.vscode/settings.json

@@ -3,47 +3,6 @@
         "xstring": "cpp",
         "iterator": "cpp",
         "ostream": "cpp",
-        "vector": "cpp",
+        "vector": "cpp"
-        "*.tcc": "cpp",
-        "iostream": "cpp",
-        "map": "cpp",
-        "array": "cpp",
-        "atomic": "cpp",
-        "cctype": "cpp",
-        "clocale": "cpp",
-        "cmath": "cpp",
-        "cstdarg": "cpp",
-        "cstddef": "cpp",
-        "cstdint": "cpp",
-        "cstdio": "cpp",
-        "cstdlib": "cpp",
-        "cstring": "cpp",
-        "cwchar": "cpp",
-        "cwctype": "cpp",
-        "deque": "cpp",
-        "unordered_map": "cpp",
-        "unordered_set": "cpp",
-        "exception": "cpp",
-        "algorithm": "cpp",
-        "memory": "cpp",
-        "memory_resource": "cpp",
-        "optional": "cpp",
-        "set": "cpp",
-        "string": "cpp",
-        "string_view": "cpp",
-        "system_error": "cpp",
-        "tuple": "cpp",
-        "type_traits": "cpp",
-        "utility": "cpp",
-        "fstream": "cpp",
-        "initializer_list": "cpp",
-        "iosfwd": "cpp",
-        "istream": "cpp",
-        "limits": "cpp",
-        "new": "cpp",
-        "sstream": "cpp",
-        "stdexcept": "cpp",
-        "streambuf": "cpp",
-        "typeinfo": "cpp"
     }
 }

CMakeLists.txt

@@ -3,19 +3,19 @@ project(compiler-bin)
 
 # 收集所有的cpp源文件
 file(GLOB SOURCES_LL "LL1/*.cpp")
-file(GLOB SOURCES_NFA "nfa/src/*.cpp")
+file(GLOB SOURCES_NFA "nfa/*.cpp")
 file(GLOB SOURCES_MAIN "main/*.cpp")
 
 # 设置输出目录为 bin
-# set(CMAKE_RUNTIME_OUTPUT_DIRECTORY ${CMAKE_BINARY_DIR}/bin)
+set(CMAKE_RUNTIME_OUTPUT_DIRECTORY ${CMAKE_BINARY_DIR}/bin)
 
 # 创建静态链接库
 add_library(LL STATIC ${SOURCES_LL})
 add_library(nfa STATIC ${SOURCES_NFA})
 
 # 添加头文件目录
-target_include_directories(LL PUBLIC ${CMAKE_CURRENT_SOURCE_DIR}/LL1)
+target_include_directories(LL PUBLIC ${CMAKE_CURRENT_SOURCE_DIR}/LL)
-target_include_directories(nfa PUBLIC ${CMAKE_CURRENT_SOURCE_DIR}/nfa/include)
+target_include_directories(nfa PUBLIC ${CMAKE_CURRENT_SOURCE_DIR}/nfa)
 
 # 添加可执行文件
 add_executable(main ${SOURCES_MAIN})

main/CMakeLists.txt

@@ -0,0 +1,14 @@
+cmake_minimum_required(VERSION 3.10)
+project(main)
+
+file(GLOB SOURCES "*.cpp")
+
+add_executable(main ${SOURCES})
+
+# 链接静态库
+target_link_libraries(main PRIVATE ${CMAKE_BINARY_DIR}/../../bin/LL.lib)
+target_link_libraries(main PRIVATE ${CMAKE_BINARY_DIR}/../../bin/nfa.lib)
+
+
+# 添加头文件目录
+# target_include_directories(main PUBLIC ${CMAKE_CURRENT_SOURCE_DIR})

