rbbt-util 5.43.0 → 5.44.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: d1bbf2cefca44eecad7465a8d4dc1b88f53f18d1e63e310353061b43ad46bed9
-  data.tar.gz: f54f659da9eca312d116430d88019f067ce5ccf519724a2a448e3b4d31dfb767
+  metadata.gz: a9269fd6f3ed8e0b03f575c59f50d42c45a11bc07e138f4377e5069f3050fb29
+  data.tar.gz: 488a57247f23d41f8c94aa64cb38cf666c99ee43c4fa14399ed77b8bb1854519
 SHA512:
-  metadata.gz: eaad34515129ffd123064e9af920b5f83f3897c957de45e3bef04a1101d961d419863729f21665773b81f535f3fdba45d490ce41870f9db87f0e0e5d5f987233
-  data.tar.gz: d48552f30e6434b0e27e173eb62f41a3126ecb9065cba58f2f5737f8e3aef0e2183503076a40cc6586832d90458ae5e572a55171758452f3699a4225704bc25e
+  metadata.gz: 3a288fcd2e11209621bc61f911097c104e75c22c759ca7ac6ca0a1f908bf1ea1711587bf776b262f082a60c0296a9004cfc8fad85de738dabd6bad0bc45f6fed
+  data.tar.gz: 91e775b843358c29df1d87e1d9d5db8a92c37d842fd05757cc810a5f4c77a38cfe154a0a368429abb921cf43014333361426546a43aac09eabe81f07ca4315a5

data/etc/app.d/base.rb

@@ -19,7 +19,7 @@ end
 use Rack::Session::Cookie, :key => 'rack.session',
   :path => '/',
   :expire_after => 2592000,
-  :secret => "#{self.to_s} secret!!"
+  :secret => Misc.digest("#{self.to_s} secret!!") * 4
 
 #{{{ DIRECTORIES
 global_var = Rbbt.var.sinatra

data/lib/rbbt/association/util.rb

@@ -10,7 +10,7 @@ module Association
   end
 
   def self.parse_field_specification(spec)
-    return [2,nil,nil] if Numeric === spec
+    return [spec,nil,nil] if Numeric === spec
     spec = spec.split "=>" unless Array === spec
     field_part, final_format = spec
 

data/lib/rbbt/hpc/batch.rb

@@ -110,23 +110,25 @@ module HPC
 
       task = Symbol === job.overriden ? job.overriden : job.task_name
 
-      #override_deps = job.overriden_deps.collect do |dep| 
-      #  name = [dep.workflow.to_s, dep.task_name] * "#"
-      #  [name, dep.path] * "="  
-      #end.uniq * ","
-
-      if job.overriden?
-        #override_deps = job.rec_dependencies.
-        #  select{|dep| Symbol === dep.overriden }.
-        
-        override_deps = job.overriden_deps.
-          collect do |dep| 
-          name = [dep.workflow.to_s, dep.task_name] * "#"
-          [name, dep.path] * "="  
-        end.uniq * ","
-
-        options[:override_deps] = override_deps unless override_deps.empty?
-      end
+      override_deps = job.overriden_deps.collect do |dep| 
+        name = [dep.workflow.to_s, dep.task_name] * "#"
+        [name, dep.path] * "="  
+      end.uniq * ","
+
+      options[:override_deps] = override_deps unless override_deps.empty?
+
+      #if job.overriden?
+      #  #override_deps = job.rec_dependencies.
+      #  #  select{|dep| Symbol === dep.overriden }.
+      #  
+      #  override_deps = job.overriden_deps.
+      #    collect do |dep| 
+      #    name = [dep.workflow.to_s, dep.task_name] * "#"
+      #    [name, dep.path] * "="  
+      #  end.uniq * ","
+
+      #  options[:override_deps] = override_deps unless override_deps.empty?
+      #end
 
