實現一個一遍掃描的編譯前端，將簡化高級語言的部分語法成分（含賦值語句、分支語句、循環語句等）翻譯成四元式（或三地址代碼），還要求有合理的語法出錯報錯和錯誤恢復功能。
測試樣例
beginwhile a<b doif c<5beginwhile x>ybeginz:=x+1;enda:=2; b:=4;c:=c-1;area:=3.14*a*a;s:=2*3.1416*r*(h+r);end
endend
#
測試結果
詞法分析程序
從文件中讀取程序
(1, begin)
(4, while)
(10, a)
(20, <)
(10, b)
(5, do)
(2, if)
(10, c)
(20, <)
(11, 5)
(1, begin)
(4, while)
(10, x)
(23, >)
(10, y)
(1, begin)
(10, z)
(18, :=)
(10, x)
(13, +)
(11, 1)
(26, ; )
(6, end)
(10, a)
(18, :=)
(11, 2)
(26, ; )
(10, b)
(18, :=)
(11, 4)
(26, ; )
(10, c)
(18, :=)
(10, c)
(14, -)
(11, 1)
(26, ; )
(10, area)
(18, :=)
(11, 3.14)
(15, *)
(10, a)
(15, *)
(10, a)
(26, ; )
(10, s)
(18, :=)
(11, 2)
(15, *)
(11, 3.1416)
(15, *)
(10, r)
(15, *)
(27, ()
(10, h)
(13, +)
(10, r)
(28, ))
(26, ; )
(6, end)
(6, end)
(6, end)
(0, #)
=詞法分析完成=
語法分析中…,請稍候
error!--------缺少開頭符號begin，程序第4行出現語法錯誤
error!--------不是符號then，程序第5行出現語法錯誤
error!--------不是符號do，程序第7行出現語法錯誤
=詞法分析完成=
語法分析完成，共檢查出3個語法錯誤
=中間代碼生成結果=
0:if a < b goto 2
1:goto 22
2:if c < 5 goto 4
3:goto 21
4:if x > y goto 6
5:goto 9
6:t1 = x + 1
7:z = t1
8:goto 4
9:a = 2
10:b = 4
11:t2 = c - 1
12:c = t2
13:t3 = 3.14 * a
14:t4 = t3 * a
15:area = t4
16:t5 = 2 * 3.1416
17:t6 = t5 * r
18:t7 = h + r
19:t8 = t6 * t7
20:s = t8
21:goto 0
語義分析
public class Element {String times;String data1;String op;String data2;String type;public void setInteger(Integer integer) {this.integer = integer;}Integer integer;Element(String times,String data1,String op,String data2) {//=this.times = times;this.data1 = data1;this.op = op;this.data2 = data2;}Element(String times,String data1,String op,String data2,Integer integer) {//if gotothis.times = times;this.data1 = data1;this.op = op;this.data2 = data2;this.integer=integer;}Element(Integer integer) {//if gotothis.integer=integer;}Element() {//if goto}
}
public class SemanticAnalysis {static int j=0,t=1;static List<Element> elements = new ArrayList<Element>();static void memset(String times,String data1,String op,String data2) {Element e = new Element(times,data1,op,data2);elements.add(e);}public static String expression() { // 表達式String times,data1,op,data2;data1 = term();while(analyzer.llist.get(j).equals("+") || analyzer.llist.get(j).equals("-")) {// 當前單詞為+、－if(analyzer.llist.get(j).equals("+")) // +op = "+";else // -op = "-";j++;data2 = term();times = "t" + (t++);memset(times,data1,op,data2);data1 = times;}return data1;}private static String term() { // 項String times,data1,op,data2;data1 = factor();while(analyzer.llist.get(j).equals("*") || analyzer.llist.get(j).equals("/") ) { // 當前單詞為*、/if(analyzer.llist.get(j).equals("*")) // *op = "*";else // /op = "/";j++;data2 = factor();times = "t" + (t++);memset(times,data1,op,data2);data1 = times;}return data1;}private static String factor() { // 因子String data = "";if(analyzer.map2.get(analyzer.llist.get(j)) == 10) { // IDdata = analyzer.llist.get(j);j++;} else if(analyzer.map2.get(analyzer.llist.get(j)) == 11) { // NUMdata = analyzer.llist.get(j);j++;}else if(analyzer.llist.get(j).equals("(")) { // 左括號j++;data = expression();if(analyzer.llist.get(j).equals(")"))j++;} else {System.out.println("Error,表達式錯誤");}return data;}}語法分析