main/LL1.h

@@ -0,0 +1,32 @@
+// LL1 语法分析器
+#ifndef LL1_H
+#define LL1_H
+
+#include "grammar.h"
+
+using namespace std;
+
+class LL1:public Grammar{
+public:
+	LL1();
+	~LL1();
+
+	bool IsLL1();														// 判断该文法是否为 LL1 文法
+	void build_LL1_predict();											// 构建 LL1 的预测分析表
+	void print_LL1_predict();											// 打印 LL1 的预测分析表
+	void build_LL1_grammar();											// 构建规约序列
+	void print_LL1_grammar_log();
+	void fileout_LL1_grammar_log(string file_name);
+
+
+private:
+	unordered_map<string, vector<string>> select;						// 计算符号的 SELECT 集合
+	unordered_map<string, unordered_map<string, int>> LL1_predict;		// LL1 的预测分析表
+	vector<string> LL1_grammar_log;									    // 规约序列
+
+	int insert_rule(pair<string, vector<string>>& new_rule);			// 增加新的规则
+};
+
+
+
+#endif // !LL1_H

main/grammar.h

@@ -0,0 +1,55 @@
+// 语法生成器
+#ifndef GRAMMAR_H
+#define GRAMMAR_H
+
+
+#include <string>
+#include <vector>
+#include <map>
+#include <unordered_set>
+#include <unordered_map>
+
+using namespace std;
+
+class Grammar
+{
+public:
+	const string grammar_file = "./tests/grammar.txt";
+	
+	Grammar();
+	~Grammar();
+	void read_grammar();									// 读取语法规则
+	void print_grammar();									// 打印语法规则
+	void expand_grammar();									// 拓展语法规则
+	void init_grammar_set();								// 初始化语法相关集合
+	void print_grammar_set();								// 打印语法相关集合
+	void get_token_strings(vector<string> &);				// 获取 token_stirngs
+	void print_token_strings();
+
+protected:
+	vector<pair<string, vector<string>>> grammar_rules;		// 产生式规则
+	string start;											// 起始字符
+	vector<string> symbols;									// 符号
+	vector<string> VTs;										// 终结符								
+	vector<string> VNs;										// 非终结符
+	unordered_map<string, vector<string>> first;			// FIRST 集
+	unordered_map<string, vector<string>> follow;			// FOLLOW 集
+	unordered_map<string, bool> infer_empty;				// 是否可以推导出 $ 空字符
+	vector<string> token_strings;
+
+
+private:
+	unordered_map<string, vector<int>> left_appears;		// 该符号出现在哪些产生式左侧
+	unordered_map<string, vector<int>> right_appears;		// 该符号出现在哪些产生式右侧
+	unordered_map<string, vector<string>> depend;			// FOLLOW 集的依赖关系
+	
+
+	void init_appears_depend();								// 获取 appear depend 集合
+	bool symbol_infer_empty(const string& symbol);			// 判断符号是否可以推导出 $ 空字符
+	vector<string> symbol_infer_first(const string& symbol);// 推导符号的 FIRST 集
+	vector<string> symbol_infer_follow(const string& symbol);// 推导符号的 FOLLOW 集
+
+};
+
+
+#endif // !GRAMMAR_H

