Merge pull request #246 from cdk/patch/atom-creation

Improved API for atom creation.
cdk · Oct 28, 2016 · ddbc988 · ddbc988
2 parents 3030f4d + f3c112b
commit ddbc988
Show file tree

Hide file tree

Showing 42 changed files with 771 additions and 235 deletions.
diff --git a/base/data/src/main/java/org/openscience/cdk/Atom.java b/base/data/src/main/java/org/openscience/cdk/Atom.java
@@ -22,6 +22,7 @@
  */
 package org.openscience.cdk;
 
+import org.openscience.cdk.config.Elements;
 import org.openscience.cdk.interfaces.IAtom;
 import org.openscience.cdk.interfaces.IElement;
 import org.openscience.cdk.tools.periodictable.PeriodicTable;
@@ -113,15 +114,67 @@ public Atom() {
     }
 
     /**
-     * Constructs an Atom from a String containing an element symbol.
+     * Create a new atom with of the specified element.
      *
-     * @param elementSymbol The String describing the element for the Atom
+     * @param elem atomic number
      */
-    public Atom(String elementSymbol) {
-        this(new Element(elementSymbol, PeriodicTable.getAtomicNumber(elementSymbol)));
-        this.formalCharge = 0;
+    public Atom(int elem) {
+        this(elem, 0, 0);
     }
 
+    /**
+     * Create a new atom with of the specified element and hydrogen count.
+     *
+     * @param elem atomic number
+     * @param hcnt hydrogen count
+     */
+    public Atom(int elem, int hcnt) {
+        this(elem, hcnt, 0);
+    }
+
+    /**
+     * Create a new atom with of the specified element, hydrogen count, and formal charge.
+     *
+     * @param elem atomic number
+     * @param hcnt hydrogen count
+     * @param fchg formal charge
+     */
+    public Atom(int elem, int hcnt, int fchg) {
+        super((String)null);
+        setAtomicNumber(elem);
+        setSymbol(Elements.ofNumber(elem).symbol());
+        setImplicitHydrogenCount(hcnt);
+        setFormalCharge(fchg);
+    }
+
+    /**
+     * Constructs an Atom from a string containing an element symbol and optionally
+     * the atomic mass, hydrogen count, and formal charge. The symbol grammar allows
+     * easy construction from common symbols, for example:
+     *
+     * <pre>
+     *     new Atom("NH+");   // nitrogen cation with one hydrogen
+     *     new Atom("OH");    // hydroxy
+     *     new Atom("O-");    // oxygen anion
+     *     new Atom("13CH3"); // methyl isotope 13
+     * </pre>
+     *
+     * <pre>
+     *     atom := {mass}? {symbol} {hcnt}? {fchg}?
+     *     mass := \d+
+     *     hcnt := 'H' \d+
+     *     fchg := '+' \d+? | '-' \d+?
+     * </pre>
+     *
+     * @param symbol string with the element symbol
+     */
+    public Atom(String symbol) {
+        super((String)null);
+        if (!parseAtomSymbol(this, symbol))
+            throw new IllegalArgumentException("Cannot pass atom symbol: " + symbol);
+    }
+
+
     /**
          * Constructs an Atom from an Element and a Point3d.
          *
@@ -452,4 +505,110 @@ public IAtom clone() throws CloneNotSupportedException {
         return (IAtom) clone;
     }
 