       # Save inputs into inputs_dir
       inputs_dir = Misc.process_options options, :inputs_dir

data/lib/rbbt/persist/tsv/sharder.rb

@@ -214,7 +214,7 @@ module Persist
     def [](key, clean=false)
       database = database(key)
       return nil if database.nil?
-      v = database.send(:[], key)
+      database.send(:[], key)
     end
 
     def <<(p)

data/lib/rbbt/tsv/accessor.rb

@@ -567,13 +567,13 @@ module TSV
     end
   end
 
-  def dumper_stream(keys = nil, no_options = false, unmerge = false)
+  def dumper_stream(keys = nil, no_options = false, unmerge = false, stream = nil)
     unmerge = false unless type == :double
 
     options = self.options
     options[:type] = :list if unmerge
 
-    TSV::Dumper.stream options do |dumper|
+    TSV::Dumper.stream options, filename, stream do |dumper|
       case no_options
       when FalseClass, nil
         dumper.init
@@ -631,11 +631,11 @@ module TSV
             end
           end
         end
+        dumper.close
       rescue Exception
         Log.exception $!
         raise $!
       end
-      dumper.close
     end
   end
 
@@ -651,14 +651,9 @@ module TSV
       end
     end
 
-    io = dumper_stream(keys, no_options, unmerge)
-
-    str = ''
-    while block = io.read(Misc::BLOCK_SIZE)
-      str << block
-    end
-
-    str
+    io = dumper_stream(keys, no_options, unmerge, StringIO.new)
+    io.rewind
+    io.read
   end
 
   def to_unmerged_s(keys = nil, no_options = false)

data/lib/rbbt/tsv/dumper.rb

@@ -1,13 +1,24 @@
 module TSV
   class Dumper
     attr_accessor :in_stream, :stream, :options, :filename, :sep
-    def self.stream(options = {}, filename = nil, &block)
+    def self.stream(options = {}, filename = nil, stream = nil, &block)
       dumper = TSV::Dumper.new options, filename
-      Thread.new(Thread.current) do |parent|
+      if stream
+        dumper.set_stream stream if stream
         yield dumper
-        dumper.close
+        stream
+      else
+        thread = Thread.new(Thread.current) do |parent|
+          yield dumper
+        end
+        ConcurrentStream.setup(dumper.stream, threads: thread)
       end
-      dumper.stream
+    end
+
+    def set_stream(stream)
+      @stream.close
+      @in_stream.close
+      @in_stream = @stream = stream
     end
 
     def initialize(options, filename = nil)
@@ -56,16 +67,16 @@ module TSV
 
       str = TSV.header_lines(key_field, fields, options.merge(init_options || {}))
 
-      Thread.pass while IO.select(nil, [@in_stream],nil,1).nil?
+      Thread.pass while IO.select(nil, [@in_stream],nil,1).nil? if IO === @in_stream
 
-      @in_stream.puts str
+      @in_stream << str
     end
 
     def add(k,v)
       @fields ||= @options[:fields]
       @sep ||= @options[:sep]
       begin
-        Thread.pass while IO.select(nil, [@in_stream],nil,1).nil?
+        Thread.pass while IO.select(nil, [@in_stream],nil,1).nil? if IO === @in_stream
         @in_stream << k << TSV::Dumper.values_to_s(v, @fields, @sep)
       rescue IOError
       rescue Exception
@@ -74,16 +85,16 @@ module TSV
     end
 
     def close_out
-      @stream.close unless @stream.closed?
+      @stream.close unless StringIO === @stream || @stream.closed?
     end
 
     def close_in
       @in_stream.join if @in_stream.respond_to?(:join) && ! @in_stream.joined?
-      @in_stream.close unless @in_stream.closed?
+      @in_stream.close if @in_stream.respond_to?(:close) && ! @in_stream.closed? 
     end
 
     def close
-      close_in
+      close_in unless @in_stream == @stream
     end
   end
 end

data/lib/rbbt/tsv/index.rb

@@ -125,7 +125,7 @@ module TSV
   def self.index(file, options = {})
     persist_options = Misc.pull_keys options, :persist
     persist_options[:prefix] ||= "StaticIndex[#{options[:target] || :key}]"
-     
+
     Log.debug "Static Index: #{ file } - #{Misc.fingerprint options}"
     Persist.persist_tsv nil, file, options, persist_options do |data|
       data_options = Misc.pull_keys options, :data
@@ -258,6 +258,7 @@ module TSV
                else
                  file.object_id.to_s
                end
+
     persist_options = Misc.pull_keys options, :persist
     persist_options[:prefix] ||= "StaticRangeIndex[#{start_field}-#{end_field}]"
 

