diff --git a/.classpath b/.classpath
index 3d63d381df73f32044caca209147d811f86d7b60..200d9806da25967234170c1b5c51370cf62683a0 100644
--- a/.classpath
+++ b/.classpath
@@ -1,6 +1,7 @@
<?xml version="1.0" encoding="UTF-8"?>
<classpath>
<classpathentry kind="src" path="corba"/>
+ <classpathentry kind="src" path="lib"/>
<classpathentry including="nsdb/|seqdb/|type/" kind="src" path="ant-build/src/main"/>
<classpathentry excluding="ant-build/src/main/|uk/ac/sanger/artemis/ExternalProgramUtils.java" including="nsdb/|org/|seqdb/|type/|uk/" kind="src" path=""/>
<classpathentry kind="con" path="org.eclipse.jdt.launching.JRE_CONTAINER"/>
@@ -23,5 +24,6 @@
<classpathentry kind="lib" path="lib/batik/batik-svggen.jar"/>
<classpathentry kind="lib" path="lib/batik/batik-util.jar"/>
<classpathentry kind="lib" path="lib/batik/batik-xml.jar"/>
+ <classpathentry kind="lib" path="lib/commons-lang-2.6.jar"/>
<classpathentry kind="output" path="ant-build/classes/main"/>
</classpath>
diff --git a/ChangeLog b/ChangeLog
index ac4dd048395daa01284b23dad4492a9d26cf6eb6..612a9bab76c4cd92381aa2e070877f68f7da2c8c 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,4 +1,4 @@
-Version XX
+Version 16
Add 'Features Within Selection' option to the 'Select' menu to select
features that are contained by a selected base range.
diff --git a/Makefile b/Makefile
index 8dc99b0bb2a7e42b5d43bea05d46c8bde2f5a72e..8d27e27af0755be37cea8ca51ba6bceb2d6957bb 100644
--- a/Makefile
+++ b/Makefile
@@ -8,7 +8,7 @@ SHELL=/bin/sh
JAVAC := javac -source 1.5 -target 1.5 $(OPT_FLAGS) $(EXTRA_FLAGS)
-REAL_CLASSPATH := CLASSPATH=lib/biojava.jar:lib/jemAlign.jar:lib/j2ssh/j2ssh-core.jar:lib/ibatis/ibatis-2.3.4.726.jar:lib/ibatis/log4j-1.2.14.jar:lib/postgresql-8.4-701.jdbc3.jar:lib/picard/picard.jar:lib/picard/sam.jar:lib/commons-net-2.2.jar:lib/batik/batik-awt-util.jar:lib/batik/batik-dom.jar:lib/batik/batik-ext.jar:lib/batik/batik-svggen.jar:lib/batik/batik-util.jar:lib/batik/batik-xml.jar:.
+REAL_CLASSPATH := CLASSPATH=lib/commons-lang-2.6.jar:lib/biojava.jar:lib/jemAlign.jar:lib/j2ssh/j2ssh-core.jar:lib/ibatis/ibatis-2.3.4.726.jar:lib/ibatis/log4j-1.2.14.jar:lib/postgresql-8.4-701.jdbc3.jar:lib/picard/picard.jar:lib/picard/sam.jar:lib/commons-net-2.2.jar:lib/batik/batik-awt-util.jar:lib/batik/batik-dom.jar:lib/batik/batik-ext.jar:lib/batik/batik-svggen.jar:lib/batik/batik-util.jar:lib/batik/batik-xml.jar:.
# NAMES:= \
# uk/ac/sanger/artemis/OptionChangeListener \
diff --git a/etc/writedb_entry b/etc/writedb_entry
index d747fc495a7097537be2dc50c4345ca6d1d3a054..12e7f55bd481f34ce6093299e205d19c2daf9f82 100755
--- a/etc/writedb_entry
+++ b/etc/writedb_entry
@@ -1,6 +1,6 @@
#!/bin/sh -
-#
-# This script reads and writes entries from a database.
+#
+# This script reads and writes entries from a database.
# Examples:
# writedb_entry -help
# writedb_entry -s Pf3D7_01 Pf3D7_05 Pf3D7_07
@@ -28,6 +28,7 @@ done
ARTEMIS_HOME=`dirname "$PRG"`/..
CLASSPATH="$ARTEMIS_HOME:$ARTEMIS_HOME/lib/biojava.jar:$ARTEMIS_HOME/lib/jemAlign.jar:$ARTEMIS_HOME/lib/jakarta-regexp-1.2.jar:$ARTEMIS_HOME/lib/macos.jar:$ARTEMIS_HOME/lib/postgresql-8.4-701.jdbc3.jar:$ARTEMIS_HOME/lib/chado-14-interface.jar:$CLASSPATH"
+CLASSPATH="$CLASSPATH:$ARTEMIS_HOME/lib/commons-lang-2.6.jar"
# iBatis jars
CLASSPATH="$CLASSPATH:$ARTEMIS_HOME/lib/ibatis/ibatis-2.3.4.726.jar:$ARTEMIS_HOME/lib/ibatis/:$ARTEMIS_HOME/lib/ibatis/log4j-1.2.14.jar:$ARTEMIS_HOME/lib/ibatis/cglib-nodep-2.2.jar:$ARTEMIS_HOME/lib/retrotranslator-runtime-1.1.0.jar"
@@ -42,7 +43,7 @@ while test $# != 0
case $1 in
-Dchado*)
DEFAULT_CONNECTION="$1" ;;
- -D*)
+ -D*)
FLAGS="$FLAGS $1" ;;
*) break ;;
esac
@@ -55,7 +56,7 @@ for arg in "$@"
do
if [ '-c' == "${arg}" ]; then
let "nextID = $idx + 1";
- DEFAULT_CONNECTION="-Dchado=${!nextID}"
+ DEFAULT_CONNECTION="-Dchado=${!nextID}"
fi
if [ '-l' == "${arg}" ]; then
let "nextID = $idx + 2";
diff --git a/lib/commons-lang-2.6.jar b/lib/commons-lang-2.6.jar
new file mode 100644
index 0000000000000000000000000000000000000000..98467d3a653ebad776ffa3542efeb9732fe0b482
Binary files /dev/null and b/lib/commons-lang-2.6.jar differ
diff --git a/test/uk/ac/sanger/artemis/io/GFF3AttributeBuilderTest.java b/test/uk/ac/sanger/artemis/io/GFF3AttributeBuilderTest.java
new file mode 100644
index 0000000000000000000000000000000000000000..e65c526b62b2ffe244eae2f73c48429e7da1187f
--- /dev/null
+++ b/test/uk/ac/sanger/artemis/io/GFF3AttributeBuilderTest.java
@@ -0,0 +1,295 @@
+/*
+ * This file is part of Artemis
+ *
+ * Copyright (C) 2014 Genome Research Limited
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ */
+package uk.ac.sanger.artemis.io;
+
+import static org.junit.Assert.assertTrue;
+import static org.junit.Assert.assertFalse;
+import static org.junit.Assert.assertEquals;
+import junit.framework.Assert;
+
+import org.junit.Test;
+import org.junit.Before;
+
+import uk.ac.sanger.artemis.io.GFF3AttributeAggregator;
+import uk.ac.sanger.artemis.io.GFF3AttributeBuilder;
+import uk.ac.sanger.artemis.io.GFF3Encoder;
+import uk.ac.sanger.artemis.util.StringVector;
+
+public class GFF3AttributeBuilderTest {
+ private GFF3Encoder enc;
+ private String[] invals = { "foo", "bar" };
+ private String[] invalsC = { "foo,bar", "baz,quux" };
+ private static GFF3AttributeAggregator testProc;
+
+ @Before
+ public void setUp() {
+ enc = new GFF3Encoder();
+ testProc = new GFF3AttributeAggregator() {
+ @Override
+ public String process(StringVector values) {
+ StringBuilder buffer = new StringBuilder();
+ if (values != null && values.size() > 0) {
+ for (int value_index = 0; value_index < values.size(); ++value_index) {
+ buffer.append(">>"
+ + GFF3Encoder.encode(values.elementAt(value_index)) + "<<");
+ if (value_index < (values.size()) - 1)
+ buffer.append("|");
+ }
+ }
+ return buffer.toString();
+ }
+ };
+ }
+
+ @Test
+ /**
+ * Tests adding one attribute.
+ */
+ public void testAdd1() {
+ GFF3AttributeBuilder ab = new GFF3AttributeBuilder();
+ StringVector in = new StringVector(invals);
+
+ ab.add("attr1", in);
+ assertEquals(ab.toString(), "attr1=foo,bar");
+ }
+
+ @Test
+ /**
+ * Tests adding two different attributes.
+ */
+ public void testAdd2() {
+ GFF3AttributeBuilder ab = new GFF3AttributeBuilder();
+ StringVector in = new StringVector(invals);
+
+ ab.add("attr1", in);
+ ab.add("attr2", in);
+ assertEquals(ab.toString(), "attr1=foo,bar;attr2=foo,bar");
+ }
+
+ @Test
+ /**
+ * Tests adding attributes with custom aggregators.
+ */
+ public void testAddWithAggs() {
+ GFF3AttributeBuilder ab = new GFF3AttributeBuilder();
+ StringVector in = new StringVector(invals);
+ ab.setAggregator("attr1", testProc);
+ ab.add("attr1", in);
+ assertEquals(ab.toString(), "attr1=>>foo<<|>>bar<<");
+ ab.add("attr1", in);
+ assertEquals(ab.toString(), "attr1=>>foo<<|>>bar<< >>foo<<|>>bar<<");
+ }
+
+ @Test
+ /**
+ * Tests adding attributes (encoded values) with custom aggregators.
+ */
+ public void testAddWithAggsCommas() {
+ GFF3AttributeBuilder ab = new GFF3AttributeBuilder();
+ StringVector in = new StringVector(invalsC);
+ ab.add("attr1", in);
+ assertEquals(ab.toString(), "attr1=foo%2Cbar,baz%2Cquux");
+ ab.add("attr1", in);
+ assertEquals(ab.toString(),
+ "attr1=foo%2Cbar,baz%2Cquux foo%2Cbar,baz%2Cquux");
+ ab = new GFF3AttributeBuilder();
+ ab.setAggregator("attr1", testProc);
+ ab.add("attr1", in);
+ assertEquals(ab.toString(), "attr1=>>foo%2Cbar<<|>>baz%2Cquux<<");
+ ab.add("attr1", in);
+ assertEquals(ab.toString(),
+ "attr1=>>foo%2Cbar<<|>>baz%2Cquux<< >>foo%2Cbar<<|>>baz%2Cquux<<");
+ }
+
+ @Test
+ /**
+ * Tests the ignoring of attribute fields in the output.
+ */
+ public void testIgnore() {
+ GFF3AttributeBuilder ab = new GFF3AttributeBuilder();
+ StringVector in = new StringVector(invals);
+
+ ab.ignore("attr1");
+ ab.add("attr1", in);
+ ab.add("attr2", in);
+ assertEquals(ab.toString(), "attr2=foo,bar");
+ ab.unignore("attr1");
+ assertEquals(ab.toString(), "attr1=foo,bar;attr2=foo,bar");
+ }
+
+ @Test
+ /**
+ * Tests the handling of duplicate attributes.
+ */
+ public void testAddMultiAttr() {
+ GFF3AttributeBuilder ab = new GFF3AttributeBuilder();
+ StringVector in = new StringVector(invals);
+
+ ab.add("attr1", in);
+ ab.add("attr1", in);
+ assertEquals(ab.toString(), "attr1=foo,bar foo,bar");
+ }
+
+ @Test
+ /**
+ * Tests the handling of duplicate attributes, with delimiter.
+ */
+ public void testAddMultiAttrWithGlue() {
+ GFF3AttributeBuilder ab = new GFF3AttributeBuilder();
+ StringVector in = new StringVector(invals);
+
+ ab.setGlue("attr1", "X");
+ ab.add("attr1", in);
+ ab.add("attr1", in);
+ ab.add("attr1", in);
+ assertEquals(ab.toString(), "attr1=foo,barXfoo,barXfoo,bar");
+ }
+
+ @Test
+ /**
+ * Tests cloning of attributes to separate keys with default aggregator.
+ */
+ public void testClone() {
+ GFF3AttributeBuilder ab = new GFF3AttributeBuilder();
+ StringVector in = new StringVector(invals);
+
+ ab.setClone("attr1", "brand_new");
+ ab.add("attr1", in);
+ assertEquals(ab.toString(), "attr1=foo,bar;brand_new=foo,bar");
+ ab.add("brand_new", in);
+ assertEquals(ab.toString(), "attr1=foo,bar;brand_new=foo,bar foo,bar");
+ }
+
+ @Test
+ /**
+ * Tests cloning of attributes to separate keys with different aggregators.
