1
0
mirror of https://github.com/DanilaFe/abacus synced 2024-12-22 15:30:09 -08:00

Implement a lexer.

This commit is contained in:
Danila Fedorin 2017-07-24 20:47:25 -07:00
parent 43c3d5f754
commit c86e192d2e
2 changed files with 96 additions and 0 deletions

View File

@ -0,0 +1,70 @@
package org.nwapw.abacus.lexing;
import org.nwapw.abacus.lexing.pattern.EndNode;
import org.nwapw.abacus.lexing.pattern.Match;
import org.nwapw.abacus.lexing.pattern.Pattern;
import org.nwapw.abacus.lexing.pattern.PatternNode;
import java.util.ArrayList;
import java.util.Collections;
import java.util.Comparator;
import java.util.HashSet;
public class Lexer<T> {
private ArrayList<Pattern<T>> patterns;
public Lexer(){
patterns = new ArrayList<>();
}
public void register(String pattern, T id){
Pattern<T> compiledPattern = new Pattern<>(pattern, id);
if(compiledPattern.getHead() != null) patterns.add(compiledPattern);
}
public Match<T> lexOne(String from, int startAt, Comparator<T> compare){
ArrayList<Match<T>> matches = new ArrayList<>();
HashSet<PatternNode<T>> currentSet = new HashSet<>();
HashSet<PatternNode<T>> futureSet = new HashSet<>();
int index = startAt;
for(Pattern<T> pattern : patterns){
pattern.getHead().addInto(currentSet);
}
while(!currentSet.isEmpty() && index < from.length()){
char currentChar = from.charAt(index);
for(PatternNode<T> node : currentSet){
if(node.matches(currentChar)) {
node.addOutputsInto(futureSet);
} else if(node instanceof EndNode){
matches.add(new Match<>(startAt, index, ((EndNode<T>) node).getPatternId()));
}
}
HashSet<PatternNode<T>> tmp = currentSet;
currentSet = futureSet;
futureSet = tmp;
futureSet.clear();
index++;
}
matches.sort((a, b) -> compare.compare(a.getType(), b.getType()));
if(compare != null) {
matches.sort(Comparator.comparingInt(a -> a.getTo() - a.getFrom()));
}
return matches.isEmpty() ? null : matches.get(matches.size() - 1);
}
public ArrayList<Match<T>> lexAll(String from, int startAt, Comparator<T> compare){
int index = startAt;
ArrayList<Match<T>> matches = new ArrayList<>();
Match<T> lastMatch = null;
while((lastMatch = lexOne(from, index, compare)) != null && index < from.length()){
if(lastMatch.getTo() == lastMatch.getFrom()) return null;
matches.add(lastMatch);
index += lastMatch.getTo() - lastMatch.getFrom();
}
return matches;
}
}

View File

@ -0,0 +1,26 @@
package org.nwapw.abacus.lexing.pattern;
public class Match<T> {
private int from;
private int to;
private T type;
public Match(int from, int to, T type){
this.from = from;
this.to = to;
this.type = type;
}
public int getFrom() {
return from;
}
public int getTo() {
return to;
}
public T getType() {
return type;
}
}