data/lib/rbbt/util/misc/math.rb

@@ -1,4 +1,3 @@
-
 module Misc
 
   Log2Multiplier = 1.0 / Math.log(2.0)

data/lib/rbbt/util/misc/omics.rb

@@ -256,8 +256,9 @@ module Misc
       ref = m[1]
       num = m[2]
       alt = m[3]
+      alt = "*" if alt == "Ter"
       ref = THREE_TO_ONE_AA_CODE[ref.downcase]
-      alt = THREE_TO_ONE_AA_CODE[alt.downcase]
+      alt = THREE_TO_ONE_AA_CODE[alt.downcase] unless alt == "*"
       mutation = [ref, num, alt] * ""
     end
     one_aa_code = THREE_TO_ONE_AA_CODE.values

data/lib/rbbt/util/misc/ssw.rb

@@ -0,0 +1,298 @@
+require 'rbbt'
+
+require 'inline'
+
+# From: https://github.com/mengyao/Complete-Striped-Smith-Waterman-Library
+# Citation:  SSW Library: An SIMD Smith-Waterman C/C++ Library for Use in Genomic Applications
+#            Mengyao Zhao, Wan-Ping Lee, Gabor T. Marth 
+#            http://arxiv.org/abs/1208.6350
+module SmithWaterman
+
+  inline(:C) do |builder|
+    prefix =<<-EOF
+#include <stdlib.h>
+#include <stdio.h>
+#include <stdint.h>
+#include #{'"' + Rbbt.share.software.opt.ssw["ssw.h"].find + '"'}
+#include #{'"' + Rbbt.share.software.opt.ssw["ssw.c"].find + '"'}
+    EOF
+
+    prefix +=<<-'EOF'
+void ssw_write (s_align* a, 
+      char* ref_seq,
+      char* read_seq,
+      int8_t* table,
+      int fd) { 
+
+  int max_length = 1000000;
+  dprintf(fd, "optimal_alignment_score: %d\tsub-optimal_alignment_score: %d\t", a->score1, a->score2);
+  if (a->ref_begin1 + 1) dprintf(fd, "target_begin: %d\t", a->ref_begin1 + 1);
+  dprintf(fd, "target_end: %d\t", a->ref_end1 + 1);
+  if (a->read_begin1 + 1) dprintf(fd, "query_begin: %d\t", a->read_begin1 + 1);
+  dprintf(fd, "query_end: %d\n\n", a->read_end1 + 1);
+  if (a->cigar) {
+    int32_t i, c = 0, left = 0, e = 0, qb = a->ref_begin1, pb = a->read_begin1;
+    while (e < a->cigarLen || left > 0) {
+      int32_t count = 0;
+      int32_t q = qb;
+      int32_t p = pb;
+      dprintf(fd, "Target: %8d    ", q + 1);
+      for (c = e; c < a->cigarLen; ++c) {
+        int32_t letter = 0xf&*(a->cigar + c);
+        int32_t length = (0xfffffff0&*(a->cigar + c))>>4;
+        int32_t l = (count == 0 && left > 0) ? left: length;
+        for (i = 0; i < l; ++i) {
+          if (letter == 1) dprintf(fd, "-");
+          else {
+            dprintf(fd, "%c", *(ref_seq + q));
+            ++ q;
+          }
+          ++ count;
+          if (count == max_length) goto step2;
+        }
+      }
+step2:
+      dprintf(fd, "    %d\n                    ", q);
+      q = qb;
+      count = 0;
+      for (c = e; c < a->cigarLen; ++c) {
+        int32_t letter = 0xf&*(a->cigar + c);
+        int32_t length = (0xfffffff0&*(a->cigar + c))>>4;
+        int32_t l = (count == 0 && left > 0) ? left: length;
+        for (i = 0; i < l; ++i){ 
+          if (letter == 0) {
+            if (table[(int)*(ref_seq + q)] == table[(int)*(read_seq + p)])dprintf(fd, "|");
+            else dprintf(fd, "*");
+            ++q;
+            ++p;
+          } else {
+            dprintf(fd, "*");
+            if (letter == 1) ++p;
+            else ++q;
+          }
+          ++ count;
+          if (count == max_length) {
+            qb = q;
+            goto step3;
+          }
+        }
+      }
+step3:
+      p = pb;
