Created
March 8, 2014 03:00
-
-
Save sharwell/9424666 to your computer and use it in GitHub Desktop.
Case insensitive input stream for ANTLR 4
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
/* | |
* [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.runtime; | |
/** | |
* | |
* @author Sam Harwell | |
*/ | |
public class CaseInsensitiveInputStream extends ANTLRInputStream { | |
protected char[] lookaheadData; | |
public CaseInsensitiveInputStream(String input) { | |
super(input); | |
lookaheadData = input.toLowerCase().toCharArray(); | |
} | |
@Override | |
public int LA(int i) { | |
if (i == 0) { | |
return 0; // undefined | |
} | |
if (i < 0) { | |
i++; // e.g., translate LA(-1) to use offset i=0; then data[p+0-1] | |
if ((p + i - 1) < 0) { | |
return IntStream.EOF; // invalid; no char before first char | |
} | |
} | |
if ((p + i - 1) >= n) { | |
return IntStream.EOF; | |
} | |
return lookaheadData[p + i - 1]; | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
For truly case-insensitive languages, a case-insensitive lookahead stream causes the ANTLR lexer to behave as though the input contained only lowercase letters, but messaging and other
getText()
methods return data from the original input string.This implementation duplicates the data buffer in an effort to improve performance (since calling
Character.toLowerCase(char)
is quite slow andLA(int)
is a performance-critical method). If memory overhead is more important than speed, thelookaheadData
buffer could be removed.