nomparser.jj

化学图形处理软件

|	< NEPTUNIUM: "neptunium" >
|	< PLUTONIUM: "plutonium" >
|	< AMERCIUM: "amercium" >
|	< CURIUM: "curium" >
|	< BERKELIUM: "berkelium" >
|	< CALIFORNIUM: "californium" >
|	< EINSTEINIUM: "einsteinium" >
|	< FERMIUM: "fermium" >
|	< MENDELEVIUM: "mendelevium" >
|	< NOBELIUM: "nobelium" >
|	< LAWRENCIUM: "lawrencium" >
}

/**
 * The general form all chemical names must follow.
 */
void completeChemicalName() :
{}
{
    LOOKAHEAD (2) ( mainChainConstruct() ) | ( prefixConstruct() mainChainConstruct() ) <EOL>
    
}

/**
 * Allows 1 or more prefixes
 */
void prefixConstruct() :
{}
{
    //Dash not needed in the first case
    prefixType() (<DASH> prefixType())*
}

void prefixType() :
{}
{
    ( attachLocationSpecified()
    | AddUnknownFunGroupPos() ) 

    ( subChain() 
    | functionalGroupPrefix() )
}

/** The substituent part of the prefix */
void subChain() :
{}
{
    //Only allow *specified location* substituents delt with in prefixType()
    chainPrefix() AddHeadToken() <YL>
}

/** 
 * An attach position has been specified using a 
 * comma seperated list followed by a dash
 */
void attachLocationSpecified() :
{}
{
    //Must be at least one constant, so add that to begin with.

    <CONSTANT> AddFunGroupPos()

    (   oneAttachLocation()
    |   twoOrThreeAttachLocations() )
}

/**
 * Only one attach location specified, should be followed by a dash.
 */
void oneAttachLocation() :
{}
{
	 <DASH>
}

/**
 * Two or three attach locations specidied, handle the second and if needed, the third one here.
 */
void twoOrThreeAttachLocations() :
{}
{
	<COMMA> <CONSTANT> AddFunGroupPos() 
        ( (<DASH> <DI>) | (<COMMA> <CONSTANT> AddFunGroupPos() <DASH> <TRI>) )
}

/**
 * A list of known tokens denoting a chain's length.
 */
void chainPrefix() :
{}
{
    specialCase() | allBaseNumbers() [tensWithUnits() | tensNoUnits()]
}

/** Deal with special cases where the rules don't apply. */
void specialCase() :
{}
{
    < METH > {currentNumber = 1;}
|   < ETH > {currentNumber = 2;}
|   < PROP > {currentNumber = 3;}
|   < BUT > {currentNumber = 4;}
|   < DEC > {currentNumber = 10;}
|   < UNDEC > {currentNumber = 11;}
|   < EICOS > {currentNumber = 20;}
|   < HENICOS > {currentNumber = 21;}
}

/** The usual numbers .*/
void allBaseNumbers() :
{}
{
    < HEN > {currentNumber = 1;}
|   < DO > {currentNumber = 2;}
|   < TRI > {currentNumber = 3;}
|   < TETR > {currentNumber = 4;}
|   < PENT > {currentNumber = 5;}
|   < HEX > {currentNumber = 6;}
|   < HEPT > {currentNumber = 7;}
|   < OCT > {currentNumber = 8;}
|   < NON > {currentNumber = 9;}
}

/** Deal with fragments refering to the positioning of the base numbers (denoting their magnitude) */
void tensNoUnits() :
{}
{
    <DEC> { currentNumber += 10; }
|   <COS> { currentNumber += 20; }
|   <CONT> { currentNumber *= 10; }
}

/** 
 * Deals with numbers above 30 where the base numbers set appear twice.
 * For example, in the tens and the units. */
void tensWithUnits() :
{
    int tempBackup;
}
{
    { tempBackup = currentNumber; }
    allBaseNumbers() <CONT>
    { currentNumber *= 10; currentNumber += tempBackup; }
}

/** The functional group part of the prefix */
void functionalGroupPrefix() :
{}
{
    prefixFunctionalGroups()
    AddFunGroup()
}

/**
 * Main chains are compulsary and consist of an optional "cyclo", a length prefix and
 * a posfix denoting functional groups.
 */
void mainChainConstruct() :
{}
{
    [cycle()] mainChainPrefix()( 
    
    <YL>  AddUnknownFunGroupPos() MakeMainChainIntoSubstituent() ( prioritySubstituents()
        | mainChainPrefix() <AN> prioritySubstituentsFunGroups() ) AddUnknownFunGroupPos() AddFunGroup()
    | bondType() mainChainSuffix() )

}

/**
 * Deals with cyclic main chains.
 */
void cycle() :
{}
{
    <CYCLO> SetMainCyclic()
}

/**
 * Deal with the main chain's length.
 */
void mainChainPrefix() :
{}
{
    chainPrefix() AddMainChain()
}


