All Downloads are FREE. Search and download functionalities are using the official Maven repository.

org.antlr.v4.tool.Grammar Maven / Gradle / Ivy

There is a newer version: 4.9.0
Show newest version
/*
 * [The "BSD license"]
 *  Copyright (c) 2012 Terence Parr
 *  Copyright (c) 2012 Sam Harwell
 *  All rights reserved.
 *
 *  Redistribution and use in source and binary forms, with or without
 *  modification, are permitted provided that the following conditions
 *  are met:
 *
 *  1. Redistributions of source code must retain the above copyright
 *     notice, this list of conditions and the following disclaimer.
 *  2. Redistributions in binary form must reproduce the above copyright
 *     notice, this list of conditions and the following disclaimer in the
 *     documentation and/or other materials provided with the distribution.
 *  3. The name of the author may not be used to endorse or promote products
 *     derived from this software without specific prior written permission.
 *
 *  THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR
 *  IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
 *  OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
 *  IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT,
 *  INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
 *  NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
 *  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
 *  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
 *  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
 *  THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 */

package org.antlr.v4.tool;

import org.antlr.v4.Tool;
import org.antlr.v4.analysis.LeftRecursiveRuleTransformer;
import org.antlr.v4.misc.CharSupport;
import org.antlr.v4.misc.OrderedHashMap;
import org.antlr.v4.misc.Utils;
import org.antlr.v4.parse.ANTLRParser;
import org.antlr.v4.parse.GrammarASTAdaptor;
import org.antlr.v4.parse.GrammarTreeVisitor;
import org.antlr.v4.parse.TokenVocabParser;
import org.antlr.v4.runtime.CharStream;
import org.antlr.v4.runtime.Lexer;
import org.antlr.v4.runtime.LexerInterpreter;
import org.antlr.v4.runtime.ParserInterpreter;
import org.antlr.v4.runtime.Token;
import org.antlr.v4.runtime.TokenStream;
import org.antlr.v4.runtime.atn.ATN;
import org.antlr.v4.runtime.atn.ATNDeserializer;
import org.antlr.v4.runtime.atn.ATNSerializer;
import org.antlr.v4.runtime.dfa.DFA;
import org.antlr.v4.runtime.misc.IntSet;
import org.antlr.v4.runtime.misc.IntegerList;
import org.antlr.v4.runtime.misc.IntervalSet;
import org.antlr.v4.runtime.misc.NotNull;
import org.antlr.v4.runtime.misc.Nullable;
import org.antlr.v4.runtime.misc.Tuple;
import org.antlr.v4.runtime.misc.Tuple2;
import org.antlr.v4.tool.ast.ActionAST;
import org.antlr.v4.tool.ast.GrammarAST;
import org.antlr.v4.tool.ast.GrammarASTWithOptions;
import org.antlr.v4.tool.ast.GrammarRootAST;
import org.antlr.v4.tool.ast.PredAST;
import org.antlr.v4.tool.ast.TerminalAST;

import java.io.IOException;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.HashMap;
import java.util.HashSet;
import java.util.LinkedHashMap;
import java.util.List;
import java.util.Map;
import java.util.Set;

public class Grammar implements AttributeResolver {
	public static final String GRAMMAR_FROM_STRING_NAME = "";

	public static final Set parserOptions = new HashSet();
	static {
		parserOptions.add("superClass");
		parserOptions.add("TokenLabelType");
		parserOptions.add("abstract");
		parserOptions.add("tokenVocab");
		parserOptions.add("language");
	}

	public static final Set lexerOptions = parserOptions;

	public static final Set ruleOptions = new HashSet();

	public static final Set ParserBlockOptions = new HashSet();
	static {
		ParserBlockOptions.add("sll");
	}

	public static final Set LexerBlockOptions = new HashSet();

	/** Legal options for rule refs like id */
	public static final Set ruleRefOptions = new HashSet();
	static {
		ruleRefOptions.add(LeftRecursiveRuleTransformer.PRECEDENCE_OPTION_NAME);
	}