public class GrammarAnalysis {static char[] s = new char[100];static int sing;static int i; //用來記錄數組s中的下標；static int error = 0;static void P() {if (Objects.equals(analyzer.llist.get(i), "begin")) {++i;int cur = analyzer.map.get(i);S();
//處理if (Objects.equals(analyzer.llist.get(i), "end")) {++i;} else {System.out.println("error!--------不是結尾符號end，" + "程序第" + analyzer.map.get(i) + "行出現語法錯誤");error++;++i;}} else {System.out.println("error!--------缺少開頭符號begin，" + "程序第" + analyzer.map.get(i) + "行出現語法錯誤");error++;S();
//處理if (Objects.equals(analyzer.llist.get(i), "end")) {++i;} else {System.out.println("error!--------不是結尾符號end，" + "程序第" + analyzer.map.get(i) + "行出現語法錯誤");error++;++i;}}}static void B() {i++;D();int cur = SemanticAnalysis.elements.size();SemanticAnalysis.elements.add(new Element());//thenif (!analyzer.llist.get(i).equals("then")) {System.out.println("error!--------不是符號then，" + "程序第" + analyzer.map.get(i) + "行出現語法錯誤");error++;} elsei++;P();SemanticAnalysis.elements.get(cur).setInteger(SemanticAnalysis.elements.size());//elsei--;}static void C() {i++;D();int cur = SemanticAnalysis.elements.size();SemanticAnalysis.elements.add(new Element());//doif (!analyzer.llist.get(i).equals("do")) {System.out.println("error!--------不是符號do，" + "程序第" + analyzer.map.get(i) + "行出現語法錯誤");error++;} elsei++;P();SemanticAnalysis.elements.add(new Element(cur - 1));SemanticAnalysis.elements.get(cur).setInteger(SemanticAnalysis.elements.size());i--;}static void D() {String data1, data2, op;SemanticAnalysis.j = i;;data1 = SemanticAnalysis.expression();//表達式E();op = analyzer.llist.get(i);//<|<=....i++;SemanticAnalysis.j = i;data2 = SemanticAnalysis.expression();//表達式SemanticAnalysis.elements.add(new Element("if", data1, op, data2, SemanticAnalysis.elements.size() + 2));E();}static void S() {if (analyzer.map2.get(analyzer.llist.get(i)) == 10)A();else if (analyzer.llist.get(i).equals("while"))C();else if (analyzer.llist.get(i).equals("if")) {B();}i++;S1();// if(s[i]!='e') {// }
/* if(Objects.equals(analyzer.llist.get(i), ";")) {}else {System.out.println("error!-----------缺少結尾符號;"+"，程序第"+analyzer.map.get(i)+"行出現語法錯誤");error++;++i;S1();}*/}static void S1() {if (i < analyzer.llist.size() && !Objects.equals(analyzer.llist.get(i), "end")) {// ++i;S();}}static void A() {if (i + 1 < analyzer.llist.size() && Objects.equals(analyzer.llist.get(i + 1), ":=")) {String times = analyzer.llist.get(i), data1;SemanticAnalysis.j = i;SemanticAnalysis.j += 2;data1 = SemanticAnalysis.expression();//表達式SemanticAnalysis.memset(times, data1, "", "");++i;++i;E();if (Objects.equals(analyzer.llist.get(i), ")") || Objects.equals(analyzer.llist.get(i), ";")) {if (Objects.equals(analyzer.llist.get(i), ")")) {++i;}} else {System.out.println("error!--------不是結尾符號；或者）" + "，程序第" + analyzer.map.get(i) + analyzer.llist.get(i) + "行出現語法錯誤");error++;++i;}} else {System.out.println("error!---------不是賦值語句" + "，程序第" + analyzer.map.get(i) + "行出現語法錯誤");error++;++i;++i;E();if (Objects.equals(analyzer.llist.get(i), ")") || Objects.equals(analyzer.llist.get(i), ";")) {if (Objects.equals(analyzer.llist.get(i), ")")) {++i;}} else {System.out.println("error!