+      dprintf(fd, "\nQuery:  %8d    ", p + 1);
+      count = 0;
+      for (c = e; c < a->cigarLen; ++c) {
+        int32_t letter = 0xf&*(a->cigar + c);
+        int32_t length = (0xfffffff0&*(a->cigar + c))>>4;
+        int32_t l = (count == 0 && left > 0) ? left: length;
+        for (i = 0; i < l; ++i) { 
+          if (letter == 2) dprintf(fd, "-");
+          else {
+            dprintf(fd, "%c", *(read_seq + p));
+            ++p;
+          }
+          ++ count;
+          if (count == max_length) {
+            pb = p;
+            left = l - i - 1;
+            e = (left == 0) ? (c + 1) : c;
+            goto end;
+          }
+        }
+      }
+      e = c;
+      left = 0;
+end:
+      dprintf(fd, "    %d\n\n", p);
+    }
+  }
+}
+
+    EOF
+
+    builder.prefix prefix
+
+
+    script = <<-EOF
+  int ssw_nt(char * read_seq, char * ref_seq){
+    int32_t l, m, k, match = 2, mismatch = 2, gap_open = 3, gap_extension = 1;	// default parameters for genome sequence alignment
+    // reference sequence
+    //char ref_seq[40] = {'C', 'A', 'G', 'C', 'C', 'T', 'T', 'T', 'C', 'T', 'G', 'A', 'C', 'C', 'C', 'G', 'G', 'A', 'A', 'A', 'T', 
+    //					'C', 'A', 'A', 'A', 'A', 'T', 'A', 'G', 'G', 'C', 'A', 'C', 'A', 'A', 'C', 'A', 'A', 'A', '\0'};	
+    //char read_seq[16] = {'C', 'T', 'G', 'A', 'G', 'C', 'C', 'G', 'G', 'T', 'A', 'A', 'A', 'T', 'C', '\0'};	// read sequence
+
+    s_profile* profile;
+    int8_t* num = (int8_t*)malloc(16);	// the read sequence represented in numbers
+    int8_t* ref_num = (int8_t*)malloc(64);	// the read sequence represented in numbers
+    s_align* result;
+
+    /* This table is used to transform nucleotide letters into numbers. */
+    int8_t nt_table[128] = {
+      4, 4, 4, 4,  4, 4, 4, 4,  4, 4, 4, 4,  4, 4, 4, 4, 
+      4, 4, 4, 4,  4, 4, 4, 4,  4, 4, 4, 4,  4, 4, 4, 4, 
+      4, 4, 4, 4,  4, 4, 4, 4,  4, 4, 4, 4,  4, 4, 4, 4,
+      4, 4, 4, 4,  4, 4, 4, 4,  4, 4, 4, 4,  4, 4, 4, 4, 
+      4, 0, 4, 1,  4, 4, 4, 2,  4, 4, 4, 4,  4, 4, 4, 4, 
+      4, 4, 4, 4,  3, 0, 4, 4,  4, 4, 4, 4,  4, 4, 4, 4, 
+      4, 0, 4, 1,  4, 4, 4, 2,  4, 4, 4, 4,  4, 4, 4, 4, 
+      4, 4, 4, 4,  3, 0, 4, 4,  4, 4, 4, 4,  4, 4, 4, 4 
+    };
+
+    // initialize scoring matrix for genome sequences
+    //  A  C  G  T	N (or other ambiguous code) 
+    //  2 -2 -2 -2 	0	A
+    // -2  2 -2 -2 	0	C
+    // -2 -2  2 -2 	0	G
+    // -2 -2 -2  2 	0	T
+    //	0  0  0  0  0	N (or other ambiguous code)	
+    int8_t* mat = (int8_t*)calloc(25, sizeof(int8_t));
+    for (l = k = 0; l < 4; ++l) {
+      for (m = 0; m < 4; ++m) mat[k++] = l == m ? match : - mismatch;	/* weight_match : -weight_mismatch */
+      mat[k++] = 0; // ambiguous base: no penalty
+    }
+    for (m = 0; m < 5; ++m) mat[k++] = 0;
+
+    for (m = 0; m < 15; ++m) num[m] = nt_table[(int)read_seq[m]];
+    profile = ssw_init(num, 15, mat, 5, 2);
+    for (m = 0; m < 39; ++m) ref_num[m] = nt_table[(int)ref_seq[m]];
+
+    // Only the 8 bit of the flag is setted. ssw_align will always return the best alignment beginning position and cigar.
+    result = ssw_align (profile, ref_num, 39, gap_open, gap_extension, 1, 0, 0, 15);	
+    //ssw_write(result, ref_seq, read_seq, nt_tablte);
+
+    free(mat);
+    free(ref_num);
+    free(num);