	/** Legal options for terminal refs like ID */
	public static final Set tokenOptions = new HashSet();
	static {
		tokenOptions.add("assoc");
	}

	public static final Set actionOptions = new HashSet();

	public static final Set semPredOptions = new HashSet();
	static {
		semPredOptions.add(LeftRecursiveRuleTransformer.PRECEDENCE_OPTION_NAME);
		semPredOptions.add("fail");
	}

	public static final Set doNotCopyOptionsToLexer = new HashSet();
	static {
		doNotCopyOptionsToLexer.add("superClass");
		doNotCopyOptionsToLexer.add("TokenLabelType");
		doNotCopyOptionsToLexer.add("abstract");
		doNotCopyOptionsToLexer.add("tokenVocab");
	}

	public static final Map grammarAndLabelRefTypeToScope =
		new HashMap();
	static {
		grammarAndLabelRefTypeToScope.put("parser:RULE_LABEL", Rule.predefinedRulePropertiesDict);
		grammarAndLabelRefTypeToScope.put("parser:TOKEN_LABEL", AttributeDict.predefinedTokenDict);
		grammarAndLabelRefTypeToScope.put("combined:RULE_LABEL", Rule.predefinedRulePropertiesDict);
		grammarAndLabelRefTypeToScope.put("combined:TOKEN_LABEL", AttributeDict.predefinedTokenDict);
	}

	public String name;
    public GrammarRootAST ast;
	/** Track stream used to create this grammar */
	@NotNull
	public final org.antlr.runtime.TokenStream tokenStream;
    public String text; // testing only
    public String fileName;

    /** Was this parser grammar created from a COMBINED grammar?  If so,
	 *  this is what we extracted.
	 */
    public LexerGrammar implicitLexer;

	/** If this is an extracted/implicit lexer, we point at original grammar */
	public Grammar originalGrammar;

    /** If we're imported, who imported us? If null, implies grammar is root */
    public Grammar parent;
    public List importedGrammars;

	/** All rules defined in this specific grammar, not imported. Also does
	 *  not include lexical rules if combined.
	 */
    public OrderedHashMap rules = new OrderedHashMap();
	public List indexToRule = new ArrayList();

	int ruleNumber = 0; // used to get rule indexes (0..n-1)
	int stringLiteralRuleNumber = 0; // used to invent rule names for 'keyword', ';', ... (0..n-1)

	/** The ATN that represents the grammar with edges labelled with tokens
	 *  or epsilon.  It is more suitable to analysis than an AST representation.
	 */
	public ATN atn;

	public Map decisionDFAs = new HashMap();

	public List decisionLOOK;

	@NotNull
	public final Tool tool;

	/** Token names and literal tokens like "void" are uniquely indexed.
	 *  with -1 implying EOF.  Characters are different; they go from
	 *  -1 (EOF) to \uFFFE.  For example, 0 could be a binary byte you
	 *  want to lexer.  Labels of DFA/ATN transitions can be both tokens
	 *  and characters.  I use negative numbers for bookkeeping labels
	 *  like EPSILON. Char/String literals and token types overlap in the same
	 *  space, however.
	 */
	int maxTokenType = Token.MIN_USER_TOKEN_TYPE -1;

	/** Map token like ID (but not literals like "while") to its token type */
	public Map tokenNameToTypeMap = new LinkedHashMap();

	/** Map token literals like "while" to its token type.  It may be that
	 *  WHILE="while"=35, in which case both tokenIDToTypeMap and this
	 *  field will have entries both mapped to 35.
	 */
	public Map stringLiteralToTypeMap = new LinkedHashMap();

	/** Reverse index for stringLiteralToTypeMap.  Indexed with raw token type.
	 *  0 is invalid. */
	public List typeToStringLiteralList = new ArrayList();

	/** Map a token type to its token name. Indexed with raw token type.
	 *  0 is invalid.
	 */
	public List typeToTokenList = new ArrayList();

    /** Map a name to an action.
     *  The code generator will use this to fill holes in the output files.
     *  I track the AST node for the action in case I need the line number
     *  for errors.
     */
	public Map namedActions = new HashMap();

	/** Tracks all user lexer actions in all alternatives of all rules.
	 *  Doesn't track sempreds.  maps tree node to action index (alt number 1..n).
 	 */
	public LinkedHashMap lexerActions = new LinkedHashMap();