main/nfa.h

@@ -0,0 +1,175 @@
+#pragma once
+#ifndef __NFA__H__
+#define __NFA__H__
+
+#include <map>
+#include <set>
+#include <deque>
+#include <vector>
+#include <iostream>
+#include <fstream>
+#include <string>
+#include <stdio.h>
+#include <sstream>
+#include <stack>
+#include <queue>
+#include <algorithm>
+using namespace std;
+//单词符号的类型，返回<待测代码中的单词符号,WordType>
+typedef enum WordType {
+	//当识别成标识符后，先判断是不是保留字，让后再判断IDN
+	KW_INT = 0,		// int
+	KW_VOID,		// void
+	KW_RETURN,		// return
+	KW_CONST,		// const
+	KW_MAIN,        //main
+
+	OP_ADD,			// +
+	OP_SUB,			// -
+	OP_MUL,			// *
+	OP_DIV,			// /
+	OP_MOD,			// %
+	OP_ASSIGN,		// =
+	OP_GT,			// >
+	OP_LT,			// <
+	OP_EQ,			// ==
+	OP_LE,			// <=
+	OP_GE,			// >=
+	OP_NE,			// !=
+	OP_AND,			// &&
+	OP_OR,			// ||
+
+	SE_LBRAC,		// ( left backet
+	SE_RBRAC,		// ) right bracket
+	SE_LCBRAC,		// { left curly bracket
+	SE_RCBRAC,		// } right curly bracket
+	SE_COMMA,		// ,
+	SE_SEMI,		// ;
+
+	IDN,			// [a-zA-Z][a-zA-Z_0-9]*
+	INT_VAL,		// -*[0-9]+
+	UNKOWN
+}WordType;
+string getWordTypeName(WordType type);
+//定义输入的字符类别
+typedef enum InputCharType {
+	LETTER = 0,		// 字母					0
+	UNDERLINE,		// _ 					1
+	DIGIT,			// 数字					2  当识别成功一个数字时，为了避免出现数字01的情况，返回前先进行一个判断，对GCC，01可以识别并等于1的
+	//OP
+	ADD,			// +					3
+	SUB,			// -					4
+	MUL,			// *					5
+	DIV,			// /					6
+	MOD,			// %					7
+	EQ,				// =					8
+	GT,				// >					9
+	LT,				// <					10
+	NOT,			// !					11
+	AND,			// &					12
+	OR,				// |					13
+	//SE
+	LBRACKET,		// (					14
+	RBRACKET,		// )					15
+	LCBRAC,			// {					16
+	RCBRAC,			// }					17
+	COMMA,			// ,					18
+	SEMI,			// ;					19
+
+	EPSILON,		// 空字符				20
+}InputCharType;
+string getInputChartypeName(InputCharType type);
+enum class TokenType {
+	KW = 0,
+	OP,
+	SE,
+	IDN,
+	INT,
+	UNKNOWN
+};
+TokenType getTokenType(WordType wordType,string buffer);
+typedef struct Token {
+	string value;
+	TokenType type;
+} Token;
+
+//定义函数判断输入的字符类别
+InputCharType getInputCharType(char c);
+string getWordTypeName(WordType type,string buffer);
+string getWordAttribute(WordType type,string buffer);
+
+//定义状态类
+class State {
+public:
+	int id; // 状态编号
+	map<InputCharType, set<State*>> transitions; // 转移函数映射表，记录每个输入字符类型对应的目标状态集合
+	bool isFinalState; // 是否为最终状态
+	WordType wordType; // 到达该状态时应该返回的词法单元类型
+	State(int id) : id(id), isFinalState(false), wordType(UNKOWN) {}
+	void addTransition(InputCharType input, State* targetState) {
+		transitions[input].insert(targetState);
+	}
+	void setFinalState(bool isFinal, WordType type) {
+		isFinalState = isFinal;
+		wordType = type;
+	}
+	bool operator<(const State& other) const {
+		return id < other.id;
+	}
+};
+//为了是set内部有序，定义排序结构体StatePtrCompare
+struct StatePtrCompare {
+	bool operator()(const State* lhs, const State* rhs) const {
+		return lhs->id < rhs->id;
+	}
+};
+
+//定义NFA类
+class NFA {
+public:
+	State* startState; // 起始状态
+	set<State*, StatePtrCompare> endStates; // 终止状态集合
+	set<State*, StatePtrCompare> states; // 状态集合
+	NFA(State* startState, set<State*, StatePtrCompare> endStates, set<State*, StatePtrCompare> states) :
+		startState(startState), endStates(endStates), states(states) {}
+	// void printNFA();
+};
+NFA RexToNFA();
+void printNFA(const NFA& nfa);
+NFA buildNFA(string filename);
+NFA RexToNFA();
+set<State*, StatePtrCompare> move(const set<State*, StatePtrCompare>& states, InputCharType input);
+set<State*, StatePtrCompare> epsilonClosure(const set<State*, StatePtrCompare>& states);
+
+class DFA {
+public:
+	State* startState; // 起始状态
+	set<State*, StatePtrCompare> endStates; // 终止状态集合
+	set<State*, StatePtrCompare> states; // 状态集合
+	DFA(State* startState, set<State*, StatePtrCompare> endStates, set<State*, StatePtrCompare> states) :
+		startState(startState), endStates(endStates), states(states) {}
+};
+void removeUnreachableStates(DFA& dfa);
+void printDFA(const DFA& dfa);
+DFA nfaToDFA(const NFA& nfa);
+void printDFA(const DFA& dfa);
+struct SetComparator {
+	bool operator()(const set<State*, StatePtrCompare>& a, const set<State*, StatePtrCompare>& b) const {
+		if (a.size() != b.size()) {
+			return a.size() < b.size();
+		}
+
+		vector<State*> vecA(a.begin(), a.end());
+		vector<State*> vecB(b.begin(), b.end());
+
+		sort(vecA.begin(), vecA.end(), [](const State* a, const State* b) { return a->id < b->id; });
+		sort(vecB.begin(), vecB.end(), [](const State* a, const State* b) { return a->id < b->id; });
+
+		return vecA < vecB;
+	}
+};
+string getGrammarName(WordType type, string buffer);
+DFA minimizeDFA(const DFA& dfa);
+vector<string> recognize(const DFA& dfa, const string& input, const string& output);
+string readfile(const string& filename);
+#endif 

