Fixes #2 by adding the missing -D option in the help

Convert svn:ignore properties to .gitignore.
unsufficient space allocated for handling strings in arguments
2015-05-19 13:52:35 +02:00 · 2015-05-16 17:51:46 +02:00 · 2013-03-07 09:25:16 +00:00 · 2012-05-16 11:56:36 +00:00 · 2012-05-16 11:43:33 +00:00 · 2012-05-16 07:52:28 +00:00
28 changed files with 1443 additions and 178 deletions
--- a/.cproject
+++ b/.cproject
@ -0,0 +1,122 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<?fileVersion 4.0.0?>
+
+<cproject>
+<storageModule moduleId="org.eclipse.cdt.core.settings">
+<cconfiguration id="cdt.managedbuild.toolchain.gnu.macosx.base.985481067">
+<storageModule buildSystemId="org.eclipse.cdt.managedbuilder.core.configurationDataProvider" id="cdt.managedbuild.toolchain.gnu.macosx.base.985481067" moduleId="org.eclipse.cdt.core.settings" name="MacOSX GCC">
+<externalSettings/>
+<extensions>
+<extension id="org.eclipse.cdt.core.MachO" point="org.eclipse.cdt.core.BinaryParser"/>
+<extension id="org.eclipse.cdt.core.GASErrorParser" point="org.eclipse.cdt.core.ErrorParser"/>
+<extension id="org.eclipse.cdt.core.GLDErrorParser" point="org.eclipse.cdt.core.ErrorParser"/>
+<extension id="org.eclipse.cdt.core.GCCErrorParser" point="org.eclipse.cdt.core.ErrorParser"/>
+<extension id="org.eclipse.cdt.core.MakeErrorParser" point="org.eclipse.cdt.core.ErrorParser"/>
+</extensions>
+</storageModule>
+<storageModule moduleId="cdtBuildSystem" version="4.0.0">
+<configuration artifactName="ecoPCR" buildProperties="" id="cdt.managedbuild.toolchain.gnu.macosx.base.985481067" name="MacOSX GCC" parent="org.eclipse.cdt.build.core.emptycfg">
+<folderInfo id="cdt.managedbuild.toolchain.gnu.macosx.base.985481067.141857048" name="/" resourcePath="">
+<toolChain id="cdt.managedbuild.toolchain.gnu.macosx.base.1673936174" name="cdt.managedbuild.toolchain.gnu.macosx.base" superClass="cdt.managedbuild.toolchain.gnu.macosx.base">
+<targetPlatform archList="all" binaryParser="org.eclipse.cdt.core.MachO" id="cdt.managedbuild.target.gnu.platform.macosx.base.584997877" name="Debug Platform" osList="macosx" superClass="cdt.managedbuild.target.gnu.platform.macosx.base"/>
+<builder id="cdt.managedbuild.target.gnu.builder.macosx.base.328283627" managedBuildOn="false" name="Gnu Make Builder.MacOSX GCC" superClass="cdt.managedbuild.target.gnu.builder.macosx.base"/>
+<tool id="cdt.managedbuild.tool.macosx.c.linker.macosx.base.627652869" name="MacOS X C Linker" superClass="cdt.managedbuild.tool.macosx.c.linker.macosx.base"/>
+<tool id="cdt.managedbuild.tool.macosx.cpp.linker.macosx.base.815782479" name="MacOS X C++ Linker" superClass="cdt.managedbuild.tool.macosx.cpp.linker.macosx.base"/>
+<tool id="cdt.managedbuild.tool.gnu.assembler.macosx.base.536333148" name="GCC Assembler" superClass="cdt.managedbuild.tool.gnu.assembler.macosx.base"/>
+<tool id="cdt.managedbuild.tool.gnu.archiver.macosx.base.202459766" name="GCC Archiver" superClass="cdt.managedbuild.tool.gnu.archiver.macosx.base"/>
+<tool id="cdt.managedbuild.tool.gnu.cpp.compiler.macosx.base.1142106025" name="GCC C++ Compiler" superClass="cdt.managedbuild.tool.gnu.cpp.compiler.macosx.base"/>
+<tool id="cdt.managedbuild.tool.gnu.c.compiler.macosx.base.845498516" name="GCC C Compiler" superClass="cdt.managedbuild.tool.gnu.c.compiler.macosx.base"/>
+</toolChain>
+</folderInfo>
+</configuration>
+</storageModule>
+<storageModule moduleId="scannerConfiguration">
+<autodiscovery enabled="true" problemReportingEnabled="true" selectedProfileId="org.eclipse.cdt.make.core.GCCStandardMakePerProjectProfile"/>
+<profile id="org.eclipse.cdt.make.core.GCCStandardMakePerProjectProfile">
+<buildOutputProvider>
+<openAction enabled="true" filePath=""/>
+<parser enabled="true"/>
+</buildOutputProvider>
+<scannerInfoProvider id="specsFile">
+<runAction arguments="-E -P -v -dD ${plugin_state_location}/${specs_file}" command="gcc" useDefault="true"/>
+<parser enabled="true"/>
+</scannerInfoProvider>
+</profile>
+<profile id="org.eclipse.cdt.make.core.GCCStandardMakePerFileProfile">
+<buildOutputProvider>
+<openAction enabled="true" filePath=""/>
+<parser enabled="true"/>
+</buildOutputProvider>
+<scannerInfoProvider id="makefileGenerator">
+<runAction arguments="-f ${project_name}_scd.mk" command="make" useDefault="true"/>
+<parser enabled="true"/>
+</scannerInfoProvider>
+</profile>
+<profile id="org.eclipse.cdt.managedbuilder.core.GCCManagedMakePerProjectProfile">
+<buildOutputProvider>
+<openAction enabled="false" filePath=""/>
+<parser enabled="false"/>
+</buildOutputProvider>
+<scannerInfoProvider id="specsFile">
+<runAction arguments="-E -P -v -dD ${plugin_state_location}/${specs_file}" command="gcc" useDefault="true"/>
+<parser enabled="true"/>
+</scannerInfoProvider>
+</profile>
+<profile id="org.eclipse.cdt.managedbuilder.core.GCCManagedMakePerProjectProfileCPP">
+<buildOutputProvider>
+<openAction enabled="false" filePath=""/>
+<parser enabled="false"/>
+</buildOutputProvider>
+<scannerInfoProvider id="specsFile">
+<runAction arguments="-E -P -v -dD ${plugin_state_location}/specs.cpp" command="g++" useDefault="true"/>
+<parser enabled="true"/>
+</scannerInfoProvider>
+</profile>
+<profile id="org.eclipse.cdt.managedbuilder.core.GCCManagedMakePerProjectProfileC">
+<buildOutputProvider>
+<openAction enabled="false" filePath=""/>
+<parser enabled="false"/>
+</buildOutputProvider>
+<scannerInfoProvider id="specsFile">
+<runAction arguments="-E -P -v -dD ${plugin_state_location}/specs.c" command="gcc" useDefault="true"/>
+<parser enabled="true"/>
+</scannerInfoProvider>
+</profile>
+<profile id="org.eclipse.cdt.managedbuilder.core.GCCWinManagedMakePerProjectProfile">
+<buildOutputProvider>
+<openAction enabled="false" filePath=""/>
+<parser enabled="false"/>
+</buildOutputProvider>
+<scannerInfoProvider id="specsFile">
+<runAction arguments="-E -P -v -dD ${plugin_state_location}/${specs_file}" command="gcc" useDefault="true"/>
+<parser enabled="true"/>
+</scannerInfoProvider>
+</profile>
+<profile id="org.eclipse.cdt.managedbuilder.core.GCCWinManagedMakePerProjectProfileCPP">
+<buildOutputProvider>
+<openAction enabled="false" filePath=""/>
+<parser enabled="false"/>
+</buildOutputProvider>
+<scannerInfoProvider id="specsFile">
+<runAction arguments="-E -P -v -dD ${plugin_state_location}/specs.cpp" command="g++" useDefault="true"/>
+<parser enabled="true"/>
+</scannerInfoProvider>
+</profile>
+<profile id="org.eclipse.cdt.managedbuilder.core.GCCWinManagedMakePerProjectProfileC">
+<buildOutputProvider>
+<openAction enabled="false" filePath=""/>
+<parser enabled="false"/>
+</buildOutputProvider>
+<scannerInfoProvider id="specsFile">
+<runAction arguments="-E -P -v -dD ${plugin_state_location}/specs.c" command="gcc" useDefault="true"/>
+<parser enabled="true"/>
+</scannerInfoProvider>
+</profile>
+</storageModule>
+<storageModule moduleId="org.eclipse.cdt.core.externalSettings"/>
+</cconfiguration>
+</storageModule>
+<storageModule moduleId="cdtBuildSystem" version="4.0.0">
+<project id="ecoPCR.null.1320766773" name="ecoPCR"/>
+</storageModule>
+</cproject>
--- a/.gitignore
+++ b/.gitignore
@ -0,0 +1,16 @@
+
+# /src/
+/src/ecoPCR
+/src/ecofind
+/src/*.P
+/src/ecogrep
+
+# /src/libapat/
+/src/libapat/libapat.a
+/src/libapat/*.P
+
+# /src/libecoPCR/
+/src/libecoPCR/*.P
+
+# /src/libthermo/
+/src/libthermo/*.P
--- a/.project
+++ b/.project
@ -0,0 +1,83 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<projectDescription>
+	<name>ecoPCR</name>
+	<comment></comment>
+	<projects>
+	</projects>
+	<buildSpec>
+		<buildCommand>
+			<name>org.python.pydev.PyDevBuilder</name>
+			<arguments>
+			</arguments>
+		</buildCommand>
+		<buildCommand>
+			<name>org.eclipse.cdt.managedbuilder.core.genmakebuilder</name>
+			<triggers>clean,full,incremental,</triggers>
+			<arguments>
+				<dictionary>
+					<key>org.eclipse.cdt.make.core.fullBuildTarget</key>
+					<value>all</value>
+				</dictionary>
+				<dictionary>
+					<key>?name?</key>
+					<value></value>
+				</dictionary>
+				<dictionary>
+					<key>org.eclipse.cdt.make.core.enableAutoBuild</key>
+					<value>false</value>
+				</dictionary>
+				<dictionary>
+					<key>org.eclipse.cdt.make.core.enableFullBuild</key>
+					<value>true</value>
+				</dictionary>
+				<dictionary>
+					<key>org.eclipse.cdt.make.core.enableCleanBuild</key>
+					<value>true</value>
+				</dictionary>
+				<dictionary>
+					<key>org.eclipse.cdt.make.core.cleanBuildTarget</key>
+					<value>clean</value>
+				</dictionary>
+				<dictionary>
+					<key>org.eclipse.cdt.make.core.append_environment</key>
+					<value>true</value>
+				</dictionary>
+				<dictionary>
+					<key>org.eclipse.cdt.make.core.contents</key>
+					<value>org.eclipse.cdt.make.core.activeConfigSettings</value>
+				</dictionary>
+				<dictionary>
+					<key>org.eclipse.cdt.make.core.useDefaultBuildCmd</key>
+					<value>true</value>
+				</dictionary>
+				<dictionary>
+					<key>org.eclipse.cdt.make.core.buildArguments</key>
+					<value></value>
+				</dictionary>
+				<dictionary>
+					<key>org.eclipse.cdt.make.core.buildCommand</key>
+					<value>make</value>
+				</dictionary>
+				<dictionary>
+					<key>org.eclipse.cdt.make.core.autoBuildTarget</key>
+					<value>all</value>
+				</dictionary>
+				<dictionary>
+					<key>org.eclipse.cdt.make.core.stopOnError</key>
+					<value>true</value>
+				</dictionary>
+			</arguments>
+		</buildCommand>
+		<buildCommand>
+			<name>org.eclipse.cdt.managedbuilder.core.ScannerConfigBuilder</name>
+			<arguments>
+			</arguments>
+		</buildCommand>
+	</buildSpec>
+	<natures>
+		<nature>org.eclipse.cdt.core.cnature</nature>
+		<nature>org.eclipse.cdt.managedbuilder.core.ScannerConfigNature</nature>
+		<nature>org.eclipse.cdt.managedbuilder.core.managedBuildNature</nature>
+		<nature>org.python.pydev.pythonNature</nature>
+	</natures>
+</projectDescription>
--- a/.pydevproject
+++ b/.pydevproject
@ -0,0 +1,7 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<?eclipse-pydev version="1.0"?>
+
+<pydev_project>
+<pydev_property name="org.python.pydev.PYTHON_PROJECT_VERSION">python 2.4</pydev_property>
+<pydev_property name="org.python.pydev.PYTHON_PROJECT_INTERPRETER">Default</pydev_property>
+</pydev_project>
--- a/1
+++ b/1
@ -0,0 +1 @@
+0.5.0
--- a/src/Makefile
+++ b/src/Makefile
@ -1,4 +1,4 @@
-EXEC=ecoPCR ecofind ecoisundertaxon
+EXEC=ecoPCR ecofind ecogrep

 PCR_SRC= ecopcr.c
 PCR_OBJ= $(patsubst %.c,%.o,$(PCR_SRC))
@ -6,15 +6,19 @@ PCR_OBJ= $(patsubst %.c,%.o,$(PCR_SRC))
 FIND_SRC= ecofind.c
 FIND_OBJ= $(patsubst %.c,%.o,$(FIND_SRC))

+GREP_SRC= ecogrep.c
+GREP_OBJ= $(patsubst %.c,%.o,$(GREP_SRC))
+
 IUT_SRC= ecoisundertaxon.c
 IUT_OBJ= $(patsubst %.c,%.o,$(IUT_SRC))

 SRCS= $(PCR_SRC) $(FIND_SRC) $(IUT_SRC)

-LIB= -lecoPCR -lapat -lz -lm
+LIB= -lecoPCR -lthermo -lapat -lz -lm

 LIBFILE= libapat/libapat.a \
-         libecoPCR/libecoPCR.a
+         libecoPCR/libecoPCR.a \
+         libthermo/libthermo.a


 include global.mk
@ -44,6 +48,17 @@ ecoPCR: $(PCR_OBJ) $(LIBFILE)
 ecofind: $(FIND_OBJ) $(LIBFILE)
 	$(CC) $(LDFLAGS) -o $@ $< $(LIBPATH) $(LIB)
 	
+########
+#
+# ecogrep compilation
+#
+########
+	
+# executable compilation and link
+
+ecogrep: $(GREP_OBJ) $(LIBFILE)
+	$(CC) $(LDFLAGS) -o $@ $< $(LIBPATH) $(LIB)
+	
 ########
 #
 # IsUnderTaxon compilation
@ -67,6 +82,9 @@ libapat/libapat.a:
 libecoPCR/libecoPCR.a:
 	$(MAKE) -C libecoPCR
 	
+libthermo/libthermo.a:
+	$(MAKE) -C libthermo
+	
 	
 ########
 #
@ -79,6 +97,7 @@ clean:
 	rm -f $(EXEC)
 	$(MAKE) -C libapat clean
 	$(MAKE) -C libecoPCR clean
+	$(MAKE) -C libthermo clean
 		