	/** All sempreds found in grammar; maps tree node to sempred index;
	 *  sempred index is 0..n-1
	 */
	public LinkedHashMap sempreds = new LinkedHashMap();

	public static final String AUTO_GENERATED_TOKEN_NAME_PREFIX = "T__";

	public Grammar(Tool tool, @NotNull GrammarRootAST ast) {
		if ( ast==null ) {
			throw new NullPointerException("ast");
		}

		if (ast.tokenStream == null) {
			throw new IllegalArgumentException("ast must have a token stream");
		}

        this.tool = tool;
        this.ast = ast;
        this.name = (ast.getChild(0)).getText();
		this.tokenStream = ast.tokenStream;

		initTokenSymbolTables();
    }

	/** For testing */
	public Grammar(String grammarText) throws org.antlr.runtime.RecognitionException {
		this(GRAMMAR_FROM_STRING_NAME, grammarText, null);
	}

	public Grammar(String grammarText, LexerGrammar tokenVocabSource) throws org.antlr.runtime.RecognitionException {
		this(GRAMMAR_FROM_STRING_NAME, grammarText, tokenVocabSource, null);
	}

	/** For testing */
	public Grammar(String grammarText, ANTLRToolListener listener)
		throws org.antlr.runtime.RecognitionException
	{
		this(GRAMMAR_FROM_STRING_NAME, grammarText, listener);
	}

	/** For testing; builds trees, does sem anal */
	public Grammar(String fileName, String grammarText)
		throws org.antlr.runtime.RecognitionException
	{
		this(fileName, grammarText, null);
	}

	/** For testing; builds trees, does sem anal */
	public Grammar(String fileName, String grammarText, @Nullable ANTLRToolListener listener)
		throws org.antlr.runtime.RecognitionException
	{
		this(fileName, grammarText, null, listener);
	}

	/** For testing; builds trees, does sem anal */
	public Grammar(String fileName, String grammarText, Grammar tokenVocabSource, @Nullable ANTLRToolListener listener)
		throws org.antlr.runtime.RecognitionException
	{
        this.text = grammarText;
		this.fileName = fileName;
		this.tool = new Tool();
		this.tool.addListener(listener);
		org.antlr.runtime.ANTLRStringStream in = new org.antlr.runtime.ANTLRStringStream(grammarText);
		in.name = fileName;

		this.ast = tool.parse(fileName, in);
		if ( ast==null ) {
			throw new UnsupportedOperationException();
		}

		if (ast.tokenStream == null) {
			throw new IllegalStateException("expected ast to have a token stream");
		}

		this.tokenStream = ast.tokenStream;

		// ensure each node has pointer to surrounding grammar
		final Grammar thiz = this;
		org.antlr.runtime.tree.TreeVisitor v = new org.antlr.runtime.tree.TreeVisitor(new GrammarASTAdaptor());
		v.visit(ast, new org.antlr.runtime.tree.TreeVisitorAction() {
			@Override
			public Object pre(Object t) { ((GrammarAST)t).g = thiz; return t; }
			@Override
			public Object post(Object t) { return t; }
		});
		initTokenSymbolTables();

		if (tokenVocabSource != null) {
			importVocab(tokenVocabSource);
		}

		tool.process(this, false);
    }

	protected void initTokenSymbolTables() {
		tokenNameToTypeMap.put("EOF", Token.EOF);

		// reserve a spot for the INVALID token
		typeToTokenList.add(null);
	}

    public void loadImportedGrammars() {
		if ( ast==null ) return;
        GrammarAST i = (GrammarAST)ast.getFirstChildWithType(ANTLRParser.IMPORT);
        if ( i==null ) return;
        importedGrammars = new ArrayList();
        for (Object c : i.getChildren()) {
            GrammarAST t = (GrammarAST)c;
            String importedGrammarName = null;
            if ( t.getType()==ANTLRParser.ASSIGN ) {
                importedGrammarName = t.getChild(1).getText();
                tool.log("grammar", "import "+ importedGrammarName);
            }
            else if ( t.getType()==ANTLRParser.ID ) {
                importedGrammarName = t.getText();
                tool.log("grammar", "import " + t.getText());
			}
			Grammar g;
			try {
				g = tool.loadImportedGrammar(this, importedGrammarName);
			}
			catch (IOException ioe) {
				tool.errMgr.toolError(ErrorType.CANNOT_FIND_IMPORTED_GRAMMAR, ioe,
									  importedGrammarName);
				continue;
			}
			// did it come back as error node or missing?
			if ( g == null ) continue;
			g.parent = this;
			importedGrammars.add(g);
			g.loadImportedGrammars(); // recursively pursue any imports in this import
        }
    }