/**
 * Tokens which affect the bond order of the first bond. 
 */
void bondType() :
{}
{
    ( <AN> AddUnknownFunGroupPos()
      | ( <DASH> attachLocationSpecified() | AddUnknownFunGroupPos() ) 
        ( <EN> | <YN> ) )
    AddFunGroup()
}

/**
 * Figure out the functional group by the main chain's suffix.
 */
void mainChainSuffix() :
{}
{
      endFunctionalGroups() | connectingFunctionalGroupsConstruct()
}

/**
 * Functional groups which occur at the end of the main chain and need 
 * a connecting "an". 
 */
void endFunctionalGroups() :
{}
{
(   <E>[<NITRILE>]
|   <AMIDE>
|   <AMINE>
|   <OATE>
|   <ONE>
|   <OICACID>
|   <OYLCHLORIDE>
|   <AL> ) AddUnknownFunGroupPos() AddFunGroup()
}

/**
 * The layout of a functional group(s) which can connect anywhere.
 * No number specified, or a number list specified.
 */
void connectingFunctionalGroupsConstruct() :
{}
{
    (  connectingFunctionalGroupSuffix() AddUnknownFunGroupPos()
    | <DASH> attachLocationSpecified() connectingFunctionalGroupSuffix() )
 
    AddFunGroup()
}

/**
 * Functional groups suffixs for groups which can be connected anywhere 
 * along the main chain.
 */
void connectingFunctionalGroupSuffix() :
{}
{
    <OL>
}

void prefixFunctionalGroups() :
{}
{
	<CHLORO>
|	<BROMO>
|	<IODO>
|	<FLUORO>
|       <NITRO>
|       <OXO>
|       <PHENYL>
|       <AMINO>
|       <HYDROXY>
}

/**
 * Things which have sub chains branching off them and the molecule does have a main chain.
 */
void prioritySubstituentsFunGroups() :
{}
{
    <AMINE>
|   <AMIDE>
|   <OATE>
|   <ONE>
}

/**
 * Things which have sub chains branching off them but the molecule has no main chain.
 */
void prioritySubstituents () :
{}
{
		 groupOneMetals()
|		 groupTwoMetals()
|		 dBlockMetals()
|		 pBlockMetals()
|		 fBlockMetals()

}

void groupOneMetals() :
{}
{
	
	<LITHIUM>
|	<SODIUM>
|	<POTASSIUM>
|	<RUBIDIUM>
|	<CESIUM>
|	<FRANCIUM>

}

void groupTwoMetals() :
{}
{
	<BERYLLIUM>
|	<MAGNESIUM>
|	<CALCIUM>
|	<STRONTIUM>
|	<BARIUM>
|	<RADIUM>
}

void dBlockMetals() :
{}
{
	<SCANDIUM>
|	<YTTRIUM>
|	<LANTHANUM>
| 	<ACTINIUM>
|	<TITANIUM>
|	<ZIRCONIUM>
|	<HAFNIUM>
|	<RUTHERFORDIUM>
|	<VANADIUM>
|	<NIOBIUM>
|	<TANTALUM>
| 	<DUBNIUM>
|	<CHROMIUM>
|	<MOLYBDENUM>
|	<TUNGSTEN>
|	<SEABORGIUM>
|	<MANGANESE>
|	<TECHNETIUM>
|	<RHENIUM>
|	<BOHRIUM>
|	<IRON>
|	<RUTHENIUM>
|	<OSMIUM>
|	<HASSIUM>
|	<COBALT>
|	<RHODIUM>
|	<IRIDIUM>
|	<MEITMERIUM>
|	<NICKEL>
|	<PALLADIUM>
|	<PLATINUM>
|	<COPPER>
|	<SILVER>
|	<GOLD>
|	<ZINC>
|	<CADMIUM>
|	<MECURY>
}

void pBlockMetals() :
{}
{
	<ALUMINIUM>
|	<GALLIUM>
|	<INDIUM>
|	<THALLIUM>
|	<GERMAINIUM>
|	<TIN>
|	<LEAD>
|	<ARSENIC>
|	<ANTIMONY>
|	<BISMUTH>
|	<SELENIUM>
|	<TELLURIUM>
|	<POLONIUM>

}

void fBlockMetals() :
{}
{
	<CERIUM>
|	<PRASEODYMIUM>
|	<NEODYMIUM>
|	<PROMETHIUM>
|	<SANARIUM>
|	<EUROPIUM>
|	<GADOLINIUM>
|	<TERBIUM>
|	<DYSPROSIUM>
|	<HOLMIUM>
|	<ERBIUM>
|	<THULIUM>
|	<YTTERBIUM>
|	<LUTETIUM>
|	<THORIUM>
|	<PROTACTINIUM>
|	<URANIUM>
|	<NEPTUNIUM>
|	<PLUTONIUM>
|	<AMERCIUM>
|	<CURIUM>
|	<BERKELIUM>
|	<CALIFORNIUM>
|	<EINSTEINIUM>
|	<FERMIUM>
|	<MENDELEVIUM>
|	<NOBELIUM>
|	<LAWRENCIUM>

}