mirror of
https://github.com/DanilaFe/abacus
synced 2024-12-23 07:50:09 -08:00
Move parsing code into TreeBuilder, change lexing and parsing algorithms
This commit is contained in:
parent
4eff4760e5
commit
7d822a3e77
|
@ -33,6 +33,7 @@ public class PluginManager {
|
|||
public PluginManager(){
|
||||
plugins = new ArrayList<>();
|
||||
cachedFunctions = new HashMap<>();
|
||||
cachedOperators = new HashMap<>();
|
||||
}
|
||||
|
||||
/**
|
||||
|
|
|
@ -95,13 +95,6 @@ public class OpNode extends TreeNode {
|
|||
String leftString = left != null ? left.toString() : "null";
|
||||
String rightString = right != null ? right.toString() : "null";
|
||||
|
||||
if(right != null && right instanceof OpNode){
|
||||
if(TreeNode.precedenceMap.get(((OpNode) right).getOperation()) >
|
||||
TreeNode.precedenceMap.get(operation)) {
|
||||
rightString = "(" + rightString + ")";
|
||||
}
|
||||
}
|
||||
|
||||
return leftString + operation + rightString;
|
||||
return "(" + leftString + operation + rightString + ")";
|
||||
}
|
||||
}
|
||||
|
|
|
@ -6,7 +6,8 @@ package org.nwapw.abacus.tree;
|
|||
*/
|
||||
public enum TokenType {
|
||||
|
||||
INTERNAL_FUNCTION_END(-1), INTERNAL_FUNCTION_START(-1), ANY(0), COMMA(1), OP(2), NUM(3), WORD(4), OPEN_PARENTH(5), CLOSE_PARENTH(6);
|
||||
INTERNAL_FUNCTION_END(-1),
|
||||
ANY(0), COMMA(1), OP(2), NUM(3), FUNCTION(4), OPEN_PARENTH(5), CLOSE_PARENTH(6);
|
||||
|
||||
/**
|
||||
* The priority by which this token gets sorted.
|
||||
|
|
142
src/org/nwapw/abacus/tree/TreeBuilder.java
Normal file
142
src/org/nwapw/abacus/tree/TreeBuilder.java
Normal file
|
@ -0,0 +1,142 @@
|
|||
package org.nwapw.abacus.tree;
|
||||
|
||||
import org.nwapw.abacus.function.OperatorAssociativity;
|
||||
import org.nwapw.abacus.lexing.Lexer;
|
||||
import org.nwapw.abacus.lexing.pattern.Match;
|
||||
import org.nwapw.abacus.plugin.PluginManager;
|
||||
|
||||
import java.util.*;
|
||||
|
||||
public class TreeBuilder {
|
||||
|
||||
private Lexer<TokenType> lexer;
|
||||
private HashMap<String, Integer> precedenceMap;
|
||||
private HashMap<String, OperatorAssociativity> associativityMap;
|
||||
|
||||
/**
|
||||
* Comparator used to sort token types.
|
||||
*/
|
||||
protected static Comparator<TokenType> tokenSorter = Comparator.comparingInt(e -> e.priority);
|
||||
|
||||
public TreeBuilder(){
|
||||
lexer = new Lexer<TokenType>(){{
|
||||
register(",", TokenType.COMMA);
|
||||
register("[0-9]+(\\.[0-9]+)?", TokenType.NUM);
|
||||
register("\\(", TokenType.OPEN_PARENTH);
|
||||
register("\\)", TokenType.CLOSE_PARENTH);
|
||||
}};
|
||||
precedenceMap = new HashMap<>();
|
||||
associativityMap = new HashMap<>();
|
||||
}
|
||||
|
||||
/**
|
||||
* Tokenizes a string, converting it into matches
|
||||
* @param string the string to tokenize.
|
||||
* @return the list of tokens produced.
|
||||
*/
|
||||
public ArrayList<Match<TokenType>> tokenize(String string){
|
||||
return lexer.lexAll(string, 0, tokenSorter);
|
||||
}
|
||||
|
||||
/**
|
||||
* Rearranges tokens into a postfix list, using Shunting Yard.
|
||||
* @param source the source string.
|
||||
* @param from the tokens to be rearranged.
|
||||
* @return the resulting list of rearranged tokens.
