Parsing 使用ANTLR的DSL代码替换
我正在使用的DSL允许用户定义一个“完全文本替换”变量。在解析代码时,我们需要查找变量的值,然后再次从该代码开始解析 替换可以是非常简单的(单个常量)或整个语句或代码块。 这是一个模拟语法,我希望能说明我的观点Parsing 使用ANTLR的DSL代码替换,parsing,antlr,interpreter,antlr4,lexer,Parsing,Antlr,Interpreter,Antlr4,Lexer,我正在使用的DSL允许用户定义一个“完全文本替换”变量。在解析代码时,我们需要查找变量的值,然后再次从该代码开始解析 替换可以是非常简单的(单个常量)或整个语句或代码块。 这是一个模拟语法,我希望能说明我的观点 grammar a; entry : (set_variable | print_line)* ; set_variable : 'SET' ID '=' STRING_CONSTANT ';' ; print_line : 'PRINT' ID ';'
grammar a;
entry
: (set_variable
| print_line)*
;
set_variable
: 'SET' ID '=' STRING_CONSTANT ';'
;
print_line
: 'PRINT' ID ';'
;
STRING_CONSTANT: '\'' ('\'\'' | ~('\''))* '\'' ;
ID: [a-z][a-zA-Z0-9_]* ;
VARIABLE: '&' ID;
BLANK: [ \t\n\r]+ -> channel(HIDDEN) ;
然后,连续执行的以下语句应有效
SET foo = 'Hello world!';
PRINT foo;
SET bar = 'foo;'
PRINT &bar // should be interpreted as 'PRINT foo;'
SET baz = 'PRINT foo; PRINT'; // one complete statement and one incomplete statement
&baz foo; // should be interpreted as 'PRINT foo; PRINT foo;'
无论何时发现&variable标记,我们都会立即转而解释该变量的值。如上所述,这可能意味着您设置代码的方式是无效的,充满了只有在值恰好正确时才完成的半语句。变量可以在文本中的任意点重新定义
严格地说,当前的语言定义不允许嵌套和变量在彼此内部,但是当前的解析不能处理这个问题,如果不允许的话,我也不会感到不安
目前,我正在使用访问者构建一个口译员,但这一个我被卡住了
我如何构建一个lexer/解析器/解释器来实现这一点?谢谢你的帮助 处理需求的标准模式是实现符号表。最简单的形式是键:值存储。在访问者中,添加遇到的var声明,并在遇到var引用时读取值 如上所述,DSL没有对声明的变量定义范围要求。如果您确实需要作用域变量,那么就使用一堆key:value存储,在作用域入口和出口上推送和弹出 看这个相关的 另外,由于字符串可能包含命令,因此可以简单地将内容作为初始解析的一部分进行解析。也就是说,使用包含全套有效内容的规则扩展语法:
set_variable
: 'SET' ID '=' stringLiteral ';'
;
stringLiteral:
Quote Quote? (
( set_variable
| print_line
| VARIABLE
| ID
)
| STRING_CONSTANT // redefine without the quotes
)
Quote
;
所以我找到了一个解决这个问题的办法。我认为它可能会更好,因为它可能会进行大量的数组复制,但至少目前它还可以工作 编辑:我以前是错的,我的解决方案将使用它找到的任何&包括那些位于有效位置(如字符串常量内部)的。这似乎是一个更好的解决方案: 首先,我扩展了InputStream,以便在遇到&时能够重写输入流。不幸的是,这涉及到复制阵列,我将来可能会解决这一问题: MacroInputStream.java
package preprocessor;
import org.antlr.v4.runtime.ANTLRInputStream;
public class MacroInputStream extends ANTLRInputStream {
private HashMap<String, String> map;
public MacroInputStream(String s, HashMap<String, String> map) {
super(s);
this.map = map;
}
public void rewrite(int startIndex, int stopIndex, String replaceText) {
int length = stopIndex-startIndex+1;
char[] replData = replaceText.toCharArray();
if (replData.length == length) {
for (int i = 0; i < length; i++) data[startIndex+i] = replData[i];
} else {
char[] newData = new char[data.length+replData.length-length];
System.arraycopy(data, 0, newData, 0, startIndex);
System.arraycopy(replData, 0, newData, startIndex, replData.length);
System.arraycopy(data, stopIndex+1, newData, startIndex+replData.length, data.length-(stopIndex+1));
data = newData;
n = data.length;
}
}
}
package language;
import language.DSL_GrammarLexer;
import org.antlr.v4.runtime.Token;
import java.util.HashMap;
public class MacroGrammarLexer extends MacroGrammarLexer{
private HashMap<String, String> map;
public DSL_GrammarLexerPre(MacroInputStream input, HashMap<String, String> map) {
super(input);
this.map = map;
// TODO Auto-generated constructor stub
}
private MacroInputStream getInput() {
return (MacroInputStream) _input;
}
@Override
public Token nextToken() {
Token t = super.nextToken();
if (t.getType() == VARIABLE) {
System.out.println("Encountered token " + t.getText()+" ===> rewriting!!!");
getInput().rewrite(t.getStartIndex(), t.getStopIndex(),
map.get(t.getText().substring(1)));
getInput().seek(t.getStartIndex()); // reset input stream to previous
return super.nextToken();
}
return t;
}
}
...