 		
--- a/src/ecoPCR.gz
+++ b/src/ecoPCR.gz
--- a/src/ecofind.c
+++ b/src/ecofind.c
@ -9,10 +9,23 @@
 /**
 * display the result
 **/
-static void printresult(ecotx_t *taxon,econame_t* name,ecotaxonomy_t *taxonomy)
+
+void displayPath(ecotx_t *taxon, ecotaxonomy_t *taxonomy){
+
+	if (taxon != taxon->parent){
+		displayPath(taxon->parent,taxonomy);
+		printf(";");
+	}
+	if (rank_index("no rank",taxonomy->ranks) != taxon->rank)
+		printf("%s:", taxonomy->ranks->label[taxon->rank]);
+	printf("%s", taxon->name);
+}
+
+
+static void printresult(ecotx_t *taxon,econame_t* name,ecotaxonomy_t *taxonomy, int32_t pathDisplay)
 {
 	char* rankname;
-	char*  classname;
+	char* classname;
 	char* matchedname=taxon->name;
 	
 	classname="scientific name";
@ -24,31 +37,38 @@ static void printresult(ecotx_t *taxon,econame_t* name,ecotaxonomy_t *taxonomy)
 	
 	rankname= taxonomy->ranks->label[taxon->rank];	
 	
-	printf("%10d \t| %15s \t|\t %-50s \t|\t %15s \t|\t %s\n",
+	printf("%10d \t| %15s \t|\t %-50s \t|\t %15s \t|\t %s",
 			taxon->taxid,
 			rankname,
 			matchedname,
 			classname,
-			taxon->name);	
+			taxon->name);
+	if (pathDisplay) {
+	    printf("\t|\t");
+	    displayPath(taxon, taxonomy);
+	}
+    printf("\n");
 }

 /**
 * display header before printing any result
 **/
-static void printheader(void)
+static void printheader(int32_t pathDisplay)
 {
-	printf("# %12s \t| %15s \t|\t %-50s \t|\t %-15s \t|\t %s\n#\n",
+	printf("# %12s \t| %15s \t|\t %-50s \t|\t %-15s \t|\t %s%s\n#\n",
 			"taxonomy id",
 			"taxonomy rank",
 			"name",
 			"class name",
-			"scientific name");
+			"scientific name",
+			pathDisplay ? "\t|\t path":"");
 }

+
 /**
 * display son's list for given taxon
 **/
-static void get_son(ecotaxonomy_t *taxonomy, ecotx_t *taxon, int32_t *count, char *rankname)
+static void get_son(ecotaxonomy_t *taxonomy, ecotx_t *taxon, int32_t *count, char *rankname, int32_t pathDisplay)
 {
 	int32_t		i;
 	ecotx_t 	*current_taxon;
@ -57,14 +77,15 @@ static void get_son(ecotaxonomy_t *taxonomy, ecotx_t *taxon, int32_t *count, cha
 			i < taxonomy->taxons->count; 
 			i++, current_taxon++)
 	{	
-		if (taxon->taxid == current_taxon->parent->taxid)
+
+		if (taxon != current_taxon && taxon->taxid == current_taxon->parent->taxid)
 		{
 			if (rankname == NULL || !strcmp(rankname,taxonomy->ranks->label[current_taxon->rank]))
 			{
-				printresult(current_taxon, NULL, taxonomy);
+				printresult(current_taxon, NULL, taxonomy, pathDisplay);
 				(*count)++;	
 			}
-			get_son(taxonomy,current_taxon,count,rankname);
+			get_son(taxonomy,current_taxon,count,rankname, pathDisplay);
 		}
 	}
 }
@ -95,23 +116,23 @@ static void listfilteroptions(ecorankidx_t *ranks)
 /* get back on given taxid taxonomic parent	*/
 /* and display it							*/
 /* ---------------------------------------- */
-void gettaxidparents(int32_t taxid, ecotaxonomy_t *taxonomy, char *rankname)
+void gettaxidparents(int32_t taxid, ecotaxonomy_t *taxonomy, char *rankname, int32_t pathDisplay)
 {
 	ecotx_t *next_parent;
 	int32_t	c = 0;
 	
 	next_parent = eco_findtaxonbytaxid(taxonomy, taxid);		
 	
-	printheader();
+	printheader(pathDisplay);
 	
-	printresult(next_parent, NULL,taxonomy);
+	printresult(next_parent, NULL,taxonomy, pathDisplay);
 		
 	while ( strcmp(next_parent->name, "root") )
 	{
 		next_parent = next_parent->parent;
 		if (rankname == NULL || !strcmp(rankname,taxonomy->ranks->label[next_parent->rank]))
 		{
-			printresult(next_parent, NULL,taxonomy);
+			printresult(next_parent, NULL,taxonomy, pathDisplay);
 			c++;
 		}
 	}
@ -128,7 +149,7 @@ void gettaxidparents(int32_t taxid, ecotaxonomy_t *taxonomy, char *rankname)
 static void ExitUsage(stat)
        int stat;
 {
-        PP      "usage: ecofind [-d database] [-h] [-l] [-r taxonomic rank] [-p taxid] [-s taxid] <taxon name pattern> ... \n");
+        PP      "usage: ecofind [-d database] [-h] [-l] [-P] [-r taxonomic rank] [-p taxid] [-s taxid] <taxon name pattern> ... \n");
        PP      "type \"ecofind -h\" for help\n");
        if (stat)
            exit(stat);
@ -159,9 +180,11 @@ static void PrintHelp()
        PP		"     Write the database radical without any extension.\n\n");
        PP      "-h : [H]elp - print <this> help\n\n");
        PP      "-l : [L]ist all taxonomic rank available for -r option\n\n");
+        PP      "-P : [P]ath : add a column containing the full path for each displayed taxon\n\n");
        PP      "-p : [P]arents : specifiying this option displays all parental tree's information for the given taxid.\n\n");
        PP      "-r : [R]estrict to given taxonomic rank\n\n");      
        PP      "-s : [S]ons: specifiying this option displays all subtree's information for the given taxid.\n\n");
+        PP      "-P : Display taxonomic [P]ath as suplementary column in output\n\n");
        PP      "arguments:\n");        
        PP      "<taxon> name pattern bearing regular expressions\n\n");
        PP      "------------------------------------------\n");
@ -197,31 +220,36 @@ int main(int argc, char **argv)
 	char			*rankname	= NULL;
 	int32_t			rankfilter 	= 1;
 	int32_t			list 		= 0;
+	int32_t			path 		= 0;
 	
 	ecotx_t 		*subtree_parent;
 	int32_t			count_son = 0;


-	while ((carg = getopt(argc, argv, "had:p:s:r:l")) != -1) {
+	while ((carg = getopt(argc, argv, "had:p:s:r:lP")) != -1) {
 	    switch (carg) {                        
 	       case 's':               	/* path to the database     */
 	          sscanf(optarg,"%d",&subtree);
 	          break;

 	       case 'r':               	/* rank filter     */
-	          rankname = ECOMALLOC(strlen(optarg),"allocation rankname");
+	          rankname = ECOMALLOC(strlen(optarg)+1,"allocation rankname");
 	          strcpy(rankname,optarg);
 	          rankfilter = 0;
 	          break;

 	       case 'd':               	/* path to the database     */
-	          prefix = ECOMALLOC(strlen(optarg),"allocation prefix");
+	          prefix = ECOMALLOC(strlen(optarg)+1,"allocation prefix");
 	          strcpy(prefix,optarg);
 	          break;
 	          
 	       case 'l':               	/* list rank filter options */
 	          list = 1;
 	          break;
+
+	       case 'P':               	/* Path output option */
+	          path=1;
+	          break;
 	
 	       case 'a':               	/* allow alternative names  */
 	          alternative = 1;
@ -279,7 +307,7 @@ int main(int argc, char **argv)
 	/* ----------------------------------------	*/	
 	if (uptree)
 	{
-		gettaxidparents(uptree,taxonomy,rankname);
+		gettaxidparents(uptree,taxonomy,rankname, path);
 		return 0;	
 	}
 	
@ -289,10 +317,10 @@ int main(int argc, char **argv)
 	/* ----------------------------------------	*/		
 	if (subtree)
 	{
-		printheader();
+		printheader(path);
 		subtree_parent = eco_findtaxonbytaxid(taxonomy,subtree);
-		printresult(subtree_parent, NULL,taxonomy);
-		get_son(taxonomy, subtree_parent,&count_son,rankname);
+		printresult(subtree_parent, NULL,taxonomy, path);
+		get_son(taxonomy, subtree_parent,&count_son,rankname, path);
 		printf("#  %d son(s) found\n#\n",count_son);
 		return 0;
 	}
@ -315,7 +343,7 @@ int main(int argc, char **argv)
 		
 		nummatch=0;
 		
-	    printheader();
+	    printheader(path);
 		
 		for (j=0,name=taxonomy->names->names;
 		     j < name_count;
@ -329,7 +357,7 @@ int main(int argc, char **argv)
   			
   			if (!re_match && (alternative || name->is_scientificname) && rankfilter)
   			{
-   				printresult(name->taxon,name,taxonomy);
+   				printresult(name->taxon,name,taxonomy, path);
   				nummatch++;
   			}
   			
--- a/src/ecofind.gz
+++ b/src/ecofind.gz
--- a/src/ecogrep.c
+++ b/src/ecogrep.c
@ -22,18 +22,18 @@ void getLineContent(char *stream, ecoseq_t *seq, ecoseq_t *oligoseq_1, ecoseq_t
 				case 0:
 					seq->AC = strdup(buffer);
 					break;
-				case 4:
+				case 2:
 					sscanf(buffer,"%d",&seq->taxid);
 					break;
 				case 13:
 					oligoseq_1->SQ = strdup(buffer);
 					oligoseq_1->SQ_length = strlen(buffer);
 					break;
-				case 15:
+				case 16:
 					oligoseq_2->SQ = strdup(buffer);
 					oligoseq_2->SQ_length = strlen(buffer);
 					break;
-				case 18:
+				case 20:
 					seq->SQ = strdup(buffer);
 					seq->SQ_length = strlen(buffer);
 					break;
@ -64,7 +64,7 @@ int	ispatternmatching(ecoseq_t *seq, PatternPtr pattern){
 	if (pattern != NULL)
 	{
 		SeqPtr 	apatseq	= NULL;
-		apatseq=ecoseq2apatseq(seq,apatseq);
+		apatseq=ecoseq2apatseq(seq,apatseq,0);
 		return ManberAll(apatseq,pattern,0,0,apatseq->seqlen) > 0;
 	}
 	else return 0;
@ -400,4 +400,4 @@ int main(int argc, char **argv){
 	ECOFREE(restricted_taxid,"Error in free stream");
 	
 	return 0;
-}
+}
--- a/src/ecogrep.gz
+++ b/src/ecogrep.gz
--- a/src/ecoisundertaxon
+++ b/src/ecoisundertaxon
--- a/src/ecopcr.c
+++ b/src/ecopcr.c
@ -1,11 +1,13 @@
 #include "libecoPCR/ecoPCR.h"
+#include "libthermo/nnparams.h"
 #include <stdio.h>
 #include <string.h>
 #include <stdlib.h>
 #include <getopt.h>


-#define VERSION "0.1"
+#define VERSION "0.2"
+

 /* ----------------------------------------------- */
 /* printout help                                   */                                           
@ -21,6 +23,8 @@ static void PrintHelp()
        PP      "usage: ecoPCR [options] <nucleotidic patterns>\n");
        PP      "------------------------------------------\n");
        PP      "options:\n");
+        PP      "-a    : Salt concentration in M for Tm computation (default 0.05 M)\n\n");
+        PP      "-c    : Consider that the database sequences are [c]ircular\n\n");
        PP      "-d    : [D]atabase : to match the expected format, the database\n");
        PP      "        has to be formated first by the ecoPCRFormat.py program located.\n");
        PP      "        in the tools directory.\n");
@ -29,8 +33,11 @@ static void PrintHelp()
        PP      "            .tdx : contains information concerning the taxonomy\n");
        PP      "            .rdx : contains the taxonomy rank\n\n");
        PP      "        ecoPCR needs all the file type. As a result, you have to write the\n");
-        PP      "        database radical without any extension. For example /ecoPCRDB/gbmam\n\n");        
-        PP      "-e    : [E]rror : max error allowed by oligonucleotide (0 by default)\n\n");
+        PP      "        database radical without any extension. For example /ecoPCRDB/gbmam\n\n");
+        PP      "-D    : Keeps the specified number of nucleotides on each side of the in silico \n");
+        PP      "        amplified sequences (including the amplified DNA fragment plus the two target \n");
+        PP      "        sequences of the primers).\n\n");
+        PP      "-e    : [E]rror : max errors allowed by oligonucleotide (0 by default)\n\n");
        PP      "-h    : [H]elp - print <this> help\n\n");
        PP      "-i    : [I]gnore the given taxonomy id.\n");
        PP      "        Taxonomy id are available using the ecofind program.\n");
@ -39,9 +46,11 @@ static void PrintHelp()
        PP      "        super kingdom mode by default.\n\n");
        PP      "-l    : minimum [L]ength : define the minimum amplication length. \n\n");
        PP      "-L    : maximum [L]ength : define the maximum amplicationlength. \n\n");
+        PP      "-m    : Salt correction method for Tm computation (SANTALUCIA : 1\n");
+		PP      "        or OWCZARZY:2, default=1)\n\n");
        PP      "-r    : [R]estricts the search to the given taxonomic id.\n");
        PP      "        Taxonomy id are available using the ecofind program.\n");
-        PP      "        see its help typing ecofind -h for more information.\n");
+        PP      "        see its help typing ecofind -h for more information.\n\n");
        PP      "\n");
        PP      "------------------------------------------\n");
        PP      "first argument : oligonucleotide for direct strand\n\n");
@ -63,11 +72,13 @@ static void PrintHelp()
        PP      "column 13 : strand (direct or reverse)\n");
        PP      "column 14 : first oligonucleotide\n");
        PP      "column 15 : number of errors for the first strand\n");
-        PP      "column 16 : second oligonucleotide\n");
-        PP      "column 17 : number of errors for the second strand\n");
-        PP      "column 18 : amplification length\n");
-        PP      "column 19 : sequence\n");
-        PP      "column 20 : definition\n");
+        PP      "column 16 : Tm for hybridization of primer 1 at this site\n");
+        PP      "column 17 : second oligonucleotide\n");
+        PP      "column 18 : number of errors for the second strand\n");
+        PP      "column 19 : Tm for hybridization of primer 1 at this site\n");
+        PP      "column 20 : amplification length\n");
+        PP      "column 21 : sequence\n");
+        PP      "column 22 : definition\n");
        PP      "------------------------------------------\n");
        PP		" http://www.grenoble.prabi.fr/trac/ecoPCR/\n");
        PP      "------------------------------------------\n\n");        
@ -96,12 +107,15 @@ static void ExitUsage(stat)
 #undef  PP

 void printRepeat(ecoseq_t *seq,
+				 char* primer1, char* primer2,
+				 PNNParams tparm,
                 PatternPtr o1, PatternPtr o2,
                 char strand, 
                 char kingdom,
                 int32_t pos1, int32_t pos2,
                 int32_t err1, int32_t err2,
-                 ecotaxonomy_t *taxonomy)
+                 ecotaxonomy_t *taxonomy,
+                 int32_t delta)
 {
 	char     *AC;
 	int32_t  seqlength;
@ -124,12 +138,18 @@ void printRepeat(ecoseq_t *seq,
 	
 	int32_t  error1;
 	int32_t  error2;
+	int32_t  ldelta,rdelta;
 	
 	char     *amplifia = NULL;
 	int32_t  amplength;
+	double   tm1,tm2;
+	double   tm=0;
 	