+ */
+ public void testCloneWithAggs() {
+ GFF3AttributeBuilder ab = new GFF3AttributeBuilder();
+ StringVector in = new StringVector(invals);
+ ab.setClone("attr1", "brand_new");
+ ab.setAggregator("brand_new", testProc);
+ ab.add("attr1", in);
+ assertEquals(ab.toString(), "attr1=foo,bar;brand_new=>>foo<<|>>bar<<");
+ ab.add("attr1", in);
+ assertEquals(ab.toString(),
+ "attr1=foo,bar foo,bar;brand_new=>>foo<<|>>bar<< >>foo<<|>>bar<<");
+ }
+
+ @Test
+ /**
+ * Tests mapping/cloning of attributes to separate keys with different aggregators.
+ */
+ public void testMappingAndCloneWithAggs1() {
+ GFF3AttributeBuilder ab = new GFF3AttributeBuilder();
+ StringVector in = new StringVector(invals);
+
+ ab.setMapping("attr1", "aaaa");
+ ab.setClone("aaaa", "brand_new");
+ ab.setAggregator("brand_new", testProc);
+ ab.add("attr1", in);
+ assertEquals(ab.toString(), "aaaa=foo,bar;brand_new=>>foo<<|>>bar<<");
+ ab.add("attr1", in);
+ assertEquals(ab.toString(),
+ "aaaa=foo,bar foo,bar;brand_new=>>foo<<|>>bar<< >>foo<<|>>bar<<");
+ }
+
+ @Test
+ /**
+ * Tests mapping/cloning of attributes to separate keys with different aggregators.
+ */
+ public void testMappingAndCloneWithAggs2() {
+ GFF3AttributeBuilder ab = new GFF3AttributeBuilder();
+ StringVector in = new StringVector(invals);
+
+ ab.setMapping("attr1", "aaaa");
+ ab.setClone("attr1", "brand_new");
+ ab.setAggregator("brand_new", testProc);
+ ab.add("attr1", in);
+ assertEquals(ab.toString(), "aaaa=foo,bar;brand_new=>>foo<<|>>bar<<");
+ ab.add("attr1", in);
+ assertEquals(ab.toString(),
+ "aaaa=foo,bar foo,bar;brand_new=>>foo<<|>>bar<< >>foo<<|>>bar<<");
+ }
+
+ @Test
+ /**
+ * Tests mapping one attribute to a new name.
+ */
+ public void testMapping() {
+ GFF3AttributeBuilder ab = new GFF3AttributeBuilder();
+ StringVector in = new StringVector(invals);
+
+ ab.setMapping("attr1", "brand_new");
+ ab.add("attr1", in);
+ ab.add("attr2", in);
+ assertEquals(ab.toString(), "attr2=foo,bar;brand_new=foo,bar");
+ }
+
+ @Test
+ /**
+ * Tests mapping one attribute to a new name with custom target aggregator.
+ */
+ public void testMappingWithAggs() {
+ GFF3AttributeBuilder ab = new GFF3AttributeBuilder();
+ StringVector in = new StringVector(invals);
+ ab.setMapping("attr1", "brand_new");
+ ab.setAggregator("brand_new", testProc);
+ ab.add("attr1", in);
+ ab.add("attr2", in);
+ assertEquals(ab.toString(), "attr2=foo,bar;brand_new=>>foo<<|>>bar<<");
+ }
+
+ @Test
+ /**
+ * Tests mapping one attribute to a new name with custom target aggregator.
+ */
+ public void testMappingCollision() {
+ GFF3AttributeBuilder ab = new GFF3AttributeBuilder();
+ StringVector in = new StringVector(invals);
+
+ ab.setMapping("attr1", "attr2");
+ ab.add("attr1", in);
+ ab.add("attr2", in);
+ assertEquals(ab.toString(), "attr2=foo,bar foo,bar");
+ }
+
+ @Test
+ /**
+ * Tests mapping one attribute to a new name with custom target aggregator.
+ */
+ public void testMappingCollisionWithAggs() {
+ GFF3AttributeBuilder ab = new GFF3AttributeBuilder();
+ StringVector in = new StringVector(invals);
+
+ ab.setMapping("attr1", "attr2");
+ ab.setAggregator("attr2", testProc);
+ ab.add("attr1", in);
+ ab.add("attr2", in);
+ assertEquals(ab.toString(), "attr2=>>foo<<|>>bar<< >>foo<<|>>bar<<");
+ ab = new GFF3AttributeBuilder();
+ ab.setMapping("attr1", "attr2");
+ ab.setAggregator("attr1", testProc);
+ ab.add("attr1", in);
+ ab.add("attr2", in);
+ assertEquals(ab.toString(), "attr2=>>foo<<|>>bar<< foo,bar");
+ }
+}
diff --git a/test/uk/ac/sanger/artemis/io/GFF3EncoderTest.java b/test/uk/ac/sanger/artemis/io/GFF3EncoderTest.java
new file mode 100644
index 0000000000000000000000000000000000000000..56f8a5a4d4dbafc4bf0b9352f0478c0ec803d8a4
--- /dev/null
+++ b/test/uk/ac/sanger/artemis/io/GFF3EncoderTest.java
@@ -0,0 +1,102 @@
+/*
+ * This file is part of Artemis
+ *
+ * Copyright (C) 2014 Genome Research Limited
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ */
+package uk.ac.sanger.artemis.io;
+
+import static org.junit.Assert.assertTrue;
+import static org.junit.Assert.assertFalse;
+import static org.junit.Assert.assertEquals;
+import junit.framework.Assert;
+
+import org.junit.Test;
+import org.junit.Before;
+
+import uk.ac.sanger.artemis.io.GFF3Encoder;
+
+public class GFF3EncoderTest {
+ private GFF3Encoder enc;
+
+ @Before
+ public void setUp() {
+ enc = new GFF3Encoder();
+ }
+
+ @Test
+ /**
+ * Tests whether there are missing map characters.
+ */
+ public void testMapEqualLength() {
+ assertEquals(GFF3Encoder.mapChars.length, GFF3Encoder.mappedEscapes.length);
+ }
+
+ @Test
+ /**
+ * Tests whether the mapping is correct according to GFF3 spec.
+ */
+ public void testMapChars() {
+ assertEquals(enc.encode("%"), "%25");
+ assertEquals(enc.decode("%25"), "%");
+ assertEquals(enc.encode("&"), "%26");
+ assertEquals(enc.decode("%26"), "&");
+ assertEquals(enc.encode(","), "%2C");
+ assertEquals(enc.decode("%2C"), ",");
+ assertEquals(enc.encode(";"), "%3B");
+ assertEquals(enc.decode("%3B"), ";");
+ assertEquals(enc.encode("="), "%3D");
+ assertEquals(enc.decode("%3D"), "=");
+ assertEquals(enc.encode("\t"), "%09");
+ assertEquals(enc.decode("%09"), "\t");
+ assertEquals(enc.encode("\n"), "%0A");
+ assertEquals(enc.decode("%0A"), "\n");
+ assertEquals(enc.encode("\r"), "%0D");
+ assertEquals(enc.decode("%0D"), "\r");
+ }
+
+ @Test
+ /**
+ * Tests the decoding of escaped characters in GFF files.
+ */
+ public void testDecode() {
+ for (int i=0; i < GFF3Encoder.mappedEscapes.length; i++) {
+ assertEquals(enc.decode("test"+GFF3Encoder.mappedEscapes[i]+"foo"),
+ "test"+GFF3Encoder.mapChars[i]+"foo");
+ assertEquals(enc.decode("test%"+GFF3Encoder.mappedEscapes[i]+"foo"),
+ "test%"+GFF3Encoder.mapChars[i]+"foo");
+ assertEquals(enc.decode("test1"+GFF3Encoder.mappedEscapes[i]+"foo," +
+ "test2"+GFF3Encoder.mappedEscapes[i]),
+ "test1"+GFF3Encoder.mapChars[i]+"foo," +
+ "test2"+GFF3Encoder.mapChars[i]);
+ }
+ }
+
+ @Test
+ /**
+ * Tests the encoding of escaped characters in GFF files.
+ */
+ public void testEncode() {
+ for (int i=0; i < GFF3Encoder.mappedEscapes.length; i++) {
+ assertEquals(enc.encode("test"+GFF3Encoder.mapChars[i]+"foo"),
+ "test"+GFF3Encoder.mappedEscapes[i]+"foo");
+ assertEquals(enc.encode("test%"+GFF3Encoder.mapChars[i]+"foo"),
+ "test%25"+GFF3Encoder.mappedEscapes[i]+"foo");
+ }
+ }
+
+}
diff --git a/uk/ac/sanger/artemis/chado/ArtemisUtils.java b/uk/ac/sanger/artemis/chado/ArtemisUtils.java
index f0eea5f306acbd15af4d5c04e2f7f0e988c8e2bf..277a787c2958517ce3851c4832b6d7ffe40e17d2 100644
--- a/uk/ac/sanger/artemis/chado/ArtemisUtils.java
+++ b/uk/ac/sanger/artemis/chado/ArtemisUtils.java
@@ -47,6 +47,7 @@ import org.gmod.schema.sequence.FeatureProp;
import org.gmod.schema.sequence.FeatureRelationship;
import uk.ac.sanger.artemis.io.DatabaseDocumentEntry;
+import uk.ac.sanger.artemis.io.GFF3Encoder;
import uk.ac.sanger.artemis.io.GFFStreamFeature;
import uk.ac.sanger.artemis.util.DatabaseDocument;
import uk.ac.sanger.artemis.util.StringVector;
@@ -262,7 +263,7 @@ public class ArtemisUtils
if(this_fcp.getValue().equals(fcp.getValue()))
return true;
- if(this_fcp.getValue().equals(GFFStreamFeature.decode(fcp.getValue())))
+ if(this_fcp.getValue().equals(GFF3Encoder.decode(fcp.getValue())))
return true;
}
return false;
diff --git a/uk/ac/sanger/artemis/components/genebuilder/GeneUtils.java b/uk/ac/sanger/artemis/components/genebuilder/GeneUtils.java
index bee966d31a6871bce8f6089e57f9d5445af15eb0..7d8f1607d6efa7ded64018cab65a1c165fbf2ac7 100644
--- a/uk/ac/sanger/artemis/components/genebuilder/GeneUtils.java
+++ b/uk/ac/sanger/artemis/components/genebuilder/GeneUtils.java
@@ -61,6 +61,7 @@ import uk.ac.sanger.artemis.io.DatabaseInferredFeature;
import uk.ac.sanger.artemis.io.DocumentEntry;
import uk.ac.sanger.artemis.io.EntryInformationException;
import uk.ac.sanger.artemis.io.Feature;
+import uk.ac.sanger.artemis.io.GFF3Encoder;
import uk.ac.sanger.artemis.io.GFFDocumentEntry;
import uk.ac.sanger.artemis.io.GFFStreamFeature;
import uk.ac.sanger.artemis.io.InvalidRelationException;
@@ -126,7 +127,7 @@ public class GeneUtils
String value = featureSynonym.getSynonym().getName();
if(!featureSynonym.isCurrent())
- value.concat(GFFStreamFeature.encode(";current=false"));
+ value.concat(GFF3Encoder.encode(";current=false"));
Qualifier qualifier = feature.getQualifiers().getQualifierByName(name);
if(qualifier == null)
@@ -198,7 +199,7 @@ public class GeneUtils
final String qualifierString = new String(this_buff.getBytes());
int ind = qualifierString.indexOf('=');
final String name = qualifierString.substring(0, ind);
- final String value = GFFStreamFeature.decode(
+ final String value = GFF3Encoder.decode(
qualifierString.substring(ind+1, qualifierString.length()-1));
Qualifier qualifier = feature.getQualifiers().getQualifierByName(name);
diff --git a/uk/ac/sanger/artemis/io/GFF3AttributeAggregator.java b/uk/ac/sanger/artemis/io/GFF3AttributeAggregator.java
new file mode 100644
index 0000000000000000000000000000000000000000..4a8a737a30b5fb2695e0614e7a1dd2166a1293ad
--- /dev/null
+++ b/uk/ac/sanger/artemis/io/GFF3AttributeAggregator.java
@@ -0,0 +1,38 @@
+/* GFF3AttributeAggregator.java
+ * *
+ * This file is part of Artemis
+ *
+ * Copyright (C) 2014 Genome Research Limited
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ */
+
+package uk.ac.sanger.artemis.io;
+
+import uk.ac.sanger.artemis.util.StringVector;
+
+/**
+ * Abstraction for processing various Artemis qualifiers into usable GFF3 strings.
+ */
+public interface GFF3AttributeAggregator {
+ /**
+ * Prepare a set of string values as a GFF attribute value.