--------不是結尾符號；或者）" + "，程序第" + analyzer.map.get(i) + "行出現語法錯誤");error++;++i;}}}static void E() {T();/* if(Objects.equals(analyzer.llist.get(i), "+") || Objects.equals(analyzer.llist.get(i), "-") || Objects.equals(analyzer.llist.get(i), ";") || Objects.equals(analyzer.llist.get(i), ")")) {*/E1();/* }else {System.out.println("error!-----------不是結尾符號+或者-或者；或者）"+"，程序第"+analyzer.map.get(i)+"行出現語法錯誤"); error++;E1();}*/}static void T() {F();if (Objects.equals(analyzer.llist.get(i), "+") || Objects.equals(analyzer.llist.get(i), "-") || Objects.equals(analyzer.llist.get(i), ";") || Objects.equals(analyzer.llist.get(i), ")") || Objects.equals(analyzer.llist.get(i), "*") || Objects.equals(analyzer.llist.get(i), "/")) {T1();}}static void F() {if (Objects.equals(analyzer.llist.get(i), "(")) {++i;E();} else {++i;}}static void T1() {if (Objects.equals(analyzer.llist.get(i), "*")) {++i;F();T1();} else if (Objects.equals(analyzer.llist.get(i), "/")) {++i;F();T1();}}static void E1() {if (Objects.equals(analyzer.llist.get(i), "+")) {++i;T();E1();} else if (Objects.equals(analyzer.llist.get(i), "-")) {++i;T();E1();}}public static void main(String[] args) {Scanner sc = new Scanner(System.in);System.out.println("==詞法分析程序==");System.out.println("從文件中讀取程序");System.out.println("==============");analyzer.initToken();analyzer.ReadFile1();System.out.println("語法分析中....,請稍候");i = 0;sing = 0;if (Objects.equals(analyzer.llist.get(0), "#")) System.exit(-1);P();if (Objects.equals(analyzer.llist.get(i), "#")) {} else {System.out.println("error!-------不是結尾符號#" + analyzer.llist.get(i) + i);error++;}System.out.println("===詞法分析完成===");System.out.println("語法分析完成，共檢查出" + error + "個語法錯誤");System.out.println("\n===中間代碼生成結果===");for (int i = 0; i < SemanticAnalysis.elements.size(); i++) {Element e = SemanticAnalysis.elements.get(i);if (e.times == null)System.out.println(i + ":" + "goto " + e.integer);else if (e.times.equals("if"))System.out.println(i + ":" + e.times + " " + e.data1 + " " + e.op + " " + e.data2 + " goto " + e.integer);elseSystem.out.println(i + ":" + e.times + " = " + e.data1 + " " + e.op + " " + e.data2);}}}詞法分析
public class analyzer {public static List<String> llist=new ArrayList<>();static Map<Integer,Integer> map=new HashMap<>();static Map<String,Integer> map2=new HashMap<>();final static String ID = "\\p{Alpha}(\\p{Alpha}|\\d)*";static int countLine=1;/** 整形常數 NUM >> 正則表達式*/final static String NUM = "\\d\\d*";final static String regex = "^-?([1-9]\\d*\\.\\d*|0\\.\\d*[1-9]\\d*|0?\\.0+|0)$";/** token 詞法單元* <詞符號， 種別碼> *//** 關鍵字 token*/static Map<String, Integer> TOKEN_KEYWORDS;/** 運算符/界符 token */static Map<String, Integer> TOKEN_OPERATOR_BOUNDARY;/** 其他單詞 token*/static Map<String, Integer> TOKEN_ID_SUM;/** 文件根目錄*/static final String ROOT_DIRECTORY = "program.txt";/*** 初始化 token 單元*/public static void initToken(){//種別碼創建TOKEN_KEYWORDS = new HashMap<String, Integer>(){//關鍵字{put("begin", 1);put("if", 2);put("then", 3);put("while", 4);put("do", 5);put("end", 6);}};TOKEN_OPERATOR_BOUNDARY= new HashMap<String, Integer>(){//運算符和界符{put("+", 13);put("-", 14);put("*", 15);put("/", 16);put(":", 17);put(":=", 18);put("<", 