Turner/CS4308_CompilerProject
Archived
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Java now works thank God ;-;

Browse Source
This commit is contained in:
Jonathan Turner 2023-11-21 23:52:43 -05:00
parent b8d25b4d51
commit 78c8452874
7 changed files with 182 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
.idea/misc.xml
View File

@ -1,6 +1,6 @@
<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
<component name="ProjectRootManager" version="2" languageLevel="JDK_18" default="true" project-jdk-name="openjdk-18" project-jdk-type="JavaSDK">
<component name="ProjectRootManager" version="2" languageLevel="JDK_19" default="true" project-jdk-name="openjdk-18" project-jdk-type="JavaSDK">
<output url="file://$PROJECT_DIR$/out" />
</component>
</project>

3
src/LexicalAnalyzer.java
View File

@ -1,3 +0,0 @@
public class LexicalAnalyzer {
}

18
src/edu/jt_kb/cs4308/compiler/Driver.java
View File

@ -1,9 +1,15 @@
package edu.jt_kb.cs4308.compiler;
import edu.jt_kb.cs4308.compiler.FileManagement.FileReader;
import edu.jt_kb.cs4308.compiler.models.JavaSyntaxAnalyzer;
import edu.jt_kb.cs4308.compiler.models.Pair;
import edu.jt_kb.cs4308.compiler.models.TokenType;
import org.xml.sax.ext.LexicalHandler;
import java.io.File;
import java.sql.Array;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.List;
import java.util.Scanner;
@ -17,11 +23,17 @@ public class Driver {
public void start() {
File java = new File("src/edu/jt_kb/cs4308/compiler/resources/Java.txt");
File python = new File("src/edu/jt_kb/cs4308/compiler/resources/Python.txt");
List<String> code = new ArrayList<>();
JavaSyntaxAnalyzer analyzer = new JavaSyntaxAnalyzer();
code = FileReader.readFile(java);
System.out.println(code);
code = FileReader.readFile(python);
System.out.println(code);
List<Pair> analysis = analyzer.start(code);
for (Pair curr : analysis) {
if (curr.type != TokenType.EOF) {
System.out.println("Next token is: " + curr.type.value + " lexeme is " + curr.lexeme);
}
}
}

10
src/edu/jt_kb/cs4308/compiler/JavaSyntaxAnalyzer.java
View File

@ -1,10 +0,0 @@
package edu.jt_kb.cs4308.compiler;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.List;
public class JavaSyntaxAnalyzer {
List<String> KeyWords=new ArrayList<>(Arrays.asList("public","class","static","void","int"));
}

147
src/edu/jt_kb/cs4308/compiler/models/JavaSyntaxAnalyzer.java Normal file
View File

@ -0,0 +1,147 @@
package edu.jt_kb.cs4308.compiler.models;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.List;
public class JavaSyntaxAnalyzer {
public List<Pair> start(List<String> source) {
List<Pair> values = new ArrayList<>();
for (String line : source) {
List<Pair> result = readline(line);
values.addAll(result);
}
return values;
}
private List<Pair> readline(String line) {
List<Pair> analyzedLine = new ArrayList<>();
String active = line.trim();
Pair result = null;
do {
active = active.trim();
result = lex(active);
if (result != null) {
analyzedLine.add(result);
if (result.lexeme.length() > 1) {
active = active.replaceFirst(result.lexeme, "");
} else {
active = active.substring(1);
}
}
} while (result != null && result.type != TokenType.EOF);
return analyzedLine;
}
private Pair lex(String line) {
if (line == null || line.isEmpty()) {
return null;
}
char[] letters = line.toCharArray();
if (Character.isDigit(letters[0])) {
String lexeme = "";
int index = 0;
while (index < letters.length && Character.isDigit(letters[index])) {
lexeme += letters[index];
index++;
}
return new Pair(lexeme, TokenType.INT_LIT);
}
if (Character.isLetter(letters[0])) {
String lexeme = "";
int index = 0;
while (index < letters.length
&& (Character.isLetter(letters[index])
|| Character.isDigit(letters[index]))) {
lexeme += letters[index];
index++;
}
Pair lookup_result = lookup(lexeme);
if (lookup_result.type != TokenType.UNKNOWN) {
return lookup_result;
}
return new Pair(lexeme, TokenType.IDENT);
}
if (letters[0] == '"') {
String lexeme = "\"";
int index = 1;
while (index < letters.length) {
lexeme += letters[index];
if (letters[index] == '"') {
break;
}
index++;
}
return new Pair(lexeme, TokenType.STRING_LITERAL);
}
Pair temp = lookup(line.split(" ")[0]);
if (temp.type != TokenType.UNKNOWN) {
return temp;
}
return lookup(letters[0]);
}
public Pair lookup(char lexeme) {
TokenType token = null;
switch (lexeme) {
case '=':
token = TokenType.ASSIGN_OP;
break;
case '+':
token = TokenType.ADD_OP;
break;
case '-':
token = TokenType.SUB_OP;
break;
case '*':
token = TokenType.MULT_OP;
break;
case '/':
token = TokenType.DIV_OP;
break;
case ';':
token = TokenType.SEMI_COLON;
break;
case ',':
token = TokenType.COMMA;
break;
case '{':
token = TokenType.LEFT_CURLY;
break;
case '}':
token = TokenType.RIGHT_CURLY;
break;
case '(':
token = TokenType.LEFT_PAREN;
break;
case ')':
token = TokenType.RIGHT_PAREN;
break;
case '[':
token = TokenType.LEFT_SQUARE;
break;
case ']':
token = TokenType.RIGHT_SQUARE;
break;
case '$':
token = TokenType.EOF;
break;
default:
token = TokenType.UNKNOWN;
}
return new Pair(String.valueOf(lexeme), token);
}
private Pair lookup(String lexeme) {
TokenType token = null;
List<String> keywords = new ArrayList<>(Arrays.asList("public","class","static","void","int"));
if (keywords.contains(lexeme.trim())) {
token = TokenType.RESERVED_WORD;
} else {
token = TokenType.UNKNOWN;
}
return new Pair(lexeme, token);
}
}

17
src/edu/jt_kb/cs4308/compiler/models/Pair.java Normal file
View File

@ -0,0 +1,17 @@
package edu.jt_kb.cs4308.compiler.models;
public class Pair {
public String lexeme;
public TokenType type;
public Pair (String lexeme, TokenType type) {
this.lexeme = lexeme;
this.type = type;
}
@Override
public String toString() {
return lexeme + " : " + type;
}
}

3
src/edu/jt_kb/cs4308/compiler/models/TokenType.java
View File

@ -3,7 +3,8 @@ package edu.jt_kb.cs4308.compiler.models;
public enum TokenType {
INT_LIT(10),IDENT(11),ASSIGN_OP(20),ADD_OP(21),SUB_OP(22),MULT_OP(23),
DIV_OP(24),LEFT_PAREN(26),RIGHT_PAREN(27),SEMI_COLON(28), STRING_LITERAL(29),
COMMA(30), LEFT_CURLY(31), RIGHT_CURLY(32), LEFT_SQUARE(33), RIGHT_SQUARE(34);
COMMA(30), LEFT_CURLY(31), RIGHT_CURLY(32), LEFT_SQUARE(33), RIGHT_SQUARE(34),
RESERVED_WORD(35),EOF(-1),UNKNOWN(-2);
public final int value; /* represents which Token you are referencing. */