nfa/CMakeLists.txt

@@ -2,14 +2,13 @@ cmake_minimum_required(VERSION 3.10)
 project(nfa)
 
 # 收集所有的cpp源文件
-file(GLOB SOURCES "src/*.cpp")
+file(GLOB SOURCES "*.cpp")
+
+# 设置输出目录为 bin
+set(CMAKE_RUNTIME_OUTPUT_DIRECTORY ${CMAKE_BINARY_DIR})
 
 # 创建静态链接库
 add_library(nfa STATIC ${SOURCES})
 
-# Test:添加可执行文件并链接目标库
-add_executable(test_nfa test/test_main.cpp)
-target_link_libraries(test_nfa nfa)
-
 # 添加头文件目录
-target_include_directories(nfa PUBLIC ${CMAKE_CURRENT_SOURCE_DIR}/include)
+target_include_directories(nfa PUBLIC ${CMAKE_CURRENT_SOURCE_DIR})

nfa/dfa.cpp

@@ -84,7 +84,7 @@ DFA minimizeDFA(const DFA& dfa) {
     size_t oldSize;//分割集初始大小
     do {
         oldSize = partitions.size();
-        for (InputCharType input = static_cast<InputCharType>(0); input < InputCharType::EPSILON; input = static_cast<InputCharType>(static_cast<int>(input) + 1)) {//类似于求Ia,Ib等
+        for (InputCharType input = static_cast<InputCharType>(0); input < EPSILON; input = static_cast<InputCharType>(input + 1)) {//类似于求Ia,Ib等
             for (Partition* partition : set<Partition*>(partitions)) {//遍历现存分割的每一个割集，看是否可再分割
                 if (partition->states.size() > 1) {//为1的集合不可再分割
                     split(partition->states, input, partitions);//核心分割函数

nfa/nfa.cpp

@@ -1,4 +1,8 @@
 // 将正则表达式转换为非确定性有限自动机
+
+
+
+
 #include "nfa.h"
 
 
@@ -7,32 +11,12 @@
 NFA RexToNFA() {
     //由于里面存在||,所以不同正则间使用空格分隔代表| l代表letter，_代表下划线，0代表数字(也可以是d，但是为了使用已经有的函数)，
     //[lu]代表l|u
-    std::string rex = "+ - * / % = > < == <= >= != && || ( ) { } , ; [l_][l_0]* -?00*";
+    string rex = "+ - * / % = > < == <= >= != && || ( ) { } , ; [l_][l_0]* -?00*";
    