+ * @param values the value set to convert to a <code>String</code>
+ * @return the <code>String</code> representation
+ */
+ public abstract String process(StringVector values);
+
+}
diff --git a/uk/ac/sanger/artemis/io/GFF3AttributeBuilder.java b/uk/ac/sanger/artemis/io/GFF3AttributeBuilder.java
new file mode 100644
index 0000000000000000000000000000000000000000..f7b1db25177bdafbdfa4fc48ca6b15ff248ad0d4
--- /dev/null
+++ b/uk/ac/sanger/artemis/io/GFF3AttributeBuilder.java
@@ -0,0 +1,212 @@
+/* GFF3AttributeBuilder.java
+ * *
+ * This file is part of Artemis
+ *
+ * Copyright (C) 2014 Genome Research Limited
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ */
+
+package uk.ac.sanger.artemis.io;
+
+import java.util.ArrayList;
+import java.util.Collections;
+import java.util.Comparator;
+import java.util.HashMap;
+import java.util.HashSet;
+import java.lang.StringBuilder;
+
+import uk.ac.sanger.artemis.io.EntryInformationException;
+import uk.ac.sanger.artemis.io.GFF3AttributeAggregator;
+import uk.ac.sanger.artemis.util.StringVector;
+
+public class GFF3AttributeBuilder {
+ private HashMap<String, String> attrs = new HashMap<String, String>();
+ private HashMap<String, String> mappings = new HashMap<String, String>();
+ private HashMap<String, String> glue = new HashMap<String, String>();
+ private HashSet<String> ignores = new HashSet<String>();
+ private HashMap<String, String> clones = new HashMap<String, String>();
+ private HashMap<String, GFF3AttributeAggregator> aggs = new HashMap<String, GFF3AttributeAggregator>();
+ private HashSet<String> reserved = new HashSet<String>(
+ 13);
+ private static final GFF3AttributeAggregator defaultAgg = new GFF3AttributeAggregator() {
+ @Override
+ public String process(StringVector values) {
+ StringBuilder buffer = new StringBuilder();
+ if (values != null && values.size() > 0) {
+ for (int value_index = 0; value_index < values.size(); ++value_index) {
+ final String this_value = GFF3Encoder.encode(values.elementAt(value_index));
+ if (value_index > 0 && value_index < (values.size())) {
+ buffer.append(",");
+ }
+ buffer.append(this_value);
+ }
+ }
+ return buffer.toString();
+ }
+ };
+
+ final String reserved_a[] = { "ID",
+ "Name", "Alias", "Parent", "Derives_from", "Target", "Gap", "Note",
+ "Dbxref", "Ontology_term", "Start_range", "End_range", "Is_circular" };
+
+ public GFF3AttributeBuilder() {
+ for (String s : reserved_a) {
+ reserved.add(s);
+ }
+ }
+
+ public void setMapping(String attr, String mapsto) {
+ /* XXX: make sure only one level of mapping is used */
+ mappings.put(attr, mapsto);
+ }
+
+ public void unsetMapping(String attr, String mapsto) {
+ mappings.remove(attr);
+ }
+
+ public void setGlue(String attr, String glue_str) {
+ glue.put(attr, glue_str);
+ }
+
+ public void unsetGlue(String attr) {
+ glue.remove(attr);
+ }
+
+ public void setClone(String attr, String glue_str) {
+ clones.put(attr, glue_str);
+ }
+
+ public void unsetClone(String attr) {
+ clones.remove(attr);
+ }
+
+ public void setAggregator(String attr, GFF3AttributeAggregator agg) {
+ aggs.put(attr, agg);
+ }
+
+ public void unsetAggregator(String attr, GFF3AttributeAggregator agg) {
+ aggs.remove(attr);
+ }
+
+ public void ignore(String attr) {
+ ignores.add(attr);
+ }
+
+ public void unignore(String attr) {
+ ignores.remove(attr);
+ }
+
+ public void add(String attr, String val) {
+ StringVector v = new StringVector(val);
+ add(attr, v);
+ }
+
+ public void add(String attr, StringVector val) {
+ String origAttr = attr;
+ ArrayList<String> targetAttrs = new ArrayList<String>();
+ // expand attributes
+ if (clones.containsKey(attr))
+ targetAttrs.add(clones.get(attr));
+ if (mappings.containsKey(attr)) {
+ attr = mappings.get(attr);
+ targetAttrs.add(attr);
+ if (clones.containsKey(attr))
+ targetAttrs.add(clones.get(attr));
+ } else {
+ targetAttrs.add(attr);
+ }
+ // drop attributes with null or empty values
+ if (val == null || (val.size() == 1
+ && val.elementAt(0).replaceAll("\\s+", "").equals("")) )
+ return;
+ // process expanded list of attributes
+ for (String this_attr : targetAttrs) {
+ String aggregatedVal;
+ // do we have an aggregator for this type?
+ if (aggs.containsKey(origAttr)) {
+ GFF3AttributeAggregator agg = aggs.get(origAttr);
+ aggregatedVal = agg.process(val);
+ } else if (aggs.containsKey(this_attr)) {
+ GFF3AttributeAggregator agg = aggs.get(this_attr);
+ aggregatedVal = agg.process(val);
+ } else {
+ aggregatedVal = defaultAgg.process(val);
+ }
+ // do not add empty values
+ if (aggregatedVal == null)
+ return;
+ // append or set?
+ if (attrs.containsKey(this_attr)) {
+ String this_val = attrs.get(this_attr),
+ this_glue = " ";
+ if (glue.containsKey(this_attr))
+ this_glue = glue.get(this_attr);
+ this_val = this_val + this_glue + aggregatedVal;
+ attrs.put(this_attr, this_val);
+ } else {
+ attrs.put(this_attr, aggregatedVal);
+ }
+ }
+ }
+
+ private String decapitalize(String line) {
+ if (!reserved.contains(line)
+ && Character.toUpperCase(line.charAt(0)) == line.charAt(0)) {
+ return Character.toLowerCase(line.charAt(0)) + line.substring(1);
+ } else {
+ return line;
+ }
+ }
+
+ public String get(String attr) throws EntryInformationException {
+ if (mappings.containsKey(attr)) {
+ attr = mappings.get(attr);
+ }
+ if (attrs.containsKey(attr)) {
+ return attrs.get(attr);
+ } else {
+ throw new EntryInformationException("empty attribute value for " + attr);
+ }
+ }
+
+ private Comparator<String> comparator = new Comparator<String>() {
+ // make sure 'ID' is always at the beginning of the attribute list
+ public int compare(String o1, String o2) {
+ if (o1.equals("ID"))
+ return -1;
+ if (o2.equals("ID"))
+ return 1;
+ return o1.compareTo(o2);
+ }
+ };
+
+ public String toString() {
+ StringBuilder b = new StringBuilder();
+ int i = 0;
+ ArrayList<String> sortedAttrs = new ArrayList<String>(attrs.keySet());
+ Collections.sort(sortedAttrs, comparator);
+ for (String key : sortedAttrs) {
+ if (!ignores.contains(key)) {
+ String value = attrs.get(key);
+ if (i++ != 0)
+ b.append(";");
+ b.append(decapitalize(key) + "=" + value);
+ }
+ }
+ return b.toString();
+ }
+}
diff --git a/uk/ac/sanger/artemis/io/GFF3Encoder.java b/uk/ac/sanger/artemis/io/GFF3Encoder.java
new file mode 100644
index 0000000000000000000000000000000000000000..49f5507a61452ab3eb77a7b16583c7cd2f4b2b6d
--- /dev/null
+++ b/uk/ac/sanger/artemis/io/GFF3Encoder.java
@@ -0,0 +1,38 @@
+/* GFF3Encoder.java
+ * *
+ * This file is part of Artemis
+ *
+ * Copyright (C) 2014 Genome Research Limited
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ */
+
+package uk.ac.sanger.artemis.io;
+
+import org.apache.commons.lang.StringUtils;
+
+public class GFF3Encoder {
+ public static final String mapChars[] = { "%", "&", ",", ";", "=", "\t", "\n", "\r" };
+ public static final String mappedEscapes[] = { "%25", "%26", "%2C", "%3B", "%3D", "%09", "%0A", "%0D" };
+
+ public static String decode(String s) {
+ return StringUtils.replaceEach(s, mappedEscapes, mapChars);
+ }
+
+ public static String encode(String s) {
+ return StringUtils.replaceEach(s, mapChars, mappedEscapes);
+ }
+}
diff --git a/uk/ac/sanger/artemis/io/GFFStreamFeature.java b/uk/ac/sanger/artemis/io/GFFStreamFeature.java
index 8e68ac3c0d8bbc09c0919b8e72cd5858048fc43b..bfec1da894ca1d501f6e59cf8c971b9984bae9ac 100644
--- a/uk/ac/sanger/artemis/io/GFFStreamFeature.java
+++ b/uk/ac/sanger/artemis/io/GFFStreamFeature.java
@@ -25,7 +25,6 @@
package uk.ac.sanger.artemis.io;
-
import java.util.Hashtable;
import java.util.HashSet;
import java.util.Enumeration;
@@ -47,330 +46,273 @@ import uk.ac.sanger.artemis.util.LinePushBackReader;
import uk.ac.sanger.artemis.util.OutOfRangeException;
import uk.ac.sanger.artemis.util.ReadOnlyException;
import uk.ac.sanger.artemis.util.StringVector;
-
+import uk.ac.sanger.artemis.io.GFF3Encoder;
/**
- * A StreamFeature that thinks it is a GFF feature.
- * @author Kim Rutherford
+ * A StreamFeature that thinks it is a GFF feature.
+ *
+ * @author Kim Rutherford
**/
-public class GFFStreamFeature extends SimpleDocumentFeature
- implements DocumentFeature, StreamFeature, ComparableFeature
-{
+public class GFFStreamFeature extends SimpleDocumentFeature implements
+ DocumentFeature, StreamFeature, ComparableFeature {
- private static org.apache.log4j.Logger logger4j =
- org.apache.log4j.Logger.getLogger(GFFStreamFeature.class);
+ private static org.apache.log4j.Logger logger4j = org.apache.log4j.Logger
+ .getLogger(GFFStreamFeature.class);
/** store for spliced features containing id and range of each segment */
- private Hashtable<String, Range> id_range_store;
+ private Hashtable<String, Range> id_range_store;
/** store a record of the new and old uniquenames that have been changed */
- private Hashtable<String, String> newIdMapToOldId;
+ private Hashtable<String, String> newIdMapToOldId;
/** store the Timestamp for the feature */
- private Timestamp timelastmodified;
+ private Timestamp timelastmodified;
- private ChadoCanonicalGene chadoGene;
+ private ChadoCanonicalGene chadoGene;
- private boolean visible = true;
+ private boolean visible = true;
/** combined feature_relationship.rank store for exons */
- private Hashtable<String, Integer> feature_relationship_rank_store;
+ private Hashtable<String, Integer> feature_relationship_rank_store;
- /** first tabbed parameter */
- private String gffSeqName;
+ /** first tabbed parameter */
+ private String gffSeqName;
/** second tabbed parameter */
- private String gffSource;
+ private String gffSource;
/** duplication count */
- private short duplicate = 0;
+ private short duplicate = 0;
protected static Hashtable<String, Range> contig_ranges;
- private boolean lazyLoaded = false;
- private org.gmod.schema.sequence.Feature chadoLazyFeature;
- private boolean readOnlyFeature = false;
-
-
- private static String MAP_DECODE[][] = {
- { " ", "%20" }, // white space
- { ",", "%2C" }, // comma
- { ";", "%3B" }, // semi-colon
- { "=", "%3D" }, // equals
- { "\t", "%09" }, // tab
- { " ", "+" }, // white space
- { "+", "%2B" },
- { "(", "%28" }, // left bracket
- { ")", "%29" }, // right bracket
- { "'", "\"" }
- };
-
- private static String MAP_ENCODE[][] = {
-// { " ", "%20" }, // white space
- { ",", "%2C" }, // comma
- { ";", "%3B" }, // semi-colon
- { "=", "%3D" }, // equals
- { "\t", "%09" }, // tab
- { "+", "%2B" },
- { " ", "+" }, // white space
- { "(", "%28" }, // left bracket
- { ")", "%29" }, // right bracket
- { "\n", "%5C" } // new-line
- };
-
- private static Set<String> attrs_to_filter = new HashSet<String>();
+ private boolean lazyLoaded = false;
+ private org.gmod.schema.sequence.Feature chadoLazyFeature;
+ private boolean readOnlyFeature = false;
+
+ private static Set<String> attrs_to_filter = new HashSet<String>();
/**
- * Registers an attribute not to be included in the GFF3 output for
- * GFFStreamFeatures
- * @param attr The GFF3 attribute to remove
+ * Registers an attribute not to be included in the GFF3 output for
+ * GFFStreamFeatures
+ *
+ * @param attr
+ * The GFF3 attribute to remove
**/
- public static void removeAttribute(String attr)
- {
+ public static void removeAttribute(String attr) {
attrs_to_filter.add(attr);
}
/**
- * Registers an attribute to be included in the GFF3 output for
- * GFFStreamFeatures
- * @param attr The GFF3 attribute to include
+ * Registers an attribute to be included in the GFF3 output for
+ * GFFStreamFeatures
+ *
+ * @param attr
+ * The GFF3 attribute to include
**/
- public static void includeAttribute(String attr)
- {
+ public static void includeAttribute(String attr) {
attrs_to_filter.remove(attr);
}
/**
- * Create a new GFFStreamFeature object. The feature should be added
- * to an Entry (with Entry.add()).
