Trim newlines from descriptions and attribute values.

Author: heuermh

src/main/java/org/biojava/nbio/adam/convert/ConvertUtils.java

@@ -0,0 +1,47 @@
+/*
+
+    biojava-adam  Biojava and ADAM integration.
+    Copyright (c) 2017-2019 held jointly by the individual authors.
+
+    This library is free software; you can redistribute it and/or modify it
+    under the terms of the GNU Lesser General Public License as published
+    by the Free Software Foundation; either version 3 of the License, or (at
+    your option) any later version.
+
+    This library is distributed in the hope that it will be useful, but WITHOUT
+    ANY WARRANTY; with out even the implied warranty of MERCHANTABILITY or
+    FITNESS FOR A PARTICULAR PURPOSE.  See the GNU Lesser General Public
+    License for more details.
+
+    You should have received a copy of the GNU Lesser General Public License
+    along with this library;  if not, write to the Free Software Foundation,
+    Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307  USA.
+
+    > http://www.fsf.org/licensing/licenses/lgpl.html
+    > http://www.opensource.org/licenses/lgpl-license.php
+
+*/
+package org.biojava.nbio.adam.convert;
+
+/**
+ * Utility methods for the convert package.
+ *
+ * @author  Michael Heuer
+ */
+final class ConvertUtils {
+
+    /**
+     * Return the specified value with newlines removed and whitespace
+     * trimmed from the beginning and end.
+     *
+     * @param value value to trim
+     * @return the specified value with newlines removed and whitespace
+     *    trimmed from the beginning and end
+     */
+    static String trimNewlines(final String value) {
+        if (value == null) {
+            return value;
+        }
+        return value.replaceAll("\\R+", " ").trim();
+    }
+}

src/main/java/org/biojava/nbio/adam/convert/DnaSequenceToFeatures.java

@@ -23,6 +23,8 @@
 */
 package org.biojava.nbio.adam.convert;
 
+import static org.biojava.nbio.adam.convert.ConvertUtils.trimNewlines;
+
 import java.util.ArrayList;
 import java.util.HashMap;
 import java.util.Iterator;
@@ -130,10 +132,10 @@ public List<Feature> convert(final DNASequence dnaSequence,
             }
 
             if (feature.getShortDescription() != null) {
-                fb.setName(feature.getShortDescription());
+                fb.setName(trimNewlines(feature.getShortDescription()));
             }
             else if (feature.getDescription() != null) {
-                fb.setName(feature.getDescription());
+                fb.setName(trimNewlines(feature.getDescription()));
             }
             else {
                 fb.clearName();
@@ -146,7 +148,7 @@ else if (feature.getDescription() != null) {
                 List<Qualifier> value = entry.getValue();
                 StringBuilder sb = new StringBuilder();
                 for (Iterator<Qualifier> i = value.iterator(); i.hasNext(); ) {
-                    sb.append(i.next().getValue());
+                    sb.append(trimNewlines(i.next().getValue()));
                     if (i.hasNext()) {
                         sb.append(",");
                     }

src/main/java/org/biojava/nbio/adam/convert/DnaSequenceToSequence.java

@@ -23,6 +23,8 @@
 */
 package org.biojava.nbio.adam.convert;
 
+import static org.biojava.nbio.adam.convert.ConvertUtils.trimNewlines;
+
 import javax.annotation.concurrent.Immutable;
 
 import org.bdgenomics.convert.AbstractConverter;
@@ -64,7 +66,7 @@ public Sequence convert(final DNASequence dnaSequence,
 
         Sequence.Builder sb = Sequence.newBuilder()
             .setName(dnaSequence.getAccession().toString())
-            .setDescription(dnaSequence.getDescription())
+            .setDescription(trimNewlines(dnaSequence.getDescription()))
             .setAlphabet(Alphabet.DNA)
             .setSequence(dnaSequence.getSequenceAsString().toUpperCase())
             .setLength((long) dnaSequence.getLength());

src/main/java/org/biojava/nbio/adam/convert/ProteinSequenceToFeatures.java

@@ -23,6 +23,8 @@
 */
 package org.biojava.nbio.adam.convert;
 
