org.antlr.v4.codegen.JavaTarget Maven / Gradle / Ivy
Go to download
Show more of this group Show more artifacts with this name
Show all versions of antlr4 Show documentation
Show all versions of antlr4 Show documentation
The ANTLR 4 grammar compiler.
/*
* [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.codegen;
import org.antlr.v4.tool.ast.GrammarAST;
import org.stringtemplate.v4.STGroup;
import org.stringtemplate.v4.StringRenderer;
import java.util.Arrays;
import java.util.HashSet;
import java.util.Locale;
import java.util.Set;
/**
*
* @author Sam Harwell
*/
public class JavaTarget extends Target {
protected static final String[] javaKeywords = {
"abstract", "assert", "boolean", "break", "byte", "case", "catch",
"char", "class", "const", "continue", "default", "do", "double", "else",
"enum", "extends", "false", "final", "finally", "float", "for",
"if", "implements", "import", "instanceof", "int", "interface",
"long", "native", "new", "null", "package", "private", "protected",
"public", "return", "short", "static", "strictfp", "super", "switch",
"synchronized", "this", "throw", "throws", "transient", "true", "try",
"void", "volatile", "while"
};
/** Avoid grammar symbols in this set to prevent conflicts in gen'd code. */
protected final Set badWords = new HashSet();
public JavaTarget(CodeGenerator gen) {
super(gen, "Java");
}
public Set getBadWords() {
if (badWords.isEmpty()) {
addBadWords();
}
return badWords;
}
protected void addBadWords() {
badWords.addAll(Arrays.asList(javaKeywords));
badWords.add("rule");
badWords.add("parserRule");
}
/**
* {@inheritDoc}
*
* For Java, this is the translation {@code 'a\n"'} → {@code "a\n\""}.
* Expect single quotes around the incoming literal. Just flip the quotes
* and replace double quotes with {@code \"}.
*
* Note that we have decided to allow people to use '\"' without penalty, so
* we must build the target string in a loop as {@link String#replace}
* cannot handle both {@code \"} and {@code "} without a lot of messing
* around.
*/
@Override
public String getTargetStringLiteralFromANTLRStringLiteral(
CodeGenerator generator,
String literal, boolean addQuotes)
{
StringBuilder sb = new StringBuilder();
String is = literal;
if ( addQuotes ) sb.append('"');
for (int i = 1; i < is.length() -1; i++) {
if (is.charAt(i) == '\\') {
// Anything escaped is what it is! We assume that
// people know how to escape characters correctly. However
// we catch anything that does not need an escape in Java (which
// is what the default implementation is dealing with and remove
// the escape. The C target does this for instance.
//
switch (is.charAt(i+1)) {
// Pass through any escapes that Java also needs
//
case '"':
case 'n':
case 'r':
case 't':
case 'b':
case 'f':
case '\\':
// Pass the escape through
sb.append('\\');
break;
case 'u': // Assume unnnn
// Pass the escape through as double \\
// so that Java leaves as \u0000 string not char
sb.append('\\');
sb.append('\\');
break;
default:
// Remove the escape by virtue of not adding it here
// Thus \' becomes ' and so on
break;
}
// Go past the \ character
i++;
} else {
// Characters that don't need \ in ANTLR 'strings' but do in Java
if (is.charAt(i) == '"') {
// We need to escape " in Java
sb.append('\\');
}
}
// Add in the next character, which may have been escaped
sb.append(is.charAt(i));
}
if ( addQuotes ) sb.append('"');
return sb.toString();
}
@Override
public String encodeIntAsCharEscape(int v) {
if (v < Character.MIN_VALUE || v > Character.MAX_VALUE) {
throw new IllegalArgumentException(String.format("Cannot encode the specified value: %d", v));
}
if (v >= 0 && v < targetCharValueEscape.length && targetCharValueEscape[v] != null) {
return targetCharValueEscape[v];
}
if (v >= 0x20 && v < 127 && (!Character.isDigit(v) || v == '8' || v == '9')) {
return String.valueOf((char)v);
}
if ( v>=0 && v<=127 ) {
String oct = Integer.toOctalString(v);
return "\\"+ oct;
}
String hex = Integer.toHexString(v|0x10000).substring(1,5);
return "\\u"+hex;
}
@Override
public int getSerializedATNSegmentLimit() {
// 65535 is the class file format byte limit for a UTF-8 encoded string literal
// 3 is the maximum number of bytes it takes to encode a value in the range 0-0xFFFF
return 65535 / 3;
}
@Override
protected boolean visibleGrammarSymbolCausesIssueInGeneratedCode(GrammarAST idNode) {
return getBadWords().contains(idNode.getText());
}
@Override
protected STGroup loadTemplates() {
STGroup result = super.loadTemplates();
result.registerRenderer(String.class, new JavaStringRenderer(), true);
return result;
}
protected static class JavaStringRenderer extends StringRenderer {
@Override
public String toString(Object o, String formatString, Locale locale) {
if ("java-escape".equals(formatString)) {
// 5C is the hex code for the \ itself
return ((String)o).replace("\\u", "\\u005Cu");
}
return super.toString(o, formatString, locale);
}
}
}