    public void defineAction(GrammarAST atAST) {
        if ( atAST.getChildCount()==2 ) {
            String name = atAST.getChild(0).getText();
            namedActions.put(name, (ActionAST)atAST.getChild(1));
        }
        else {
			String scope = atAST.getChild(0).getText();
            String gtype = getTypeString();
            if ( scope.equals(gtype) || (scope.equals("parser")&>ype.equals("combined")) ) {
				String name = atAST.getChild(1).getText();
				namedActions.put(name, (ActionAST)atAST.getChild(2));
			}
        }
    }

    public void defineRule(Rule r) {
		if ( rules.get(r.name)!=null ) return;
		rules.put(r.name, r);
		r.index = ruleNumber++;
		indexToRule.add(r);
	}

//	public int getNumRules() {
//		int n = rules.size();
//		List imports = getAllImportedGrammars();
//		if ( imports!=null ) {
//			for (Grammar g : imports) n += g.getNumRules();
//		}
//		return n;
//	}

    public Rule getRule(String name) {
		Rule r = rules.get(name);
		if ( r!=null ) return r;
		return null;
		/*
		List imports = getAllImportedGrammars();
		if ( imports==null ) return null;
		for (Grammar g : imports) {
			r = g.getRule(name); // recursively walk up hierarchy
			if ( r!=null ) return r;
		}
		return null;
		*/
	}

	public Rule getRule(int index) { return indexToRule.get(index); }

	public Rule getRule(String grammarName, String ruleName) {
		if ( grammarName!=null ) { // scope override
			Grammar g = getImportedGrammar(grammarName);
			if ( g ==null ) {
				return null;
			}
			return g.rules.get(ruleName);
		}
		return getRule(ruleName);
	}

    /** Get list of all imports from all grammars in the delegate subtree of g.
     *  The grammars are in import tree preorder.  Don't include ourselves
     *  in list as we're not a delegate of ourselves.
     */
    public List getAllImportedGrammars() {
        if ( importedGrammars==null ) return null;
        List delegates = new ArrayList();
		for (Grammar d : importedGrammars) {
			delegates.add(d);
			List ds = d.getAllImportedGrammars();
			if (ds != null) delegates.addAll(ds);
		}
        return delegates;
    }

    public List getImportedGrammars() { return importedGrammars; }

    /** Get delegates below direct delegates of g
    public List getIndirectDelegates(Grammar g) {
        List direct = getDirectDelegates(g);
        List delegates = getDelegates(g);
        delegates.removeAll(direct);
        return delegates;
    }
*/

	public LexerGrammar getImplicitLexer() {
		return implicitLexer;
	}

	/** convenience method for Tool.loadGrammar() */
	public static Grammar load(String fileName) {
		Tool antlr = new Tool();
		return antlr.loadGrammar(fileName);
	}

	/** Return list of imported grammars from root down to our parent.
     *  Order is [root, ..., this.parent].  (us not included).
     */
    public List getGrammarAncestors() {
        Grammar root = getOutermostGrammar();
        if ( this==root ) return null;
        List grammars = new ArrayList();
        // walk backwards to root, collecting grammars
        Grammar p = this.parent;
        while ( p!=null ) {
            grammars.add(0, p); // add to head so in order later
            p = p.parent;
        }
        return grammars;
    }

    /** Return the grammar that imported us and our parents. Return this
     *  if we're root.
     */
    public Grammar getOutermostGrammar() {
        if ( parent==null ) return this;
        return parent.getOutermostGrammar();
    }

	public boolean isAbstract() {
		return Boolean.parseBoolean(getOptionString("abstract"));
	}