- * @param key The new feature key
- * @param location The Location object for the new feature
- * @param qualifiers The qualifiers for the new feature
+ * Create a new GFFStreamFeature object. The feature should be added to an
+ * Entry (with Entry.add()).
+ *
+ * @param key
+ * The new feature key
+ * @param location
+ * The Location object for the new feature
+ * @param qualifiers
+ * The qualifiers for the new feature
**/
public GFFStreamFeature(final Key key, final Location location,
- final QualifierVector qualifiers)
- {
+ final QualifierVector qualifiers) {
super(null);
- try
- {
+ try {
setKey(key);
setLocation(location);
setQualifiers(qualifiers);
- if(getQualifierByName("ID") == null)
- {
+ if (getQualifierByName("ID") == null) {
String idStr = null;
StringVector v = Options.getOptions().getSystematicQualifierNames();
- for(int i=0; i<v.size(); i++)
- {
- final String sysName = (String)v.get(i);
- if(getQualifierByName(sysName) != null)
- {
- idStr = (String)getQualifierByName(sysName).getValues().get(0);
+ for (int i = 0; i < v.size(); i++) {
+ final String sysName = (String) v.get(i);
+ if (getQualifierByName(sysName) != null) {
+ idStr = (String) getQualifierByName(sysName).getValues().get(0);
break;
}
}
// autogenerate ID
- if(idStr == null)
- idStr = key.getKeyString()+":"+location.toString();
+ if (idStr == null)
+ idStr = key.getKeyString() + ":" + location.toString();
setQualifier(new Qualifier("ID", idStr));
}
- }
- catch(EntryInformationException e)
- {
+ } catch (EntryInformationException e) {
// this should never happen because the feature will not be in an Entry
throw new Error("internal error - unexpected exception: " + e);
- }
- catch(ReadOnlyException e)
- {
+ } catch (ReadOnlyException e) {
// this should never happen because the feature will not be in an Entry
throw new Error("internal error - unexpected exception: " + e);
- }
- catch(OutOfRangeException e)
- {
+ } catch (OutOfRangeException e) {
// this should never happen because the feature will not be in an Entry
throw new Error("internal error - unexpected exception: " + e);
}
}
- public GFFStreamFeature(final Feature feature)
- {
+ public GFFStreamFeature(final Feature feature) {
this(feature, false);
}
/**
- * Create a new GFFStreamFeature with the same key, location and
- * qualifiers as the given feature. The feature should be added to an
- * Entry (with Entry.add()).
- * @param feature The feature to copy.
+ * Create a new GFFStreamFeature with the same key, location and qualifiers as
+ * the given feature. The feature should be added to an Entry (with
+ * Entry.add()).
+ *
+ * @param feature
+ * The feature to copy.
**/
- public GFFStreamFeature(final Feature feature, final boolean isDuplicatedInChado)
- {
+ @SuppressWarnings("unchecked")
+ public GFFStreamFeature(final Feature feature,
+ final boolean isDuplicatedInChado) {
this(feature.getKey(), feature.getLocation(), feature.getQualifiers());
- if(feature instanceof GFFStreamFeature)
- {
- if(((GFFStreamFeature)feature).id_range_store != null)
- this.id_range_store =
- (Hashtable)(((GFFStreamFeature)feature).id_range_store).clone();
+ if (feature instanceof GFFStreamFeature) {
+ if (((GFFStreamFeature) feature).id_range_store != null)
+ this.id_range_store = (Hashtable<String, Range>) (((GFFStreamFeature) feature).id_range_store)
+ .clone();
- if(((GFFStreamFeature)feature).feature_relationship_rank_store != null)
- this.feature_relationship_rank_store =
- (Hashtable)(((GFFStreamFeature)feature).feature_relationship_rank_store).clone();
+ if (((GFFStreamFeature) feature).feature_relationship_rank_store != null)
+ this.feature_relationship_rank_store = (Hashtable<String, Integer>) (((GFFStreamFeature) feature).feature_relationship_rank_store)
+ .clone();
- this.setGffSeqName(((GFFStreamFeature)feature).getGffSeqName());
- this.setGffSource(((GFFStreamFeature)feature).getGffSource());
+ this.setGffSeqName(((GFFStreamFeature) feature).getGffSeqName());
+ this.setGffSource(((GFFStreamFeature) feature).getGffSource());
- if(isDuplicatedInChado)
- {
- try
- {
+ if (isDuplicatedInChado) {
+ try {
final String uniquename;
final String duplicatePrefix;
- if(feature instanceof GFFStreamFeature)
- {
- ((GFFStreamFeature)feature).duplicate++;
- duplicatePrefix = "DUP"+Short.toString(((GFFStreamFeature)feature).duplicate)+"-";
- }
- else
+ if (feature instanceof GFFStreamFeature) {
+ ((GFFStreamFeature) feature).duplicate++;
+ duplicatePrefix = "DUP"
+ + Short.toString(((GFFStreamFeature) feature).duplicate) + "-";
+ } else
duplicatePrefix = "DUP";
- if(id_range_store != null)
- {
- final Hashtable<String, Range> new_id_range_store = new Hashtable<String, Range>(id_range_store.size());
+ if (id_range_store != null) {
+ final Hashtable<String, Range> new_id_range_store = new Hashtable<String, Range>(
+ id_range_store.size());
final Enumeration<String> enumIdRangeStore = id_range_store.keys();
- while(enumIdRangeStore.hasMoreElements())
- {
+ while (enumIdRangeStore.hasMoreElements()) {
final String keyId = enumIdRangeStore.nextElement();
- final Range range = id_range_store.get(keyId);
- new_id_range_store.put(duplicatePrefix+keyId, range);
+ final Range range = id_range_store.get(keyId);
+ new_id_range_store.put(duplicatePrefix + keyId, range);
}
id_range_store.clear();
- this.id_range_store = (Hashtable) new_id_range_store.clone();
-
+ this.id_range_store = (Hashtable<String, Range>) new_id_range_store
+ .clone();
- if(getLocation().getRanges().size() > 1)
+ if (getLocation().getRanges().size() > 1)
uniquename = getSegmentID(getLocation().getRanges());
- else
- {
- if( ((String)getQualifierByName("ID").getValues().get(0)).endsWith("}") )
+ else {
+ if (((String) getQualifierByName("ID").getValues().get(0))
+ .endsWith("}"))
uniquename = id_range_store.keys().nextElement();
else
- uniquename = duplicatePrefix+ (String)getQualifierByName("ID").getValues().get(0);
+ uniquename = duplicatePrefix
+ + (String) getQualifierByName("ID").getValues().get(0);
}
- }
- else
- uniquename = duplicatePrefix+ (String)getQualifierByName("ID").getValues().get(0);
+ } else
+ uniquename = duplicatePrefix
+ + (String) getQualifierByName("ID").getValues().get(0);
setQualifier(new Qualifier("ID", uniquename));
- if(getQualifierByName("Parent") != null)
- {
- final String parent =
- (String) getQualifierByName("Parent").getValues().get(0);
- setQualifier(new Qualifier("Parent", duplicatePrefix+parent));
+ if (getQualifierByName("Parent") != null) {
+ final String parent = (String) getQualifierByName("Parent")
+ .getValues().get(0);
+ setQualifier(new Qualifier("Parent", duplicatePrefix + parent));
}
- if(getQualifierByName("Derives_from") != null)
- {
- final String derives_from =
- (String) getQualifierByName("Derives_from").getValues().get(0);
- setQualifier(new Qualifier("Derives_from", duplicatePrefix+derives_from));
+ if (getQualifierByName("Derives_from") != null) {
+ final String derives_from = (String) getQualifierByName(
+ "Derives_from").getValues().get(0);
+ setQualifier(new Qualifier("Derives_from", duplicatePrefix
+ + derives_from));
}
// remove qualifiers that don't get transferred to duplicate
- final String removeQualifierNames[] =
- { "feature_id",
- "timelastmodified",
- "feature_relationship_rank",
- ProteinMapPanel.POLYPEPTIDE_DOMAIN,
- ProteinMapPanel.TMHMM[0],
- ProteinMapPanel.TMHMM[1],
- ProteinMapPanel.TMHMM[2],
- ProteinMapPanel.TMHMM[3],
- MatchPanel.ORTHOLOG,
- MatchPanel.ORTHOLOG
- };
-
- for(int i=0;i<removeQualifierNames.length; i++)
+ final String removeQualifierNames[] = { "feature_id",
+ "timelastmodified", "feature_relationship_rank",
+ ProteinMapPanel.POLYPEPTIDE_DOMAIN, ProteinMapPanel.TMHMM[0],
+ ProteinMapPanel.TMHMM[1], ProteinMapPanel.TMHMM[2],
+ ProteinMapPanel.TMHMM[3], MatchPanel.ORTHOLOG,
+ MatchPanel.ORTHOLOG };
+
+ for (int i = 0; i < removeQualifierNames.length; i++)
removeQualifierByName(removeQualifierNames[i]);
+ } catch (ReadOnlyException e) {
+ } catch (EntryInformationException e) {
}
- catch(ReadOnlyException e){}
- catch(EntryInformationException e){}
- }
- else
- {
- chadoGene = ((GFFStreamFeature)feature).chadoGene;
+ } else {
+ chadoGene = ((GFFStreamFeature) feature).chadoGene;
}
}
}
/**
- * Create a new GFFStreamFeature from the given line. The String should be
- * in gene finder format.
+ * Create a new GFFStreamFeature from the given line. The String should be in
+ * gene finder format.
**/
- public GFFStreamFeature(final String line)
- throws ReadFormatException
- {
+ public GFFStreamFeature(final String line) throws ReadFormatException {
super(null);
final StringVector line_bits = StringVector.getStrings(line, "\t", true);
- if(line_bits.size() < 8)
- throw new ReadFormatException("invalid GFF line: 8 fields needed " +
- "(got " + line_bits.size () +
- " fields) from: " + line);
+ if (line_bits.size() < 8)
+ throw new ReadFormatException("invalid GFF line: 8 fields needed "
+ + "(got " + line_bits.size() + " fields) from: " + line);
final String start_base_str = line_bits.elementAt(3).trim();
- final String end_base_str = line_bits.elementAt(4).trim();
+ final String end_base_str = line_bits.elementAt(4).trim();
final int start_base;
final int end_base;
- try
- {
+ try {
start_base = Integer.parseInt(start_base_str);
- end_base = Integer.parseInt(end_base_str);
- }
- catch(NumberFormatException e)
- {
- throw new ReadFormatException("Could not understand the start or end base " +
- "of a GFF feature: " + start_base_str +
- " " + end_base_str);
+ end_base = Integer.parseInt(end_base_str);
+ } catch (NumberFormatException e) {
+ throw new ReadFormatException(
+ "Could not understand the start or end base " + "of a GFF feature: "
+ + start_base_str + " " + end_base_str);
}
// start of qualifier parsing and setting
- try
- {
+ try {
final boolean complement_flag;
- if(line_bits.elementAt(6).equals("+"))
+ if (line_bits.elementAt(6).equals("+"))
complement_flag = false;
- else if(line_bits.elementAt(6).equals("-"))
+ else if (line_bits.elementAt(6).equals("-"))
complement_flag = true;
- else
- {
+ else {
// must be unstranded
complement_flag = false;
}
- if(line_bits.size() == 9)
- {
+ if (line_bits.size() == 9) {
final String rest_of_line = line_bits.elementAt(8);
final Hashtable<String, StringVector> attributes = parseAttributes(rest_of_line);
- for(final Enumeration<String> attribute_enum = attributes.keys();
- attribute_enum.hasMoreElements();)
- {
+ for (final Enumeration<String> attribute_enum = attributes.keys(); attribute_enum
+ .hasMoreElements();) {
String name = attribute_enum.nextElement();
final StringVector values = attributes.get(name);
- if(MatchPanel.isClusterTag(name))
- {
+ if (MatchPanel.isClusterTag(name)) {
List<ClusterLazyQualifierValue> lazyValues = new Vector<ClusterLazyQualifierValue>();
- for(int i=0; i<values.size(); i++)
- lazyValues.add(
- new ClusterLazyQualifierValue( (String)values.get(i), name,
- this ));
+ for (int i = 0; i < values.size(); i++)
+ lazyValues.add(new ClusterLazyQualifierValue((String) values
+ .get(i), name, this));
setQualifier(new QualifierLazyLoading(name, lazyValues));
- }
- else
- {
- if(values.size() == 0)
+ } else {
+ if (values.size() == 0)
setQualifier(new Qualifier(name));
else
setQualifier(new Qualifier(name, values));
@@ -378,200 +320,173 @@ public class GFFStreamFeature extends SimpleDocumentFeature
}
}
- if( !line_bits.elementAt(0).equals("null") )
- setGffSeqName( decode(line_bits.elementAt(0)) );
+ if (!line_bits.elementAt(0).equals("null"))
+ setGffSeqName(GFF3Encoder.decode(line_bits.elementAt(0)));
setKey(new Key(line_bits.elementAt(2)));
setGffSource(line_bits.elementAt(1));
- if( !line_bits.elementAt(5).equals(".") )
- {
- final Qualifier score_qualifier =
- new Qualifier("score", line_bits.elementAt(5));
+ if (!line_bits.elementAt(5).equals(".")) {
+ final Qualifier score_qualifier = new Qualifier("score",
+ line_bits.elementAt(5));
setQualifier(score_qualifier);
}
String frame = line_bits.elementAt(7);
- if(frame.equals ("0"))
+ if (frame.equals("0"))
frame = "1";
- else if(frame.equals("1"))
+ else if (frame.equals("1"))
frame = "2";
- else if(frame.equals("2"))
+ else if (frame.equals("2"))
frame = "3";
else
frame = ".";
- if(!frame.equals("."))