|
||||
*/
|
||||
public ArrayList<Match<TokenType>> intoPostfix(String source, ArrayList<Match<TokenType>> from){
|
||||
ArrayList<Match<TokenType>> output = new ArrayList<>();
|
||||
Stack<Match<TokenType>> tokenStack = new Stack<>();
|
||||
while(!from.isEmpty()){
|
||||
Match<TokenType> match = from.remove(0);
|
||||
TokenType matchType = match.getType();
|
||||
if(matchType == TokenType.NUM) {
|
||||
output.add(match);
|
||||
} else if(matchType == TokenType.FUNCTION) {
|
||||
output.add(new Match<>(0, 0, TokenType.INTERNAL_FUNCTION_END));
|
||||
tokenStack.push(match);
|
||||
} else if(matchType == TokenType.OP){
|
||||
String tokenString = source.substring(match.getFrom(), match.getTo());
|
||||
int precedence = precedenceMap.get(tokenString);
|
||||
OperatorAssociativity associativity = associativityMap.get(tokenString);
|
||||
|
||||
while(!tokenStack.empty()) {
|
||||
Match<TokenType> otherMatch = tokenStack.peek();
|
||||
TokenType otherMatchType = otherMatch.getType();
|
||||
if(otherMatchType != TokenType.OP) break;
|
||||
|
||||
int otherPrecdence = precedenceMap.get(source.substring(otherMatch.getFrom(), otherMatch.getTo()));
|
||||
if(otherPrecdence < precedence ||
|
||||
(associativity == OperatorAssociativity.RIGHT && otherPrecdence == precedence)) {
|
||||
break;
|
||||
}
|
||||
output.add(tokenStack.pop());
|
||||
}
|
||||
tokenStack.push(match);
|
||||
} else if(matchType == TokenType.OPEN_PARENTH){
|
||||
tokenStack.push(match);
|
||||
} else if(matchType == TokenType.CLOSE_PARENTH || matchType == TokenType.COMMA){
|
||||
while(!tokenStack.empty() && tokenStack.peek().getType() != TokenType.OPEN_PARENTH){
|
||||
output.add(tokenStack.pop());
|
||||
}
|
||||
if(tokenStack.empty()) return null;
|
||||
if(matchType == TokenType.CLOSE_PARENTH){
|
||||
tokenStack.pop();
|
||||
}
|
||||
}
|
||||
}
|
||||
while(!tokenStack.empty()){
|
||||
if(!(tokenStack.peek().getType() == TokenType.OP)) return null;
|
||||
output.add(tokenStack.pop());
|
||||
}
|
||||
return output;
|
||||
}
|
||||
|
||||
/**
|
||||
* Constructs a tree recursively from a list of tokens.
|
||||
* @param source the source string.
|
||||
* @param matches the list of tokens from the source string.
|
||||
* @return the construct tree expression.
|
||||
*/
|
||||
public TreeNode fromStringRecursive(String source, ArrayList<Match<TokenType>> matches){
|
||||
if(matches.size() == 0) return null;
|
||||
Match<TokenType> match = matches.remove(0);
|
||||
TokenType matchType = match.getType();
|
||||
if(matchType == TokenType.OP){
|
||||
TreeNode right = fromStringRecursive(source, matches);
|
||||
TreeNode left = fromStringRecursive(source, matches);
|
||||
if(left == null || right == null) return null;
|
||||
else return new OpNode(source.substring(match.getFrom(), match.getTo()), left, right);
|
||||
} else if(matchType == TokenType.NUM){
|
||||
return new NumberNode(Double.parseDouble(source.substring(match.getFrom(), match.getTo())));
|
||||
} else if(matchType == TokenType.FUNCTION){
|
||||
String functionName = source.substring(match.getFrom(), match.getTo());
|
||||
FunctionNode node = new FunctionNode(functionName);
|
||||
while(!matches.isEmpty() && matches.get(0).getType() != TokenType.INTERNAL_FUNCTION_END){
|
||||
TreeNode argument = fromStringRecursive(source, matches);
|
||||
if(argument == null) return null;
|
||||
node.addChild(argument);
|
||||
}
|
||||
if(matches.isEmpty()) return null;
|
||||
matches.remove(0);
|
||||
return node;
|
||||
}
|
||||
return null;
|
||||
}
|
||||
|
||||
/**
|
||||
* Creates a tree node from a string.
|
||||
* @param string the string to create a node from.
|
||||
* @return the resulting tree.
|
||||
*/
|
||||
public TreeNode fromString(String string){
|
||||
ArrayList<Match<TokenType>> matches = tokenize(string);
|
||||
if(matches == null) return null;
|
||||
matches = intoPostfix(string, matches);
|
||||
if(matches == null) return null;
|
||||
|
||||
Collections.reverse(matches);
|
||||
return fromStringRecursive(string, matches);
|
||||
}
|
||||
|
||||
}
|
|
@ -11,158 +11,6 @@ import java.util.*;
|
|||
*/
|
||||
public abstract class TreeNode {
|
||||
|
||||
/**
|
||||
* The lexer used to lex tokens.