    /** Get the name of the generated recognizer; may or may not be same
     *  as grammar name.
     *  Recognizer is TParser and TLexer from T if combined, else
     *  just use T regardless of grammar type.
     */
    public String getRecognizerName() {
        String suffix = "";
        List grammarsFromRootToMe = getOutermostGrammar().getGrammarAncestors();
        String qualifiedName = name;
        if ( grammarsFromRootToMe!=null ) {
            StringBuilder buf = new StringBuilder();
            for (Grammar g : grammarsFromRootToMe) {
                buf.append(g.name);
                buf.append('_');
            }
			if (isAbstract()) {
				buf.append("Abstract");
			}
            buf.append(name);
            qualifiedName = buf.toString();
        }
		else if (isAbstract()) {
			qualifiedName = "Abstract" + name;
		}

        if ( isCombined() || (isLexer() && implicitLexer!=null) )
        {
            suffix = Grammar.getGrammarTypeToFileNameSuffix(getType());
        }
        return qualifiedName+suffix;
    }

	public String getStringLiteralLexerRuleName(String lit) {
		return AUTO_GENERATED_TOKEN_NAME_PREFIX + stringLiteralRuleNumber++;
	}

    /** Return grammar directly imported by this grammar */
    public Grammar getImportedGrammar(String name) {
		for (Grammar g : importedGrammars) {
            if ( g.name.equals(name) ) return g;
        }
        return null;
    }

	public int getTokenType(String token) {
		Integer I;
		if ( token.charAt(0)=='\'') {
			I = stringLiteralToTypeMap.get(token);
		}
		else { // must be a label like ID
			I = tokenNameToTypeMap.get(token);
		}
		int i = (I!=null)? I : Token.INVALID_TYPE;
		//tool.log("grammar", "grammar type "+type+" "+tokenName+"->"+i);
		return i;
	}

	/** Given a token type, get a meaningful name for it such as the ID
	 *  or string literal.  If this is a lexer and the ttype is in the
	 *  char vocabulary, compute an ANTLR-valid (possibly escaped) char literal.
	 */
	public String getTokenDisplayName(int ttype) {
		String tokenName;
		// inside any target's char range and is lexer grammar?
		if ( isLexer() &&
			 ttype >= Lexer.MIN_CHAR_VALUE && ttype <= Lexer.MAX_CHAR_VALUE )
		{
			return CharSupport.getANTLRCharLiteralForChar(ttype);
		}
		else if ( ttype==Token.EOF ) {
			tokenName = "EOF";
		}
		else {
			if ( ttype>0 && ttype tokens = vparser.load();
			tool.log("grammar", "tokens=" + tokens);
			for (String t : tokens.keySet()) {
				if ( t.charAt(0)=='\'' ) defineStringLiteral(t, tokens.get(t));
				else defineTokenName(t, tokens.get(t));
			}
		}
	}

	public void importVocab(Grammar importG) {
		for (String tokenName: importG.tokenNameToTypeMap.keySet()) {
			defineTokenName(tokenName, importG.tokenNameToTypeMap.get(tokenName));
		}
		for (String tokenName: importG.stringLiteralToTypeMap.keySet()) {
			defineStringLiteral(tokenName, importG.stringLiteralToTypeMap.get(tokenName));
		}
//		this.tokenNameToTypeMap.putAll( importG.tokenNameToTypeMap );
//		this.stringLiteralToTypeMap.putAll( importG.stringLiteralToTypeMap );
		int max = Math.max(this.typeToTokenList.size(), importG.typeToTokenList.size());
		Utils.setSize(typeToTokenList, max);
		for (int ttype=0; ttype=typeToStringLiteralList.size() ) {
				Utils.setSize(typeToStringLiteralList, ttype+1);
			}
			typeToStringLiteralList.set(ttype, lit);

			setTokenForType(ttype, lit);
			return ttype;
		}
		return Token.INVALID_TYPE;
	}

	public int defineTokenAlias(String name, String lit) {
		int ttype = defineTokenName(name);
		stringLiteralToTypeMap.put(lit, ttype);
		setTokenForType(ttype, name);
		return ttype;
	}

	public void setTokenForType(int ttype, String text) {
		if ( ttype>=typeToTokenList.size() ) {
			Utils.setSize(typeToTokenList, ttype+1);
		}
		String prevToken = typeToTokenList.get(ttype);
		if ( prevToken==null || prevToken.charAt(0)=='\'' ) {
			// only record if nothing there before or if thing before was a literal
			typeToTokenList.set(ttype, text);
		}
	}