- {
- final Qualifier codon_start_qualifier =
- new Qualifier("codon_start", frame);
+ if (!frame.equals(".")) {
+ final Qualifier codon_start_qualifier = new Qualifier("codon_start",
+ frame);
setQualifier(codon_start_qualifier);
}
- if(start_base > end_base)
- throw new ReadFormatException("start position is greater than end " +
- "position: " + start_base + " > " +
- end_base+"\n"+line);
+ if (start_base > end_base)
+ throw new ReadFormatException("start position is greater than end "
+ + "position: " + start_base + " > " + end_base + "\n" + line);
- if(start_base < 0)
- throw new ReadFormatException("start position must be positive: " +
- start_base);
+ if (start_base < 0)
+ throw new ReadFormatException("start position must be positive: "
+ + start_base);
final Range location_range = new Range(start_base, end_base);
final RangeVector location_ranges = new RangeVector(location_range);
setLocation(new Location(location_ranges, complement_flag));
- }
- catch(ReadOnlyException e)
- {
+ } catch (ReadOnlyException e) {
throw new Error("internal error - unexpected exception: " + e);
- }
- catch(EntryInformationException e)
- {
+ } catch (EntryInformationException e) {
throw new Error("internal error - unexpected exception: " + e);
- }
- catch(OutOfRangeException e)
- {
+ } catch (OutOfRangeException e) {
throw new Error("internal error - unexpected exception: " + e);
}
- //this.gff_lines = new StringVector(line);
+ // this.gff_lines = new StringVector(line);
}
/**
- *
- * Store for spliced regions of segments ID's and ranges.
- *
- */
- public void setSegmentRangeStore(Hashtable<String, Range> id_range_store)
- {
+ *
+ * Store for spliced regions of segments ID's and ranges.
+ *
+ */
+ public void setSegmentRangeStore(Hashtable<String, Range> id_range_store) {
this.id_range_store = id_range_store;
}
- public Hashtable<String, Range> getSegmentRangeStore()
- {
- if(id_range_store == null)
- {
+ public Hashtable<String, Range> getSegmentRangeStore() {
+ if (id_range_store == null) {
id_range_store = new Hashtable<String, Range>();
- id_range_store.put((String)this.getQualifierByName("ID").getValues().get(0),
- this.getLocation().getTotalRange());
+ id_range_store.put((String) this.getQualifierByName("ID").getValues()
+ .get(0), this.getLocation().getTotalRange());
}
return id_range_store;
}
- public Hashtable<String, String> getNewIdMapToOldId()
- {
+ public Hashtable<String, String> getNewIdMapToOldId() {
return newIdMapToOldId;
}
/**
* Used when changing spliced feature uniquenames
+ *
* @param newIdMapToOldId
*/
- public void setNewIdMapToOldId(Hashtable<String, String> newIdMapToOldId)
- {
+ public void setNewIdMapToOldId(Hashtable<String, String> newIdMapToOldId) {
this.newIdMapToOldId = newIdMapToOldId;
}
/**
* Store for ID's and CHADO feature_relationship.rank
+ *
* @param feature_relationship_rank_store
*/
public void setFeature_relationship_rank_store(
- Hashtable<String, Integer> feature_relationship_rank_store)
- {
+ Hashtable<String, Integer> feature_relationship_rank_store) {
this.feature_relationship_rank_store = feature_relationship_rank_store;
}
/**
* Store for ID's and CHADO feature_relationship.rank
+ *
* @return
*/
- public Hashtable<String, Integer> getFeature_relationship_rank_store()
- {
+ public Hashtable<String, Integer> getFeature_relationship_rank_store() {
return feature_relationship_rank_store;
}
-
/**
* Get the chado uniquename
+ *
* @param r
* @return
*/
- public String getSegmentID(final Range r)
- {
- if(id_range_store != null)
- {
+ public String getSegmentID(final Range r) {
+ if (id_range_store != null) {
int offset = 0;
- if(getGffSeqName() != null && contig_ranges != null &&
- contig_ranges.containsKey(getGffSeqName()))
- {
+ if (getGffSeqName() != null && contig_ranges != null
+ && contig_ranges.containsKey(getGffSeqName())) {
// adjust for coordinates in multi-sequence GFF
Range offset_range = contig_ranges.get(getGffSeqName());
- offset = offset_range.getStart()-1;
+ offset = offset_range.getStart() - 1;
}
Enumeration<String> enum_ranges = id_range_store.keys();
- while(enum_ranges.hasMoreElements())
- {
- String key = enum_ranges.nextElement();
+ while (enum_ranges.hasMoreElements()) {
+ String key = enum_ranges.nextElement();
Range range = id_range_store.get(key);
- if(range.getStart() == r.getStart()-offset &&
- range.getEnd() == r.getEnd()-offset)
+ if (range.getStart() == r.getStart() - offset
+ && range.getEnd() == r.getEnd() - offset)
return key;
}
- }
- else if (getQualifierByName("ID") != null)
- {
- return (String)getQualifierByName("ID").getValues().get(0);
+ } else if (getQualifierByName("ID") != null) {
+ return (String) getQualifierByName("ID").getValues().get(0);
}
- logger4j.warn("RANGE NOT FOUND "+r.toString());
+ logger4j.warn("RANGE NOT FOUND " + r.toString());
return null;
}
/**
- * Get the feature ID based on the segments chado
- * uniquename's.
+ * Get the feature ID based on the segments chado uniquename's.
+ *
* @param rv
* @return
*/
- public String getSegmentID(final RangeVector rv)
- {
+ public String getSegmentID(final RangeVector rv) {
String id = "";
- if(id_range_store != null)
- {
+ if (id_range_store != null) {
String id_new;
Range range;
int index;
- for(int i=0; i<rv.size(); i++)
- {
- range = (Range)rv.get(i);
+ for (int i = 0; i < rv.size(); i++) {
+ range = (Range) rv.get(i);
id_new = getSegmentID(range);
String prefix[] = getPrefix(id_new, ':');
- if(prefix[0] != null)
- {
+ if (prefix[0] != null) {
index = id.indexOf(prefix[0]);
- if(id.equals("") || index < 0)
- {
- if(!id.equals(""))
- id = id +",";
- id = id+prefix[0] + "{" + prefix[1] + "}";
+ if (id.equals("") || index < 0) {
+ if (!id.equals(""))
+ id = id + ",";
+ id = id + prefix[0] + "{" + prefix[1] + "}";
continue;
}
index = id.indexOf('}', index);
- id = id.substring(0,index) + "," +
- prefix[1] + id.substring(index);
- }
- else if(id_new != null)
- {
- if(!id.equals(""))
- id = id +",";
- id = id+id_new;
+ id = id.substring(0, index) + "," + prefix[1] + id.substring(index);
+ } else if (id_new != null) {
+ if (!id.equals(""))
+ id = id + ",";
+ id = id + id_new;
}
}
}
@@ -580,204 +495,149 @@ public class GFFStreamFeature extends SimpleDocumentFeature
}
/**
- * Get the ID prefix, e.g. for SPAC1556.06.1:exon:2
- * returns SPAC1556.06.1:exon as the prefix and 2 as the
- * index.
+ * Get the ID prefix, e.g. for SPAC1556.06.1:exon:2 returns SPAC1556.06.1:exon
+ * as the prefix and 2 as the index.
+ *
* @param id
* @return
*/
- public String[] getPrefix(final String id,
- final char separator)
- {
+ public String[] getPrefix(final String id, final char separator) {
String prefix[] = new String[2];
int index = id.lastIndexOf(separator);
- if(index > -1)
- {
- prefix[0] = id.substring(0,index);
- prefix[1] = id.substring(index+1);
+ if (index > -1) {
+ prefix[0] = id.substring(0, index);
+ prefix[1] = id.substring(index + 1);
}
return prefix;
}
/**
* Used to automatically generate
+ *
* @param prefix
* @return
*/
- public int getAutoNumber(final String prefix,
- final char separator)
- {
- int auto = 1;
+ public int getAutoNumber(final String prefix, final char separator) {
+ int auto = 1;
String val = prefix + separator + auto;
- while(id_range_store.containsKey(val))
- {
+ while (id_range_store.containsKey(val)) {
auto++;
val = prefix + separator + auto;
}
return auto;
}
-
- /**
- * For gff-version 3:
- * http://www.sequenceontology.org/gff3.shtml
- * Remove URL escaping rule (e.g. space="%20" or "+")
- */
- public static String decode(String s)
- {
- int ind;
- String enc;
- String dec;
-
- for(int i=0; i<MAP_DECODE.length; i++)
- {
- enc = MAP_DECODE[i][1];
- dec = MAP_DECODE[i][0];
- while( (ind = s.indexOf(enc)) > -1)
- s = s.substring(0,ind) + dec + s.substring(ind+enc.length());
- }
- return s;
- }
-
-
- /**
- * For gff-version 3:
- * http://www.sequenceontology.org/gff3.shtml
- * Add URL escaping rule (e.g. space="%20" or "+")
- */
- public static String encode(String s)
- {
- int ind;
- String enc;
- String dec;
-
- for(int i=0; i<MAP_ENCODE.length; i++)
- {
- enc = MAP_ENCODE[i][1];
- dec = MAP_ENCODE[i][0];
- while( (ind = s.indexOf(dec)) > -1 )
- s = s.substring(0,ind) + enc + s.substring(ind+1);
- }
- return s;
- }
-
-
/**
- * Return the reference of a new copy of this Feature.
+ * Return the reference of a new copy of this Feature.
**/
- public Feature copy()
- {
+ public Feature copy() {
final Feature return_value = new GFFStreamFeature(this);
return return_value;
}
/**
- * Read and return a GFFStreamFeature from a stream. A feature must be the
- * next thing in the stream.
- * @param stream the Feature is read from this stream
- * @exception IOException thrown if there is a problem reading the Feature -
- * most likely ReadFormatException.
- * @exception InvalidRelationException Thrown if this Feature cannot contain
- * the given Qualifier.
- * @return null if in_stream is at the end of file when the method is
- * called
+ * Read and return a GFFStreamFeature from a stream. A feature must be the
+ * next thing in the stream.
+ *
+ * @param stream
+ * the Feature is read from this stream
+ * @exception IOException
+ * thrown if there is a problem reading the Feature - most likely
+ * ReadFormatException.
+ * @exception InvalidRelationException
+ * Thrown if this Feature cannot contain the given Qualifier.
+ * @return null if in_stream is at the end of file when the method is called
*/
protected static GFFStreamFeature readFromStream(LinePushBackReader stream)
- throws IOException, InvalidRelationException
- {
+ throws IOException, InvalidRelationException {
final String line = stream.readLine();
- if(line == null)
+ if (line == null)
return null;
- try
- {
+ try {
return new GFFStreamFeature(line);
- }
- catch(ReadFormatException exception)
- {
+ } catch (ReadFormatException exception) {
// re-throw the exception with the line number added
final String new_error_string = exception.getMessage();
- throw new ReadFormatException(new_error_string,
- stream.getLineNumber());
+ throw new ReadFormatException(new_error_string, stream.getLineNumber());
}
}
/**
- * Read the details of a feature from an EMBL stream into the current
- * object.
