Get rid of all (char) casts

runtime/Java/src/org/antlr/v4/runtime/atn/RangeTransition.java

@@ -34,6 +34,11 @@ public final class RangeTransition extends Transition {
 
 	@Override
 	public String toString() {
-		return "'"+(char)from+"'..'"+(char)to+"'";
+		return new StringBuilder("'")
+				.appendCodePoint(from)
+				.append("'..'")
+				.appendCodePoint(to)
+				.append("'")
+				.toString();
 	}
 }

runtime/Java/src/org/antlr/v4/runtime/dfa/LexerDFASerializer.java

@@ -16,6 +16,9 @@ public class LexerDFASerializer extends DFASerializer {
 	@Override
 
 	protected String getEdgeLabel(int i) {
-		return "'"+(char)i+"'";
+		return new StringBuilder("'")
+				.appendCodePoint(i)
+				.append("'")
+				.toString();
 	}
 }

runtime/Java/src/org/antlr/v4/runtime/misc/IntervalSet.java

@@ -505,11 +505,11 @@ public class IntervalSet implements IntSet {
 			int b = I.b;
 			if ( a==b ) {
 				if ( a==Token.EOF ) buf.append("<EOF>");
-				else if ( elemAreChar ) buf.append("'").append((char)a).append("'");
+				else if ( elemAreChar ) buf.append("'").appendCodePoint(a).append("'");
 				else buf.append(a);
 			}
 			else {
-				if ( elemAreChar ) buf.append("'").append((char)a).append("'..'").append((char)b).append("'");
+				if ( elemAreChar ) buf.append("'").appendCodePoint(a).append("'..'").appendCodePoint(b).append("'");
 				else buf.append(a).append("..").append(b);
 			}
 			if ( iter.hasNext() ) {

tool/src/org/antlr/v4/automata/ATNOptimizer.java

@@ -18,6 +18,7 @@ import org.antlr.v4.runtime.atn.SetTransition;
 import org.antlr.v4.runtime.atn.Transition;
 import org.antlr.v4.runtime.misc.Interval;
 import org.antlr.v4.runtime.misc.IntervalSet;
+import org.antlr.v4.misc.CharSupport;
 import org.antlr.v4.tool.ErrorType;
 import org.antlr.v4.tool.Grammar;
 import org.antlr.v4.tool.Rule;
@@ -101,11 +102,11 @@ public class ATNOptimizer {
 					int maxElem = set.getMaxElement();
 					for (int k = minElem; k <= maxElem; k++) {
 						if (matchSet.contains(k)) {
-							char setMin = (char) set.getMinElement();
-							char setMax = (char) set.getMaxElement();
 							// TODO: Token is missing (i.e. position in source will not be displayed).
 							g.tool.errMgr.grammarError(ErrorType.CHARACTERS_COLLISION_IN_SET, g.fileName,
-							                           null, (char) minElem + "-" + (char) maxElem, "[" + setMin + "-" + setMax + "]");
+										   null,
+										   CharSupport.toRange(minElem, maxElem, CharSupport.ToRangeMode.NOT_BRACKETED),
+										   CharSupport.toRange(set.getMinElement(), set.getMaxElement(), CharSupport.ToRangeMode.BRACKETED));
 							break;
 						}
 					}