+    return(0);
+  }
+
+    EOF
+    builder.c_singleton script
+
+    script = <<-EOF
+  int ssw_aa(char * read_seq, char * ref_seq, int read_seq_len, int ref_seq_len, int fd){
+
+    int32_t l, m, k, match = 2, mismatch = 2, gap_open = 3, gap_extension = 1;	// default parameters for genome sequence alignment
+
+    s_profile* profile;
+    int8_t* num = (int8_t*)malloc(read_seq_len);	// the read sequence represented in numbers
+    int8_t* ref_num = (int8_t*)malloc(ref_seq_len);	// the reference sequence represented in numbers
+    s_align* result;
+
+    /* This table is used to transform amino acid letters into numbers. */
+    int8_t aa_table[128] = {
+      23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 
+      23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 
+      23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23,
+      23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 
+      23, 0,  20, 4,  3,  6,  13, 7,  8,  9,  23, 11, 10, 12, 2,  23, 
+      14, 5,  1,  15, 16, 23, 19, 17, 22, 18, 21, 23, 23, 23, 23, 23, 
+      23, 0,  20, 4,  3,  6,  13, 7,  8,  9,  23, 11, 10, 12, 2,  23, 
+      14, 5,  1,  15, 16, 23, 19, 17, 22, 18, 21, 23, 23, 23, 23, 23 
+    };
+
+    int8_t mat[] = {
+    //  A   R   N   D   C   Q   E   G   H   I   L   K   M   F   P   S   T   W   Y   V   B   Z   X   *   
+        5, -2, -1, -2, -1, -1, -1,  0, -2, -1, -2, -1, -1, -3, -1,  1,  0, -3, -2,  0, -2, -1, -1, -5,	// A
+         -2,  7, -1, -2, -4,  1,  0, -3,  0, -4, -3,  3, -2, -3, -3, -1, -1, -3, -1, -3, -1,  0, -1, -5,	// R
+         -1, -1,  7,  2, -2,  0,  0,  0,  1, -3, -4,  0, -2, -4, -2,  1,  0, -4, -2, -3,  5,  0, -1, -5,	// N
+         -2, -2,  2,  8, -4,  0,  2, -1, -1, -4, -4, -1, -4, -5, -1,  0, -1, -5, -3, -4,  6,  1, -1, -5,	// D
+         -1, -4, -2, -4, 13, -3, -3, -3, -3, -2, -2, -3, -2, -2, -4, -1, -1, -5, -3, -1, -3, -3, -1, -5,	// C
+         -1,  1,  0,  0, -3,  7,  2, -2,  1, -3, -2,  2,  0, -4, -1,  0, -1, -1, -1, -3,  0,  4, -1, -5,	// Q
+         -1,  0,  0,  2, -3,  2,  6, -3,  0, -4, -3,  1, -2, -3, -1, -1, -1, -3, -2, -3,  1,  5, -1, -5,	// E
+        0, -3,  0, -1, -3, -2, -3,  8, -2, -4, -4, -2, -3, -4, -2,  0, -2, -3, -3, -4, -1, -2, -1, -5,	// G
+         -2,  0,  1, -1, -3,  1,  0, -2, 10, -4, -3,  0, -1, -1, -2, -1, -2, -3,  2, -4,  0,  0, -1, -5,	// H
+         -1, -4, -3, -4, -2, -3, -4, -4, -4,  5,  2, -3,  2,  0, -3, -3, -1, -3, -1,  4, -4, -3, -1, -5,	// I
+         -2, -3, -4, -4, -2, -2, -3, -4, -3,  2,  5, -3,  3,  1, -4, -3, -1, -2, -1,  1, -4, -3, -1, -5,	// L
+         -1,  3,  0, -1, -3,  2,  1, -2,  0, -3, -3,  6, -2, -4, -1,  0, -1, -3, -2, -3,  0,  1, -1, -5,	// K
+         -1, -2, -2, -4, -2,  0, -2, -3, -1,  2,  3, -2,  7,  0, -3, -2, -1, -1,  0,  1, -3, -1, -1, -5,	// M
+         -3, -3, -4, -5, -2, -4, -3, -4, -1,  0,  1, -4,  0,  8, -4, -3, -2,  1,  4, -1, -4, -4, -1, -5,	// F
+         -1, -3, -2, -1, -4, -1, -1, -2, -2, -3, -4, -1, -3, -4, 10, -1, -1, -4, -3, -3, -2, -1, -1, -5,	// P
+        1, -1,  1,  0, -1,  0, -1,  0, -1, -3, -3,  0, -2, -3, -1,  5,  2, -4, -2, -2,  0,  0, -1, -5,	// S
+        0, -1,  0, -1, -1, -1, -1, -2, -2, -1, -1, -1, -1, -2, -1,  2,  5, -3, -2,  0,  0, -1, -1, -5, 	// T