+
+    private static boolean isUpper(char c) {
+        return c >= 'A' && c <= 'Z';
+    }
+
+    private static boolean isLower(char c) {
+        return c >= 'a' && c <= 'z';
+    }
+
+    private static boolean isDigit(char c) {
+        return c >= '0' && c <= '9';
+    }
+
+    private static boolean parseAtomSymbol(IAtom atom, String str) {
+        final int len = str.length();
+        int pos = 0;
+
+        int mass = -1;
+        int anum = 0;
+        int hcnt = 0;
+        int chg = 0;
+
+        // optional mass
+        if (pos < len && isDigit(str.charAt(pos))) {
+            mass = (str.charAt(pos++) - '0');
+            while (pos < len && isDigit(str.charAt(pos)))
+                mass = 10 * mass + (str.charAt(pos++) - '0');
+        } else if ("R".equals(str)) {
+            atom.setAtomicNumber(0);
+            atom.setSymbol("R");
+            return true;
+        } else if ("D".equals(str)) {
+            atom.setAtomicNumber(1);
+            atom.setMassNumber(2);
+            atom.setSymbol("H");
+            return true;
+        } else if ("T".equals(str)) {
+            atom.setAtomicNumber(1);
+            atom.setMassNumber(3);
+            atom.setSymbol("H");
+            return true;
+        }
+
+        // atom symbol
+        if (pos < len && isUpper(str.charAt(pos))) {
+            int beg = pos;
+            pos++;
+            while (pos < len && isLower(str.charAt(pos)))
+                pos++;
+            Elements elem = Elements.ofString(str.substring(beg, pos));
+            if (elem == Elements.Unknown)
+                return false;
+            anum = elem.number();
+
+            // optional fields after atom symbol
+            while (pos < len) {
+                switch (str.charAt(pos)) {
+                    case 'H':
+                        pos++;
+                        if (pos < len && isDigit(str.charAt(pos))) {
+                            while (pos < len && isDigit(str.charAt(pos)))
+                                hcnt = 10 * hcnt + (str.charAt(pos++) - '0');
+                        } else {
+                            hcnt = 1;
+                        }
+                        break;
+                    case '+':
+                        pos++;
+                        if (pos < len && isDigit(str.charAt(pos))) {
+                            chg = (str.charAt(pos++) - '0');
+                            while (pos < len && isDigit(str.charAt(pos)))
+                                chg = 10 * chg + (str.charAt(pos++) - '0');
+                        } else {
+                            chg = +1;
+                        }
+                        break;
+                    case '-':
+                        pos++;
+                        if (pos < len && isDigit(str.charAt(pos))) {
+                            chg = (str.charAt(pos++) - '0');
+                            while (pos < len && isDigit(str.charAt(pos)))
+                                chg = 10 * chg + (str.charAt(pos++) - '0');
+                            chg *= -1;
+                        } else {
+                            chg = -1;
+                        }
+                        break;
+                    default:
+                        return false;
+                }
+            }
+        } else {
+            return false;
+        }
+
+        if (mass < 0)
+            atom.setMassNumber(null);
+        else
+            atom.setMassNumber(mass);
+        atom.setAtomicNumber(anum);
+        atom.setSymbol(Elements.ofNumber(anum).symbol());
+        atom.setImplicitHydrogenCount(hcnt);
+        atom.setFormalCharge(chg);
+
+        return pos == len && len > 0;
+    }
 }
diff --git a/base/data/src/main/java/org/openscience/cdk/protein/data/PDBAtom.java b/base/data/src/main/java/org/openscience/cdk/protein/data/PDBAtom.java
@@ -110,6 +110,7 @@ record = null;
         oxt = false;
         hetAtom = false;
 
+        super.hydrogenCount = null;
         super.charge = Double.valueOf(0.0);
         super.formalCharge = Integer.valueOf(0);
     }

diff --git a/base/data/src/test/java/org/openscience/cdk/AtomTest.java b/base/data/src/test/java/org/openscience/cdk/AtomTest.java
@@ -77,6 +77,92 @@ public void testAtom_String() {
         Assert.assertNull(a.getFractionalPoint3d());
     }
 