-    //正则对应的输出(终态)
+    //下面给出正则对应的输出(终态)
     vector<WordType> finalState = {
-        WordType::OP_ADD, 
+        OP_ADD, OP_SUB,OP_MUL,OP_DIV,OP_MOD,OP_ASSIGN,OP_GT,OP_LT, OP_EQ,OP_LE,OP_GE,OP_NE, OP_AND, OP_OR,SE_LBRAC, SE_RBRAC,
-        WordType::OP_SUB,
+        SE_LCBRAC,SE_RCBRAC,SE_COMMA,SE_SEMI,IDN,INT_VAL
-        WordType::OP_MUL,
-        WordType::OP_DIV,
-        WordType::OP_MOD,
-        WordType::OP_ASSIGN,
-        WordType::OP_GT,
-        WordType::OP_LT,
-        WordType::OP_EQ,
-        WordType::OP_LE,
-        WordType::OP_GE,
-        WordType::OP_NE,
-        WordType::OP_AND,
-        WordType::OP_OR,
-        WordType::SE_LBRAC, 
-        WordType::SE_RBRAC,
-        WordType::SE_LCBRAC,
-        WordType::SE_RCBRAC,
-        WordType::SE_COMMA,
-        WordType::SE_SEMI,
-        WordType::IDN,
-        WordType::INT_VAL
     };
 
     stringstream ss(rex);
@@ -59,7 +43,7 @@ NFA RexToNFA() {
                 //[...]构成一种输入，查看]后面是否有？或者*，来判断当前状态的构成
                 for (i=i+1; i < target.length() && target[i] != ']'; i++) {
                     InputCharType input = getInputCharType(target[i]);
-                    if (input != InputCharType::EPSILON) {
+                    if (input != EPSILON) {
                         // 添加转移函数，从当前状态向新状态转移
                         currentState->addTransition(input, newState);
                     }
@@ -74,8 +58,8 @@ NFA RexToNFA() {
                 //创建EPSILON转移状态
                 State* epsState = new State(stateIndex++);
                 allStates.insert(epsState);
-                currentState->addTransition(InputCharType::EPSILON, epsState);
+                currentState->addTransition(EPSILON, epsState);
-                newState->addTransition(InputCharType::EPSILON, epsState);
+                newState->addTransition(EPSILON, epsState);
                 currentState = epsState;
                 // 跳过'?'字符
                 i++;
@@ -83,9 +67,9 @@ NFA RexToNFA() {
             else if (i + 1 < target.length() && target[i + 1] == '*') {
                 State* epsState = new State(stateIndex++);
                 allStates.insert(epsState);
-                currentState->addTransition(InputCharType::EPSILON, epsState);
+                currentState->addTransition(EPSILON, epsState);
-                newState->addTransition(InputCharType::EPSILON, epsState);
+                newState->addTransition(EPSILON, epsState);
-                epsState->addTransition(InputCharType::EPSILON, currentState);
+                epsState->addTransition(EPSILON, currentState);
                 currentState = epsState;
                 // 跳过'*'字符
                 i++;
@@ -105,6 +89,51 @@ NFA RexToNFA() {
     return NFA(startState, endStates, allStates);
 }
 
