Merge pull request #1748 from parrt/rm-xpath-grammar
Fixes #1620. Make handbuilt lexer to avoid cyclic dependence of tool and plugin.
This commit is contained in:
Terence Parr
GitHub
commit
9bf3946515
|
|
@ -1,63 +0,0 @@
|
|||
lexer grammar XPathLexer;
|
||||
|
||||
tokens { TOKEN_REF, RULE_REF }
|
||||
|
||||
/*
|
||||
path : separator? word (separator word)* EOF ;
|
||||
|
||||
separator
|
||||
: '/' '!'
|
||||
| '//' '!'
|
||||
| '/'
|
||||
| '//'
|
||||
;
|
||||
|
||||
word: TOKEN_REF
|
||||
| RULE_REF
|
||||
| STRING
|
||||
| '*'
|
||||
;
|
||||
*/
|
||||
|
||||
ANYWHERE : '//' ;
|
||||
ROOT : '/' ;
|
||||
WILDCARD : '*' ;
|
||||
BANG : '!' ;
|
||||
|
||||
ID : NameStartChar NameChar*
|
||||
{
|
||||
String text = getText();
|
||||
if ( Character.isUpperCase(text.charAt(0)) ) setType(TOKEN_REF);
|
||||
else setType(RULE_REF);
|
||||
}
|
||||
;
|
||||
|
||||
fragment
|
||||
NameChar : NameStartChar
|
||||
| '0'..'9'
|
||||
| '_'
|
||||
| '\u00B7'
|
||||
| '\u0300'..'\u036F'
|
||||
| '\u203F'..'\u2040'
|
||||
;
|
||||
|
||||
fragment
|
||||
NameStartChar
|
||||
: 'A'..'Z' | 'a'..'z'
|
||||
| '\u00C0'..'\u00D6'
|
||||
| '\u00D8'..'\u00F6'
|
||||
| '\u00F8'..'\u02FF'
|
||||
| '\u0370'..'\u037D'
|
||||
| '\u037F'..'\u1FFF'
|
||||
| '\u200C'..'\u200D'
|
||||
| '\u2070'..'\u218F'
|
||||
| '\u2C00'..'\u2FEF'
|
||||
| '\u3001'..'\uD7FF'
|
||||
| '\uF900'..'\uFDCF'
|
||||
| '\uFDF0'..'\uFFFD'
|
||||
; // ignores | ['\u10000-'\uEFFFF] ;
|
||||
|
||||
STRING : '\'' .*? '\'' ;
|
||||
|
||||
//WS : [ \t\r\n]+ -> skip ;
|
||||
|
||||
|
|
@ -0,0 +1,179 @@
|
|||
/*
|
||||
* Copyright (c) 2012-2016 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.runtime.tree.xpath;
|
||||
|
||||
import org.antlr.v4.runtime.CharStream;
|
||||
import org.antlr.v4.runtime.CommonToken;
|
||||
import org.antlr.v4.runtime.Lexer;
|
||||
import org.antlr.v4.runtime.LexerNoViableAltException;
|
||||
import org.antlr.v4.runtime.Token;
|
||||
import org.antlr.v4.runtime.Vocabulary;
|
||||
import org.antlr.v4.runtime.VocabularyImpl;
|
||||
import org.antlr.v4.runtime.atn.ATN;
|
||||
import org.antlr.v4.runtime.misc.Interval;
|
||||
|
||||
/** Mimic the old XPathLexer from .g4 file */
|
||||
public class XPathLexer extends Lexer {
|
||||
public static final int
|
||||
TOKEN_REF=1, RULE_REF=2, ANYWHERE=3, ROOT=4, WILDCARD=5, BANG=6, ID=7,
|
||||
STRING=8;
|
||||
public static String[] modeNames = {
|
||||
"DEFAULT_MODE"
|
||||
};
|
||||
|
||||
public static final String[] ruleNames = {
|
||||
"ANYWHERE", "ROOT", "WILDCARD", "BANG", "ID", "NameChar", "NameStartChar",
|
||||
"STRING"
|
||||
};
|
||||
|
||||
private static final String[] _LITERAL_NAMES = {
|
||||
null, null, null, "'//'", "'/'", "'*'", "'!'"
|
||||
};
|
||||
private static final String[] _SYMBOLIC_NAMES = {
|
||||
null, "TOKEN_REF", "RULE_REF", "ANYWHERE", "ROOT", "WILDCARD", "BANG",
|
||||
"ID", "STRING"
|
||||
};
|
||||
public static final Vocabulary VOCABULARY = new VocabularyImpl(_LITERAL_NAMES, _SYMBOLIC_NAMES);
|
||||
|
||||
/**
|
||||
* @deprecated Use {@link #VOCABULARY} instead.