...
HashMap<String, String> map; // same map as before, passed as a new argument.
...
...
public final SetContext set() throws RecognitionException {
SetContext _localctx = new SetContext(_ctx, getState());
enterRule(_localctx, 130, RULE_set);
try {
enterOuterAlt(_localctx, 1);
{
String vname = null; String vval = null; // set up variables
setState(1215); match(SET);
setState(1216); vname = variable_name().getText(); // set vname
setState(1217); match(EQUALS);
setState(1218); vval = string_constant().getText(); // set vval
System.out.println("Found SET " + vname +" = " + vval+";");
map.put(vname, vval);
}
}
catch (RecognitionException re) {
_localctx.exception = re;
_errHandler.reportError(this, re);
_errHandler.recover(this, re);
}
finally {
exitRule();
}
return _localctx;
}
...
...
包预处理器;
导入org.antlr.v4.runtime.antlInputStream;
公共类MacroInputStream扩展了AntlInputStream{
私有哈希映射;
公共宏输入流(字符串s、哈希映射){
超级(s);
this.map=map;
}
公共void重写(int startIndex、int stopIndex、String replaceText){
int length=stopIndex startIndex+1;
char[]replData=replaceText.toCharArray();
if(replData.length==长度){
对于(int i=0;i
其次,我扩展了Lexer,以便在遇到变量令牌时,调用上面的重写方法:
宏语法EXER.java
package preprocessor;
import org.antlr.v4.runtime.ANTLRInputStream;
public class MacroInputStream extends ANTLRInputStream {
private HashMap<String, String> map;
public MacroInputStream(String s, HashMap<String, String> map) {
super(s);
this.map = map;
}
public void rewrite(int startIndex, int stopIndex, String replaceText) {
int length = stopIndex-startIndex+1;
char[] replData = replaceText.toCharArray();
if (replData.length == length) {
for (int i = 0; i < length; i++) data[startIndex+i] = replData[i];
} else {
char[] newData = new char[data.length+replData.length-length];
System.arraycopy(data, 0, newData, 0, startIndex);
System.arraycopy(replData, 0, newData, startIndex, replData.length);
System.arraycopy(data, stopIndex+1, newData, startIndex+replData.length, data.length-(stopIndex+1));
data = newData;
n = data.length;
}
}
}
package language;
import language.DSL_GrammarLexer;
import org.antlr.v4.runtime.Token;
import java.util.HashMap;
public class MacroGrammarLexer extends MacroGrammarLexer{
private HashMap<String, String> map;
public DSL_GrammarLexerPre(MacroInputStream input, HashMap<String, String> map) {
super(input);
this.map = map;
// TODO Auto-generated constructor stub
}
private MacroInputStream getInput() {
return (MacroInputStream) _input;
}
@Override
public Token nextToken() {
Token t = super.nextToken();
if (t.getType() == VARIABLE) {
System.out.println("Encountered token " + t.getText()+" ===> rewriting!!!");
getInput().rewrite(t.getStartIndex(), t.getStopIndex(),
map.get(t.getText().substring(1)));
getInput().seek(t.getStartIndex()); // reset input stream to previous
return super.nextToken();
}
return t;
}
}
...
...
HashMap<String, String> map; // same map as before, passed as a new argument.
...
...
public final SetContext set() throws RecognitionException {
SetContext _localctx = new SetContext(_ctx, getState());
enterRule(_localctx, 130, RULE_set);
try {
enterOuterAlt(_localctx, 1);
{
String vname = null; String vval = null; // set up variables
setState(1215); match(SET);
setState(1216); vname = variable_name().getText(); // set vname
setState(1217); match(EQUALS);
setState(1218); vval = string_constant().getText(); // set vval
System.out.println("Found SET " + vname +" = " + vval+";");
map.put(vname, vval);
}
}
catch (RecognitionException re) {
_localctx.exception = re;
_errHandler.reportError(this, re);
_errHandler.recover(this, re);
}
finally {
exitRule();
}
return _localctx;
}
...
...
