nomparser.jj

化学图形处理软件

options {
STATIC=false;
OPTIMIZE_TOKEN_MANAGER=true;
FORCE_LA_CHECK=true;
}

PARSER_BEGIN(NomParser)
/*
 *   Copyright (C) 2003-2007  University of Manchester
 *
 *   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 2.1 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; without 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, 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. 
 *   (or see http://www.gnu.org/copyleft/lesser.html)
 */
package org.openscience.cdk.iupac.parser;

import java.io.StringReader;
import org.openscience.cdk.Molecule;
import org.openscience.cdk.exception.*;
import java.util.*;

/**
 * A class partly generated by <a href="http://javacc.dev.java.net" target="_top">JavaCC</a> which breaks down the chemical name
 * into computable subparts and passes these parts to the MoleculeBuilder.
 *
 * @author David Robinson (University of Manchester)
 * @author Bhupinder Sandhu
 * @author Stephen Tomkinson
 *
 * @cdk.keyword IUPAC name
 */
public class NomParser {
    //private variables needed throughout the program
    private static int mainChainPrefix;
    private static boolean isMainCyclic;

    /** The tempory vector of locations the current group/substiuant is attached to */
    private static Vector tempLocation;

    /** The vector of attached functional groups, with an instance of AttachedGroup for each
     * functional group.
     */
    private static Vector attachedGroups;

    /** The vector of attached substituent, with an instance of AttachedGroup for each
     * substituent.
     */
    private static Vector attachedSubstituents;

    /**
     * Used in the build up of ancient greek style prfixes
     */
    private static int currentNumber;

    /**
     * Parses the chemical name and returns the built molecule.
     *
     * @param stringToParse A case-insensitive name of the chemical to build.
     * @return A molecule which represents the interpretatation of the name.
     * @throws ParseException Any error which occur in the parsing get wrapped
     * up in a ParseException and thrown.
     */
    public static Molecule generate (String stringToParse) throws ParseException, CDKException
    {
        isMainCyclic = false;
        tempLocation = new Vector();
        attachedSubstituents = new Vector();
        attachedGroups = new Vector();
        currentNumber = 0;

        StringReader stringReader = new StringReader (stringToParse.toLowerCase() + "\n");
        NomParser parser = new NomParser (stringReader);               
        parser.completeChemicalName();
        
        //Scan substituents for a too high connection point
        checkConnections (attachedSubstituents.iterator());
        
        //Scan functional groups for a too high connection point
        checkConnections (attachedGroups.iterator());

        MoleculeBuilder moleculeBuilder = new MoleculeBuilder();
        Molecule returnedMolecule = moleculeBuilder.buildMolecule(mainChainPrefix, attachedSubstituents, attachedGroups, isMainCyclic, stringToParse);
        
        return returnedMolecule;
    }

    /**
     * Checks to ensure that all groups/substituents attached to the main chain
     * are connected to a valid atom which occurs on the main chain.
     *
     * @param vectorIterator An iterator which provides instances of AttachedGroup to check
     * @throws ParseException A taylored instance of ParseException so nomen can display
     * the error to the user.
     */
    private static void checkConnections (Iterator vectorIterator) throws ParseException
    {
        while (vectorIterator.hasNext())
        {
            AttachedGroup ag = (AttachedGroup) vectorIterator.next();
            Vector locations = ag.getLocations();

            Iterator locationsIterator = locations.iterator();
            while (locationsIterator.hasNext())
            {
                Token tok = (Token) locationsIterator.next();

                try
                {
                    if (Integer.parseInt(tok.image) > mainChainPrefix)
                    {
                        //Create a tiny 2D array with a single slot for data, 
                        //insert 0 into it as as to reference the first slot in the stringArray
                        int [][] intArray = new int [1][1];
                        intArray [0][0] = 0;

                        //Put useful message in stringArray
                        String [] stringArray = new String [1];
                        stringArray [0] = " MUST BE BELOW " + (mainChainPrefix + 1) + " ";

                        tok.next = tok;