+	int32_t i;
+
 	AC = seq->AC;
 	seqlength = seq->SQ_length;
+
 	
 	main_taxon    = &taxonomy->taxons->taxon[seq->taxid];
 	taxid         = main_taxon->taxid;
@ -184,44 +204,81 @@ void printRepeat(ecoseq_t *seq,
 			superkingdom_name  = "###";
 		}
 	
-	amplength = pos2-pos1;     
-	
-	amplifia = getSubSequence(seq->SQ,pos1,pos2);
-	
+
+
+	ldelta=(pos1 <= delta)?pos1:delta;
+
+
+
+	/*rdelta=((pos2+delta)>=seqlength)?seqlength-pos2-1:delta;        */
+	rdelta=((pos2+delta)>=seqlength)?seqlength-pos2:delta;
+
+	amplifia = getSubSequence(seq->SQ,pos1-ldelta,pos2+rdelta);
+	amplength= strlen(amplifia)-rdelta-ldelta;
 	
 	if (strand=='R')
 	{
-		ecoComplementSequence(amplifia);
-		strncpy(oligo1,amplifia,o2->patlen);
+
+	    ecoComplementSequence(amplifia);
+
+		strncpy(oligo1,amplifia + rdelta ,o2->patlen);
+
 		oligo1[o2->patlen]=0;
 		error1=err2;
-		
-		strncpy(oligo2,amplifia + amplength - o1->patlen,o1->patlen);
+
+		strncpy(oligo2, amplifia + rdelta + amplength - o1->patlen,o1->patlen);
 		oligo2[o1->patlen]=0;
 		error2=err1;
 		
-		amplifia+=o2->patlen;
+		if (delta==0)
+			amplifia+=o2->patlen;
+		else
+		{
+			delta=ldelta;
+			ldelta=rdelta+o2->patlen;
+			rdelta=delta+o1->patlen;
+		}
 	}
-	else
+	else /* strand == 'D' */
 	{
-		strncpy(oligo1,amplifia,o1->patlen);
+		strncpy(oligo1,amplifia+ldelta,o1->patlen);
 		oligo1[o1->patlen]=0;
 		error1=err1;
 		
-		strncpy(oligo2,amplifia + amplength - o2->patlen,o2->patlen);
+		strncpy(oligo2,amplifia + ldelta + amplength - o2->patlen,o2->patlen);
 		oligo2[o2->patlen]=0;
 		error2=err2;
 		
-		amplifia+=o1->patlen;
+		if (delta==0)
+			amplifia+=o1->patlen;
+		else
+		{
+			ldelta+=o1->patlen;
+			rdelta+=o2->patlen;
+		}
 		
 	}
 	
-
 	
 	ecoComplementSequence(oligo2);
-	amplifia[amplength - o2->patlen - o1->patlen]=0;
+	if(delta==0)
+		amplifia[amplength - o2->patlen - o1->patlen]=0;
+	else
+	{
+		delta=ldelta+rdelta+amplength-o1->patlen-o2->patlen;
+		for (i=0;i<ldelta;i++)
+			amplifia[i]|=32;
+		for (i=1;i<=rdelta;i++)
+			amplifia[delta-i]|=32;
+
+		amplifia[delta]=0;
+
+	}
 	
-	printf("%-15s | %9d | %8d | %-20s | %8d | %-30s | %8d | %-30s | %8d | %-30s | %8d | %-30s | %c | %-32s | %2d | %-32s | %2d | %5d | %s | %s\n",
+	tm1=nparam_CalcTwoTM(tparm,oligo1,primer1,o1->patlen) - 273.15;
+	tm2=nparam_CalcTwoTM(tparm,oligo2,primer2,o2->patlen) - 273.15;
+	tm = (tm1 < tm2) ? tm1:tm2;
+	printf("%-15s | %9d | %8d | %-20s | %8d | %-30s | %8d | %-30s | %8d | %-30s | %8d | %-30s | %c | %-32s | %2d | %5.2f | %-32s | %2d | %5.2f | %5d | %s | %s\n",
 			AC,
 			seqlength,
 			taxid,
@ -237,12 +294,15 @@ void printRepeat(ecoseq_t *seq,
 			strand,
 			oligo1,
 			error1,
+			tm1,
 			oligo2,
 			error2,
-			amplength,
+			tm2,
+			amplength - o1->patlen - o2->patlen,
 			amplifia,
 			seq->DE
 		  );
+
 }

 int main(int argc, char **argv) 
@ -263,6 +323,7 @@ int main(int argc, char **argv)
 	PatternPtr    o1c;
 	PatternPtr 	  o2c;
 	
+	int32_t       delta=0;
 	int32_t       lmin=0;
 	int32_t       lmax=0;
 	int32_t       error_max=0;
@ -297,9 +358,13 @@ int main(int argc, char **argv)
 	int32_t       *ignored_taxid	= NULL;
 	int32_t		  r=0;
 	int32_t		  g=0;	
+	int32_t		  circular=0;
 	
+	int32_t		  saltmethod=SALT_METHOD_SANTALUCIA;
+	double		  salt=0.05;
+	CNNParams     tparm;

-    while ((carg = getopt(argc, argv, "hd:l:L:e:i:r:k")) != -1) {
+    while ((carg = getopt(argc, argv, "hcd:l:L:e:i:r:km:a:tD:")) != -1) {
    	
     switch (carg) {
                                /* -------------------- */
@ -317,6 +382,12 @@ int main(int argc, char **argv)
           exit(0);
           break;

+           	   	   	   	   	    /* ------------------------- */
+        case 'D':               /* min amplification lenght  */
+        						/* ------------------------- */
+        	sscanf(optarg,"%d",&delta);
+        	break;
+
                                /* ------------------------- */
        case 'l':               /* min amplification lenght  */
                                /* ------------------------- */
@ -359,7 +430,25 @@ int main(int argc, char **argv)
          break;
          
                                /* -------------------- */
-        case '?':               /* bad option           */
+        case 'c':               /* stores the taxonomic id to ignore */
+        						/* --------------------------------- */
+		  circular = 1;
+          break;
+          
+
+					/* --------------------------------- */
+		case 'm':               /* set salt method                   */
+					/* --------------------------------- */
+		sscanf(optarg,"%d",&(saltmethod));
+		break;
+
+					/* --------------------------------- */
+		case 'a':               /* set salt 	         */
+					/* --------------------------------- */
+		sscanf(optarg,"%lf",&(salt));
+		break;
+
+		case '?':               /* bad option           */
                                /* -------------------- */
            errflag++;
   		}
@ -379,6 +468,13 @@ int main(int argc, char **argv)
 		oligo2 = ECOMALLOC(strlen(argv[optind])+1,
                              "Error on oligo1 allocation");
 		strcpy(oligo2,argv[optind]);
+		
+		if (circular)
+		{
+			circular = strlen(oligo1);
+			if (strlen(oligo2)>(size_t)circular)
+				circular = strlen(oligo2);
+		}
 	}
 	else
 		errflag++;
@ -390,6 +486,10 @@ int main(int argc, char **argv)
 			errflag++;
 	}
 	
+	nparam_InitParams(&tparm,DEF_CONC_PRIMERS,
+				 	  DEF_CONC_PRIMERS,
+					  salt,
+					  saltmethod);
 	                  
    if (!oligo1 || !oligo2)
    		errflag++;
@ -403,12 +503,22 @@ int main(int argc, char **argv)
 	o1c = complementPattern(o1);
 	o2c = complementPattern(o2);
 	
+	printf("#@ecopcr-v2\n");
 	printf("#\n");
 	printf("# ecoPCR version %s\n",VERSION);
 	printf("# direct  strand oligo1 : %-32s ; oligo2c : %32s\n", o1->cpat,o2c->cpat);
 	printf("# reverse strand oligo2 : %-32s ; oligo1c : %32s\n", o2->cpat,o1c->cpat);
 	printf("# max error count by oligonucleotide : %d\n",error_max);
 	
+	double tm,tm1,tm2;
+
+	tm1=nparam_CalcSelfTM(&tparm,o1->cpat,o1->patlen) - 273.15;
+	tm2=nparam_CalcSelfTM(&tparm,o2->cpat,o2->patlen) - 273.15;
+	tm = (tm1 < tm2) ? tm1:tm2;
+
+	printf("# optimal Tm for primers 1 : %5.2f\n",tm1);
+	printf("# optimal Tm for primers 2 : %5.2f\n",tm2);
+
 	printf("# database : %s\n",prefix);
 	if (lmin && lmax)
 		printf("# amplifiat length between [%d,%d] bp\n",lmin,lmax);
@ -420,6 +530,10 @@ int main(int argc, char **argv)
 		printf("# output in kingdom mode\n");
 	else
 		printf("# output in superkingdom mode\n");
+	if (circular)
+		printf("# DB sequences are considered as circular\n");
+	else
+		printf("# DB sequences are considered as linear\n");
 	printf("#\n");

 	taxonomy = read_taxonomy(prefix,0);
@ -458,9 +572,9 @@ int main(int argc, char **argv)
 				strncpy(tail,seq->SQ+seq->SQ_length-10,10);
 				tail[10]=0;
 		
-				apatseq=ecoseq2apatseq(seq,apatseq);
+				apatseq=ecoseq2apatseq(seq,apatseq,circular);
 				
-				o1Hits = ManberAll(apatseq,o1,0,0,apatseq->seqlen);
+				o1Hits = ManberAll(apatseq,o1,0,0,apatseq->seqlen+apatseq->circular);
 				o2cHits= 0;
 				
 				if (o1Hits)
@ -472,24 +586,44 @@ int main(int argc, char **argv)
 						length= stktmp->val[stktmp->top-1] + o1->patlen - begin + lmax + o2->patlen;
 					else
 						length= apatseq->seqlen - begin;
-						
+					
+					if (circular)
+					{
+						begin = 0;
+						length=apatseq->seqlen+circular;
+					}	
 					o2cHits = ManberAll(apatseq,o2c,1,begin,length);
 		
 					if (o2cHits)
 						for (i=0; i < o1Hits;i++)
 						{
 							posi = apatseq->hitpos[0]->val[i];
-							erri = apatseq->hiterr[0]->val[i];
-							for (j=0; j < o2cHits; j++)
+														
+							if (posi < apatseq->seqlen)
 							{
-								posj  =apatseq->hitpos[1]->val[j] + o2c->patlen;
-								errj  =apatseq->hiterr[1]->val[j];
-								length=posj - posi + 1  - o1->patlen - o2->patlen;
-								
-								if ((!lmin || (length >= lmin)) &&
-								    (!lmax || (length <= lmax)))
-								    printRepeat(seq,o1,o2c,'D',kingdom_mode,posi,posj,erri,errj,taxonomy);
-									//printf("%s\tD\t%s...%s (%d)\t%d\t%d\t%d\t%d\t%s\n",seq->AC,head,tail,seq->SQ_length,o1Hits,o2cHits,posi,posj,scname);
+								erri = apatseq->hiterr[0]->val[i];
+								for (j=0; j < o2cHits; j++)
+								{
+									posj  =apatseq->hitpos[1]->val[j];
+									
+									if (posj < apatseq->seqlen)
+									{
+										posj+=o2c->patlen;
+										// printf("coucou %d %d %d\n",posi,posj,apatseq->seqlen);
+										errj  =apatseq->hiterr[1]->val[j];
+										length = 0;
+										if (posj > posi)
+											length=posj - posi  - o1->patlen - o2->patlen; 
+										if (posj < posi)
+											length= posj + apatseq->seqlen - posi - o1->patlen - o2->patlen;
+										if (length &&
+											(!lmin || (length >= lmin)) &&
+										    (!lmax || (length <= lmax)))
+										    printRepeat(seq,oligo1,oligo2,&tparm,o1,o2c,'D',kingdom_mode,posi,posj,erri,errj,taxonomy,delta);
+											//printf("%s\tD\t%s...%s (%d)\t%d\t%d\t%d\t%d\t%s\n",seq->AC,head,tail,seq->SQ_length,o1Hits,o2cHits,posi,posj,scname);
+	
+									}
+								}
 							}
 						}
 				}
@ -506,23 +640,43 @@ int main(int argc, char **argv)
 					else
 						length= apatseq->seqlen - begin;
 						
+					if (circular)
+					{
+						begin = 0;
+						length=apatseq->seqlen+circular;
+					}	
+
 					o1cHits = ManberAll(apatseq,o1c,3,begin,length);
 					
 					if (o1cHits)
 						for (i=0; i < o2Hits;i++)
 						{
 							posi = apatseq->hitpos[2]->val[i];
-							erri = apatseq->hiterr[2]->val[i];
-							for (j=0; j < o1cHits; j++)
+
+							if (posi < apatseq->seqlen)
 							{
-								posj=apatseq->hitpos[3]->val[j] + o1c->patlen;
-								errj=apatseq->hiterr[3]->val[j];
-								length=posj - posi + 1 - o1->patlen - o2->patlen;
-								
-								if ((!lmin || (length >= lmin)) &&
-								    (!lmax || (length <= lmax)))
-								    printRepeat(seq,o2,o1c,'R',kingdom_mode,posi,posj,erri,errj,taxonomy);
-									//printf("%s\tR\t%s...%s (%d)\t%d\t%d\t%d\t%d\t%s\n",seq->AC,head,tail,seq->SQ_length,o2Hits,o1cHits,posi,posj,scname);
+								erri = apatseq->hiterr[2]->val[i];
+								for (j=0; j < o1cHits; j++)
+								{
+									posj=apatseq->hitpos[3]->val[j];
+									if (posj < apatseq->seqlen)
+									{
+										posj+=o1c->patlen;
+										errj=apatseq->hiterr[3]->val[j];
+
+										length = 0;
+										if (posj > posi)
+											length=posj - posi + 1  - o2->patlen - o1->patlen; /* - o1->patlen : suppress by <EC> */
+										if (posj < posi)
+											length= posj + apatseq->seqlen - posi - o1->patlen - o2->patlen;
+
+										if (length &&
+											(!lmin || (length >= lmin)) &&
+										    (!lmax || (length <= lmax)))
+										    printRepeat(seq,oligo1,oligo2,&tparm,o2,o1c,'R',kingdom_mode,posi,posj,erri,errj,taxonomy,delta);
+											//printf("%s\tR\t%s...%s (%d)\t%d\t%d\t%d\t%d\t%s\n",seq->AC,head,tail,seq->SQ_length,o2Hits,o1cHits,posi,posj,scname);								
+									}
+								}
 							}
 						}
 				}	
--- a/src/global.mk
+++ b/src/global.mk
@ -1,5 +1,5 @@
 MACHINE=MAC_OS_X
-LIBPATH= -Llibapat -LlibecoPCR
+LIBPATH= -Llibapat -LlibecoPCR -Llibthermo
 MAKEDEPEND = gcc -D$(MACHINE) -M $(CPPFLAGS) -o $*.d $<

 CC=gcc
--- a/src/libapat/Makefile
+++ b/src/libapat/Makefile
@ -9,6 +9,7 @@ SRCS=$(SOURCES)
 OBJECTS= $(patsubst %.c,%.o,$(SOURCES))

 LIBFILE= libapat.a
+RANLIB=ranlib


 include ../global.mk
@ -20,4 +21,4 @@ clean:

 $(LIBFILE): $(OBJECTS)
 	ar -cr $@ $?
-	
+	$(RANLIB) $@
--- a/src/libapat/apat.h
+++ b/src/libapat/apat.h
@ -103,6 +103,7 @@ typedef struct {                        /* sequence             */
    Int32     seqlen;                   /* sequence length      */
    Int32     seqsiz;                   /* sequence buffer size */
    Int32     datsiz;                   /* data buffer size     */
+    Int32     circular;
    UInt8     *data;                    /* data buffer          */
    char      *cseq;                    /* sequence buffer      */
    StackiPtr hitpos[MAX_PATTERN];      /* stack of hit pos.    */
--- a/src/libapat/apat_search.c
+++ b/src/libapat/apat_search.c
@ -80,14 +80,14 @@ int CreateS(Pattern *ppat, Int32 lalpha)
 /* -------------------------------------------- */
 Int32 ManberNoErr(Seq *pseq, Pattern *ppat, int patnum,int begin,int length)
 {
-        Int32     pos;
+        UInt32     pos;
        UInt32    smask, r;
        UInt8     *data;
        StackiPtr *stkpos, *stkerr;
        UInt32    end;
        
        end = begin + length;
-        end = (end <= pseq->seqlen) ? end:pseq->seqlen;
+        end = (end <= (size_t)(pseq->seqlen+pseq->circular)) ? end:(size_t)(pseq->seqlen+pseq->circular);
        

                                        /* create local masks   */
@ -127,7 +127,7 @@ Int32 ManberNoErr(Seq *pseq, Pattern *ppat, int patnum,int begin,int length)
 Int32 ManberSub(Seq *pseq, Pattern *ppat, int patnum,int begin,int length)
 {
        int       e, emax, found;
-        Int32     pos;
+        UInt32     pos;
        UInt32    smask, cmask, sindx;
        UInt32    *pr, r[2 * MAX_PAT_ERR + 2];
        UInt8     *data;
@ -135,7 +135,7 @@ Int32 ManberSub(Seq *pseq, Pattern *ppat, int patnum,int begin,int length)
        UInt32    end;
        
        end = begin + length;
-        end = (end <= pseq->seqlen) ? end:pseq->seqlen;
+        end = (end <= (size_t)(pseq->seqlen+pseq->circular)) ? end:(size_t)(pseq->seqlen+pseq->circular);

                                        /* create local masks   */
        emax = ppat->maxerr;
@ -193,7 +193,7 @@ Int32 ManberSub(Seq *pseq, Pattern *ppat, int patnum,int begin,int length)
 Int32 ManberIndel(Seq *pseq, Pattern *ppat, int patnum,int begin,int length)
 {
        int       e, emax, found;
-        Int32     pos;
+        UInt32     pos;
        UInt32    smask, cmask, sindx;
        UInt32    *pr, r[2 * MAX_PAT_ERR + 2];
        UInt8     *data;
@ -201,7 +201,7 @@ Int32 ManberIndel(Seq *pseq, Pattern *ppat, int patnum,int begin,int length)
        UInt32    end;
        
        end = begin + length;
-        end = (end <= pseq->seqlen) ? end:pseq->seqlen;
+        end = (end <= (size_t)(pseq->seqlen+pseq->circular)) ? end:(size_t)(pseq->seqlen+pseq->circular);

                                        /* create local masks   */
        emax = ppat->maxerr;
--- a/src/libecoPCR/Makefile
+++ b/src/libecoPCR/Makefile
@ -15,6 +15,7 @@ SRCS=$(SOURCES)
 OBJECTS= $(patsubst %.c,%.o,$(SOURCES))

 LIBFILE= libecoPCR.a
+RANLIB= ranlib


 include ../global.mk
@ -27,3 +28,4 @@ clean:

 $(LIBFILE): $(OBJECTS)
 	ar -cr $@ $?
+	$(RANLIB) $@
--- a/src/libecoPCR/ecoPCR.h
+++ b/src/libecoPCR/ecoPCR.h
@ -220,7 +220,7 @@ econameidx_t     *read_nameidx(const char *filename,ecotaxonomy_t *taxonomy);
 	 * @return pointer to a taxonomy index structure
 	 */
 
-ecotxidx_t       *read_taxonomyidx(const char *filename);
+ecotxidx_t       *read_taxonomyidx(const char *filename,const char *filename2);

 ecotaxonomy_t    *read_taxonomy(const char *prefix,int32_t readAlternativeName);

@ -251,7 +251,7 @@ int32_t  delete_apatseq(SeqPtr pseq);
 PatternPtr buildPattern(const char *pat, int32_t error_max);
 PatternPtr complementPattern(PatternPtr pat);

-SeqPtr ecoseq2apatseq(ecoseq_t *in,SeqPtr out);
+SeqPtr ecoseq2apatseq(ecoseq_t *in,SeqPtr out,int32_t circular);

 char *ecoComplementPattern(char *nucAcSeq);
 char *ecoComplementSequence(char *nucAcSeq);
--- a/src/libecoPCR/ecoapat.c
+++ b/src/libecoPCR/ecoapat.c
@ -50,10 +50,13 @@ void EncodeSequence(SeqPtr seq)

        while (*cseq) {

-            *data++ = (IS_UPPER(*cseq) ? *cseq - 'A' : 0x0);
-
+            *data = (IS_UPPER(*cseq) ? *cseq - 'A' : 0x0);
+            data++;
            cseq++;
        }
+        
+        for (i=0,cseq=seq->cseq;i < seq->circular; i++,cseq++,data++)
+            *data = (IS_UPPER(*cseq) ? *cseq - 'A' : 0x0);

        for (i = 0 ; i < MAX_PATTERN ; i++)
            seq->hitpos[i]->top = seq->hiterr[i]->top = 0;
@ -63,7 +66,7 @@ void EncodeSequence(SeqPtr seq)
 #undef IS_UPPER


-SeqPtr ecoseq2apatseq(ecoseq_t *in,SeqPtr out)
+SeqPtr ecoseq2apatseq(ecoseq_t *in,SeqPtr out,int32_t circular)
 {
        int    i;

@ -83,20 +86,22 @@ SeqPtr ecoseq2apatseq(ecoseq_t *in,SeqPtr out)
 	        }
 		}

+		
 		out->name    = in->AC;
 		out->seqsiz = out->seqlen = in->SQ_length;
-
+		out->circular = circular;
+		
 		if (!out->data)
 		{
-			out->data = ECOMALLOC(out->seqlen *sizeof(UInt8),
+			out->data = ECOMALLOC((out->seqlen+circular) *sizeof(UInt8),
 		    	     			  "Error in Allocation of a new Seq data member");    
-		   	out->datsiz=  out->seqlen;
+		   	out->datsiz=  out->seqlen+circular;
 		}
-		else if (out->seqlen >= out->datsiz)
+		else if ((out->seqlen +circular) >= out->datsiz)
 		{
-			out->data = ECOREALLOC(out->data,out->seqlen,
+			out->data = ECOREALLOC(out->data,(out->seqlen+circular),
 			                      "Error during Seq data buffer realloc");
-		   	out->datsiz=  out->seqlen;			                      
+		   	out->datsiz=  out->seqlen+circular;			                      
 		}

 		out->cseq = in->SQ;
@ -191,4 +196,4 @@ PatternPtr complementPattern(PatternPtr pat)
 	
 	return pattern;
 		
-}
+}
--- a/src/libecoPCR/ecodna.c
+++ b/src/libecoPCR/ecodna.c
@ -104,27 +104,52 @@ char *ecoComplementSequence(char *nucAcSeq)


 char *getSubSequence(char* nucAcSeq,int32_t begin,int32_t end)
+/*
+   extract subsequence from nucAcSeq [begin,end[
+*/
 {
 	static char *buffer  = NULL;
 	static int32_t buffSize= 0;
 	int32_t length;
 	
-	length = end - begin;
-	
-	if (length >= buffSize)
+	if (begin < end)
 	{
-		buffSize = length+1;
-		if (buffer)
-			buffer=ECOREALLOC(buffer,buffSize,
-					   	      "Error in reallocating sub sequence buffer");
-		else
-			buffer=ECOMALLOC(buffSize,
-			          		 "Error in allocating sub sequence buffer");
-			
+		length = end - begin;
+		
+		if (length >= buffSize)
+		{
+			buffSize = length+1;
+			if (buffer)
+				buffer=ECOREALLOC(buffer,buffSize,
+						   	      "Error in reallocating sub sequence buffer");
+			else
+				buffer=ECOMALLOC(buffSize,
+				          		 "Error in allocating sub sequence buffer");
+				
+		}
+		
+		strncpy(buffer,nucAcSeq + begin,length);
+		buffer[length]=0;
+	}
+	else
+	{
+		length = end + strlen(nucAcSeq) - begin;
+		
+		if (length >= buffSize)
+		{
+			buffSize = length+1;
+			if (buffer)
+				buffer=ECOREALLOC(buffer,buffSize,
+						   	      "Error in reallocating sub sequence buffer");
+			else
+				buffer=ECOMALLOC(buffSize,
+				          		 "Error in allocating sub sequence buffer");
+				
+		}
+		strncpy(buffer,nucAcSeq+begin,length - end);
+		strncpy(buffer+(length-end),nucAcSeq ,end);
+		buffer[length]=0;
 	}
-	
-	strncpy(buffer,nucAcSeq + begin,length);
-	buffer[length]=0;
 	
 	return buffer;
 }
--- a/src/libecoPCR/ecofilter.c
+++ b/src/libecoPCR/ecofilter.c
@ -10,10 +10,11 @@ int eco_is_taxid_included(	ecotaxonomy_t *taxonomy,
 	
 	taxon = eco_findtaxonbytaxid(taxonomy, taxid);
 	
-	for (i=0; i < tab_len; i++)
-		if ( (taxon->taxid == restricted_taxid[i]) ||
-			 (eco_isundertaxon(taxon, restricted_taxid[i])) )
-			return 1;
+	if (taxon)
+		for (i=0; i < tab_len; i++)
+			if ( (taxon->taxid == restricted_taxid[i]) ||
+				 (eco_isundertaxon(taxon, restricted_taxid[i])) )
+				return 1;
 	
 	return 0;
-}
+}
--- a/src/libecoPCR/ecoseq.c
+++ b/src/libecoPCR/ecoseq.c
@ -4,6 +4,7 @@
 #include <zlib.h>
 #include <string.h>
 #include <stdio.h>
+#include <ctype.h>

 static FILE *open_seqfile(const char *prefix,int32_t index);

@ -11,32 +12,32 @@ static FILE *open_seqfile(const char *prefix,int32_t index);
 ecoseq_t *new_ecoseq()
 {
 	void *tmp;
-	
+
 	tmp = ECOMALLOC(sizeof(ecoseq_t),"Allocate new ecoseq structure");
-	
+
 	return tmp;
 }

 int32_t delete_ecoseq(ecoseq_t * seq)
 {
-	
+
 	if (seq)
 	{
 		if (seq->AC)
 			ECOFREE(seq->AC,"Free sequence AC");
-			
+
 		if (seq->DE)
 			ECOFREE(seq->DE,"Free sequence DE");
-			
+
 		if (seq->SQ)
 			ECOFREE(seq->SQ,"Free sequence SQ");
-			
+
 		ECOFREE(seq,"Free sequence structure");
-		
+
 		return 0;
-			
+
 	}
-	
+
 	return 1;
 }

@ -49,9 +50,9 @@ ecoseq_t *new_ecoseq_with_data( char *AC,
 	ecoseq_t *tmp;
 	int32_t lstr;
 	tmp = new_ecoseq();
-	
+
 	tmp->taxid=taxid_idx;
-	
+
 	if (AC)
 		{
 			lstr =strlen(AC);
@ -97,12 +98,14 @@ ecoseq_t *readnext_ecoseq(FILE *f)
 	int32_t  comp_status;
 	unsigned long int seqlength;
 	int32_t  rs;
-	
+	char *c;
+	int32_t i;
+
 	raw = read_ecorecord(f,&rs);
-	
+
 	if (!raw)
 		return NULL;
-		
+
 	if (is_big_endian())
 	{
 		raw->CSQ_length = swap_int32_t(raw->CSQ_length);
@ -110,44 +113,48 @@ ecoseq_t *readnext_ecoseq(FILE *f)
 		raw->SQ_length  = swap_int32_t(raw->SQ_length);
 		raw->taxid      = swap_int32_t(raw->taxid);
 	}
-	
+
 	seq = new_ecoseq();
-	
+
 	seq->taxid = raw->taxid;
-	
+
    seq->AC    = ECOMALLOC(strlen(raw->AC) +1,
                           "Allocate Sequence Accesion number");
    strncpy(seq->AC,raw->AC,strlen(raw->AC));

-                           
+
    seq->DE    = ECOMALLOC(raw->DE_length+1,
                           "Allocate Sequence definition");
    strncpy(seq->DE,raw->data,raw->DE_length);
-    
+
 	seqlength = seq->SQ_length = raw->SQ_length;
-    
+
    compressed = raw->data + raw->DE_length;

    seq->SQ = ECOMALLOC(seqlength+1,
                        "Allocate sequence buffer");
-                        
+
    comp_status = uncompress((unsigned char*)seq->SQ,
                             &seqlength,
                             (unsigned char*)compressed,
                             raw->CSQ_length);
-    
+
    if (comp_status != Z_OK)
    	ECOERROR(ECO_IO_ERROR,"I cannot uncompress sequence data");
-    
+
+    for (c=seq->SQ,i=0;i<seqlength;c++,i++)
+    	*c=toupper(*c);
+
+
 	return seq;
 }

 /**
 * Open the sequences database (.sdx file)
- * @param	prefix	name of the database (radical without extension) 
+ * @param	prefix	name of the database (radical without extension)
 * @param	index 	integer
- * 
- * @return	file object 
+ *
+ * @return	file object
 */
 FILE *open_seqfile(const char *prefix,int32_t index)
 {
@ -161,22 +168,22 @@ FILE *open_seqfile(const char *prefix,int32_t index)
 	                           "%s_%03d.sdx",
 	                           prefix,
 	                           index);
-	                           
-			fprintf(stderr,"# Coucou %s\n",filename_buffer);
-	                           
+
+		//	fprintf(stderr,"# Coucou %s\n",filename_buffer);
+

 	if (filename_length >= 1024)
 		ECOERROR(ECO_ASSERT_ERROR,"file name is too long");

 	filename_buffer[filename_length]=0;
-		
+
 	input=open_ecorecorddb(filename_buffer,&seqcount,0);
-	
+
 	if (input)
 		fprintf(stderr,"# Reading file %s containing %d sequences...\n",
 				filename_buffer,
 				seqcount);
-				
+
 	return input;
 }