|
||||
*/
|
||||
@Deprecated
|
||||
public static final String[] tokenNames;
|
||||
static {
|
||||
tokenNames = new String[_SYMBOLIC_NAMES.length];
|
||||
for (int i = 0; i < tokenNames.length; i++) {
|
||||
tokenNames[i] = VOCABULARY.getLiteralName(i);
|
||||
if (tokenNames[i] == null) {
|
||||
tokenNames[i] = VOCABULARY.getSymbolicName(i);
|
||||
}
|
||||
|
||||
if (tokenNames[i] == null) {
|
||||
tokenNames[i] = "<INVALID>";
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@Override
|
||||
public String getGrammarFileName() { return "XPathLexer.g4"; }
|
||||
|
||||
@Override
|
||||
public String[] getRuleNames() { return ruleNames; }
|
||||
|
||||
@Override
|
||||
public String[] getModeNames() { return modeNames; }
|
||||
|
||||
@Override
|
||||
@Deprecated
|
||||
public String[] getTokenNames() {
|
||||
return tokenNames;
|
||||
}
|
||||
|
||||
@Override
|
||||
public Vocabulary getVocabulary() {
|
||||
return VOCABULARY;
|
||||
}
|
||||
|
||||
@Override
|
||||
public ATN getATN() {
|
||||
return null;
|
||||
}
|
||||
|
||||
protected int line = 1;
|
||||
protected int charPositionInLine = 0;
|
||||
|
||||
public XPathLexer(CharStream input) {
|
||||
super(input);
|
||||
}
|
||||
|
||||
@Override
|
||||
public Token nextToken() {
|
||||
_tokenStartCharIndex = _input.index();
|
||||
CommonToken t = null;
|
||||
while ( t==null ) {
|
||||
switch ( _input.LA(1) ) {
|
||||
case '/':
|
||||
consume();
|
||||
if ( _input.LA(1)=='/' ) {
|
||||
consume();
|
||||
t = new CommonToken(ANYWHERE, "//");
|
||||
}
|
||||
else {
|
||||
t = new CommonToken(ROOT, "/");
|
||||
}
|
||||
break;
|
||||
case '*':
|
||||
consume();
|
||||
t = new CommonToken(WILDCARD, "*");
|
||||
break;
|
||||
case '!':
|
||||
consume();
|
||||
t = new CommonToken(BANG, "!");
|
||||
break;
|
||||
case '\'':
|
||||
String s = matchString();
|
||||
t = new CommonToken(STRING, s);
|
||||
break;
|
||||
case CharStream.EOF :
|
||||
return new CommonToken(EOF, "<EOF>");
|
||||
default:
|
||||
if ( isNameStartChar(_input.LA(1)) ) {
|
||||
String id = matchID();
|
||||
if ( Character.isUpperCase(id.charAt(0)) ) t = new CommonToken(TOKEN_REF, id);
|
||||
else t = new CommonToken(RULE_REF, id);
|
||||
}
|
||||
else {
|
||||
throw new LexerNoViableAltException(this, _input, _tokenStartCharIndex, null);
|
||||
}
|
||||
break;
|
||||
}
|
||||
}
|
||||
t.setStartIndex(_tokenStartCharIndex);
|
||||
t.setCharPositionInLine(_tokenStartCharIndex);
|
||||
t.setLine(line);
|
||||
return t;
|
||||
}
|
||||
|
||||
public void consume() {
|
||||
int curChar = _input.LA(1);
|
||||
if ( curChar=='\n' ) {
|
||||
line++;
|
||||
charPositionInLine=0;
|
||||
}
|
||||
else {
|
||||
charPositionInLine++;
|
||||
}
|
||||
_input.consume();
|
||||
}
|
||||
|
||||
@Override
|
||||
public int getCharPositionInLine() {
|
||||
return charPositionInLine;
|
||||
}
|
||||
|
||||
public String matchID() {
|
||||
int start = _input.index();
|
||||
consume(); // drop start char
|
||||
while ( isNameChar(_input.LA(1)) ) {
|
||||
consume();
|
||||
}
|
||||
return _input.getText(Interval.of(start,_input.index()-1));
|
||||
}
|
||||
|
||||
public String matchString() {
|
||||
int start = _input.index();
|
||||
consume(); // drop first quote
|
||||
while ( _input.LA(1)!='\'' ) {
|
||||
consume();
|
||||
}
|
||||
consume(); // drop last quote
|
||||
return _input.getText(Interval.of(start,_input.index()-1));
|
||||
}
|
||||
|
||||
public boolean isNameChar(int c) { return Character.isUnicodeIdentifierPart(c); }
|
||||
|
||||
public boolean isNameStartChar(int c) { return Character.isUnicodeIdentifierStart(c); }
|
||||
}
|
||||
Loading…
Reference in New Issue