+// 构造状态机
+NFA buildNFA(string filename) {
+    ifstream ifs(filename);
+    if (!ifs) {
+        cerr << "Cannot open file: " << filename << endl;
+        exit(EXIT_FAILURE);
+    }
+
+    int stateNum, inputNum;
+    ifs >> stateNum >> inputNum;
+
+    vector<State*> states(stateNum);
+    for (int i = 0; i < stateNum; i++) {
+        states[i] = new State(i);
+    }
+
+    State* startState = states[0];
+    set<State*, StatePtrCompare> endStates;
+    for (int i = 0; i < stateNum; i++) {
+        for (int j = 0; j < inputNum; j++) {
+            string targetStateIDs;
+            ifs >> targetStateIDs;
+            if (targetStateIDs.compare("#") != 0) {
+                stringstream ss(targetStateIDs);
+                string targetStateIDStr;
+                while (getline(ss, targetStateIDStr, ',')) {
+                    int targetStateID = stoi(targetStateIDStr);
+                    states[i]->addTransition(static_cast<InputCharType>(j), states[targetStateID]);
+                }
+            }
+        }
+    }
+
+    int endStateNum;
+    ifs >> endStateNum;
+    for (int i = 0; i < endStateNum; i++) {
+        int endStateID, wordTypeID;
+        ifs >> endStateID >> wordTypeID;
+        states[endStateID]->setFinalState(true, static_cast<WordType>(wordTypeID));
+        endStates.insert(states[endStateID]);
+    }
+
+    return NFA(startState, endStates, set<State*, StatePtrCompare>(states.begin(), states.end()));
+}
+
 void printNFA(const NFA& nfa) {
     cout << "Start state: " << nfa.startState->id << endl;
     cout << "End states: "<<endl;
@@ -151,7 +180,7 @@ set<State*, StatePtrCompare> epsilonClosure(const set<State*, StatePtrCompare>&
     while (!stateStack.empty()) {
         State* currentState = stateStack.top();
         stateStack.pop();
-        auto it = currentState->transitions.find(InputCharType::EPSILON);
+        auto it = currentState->transitions.find(EPSILON);
         if (it != currentState->transitions.end()) {
             for (State* nextState : it->second) {
                 if (closure.find(nextState) == closure.end()) {//防止同一状态多次进栈，set自带去重
@@ -194,7 +223,7 @@ DFA nfaToDFA(const NFA& nfa) {
         }
 
         // 遍历所有输入字符类型
-        for (int i = 0; i < static_cast<int>(InputCharType::EPSILON); i++) {
+        for (int i = 0; i < static_cast<int>(EPSILON); i++) {
             InputCharType inputCharType = static_cast<InputCharType>(i);
             set<State*, StatePtrCompare> nextNFAStates = epsilonClosure(move(currentNFAStates, inputCharType));
             if (nextNFAStates.empty()) {

nfa/nfa.h

@@ -1,4 +1,7 @@
 #pragma once
+#ifndef __NFA__H__
+#define __NFA__H__
+
 #include <map>
 #include <set>
 #include <deque>
@@ -11,29 +14,19 @@
 #include <stack>
 #include <queue>
 #include <algorithm>
-#include <unordered_map>
-
 using namespace std;
 
 
-
 //单词符号的类型，返回<待测代码中的单词符号,WordType>
+// 保留关键字
+typedef enum WordType {
 	//当识别成标识符后，先判断是不是保留字，让后再判断IDN
-
-// Token 类型定义
-enum class WordType {
-
-	//关键字
 	KW_INT = 0,		// int
 	KW_VOID,		// void
 	KW_RETURN,		// return
 	KW_CONST,		// const
 	KW_MAIN,        //main
-	KW_IF,			// if
-	KW_ELSE,		// else
-	KW_FLOAT,		// float
 
-	//操作符
 	OP_ADD,			// +
 	OP_SUB,			// -
 	OP_MUL,			// *
@@ -49,8 +42,6 @@ enum class WordType {
 	OP_AND,			// &&
 	OP_OR,			// ||
 
-
-	//界符
 	SE_LBRAC,		// ( left backet
 	SE_RBRAC,		// ) right bracket
 	SE_LCBRAC,		// { left curly bracket
@@ -60,14 +51,14 @@ enum class WordType {
 
 	IDN,			// [a-zA-Z][a-zA-Z_0-9]*
 	INT_VAL,		// -*[0-9]+
-	FLOAT_VAL,		// -?[0-9]+\\.[0-9]+
-
 	UNKOWN
-};
+}WordType;
-extern std::unordered_map<WordType, std::string> WordTypeNames;
+string getWordTypeName(WordType type);
 