+         -3, -3, -4, -5, -5, -1, -3, -3, -3, -3, -2, -3, -1,  1, -4, -4, -3, 15,  2, -3, -5, -2, -1, -5, 	// W
+         -2, -1, -2, -3, -3, -1, -2, -3,  2, -1, -1, -2,  0,  4, -3, -2, -2,  2,  8, -1, -3, -2, -1, -5, 	// Y
+        0, -3, -3, -4, -1, -3, -3, -4, -4,  4,  1, -3,  1, -1, -3, -2,  0, -3, -1,  5, -3, -3, -1, -5, 	// V
+         -2, -1,  5,  6, -3,  0,  1, -1,  0, -4, -4,  0, -3, -4, -2,  0,  0, -5, -3, -3,  6,  1, -1, -5, 	// B
+         -1,  0,  0,  1, -3,  4,  5, -2,  0, -3, -3,  1, -1, -4, -1,  0, -1, -2, -2, -3,  1,  5, -1, -5, 	// Z
+         -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -5, 	// X
+         -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5,  1 	// *
+    };	
+
+
+    for (m = 0; m < read_seq_len; ++m) num[m] = aa_table[(int)read_seq[m]];
+    profile = ssw_init(num, read_seq_len, mat, 24, 2);
+    for (m = 0; m < ref_seq_len; ++m) ref_num[m] = aa_table[(int)ref_seq[m]];
+
+    // Only the 8 bit of the flag is setted. ssw_align will always return the best alignment beginning position and cigar.
+    result = ssw_align(profile, ref_num, ref_seq_len, gap_open, gap_extension, 1, 0, 0, read_seq_len );	
+    ssw_write(result, ref_seq, read_seq, aa_table, fd);
+
+    free(num);
+    free(ref_num);
+    return(0);
+  }
+
+    EOF
+    builder.c_singleton script
+
+  end
+
+  def self.align(query_sequence, target_sequence)
+    Log.low { "Aligning #{ Misc.fingerprint query_sequence } to #{ Misc.fingerprint target_sequence }" }
+
+    begin
+      raise "No query sequence" if query_sequence.nil?
+      raise "No target sequence" if target_sequence.nil?
+
+      s_out = Misc.open_pipe do |s_in|
+        SmithWaterman.ssw_aa(query_sequence, target_sequence, query_sequence.length, target_sequence.length, s_in.fileno)
+      end
+
+      txt = s_out.read
+      s_out.close
+      s_out.join
+      txt
+
+      target_start, target, target_end = txt.match(/Target:\s+(\d+)\s+([A-Z\-?*]+)\s+(\d+)/).values_at 1, 2, 3
+
+      query_start, query, query_end = txt.match(/Query:\s+(\d+)\s+([A-Z\-?*]+)\s+(\d+)/).values_at 1, 2, 3
+
+      txt.replace ""
+      [("_" * (query_start.to_i - 1)) + query, ("_" * (target_start.to_i - 1)) + target]
+    rescue
+      Log.warn("Error in aligmnent: #{$!.message}")
+      return ["-", "-"]
+    end
+  end
+
+  def self.alignment_map(source, target)
+    alignment_source, alignment_target = SmithWaterman.align(source, target)
+    map = {}
+
+    offset_source, alignment_source = alignment_source.match(/^(_*)(.*)/).values_at( 1, 2)
+    offset_target, alignment_target = alignment_target.match(/^(_*)(.*)/).values_at( 1, 2)
+
+    gaps_source = 0 
+    gaps_target = 0
+    miss_match = 0
+    alignment_source.chars.zip(alignment_target.chars).each_with_index do |p,i|
+      char_source, char_target = p
+      gaps_source += 1 if char_source == '-'
+      gaps_target += 1 if char_target == '-'
+      source_pos = i + 1 + offset_source.length - gaps_source
+      target_pos = i + 1 + offset_target.length - gaps_target
+      if char_source != char_target or char_source == "-"
+        miss_match += 1
+      else
+        map[source_pos] = target_pos 
+      end
+    end
+
+    if miss_match + gaps_source > alignment_source.length.to_f / 2
+      {}
+    else
+      map
+    end
+  end
+end