- * @param entry_information The EntryInformation object of the Entry that
- * will contain the Feature.
- * @param in_stream the Feature is read from this stream
- * @exception IOException thrown if there is a problem reading the Feature -
- * most likely ReadFormatException if the stream does not contain GFF
- * feature.
+ * Read the details of a feature from an EMBL stream into the current object.
+ *
+ * @param entry_information
+ * The EntryInformation object of the Entry that will contain the
+ * Feature.
+ * @param in_stream
+ * the Feature is read from this stream
+ * @exception IOException
+ * thrown if there is a problem reading the Feature - most likely
+ * ReadFormatException if the stream does not contain GFF
+ * feature.
**/
public void setFromStream(final EntryInformation entry_information,
- final LinePushBackReader in_stream)
- throws IOException, InvalidRelationException, ReadOnlyException
- {
+ final LinePushBackReader in_stream) throws IOException,
+ InvalidRelationException, ReadOnlyException {
throw new ReadOnlyException();
}
/**
- * Write this Feature to the given stream.
- * @param writer The stream to write to.
- * @exception IOException thrown if there is an io problem while writing
- * the Feature.
+ * Write this Feature to the given stream.
+ *
+ * @param writer
+ * The stream to write to.
+ * @exception IOException
+ * thrown if there is an io problem while writing the Feature.
**/
- public void writeToStream(final Writer writer)
- throws IOException
- {
+ public void writeToStream(final Writer writer) throws IOException {
final RangeVector ranges = getLocation().getRanges();
final int ranges_size = ranges.size();
-// final Hashtable contig_ranges = SimpleDocumentEntry.getContigRanges();
- for(int i = 0; i < ranges_size; ++i)
- {
- Range this_range = (Range)ranges.elementAt(i);
+ // final Hashtable contig_ranges = SimpleDocumentEntry.getContigRanges();
+ for (int i = 0; i < ranges_size; ++i) {
+ Range this_range = (Range) ranges.elementAt(i);
String seqname = getGffSeqName();
- String source = getGffSource();
- Qualifier score = getQualifierByName("score");
- Qualifier group = getQualifierByName("group");
+ String source = getGffSource();
+ Qualifier score = getQualifierByName("score");
+ Qualifier group = getQualifierByName("group");
// source becomes a Dbxref in chado
String source_str = null;
- if(getQualifierByName("Dbxref") != null)
- {
+ if (getQualifierByName("Dbxref") != null) {
source_str = getDbxrefGFFSource(getQualifierByName("Dbxref"));
}
int start = this_range.getStart();
- int end = this_range.getEnd();
+ int end = this_range.getEnd();
- if(seqname == null && ((GFFDocumentEntry)getEntry()).getDocument() != null)
- seqname = ((GFFDocumentEntry)getEntry()).getDocument().getName();
- if(seqname == null)
+ if (seqname == null
+ && ((GFFDocumentEntry) getEntry()).getDocument() != null)
+ seqname = ((GFFDocumentEntry) getEntry()).getDocument().getName();
+ if (seqname == null)
seqname = deriveSeqName(start);
- if(source == null)
+ if (source == null)
source = "artemis";
- if(score == null)
+ if (score == null)
score = new Qualifier("score", ".");
- if(seqname != null && contig_ranges != null &&
- contig_ranges.containsKey(seqname))
- {
+ if (seqname != null && contig_ranges != null
+ && contig_ranges.containsKey(seqname)) {
Range offset_range = contig_ranges.get(seqname);
- start = start-offset_range.getStart()+1;
- end = end-offset_range.getStart()+1;
+ start = start - offset_range.getStart() + 1;
+ end = end - offset_range.getStart() + 1;
}
- if(group == null || group.getValues() == null ||
- group.getValues().elementAt(0).equals(""))
- {
+ if (group == null || group.getValues() == null
+ || group.getValues().elementAt(0).equals("")) {
final Qualifier gene = getQualifierByName("gene");
- if(gene == null)
+ if (gene == null)
group = new Qualifier("group", "");
else
group = gene;
@@ -786,333 +646,358 @@ public class GFFStreamFeature extends SimpleDocumentFeature
String frame = ".";
final Qualifier codon_start = getQualifierByName("codon_start");
- if(codon_start != null)
- {
- frame = (String)(codon_start.getValues()).elementAt(0);
+ if (codon_start != null) {
+ frame = (String) (codon_start.getValues()).elementAt(0);
- if(frame.equals ("1"))
+ if (frame.equals("1"))
frame = "0";
- else if(frame.equals("2"))
+ else if (frame.equals("2"))
frame = "1";
- else if(frame.equals("3"))
+ else if (frame.equals("3"))
frame = "2";
else
frame = ".";
}
// phase is REQUIRED for all CDS features
- if(getKey().equals("CDS") && frame.equals("."))
+ if (getKey().equals("CDS") && frame.equals("."))
frame = "0";
final String myId = getSegmentID(this_range);
String attribute_string = unParseAttributes(myId);
- if(source_str == null && source != null)
- source_str = source;
+ if (source_str == null && source != null)
+ source_str = source;
final String translation = getTranslation();
- if(translation != null)
+ if (translation != null)
attribute_string = attribute_string + ";" + translation;
- writer.write(seqname + "\t" +
- source_str + "\t" +
- getKey().getKeyString() + "\t" +
- start + "\t" +
- end + "\t" +
- score.getValues() .elementAt(0)+ "\t" +
- (getLocation().isComplement() ? "-\t" : "+\t") +
- frame + "\t" +
- attribute_string + "\n");
+ writer.write(seqname + "\t" + source_str + "\t" + getKey().getKeyString()
+ + "\t" + start + "\t" + end + "\t" + score.getValues().elementAt(0)
+ + "\t" + (getLocation().isComplement() ? "-\t" : "+\t") + frame
+ + "\t" + attribute_string + "\n");
}
}
/**
- * If the seqname is not set for this feature try to derive the contig/chromosome
- * it is located on
+ * If the seqname is not set for this feature try to derive the
+ * contig/chromosome it is located on
+ *
* @param start
* @return
*/
- private String deriveSeqName(int start)
- {
+ private String deriveSeqName(int start) {
String seqname = null;
- if(contig_ranges != null)
- {
+ if (contig_ranges != null) {
final Enumeration<String> contigEnum = contig_ranges.keys();
- while(contigEnum.hasMoreElements())
- {
+ while (contigEnum.hasMoreElements()) {
final String key = contigEnum.nextElement();
final Range r = contig_ranges.get(key);
- if(r.getStart() > start)
+ if (r.getStart() > start)
continue;
- if(r.getEnd() > start)
+ if (r.getEnd() > start)
return key;
}
- }
- else
- {
- try
- {
- seqname = ((GFFStreamFeature)(getEntry().getAllFeatures().elementAt(0))).getGffSeqName();
+ } else {
+ try {
+ seqname = ((GFFStreamFeature) (getEntry().getAllFeatures().elementAt(0)))
+ .getGffSeqName();
+ } catch (Exception e) {
}
- catch(Exception e) {}
}
- if(seqname == null)
+ if (seqname == null)
seqname = "gff_seqname";
return seqname;
}
/**
- * Return a String containing the qualifiers of this feature in a form
- * suitable for using as the last field of a GFF line. The codon_start
- * attribute is not included since GFF has a frame field. gff_seqname,
- * gff_source and score aren't included since they have corresponding
- * fields.
+ * Return a String containing the qualifiers of this feature in a form
+ * suitable for using as the last field of a GFF line.
**/
- private String unParseAttributes(final String myId)
- {
- final StringBuffer buffer = new StringBuffer();
+ private String unParseAttributes(final String myId) {
final QualifierVector qualifiers = getQualifiers();
-
- final String names[] = { "ID", "Name", "Alias", "Parent",
- "Derives_from",
- "Target", "Gap", "Note",
- "Dbxref", "Ontology_term",
- "Start_range", "End_range",
- "Is_circular"};
- int count = 0;
- final int names_length = names.length;
-
- if(myId != null)
- {
- buffer.append("ID=");
- buffer.append(encode(myId));
- count++;
+ GFF3AttributeBuilder abuf = new GFF3AttributeBuilder();
+ prepareProcessors(abuf);
+
+ for (String attr : attrs_to_filter) {
+ abuf.ignore(attr);
}
- for(int i=1; i<names_length; i++)
- {
- Qualifier this_qualifier = qualifiers.getQualifierByName(names[i]);
+ final int names_length = abuf.reserved_a.length;
- if(this_qualifier == null)
- continue;
-
- final String this_qualifier_str = getQualifierString(this_qualifier, true);
- if(this_qualifier_str == null)
+ // add ID attribute
+ if (myId != null) {
+ abuf.add("ID", myId);
+ }
+
+ // build reserved attributes
+ for (int i = 1; i < names_length; i++) {
+ Qualifier this_qualifier = qualifiers.getQualifierByName(abuf.reserved_a[i]);
+
+ if (this_qualifier == null)
continue;
- if(count != 0)
- buffer.append(";");
- buffer.append(this_qualifier_str);
- count++;
+ abuf.add(this_qualifier.getName(), this_qualifier.getValues());
}
+ // build remaining attributes
boolean lname;
- for(Qualifier this_qualifier: qualifiers)
- {
+ for (Qualifier this_qualifier : qualifiers) {
lname = false;
- for(int j=0; j<names_length; j++)
- if(this_qualifier.getName().equals(names[j]))
- lname = true;
- if(lname)
- continue;
-
- if(attrs_to_filter.contains(this_qualifier.getName()))
- continue;
-
- if( (this_qualifier.getName().equals("private") && System.getProperty("noprivate") != null) ||
- (this_qualifier.getName().equals("history") && System.getProperty("nohistory") != null) )
+ // skip reserved names
+ for (int j = 0; j < names_length; j++)
+ if (this_qualifier.getName().equals(abuf.reserved_a[j]))
+ lname = true;
+ if (lname)
continue;
- final String this_qualifier_str = getQualifierString(this_qualifier, false);
-
- if(this_qualifier_str == null)
+ // skip internal qualifiers
+ if ((this_qualifier.getName().equals("private") && System
+ .getProperty("noprivate") != null)
+ || (this_qualifier.getName().equals("history") && System
+ .getProperty("nohistory") != null))
continue;
- if(count != 0)
- buffer.append(";");
- buffer.append(this_qualifier_str);
+ abuf.add(this_qualifier.getName(), this_qualifier.getValues());
}
- return buffer.toString();
+ return abuf.toString();
}
+ void prepareProcessors(GFF3AttributeBuilder abuf) {
+ GFF3AttributeAggregator productProc = new GFF3AttributeAggregator() {
+ @Override
+ public String process(StringVector values) {
+ StringBuilder buffer = new StringBuilder();
+ if (values != null && values.size() > 0) {
+ for (int value_index = 0; value_index < values.size(); ++value_index) {
+ final String this_value;
+ int index = values.elementAt(value_index).indexOf("term=");
+ // strip off the 'term=' etc
+ if (index > -1)
+ this_value = GFF3Encoder.encode(values.elementAt(value_index)
+ .substring(index + 5,
+ values.elementAt(value_index).length() - 1));
+ else
+ this_value = GFF3Encoder.encode(values.elementAt(value_index));
+ if (value_index > 0 && value_index < (values.size())) {
+ buffer.append(",");
+ }
+ buffer.append(this_value);
+ }
+ }
+ return buffer.toString();
+ }
+ };
+
+ GFF3AttributeAggregator ecProc = new GFF3AttributeAggregator() {
+ @Override
+ public String process(StringVector values) {
+ StringBuilder buffer = new StringBuilder();
+ if (values != null && values.size() > 0) {
+ for (int value_index = 0; value_index < values.size(); ++value_index) {
+ final String this_value = "EC:"
+ + GFF3Encoder.encode(values.elementAt(value_index));
+ if (value_index > 0 && value_index < (values.size())) {
+ buffer.append(",");
+ }
+ buffer.append(this_value);
+ }
+ }
+ return buffer.toString();
+ }
+ };
+
+ GFF3AttributeAggregator psysIDProc = new GFF3AttributeAggregator() {
+ @Override
+ public String process(StringVector values) {
+ StringBuilder buffer = new StringBuilder();
+ if (values != null && values.size() > 0) {
+ for (int value_index = 0; value_index < values.size(); ++value_index) {
+ final String this_value;
+ int index = values.elementAt(value_index).indexOf(";current=");
+ if (index > -1)
+ this_value = GFF3Encoder.encode(values.elementAt(value_index)
+ .substring(0, index - 1));
+ else
+ this_value = GFF3Encoder.encode(values.elementAt(value_index));
+ if (value_index > 0 && value_index < (values.size())) {
+ buffer.append(",");
+ }
+ buffer.append(this_value);
+ }
+ }
+ return buffer.toString();
+ }
+ };
+
+ GFF3AttributeAggregator classProc = new GFF3AttributeAggregator() {
+ @Override
+ public String process(StringVector values) {
+ StringBuilder buffer = new StringBuilder();
+ if (values != null && values.size() > 0) {
+ for (int value_index = 0; value_index < values.size(); ++value_index) {
+ final String this_value;
+ int index = values.elementAt(value_index).indexOf("::");
+ if (index > -1)
+ this_value = GFF3Encoder.encode(values.elementAt(value_index)
+ .substring(0, index));
+ else
+ this_value = GFF3Encoder.encode(values.elementAt(value_index));
+ if (value_index > 0 && value_index < (values.size())) {
+ buffer.append(",");
+ }
+ buffer.append(this_value);
+ }
+ }
+ return buffer.toString();
+ }
+ };
+
+ GFF3AttributeAggregator startEndRangeProc = new GFF3AttributeAggregator() {
+ @Override
+ public String process(StringVector values) {
+ StringBuilder buffer = new StringBuilder();
+ if (values != null && values.size() > 0) {
+ for (int value_index = 0; value_index < values.size(); ++value_index) {
+ if (value_index > 0 && value_index < (values.size())) {
+ buffer.append(",");
+ }
+ buffer.append(values.elementAt(value_index));
+ }
+ }
+ return buffer.toString();
+ }
+ };
+
+ GFF3AttributeAggregator goProc = new GFF3AttributeAggregator() {
+ @Override
+ public String process(StringVector values) {
+ StringBuilder buffer = new StringBuilder();
+ if (values != null && values.size() > 0) {
+ for (int value_index = 0; value_index < values.size(); ++value_index) {
+ int goindex = values.elementAt(value_index).indexOf("GOid=");
+ int termindex = values.elementAt(value_index).indexOf(";term=");
+ if (goindex > -1 && termindex > -1) {
+ buffer.append(GFF3Encoder.encode(values.elementAt(value_index)
+ .substring(goindex + 5, termindex)));
+ if (value_index < (values.size()) - 1)
+ buffer.append(",");
+ }
+ }
+ }
+ return buffer.toString();
+ }
+ };
+
+ // map GO -> full_GO
+ abuf.setMapping("GO", "full_GO");
+ abuf.setGlue("full_GO", ",");
+
+ // merge curation and comment
+ abuf.setMapping("curation", "comment");
+
+ // also put GOs in Ontology_term
+ abuf.setClone("full_GO", "Ontology_term");
+ abuf.setAggregator("Ontology_term", goProc);
+ abuf.setGlue("Ontology_term", ",");
+
+ // class
+ abuf.setAggregator("class", classProc);
+
+ // EC numbers go into Dbxref
+ abuf.setMapping("EC_number", "Dbxref");
+ abuf.setAggregator("EC_number", ecProc);
+ abuf.setGlue("Dbxref", ",");
+
+ // start/end ranges
+ abuf.setAggregator("Start_range", startEndRangeProc);
+ abuf.setAggregator("End_range", startEndRangeProc);
+
+ // previous_systematic_id
+ abuf.setAggregator("previous_systematic_id", psysIDProc);
+
+ // product
+ abuf.setAggregator("product", productProc);
+ }
/**
* Get the translation qualifier string for polypeptide features.