+    @Test
+    public void testAtom_NH4plus_direct() {
+        IAtom a = new Atom(7, 4, +1);
+        Assert.assertEquals("N", a.getSymbol());
+        Assert.assertEquals((Integer) 7, a.getAtomicNumber());
+        Assert.assertEquals((Integer) 4, a.getImplicitHydrogenCount());
+        Assert.assertEquals((Integer) 1, a.getFormalCharge());
+        Assert.assertNull(a.getPoint2d());
+        Assert.assertNull(a.getPoint3d());
+        Assert.assertNull(a.getFractionalPoint3d());
+    }
+
+    @Test
+    public void testAtom_CH3_direct() {
+        IAtom a = new Atom(6, 3);
+        Assert.assertEquals("C", a.getSymbol());
+        Assert.assertEquals((Integer) 6, a.getAtomicNumber());
+        Assert.assertEquals((Integer) 3, a.getImplicitHydrogenCount());
+        Assert.assertEquals((Integer) 0, a.getFormalCharge());
+        Assert.assertNull(a.getPoint2d());
+        Assert.assertNull(a.getPoint3d());
+        Assert.assertNull(a.getFractionalPoint3d());
+    }
+
+    @Test
+    public void testAtom_Cl_direct() {
+        IAtom a = new Atom(17);
+        Assert.assertEquals("Cl", a.getSymbol());
+        Assert.assertEquals((Integer) 17, a.getAtomicNumber());
+        Assert.assertEquals((Integer) 0, a.getImplicitHydrogenCount());
+        Assert.assertEquals((Integer) 0, a.getFormalCharge());
+        Assert.assertNull(a.getPoint2d());
+        Assert.assertNull(a.getPoint3d());
+        Assert.assertNull(a.getFractionalPoint3d());
+    }
+
+    @Test
+    public void testAtom_NH4plus() {
+        IAtom a = new Atom("NH4+");
+        Assert.assertEquals("N", a.getSymbol());
+        Assert.assertEquals((Integer) 7, a.getAtomicNumber());
+        Assert.assertEquals((Integer) 4, a.getImplicitHydrogenCount());
+        Assert.assertEquals((Integer) 1, a.getFormalCharge());
+        Assert.assertNull(a.getPoint2d());
+        Assert.assertNull(a.getPoint3d());
+        Assert.assertNull(a.getFractionalPoint3d());
+    }
+
+    @Test
+    public void testAtom_Ominus() {
+        IAtom a = new Atom("O-");
+        Assert.assertEquals("O", a.getSymbol());
+        Assert.assertEquals((Integer) 8, a.getAtomicNumber());
+        Assert.assertEquals((Integer) 0, a.getImplicitHydrogenCount());
+        Assert.assertEquals(Integer.valueOf(-1), a.getFormalCharge());
+        Assert.assertNull(a.getPoint2d());
+        Assert.assertNull(a.getPoint3d());
+        Assert.assertNull(a.getFractionalPoint3d());
+    }
+
+    @Test
+    public void testAtom_Ca2plus() {
+        IAtom a = new Atom("Ca+2");
+        Assert.assertEquals("Ca", a.getSymbol());
+        Assert.assertEquals((Integer) 20, a.getAtomicNumber());
+        Assert.assertEquals((Integer) 0, a.getImplicitHydrogenCount());
+        Assert.assertEquals(Integer.valueOf(+2), a.getFormalCharge());
+        Assert.assertNull(a.getPoint2d());
+        Assert.assertNull(a.getPoint3d());
+        Assert.assertNull(a.getFractionalPoint3d());
+    }
+
+    @Test
+    public void testAtom_13CH3() {
+        IAtom a = new Atom("13CH3");
+        Assert.assertEquals("C", a.getSymbol());
+        Assert.assertEquals((Integer) 13, a.getMassNumber());
+        Assert.assertEquals((Integer) 6, a.getAtomicNumber());
+        Assert.assertEquals((Integer) 3, a.getImplicitHydrogenCount());
+        Assert.assertEquals((Integer) 0, a.getFormalCharge());
+        Assert.assertNull(a.getPoint2d());
+        Assert.assertNull(a.getPoint3d());
+        Assert.assertNull(a.getFractionalPoint3d());
+    }
+
+
     /**
      * Method to test the Atom(String symbol, javax.vecmath.Point3d point3D) method.
      */

diff --git a/base/data/src/test/java/org/openscience/cdk/BioPolymerTest.java b/base/data/src/test/java/org/openscience/cdk/BioPolymerTest.java
@@ -66,11 +66,11 @@ public void testBioPolymer() {
         oMono2.setMonomerName(new String("HOH"));
         IMonomer oMono3 = oBioPolymer.getBuilder().newInstance(IMonomer.class);
         oMono3.setMonomerName(new String("GLYA16"));
-        IAtom oAtom1 = oBioPolymer.getBuilder().newInstance(IAtom.class, "C1");
-        IAtom oAtom2 = oBioPolymer.getBuilder().newInstance(IAtom.class, "C2");
-        IAtom oAtom3 = oBioPolymer.getBuilder().newInstance(IAtom.class, "C3");
-        IAtom oAtom4 = oBioPolymer.getBuilder().newInstance(IAtom.class, "C4");
-        IAtom oAtom5 = oBioPolymer.getBuilder().newInstance(IAtom.class, "C5");
+        IAtom oAtom1 = oBioPolymer.getBuilder().newInstance(IAtom.class, "C");
+        IAtom oAtom2 = oBioPolymer.getBuilder().newInstance(IAtom.class, "C");
+        IAtom oAtom3 = oBioPolymer.getBuilder().newInstance(IAtom.class, "C");
+        IAtom oAtom4 = oBioPolymer.getBuilder().newInstance(IAtom.class, "C");
+        IAtom oAtom5 = oBioPolymer.getBuilder().newInstance(IAtom.class, "C");
 