	// no isolated attr at grammar action level
	@Override
	public Attribute resolveToAttribute(String x, ActionAST node) {
		return null;
	}

	// no $x.y makes sense here
	@Override
	public Attribute resolveToAttribute(String x, String y, ActionAST node) {
		return null;
	}

	@Override
	public boolean resolvesToLabel(String x, ActionAST node) { return false; }

	@Override
	public boolean resolvesToListLabel(String x, ActionAST node) { return false; }

	@Override
	public boolean resolvesToToken(String x, ActionAST node) { return false; }

	@Override
	public boolean resolvesToAttributeDict(String x, ActionAST node) {
		return false;
	}

	/** Given a grammar type, what should be the default action scope?
     *  If I say @members in a COMBINED grammar, for example, the
     *  default scope should be "parser".
     */
    public String getDefaultActionScope() {
        switch ( getType() ) {
            case ANTLRParser.LEXER :
                return "lexer";
            case ANTLRParser.PARSER :
            case ANTLRParser.COMBINED :
                return "parser";
        }
        return null;
    }

    public int getType() {
        if ( ast!=null ) return ast.grammarType;
        return 0;
    }

	public org.antlr.runtime.TokenStream getTokenStream() {
		if ( ast!=null ) return ast.tokenStream;
		return null;
	}

	public boolean isLexer() { return getType()==ANTLRParser.LEXER; }
	public boolean isParser() { return getType()==ANTLRParser.PARSER; }
	public boolean isCombined() { return getType()==ANTLRParser.COMBINED; }

	/** Is id a valid token name? Does id start with an uppercase letter? */
	public static boolean isTokenName(String id) {
		return Character.isUpperCase(id.charAt(0));
	}

    public String getTypeString() {
        if ( ast==null ) return null;
        return ANTLRParser.tokenNames[getType()].toLowerCase();
    }

    public static String getGrammarTypeToFileNameSuffix(int type) {
        switch ( type ) {
            case ANTLRParser.LEXER : return "Lexer";
            case ANTLRParser.PARSER : return "Parser";
            // if combined grammar, gen Parser and Lexer will be done later
            // TODO: we are separate now right?
            case ANTLRParser.COMBINED : return "Parser";
            default :
                return "";
        }
	}

	public String getOptionString(String key) { return ast.getOptionString(key); }

	/** Given ^(TOKEN_REF ^(OPTIONS ^(ELEMENT_OPTIONS (= assoc right))))
	 *  set option assoc=right in TOKEN_REF.
	 */
	public static void setNodeOptions(GrammarAST node, GrammarAST options) {
		if ( options==null ) return;
		GrammarASTWithOptions t = (GrammarASTWithOptions)node;
		if ( t.getChildCount()==0 || options.getChildCount()==0 ) return;
		for (Object o : options.getChildren()) {
			GrammarAST c = (GrammarAST)o;
			if ( c.getType()==ANTLRParser.ASSIGN ) {
				t.setOption(c.getChild(0).getText(), (GrammarAST)c.getChild(1));
			}
			else {
				t.setOption(c.getText(), null); // no arg such as ID
			}
		}
	}

