From: Diane Trout <diane@caltech.edu>
Date: Wed, 17 May 2006 19:23:45 +0000 (+0000)
Subject: finish implementing annotation by sequence
X-Git-Url: http://woldlab.caltech.edu/gitweb/?p=mussa.git;a=commitdiff_plain;h=ca1b7c45c3f77b3899a7a95986fe84f8ddd92337

finish implementing annotation by sequence
I connected the previous find_sequence code with the new spirit annotation
loading file. So now I can actually use (nearly exact) sequences for
annotating.
---

diff --git a/alg/sequence.cpp b/alg/sequence.cpp
index f3f68a8..d7b4acd 100644
--- a/alg/sequence.cpp
+++ b/alg/sequence.cpp
@@ -275,7 +275,7 @@ struct push_back_annot {
   void operator()(std::string::const_iterator, 
                   std::string::const_iterator) const 
   {
-    std::cout << "adding annot: " << begin << " " << end << " " << name << " " << type << std::endl;
+    //std::cout << "adding annot: " << begin << " " << end << " " << name << " " << type << std::endl;
     annot_list.push_back(annot(begin, end, name, type));
   };
 };
@@ -305,7 +305,7 @@ struct push_back_seq {
     {
       if (*seq_i != '\n') new_seq += *seq_i;
     }
-    std::cout << "adding seq: " << name << " " << new_seq << std::endl;
+    //std::cout << "adding seq: " << name << " " << new_seq << std::endl;
     
     Sequence s(new_seq);
     s.set_header(name);
@@ -360,6 +360,9 @@ Sequence::parse_annot(std::string data, int start_index, int end_index)
                 //end grammar
                 ) /*,
                 spirit::space_p*/).full;
+                
+  // go seearch for query sequences 
+  find_sequences(query_seqs.begin(), query_seqs.end());
 }
 
 /*
@@ -937,6 +940,8 @@ void Sequence::add_string_annotation(std::string a_seq,
                                      std::string name)
 {
   std::vector<int> seq_starts = find_motif(a_seq);
+  
+  //std::cout << "searching for " << a_seq << " found " << seq_starts.size() << std::endl;
 
   for(std::vector<int>::iterator seq_start_i = seq_starts.begin();
       seq_start_i != seq_starts.end();
diff --git a/alg/test/test_sequence.cpp b/alg/test/test_sequence.cpp
index 660f4df..0036924 100644
--- a/alg/test/test_sequence.cpp
+++ b/alg/test/test_sequence.cpp
@@ -75,21 +75,31 @@ BOOST_AUTO_TEST_CASE( annotation_load )
                       ">ident3 asdf\n"
                       "GCT\n"
                       "GCTN\n"
+                      "75\t90\tname2\ttype2\n"
                       ;
-  string s('A',100);
-  s += "GCTGCT";
+  string s(100, 'A');
+  s += "GCTGCTAATT";
   Sequence seq(s);
                      
   //istringstream annot_stream(annot_data);
   seq.parse_annot(annot_data, 0, 0);
   std::list<annot> annots_list = seq.annotations();
   std::vector<annot> annots(annots_list.begin(), annots_list.end());
-  BOOST_REQUIRE_EQUAL( annots.size(), 5);
+  BOOST_REQUIRE_EQUAL( annots.size(), 7);
   BOOST_CHECK_EQUAL( annots[0].start, 0 );
   BOOST_CHECK_EQUAL( annots[0].end, 10 );
-  //BOOST_CHECK_EQUAL( annots[0].type, "type");
+  BOOST_CHECK_EQUAL( annots[0].type, "type");
   BOOST_CHECK_EQUAL( annots[0].name, "name");
-  //BOOST_CHECK_EQUAL( annots[1].name, "myf7");
+  BOOST_CHECK_EQUAL( annots[1].name, "myf7");
+  BOOST_CHECK_EQUAL( annots[2].name, "myod");
+  BOOST_CHECK_EQUAL( annots[3].name, "anothername");
+  BOOST_CHECK_EQUAL( annots[4].name, "backward");
+  BOOST_CHECK_EQUAL( annots[5].name, "name2");
+  BOOST_CHECK_EQUAL( annots[5].end, 90);
+  // sequence defined annotations will always be after the
+  // absolute positions
+  BOOST_CHECK_EQUAL( annots[6].name, "ident3 asdf");
+  BOOST_CHECK_EQUAL( annots[6].start, 100);
 
   //BOOST_CHECK_EQUAL( annots
 }