org.antlr.v4.misc.CharSupport Maven / Gradle / Ivy

Go to download
Show more of this group Show more artifacts with this name
Show all versions of antlr4 Show documentation
The ANTLR 4 grammar compiler.
There is a newer version: 4.9.0
/*
 * Copyright (c) 2012 The ANTLR Project. All rights reserved.
 * Use of this file is governed by the BSD-3-Clause license that
 * can be found in the LICENSE.txt file in the project root.
 */

package org.antlr.v4.misc;

import org.antlr.v4.runtime.Lexer;

/** */
public class CharSupport {
	/** When converting ANTLR char and string literals, here is the
	 *  value set of escape chars.
	 */
	public static int ANTLRLiteralEscapedCharValue[] = new int[255];

	/** Given a char, we need to be able to show as an ANTLR literal.
	 */
	public static String ANTLRLiteralCharValueEscape[] = new String[255];

	static {
		ANTLRLiteralEscapedCharValue['n'] = '\n';
		ANTLRLiteralEscapedCharValue['r'] = '\r';
		ANTLRLiteralEscapedCharValue['t'] = '\t';
		ANTLRLiteralEscapedCharValue['b'] = '\b';
		ANTLRLiteralEscapedCharValue['f'] = '\f';
		ANTLRLiteralEscapedCharValue['\\'] = '\\';
		ANTLRLiteralEscapedCharValue['\''] = '\'';
		ANTLRLiteralEscapedCharValue['"'] = '"';
		ANTLRLiteralEscapedCharValue['-'] = '-';
		ANTLRLiteralEscapedCharValue[']'] = ']';
		ANTLRLiteralCharValueEscape['\n'] = "\\n";
		ANTLRLiteralCharValueEscape['\r'] = "\\r";
		ANTLRLiteralCharValueEscape['\t'] = "\\t";
		ANTLRLiteralCharValueEscape['\b'] = "\\b";
		ANTLRLiteralCharValueEscape['\f'] = "\\f";
		ANTLRLiteralCharValueEscape['\\'] = "\\\\";
		ANTLRLiteralCharValueEscape['\''] = "\\'";
	}

	/** Return a string representing the escaped char for code c.  E.g., If c
	 *  has value 0x100, you will get "\u0100".  ASCII gets the usual
	 *  char (non-hex) representation.  Control characters are spit out
	 *  as unicode.  While this is specially set up for returning Java strings,
	 *  it can be used by any language target that has the same syntax. :)
	 */
	public static String getANTLRCharLiteralForChar(int c) {
		if ( c< Lexer.MIN_CHAR_VALUE ) {
			return "''";
		}
		if ( cn ) return null; // invalid escape sequence.
						char charAt = literal.charAt(end);
						if (!Character.isDigit(charAt) && !(charAt >= 'a' && charAt <= 'f') && !(charAt >= 'A' && charAt <= 'F')) {
							return null; // invalid escape sequence.
						}
					}
				}
			}
			if ( end>n ) return null; // invalid escape sequence.
			String esc = literal.substring(i, end);
			int c = getCharValueFromCharInGrammarLiteral(esc);
			if ( c==-1 ) {
				return null; // invalid escape sequence.
			}
			else buf.append((char)c);
			i = end;
		}
		return buf.toString();
	}

	/** Given char x or \t or \u1234 return the char value;
	 *  Unnecessary escapes like '\{' yield -1.
	 */
	public static int getCharValueFromCharInGrammarLiteral(String cstr) {
		switch ( cstr.length() ) {
			case 1:
				// 'x'
				return cstr.charAt(0); // no escape char
			case 2:
				if ( cstr.charAt(0)!='\\' ) return -1;
				// '\x'  (antlr lexer will catch invalid char)
				if ( Character.isDigit(cstr.charAt(1)) ) return -1;
				int escChar = cstr.charAt(1);
				int charVal = ANTLRLiteralEscapedCharValue[escChar];
				if ( charVal==0 ) return -1;
				return charVal;
			case 6:
				// '\u1234'
				if ( !cstr.startsWith("\\u") ) return -1;
				String unicodeChars = cstr.substring(2, cstr.length());
				int result = -1;
				try {
					result = Integer.parseInt(unicodeChars, 16);
				}
				catch (NumberFormatException e) {
				}
				return result;
			default:
				return -1;
		}
	}

	public static String capitalize(String s) {
		return Character.toUpperCase(s.charAt(0)) + s.substring(1);
	}
}