|
||||
*/
|
||||
protected static Lexer<TokenType> lexer = new Lexer<TokenType>(){{
|
||||
register(",", TokenType.COMMA);
|
||||
register("\\+|-|\\*|/", TokenType.OP);
|
||||
register("[0-9]+(\\.[0-9]+)?", TokenType.NUM);
|
||||
register("[a-zA-Z]+", TokenType.WORD);
|
||||
register("\\(", TokenType.OPEN_PARENTH);
|
||||
register("\\)", TokenType.CLOSE_PARENTH);
|
||||
}};
|
||||
/**
|
||||
* A map that maps operations to their precedence.
|
||||
*/
|
||||
protected static HashMap<String, Integer> precedenceMap = new HashMap<String, Integer>(){{
|
||||
put("+", 0);
|
||||
put("-", 0);
|
||||
put("*", 1);
|
||||
put("/", 1);
|
||||
}};
|
||||
/**
|
||||
* A map that maps operations to their associativity.
|
||||
*/
|
||||
protected static HashMap<String, OperatorAssociativity> associativityMap =
|
||||
new HashMap<String, OperatorAssociativity>() {{
|
||||
put("+", OperatorAssociativity.LEFT);
|
||||
put("-", OperatorAssociativity.LEFT);
|
||||
put("*", OperatorAssociativity.LEFT);
|
||||
put("/", OperatorAssociativity.LEFT);
|
||||
}};
|
||||
|
||||
/**
|
||||
* Comparator used to sort token types.
|
||||
*/
|
||||
protected static Comparator<TokenType> tokenSorter = Comparator.comparingInt(e -> e.priority);
|
||||
|
||||
/**
|
||||
* Tokenizes a string, converting it into matches
|
||||
* @param string the string to tokenize.
|
||||
* @return the list of tokens produced.
|
||||
*/
|
||||
public static ArrayList<Match<TokenType>> tokenize(String string){
|
||||
return lexer.lexAll(string, 0, tokenSorter);
|
||||
}
|
||||
|
||||
/**
|
||||
* Rearranges tokens into a postfix list, using Shunting Yard.
|
||||
* @param source the source string.
|
||||
* @param from the tokens to be rearranged.
|
||||
* @return the resulting list of rearranged tokens.
|
||||
*/
|
||||
public static ArrayList<Match<TokenType>> intoPostfix(String source, ArrayList<Match<TokenType>> from){
|
||||
ArrayList<Match<TokenType>> output = new ArrayList<>();
|
||||
Stack<Match<TokenType>> tokenStack = new Stack<>();
|
||||
while(!from.isEmpty()){
|
||||
Match<TokenType> match = from.remove(0);
|
||||
TokenType matchType = match.getType();
|
||||
if(matchType == TokenType.NUM || matchType == TokenType.WORD) {
|
||||
output.add(match);
|
||||
} else if(matchType == TokenType.OP){
|
||||
String tokenString = source.substring(match.getFrom(), match.getTo());
|
||||
int precedence = precedenceMap.get(tokenString);
|
||||
OperatorAssociativity associativity = associativityMap.get(tokenString);
|
||||
|
||||
while(!tokenStack.empty()) {
|
||||
Match<TokenType> otherMatch = tokenStack.peek();
|
||||
if(otherMatch.getType() != TokenType.OP) break;
|
||||
|
||||
int otherPrecdence = precedenceMap.get(source.substring(otherMatch.getFrom(), otherMatch.getTo()));
|
||||
if(otherPrecdence < precedence ||
|
||||
(associativity == OperatorAssociativity.RIGHT && otherPrecdence == precedence)) {
|
||||
break;
|
||||
}
|
||||
output.add(tokenStack.pop());
|
||||
}
|
||||
tokenStack.push(match);
|
||||
} else if(matchType == TokenType.OPEN_PARENTH){
|
||||
if(!output.isEmpty() && output.get(output.size() - 1).getType() == TokenType.WORD){
|
||||
tokenStack.push(output.remove(output.size() - 1));
|
||||
output.add(new Match<>(0, 0, TokenType.INTERNAL_FUNCTION_END));
|
||||
}
|
||||
tokenStack.push(match);
|
||||
} else if(matchType == TokenType.CLOSE_PARENTH || matchType == TokenType.COMMA){
|
||||
while(!tokenStack.empty() && tokenStack.peek().getType() != TokenType.OPEN_PARENTH){
|
||||
output.add(tokenStack.pop());
|
||||
}
|
||||
if(tokenStack.empty()) return null;
|
||||
if(matchType == TokenType.CLOSE_PARENTH){
|
||||
tokenStack.pop();
|
||||
if(!tokenStack.empty() && tokenStack.peek().getType() == TokenType.WORD) {
|
||||
output.add(tokenStack.pop());
|
||||
output.add(new Match<>(0, 0, TokenType.INTERNAL_FUNCTION_START));
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
while(!tokenStack.empty()){
|
||||
if(!(tokenStack.peek().getType() == TokenType.OP)) return null;
|
||||
output.add(tokenStack.pop());
|
||||
}
|
||||
return output;
|
||||
}
|
||||
|
||||
/**
|
||||
* Constructs a tree recursively from a list of tokens.