 // 定义输入的字符类别
-enum class InputCharType {
+// 输入与实际不完全匹配
+// 注意：此处定义的；和，顺序与实验指导书中不同
+typedef enum InputCharType {
 	LETTER = 0,		// 字母					0
 	UNDERLINE,		// _ 					1
 	DIGIT,			// 数字					2  当识别成功一个数字时，为了避免出现数字01的情况，返回前先进行一个判断，对GCC，01可以识别并等于1的
@@ -90,12 +81,11 @@ enum class InputCharType {
 	RCBRAC,			// }					17
 	COMMA,			// ,					18
 	SEMI,			// ;					19
-	POINT,			// .					20 如果浮点按整数缓存判断，则将小数点作为数字类型加载，最后在缓冲区内判断
 
-	EPSILON,		// 空字符				21
+	EPSILON,		// 空字符				20
-};
+}InputCharType;
+string getInputChartypeName(InputCharType type);
 
-extern std::unordered_map<InputCharType, std::string> CharTypeNames;
 
 // 定义 token类型
 enum class TokenType {
@@ -104,21 +94,15 @@ enum class TokenType {
 	SE,
 	IDN,
 	INT,
-	FLOAT,
 	UNKNOWN
 };
+TokenType getTokenType(WordType wordType,string buffer);
 
-// 定义最终返回/输出的token的组成类型，包含值和类型两部分
+// 定义最终返回的token的组成类型，包含值和类型两部分
-class Token {
+typedef struct Token {
 	string value;
 	TokenType type;
-};
+} Token;
-
-string getWordTypeName(WordType type);
-string getInputChartypeName(InputCharType type);
-
-
-
 
 // 定义函数判断输入的字符类别
 InputCharType getInputCharType(char c);
@@ -131,11 +115,10 @@ public:
 	int id; // 状态编号
 	bool isFinalState; // 是否为最终状态
 	WordType wordType; // 到达该状态时应该返回的词法单元类型
-
 	map<InputCharType, set<State*>> transitions; // 转移函数映射表，记录每个输入字符类型对应的目标状态集合
 
 	// 构造函数
-	State(int id) : id(id), isFinalState(false), wordType(WordType::UNKOWN) {}
+	State(int id) : id(id), isFinalState(false), wordType(UNKOWN) {}
 	
 	// 添加状态转移映射
 	void addTransition(InputCharType input, State* targetState) {
@@ -177,6 +160,8 @@ public:
 // 正则表达式构建状态机
 NFA RexToNFA();
 void printNFA(const NFA& nfa);
+NFA buildNFA(string filename);
+NFA RexToNFA();
 set<State*, StatePtrCompare> move(const set<State*, StatePtrCompare>& states, InputCharType input);
 set<State*, StatePtrCompare> epsilonClosure(const set<State*, StatePtrCompare>& states);
 
@@ -211,4 +196,4 @@ string getGrammarName(WordType type, string buffer);
 DFA minimizeDFA(const DFA& dfa);
 vector<string> recognize(const DFA& dfa, const string& input, const string& output);
 string readfile(const string& filename);
-
+#endif 

