Prevent loss of isotopes in Molfiles.

cdk · Apr 25, 2018 · 5d2b717 · 5d2b717
1 parent 9980412
commit 5d2b717
Show file tree

Hide file tree

Showing 2 changed files with 52 additions and 9 deletions.
diff --git a/storage/ctab/src/main/java/org/openscience/cdk/io/MDLV2000Writer.java b/storage/ctab/src/main/java/org/openscience/cdk/io/MDLV2000Writer.java
@@ -34,6 +34,7 @@
 import org.openscience.cdk.interfaces.IChemModel;
 import org.openscience.cdk.interfaces.IChemObject;
 import org.openscience.cdk.interfaces.IChemSequence;
+import org.openscience.cdk.interfaces.IIsotope;
 import org.openscience.cdk.interfaces.IPseudoAtom;
 import org.openscience.cdk.interfaces.IStereoElement;
 import org.openscience.cdk.interfaces.ITetrahedralChirality;
@@ -180,6 +181,8 @@ public static SPIN_MULTIPLICITY ofValue(int value) throws CDKException {
 
     private BooleanIOSetting forceWriteAs2DCoords;
 
+    private BooleanIOSetting ignoreMajorIsotopes;
+
     // The next two options are MDL Query format options, not really
     // belonging to the MDLV2000 format, and will be removed when
     // a MDLV2000QueryWriter is written.
@@ -495,7 +498,6 @@ public void writeMolecule(IAtomContainer container) throws Exception {
                         }
                     }
                 }
-
                 line += String.format(" 0  0  %d  0  0", parity);
             }
 
@@ -761,15 +763,15 @@ else if (valence > 0 && valence < 15)
             IAtom atom = container.getAtom(i);
             if (!(atom instanceof IPseudoAtom)) {
                 Integer atomicMass = atom.getMassNumber();
+                if (ignoreMajorIsotopes.isSet() &&
+                    isMajorIsotope(atom))
+                    atomicMass = null;
                 if (atomicMass != null) {
-                    int majorMass = Isotopes.getInstance().getMajorIsotope(atom.getSymbol()).getMassNumber();
-                    if (atomicMass != majorMass) {
-                        writer.write("M  ISO  1 ");
-                        writer.write(formatMDLInt(i + 1, 3));
-                        writer.write(" ");
-                        writer.write(formatMDLInt(atomicMass, 3));
-                        writer.write('\n');
-                    }
+                    writer.write("M  ISO  1 ");
+                    writer.write(formatMDLInt(i + 1, 3));
+                    writer.write(" ");
+                    writer.write(formatMDLInt(atomicMass, 3));
+                    writer.write('\n');
                 }
             }
         }
@@ -828,6 +830,13 @@ else if (valence > 0 && valence < 15)
         writer.flush();
     }
 
+    private boolean isMajorIsotope(IAtom atom) throws IOException {
+        if (atom.getMassNumber() == null)
+            return false;
+        IIsotope major = Isotopes.getInstance().getMajorIsotope(atom.getSymbol());
+        return major != null && major.getMassNumber().equals(atom.getMassNumber());
+    }
+
     private void writeSgroups(IAtomContainer container, BufferedWriter writer, Map<IAtom,Integer> atomidxs) throws IOException {
         List<Sgroup> sgroups = container.getProperty(CDKConstants.CTAB_SGROUPS);
         if (sgroups == null)
@@ -1101,6 +1110,8 @@ protected static String formatMDLString(String s, int le) {
     private void initIOSettings() {
         forceWriteAs2DCoords = addSetting(new BooleanIOSetting("ForceWriteAs2DCoordinates", IOSetting.Importance.LOW,
                                                                "Should coordinates always be written as 2D?", "false"));
+        ignoreMajorIsotopes = addSetting(new BooleanIOSetting("IgnoreMajorIsotopes", IOSetting.Importance.LOW,
+                                                               "Do not write atomic mass of major isotopes (e.g. [12]C)", "false"));
         writeAromaticBondTypes = addSetting(new BooleanIOSetting("WriteAromaticBondTypes", IOSetting.Importance.LOW,
                                                                  "Should aromatic bonds be written as bond type 4?", "false"));
         writeQueryFormatValencies = addSetting(new BooleanIOSetting("WriteQueryFormatValencies",

diff --git a/storage/ctab/src/test/java/org/openscience/cdk/io/MDLV2000WriterTest.java b/storage/ctab/src/test/java/org/openscience/cdk/io/MDLV2000WriterTest.java
@@ -62,6 +62,7 @@
 
 import static org.hamcrest.CoreMatchers.containsString;
 import static org.hamcrest.CoreMatchers.is;
+import static org.hamcrest.CoreMatchers.not;
 import static org.junit.Assert.assertThat;
 import static org.openscience.cdk.CDKConstants.ISAROMATIC;
 
@@ -881,4 +882,35 @@ public void writeMoreThan8Radicals() throws Exception {
         assertThat(sw.toString(),
                    containsString("M  RAD  8   9   2  10   2  11   2  12   2  13   2  14   2  15   2  16   2"));
     }
+
+    @Test
+    public void writeCarbon12() throws Exception {
+        IAtomContainer mol = builder.newAtomContainer();
+        IAtom atom = builder.newAtom();
+        atom.setSymbol("C");
+        atom.setMassNumber(12);
+        mol.addAtom(atom);
+        StringWriter sw = new StringWriter();
+        try (MDLV2000Writer mdlw = new MDLV2000Writer(sw)) {
+            mdlw.write(mol);
+        }
+        assertThat(sw.toString(),
+                   containsString("M  ISO  1   1  12"));
+    }
+
+    @Test
+    public void ignoreCarbon12() throws Exception {
+        IAtomContainer mol = builder.newAtomContainer();
+        IAtom atom = builder.newAtom();
+        atom.setSymbol("C");
+        atom.setMassNumber(12);
+        mol.addAtom(atom);
+        StringWriter sw = new StringWriter();
+        try (MDLV2000Writer mdlw = new MDLV2000Writer(sw)) {
+            mdlw.getSetting("IgnoreMajorIsotopes").setSetting("true");
+            mdlw.write(mol);
+        }
+        assertThat(sw.toString(),
+                   not(containsString("M  ISO  1   1  12")));
+    }
 }