编译原理词法分析

import java.util.ArrayList;
import java.util.List;
public class Lexer {
public static List<Token> lexResult;
public static int Index;
public static String currLine;
public static Character ReadChar() {
    if (Index < currLine.length()) {
        char c = currLine.charAt(Index);
        return c;
    } else {
        return null;
    }
}
public static List<Token> analyzeFromCode(String code) {
        lexResult = new ArrayList();
        String[] lines = code.split("\\n");
        for(int i = 0; i < lines.length; ++i) {
            currLine = lines[i].replace("\r", "");
            analyzeFromLine();
        }
        lexResult.add(new Token(TokenType.EOF));
        return lexResult;
    }
    public static void analyzeFromLine() {
        while(ReadChar() != null) {
            if (ReadChar() >= '0' && ReadChar() <= '9') {
                extractNumberToken();
            } else if (ReadChar() == '+') {
                lexResult.add(new Token(TokenType.PLUS));
            } else if (ReadChar() == '-') {
                lexResult.add(new Token(TokenType.MINUS));
            } else if (ReadChar() == '*') {
                    lexResult.add(new Token(TokenType.MUL));
            } else if (ReadChar() == '/') {
                    lexResult.add(new Token(TokenType.DIV));
            } else if (ReadChar() == '%') {
                lexResult.add(new Token(TokenType.MODULAR));
            } else if (ReadChar() == '&') {
                lexResult.add(new Token(TokenType.AND));
            } else if (ReadChar() == '|') {
                lexResult.add(new Token(TokenType.OR));
            } else if (ReadChar() == '>') {
                if (ReadChar() == '=') {
                    lexResult.add(new Token(TokenType.COMP, ">="));
                } else {
                    lexResult.add(new Token(TokenType.COMP,  ">"));
                }
            } else if (ReadChar() == '<') {
                if (ReadChar() == '=') {
                    lexResult.add(new Token(TokenType.COMP, "<="));
                } else {
                    lexResult.add(new Token(TokenType.COMP,  "<"));
                }
            } else if (ReadChar() == '!') {
                if (ReadChar() == '=') {
                    lexResult.add(new Token(TokenType.COMP,"!="));
                } else {
                    lexResult.add(new Token(TokenType.NOT));
                }
            } else if (ReadChar() == '(') {
                lexResult.add(new Token(TokenType.LPAREN));
            } else if (ReadChar() == ')') {
                lexResult.add(new Token(TokenType.RPAREN));
            } else if (ReadChar() == '{') {
                lexResult.add(new Token(TokenType.LCB));
            } else if (ReadChar() == '}') {
                lexResult.add(new Token(TokenType.RCB));
            } else if (ReadChar() == '=') {
                if (ReadChar() != null && ReadChar() == '=') {
                    lexResult.add(new Token(TokenType.COMP));
                } else {
                    lexResult.add(new Token(TokenType.ASSIGN));
                }
            } else if (ReadChar() == '#') {
                lexResult.add(new Token(TokenType.DF));
            } else {
                StringBuilder buf;
                String st;
                    buf = new StringBuilder();
                    buf.append(ReadChar());
                    st = buf.toString();
                    if (st.equals("int")) {
                        lexResult.add(new Token(TokenType.KW));
                    } else if (st.equals("float")) {
                        lexResult.add(new Token(TokenType.KW));
                    } else if (st.equals("string")) {
                        lexResult.add(new Token(TokenType.KW));
                    } else if (st.equals("bool")) {
                        lexResult.add(new Token(TokenType.KW));
                    } else if (!st.equals("true") && !st.equals("false")) {
                        if (st.equals("print")) {
                            lexResult.add(new Token(TokenType.PRINT));
                        } else if (st.equals("fun")) {
                            lexResult.add(new Token(TokenType.FUN));
                        } else if (st.equals("if")) {
                            lexResult.add(new Token(TokenType.IF));
                        } else if (st.equals("else")) {
                            lexResult.add(new Token(TokenType.ELSE));
                        } else if (st.equals("while")) {
                            lexResult.add(new Token(TokenType.WHILE));
                        } else if (st.equals("break")) {
                            lexResult.add(new Token(TokenType.BREAK));
                        } else if (st.equals("continue")) {
                            lexResult.add(new Token(TokenType.CONTINUE));
                        } else if (st.equals("return")) {
                            lexResult.add(new Token(TokenType.RETURN));
                        } else if (st.equals("back")) {
                            lexResult.add(new Token(TokenType.BACK));
                        } else if (st.equals("readInt")) {
                            lexResult.add(new Token(TokenType.READINT));
                        } else if (st.equals("readFloat")) {
                            lexResult.add(new Token(TokenType.READFLOAT));
                        } else if (st.equals("readString")) {
                            lexResult.add(new Token(TokenType.READSTRING));
                        } else if (st.equals("readBool")) {
                            lexResult.add(new Token(TokenType.READBOOL));
                        } else {
                            lexResult.add(new Token(TokenType.ID,  st));
                        }
                    } else {
                        lexResult.add(new Token(TokenType.BOOLV, st));
                    }
            }
        }
    }
public static void extractNumberToken() {
        StringBuilder sb = new StringBuilder();
        int dotCount = 0;
        for(Character c = ReadChar(); c != null && (c >= '0' && c <= '9' || c == '.'); c = ReadChar()) {
            if (c == '.') {
                if (dotCount > 0) {
                    error("重复的小数点！");
                } else {
                    dotCount = 1;
                    sb.append(c);
                }
            } else {
                sb.append(c);
            }
        }
        if (ReadChar() != null && (ReadChar() >= 'a' && ReadChar() <= 'z' || ReadChar() >= 'A' && ReadChar() <= 'Z')) {
            error("非法的字符！");
        }
        if (dotCount == 0) {
            lexResult.add(new Token(TokenType.INT, sb.toString()));
        } else {
            lexResult.add(new Token(TokenType.FLOAT,  sb.toString()));
        }
    }
}