+import static org.biojava.nbio.adam.convert.ConvertUtils.trimNewlines;
+
 import java.util.ArrayList;
 import java.util.HashMap;
 import java.util.Iterator;
@@ -130,10 +132,10 @@ public List<Feature> convert(final ProteinSequence proteinSequence,
             }
 
             if (feature.getShortDescription() != null) {
-                fb.setName(feature.getShortDescription());
+                fb.setName(trimNewlines(feature.getShortDescription()));
             }
             else if (feature.getDescription() != null) {
-                fb.setName(feature.getDescription());
+                fb.setName(trimNewlines(feature.getDescription()));
             }
             else {
                 fb.clearName();
@@ -146,7 +148,7 @@ else if (feature.getDescription() != null) {
                 List<Qualifier> value = entry.getValue();
                 StringBuilder sb = new StringBuilder();
                 for (Iterator<Qualifier> i = value.iterator(); i.hasNext(); ) {
-                    sb.append(i.next().getValue());
+                    sb.append(trimNewlines(i.next().getValue()));
                     if (i.hasNext()) {
                         sb.append(",");
                     }

src/main/java/org/biojava/nbio/adam/convert/ProteinSequenceToSequence.java

@@ -23,6 +23,8 @@
 */
 package org.biojava.nbio.adam.convert;
 
+import static org.biojava.nbio.adam.convert.ConvertUtils.trimNewlines;
+
 import javax.annotation.concurrent.Immutable;
 
 import org.bdgenomics.convert.AbstractConverter;
@@ -64,7 +66,7 @@ public Sequence convert(final ProteinSequence proteinSequence,
 
         Sequence.Builder sb = Sequence.newBuilder()
             .setName(proteinSequence.getAccession().toString())
-            .setDescription(proteinSequence.getDescription())
+            .setDescription(trimNewlines(proteinSequence.getDescription()))
             .setAlphabet(Alphabet.PROTEIN)
             .setSequence(proteinSequence.getSequenceAsString().toUpperCase())
             .setLength((long) proteinSequence.getLength());

src/main/java/org/biojava/nbio/adam/convert/RnaSequenceToFeatures.java

@@ -23,6 +23,8 @@
 */
 package org.biojava.nbio.adam.convert;
 
+import static org.biojava.nbio.adam.convert.ConvertUtils.trimNewlines;
+
 import java.util.ArrayList;
 import java.util.HashMap;
 import java.util.Iterator;
@@ -130,10 +132,10 @@ public List<Feature> convert(final RNASequence rnaSequence,
             }
 
             if (feature.getShortDescription() != null) {
-                fb.setName(feature.getShortDescription());
+                fb.setName(trimNewlines(feature.getShortDescription()));
             }
             else if (feature.getDescription() != null) {
-                fb.setName(feature.getDescription());
+                fb.setName(trimNewlines(feature.getDescription()));
             }
             else {
                 fb.clearName();
@@ -146,7 +148,7 @@ else if (feature.getDescription() != null) {
                 List<Qualifier> value = entry.getValue();
                 StringBuilder sb = new StringBuilder();
                 for (Iterator<Qualifier> i = value.iterator(); i.hasNext(); ) {
-                    sb.append(i.next().getValue());
+                    sb.append(trimNewlines(i.next().getValue()));
                     if (i.hasNext()) {
                         sb.append(",");
                     }

src/main/java/org/biojava/nbio/adam/convert/RnaSequenceToSequence.java

@@ -23,6 +23,8 @@
 */
 package org.biojava.nbio.adam.convert;
 
+import static org.biojava.nbio.adam.convert.ConvertUtils.trimNewlines;
+
 import javax.annotation.concurrent.Immutable;
 
 import org.bdgenomics.convert.AbstractConverter;
@@ -64,7 +66,7 @@ public Sequence convert(final RNASequence rnaSequence,
 
         Sequence.Builder sb = Sequence.newBuilder()
             .setName(rnaSequence.getAccession().toString())
-            .setDescription(rnaSequence.getDescription())
+            .setDescription(trimNewlines(rnaSequence.getDescription()))
             .setAlphabet(Alphabet.RNA)
             .setSequence(rnaSequence.getSequenceAsString().toUpperCase())
             .setLength((long) rnaSequence.getLength());