tool/src/org/antlr/v4/automata/LexerATNFactory.java

@@ -353,10 +353,12 @@ public class LexerATNFactory extends ParserATNFactory {
 		int n = chars.length();
 		ATNState prev = left;
 		right = null;
-		for (int i = 0; i < n; i++) {
+		for (int i = 0; i < n; ) {
 			right = newState(stringLiteralAST);
-			prev.addTransition(new AtomTransition(right, chars.charAt(i)));
+			int codePoint = chars.codePointAt(i);
+			prev.addTransition(new AtomTransition(right, codePoint));
 			prev = right;
+			i += Character.charCount(codePoint);
 		}
 		stringLiteralAST.atnState = left;
 		return new Handle(left, right);
@@ -394,30 +396,32 @@ public class LexerATNFactory extends ParserATNFactory {
 		}
 		int n = chars.length();
 		// now make x-y become set of char
-		for (int i = 0; i < n; i++) {
+		for (int i = 0; i < n; ) {
-			int c = chars.charAt(i);
+			int c = chars.codePointAt(i);
-			if (c == '\\' && i+1 < n && chars.charAt(i+1) == '-') { // \-
+			int offset = Character.charCount(c);
+			if (c == '\\' && i+offset < n && chars.codePointAt(i+offset) == '-') { // \-
 				checkSetCollision(charSetAST, set, '-');
 				set.add('-');
-				i++;
+				offset++;
 			}
-			else if (i+2 < n && chars.charAt(i+1) == '-') { // range x-y
+			else if (i+offset+1 < n && chars.codePointAt(i+offset) == '-') { // range x-y
 				int x = c;
-				int y = chars.charAt(i+2);
+				int y = chars.codePointAt(i+offset+1);
 				if (x <= y) {
 					checkSetCollision(charSetAST, set, x, y);
 					set.add(x,y);
 				}
 				else {
 					g.tool.errMgr.grammarError(ErrorType.EMPTY_STRINGS_AND_SETS_NOT_ALLOWED,
-					                           g.fileName, charSetAST.getToken(), "[" + (char) x + "-" + (char) y + "]");
+								   g.fileName, charSetAST.getToken(), CharSupport.toRange(x, y, CharSupport.ToRangeMode.BRACKETED));
 				}
-				i += 2;
+				offset += Character.charCount(y) + 1;
 			}
 			else {
 				checkSetCollision(charSetAST, set, c);
 				set.add(c);
 			}
+			i += offset;
 		}
 		return set;
 	}
@@ -425,7 +429,7 @@ public class LexerATNFactory extends ParserATNFactory {
 	protected void checkSetCollision(GrammarAST ast, IntervalSet set, int el) {
 		if (set.contains(el)) {
 			g.tool.errMgr.grammarError(ErrorType.CHARACTERS_COLLISION_IN_SET, g.fileName, ast.getToken(),
-					(char)el, ast.getText());
+					el, ast.getText());
 		}
 	}
 
@@ -453,7 +457,7 @@ public class LexerATNFactory extends ParserATNFactory {
 					setText = sb.toString();
 				}
 				g.tool.errMgr.grammarError(ErrorType.CHARACTERS_COLLISION_IN_SET, g.fileName, ast.getToken(),
-						(char)a + "-" + (char)b, setText);
+							   CharSupport.toRange(a, b, CharSupport.ToRangeMode.NOT_BRACKETED), setText);
 				break;
 			}
 		}

tool/src/org/antlr/v4/misc/CharSupport.java

@@ -19,6 +19,11 @@ public class CharSupport {
 	 */
 	public static String ANTLRLiteralCharValueEscape[] = new String[255];
 
+	public enum ToRangeMode {
+		BRACKETED,
+		NOT_BRACKETED,
+	};
+
 	static {
 		ANTLRLiteralEscapedCharValue['n'] = '\n';
 		ANTLRLiteralEscapedCharValue['r'] = '\r';
@@ -143,4 +148,18 @@ public class CharSupport {
 	public static String capitalize(String s) {
 		return Character.toUpperCase(s.charAt(0)) + s.substring(1);
 	}
+
+	public static String toRange(int codePointStart, int codePointEnd, ToRangeMode mode) {
+		StringBuilder sb = new StringBuilder();
+		if (mode == ToRangeMode.BRACKETED) {
+			sb.append("[");
+		}
+		sb.appendCodePoint(codePointStart)
+			.append("-")
+			.appendCodePoint(codePointEnd);
+		if (mode == ToRangeMode.BRACKETED) {
+			sb.append("]");
+		}
+		return sb.toString();
+	}
 }

tool/src/org/antlr/v4/tool/DOTGenerator.java

@@ -92,7 +92,7 @@ public class DOTGenerator {
 					if ( target.stateNumber == Integer.MAX_VALUE ) continue;
 					int ttype = i-1; // we shift up for EOF as -1 for parser
 					String label = String.valueOf(ttype);
-					if ( isLexer ) label = "'"+getEdgeLabel(String.valueOf((char) i))+"'";
+					if ( isLexer ) label = "'"+getEdgeLabel(new StringBuilder().appendCodePoint(i).toString())+"'";
 					else if ( grammar!=null ) label = grammar.getTokenDisplayName(ttype);
 					ST st = stlib.getInstanceOf("edge");
 					st.add("label", label);
@@ -259,7 +259,7 @@ public class DOTGenerator {
 					edgeST = stlib.getInstanceOf("edge");
 					AtomTransition atom = (AtomTransition)edge;
 					String label = String.valueOf(atom.label);
-					if ( isLexer ) label = "'"+getEdgeLabel(String.valueOf((char)atom.label))+"'";
+					if ( isLexer ) label = "'"+getEdgeLabel(new StringBuilder().appendCodePoint(atom.label).toString())+"'";
 					else if ( grammar!=null ) label = grammar.getTokenDisplayName(atom.label);
 					edgeST.add("label", getEdgeLabel(label));
 				}