                        throw new ParseException (tok, intArray, stringArray);
                    }
                }
                catch (NumberFormatException nfe)
                {
                    //Do nothing, as this should never happen
                }
            }
        }
    }
}

PARSER_END(NomParser)

JAVACODE
/**
 * Stores "head tokens", the substituent prefix, in a vector of AttachedGroup objects.
 */
void AddHeadToken() {
    attachedSubstituents.add (new AttachedGroup (tempLocation, currentNumber) );
    tempLocation = new Vector();
}

JAVACODE
void MakeMainChainIntoSubstituent() {
    attachedSubstituents.add (new AttachedGroup (tempLocation, mainChainPrefix) );
    currentNumber = 0;
    mainChainPrefix = 0;
    tempLocation = new Vector();
}

JAVACODE
/**
 * Stores the functional groups in a vector of AttachedGroup objects.
 */
void AddFunGroup() {
    Token tok;
    tok = getToken(-1);
    attachedGroups.add (new AttachedGroup (tempLocation, tok.image) );
    tempLocation = new Vector();
}

JAVACODE
/**
* Stores the functional group positions, the number of the atom they 
* connect to, in an array.
*/
void AddFunGroupPos() {
    Token tok;
    tok = getToken(-1);
    tempLocation.add(tok);
}

JAVACODE
/**
* Adds to the position array a location of -1 to indicate no location was
* specified.
*/
void AddUnknownFunGroupPos() {
    Token tok = new Token();
    tok.image = "-1";
    tempLocation.add(tok);
}

JAVACODE
/**
 * Store the mainChainPrefix token, the chain prefix of the longest carbon chain
 */
void AddMainChain() {
    mainChainPrefix = currentNumber;
    currentNumber = 0;
}

JAVACODE
/**
 * Sets the main chain to be cyclic.
 */
void SetMainCyclic() {
    isMainCyclic = true;
}

TOKEN :
{
	< EOL: "\n" | "\r" >
}

TOKEN : /*NUMBERS*/
{
    < CONSTANT: ( <DIGIT> )+ >
|   < #DIGIT: ["0" - "9"] >
}

TOKEN : /*NUMBER CONNECTORS*/
{
	< DASH: "-" >
|	< COMMA: "," >
}

/**
 * Initial small numbers.
 */
TOKEN :
{
    < METH: "meth" >
|   < ETH: "eth" >
|   < PROP: "prop" >
|   < BUT: "but" >
}

/**
 * Other special cases.
 */
TOKEN :
{
    < UNDEC: "undec" >
|   < EICOS: "eicos" | "icos" >
|   < HENICOS: "henicos" >
}

/**
 * Usual numbers for base 10 numbering.
 */
TOKEN :
{
    < HEN: "hen" >
|   < DO: "do" >
|   < TRI: "tri" >
|   < TETR: "tetra" >
|   < PENT: "pent" >
|   < HEX: "hex" >
|   < HEPT: "hept" >
|   < OCT: "oct" >
|   < NON: "non" >
}

/**
 * Positional aides which give the magnitude of the the base numbers.
 * Equivalent to "...ty" and "...hundred" in English
 */
TOKEN :
{
    < DEC: "dec" >
|   < COS: "cos" >
|   < CONT: "cont" >
}

/* Skip the "a" letter for greek numbers */
SKIP :
{
    < A : "a" > | < SPACE : " " >
}

TOKEN : /*BOND MODIFIERS*/
{
        < AN: "an" >
    |   < EN: "en" >
    |	< YN: "yn" >
}


TOKEN : /*CONNECTOR*/
{
    	< YL: "yl" >
|	< DI: "di" >
|       < CYCLO: "cyclo" >
}

TOKEN :  /*PREFIXES*/
{
            < CHLORO: "chloro" >
	|	< FLUORO: "fluoro" >
	|	< BROMO: "bromo" >
	|	< IODO: "iodo" >
        |       < NITRO: "nitro" >
        |       < OXO: "oxo" >
        |       < PHENYL: "phenyl" >
        |       < AMINO: "amino" >
        |       < ALUMINO: "alumino" >
        |	< LITHO: "litho" >
        |	< HYDROXY: "hydroxy" >
}		
		