         oBioPolymer.addAtom(oAtom1);
         oBioPolymer.addAtom(oAtom2, oStrand1);

diff --git a/base/data/src/test/java/org/openscience/cdk/StrandTest.java b/base/data/src/test/java/org/openscience/cdk/StrandTest.java
@@ -64,11 +64,11 @@ public void testStrand() {
         oMono2.setMonomerName(new String("HOH"));
         IMonomer oMono3 = oStrand.getBuilder().newInstance(IMonomer.class);
         oMono3.setMonomerName(new String("GLYA16"));
-        IAtom oAtom1 = oStrand.getBuilder().newInstance(IAtom.class, "C1");
-        IAtom oAtom2 = oStrand.getBuilder().newInstance(IAtom.class, "C2");
-        IAtom oAtom3 = oStrand.getBuilder().newInstance(IAtom.class, "C3");
-        IAtom oAtom4 = oStrand.getBuilder().newInstance(IAtom.class, "C4");
-        IAtom oAtom5 = oStrand.getBuilder().newInstance(IAtom.class, "C5");
+        IAtom oAtom1 = oStrand.getBuilder().newInstance(IAtom.class, "C");
+        IAtom oAtom2 = oStrand.getBuilder().newInstance(IAtom.class, "C");
+        IAtom oAtom3 = oStrand.getBuilder().newInstance(IAtom.class, "C");
+        IAtom oAtom4 = oStrand.getBuilder().newInstance(IAtom.class, "C");
+        IAtom oAtom5 = oStrand.getBuilder().newInstance(IAtom.class, "C");
 
         oStrand.addAtom(oAtom1);
         oStrand.addAtom(oAtom2);

diff --git a/base/data/src/test/java/org/openscience/cdk/protein/data/PDBPolymerTest.java b/base/data/src/test/java/org/openscience/cdk/protein/data/PDBPolymerTest.java
@@ -68,11 +68,11 @@ public void testPDBPolymer() {
         oMono2.setMonomerName(new String("HOH"));
         IMonomer oMono3 = pdbPolymer.getBuilder().newInstance(IMonomer.class);
         oMono3.setMonomerName(new String("GLYA16"));
-        IPDBAtom oPDBAtom1 = pdbPolymer.getBuilder().newInstance(IPDBAtom.class, "C1");
-        IPDBAtom oPDBAtom2 = pdbPolymer.getBuilder().newInstance(IPDBAtom.class, "C2");
-        IPDBAtom oPDBAtom3 = pdbPolymer.getBuilder().newInstance(IPDBAtom.class, "C3");
-        IPDBAtom oPDBAtom4 = pdbPolymer.getBuilder().newInstance(IPDBAtom.class, "C4");
-        IPDBAtom oPDBAtom5 = pdbPolymer.getBuilder().newInstance(IPDBAtom.class, "C5");
+        IPDBAtom oPDBAtom1 = pdbPolymer.getBuilder().newInstance(IPDBAtom.class, "C");
+        IPDBAtom oPDBAtom2 = pdbPolymer.getBuilder().newInstance(IPDBAtom.class, "C");
+        IPDBAtom oPDBAtom3 = pdbPolymer.getBuilder().newInstance(IPDBAtom.class, "C");
+        IPDBAtom oPDBAtom4 = pdbPolymer.getBuilder().newInstance(IPDBAtom.class, "C");
+        IPDBAtom oPDBAtom5 = pdbPolymer.getBuilder().newInstance(IPDBAtom.class, "C");
 