data/lib/rbbt/util/open.rb

@@ -729,7 +729,7 @@ module Open
       dir_sub_path.push content
       save_content_in_repo(*dir_sub_path)
     else
-      FileUtils.mkdir_p File.dirname(file)
+      FileUtils.mkdir_p File.dirname(file) unless File.directory?(file)
       case
       when block_given?
         begin

data/lib/rbbt/workflow/step/info.rb

@@ -35,8 +35,8 @@ class Step
     rescue Exception
       Log.debug{"Error loading info file: " + info_file}
       Log.exception $!
-      Open.rm info_file
-      Misc.sensiblewrite(info_file, Step.serialize_info({:status => :error, :messages => ["Info file lost"]}))
+      #Open.rm info_file
+      #Misc.sensiblewrite(info_file, Step.serialize_info({:status => :error, :messages => ["Info file lost"]}))
       raise $!
     end
   end
@@ -62,6 +62,7 @@ class Step
   def load_dependencies_from_info
     relocated = nil
     @dependencies = (self.info[:dependencies] || []).collect do |task,name,dep_path|
+      dep_path = task if dep_path.nil?
       if Open.exists?(dep_path) || Open.exists?(dep_path + '.info')
         Workflow._load_step dep_path
       else

data/lib/rbbt/workflow/step.rb

@@ -303,7 +303,8 @@ class Step
 
             if result_description
               entity_info = info.dup
-              entity_info.merge! info[:inputs] if info[:inputs]
+              # Also load entity_info in rbbt6
+              entity_info.merge! info[:inputs] if Hash === info[:inputs]
               res = prepare_result res, result_description, entity_info 
             end
 

data/python/rbbt/__init__.py

@@ -67,10 +67,10 @@ def tsv_preamble(line, comment_char="#"):
     return header
 
 
-def tsv_header(filename, sep="\t", comment_char="#"):
+def tsv_header(filename, sep="\t", comment_char="#", encoding='utf8'):
     import re
 
-    f = open(filename)
+    f = open(filename, encoding=encoding)
     line = f.readline().strip()
 
     if (not line.startswith(comment_char)):

data/share/rbbt_commands/workflow/server

@@ -134,7 +134,12 @@ TmpFile.with_file do |app_dir|
       options.each do |k,v| fixed_options[k.to_sym] = v end
       options = fixed_options
 
-      Rack::Server.start(options)
+      begin
+        Rack::Server.start(options)
+      rescue LoadError
+        require 'rackup'
+        Rackup::Server.start(options)
+      end
     end
   end
 end

data/share/rbbt_commands/workflow/task

@@ -484,7 +484,7 @@ begin
 
   if server = options.delete(:relay)
     require 'rbbt/workflow/remote_workflow'
-    relay_dependencies = options.delete(:relay_dependencies).split(",")
+    relay_dependencies = options.delete(:relay_dependencies).split(",") if options[:relay_dependencies]
     produce_dependencies_for_relay = options.delete(:produce_dependencies_for_relay)
 
     jobs_to_relay = relay_dependencies ?  match_dependencies(relay_dependencies, job.rec_dependencies) : [job]