+#ID:Range
+#:012345678901234567890
+a:   ______
+b: ______
+c:    _______
+d:  ____
+e:    ______
+f:             ___
+g:         ____
     EOF
-
-    TmpFile.with_file(content) do |filename|
-      tsv = TSV.new(File.open(filename), :double, :sep => /\s+/)
-      index = tsv.pos_index("Pos1", :memory, true)
-      assert_equal ["row1"], index[10]
-
-      index = tsv.range_index("Pos1", "Pos2", :memory, true)
-      assert_equal ["row1"], index[20]
+    TmpFile.with_file(data) do |datafile|
+      TmpFile.with_file(load_data(datafile)) do |tsvfile|
+        f = TSV.range_index(tsvfile, "Start", "End", :filters => [["field:Start", "3"]])
+
+        assert_equal %w(), f[0].sort
+        assert_equal %w(), f[1].sort
+        assert_equal %w(), f[20].sort
+        assert_equal %w(), f[(20..100)].sort
+        assert_equal %w(a), f[3].sort
+        assert_equal %w(a), f[(3..4)].sort
+      end
     end
   end