|
||||
* @param source the source string.
|
||||
* @param matches the list of tokens from the source string.
|
||||
* @return the construct tree expression.
|
||||
*/
|
||||
public static TreeNode fromStringRecursive(String source, ArrayList<Match<TokenType>> matches){
|
||||
if(matches.size() == 0) return null;
|
||||
Match<TokenType> match = matches.remove(0);
|
||||
TokenType matchType = match.getType();
|
||||
if(matchType == TokenType.OP){
|
||||
TreeNode right = fromStringRecursive(source, matches);
|
||||
TreeNode left = fromStringRecursive(source, matches);
|
||||
if(left == null || right == null) return null;
|
||||
else return new OpNode(source.substring(match.getFrom(), match.getTo()), left, right);
|
||||
} else if(matchType == TokenType.NUM){
|
||||
return new NumberNode(Double.parseDouble(source.substring(match.getFrom(), match.getTo())));
|
||||
} else if(matchType == TokenType.INTERNAL_FUNCTION_START){
|
||||
if(matches.isEmpty() || matches.get(0).getType() != TokenType.WORD) return null;
|
||||
Match<TokenType> stringName = matches.remove(0);
|
||||
String functionName = source.substring(stringName.getFrom(), stringName.getTo());
|
||||
FunctionNode node = new FunctionNode(functionName);
|
||||
while(!matches.isEmpty() && matches.get(0).getType() != TokenType.INTERNAL_FUNCTION_END){
|
||||
TreeNode argument = fromStringRecursive(source, matches);
|
||||
if(argument == null) return null;
|
||||
node.addChild(argument);
|
||||
}
|
||||
if(matches.isEmpty()) return null;
|
||||
matches.remove(0);
|
||||
return node;
|
||||
}
|
||||
return null;
|
||||
}
|
||||
|
||||
/**
|
||||
* Creates a tree node from a string.
|
||||
* @param string the string to create a node from.
|
||||
* @return the resulting tree.
|
||||
*/
|
||||
public static TreeNode fromString(String string){
|
||||
ArrayList<Match<TokenType>> matches = tokenize(string);
|
||||
if(matches == null) return null;
|
||||
matches = intoPostfix(string, matches);
|
||||
if(matches == null) return null;
|
||||
|
||||
Collections.reverse(matches);
|
||||
return fromStringRecursive(string, matches);
|
||||
}
|
||||
|
||||
public abstract <T> T reduce(Reducer<T> reducer);
|
||||
|
||||
}
|
||||
|
|
|
@ -3,6 +3,7 @@ package org.nwapw.abacus.window;
|
|||
import org.nwapw.abacus.number.NumberInterface;
|
||||
import org.nwapw.abacus.plugin.PluginManager;
|
||||
import org.nwapw.abacus.tree.NumberReducer;
|
||||
import org.nwapw.abacus.tree.TreeBuilder;
|
||||
import org.nwapw.abacus.tree.TreeNode;
|
||||
|
||||
import javax.swing.*;
|
||||
|
@ -47,6 +48,10 @@ public class Window extends JFrame {
|
|||
* The plugin manager used to retrieve functions.
|
||||
*/
|
||||
private PluginManager manager;
|
||||
/**
|
||||
* The builder used to construct the parse trees.
|
||||
*/
|
||||
private TreeBuilder builder;
|
||||
/**
|
||||
* The reducer used to evaluate the tree.
|
||||
*/
|
||||
|
@ -123,7 +128,8 @@ public class Window extends JFrame {
|
|||
* Action listener that causes the input to be evaluated.
|
||||
*/
|
||||
private ActionListener evaluateListener = (event) -> {
|
||||
TreeNode parsedExpression = TreeNode.fromString(inputField.getText());
|
||||
TreeBuilder builder = new TreeBuilder();
|
||||
TreeNode parsedExpression = builder.fromString(inputField.getText());
|
||||
if(parsedExpression == null){
|
||||
lastOutputArea.setText(SYNTAX_ERR_STRING);
|
||||
return;
|
||||
|
|
Loading…
Reference in New Issue
Block a user