@ -186,38 +193,38 @@ ecoseq_t *ecoseq_iterator(const char *prefix)
 	static int32_t current_file_idx = 1;
 	static char    current_prefix[1024];
 	ecoseq_t       *seq;
-	
+
 	if (prefix)
 	{
 		current_file_idx = 1;

 		if (current_seq_file)
 			fclose(current_seq_file);
-			
+
 		strncpy(current_prefix,prefix,1023);
 		current_prefix[1024]=0;
-		
+
 		current_seq_file = open_seqfile(current_prefix,
 		 							    current_file_idx);
-		
+
 		if (!current_seq_file)
 			return NULL;
-			
+
 	}
-	
+
 	seq = readnext_ecoseq(current_seq_file);
-	
+
 	if (!seq && feof(current_seq_file))
 	{
 		current_file_idx++;
 		fclose(current_seq_file);
 		current_seq_file = open_seqfile(current_prefix,
 		 							    current_file_idx);
-		 							    
-		
+
+
 		if (current_seq_file)
 			seq = readnext_ecoseq(current_seq_file);
 	}
-	
+
 	return seq;
-}
+}
--- a/src/libecoPCR/ecotax.c
+++ b/src/libecoPCR/ecotax.c
@ -10,23 +10,41 @@ static ecotx_t *readnext_ecotaxon(FILE *f,ecotx_t *taxon);
 * @param	pointer to the database (.tdx file) 
 * @return	a ecotxidx_t structure 
 */
-ecotxidx_t     *read_taxonomyidx(const char *filename)
+ecotxidx_t     *read_taxonomyidx(const char *filename,const char *filename2)
 {
 	int32_t      count;
+	int32_t      count2;
 	FILE         *f;
+	FILE         *f2;
 	ecotxidx_t *index;
 	int32_t      i;
 	
-	f = open_ecorecorddb(filename,&count,1);
+	f  = open_ecorecorddb(filename,&count,1);
+	f2 = open_ecorecorddb(filename2,&count2,0);
+
+
 	
-	index = (ecotxidx_t*) ECOMALLOC(sizeof(ecotxidx_t) + sizeof(ecotx_t) * (count-1),
+	index = (ecotxidx_t*) ECOMALLOC(sizeof(ecotxidx_t) + sizeof(ecotx_t) * (count+count2-1),
 	                                  "Allocate taxonomy");
 	 
-	index->count=count;                                         
+	index->count=count+count2;
+
+	fprintf(stderr,"Reading %d taxa...\n",count);
 	for (i=0; i < count; i++){
 		readnext_ecotaxon(f,&(index->taxon[i]));
 		index->taxon[i].parent=index->taxon + (int32_t)index->taxon[i].parent;
 	}					
+
+	if (count2>0)
+		fprintf(stderr,"Reading %d local taxa...\n",count2);
+	else
+		fprintf(stderr,"No local taxon\n");
+
+	for (i=0; i < count2; i++){
+		readnext_ecotaxon(f2,&(index->taxon[count+i]));
+		index->taxon[count+i].parent=index->taxon + (int32_t)index->taxon[count+i].parent;
+	}
+
 	return index;
 }

@ -111,6 +129,7 @@ ecotaxonomy_t    *read_taxonomy(const char *prefix,int32_t readAlternativeName)
 {
 	ecotaxonomy_t *tax;
 	char          *filename;
+	char          *filename2;
 	int           buffsize;
 	
 	tax = ECOMALLOC(sizeof(ecotaxonomy_t),
@ -120,14 +139,17 @@ ecotaxonomy_t    *read_taxonomy(const char *prefix,int32_t readAlternativeName)
 	
 	filename = ECOMALLOC(buffsize,
 	                     "Allocate filename");
+	filename2= ECOMALLOC(buffsize,
+	                     "Allocate filename");
 	
 	snprintf(filename,buffsize,"%s.rdx",prefix);
 	
 	tax->ranks = read_rankidx(filename);
 	
 	snprintf(filename,buffsize,"%s.tdx",prefix);
+	snprintf(filename2,buffsize,"%s.ldx",prefix);
 	
-	tax->taxons = read_taxonomyidx(filename);
+	tax->taxons = read_taxonomyidx(filename,filename2);
 	
 	if (readAlternativeName)
 	{
@ -326,4 +348,4 @@ ecotx_t *eco_getsuperkingdom(ecotx_t *taxon,
 		ECOERROR(ECO_ASSERT_ERROR,"No taxonomy defined");
 		
