遞歸下降語法分析
1. 語法成分說明
<語句塊> ::= begin<語句串> end
<語句串> ::= <語句>{;<語句>}
<語句> ::= <賦值語句> | <循環語句> | <條件語句>
<關系運算符> ::= < | <= | >= | > | == | !=
<賦值語句> ::= ID:=<表達式>
<表達式> ::= <項>{+<項> | -<項> }
<項> ::= <因子>{*<因子> | /<因子> }
<因子> ::= ID | NUM | <表達式>
2. 相應的上下文無關文法
*P — > begin S end
S — >A S1 | B S1 | C S1
S1— >S | ε
R — > < | <= | >= | > | == | !=
A — >I:=E;
E— >T E1
E1— >+TE1 | -TE1 | ε
T— >F T1
T1— >FT1 | /FT1 | ε
F — > (E) | I
測試樣例
i:=5+i*(i/3-i);
i:=i+i;
end
#
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;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 S() {A();if(Objects.equals(analyzer.llist.get(i), ";")) {++i;// if(s[i]!='e') {S1();// }}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(!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), ":=")) {++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;}}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("共檢查出"+error+"個語法錯誤");}}
詞法分析
public class analyzer {public static List<String> llist=new ArrayList<>();static Map<Integer,Integer> map=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*";/** 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);System.out.printf("(%d, %s)\n", TOKEN_ID_SUM.get(ID), key);}else if (key.matches(NUM)) {llist.add(key);map.put(llist.size()-1,countLine);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);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);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();}}