*/
- private String getTranslation()
- {
- if (! getKey().getKeyString().equals("polypeptide"))
- return null;
- if (chadoGene != null)
- {
- if(getUserData() == null)
+ private String getTranslation() {
+ if (!getKey().getKeyString().equals("polypeptide"))
+ return null;
+ if (chadoGene != null) {
+ if (getUserData() == null)
new uk.ac.sanger.artemis.Feature(this);
- // the above line constructs the appropriate userData within this current GFFStreamFeature object,
+ // the above line constructs the appropriate userData within this current
+ // GFFStreamFeature object,
// which is required by the following GeneUtils.deriveResidues()
String residues = GeneUtils.deriveResidues(this);
if (residues != null)
- return "translation="+residues;
+ return "translation=" + residues;
}
return null;
}
/**
- * Used to write out the GFF attributes.
- * @param q the qualifier to represent as a <code>String</code>
- * @param reserved indicate if this is one of the reserved tags or not
- * @return the <code>String</code> representation
- */
- private String getQualifierString(Qualifier q, boolean reserved )
- {
- StringBuffer buffer = new StringBuffer();
- final String name = q.getName();
-
- if(name.equals("codon_start") || name.equals("gff_source") ||
- name.equals("gff_seqname") || name.equals("score"))
- return null;
-
- final StringVector values = q.getValues();
-
- /* ignore qualifiers with just one empty value, will mess up GFF3 output */
- if(values != null && values.size() == 1)
- {
- if (values.elementAt(0).replaceAll("\\s+","").equals(""))
- return null;
- }
-
- /*
- * GSV :
- * The Bio::FeatureIO perl module falls over if there are Uppercased
- * attribute names for tags which aren't part of the standard reserved
- * set. So we lowercase these, since in the specification it says :
- *
- * "All attributes that begin with an uppercase letter are reserved for
- * later use. Attributes that begin with a lowercase letter can be used
- * freely by applications."
- * see http://www.sequenceontology.org/gff3.shtml
- */
- String nameToBuffer = encode(name);
-
- if (! reserved)
- nameToBuffer = Character.toLowerCase(nameToBuffer.charAt(0)) + nameToBuffer.substring(1);
- buffer.append(nameToBuffer);
-
- if(values != null && values.size() > 0)
- {
- buffer.append('=');
- for(int value_index = 0; value_index < values.size();
- ++value_index)
- {
- final String this_value;
- if(name.equals("class"))
- {
- int index = values.elementAt(value_index).indexOf("::");
- if(index > -1)
- this_value = encode(values.elementAt(value_index).substring(0,index));
- else
- this_value = encode(values.elementAt(value_index));
- }
- else
- this_value = encode(values.elementAt(value_index));
-
- if(value_index>0)
- buffer.append("%2C");
-
- if(name.equals("Parent"))
- buffer.append(this_value);
- else
- {
- try
- {
- buffer.append(Integer.valueOf(this_value));
- }
- catch(NumberFormatException _)
- {
- // not an integer
- try
- {
- buffer.append(Double.valueOf(this_value));
- }
- catch (NumberFormatException __)
- {
- // not a double or integer so quote it
- buffer.append(this_value);
- }
- }
- }
- }
- }
- if (buffer.toString().charAt(buffer.toString().length()-1) == '=')
- System.out.println(buffer.toString() + " ----- values length was " + values.size() + ": '" + values.elementAt(0) + "'");
- return buffer.toString();
- }
-
- /**
- * Parse the given String as ACeDB format attributes.
- * Adapted from code by Matthew Pocock for the BioJava project.
- *
- * Modified for gff-version 3.
- * @return Return a Hashtable. Each key is an attribute name and each value
- * of the Hashtable is a StringVector containing the attribute values.
- * If the attribute has no value then the Hashtable value will be a zero
- * length vector.
+ * Parse the given String as ACeDB format attributes. Adapted from code by
+ * Matthew Pocock for the BioJava project.
+ *
+ * Modified for gff-version 3.
+ *
+ * @return Return a Hashtable. Each key is an attribute name and each value of
+ * the Hashtable is a StringVector containing the attribute values. If
+ * the attribute has no value then the Hashtable value will be a zero
+ * length vector.
**/
- private Hashtable<String, StringVector> parseAttributes(final String att_val_list)
- {
+ private Hashtable<String, StringVector> parseAttributes(
+ final String att_val_list) {
final Hashtable<String, StringVector> attr = new Hashtable<String, StringVector>();
int ind_start = 0;
int ind_end;
- while( (ind_end = att_val_list.indexOf(";",ind_start)) > -1 ||
- ind_start < att_val_list.length() )
- {
- if(ind_end < 0)
+ while ((ind_end = att_val_list.indexOf(";", ind_start)) > -1
+ || ind_start < att_val_list.length()) {
+ if (ind_end < 0)
ind_end = att_val_list.length();
- final String this_token = decode(att_val_list.substring(ind_start, ind_end).trim());
- ind_start = ind_end+1;
+ final String this_token = GFF3Encoder.decode(att_val_list.substring(ind_start,
+ ind_end).trim());
+ ind_start = ind_end + 1;
int index_of_first_space = this_token.indexOf(" ");
final String att_name;
StringVector att_values = new StringVector();
- if( this_token.indexOf("=") > -1 &&
- (this_token.indexOf("=") < index_of_first_space ||
- index_of_first_space == -1) )
- {
+ if (this_token.indexOf("=") > -1
+ && (this_token.indexOf("=") < index_of_first_space || index_of_first_space == -1)) {
index_of_first_space = this_token.indexOf("=");
att_name = this_token.substring(0, index_of_first_space);
- att_values.add(this_token.substring(index_of_first_space+1).trim());
- }
- else if(index_of_first_space == -1)
+ att_values.add(this_token.substring(index_of_first_space + 1).trim());
+ } else if (index_of_first_space == -1)
att_name = this_token;
- else
- {
+ else {
att_name = this_token.substring(0, index_of_first_space);
- String rest_of_token =
- this_token.substring(index_of_first_space+1).trim();
+ String rest_of_token = this_token.substring(index_of_first_space + 1)
+ .trim();
- while(rest_of_token.length() > 0)
- {
- if(rest_of_token.startsWith("\""))
- {
+ while (rest_of_token.length() > 0) {
+ if (rest_of_token.startsWith("\"")) {
int quote_index = 0;
- do
- {
+ do {
quote_index++;
quote_index = rest_of_token.indexOf("\"", quote_index);
- } while(quote_index > -1 &&
- rest_of_token.charAt(quote_index - 1) == '\\');
+ } while (quote_index > -1
+ && rest_of_token.charAt(quote_index - 1) == '\\');
- if(quote_index < 0)
- {
+ if (quote_index < 0) {
// no closing quote - panic
- final Hashtable<String, StringVector> panic_attributes =
- new Hashtable<String, StringVector>();
+ final Hashtable<String, StringVector> panic_attributes = new Hashtable<String, StringVector>();
final StringVector notes = new StringVector();
notes.add(att_val_list);
panic_attributes.put("note", notes);
@@ -1123,60 +1008,52 @@ public class GFFStreamFeature extends SimpleDocumentFeature
final String next_bit = rest_of_token.substring(1, quote_index);
att_values.add(next_bit);
rest_of_token = rest_of_token.substring(quote_index + 1).trim();
- }
- else
- {
+ } else {
final int index_of_next_space = rest_of_token.indexOf(" ");
- if(index_of_next_space == -1)
- {
+ if (index_of_next_space == -1) {
att_values.add(rest_of_token);
rest_of_token = "";
- }
- else
- {
- final String next_bit =
- rest_of_token.substring(0, index_of_next_space);
+ } else {
+ final String next_bit = rest_of_token.substring(0,
+ index_of_next_space);
att_values.add(next_bit);
- rest_of_token =
- rest_of_token.substring(index_of_next_space).trim();
+ rest_of_token = rest_of_token.substring(index_of_next_space)
+ .trim();
}
}
}
- if(!rest_of_token.equals(""))
+ if (!rest_of_token.equals(""))
att_values.add(rest_of_token);
}
- if(att_name.equals("Dbxref") || att_name.equals("Alias")) // convert to multi-line
+ if (att_name.equals("Dbxref") || att_name.equals("Alias")) // convert to
+ // multi-line
{
- StringTokenizer stok =
- new StringTokenizer((String)att_values.get(0), ",");
+ StringTokenizer stok = new StringTokenizer((String) att_values.get(0),
+ ",");
StringVector str_values = new StringVector();
- while(stok.hasMoreTokens())
+ while (stok.hasMoreTokens())
str_values.add(stok.nextToken());
att_values = str_values;
}
- if(att_name.equals("timelastmodified"))
- {
- try
- {
- this.timelastmodified =
- new Timestamp( Long.parseLong((String)att_values.get(0)) );
- SimpleDateFormat date_format =
- new SimpleDateFormat("dd.MM.yyyy hh:mm:ss z");
- att_values.set(0,date_format.format(timelastmodified));
- }
- catch(NumberFormatException e)
- {
- att_values.set(0,(String)att_values.get(0));
+ if (att_name.equals("timelastmodified")) {
+ try {
+ this.timelastmodified = new Timestamp(
+ Long.parseLong((String) att_values.get(0)));
+ SimpleDateFormat date_format = new SimpleDateFormat(
+ "dd.MM.yyyy hh:mm:ss z");
+ att_values.set(0, date_format.format(timelastmodified));
+ } catch (NumberFormatException e) {
+ att_values.set(0, (String) att_values.get(0));
}
}
- if(attr.get(att_name) != null)
+ if (attr.get(att_name) != null)
attr.get(att_name).add(att_values);
else
attr.put(att_name, att_values);
@@ -1187,32 +1064,30 @@ public class GFFStreamFeature extends SimpleDocumentFeature
/**
* Get the feature time last modified timestamp.