 	return eco_findtaxonatrank(taxon,rankindex);
-}
+}
--- a/src/libthermo/Makefile
+++ b/src/libthermo/Makefile
@ -0,0 +1,22 @@
+
+SOURCES = nnparams.c 
+
+SRCS=$(SOURCES)
+         
+OBJECTS= $(patsubst %.c,%.o,$(SOURCES))
+
+LIBFILE= libthermo.a
+RANLIB= ranlib
+
+
+include ../global.mk
+
+
+all: $(LIBFILE)
+
+clean:
+	rm -rf $(OBJECTS) $(LIBFILE)
+
+$(LIBFILE): $(OBJECTS)
+	ar -cr $@ $?
+	$(RANLIB) $@
--- a/src/libthermo/nnparams.c
+++ b/src/libthermo/nnparams.c
@ -0,0 +1,619 @@
+/*
+ *  nnparams.cpp
+ *  PHunterLib
+ *
+ *  Nearest Neighbor Model / Parameters
+ *
+ *  Created by Tiayyba Riaz on 7/2/09.
+ *
+ */
+
+#include <memory.h>
+#include <math.h>
+#include <stdio.h>
+#include <string.h>
+#include"nnparams.h"
+
+static char bpencoder[] = {	1,							// A
+		                   	0,                          // b
+		                   	2,                          // C
+		                   	0,0,0,                      // d, e, f
+		                   	3,                          // G
+		                   	0,0,0,0,0,0,0,0,0,0,0,0,    // h,i,j,k,l,m,n,o,p,q,r,s
+		                   	4,0,                        // T,U
+		                   	0,0,0,0,0};                 // v,w,x,y,z
+
+
+double forbidden_entropy;
+
+
+double nparam_GetInitialEntropy(PNNParams nparm)
+{
+	return 	-5.9f+nparm->rlogc;
+}
+
+
+//Retrieve Enthalpy for given NN-Pair from parameter table
+double nparam_GetEnthalpy(PNNParams nparm, char x0, char x1, char y0, char y1)
+{
+	return ndH(x0,x1,y0,y1); //xx, yx are already numbers
+}
+
+
+//Retrieve Entropy for given NN-Pair from parameter table
+double nparam_GetEntropy(PNNParams nparm, char x0, char x1, char y0, char y1)
+{
+	//xx and yx are already numbers
+	char nx0=x0;//nparam_convertNum(x0);
+	char nx1=x1;//nparam_convertNum(x1);
+	char ny0=y0;//nparam_convertNum(y0);
+	char ny1=y1;//nparam_convertNum(y1);
+	double answer = ndS(nx0,nx1,ny0,ny1);
+	/*Salt correction Santalucia*/
+	if (nparm->saltMethod == SALT_METHOD_SANTALUCIA) {
+		if(nx0!=5 && 1<= nx1 && nx1<=4) {
+			answer += 0.5*nparm->kfac;
+		}
+		if(ny1!=5 && 1<= ny0 && ny0<=4) {
+			answer += 0.5*nparm->kfac;
+		}
+	}
+	/*Salt correction Owczarzy*/
+	if (nparm->saltMethod == SALT_METHOD_OWCZARZY) {
+		double logk = log(nparm->kplus);
+		answer += ndH(nx0,nx1,ny0,ny1)*((4.29 * nparm->gcContent-3.95)*0.00001*logk+ 0.0000094*logk*logk);
+	}
+	return answer;
+}
+
+/* PURPOSE:    Return melting temperature TM for given entropy and enthalpy
+*              Assuming a one-state transition and using the formula
+*                TM = dH / (dS + R ln(Ct/4))
+*              entropy = dS + R ln Ct/4 (must already be included!)
+*              enthaklpy = dH
+*              where
+*                dH = enthalpy
+*                dS = entropy
+*                R  = Boltzmann factor
+*                Ct = Strand Concentration
+*
+*  PARAMETERS:
+*	entrypy and enthalpy
+*
+*  RETURN VALUE:
+* 	temperature
+*/
+
+double nparam_CalcTM(double entropy,double enthalpy)
+{
+	double tm = 0;               // absolute zero - return if model fails!
+    if (enthalpy>=forbidden_enthalpy)   //||(entropy==-cfact))
+		return 0;
+	if (entropy<0)         // avoid division by zero and model errors!
+	{
+	  tm = enthalpy/entropy;// - kfac; //LKFEB
+		if (tm<0)
+			return 0;
+	}
+	return tm;
+}
+
+
+void nparam_InitParams(PNNParams nparm, double c1, double c2, double kp, int sm)
+{
+	nparm->Ct1 = c1;
+	nparm->Ct2 = c2;
+	nparm->kplus = kp;
+	int maxCT = 1;
+	if(nparm->Ct2 > nparm->Ct1)
+	{
+		maxCT = 2;
+	}
+	double ctFactor;
+ 	if(nparm->Ct1 == nparm->Ct2)
+	{
+		ctFactor = nparm->Ct1/2;
+	}
+	else if (maxCT == 1)
+	{
+		ctFactor = nparm->Ct1-nparm->Ct2/2;
+	}
+	else
+	{
+		ctFactor = nparm->Ct2-nparm->Ct1/2;
+	}
+	nparm->rlogc = R * log(ctFactor);
+	forbidden_entropy = nparm->rlogc;
+	nparm->kfac = 0.368 * log (nparm->kplus);
+	nparm->saltMethod = sm;
+	int x,y,a,b;  // variables used as counters...
+
+	// Set all parameters to zero!
+	memset(nparm->dH,0,sizeof(nparm->dH));
+	memset(nparm->dS,0,sizeof(nparm->dS));
+
+	// Set all X-/Y-, -X/Y- and X-/-Y so, that TM will be VERY small!
+	for (x=1;x<=4;x++)
+	{
+		for (y=1;y<=4;y++)
+		{
+			ndH(0,x,y,0)=forbidden_enthalpy;
+			ndS(0,x,y,0)=forbidden_entropy;
+			ndH(x,0,0,y)=forbidden_enthalpy;
+			ndS(x,0,0,y)=forbidden_entropy;
+			ndH(x,0,y,0)=forbidden_enthalpy;
+			ndS(x,0,y,0)=forbidden_entropy;
+			// forbid X-/Y$ and X$/Y- etc., i.e. terminal must not be paired with gap!
+			ndH(x,5,y,0)=forbidden_enthalpy;
+			ndS(x,5,y,0)=forbidden_entropy;
+			ndH(x,0,y,5)=forbidden_enthalpy;
+			ndS(x,0,y,5)=forbidden_entropy;
+			ndH(5,x,0,y)=forbidden_enthalpy;
+			ndS(5,x,0,y)=forbidden_entropy;
+			ndH(0,x,5,y)=forbidden_enthalpy;
+			ndS(0,x,5,y)=forbidden_entropy;
+			// forbid X$/-Y etc.
+			ndH(x,5,0,y)=forbidden_enthalpy;
+			ndS(x,5,0,y)=forbidden_entropy;
+			ndH(x,0,5,y)=forbidden_enthalpy;
+			ndS(x,0,5,y)=forbidden_entropy;
+			ndH(5,x,y,0)=forbidden_enthalpy;
+			ndS(5,x,y,0)=forbidden_entropy;
+			ndH(0,x,y,5)=forbidden_enthalpy;
+			ndS(0,x,y,5)=forbidden_entropy;
+
+		}
+		// also, forbid x-/-- and --/x-, i.e. no two inner gaps paired
+		ndH(x,0,0,0)=forbidden_enthalpy;
+		ndS(x,0,0,0)=forbidden_entropy;
+		ndH(0,0,x,0)=forbidden_enthalpy;
+		ndS(0,0,x,0)=forbidden_entropy;
+		// x-/-$
+		ndH(x,0,0,5)=forbidden_enthalpy;
+		ndS(x,0,0,5)=forbidden_entropy;
+		ndH(5,0,0,x)=forbidden_enthalpy;
+		ndS(5,0,0,x)=forbidden_entropy;
+		ndH(0,5,x,0)=forbidden_enthalpy;
+		ndS(x,0,0,5)=forbidden_entropy;
+		ndH(0,x,5,0)=forbidden_enthalpy;
+		ndS(0,x,5,0)=forbidden_entropy;
+	}
+	// forbid --/--
+	ndH(0,0,0,0)=forbidden_enthalpy;
+	ndS(0,0,0,0)=forbidden_entropy;
+
+	ndH(5,0,0,0)=forbidden_enthalpy;
+	ndS(5,0,0,0)=forbidden_entropy;
+	ndH(0,0,5,0)=forbidden_enthalpy;
+	ndS(0,0,5,0)=forbidden_entropy;
+	ndH(0,5,5,0)=forbidden_enthalpy;
+	ndS(0,5,5,0)=forbidden_entropy;
+
+	// Interior loops (double Mismatches)
+    #define iloop_entropy -0.97f
+    #define iloop_enthalpy 0.0f
+	for (x=1; x<=4; x++)
+		for (y=1; y<=4; y++)
+			for (a=1; a<=4; a++)
+				for (b=1; b<=4; b++)
+					// AT and CG pair, and as A=1, C=2, G=3, T=4 this means
+					// we have Watson-Crick pairs if (x+a==5) and (y+b)==5.
+					if (!((x+a==5)||(y+b==5)))
+					{
+						// No watson-crick-pair, i.e. double mismatch!
+						// set enthalpy/entropy to loop expansion!
+						ndH(x,y,a,b) = iloop_enthalpy;
+						ndS(x,y,a,b) = iloop_entropy;
+					}
+
+	// xy/-- and --/xy (Bulge Loops of size > 1)
+    #define bloop_entropy -1.3f
+    #define bloop_enthalpy 0.0f
+	for (x=1; x<=4; x++)
+		for (y=1; y<=4; y++)
+		{
+			ndH(x,y,0,0) = bloop_enthalpy;
+			ndS(x,y,0,0) = bloop_entropy;
+			ndH(0,0,x,y) = bloop_enthalpy;
+			ndS(0,0,x,y) = bloop_entropy;
+		}
+
+    // x-/ya abd xa/y- as well as -x/ay and ax/-y
+	// bulge opening and closing parameters with
+	// adjacent matches / mismatches
+	// obulge_mism and cbulge_mism chosen so high to avoid
+	//     AAAAAAAAA
+	//     T--G----T
+	// being better than
+	//     AAAAAAAAA
+	//     TG------T
+    #define obulge_match_H (-2.66f * 1000)
+    #define obulge_match_S -14.22f
+    #define cbulge_match_H (-2.66f * 1000)
+    #define cbulge_match_S -14.22f
+    #define obulge_mism_H (0.0f * 1000)
+    #define obulge_mism_S -6.45f
+    #define cbulge_mism_H 0.0f
+    #define cbulge_mism_S -6.45f
+	for (x=1; x<=4; x++)
+		for (y=1; y<=4; y++)
+			for (a=1; a<=4; a++)
+			{
+				if (x+y==5)  // other base pair matches!
+				{
+					ndH(x,0,y,a)=obulge_match_H;  // bulge opening
+					ndS(x,0,y,a)=obulge_match_S;
+					ndH(x,a,y,0)=obulge_match_H;
+					ndS(x,a,y,0)=obulge_match_S;
+					ndH(0,x,a,y)=cbulge_match_H;  // bulge closing
+					ndS(0,x,a,y)=cbulge_match_S;
+					ndH(a,x,0,y)=cbulge_match_H;
+					ndS(a,x,0,y)=cbulge_match_S;
+				}
+				else
+				{           // mismatch in other base pair!
+					ndH(x,0,y,a)=obulge_mism_H;   // bulge opening
+					ndS(x,0,y,a)=obulge_mism_S;
+					ndH(x,a,y,0)=obulge_mism_H;
+					ndS(x,a,y,0)=obulge_mism_S;
+					ndH(0,x,a,y)=cbulge_mism_H;   // bulge closing
+					ndS(0,x,a,y)=cbulge_mism_S;
+					ndH(a,x,0,y)=cbulge_mism_H;
+					ndS(a,x,0,y)=cbulge_mism_S;
+				}
+			}
+
+	// Watson-Crick pairs (note that only ten are unique, as obviously
+	// 5'-AG-3'/3'-TC-5'  =  5'-CT-3'/3'-GA-5' etc.
+	ndH(1,1,4,4)=-7.6f*1000;  ndS(1,1,4,4)=-21.3f;   // AA/TT 04
+	ndH(1,2,4,3)=-8.4f*1000;  ndS(1,2,4,3)=-22.4f;   // AC/TG adapted GT/CA
+	ndH(1,3,4,2)=-7.8f*1000;  ndS(1,3,4,2)=-21.0f;   // AG/TC adapted CT/GA
+	ndH(1,4,4,1)=-7.2f*1000;  ndS(1,4,4,1)=-20.4f;   // AT/TA 04
+	ndH(2,1,3,4)=-8.5f*1000;  ndS(2,1,3,4)=-22.7f;   // CA/GT 04
+	ndH(2,2,3,3)=-8.0f*1000;  ndS(2,2,3,3)=-19.9f;   // CC/GG adapted GG/CC
+	ndH(2,3,3,2)=-10.6f*1000; ndS(2,3,3,2)=-27.2f;   // CG/GC 04
+	ndH(2,4,3,1)=-7.8f*1000;  ndS(2,4,3,1)=-21.0f;   // CT/GA 04
+	ndH(3,1,2,4)=-8.2f*1000;  ndS(3,1,2,4)=-22.2f;   // GA/CT 04
+	ndH(3,2,2,3)=-9.8f*1000;  ndS(3,2,2,3)=-24.4f;   // GC/CG 04
+	ndH(3,3,2,2)=-8.0f*1000;  ndS(3,3,2,2)=-19.9f;   // GG/CC 04
+	ndH(3,4,2,1)=-8.4f*1000;  ndS(3,4,2,1)=-22.4f;   // GT/CA 04
+	ndH(4,1,1,4)=-7.2f*1000;  ndS(4,1,1,4)=-21.3f;   // TA/AT 04
+	ndH(4,2,1,3)=-8.2f*1000;  ndS(4,2,1,3)=-22.2f;   // TC/AG adapted GA/CT
+	ndH(4,3,1,2)=-8.5f*1000;  ndS(4,3,1,2)=-22.7f;   // TG/AC adapted CA/GT
+	ndH(4,4,1,1)=-7.6f*1000;  ndS(4,4,1,1)=-21.3f;   // TT/AA adapted AA/TT
+
+    // A-C Mismatches (Values for pH 7.0)
+	ndH(1,1,2,4)=7.6f*1000;   ndS(1,1,2,4)=20.2f;    // AA/CT
+	ndH(1,1,4,2)=2.3f*1000;   ndS(1,1,4,2)=4.6f;     // AA/TC
+	ndH(1,2,2,3)=-0.7f*1000;  ndS(1,2,2,3)=-3.8f;    // AC/CG
+	ndH(1,2,4,1)=5.3f*1000;   ndS(1,2,4,1)=14.6f;    // AC/TA
+	ndH(1,3,2,2)=0.6f*1000;   ndS(1,3,2,2)=-0.6f;    // AG/CC
+	ndH(1,4,2,1)=5.3f*1000;   ndS(1,4,2,1)=14.6f;    // AT/CA
+	ndH(2,1,1,4)=3.4f*1000;   ndS(2,1,1,4)=8.0f;     // CA/AT
+	ndH(2,1,3,2)=1.9f*1000;   ndS(2,1,3,2)=3.7f;     // CA/GC
+	ndH(2,2,1,3)=5.2f*1000;   ndS(2,2,1,3)=14.2f;    // CC/AG
+	ndH(2,2,3,1)=0.6f*1000;   ndS(2,2,3,1)=-0.6f;    // CC/GA
+	ndH(2,3,1,2)=1.9f*1000;   ndS(2,3,1,2)=3.7f;     // CG/AC
+	ndH(2,4,1,1)=2.3f*1000;   ndS(2,4,1,1)=4.6f;     // CT/AA
+	ndH(3,1,2,2)=5.2f*1000;   ndS(3,1,2,2)=14.2f;    // GA/CC
+	ndH(3,2,2,1)=-0.7f*1000;  ndS(3,2,2,1)=-3.8f;    // GC/CA
+	ndH(4,1,1,2)=3.4f*1000;   ndS(4,1,1,2)=8.0f;     // TA/AC
+	ndH(4,2,1,1)=7.6f*1000;   ndS(4,2,1,1)=20.2f;    // TC/AA
+
+	// C-T Mismatches
+	ndH(1,2,4,4)=0.7f*1000;   ndS(1,2,4,4)=0.2f;     // AC/TT
+	ndH(1,4,4,2)=-1.2f*1000;  ndS(1,4,4,2)=-6.2f;    // AT/TC
+	ndH(2,1,4,4)=1.0f*1000;   ndS(2,1,4,4)=0.7f;     // CA/TT
+	ndH(2,2,3,4)=-0.8f*1000;  ndS(2,2,3,4)=-4.5f;    // CC/GT
+	ndH(2,2,4,3)=5.2f*1000;   ndS(2,2,4,3)=13.5f;    // CC/TG
+	ndH(2,3,4,2)=-1.5f*1000;  ndS(2,3,4,2)=-6.1f;    // CG/TC
+	ndH(2,4,3,2)=-1.5f*1000;  ndS(2,4,3,2)=-6.1f;    // CT/GC
+	ndH(2,4,4,1)=-1.2f*1000;  ndS(2,4,4,1)=-6.2f;    // CT/TA
+	ndH(3,2,2,4)=2.3f*1000;   ndS(3,2,2,4)=5.4f;     // GC/CT
+	ndH(3,4,2,2)=5.2f*1000;   ndS(3,4,2,2)=13.5f;    // GT/CC
+	ndH(4,1,2,4)=1.2f*1000;   ndS(4,1,2,4)=0.7f;     // TA/CT
+	ndH(4,2,2,3)=2.3f*1000;   ndS(4,2,2,3)=5.4f;     // TC/CG
+	ndH(4,2,1,4)=1.2f*1000;   ndS(4,2,1,4)=0.7f;     // TC/AT
+	ndH(4,3,2,2)=-0.8f*1000;  ndS(4,3,2,2)=-4.5f;    // TG/CC
+	ndH(4,4,2,1)=0.7f*1000;   ndS(4,4,2,1)=0.2f;     // TT/CA
+	ndH(4,4,1,2)=1.0f*1000;   ndS(4,4,1,2)=0.7f;     // TT/AC
+
+	// G-A Mismatches
+	ndH(1,1,3,4)=3.0f*1000;   ndS(1,1,3,4)=7.4f;     // AA/GT
+	ndH(1,1,4,3)=-0.6f*1000;  ndS(1,1,4,3)=-2.3f;    // AA/TG
+	ndH(1,2,3,3)=0.5f*1000;   ndS(1,2,3,3)=3.2f;     // AC/GG
+	ndH(1,3,3,2)=-4.0f*1000;  ndS(1,3,3,2)=-13.2f;   // AG/GC
+	ndH(1,3,4,1)=-0.7f*1000;  ndS(1,3,4,1)=-2.3f;    // AG/TA
+	ndH(1,4,3,1)=-0.7f*1000;  ndS(1,4,3,1)=-2.3f;    // AT/GA
+	ndH(2,1,3,3)=-0.7f*1000;  ndS(2,1,3,3)=-2.3f;    // CA/GG
+	ndH(2,3,3,1)=-4.0f*1000;  ndS(2,3,3,1)=-13.2f;   // CG/GA
+	ndH(3,1,1,4)=0.7f*1000;   ndS(3,1,1,4)=0.7f;     // GA/AT
+	ndH(3,1,2,3)=-0.6f*1000;  ndS(3,1,2,3)=-1.0f;    // GA/CG
+	ndH(3,2,1,3)=-0.6f*1000;  ndS(3,2,1,3)=-1.0f;    // GC/AG
+	ndH(3,3,1,2)=-0.7f*1000;  ndS(3,3,1,2)=-2.3f;    // GG/AC
+	ndH(3,3,2,1)=0.5f*1000;   ndS(3,3,2,1)=3.2f;     // GG/CA
+	ndH(3,4,1,1)=-0.6f*1000;  ndS(3,4,1,1)=-2.3f;    // GT/AA
+	ndH(4,1,1,3)=0.7f*1000;   ndS(4,1,1,3)=0.7f;     // TA/AG
+	ndH(4,3,1,1)=3.0f*1000;   ndS(4,3,1,1)=7.4f;     // TG/AA
+
+	// G-T Mismatches
+	ndH(1,3,4,4)=1.0f*1000;   ndS(1,3,4,4)=0.9f;     // AG/TT
+	ndH(1,4,4,3)=-2.5f*1000;  ndS(1,4,4,3)=-8.3f;    // AT/TG