	/** Return list of (TOKEN_NAME node, 'literal' node) pairs */
	public static List> getStringLiteralAliasesFromLexerRules(GrammarRootAST ast) {
		String[] patterns = {
			"(RULE %name:TOKEN_REF (BLOCK (ALT %lit:STRING_LITERAL)))",
			"(RULE %name:TOKEN_REF (BLOCK (ALT %lit:STRING_LITERAL ACTION)))",
			"(RULE %name:TOKEN_REF (BLOCK (ALT %lit:STRING_LITERAL SEMPRED)))",
			"(RULE %name:TOKEN_REF (BLOCK (LEXER_ALT_ACTION (ALT %lit:STRING_LITERAL) .)))",
			"(RULE %name:TOKEN_REF (BLOCK (LEXER_ALT_ACTION (ALT %lit:STRING_LITERAL) . .)))",
			"(RULE %name:TOKEN_REF (BLOCK (LEXER_ALT_ACTION (ALT %lit:STRING_LITERAL) (LEXER_ACTION_CALL . .))))",
			"(RULE %name:TOKEN_REF (BLOCK (LEXER_ALT_ACTION (ALT %lit:STRING_LITERAL) . (LEXER_ACTION_CALL . .))))",
			"(RULE %name:TOKEN_REF (BLOCK (LEXER_ALT_ACTION (ALT %lit:STRING_LITERAL) (LEXER_ACTION_CALL . .) .)))",
			// TODO: allow doc comment in there
		};
		GrammarASTAdaptor adaptor = new GrammarASTAdaptor(ast.token.getInputStream());
		org.antlr.runtime.tree.TreeWizard wiz = new org.antlr.runtime.tree.TreeWizard(adaptor,ANTLRParser.tokenNames);
		List> lexerRuleToStringLiteral =
			new ArrayList>();

		List ruleNodes = ast.getNodesWithType(ANTLRParser.RULE);
		if ( ruleNodes==null || ruleNodes.isEmpty() ) return null;

		for (GrammarAST r : ruleNodes) {
			//tool.log("grammar", r.toStringTree());
//			System.out.println("chk: "+r.toStringTree());
			org.antlr.runtime.tree.Tree name = r.getChild(0);
			if ( name.getType()==ANTLRParser.TOKEN_REF ) {
				// check rule against patterns
				boolean isLitRule;
				for (String pattern : patterns) {
					isLitRule =
						defAlias(r, pattern, wiz, lexerRuleToStringLiteral);
					if ( isLitRule ) break;
				}
//				if ( !isLitRule ) System.out.println("no pattern matched");
			}
		}
		return lexerRuleToStringLiteral;
	}

	protected static boolean defAlias(GrammarAST r, String pattern,
									  org.antlr.runtime.tree.TreeWizard wiz,
									  List> lexerRuleToStringLiteral)
	{
		HashMap nodes = new HashMap();
		if ( wiz.parse(r, pattern, nodes) ) {
			GrammarAST litNode = (GrammarAST)nodes.get("lit");
			GrammarAST nameNode = (GrammarAST)nodes.get("name");
			Tuple2 pair = Tuple.create(nameNode, litNode);
			lexerRuleToStringLiteral.add(pair);
			return true;
		}
		return false;
	}

	public Set getStringLiterals() {
		final Set strings = new HashSet();
		GrammarTreeVisitor collector = new GrammarTreeVisitor() {
			@Override
			public void stringRef(TerminalAST ref) {
				strings.add(ref.getText());
			}
		};
		collector.visitGrammar(ast);
		return strings;
	}

	public void setLookaheadDFA(int decision, DFA lookaheadDFA) {
		decisionDFAs.put(decision, lookaheadDFA);
	}

	public LexerInterpreter createLexerInterpreter(CharStream input) {
		if (this.isParser()) {
			throw new IllegalStateException("A lexer interpreter can only be created for a lexer or combined grammar.");
		}

		if (this.isCombined()) {
			return implicitLexer.createLexerInterpreter(input);
		}

		char[] serializedAtn = ATNSerializer.getSerializedAsChars(atn, Arrays.asList(getRuleNames()));
		ATN deserialized = new ATNDeserializer().deserialize(serializedAtn);
		return new LexerInterpreter(fileName, Arrays.asList(getTokenNames()), Arrays.asList(getRuleNames()), ((LexerGrammar)this).modes.keySet(), deserialized, input);
	}

	public ParserInterpreter createParserInterpreter(TokenStream tokenStream) {
		if (this.isLexer()) {
			throw new IllegalStateException("A parser interpreter can only be created for a parser or combined grammar.");
		}

		char[] serializedAtn = ATNSerializer.getSerializedAsChars(atn, Arrays.asList(getRuleNames()));
		ATN deserialized = new ATNDeserializer().deserialize(serializedAtn);
		return new ParserInterpreter(fileName, Arrays.asList(getTokenNames()), Arrays.asList(getRuleNames()), deserialized, tokenStream);
	}
}




© 2015 - 2024 Weber Informatics LLC | Privacy Policy