         pdbPolymer.addAtom(oPDBAtom1);
         pdbPolymer.addAtom(oPDBAtom2, oStrand1);
@@ -117,8 +117,8 @@ public void testGetMonomerNamesInSequentialOrder() {
         oMono1.setMonomerName("TRP279");
         IMonomer oMono2 = pdbPolymer.getBuilder().newInstance(IMonomer.class);
         oMono2.setMonomerName("CYS280");
-        IPDBAtom oPDBAtom2 = pdbPolymer.getBuilder().newInstance(IPDBAtom.class, "C2");
-        IPDBAtom oPDBAtom3 = pdbPolymer.getBuilder().newInstance(IPDBAtom.class, "C3");
+        IPDBAtom oPDBAtom2 = pdbPolymer.getBuilder().newInstance(IPDBAtom.class, "C");
+        IPDBAtom oPDBAtom3 = pdbPolymer.getBuilder().newInstance(IPDBAtom.class, "C");
         pdbPolymer.addAtom(oPDBAtom2, oMono1, oStrand1);
         pdbPolymer.addAtom(oPDBAtom3, oMono2, oStrand1);
         Assert.assertNotNull(pdbPolymer.getAtom(0));

diff --git a/base/data/src/test/java/org/openscience/cdk/templates/TestMoleculeFactory.java b/base/data/src/test/java/org/openscience/cdk/templates/TestMoleculeFactory.java
@@ -1870,6 +1870,8 @@ public static IAtomContainer makeGappedCyclophaneLike() {
 
     private static void configureAtoms(IAtomContainer mol) {
         try {
+            for (IAtom atom : mol.atoms())
+                atom.setImplicitHydrogenCount(null);
             Isotopes.getInstance().configureAtoms(mol);
         } catch (Exception exc) {
             logger.error("Could not configure molecule!");

diff --git a/base/datadebug/src/main/java/org/openscience/cdk/debug/DebugAtom.java b/base/datadebug/src/main/java/org/openscience/cdk/debug/DebugAtom.java
@@ -45,7 +45,7 @@ public class DebugAtom extends Atom implements IAtom {
 
     private static final long serialVersionUID = 188945429187084868L;
 
-    ILoggingTool              logger           = LoggingToolFactory.createLoggingTool(DebugAtom.class);
+    private static final ILoggingTool logger = LoggingToolFactory.createLoggingTool(DebugAtom.class);
 
     public DebugAtom() {
         super();

diff --git a/base/datadebug/src/main/java/org/openscience/cdk/debug/DebugFragmentAtom.java b/base/datadebug/src/main/java/org/openscience/cdk/debug/DebugFragmentAtom.java
@@ -51,7 +51,7 @@ public class DebugFragmentAtom extends FragmentAtom {
 
     private static final long serialVersionUID = 0L;
 
-    ILoggingTool              logger           = LoggingToolFactory.createLoggingTool(DebugFragmentAtom.class);
+    private static final ILoggingTool              logger           = LoggingToolFactory.createLoggingTool(DebugFragmentAtom.class);
 
     public DebugFragmentAtom() {
         super();

diff --git a/base/datadebug/src/main/java/org/openscience/cdk/debug/DebugPDBAtom.java b/base/datadebug/src/main/java/org/openscience/cdk/debug/DebugPDBAtom.java
@@ -37,7 +37,7 @@ public class DebugPDBAtom extends PDBAtom implements IPDBAtom {
 
     private static final long serialVersionUID = -2432127382224382452L;
 
-    ILoggingTool              logger           = LoggingToolFactory.createLoggingTool(DebugPDBAtom.class);
+    private static final ILoggingTool              logger           = LoggingToolFactory.createLoggingTool(DebugPDBAtom.class);
 
     public DebugPDBAtom(IElement element) {
         super(element);

diff --git a/base/datadebug/src/main/java/org/openscience/cdk/debug/DebugPseudoAtom.java b/base/datadebug/src/main/java/org/openscience/cdk/debug/DebugPseudoAtom.java
@@ -45,7 +45,7 @@ public class DebugPseudoAtom extends PseudoAtom implements IPseudoAtom {
 
     private static final long serialVersionUID = -5935090219383862070L;
 
-    ILoggingTool              logger           = LoggingToolFactory.createLoggingTool(DebugPseudoAtom.class);
+    private static final ILoggingTool              logger           = LoggingToolFactory.createLoggingTool(DebugPseudoAtom.class);
 
     public DebugPseudoAtom() {
         super();