+	ndH(2,3,3,4)=-4.1f*1000;  ndS(2,3,3,4)=-11.7f;   // CG/GT
+	ndH(2,4,3,3)=-2.8f*1000;  ndS(2,4,3,3)=-8.0f;    // CT/GG
+	ndH(3,1,4,4)=-1.3f*1000;  ndS(3,1,4,4)=-5.3f;    // GA/TT
+	ndH(3,2,4,3)=-4.4f*1000;  ndS(3,2,4,3)=-12.3f;   // GC/TG
+	ndH(3,3,2,4)=3.3f*1000;   ndS(3,3,2,4)=10.4f;    // GG/CT
+	ndH(3,3,4,2)=-2.8f*1000;  ndS(3,3,4,2)=-8.0f;    // GG/TC
+//	ndH(3,3,4,4)=5.8f*1000;   ndS(3,3,4,4)=16.3f;    // GG/TT
+	ndH(3,4,2,3)=-4.4f*1000;  ndS(3,4,2,3)=-12.3f;   // GT/CG
+	ndH(3,4,4,1)=-2.5f*1000;  ndS(3,4,4,1)=-8.3f;    // GT/TA
+//	ndH(3,4,4,3)=4.1f*1000;   ndS(3,4,4,3)=9.5f;     // GT/TG
+	ndH(4,1,3,4)=-0.1f*1000;  ndS(4,1,3,4)=-1.7f;    // TA/GT
+	ndH(4,2,3,3)=3.3f*1000;   ndS(4,2,3,3)=10.4f;    // TC/GG
+	ndH(4,3,1,4)=-0.1f*1000;  ndS(4,3,1,4)=-1.7f;    // TG/AT
+	ndH(4,3,3,2)=-4.1f*1000;  ndS(4,3,3,2)=-11.7f;   // TG/GC
+//	ndH(4,3,3,4)=-1.4f*1000;  ndS(4,3,3,4)=-6.2f;    // TG/GT
+	ndH(4,4,1,3)=-1.3f*1000;  ndS(4,4,1,3)=-5.3f;    // TT/AG
+	ndH(4,4,3,1)=1.0f*1000;   ndS(4,4,3,1)=0.9f;     // TT/GA
+//	ndH(4,4,3,3)=5.8f*1000;   ndS(4,4,3,3)=16.3f;    // TT/GG
+
+	// A-A Mismatches
+	ndH(1,1,1,4)=4.7f*1000;   ndS(1,1,1,4)=12.9f;    // AA/AT
+	ndH(1,1,4,1)=1.2f*1000;   ndS(1,1,4,1)=1.7f;     // AA/TA
+	ndH(1,2,1,3)=-2.9f*1000;  ndS(1,2,1,3)=-9.8f;    // AC/AG
+	ndH(1,3,1,2)=-0.9f*1000;  ndS(1,3,1,2)=-4.2f;    // AG/AC
+	ndH(1,4,1,1)=1.2f*1000;   ndS(1,4,1,1)=1.7f;     // AT/AA
+	ndH(2,1,3,1)=-0.9f*1000;  ndS(2,1,3,1)=-4.2f;    // CA/GA
+    ndH(3,1,2,1)=-2.9f*1000;  ndS(3,1,2,1)=-9.8f;    // GA/CA
+	ndH(4,1,1,1)=4.7f*1000;   ndS(4,1,1,1)=12.9f;    // TA/AA
+
+	// C-C Mismatches
+	ndH(1,2,4,2)=0.0f*1000;   ndS(1,2,4,2)=-4.4f;    // AC/TC
+	ndH(2,1,2,4)=6.1f*1000;   ndS(2,1,2,4)=16.4f;    // CA/CT
+	ndH(2,2,2,3)=3.6f*1000;   ndS(2,2,2,3)=8.9f;     // CC/CG
+	ndH(2,2,3,2)=-1.5f*1000;  ndS(2,2,3,2)=-7.2f;    // CC/GC
+	ndH(2,3,2,2)=-1.5f*1000;  ndS(2,3,2,2)=-7.2f;    // CG/CC
+	ndH(2,4,2,1)=0.0f*1000;   ndS(2,4,2,1)=-4.4f;    // CT/CA
+	ndH(3,2,2,2)=3.6f*1000;   ndS(3,2,2,2)=8.9f;     // GC/CC
+	ndH(4,2,1,2)=6.1f*1000;   ndS(4,2,1,2)=16.4f;    // TC/AC
+
+	// G-G Mismatches
+	ndH(1,3,4,3)=-3.1f*1000;  ndS(1,3,4,3)=-9.5f;    // AG/TG
+	ndH(2,3,3,3)=-4.9f*1000;  ndS(2,3,3,3)=-15.3f;   // CG/GG
+	ndH(3,1,3,4)=1.6f*1000;   ndS(3,1,3,4)=3.6f;     // GA/GT
+	ndH(3,2,3,3)=-6.0f*1000;  ndS(3,2,3,3)=-15.8f;   // GC/GG
+	ndH(3,3,2,3)=-6.0f*1000;  ndS(3,3,2,3)=-15.8f;   // GG/CG
+	ndH(3,3,3,2)=-4.9f*1000;  ndS(3,3,3,2)=-15.3f;   // GG/GC
+	ndH(3,4,3,1)=-3.1f*1000;  ndS(3,4,3,1)=-9.5f;    // GT/GA
+	ndH(4,3,1,3)=1.6f*1000;   ndS(4,3,1,3)=3.6f;     // TG/AG
+
+	// T-T Mismatches
+	ndH(1,4,4,4)=-2.7f*1000;  ndS(1,4,4,4)=-10.8f;   // AT/TT
+	ndH(2,4,3,4)=-5.0f*1000;  ndS(2,4,3,4)=-15.8f;   // CT/GT
+	ndH(3,4,2,4)=-2.2f*1000;  ndS(3,4,2,4)=-8.4f;    // GT/CT
+	ndH(4,1,4,4)=0.2f*1000;   ndS(4,1,4,4)=-1.5f;    // TA/TT
+	ndH(4,2,4,3)=-2.2f*1000;  ndS(4,2,4,3)=-8.4f;    // TC/TG
+	ndH(4,3,4,2)=-5.0f*1000;  ndS(4,3,4,2)=-15.8f;   // TG/TC
+	ndH(4,4,1,4)=0.2f*1000;   ndS(4,4,1,4)=-1.5f;    // TT/AT
+	ndH(4,4,4,1)=-2.7f*1000;  ndS(4,4,4,1)=-10.8f;   // TT/TA
+
+	// Dangling Ends
+	ndH(5,1,1,4)=-0.7f*1000;  ndS(5,1,1,4)=-0.8f;    // $A/AT
+	ndH(5,1,2,4)=4.4f*1000;   ndS(5,1,2,4)=14.9f;    // $A/CT
+	ndH(5,1,3,4)=-1.6f*1000;  ndS(5,1,3,4)=-3.6f;    // $A/GT
+	ndH(5,1,4,4)=2.9f*1000;   ndS(5,1,4,4)=10.4f;    // $A/TT
+	ndH(5,2,1,3)=-2.1f*1000;  ndS(5,2,1,3)=-3.9f;    // $C/AG
+	ndH(5,2,2,3)=-0.2f*1000;  ndS(5,2,2,3)=-0.1f;    // $C/CG
+	ndH(5,2,3,3)=-3.9f*1000;  ndS(5,2,3,3)=-11.2f;   // $C/GG
+	ndH(5,2,4,3)=-4.4f*1000;  ndS(5,2,4,3)=-13.1f;   // $C/TG
+	ndH(5,3,1,2)=-5.9f*1000;  ndS(5,3,1,2)=-16.5f;   // $G/AC
+	ndH(5,3,2,2)=-2.6f*1000;  ndS(5,3,2,2)=-7.4f;    // $G/CC
+	ndH(5,3,3,2)=-3.2f*1000;  ndS(5,3,3,2)=-10.4f;   // $G/GC
+	ndH(5,3,4,2)=-5.2f*1000;  ndS(5,3,4,2)=-15.0f;   // $G/TC
+	ndH(5,4,1,1)=-0.5f*1000;  ndS(5,4,1,1)=-1.1f;    // $T/AA
+	ndH(5,4,2,1)=4.7f*1000;   ndS(5,4,2,1)=14.2f;    // $T/CA
+	ndH(5,4,3,1)=-4.1f*1000;  ndS(5,4,3,1)=-13.1f;   // $T/GA
+	ndH(5,4,4,1)=-3.8f*1000;  ndS(5,4,4,1)=-12.6f;   // $T/TA
+	ndH(1,5,4,1)=-2.9f*1000;  ndS(1,5,4,1)=-7.6f;    // A$/TA
+	ndH(1,5,4,2)=-4.1f*1000;  ndS(1,5,4,2)=-13.0f;   // A$/TC
+	ndH(1,5,4,3)=-4.2f*1000;  ndS(1,5,4,3)=-15.0f;   // A$/TG
+	ndH(1,5,4,4)=-0.2f*1000;  ndS(1,5,4,4)=-0.5f;    // A$/TT
+	ndH(1,1,5,4)=0.2f*1000;   ndS(1,1,5,4)=2.3f;     // AA/$T
+	ndH(1,1,4,5)=-0.5f*1000;  ndS(1,1,4,5)=-1.1f;    // AA/T$
+	ndH(1,2,5,3)=-6.3f*1000;  ndS(1,2,5,3)=-17.1f;   // AC/$G
+	ndH(1,2,4,5)=4.7f*1000;   ndS(1,2,4,5)=14.2f;    // AC/T$
+	ndH(1,3,5,2)=-3.7f*1000;  ndS(1,3,5,2)=-10.0f;   // AG/$C
+	ndH(1,3,4,5)=-4.1f*1000;  ndS(1,3,4,5)=-13.1f;   // AG/T$
+	ndH(1,4,5,1)=-2.9f*1000;  ndS(1,4,5,1)=-7.6f;    // AT/$A
+	ndH(1,4,4,5)=-3.8f*1000;  ndS(1,4,4,5)=-12.6f;   // AT/T$
+	ndH(2,5,3,1)=-3.7f*1000;  ndS(2,5,3,1)=-10.0f;   // C$/GA
+	ndH(2,5,3,2)=-4.0f*1000;  ndS(2,5,3,2)=-11.9f;   // C$/GC
+	ndH(2,5,3,3)=-3.9f*1000;  ndS(2,5,3,3)=-10.9f;   // C$/GG
+	ndH(2,5,3,4)=-4.9f*1000;  ndS(2,5,3,4)=-13.8f;   // C$/GT
+	ndH(2,1,5,4)=0.6f*1000;   ndS(2,1,5,4)=3.3f;     // CA/$T
+	ndH(2,1,3,5)=-5.9f*1000;  ndS(2,1,3,5)=-16.5f;   // CA/G$
+	ndH(2,2,5,3)=-4.4f*1000;  ndS(2,2,5,3)=-12.6f;   // CC/$G
+	ndH(2,2,3,5)=-2.6f*1000;  ndS(2,2,3,5)=-7.4f;    // CC/G$
+	ndH(2,3,5,2)=-4.0f*1000;  ndS(2,3,5,2)=-11.9f;   // CG/$C
+	ndH(2,3,3,5)=-3.2f*1000;  ndS(2,3,3,5)=-10.4f;   // CG/G$
+	ndH(2,4,5,1)=-4.1f*1000;  ndS(2,4,5,1)=-13.0f;   // CT/$A
+	ndH(2,4,3,5)=-5.2f*1000;  ndS(2,4,3,5)=-15.0f;   // CT/G$
+	ndH(3,5,2,1)=-6.3f*1000;  ndS(3,5,2,1)=-17.1f;   // G$/CA
+	ndH(3,5,2,2)=-4.4f*1000;  ndS(3,5,2,2)=-12.6f;   // G$/CC
+	ndH(3,5,2,3)=-5.1f*1000;  ndS(3,5,2,3)=-14.0f;   // G$/CG
+	ndH(3,5,2,4)=-4.0f*1000;  ndS(3,5,2,4)=-10.9f;   // G$/CT
+	ndH(3,1,5,4)=-1.1f*1000;  ndS(3,1,5,4)=-1.6f;    // GA/$T
+	ndH(3,1,2,5)=-2.1f*1000;  ndS(3,1,2,5)=-3.9f;    // GA/C$
+	ndH(3,2,5,3)=-5.1f*1000;  ndS(3,2,5,3)=-14.0f;   // GC/$G
+	ndH(3,2,2,5)=-0.2f*1000;  ndS(3,2,2,5)=-0.1f;    // GC/C$
+	ndH(3,3,5,2)=-3.9f*1000;  ndS(3,3,5,2)=-10.9f;   // GG/$C
+	ndH(3,3,2,5)=-3.9f*1000;  ndS(3,3,2,5)=-11.2f;   // GG/C$
+	ndH(3,4,5,1)=-4.2f*1000;  ndS(3,4,5,1)=-15.0f;   // GT/$A
+	ndH(3,4,2,5)=-4.4f*1000;  ndS(3,4,2,5)=-13.1f;   // GT/C$
+	ndH(4,5,1,1)=0.2f*1000;   ndS(4,5,1,1)=2.3f;     // T$/AA
+	ndH(4,5,1,2)=0.6f*1000;   ndS(4,5,1,2)=3.3f;     // T$/AC
+	ndH(4,5,1,3)=-1.1f*1000;  ndS(4,5,1,3)=-1.6f;    // T$/AG
+	ndH(4,5,1,4)=-6.9f*1000;  ndS(4,5,1,4)=-20.0f;   // T$/AT
+	ndH(4,1,5,4)=-6.9f*1000;  ndS(4,1,5,4)=-20.0f;   // TA/$T
+	ndH(4,1,1,5)=-0.7f*1000;  ndS(4,1,1,5)=-0.7f;    // TA/A$
+	ndH(4,2,5,3)=-4.0f*1000;  ndS(4,2,5,3)=-10.9f;   // TC/$G
+	ndH(4,2,1,5)=4.4f*1000;   ndS(4,2,1,5)=14.9f;    // TC/A$
+	ndH(4,3,5,2)=-4.9f*1000;  ndS(4,3,5,2)=-13.8f;   // TG/$C
+	ndH(4,3,1,5)=-1.6f*1000;  ndS(4,3,1,5)=-3.6f;    // TG/A$
+	ndH(4,4,5,1)=-0.2f*1000;  ndS(4,4,5,1)=-0.5f;    // TT/$A
+	ndH(4,4,1,5)=2.9f*1000;   ndS(4,4,1,5)=10.4f;    // TT/A$
+
+	return;
+}
+
+int nparam_CountGCContent(char * seq ) {
+	int lseq = strlen(seq);
+	int k;
+	double count = 0;
+	for( k=0;k<lseq;k++) {
+		if (seq[k] == 'G' || seq[k] == 'C' ) {
+			count+=1;
+		}
+	}
+	return count;
+}
+
+void nparam_CleanSeq (char* inseq, char* outseq, int len)
+{
+	int seqlen = strlen (inseq);
+	int i, j;
+
+	if (len != 0)
+		seqlen = len;
+
+	outseq[0]='x';
+
+	for (i = 0, j = 0; i < seqlen && outseq[0]; i++,j++)
+	{
+		switch (inseq[i])
+		{
+		case 'a':
+		case '\0':
+		case 'A':
+			outseq[j] = 'A'; break;
+		case 'c':
+		case '\1':
+		case 'C':
+			outseq[j] = 'C'; break;
+		case 'g':
+		case '\2':
+		case 'G':
+			outseq[j] = 'G'; break;
+		case 't':
+		case '\3':
+		case 'T':
+			outseq[j] = 'T'; break;
+		default:
+			outseq[0]=0;
+		}
+	}
+	outseq[j] = '\0';
+}
+
+//Calculate TM for given sequence against its complement
+double nparam_CalcSelfTM(PNNParams nparm, char* seq, int len)
+{
+	const unsigned long long minus1 = 0xFFFFFFFFFFFFFFFFLLU;
+	const double NaN = *((double*)&minus1);
+	double thedH = 0;
+	//double thedS = nparam_GetInitialEntropy(nparm);
+	double thedS = -5.9f+nparm->rlogc;
+	double mtemp;
+	char c1;
+	char c2;
+	char c3;
+	char c4;
+	unsigned int i;
+	char nseq[50];
+	char *useq = seq;
+
+	nparam_CleanSeq (seq, nseq, len);
+	if (!nseq[0])
+	         return NaN;
+	useq = nseq;
+
+	for ( i=1;i<len;i++)
+	{
+		c1 = GETREVCODE(useq[i-1]); //nparam_getComplement(seq[i-1],1);
+		c2 = GETREVCODE(useq[i]); //nparam_getComplement(seq[i],1);
+		c3 = GETNUMCODE(useq[i-1]);
+		c4 = GETNUMCODE(useq[i]);
+
+
+		thedH += nparm->dH[c3][c4][c1][c2];//nparam_GetEnthalpy(nparm, c3,c4,c1,c2);
+		thedS += nparam_GetEntropy(nparm, c3,c4,c1,c2);
+	}
+	//printf("------------------\n");
+	mtemp = nparam_CalcTM(thedS,thedH);
+		//fprintf(stderr,"Enthalpy: %f, entropy: %f, seq: %s  rloc=%f\n", thedH, thedS, useq, nparm->rlogc);
+		//exit (0);
+	return mtemp;
+}
+
+double nparam_CalcTwoTM(PNNParams nparm, char* seq1, char* seq2, int len)
+{
+	const unsigned long long minus1 = 0xFFFFFFFFFFFFFFFFLLU;
+	const double NaN = *((double*)&minus1);
+	double thedH = 0;
+	//double thedS = nparam_GetInitialEntropy(nparm);
+	double thedS = -5.9f+nparm->rlogc;
+	double mtemp;
+	char c1;
+	char c2;
+	char c3;
+	char c4;
+	unsigned int i;
+	char nseq1[50];
+	char nseq2[50];
+	char *useq1;
+	char *useq2;
+
+	nparam_CleanSeq (seq1, nseq1, len);
+	if (!nseq1[0])
+	         return NaN;
+	useq1 = nseq1;
+
+	nparam_CleanSeq (seq2, nseq2, len);
+	if (!nseq2[0])
+	         return NaN;
+	useq2 = nseq2;
+
+	//fprintf (stderr,"Primer : %s\n",useq);
+	for ( i=1;i<len;i++)
+	{
+		c1 = GETREVCODE(useq2[i-1]); //nparam_getComplement(seq[i-1],1);
+		c2 = GETREVCODE(useq2[i]);   //nparam_getComplement(seq[i],1);
+		c3 = GETNUMCODE(useq1[i-1]);
+		c4 = GETNUMCODE(useq1[i]);
+
+		//fprintf (stderr,"Primer : %s %f %f %d %d, %d %d %f\n",useq,thedH,thedS,(int)c3,(int)c4,(int)c1,(int)c2,nparam_GetEnthalpy(nparm, c3,c4,c1,c2));
+
+		thedH += nparm->dH[c3][c4][c1][c2];//nparam_GetEnthalpy(nparm, c3,c4,c1,c2);
+		thedS += nparam_GetEntropy(nparm, c3,c4,c1,c2);
+	}
+	//fprintf(stderr,"------------------\n");
+	mtemp = nparam_CalcTM(thedS,thedH);
+	//if (mtemp == 0)
+	//{
+	//	fprintf(stderr,"Enthalpy: %f, entropy: %f, seq: %s\n", thedH, thedS, useq);
+		//exit (0);
+	//}
+	return mtemp;
+}
+
+double calculateMeltingTemperatureBasic (char * seq) {
+	int gccount;
+	double temp;
+	int seqlen;
+
+	seqlen = strlen (seq);
+	gccount = nparam_CountGCContent (seq);
+	temp = 64.9 + 41*(gccount - 16.4)/seqlen;
+	return temp;
+}
--- a/src/libthermo/nnparams.h
+++ b/src/libthermo/nnparams.h
@ -0,0 +1,63 @@
+/*
+ *  nnparams.h
+ *  PHunterLib
+ *
+ * Nearest Neighbor Model Parameters
+ *
+ *  Created by Tiayyba Riaz on 02/07/09.
+ *
+ */
+
+#ifndef NNPARAMS_H_
+#define NNPARAMS_H_
+
+#include <math.h>
+#include <string.h>
+//#include "../libecoprimer/ecoprimer.h"
+
+// following defines to simplify coding...
+#define ndH(a,b,c,d) nparm->dH[(int)a][(int)b][(int)c][(int)d]
+#define ndS(a,b,c,d) nparm->dS[(int)a][(int)b][(int)c][(int)d]
+#define forbidden_enthalpy 1000000000000000000.0f
+#define	R 1.987f
+#define	SALT_METHOD_SANTALUCIA 1
+#define	SALT_METHOD_OWCZARZY 2
+
+#define DEF_CONC_PRIMERS 0.0000008
+#define DEF_CONC_SEQUENCES 0
+#define DEF_SALT 0.05
+
+#define GETNUMCODE(a) bpencoder[a - 'A']
+#define GETREVCODE(a) 5-bpencoder[a - 'A']
+
+
+extern double forbidden_entropy;
+
+
+typedef struct CNNParams_st
+{
+	double Ct1;
+	double Ct2;
+	double rlogc;
+	double kplus;
+	double kfac;
+	int saltMethod;
+	double gcContent;
+	double new_TM;
+	double dH[6][6][6][6];  // A-C-G-T + gap + initiation (dangling end, $ sign)
+	double dS[6][6][6][6];
+}CNNParams, * PNNParams;
+
+void nparam_InitParams(PNNParams nparm, double c1, double c2, double kp, int sm);
+int nparam_CountGCContent(char * seq );
+double nparam_GetEntropy(PNNParams nparm, char x0, char x1, char y0, char y1);
+double nparam_GetEnthalpy(PNNParams nparm, char x0, char x1, char y0, char y1);
+double nparam_CalcTM(double entropy,double enthalpy);
+double nparam_CalcSelfTM(PNNParams nparm, char* seq, int len);
+double nparam_CalcTwoTM(PNNParams nparm, char* seq1, char* seq2, int len);
+
+double nparam_GetInitialEntropy(PNNParams nparm) ;
+double calculateMeltingTemperatureBasic (char * seq);
+//void getThermoProperties (ppair_t* pairs, size_t count, poptions_t options);
+
+#endif
--- a/tools/ecoPCRFormat.py
+++ b/tools/ecoPCRFormat.py
@ -7,6 +7,12 @@ import sys
 import time
 import getopt