+ *
* @return
*/
- public Timestamp getLastModified()
- {
+ public Timestamp getLastModified() {
return timelastmodified;
}
/**
* Get the GFF_source value of a Dbxref qualifier.
+ *
* @param qualifier
- * @return the gff_source value or NULL
+ * @return the gff_source value or NULL
*/
- private String getDbxrefGFFSource(final Qualifier qualifier)
- {
- StringVector qualifier_strings =
- StreamQualifier.toStringVector(null, qualifier);
+ private String getDbxrefGFFSource(final Qualifier qualifier) {
+ StringVector qualifier_strings = StreamQualifier.toStringVector(null,
+ qualifier);
- for(int i=0; i<qualifier_strings.size(); i++)
- {
- String qualifier_string = (String)qualifier_strings.elementAt(i);
+ for (int i = 0; i < qualifier_strings.size(); i++) {
+ String qualifier_string = (String) qualifier_strings.elementAt(i);
- if(qualifier_string.indexOf("GFF_source:") >-1)
- {
- int index = qualifier_string.indexOf(":")+1;
+ if (qualifier_string.indexOf("GFF_source:") > -1) {
+ int index = qualifier_string.indexOf(":") + 1;
int len = qualifier_string.length();
- if(qualifier_string.endsWith("\""))
+ if (qualifier_string.endsWith("\""))
len--;
return qualifier_string.substring(index, len);
}
@@ -1222,136 +1097,112 @@ public class GFFStreamFeature extends SimpleDocumentFeature
/**
* Set the feature time last modified timestamp.
+ *
* @param timelastmodified
*/
- public void setLastModified(final Timestamp timelastmodified)
- {
+ public void setLastModified(final Timestamp timelastmodified) {
this.timelastmodified = timelastmodified;
// now update the qualifier value itself
QualifierVector qualifiers = getQualifiers();
Qualifier qualifier = qualifiers.getQualifierByName("timelastmodified");
- SimpleDateFormat date_format =
- new SimpleDateFormat("dd.MM.yyyy hh:mm:ss z");
-
- if(qualifier != null)
- qualifier.removeValue((String)qualifier.getValues().get(0));
- else
- {
- try
- {
+ SimpleDateFormat date_format = new SimpleDateFormat("dd.MM.yyyy hh:mm:ss z");
+
+ if (qualifier != null)
+ qualifier.removeValue((String) qualifier.getValues().get(0));
+ else {
+ try {
qualifier = new Qualifier("timelastmodified",
- date_format.format(timelastmodified));
+ date_format.format(timelastmodified));
setQualifier(qualifier);
return;
+ } catch (EntryInformationException eie) {
+ } catch (ReadOnlyException roe) {
}
- catch(EntryInformationException eie)
- {}
- catch(ReadOnlyException roe)
- {}
}
qualifier.addValue(date_format.format(timelastmodified));
}
/**
- * Returns true if and only if this Feature can't be changed or can't be
- * removed from it's entry.
+ * Returns true if and only if this Feature can't be changed or can't be
+ * removed from it's entry.
**/
- public boolean isReadOnly ()
- {
- if(readOnlyFeature)
+ public boolean isReadOnly() {
+ if (readOnlyFeature)
return true;
return super.isReadOnly();
}
- public void setReadOnlyFeature(boolean readOnlyFeature)
- {
+ public void setReadOnlyFeature(boolean readOnlyFeature) {
this.readOnlyFeature = readOnlyFeature;
}
- public ChadoCanonicalGene getChadoGene()
- {
+ public ChadoCanonicalGene getChadoGene() {
return chadoGene;
}
- public void setChadoGene(ChadoCanonicalGene chadoGene)
- {
+ public void setChadoGene(ChadoCanonicalGene chadoGene) {
this.chadoGene = chadoGene;
}
- public boolean isVisible()
- {
+ public boolean isVisible() {
return visible;
}
- public void setVisible(boolean visible)
- {
+ public void setVisible(boolean visible) {
this.visible = visible;
}
- public String getGffSeqName()
- {
+ public String getGffSeqName() {
return gffSeqName;
}
- public void setGffSeqName(String gffSeqName)
- {
+ public void setGffSeqName(String gffSeqName) {
this.gffSeqName = gffSeqName;
}
- public String getGffSource()
- {
+ public String getGffSource() {
return gffSource;
}
- public void setGffSource(String gffSource)
- {
+ public void setGffSource(String gffSource) {
this.gffSource = gffSource;
}
- public boolean isLazyLoaded()
- {
+ public boolean isLazyLoaded() {
return lazyLoaded;
}
- public void setLazyLoaded(boolean lazyLoaded)
- {
+ public void setLazyLoaded(boolean lazyLoaded) {
this.lazyLoaded = lazyLoaded;
}
- public org.gmod.schema.sequence.Feature getChadoLazyFeature()
- {
+ public org.gmod.schema.sequence.Feature getChadoLazyFeature() {
return chadoLazyFeature;
}
public void setChadoLazyFeature(
- org.gmod.schema.sequence.Feature chadoLazyFeature)
- {
+ org.gmod.schema.sequence.Feature chadoLazyFeature) {
this.chadoLazyFeature = chadoLazyFeature;
}
- protected static boolean isGTF(Feature feature)
- {
- if(!(feature instanceof GFFStreamFeature))
+ protected static boolean isGTF(Feature feature) {
+ if (!(feature instanceof GFFStreamFeature))
return false;
- final String names[] = { "ID", "Name", "Alias", "Parent",
- "Derives_from",
- "Target", "Gap", "Note",
- "Dbxref", "Ontology_term" };
+ final String names[] = { "ID", "Name", "Alias", "Parent", "Derives_from",
+ "Target", "Gap", "Note", "Dbxref", "Ontology_term" };
- for(String name: names)
- {
- if(feature.getQualifiers().getQualifierByName(name) != null)
+ for (String name : names) {
+ if (feature.getQualifiers().getQualifierByName(name) != null)
return false;
}
- if(feature.getQualifiers().getQualifierByName("gene_id") != null &&
- feature.getQualifiers().getQualifierByName("transcript_id") != null)
- {
- if(feature.getEntry() != null)
- logger4j.debug(feature.getEntry().getName()+" is in GTF format");
+ if (feature.getQualifiers().getQualifierByName("gene_id") != null
+ && feature.getQualifiers().getQualifierByName("transcript_id") != null) {
+ if (feature.getEntry() != null)
+ logger4j.debug(feature.getEntry().getName() + " is in GTF format");
return true;
}
return false;
diff --git a/uk/ac/sanger/artemis/util/DatabaseDocument.java b/uk/ac/sanger/artemis/util/DatabaseDocument.java
index 6cba75df3449f18a6ac8c27112ac66ae89d5f06d..6addbd4fa2b71679539867aabd4e32301bc0f5a2 100644
--- a/uk/ac/sanger/artemis/util/DatabaseDocument.java
+++ b/uk/ac/sanger/artemis/util/DatabaseDocument.java
@@ -27,11 +27,11 @@ package uk.ac.sanger.artemis.util;
import uk.ac.sanger.artemis.Options;
import uk.ac.sanger.artemis.io.ChadoCanonicalGene;
import uk.ac.sanger.artemis.io.DocumentEntry;
+import uk.ac.sanger.artemis.io.GFF3Encoder;
import uk.ac.sanger.artemis.io.GFFStreamFeature;
import uk.ac.sanger.artemis.io.PartialSequence;
import uk.ac.sanger.artemis.io.Range;
import uk.ac.sanger.artemis.io.ReadFormatException;
-
import uk.ac.sanger.artemis.chado.ArtemisUtils;
import uk.ac.sanger.artemis.chado.ChadoCvTermView;
import uk.ac.sanger.artemis.chado.ChadoTransactionManager;
@@ -1301,7 +1301,7 @@ public class DatabaseDocument extends Document
// ortholog/paralog/cluster data
int orthologueFeature = fr.getFeatureByObjectId().getFeatureId();
clusterOrthoParalog.append(cvTermName+"="+
- GFFStreamFeature.encode("object_id="+orthologueFeature+"; rank="+fr.getRank())+";");
+ GFF3Encoder.encode("object_id="+orthologueFeature+"; rank="+fr.getRank())+";");
}
}
}
@@ -1393,10 +1393,10 @@ public class DatabaseDocument extends Document
if(qualifier_name == null)
continue;
if(featprop.getValue() != null)
- this_buff.append(GFFStreamFeature.encode(qualifier_name)+ "=" +
- GFFStreamFeature.encode(featprop.getValue())+";");
+ this_buff.append(GFF3Encoder.encode(qualifier_name)+ "=" +
+ GFF3Encoder.encode(featprop.getValue())+";");
else
- this_buff.append(GFFStreamFeature.encode(qualifier_name)+";");
+ this_buff.append(GFF3Encoder.encode(qualifier_name)+";");
}
}
@@ -1408,7 +1408,7 @@ public class DatabaseDocument extends Document
if(feat.getDbXRef() != null)
{
this_buff.append("Dbxref=");
- this_buff.append(GFFStreamFeature.encode(
+ this_buff.append(GFF3Encoder.encode(
feat.getDbXRef().getDb().getName()+":"+feat.getDbXRef().getAccession()));
foundPrimaryDbXRef = true;
if(dbxref == null || dbxref.size() == 0)
@@ -1423,7 +1423,7 @@ public class DatabaseDocument extends Document
this_buff.append("Dbxref=");
for(int j=0; j<dbxref.size(); j++)
{
- this_buff.append(GFFStreamFeature.encode(dbxref.get(j)));
+ this_buff.append(GFF3Encoder.encode(dbxref.get(j)));
if(j<dbxref.size()-1)
this_buff.append(",");
}
@@ -1442,7 +1442,7 @@ public class DatabaseDocument extends Document
this_buff.append(alias.getSynonym().getName());
if(!alias.isCurrent())
- this_buff.append(GFFStreamFeature.encode(";current=false"));
+ this_buff.append(GFF3Encoder.encode(";current=false"));
//if(j<v_synonyms.size()-1)
this_buff.append(";");
@@ -1511,9 +1511,9 @@ public class DatabaseDocument extends Document
attr_buff.append("controlled_curation=");
attr_buff.append("term="+
- GFFStreamFeature.encode(feature_cvterm.getCvTerm().getName())+"%3B");
+ GFF3Encoder.encode(feature_cvterm.getCvTerm().getName())+"%3B");
attr_buff.append("cv="+
- GFFStreamFeature.encode(feature_cvterm.getCvTerm().getCv().getName())+"%3B");
+ GFF3Encoder.encode(feature_cvterm.getCvTerm().getCv().getName())+"%3B");
// N.B. the db_xref may be a FeatureCvTermDbXRef or a Pub for /controlled_curation
int nfound_dbxref = 0;
@@ -1584,7 +1584,7 @@ public class DatabaseDocument extends Document
attr_buff.append(getCvtermName(feature_cvtermprop.getCvTerm()
.getCvTermId(), dao, gene_builder));
attr_buff.append("=");
- attr_buff.append(GFFStreamFeature.encode(feature_cvtermprop.getValue()));
+ attr_buff.append(GFF3Encoder.encode(feature_cvtermprop.getValue()));
if(i < feature_cvtermprops.size()-1)
attr_buff.append("%3B");
}
@@ -1657,7 +1657,7 @@ public class DatabaseDocument extends Document
+ dbXRef.getAccession() + "%3B");
attr_buff.append("term="+
- GFFStreamFeature.encode(feature_cvterm.getCvTerm().getName())+"%3B");
+ GFF3Encoder.encode(feature_cvterm.getCvTerm().getName())+"%3B");
// PMID
int nfound_pub = 0;
@@ -1731,7 +1731,7 @@ public class DatabaseDocument extends Document
attr_buff.append(getCvtermName(feature_cvtermprop.getCvTerm()
.getCvTermId(), dao, gene_builder));
attr_buff.append("=");
- attr_buff.append(GFFStreamFeature.encode(feature_cvtermprop.getValue()));
+ attr_buff.append(GFF3Encoder.encode(feature_cvtermprop.getValue()));
if(i < feature_cvtermprops.size()-1)
attr_buff.append("%3B");
}