20);put("<>", 21);put("<=", 22);put(">", 23);put(">=", 24);put("=", 25);put(";", 26);put("(", 27);put(")", 28);put("#", 0);}};TOKEN_ID_SUM= new HashMap<String, Integer>(){//標識符和整型常數{put(ID, 10);put(NUM, 11);}};}/*** 讀 源程序 文件*/public static void ReadFile1() {FileInputStream fis = null;InputStreamReader isr = null;BufferedReader br = null;try {fis = new FileInputStream(ROOT_DIRECTORY);isr = new InputStreamReader(fis, "UTF-8"); // 轉化類br = new BufferedReader(isr); // 裝飾類String line;/** 記錄 程序 行數 */while ((line = br.readLine()) != null) { // 每次讀取一行，分析一行boolean answer = lexicalAnalysis(line);if(answer == false){System.out.printf("ERROR 編譯錯誤=== 第 %d 行出現 詞法錯誤 \n", countLine);break;}countLine++;}System.out.printf("===詞法分析完成===\n");} catch (Exception ex) {ex.printStackTrace();} finally {try {br.close(); // 關閉最后一個類，會將所有的底層流都關閉} catch (Exception ex) {ex.printStackTrace();}}}/** 判斷key是否是其他單詞*/private static boolean isIDOrSUM(String key){if (key.matches(ID) ) {llist.add(key);map.put(llist.size()-1,countLine);map2.put(key,TOKEN_ID_SUM.get(ID));System.out.printf("(%d, %s)\n", TOKEN_ID_SUM.get(ID), key);}else if (key.matches(NUM)||key.matches(regex)) {llist.add(key);map.put(llist.size()-1,countLine);map2.put(key,TOKEN_ID_SUM.get(NUM));System.out.printf("(%d, %s)\n", TOKEN_ID_SUM.get(NUM), key);}else {return false;}return true;}/*** 進行 詞法分析* @param word 要分析的字符串* @return 結果*/public static boolean lexicalAnalysis(String word){word = word.trim(); // 去首尾空格String[] strings = word.split("\\p{Space}+"); // 分割字符串，保證處理的字符串沒有空格for (String string : strings) {/** 3種情況：* 1. 關鍵字 == end （關鍵字的后面一定是空格 ）* 2. 運算符/ 分界符 == continue* 3. 其他單詞 == continue*/String key = "";for (int i = 0; i < string.length(); i++){String indexChar = String.valueOf(string.charAt(i)) ;if(i+1<string.length()){if((indexChar+string.charAt(i+1)).equals("//"))return true;}/** 是 運算符 或者 關鍵字*/if (TOKEN_OPERATOR_BOUNDARY.containsKey(indexChar) ||TOKEN_KEYWORDS.containsKey(string.substring(i, string.length()))){if (key.length() > 0) {if (isIDOrSUM(key) == false) {/** 詞法錯誤 */return false;}key = "";}if(TOKEN_OPERATOR_BOUNDARY.containsKey(indexChar)) {/** 1. 是 運算符/分界符 */key += indexChar;if(i + 1 < string.length() && TOKEN_OPERATOR_BOUNDARY.containsKey(indexChar + string.charAt(i+1))){ // 運算分界符key += string.charAt(++i);}llist.add(key);map.put(llist.size()-1,countLine);map2.put(key,TOKEN_OPERATOR_BOUNDARY.get(key));System.out.printf("(%d, %s)\n",TOKEN_OPERATOR_BOUNDARY.get(key),key);key = "";}else if(TOKEN_KEYWORDS.containsKey(key = string.substring(i, string.length()))) {/** 2. 是關鍵字*/llist.add(key);map.put(llist.size()-1,countLine);map2.put(key,TOKEN_KEYWORDS.get(key));System.out.printf("(%d, %s)\n",TOKEN_KEYWORDS.get(key),key);key = "";break;}}else {/** 是其他單詞*/key += indexChar;/** 其他單詞后面是 1. 換行，2. 運算符/界符 3. 其他單詞*/if(i+1 >= string.length()){if (isIDOrSUM(key) == false) {/** 詞法錯誤 */return false;}}}}}return true;}public analyzer() {}public static void main(String[] args) {initToken();System.out.println("==詞法分析程序==");System.out.println("從文件中讀取程序");System.out.println("==============");ReadFile1(); for(String s:llist) System.out.println(s);System.out.println();}}