TOKEN :  /*FUNCTIONAL GROUP SUFFIXES*/
{
        	< E: "e">
      |     < OL: "ol" >
	|	< OICACID: "oic acid" >
      |     < OYLCHLORIDE: "oyl chloride" >
      |     < NITRILE: "nitrile" >
	|	< AL: "al" >
	|	< AMIDE: "amide" >
	|	< AMINE: "amine" >
	|	< ONE: "one" >
	|	< OATE: "oate" >
}

TOKEN : /* METALS */
{
	< LITHIUM: "lithium" >
|	< SODIUM: "sodium" >
|	< POTASSIUM: "potassium" >
|	< RUBIDIUM: "rubidium" >
|	< CESIUM: "cesium" >
|	< FRANCIUM: "francium" >
|	< BERYLLIUM: "beryllium" >
|	< MAGNESIUM: "magnesium" >
|	< CALCIUM: "calcium" >
|	< STRONTIUM: "strontium" >
|	< BARIUM: "barium" >
|	< RADIUM: "radium">
|	< SCANDIUM: "scandium" >
|	< YTTRIUM: "yttrium" >
|	< LANTHANUM: "lanthanum" >
| 	< ACTINIUM: "actinium" >
|	< TITANIUM: "titanium" >
|	< ZIRCONIUM: "zirconium" >
|	< HAFNIUM: "hafnium" >
|	< RUTHERFORDIUM: "rutherfordium" >
|	< VANADIUM: "vanadium" >
|	< NIOBIUM: "niobium" >
|	< TANTALUM: "tantalum" >
| 	< DUBNIUM: "dubnium" >
|	< CHROMIUM: "chromium" >
|	< MOLYBDENUM: "molybdenum" >
|	< TUNGSTEN: "tungsten" >
|	< SEABORGIUM: "seaborgium" >
|	< MANGANESE: "manganese" >
|	< TECHNETIUM: "technetium" >
|	< RHENIUM: "rhenium" >
|	< BOHRIUM: "bohrium" >
|	< IRON: "iron" >
|	< RUTHENIUM: "ruthenium" >
|	< OSMIUM: "osmium" >
|	< HASSIUM: "hassium" >
|	< COBALT: "cobalt">
|	< RHODIUM: "rhodium">
|	< IRIDIUM: "iridium" >
|	< MEITMERIUM: "meitmerium" >
|	< NICKEL: "nickel" >
|	< PALLADIUM: "palladium" >
|	< PLATINUM: "platinum" >
|	< COPPER: "copper" >
|	< SILVER: "silver" >
|	< GOLD: "gold" >
|	< ZINC: "zinc" >
|	< CADMIUM: "cadmium" >
|	< MECURY: "mercury" >
|	< ALUMINIUM: "aluminium" >
|	< GALLIUM: "gallium" >
|	< INDIUM: "indium" >
|	< THALLIUM: "thallium" >
|	< GERMAINIUM: "germainium" >
|	< TIN: "tin" >
|	< LEAD: "lead" >
|	< ARSENIC: "arsenic" >
|	< ANTIMONY: "antimony" >
|	< BISMUTH: "bismuth" >
|	< SELENIUM: "selenium" >
|	< TELLURIUM: "tellurium" >
|	< POLONIUM: "polonium" >
|	< CERIUM: "cerium" >
|	< PRASEODYMIUM: "praseodymium" >
|	< NEODYMIUM: "neodymium" >
|	< PROMETHIUM: "promethium" >
|	< SANARIUM: "sanarium" >
|	< EUROPIUM: "europium" >
|	< GADOLINIUM: "gadolinium" >
|	< TERBIUM: "terbium" >
|	< DYSPROSIUM: "dysprosium" >
|	< HOLMIUM: "holmium" >
|	< ERBIUM: "erbium" >
|	< THULIUM: "thulium" >
|	< YTTERBIUM: "ytterbium" >
|	< LUTETIUM: "lutetium" >
|	< THORIUM: "thorium" >
|	< PROTACTINIUM: "protactinium" >
|	< URANIUM: "uranium" >