包语言;
import language.DSL_GrammarLexer;
导入org.antlr.v4.runtime.Token;
导入java.util.HashMap;
公共类MacroGrammarLexer扩展了MacroGrammarLexer{
私有哈希映射;
公共DSL_GrammarPre(宏输入流输入,HashMap映射){
超级(输入);
this.map=map;
//TODO自动生成的构造函数存根
}
私有宏输入流getInput(){
返回(宏输入流)\ u输入;
}
@凌驾
公共令牌nextToken(){
令牌t=super.nextToken();
if(t.getType()==变量){
System.out.println(“遇到的令牌”+t.getText()+“=>重写!!!”;
getInput().rewrite(t.getStartIndex(),t.getStopIndex(),
get(t.getText().substring(1));
getInput().seek(t.getStartIndex());//将输入流重置为上一个
返回super.nextToken();
}
返回t;
}
}
最后,我修改了生成的解析器,以便在解析时设置变量:
DSL\u GrammarParser.java
package preprocessor;
import org.antlr.v4.runtime.ANTLRInputStream;
public class MacroInputStream extends ANTLRInputStream {
private HashMap<String, String> map;
public MacroInputStream(String s, HashMap<String, String> map) {
super(s);
this.map = map;
}
public void rewrite(int startIndex, int stopIndex, String replaceText) {
int length = stopIndex-startIndex+1;
char[] replData = replaceText.toCharArray();
if (replData.length == length) {
for (int i = 0; i < length; i++) data[startIndex+i] = replData[i];
} else {
char[] newData = new char[data.length+replData.length-length];
System.arraycopy(data, 0, newData, 0, startIndex);
System.arraycopy(replData, 0, newData, startIndex, replData.length);
System.arraycopy(data, stopIndex+1, newData, startIndex+replData.length, data.length-(stopIndex+1));
data = newData;
n = data.length;
}
}
}
package language;
import language.DSL_GrammarLexer;
import org.antlr.v4.runtime.Token;
import java.util.HashMap;
public class MacroGrammarLexer extends MacroGrammarLexer{
private HashMap<String, String> map;
public DSL_GrammarLexerPre(MacroInputStream input, HashMap<String, String> map) {
super(input);
this.map = map;
// TODO Auto-generated constructor stub
}
private MacroInputStream getInput() {
return (MacroInputStream) _input;
}
@Override
public Token nextToken() {
Token t = super.nextToken();
if (t.getType() == VARIABLE) {
System.out.println("Encountered token " + t.getText()+" ===> rewriting!!!");
getInput().rewrite(t.getStartIndex(), t.getStopIndex(),
map.get(t.getText().substring(1)));
getInput().seek(t.getStartIndex()); // reset input stream to previous
return super.nextToken();
}
return t;
}
}
...
...
HashMap<String, String> map; // same map as before, passed as a new argument.
...
...
public final SetContext set() throws RecognitionException {
SetContext _localctx = new SetContext(_ctx, getState());
enterRule(_localctx, 130, RULE_set);
try {
enterOuterAlt(_localctx, 1);
{
String vname = null; String vval = null; // set up variables
setState(1215); match(SET);
setState(1216); vname = variable_name().getText(); // set vname
setState(1217); match(EQUALS);
setState(1218); vval = string_constant().getText(); // set vval
System.out.println("Found SET " + vname +" = " + vval+";");
map.put(vname, vval);
}
}
catch (RecognitionException re) {
_localctx.exception = re;
_errHandler.reportError(this, re);
_errHandler.recover(this, re);
}
finally {
exitRule();
}
return _localctx;
}
...
...
。。。
...
HashMap映射;//与以前相同的映射,作为新参数传递。
...
...
public final SetContext set()引发识别异常{
SetContext _localctx=新的SetContext(_ctx,getState());
enterRule(_localctx,130,RULE\u set);
试一试{
肠子宫盐(_localctx,1);
{
String vname=null;String vval=null;//设置变量
设置状态(1215);匹配(设置);
setState(1216);vname=variable_name().getText();//设置vname
设置状态(1217);匹配(等于);
setState(1218);vval=string_constant().getText();//设置vval
System.out.println(“发现集”+vname+“=”+vval+“;”);
map.put(vname,vval);
}
}
捕获(识别异常re){
_localctx.exception=re;
_errHandler.reportError(此,re);
_errHandler.recover(此,re);
}
最后{
出口();
}
返回_localctx;
}
...
...
不幸的是,这种方法是
最终的
,因此这将使维护变得更加困难,但目前它仍然有效 在你的语法中要说明这是一种卑鄙的诡计。单个条目中可以出现变量的位置和数量是否有任何限制?我是说,是吗