+try:
+    import psycopg2
+    _dbenable=True
+except ImportError:
+    _dbenable=False
+
 #####
 #
 #
@ -215,7 +221,56 @@ def readTaxonomyDump(taxdir):
    
    return taxonomy,ranks,alternativeName,index

+def readTaxonomyDB(dbname):
+    connection = psycopg2.connect(database=dbname)
+    
+    cursor = connection.cursor()
+    cursor.execute("select numid,rank,parent from ncbi_taxonomy.taxon")
+    taxonomy=[list(x) for x in cursor]

+    cursor.execute("select rank_class from ncbi_taxonomy.taxon_rank_class order by rank_class")
+    ranks=cursor.fetchall()
+    ranks = dict(map(None,(x[0] for x in ranks),xrange(len(ranks))))
+    
+    print >>sys.stderr,"Sorting taxons..."
+    taxonomy.sort(taxonCmp)
+
+    print >>sys.stderr,"Indexing taxonomy..."
+    index = {}
+    for t in taxonomy:
+        index[t[0]]=bsearchTaxon(taxonomy, t[0])
+    
+    print >>sys.stderr,"Indexing parent and rank..."
+    for t in taxonomy:
+        t[1]=ranks[t[1]]
+        try:
+            t[2]=index[t[2]]
+        except KeyError,e:
+            if t[2] is None and t[0]==1:
+                t[2]=index[t[0]]
+            else:
+                raise e
+        
+    cursor.execute("select taxid,name,category from ncbi_taxonomy.name")
+    
+    alternativeName=[]
+    for taxid,name,classname in cursor:
+        alternativeName.append((name,classname,index[taxid]))
+        if classname == 'scientific name':
+            taxonomy[index[taxid]].append(name)
+    
+    cursor.execute("select old_numid,current_numid from ncbi_taxonomy.taxon_id_alias")
+ 
+    print >>sys.stderr,"Adding taxid alias..."
+    for taxid,current in cursor:
+        if current is not None:
+            index[taxid]=index[current]
+        else:
+            index[taxid]=None
+            
+       
+    return taxonomy,ranks,alternativeName,index
+    
 #####
 #
 #
@ -293,16 +348,19 @@ def emblEntryParser(entry):

 ######################

+_fastaSplit=re.compile(';\W*')
+
 def parseFasta(seq):
+    seq=seq.split('\n')
    title = seq[0].strip()[1:].split(None,1)
    id=title[0]
    if len(title) == 2:
-        field = title[1].split('; ')
+        field = _fastaSplit.split(title[1])
    else:
        field=[]
-    info = dict(x.split('=') for x in field if '=' in x)
+    info = dict(x.split('=',1) for x in field if '=' in x)
    definition = ' '.join([x for x in field if '=' not in x])
-    seq=(''.join([x.strip() for x in seq[1:]])).upper()
+    seq=(''.join([x.strip() for x in seq[1:]])).upper()   
    return id,seq,definition,info

  
@ -527,9 +585,10 @@ def ecoParseOptions(arguments):
           }
    
    o,filenames = getopt.getopt(arguments,
-                                'ht:n:gfe',
+                                'ht:T:n:gfe',
                                ['help',
                                 'taxonomy=',
+                                 'taxonomy_db=',
                                 'name=',
                                 'genbank',
                                 'fasta',
@ -540,7 +599,11 @@ def ecoParseOptions(arguments):
            printHelp()
            exit()
        elif name in ('-t','--taxonomy'):
+            opt['taxmod']='dump'
            opt['taxdir']=value
+        elif name in ('-T','--taxonomy_db'):
+            opt['taxmod']='db'
+            opt['taxdb']=value
        elif name in ('-n','--name'):
            opt['prefix']=value
        elif name in ('-g','--genbank'):
@ -578,7 +641,11 @@ if __name__ == '__main__':
    
    opt,filenames = ecoParseOptions(sys.argv[1:])
    
-    taxonomy = readTaxonomyDump(opt['taxdir'])
+    if opt['taxmod']=='dump':
+        taxonomy = readTaxonomyDump(opt['taxdir'])
+    elif opt['taxmod']=='db':
+        taxonomy = readTaxonomyDB(opt['taxdb'])
+        
   
    ecoDBWriter(opt['prefix'], taxonomy, filenames, opt['parser'])
Author	SHA1	Message	Date
Celine Mercier	194ec811f4	Fixes #2 by adding the missing -D option in the help	2015-05-19 13:52:35 +02:00
Eric Coissac	126bf80670	Convert svn:ignore properties to .gitignore.	2015-05-16 17:51:46 +02:00
Frédéric Boyer	46d086b215	unsufficient space allocated for handling strings in arguments git-svn-id: https://www.grenoble.prabi.fr/svn/LECASofts/ecoPCR/trunk@595 60f365c0-8329-0410-b2a4-ec073aeeaa1d	2013-03-07 09:25:16 +00:00
Frédéric Boyer	0a62ff49cc	MOD: updated the help to include the -P option git-svn-id: https://www.grenoble.prabi.fr/svn/LECASofts/ecoPCR/trunk@424 60f365c0-8329-0410-b2a4-ec073aeeaa1d	2012-05-16 11:56:36 +00:00
Frédéric Boyer	2452df90de	MOD: Added a [P]ath option displaying for each taxon its full path git-svn-id: https://www.grenoble.prabi.fr/svn/LECASofts/ecoPCR/trunk@423 60f365c0-8329-0410-b2a4-ec073aeeaa1d	2012-05-16 11:43:33 +00:00
Frédéric Boyer	745d50cfa4	MOD: Corrected condition in getSon to handle the root of the taxonomy git-svn-id: https://www.grenoble.prabi.fr/svn/LECASofts/ecoPCR/trunk@422 60f365c0-8329-0410-b2a4-ec073aeeaa1d	2012-05-16 07:52:28 +00:00
Eric Coissac	e2fe83fcb7	remove extra obitools directory from ecoPCR subversion archive git-svn-id: https://www.grenoble.prabi.fr/svn/LECASofts/ecoPCR/trunk@418 60f365c0-8329-0410-b2a4-ec073aeeaa1d	2012-05-07 09:31:08 +00:00
Frédéric Boyer	2a118eedda	MOD: In the printRepeat function, corrected rdelta and ldelta management git-svn-id: https://www.grenoble.prabi.fr/svn/LECASofts/ecoPCR/trunk@417 60f365c0-8329-0410-b2a4-ec073aeeaa1d	2012-05-07 09:14:09 +00:00
Céline Mercier	93c530e090	removed the "without temperature" option git-svn-id: https://www.grenoble.prabi.fr/svn/LECASofts/ecoPCR/trunk@416 60f365c0-8329-0410-b2a4-ec073aeeaa1d	2012-05-04 14:53:33 +00:00
Eric Coissac	4e5d8893e5	git-svn-id: https://www.grenoble.prabi.fr/svn/LECASofts/ecoPCR/trunk@390 60f365c0-8329-0410-b2a4-ec073aeeaa1d	2011-12-05 12:59:34 +00:00
Eric Coissac	957a59eb5d	Add management of local taxa from the new extension of the OBI Taxonomy library git-svn-id: https://www.grenoble.prabi.fr/svn/LECASofts/ecoPCR/trunk@315 60f365c0-8329-0410-b2a4-ec073aeeaa1d	2011-07-19 06:44:47 +00:00
Eric Coissac	9adf426abf	delta bug git-svn-id: https://www.grenoble.prabi.fr/svn/LECASofts/ecoPCR/trunk@310 60f365c0-8329-0410-b2a4-ec073aeeaa1d	2011-06-30 15:26:36 +00:00
Eric Coissac	ae528e48f4	delta bug git-svn-id: https://www.grenoble.prabi.fr/svn/LECASofts/ecoPCR/trunk@309 60f365c0-8329-0410-b2a4-ec073aeeaa1d	2011-06-30 15:12:38 +00:00
Eric Coissac	f53cc6d500	patch on printing git-svn-id: https://www.grenoble.prabi.fr/svn/LECASofts/ecoPCR/trunk@299 60f365c0-8329-0410-b2a4-ec073aeeaa1d	2011-06-15 21:54:33 +00:00
Eric Coissac	8313c67a9b	syntax debug on ecopcr.c git-svn-id: https://www.grenoble.prabi.fr/svn/LECASofts/ecoPCR/trunk@297 60f365c0-8329-0410-b2a4-ec073aeeaa1d	2011-05-25 16:35:30 +00:00
Eric Coissac	01173d22cf	add an hidden -D option git-svn-id: https://www.grenoble.prabi.fr/svn/LECASofts/ecoPCR/trunk@296 60f365c0-8329-0410-b2a4-ec073aeeaa1d	2011-05-25 15:41:22 +00:00
Eric Coissac	87c2496447	patch a bug in Tm computation git-svn-id: https://www.grenoble.prabi.fr/svn/LECASofts/ecoPCR/trunk@260 60f365c0-8329-0410-b2a4-ec073aeeaa1d	2010-05-23 12:30:16 +00:00
Eric Coissac	9867859237	patch for 64bits constants git-svn-id: https://www.grenoble.prabi.fr/svn/LECASofts/ecoPCR/trunk@244 60f365c0-8329-0410-b2a4-ec073aeeaa1d	2010-02-24 15:10:11 +00:00
Eric Coissac	f6f39f58fe	patch Tm calculation to return NaN if one of the two sequence is composed with letters different than ACGT git-svn-id: https://www.grenoble.prabi.fr/svn/LECASofts/ecoPCR/trunk@243 60f365c0-8329-0410-b2a4-ec073aeeaa1d	2010-02-24 15:00:11 +00:00
Eric Coissac	7331dd5612	git-svn-id: https://www.grenoble.prabi.fr/svn/LECASofts/ecoPCR/trunk@242 60f365c0-8329-0410-b2a4-ec073aeeaa1d	2010-01-22 09:21:04 +00:00
Eric Coissac	0214be011e	git-svn-id: https://www.grenoble.prabi.fr/svn/LECASofts/ecoPCR/trunk@241 60f365c0-8329-0410-b2a4-ec073aeeaa1d	2010-01-22 09:20:09 +00:00
Eric Coissac	1c30a8604f	git-svn-id: https://www.grenoble.prabi.fr/svn/LECASofts/ecoPCR/trunk@240 60f365c0-8329-0410-b2a4-ec073aeeaa1d	2010-01-22 09:19:36 +00:00
Eric Coissac	985d067bd8	New version 0.2 of ecoPCR, with Tm computation. Take care file format have change. You must use corresponding version of ecogrep You can use -t option to go back to the old format without tm computation git-svn-id: https://www.grenoble.prabi.fr/svn/LECASofts/ecoPCR/trunk@239 60f365c0-8329-0410-b2a4-ec073aeeaa1d	2010-01-22 09:19:19 +00:00
Eric Coissac	f7e25b2082	New version 0.2 of ecoPCR, with Tm computation. Take care file format have change. You must use corresponding version of ecogrep You can use -t option to go back to the old format without tm computation git-svn-id: https://www.grenoble.prabi.fr/svn/LECASofts/ecoPCR/trunk@238 60f365c0-8329-0410-b2a4-ec073aeeaa1d	2010-01-22 09:16:53 +00:00
Eric Coissac	ad6f493d0f	Accept to deal with sequence in lower case git-svn-id: https://www.grenoble.prabi.fr/svn/LECASofts/ecoPCR/trunk@217 60f365c0-8329-0410-b2a4-ec073aeeaa1d	2009-05-13 13:21:10 +00:00
Eric Coissac	1428cd7499	patch online help in ecoPCR software git-svn-id: https://www.grenoble.prabi.fr/svn/LECASofts/ecoPCR/trunk@168 60f365c0-8329-0410-b2a4-ec073aeeaa1d	2008-05-16 08:53:11 +00:00
Eric Coissac	708b7c387e	Sequence circularity, bug correction git-svn-id: https://www.grenoble.prabi.fr/svn/LECASofts/ecoPCR/trunk@167 60f365c0-8329-0410-b2a4-ec073aeeaa1d	2008-04-28 16:46:18 +00:00
Eric Coissac	d863b7e48e	Manage sequence circularity git-svn-id: https://www.grenoble.prabi.fr/svn/LECASofts/ecoPCR/trunk@166 60f365c0-8329-0410-b2a4-ec073aeeaa1d	2008-04-28 15:49:12 +00:00
Eric Coissac	4b74056af8	change reference column for taxonomy filtering in ecogrep.c git-svn-id: https://www.grenoble.prabi.fr/svn/LECASofts/ecoPCR/trunk@165 60f365c0-8329-0410-b2a4-ec073aeeaa1d	2008-03-12 21:26:08 +00:00
Eric Coissac	f68f4af244	Add option to ecoPCRFormat to deal with an obischema db as taxonomy source git-svn-id: https://www.grenoble.prabi.fr/svn/LECASofts/ecoPCR/trunk@158 60f365c0-8329-0410-b2a4-ec073aeeaa1d	2008-02-08 10:27:42 +00:00
Eric Coissac	a1141a77b5	-- git-svn-id: https://www.grenoble.prabi.fr/svn/LECASofts/ecoPCR/trunk@119 60f365c0-8329-0410-b2a4-ec073aeeaa1d	2007-09-24 10:10:03 +00:00
Eric Coissac	6835206344	Add version file git-svn-id: https://www.grenoble.prabi.fr/svn/LECASofts/ecoPCR/trunk@118 60f365c0-8329-0410-b2a4-ec073aeeaa1d	2007-09-24 10:07:39 +00:00
Eric Coissac	45c85a9f32	git-svn-id: https://www.grenoble.prabi.fr/svn/LECASofts/ecoPCR/trunk@117 60f365c0-8329-0410-b2a4-ec073aeeaa1d	2007-09-24 10:06:00 +00:00
Eric Coissac	471bf72bf9	Add rule for ecogrep build in makefile git-svn-id: https://www.grenoble.prabi.fr/svn/LECASofts/ecoPCR/trunk@116 60f365c0-8329-0410-b2a4-ec073aeeaa1d	2007-09-24 09:58:48 +00:00
Eric Coissac	22ecb4b842	git-svn-id: https://www.grenoble.prabi.fr/svn/LECASofts/ecoPCR/trunk@115 60f365c0-8329-0410-b2a4-ec073aeeaa1d	2007-09-24 09:48:19 +00:00
Eric Coissac	bc4c7656c6	git-svn-id: https://www.grenoble.prabi.fr/svn/LECASofts/ecoPCR/trunk@114 60f365c0-8329-0410-b2a4-ec073aeeaa1d	2007-09-24 09:48:08 +00:00