nfa/src/tool.cpp

@@ -1,309 +0,0 @@
-#include "nfa.h"
-
-std::unordered_map<InputCharType, std::string> CharTypeNames = {
- 	{InputCharType::UNDERLINE, "_"},
-    {InputCharType::ADD, "+"},
-    {InputCharType::SUB, "-"},
-    {InputCharType::MUL, "*"},
-    {InputCharType::DIV, "/"},
-    {InputCharType::MOD, "%"},
-    {InputCharType::EQ, "="},
-    {InputCharType::GT, ">"},
-    {InputCharType::LT, "<"},
-    {InputCharType::NOT, "!"},
-    {InputCharType::AND, "&"},
-    {InputCharType::OR, "|"},
-    {InputCharType::LBRACKET, "("},
-    {InputCharType::RBRACKET, ")"},
-    {InputCharType::LCBRAC, "{"},
-    {InputCharType::RCBRAC, "}"},
-    {InputCharType::COMMA, ","},
-    {InputCharType::SEMI, ";"},
-    {InputCharType::POINT, "."} // 小数点
-};
-
-
-std::unordered_map<WordType, std::string> WordTypeNames = {
-    {WordType::KW_INT, "INT"}, {WordType::KW_VOID, "VOID"}, {WordType::KW_RETURN, "RETURN"},
-    {WordType::KW_CONST, "CONST"}, {WordType::KW_MAIN, "MAIN"}, {WordType::KW_IF, "IF"},
-    {WordType::KW_ELSE, "ELSE"}, {WordType::KW_FLOAT, "FLOAT"}, {WordType::OP_ADD, "+"},
-    {WordType::OP_SUB, "-"}, {WordType::OP_MUL, "*"}, {WordType::OP_DIV, "/"},
-    {WordType::OP_MOD, "%"}, {WordType::OP_ASSIGN, "="}, {WordType::OP_GT, ">"},
-    {WordType::OP_LT, "<"}, {WordType::OP_EQ, "=="}, {WordType::OP_LE, "<="},
-    {WordType::OP_GE, ">="}, {WordType::OP_NE, "!="}, {WordType::OP_AND, "&&"},
-    {WordType::OP_OR, "||"}, {WordType::SE_LBRAC, "("}, {WordType::SE_RBRAC, ")"},
-    {WordType::SE_LCBRAC, "{"}, {WordType::SE_RCBRAC, "}"}, {WordType::SE_COMMA, ","},
-    {WordType::SE_SEMI, ";"}, {WordType::IDN, "IDENTIFIER"}, {WordType::INT_VAL, "INTEGER"},
-    {WordType::FLOAT_VAL, "FLOAT"}, {WordType::UNKOWN, "UNKNOWN"}
-};
-//扫描,以字符的格式读入
-//对于界符和部分运算符，是单个组成，即可以单独代表一个状态
-InputCharType getInputCharType(char c) {
-    switch (c) {
-    case '_': return InputCharType::UNDERLINE;
-    case '+': return InputCharType::ADD;
-    case '-': return InputCharType::SUB;
-    case '*': return InputCharType::MUL;
-    case '/': return InputCharType::DIV;
-    case '%': return InputCharType::MOD;
-    case '=': return InputCharType::EQ;
-    case '>': return InputCharType::GT;
-    case '<': return InputCharType::LT;
-    case '!': return InputCharType::NOT;
-    case '&': return InputCharType::AND;
-    case '|': return InputCharType::OR;
-    case '(': return InputCharType::LBRACKET;
-    case ')': return InputCharType::RBRACKET;
-    case '{': return InputCharType::LCBRAC;
-    case '}': return InputCharType::RCBRAC;
-    case ',': return InputCharType::COMMA;
-    case ';': return InputCharType::SEMI;
-    
-    //小数点作为数字读入
-    case '.': return InputCharType::DIGIT;
-
-    default:
-        if ((c >= 'a' && c <= 'z') || (c >= 'A' && c <= 'Z')) {
-            return InputCharType::LETTER;
-        }
-        else if (c >= '0' && c <= '9') {
-            return InputCharType::DIGIT;
-        }
-        else {
-            return InputCharType::EPSILON;
-        }
-    }
-}
-
-// 根据状态获取名称
-std::string getInputChartypeName(InputCharType type) {
-    auto it = CharTypeNames.find(type);
-    if (it != CharTypeNames.end()) {
-        return it->second;
-    } else {
-        return "UNKNOWN";
-    }
-}
-
-string judeFloat(string buffer){
-    size_t firstDot = buffer.find('.');
-    size_t lastDot = buffer.rfind('.');
-    if (firstDot == lastDot && firstDot != std::string::npos) {
-        return "FLOAT";
-    }
-    else if (firstDot ==  std::string::npos)
-    {
-        return "INT";
-    }
-    else return "UNKNOWN";
-}
-
-//根据关键字类型获取其所属的种别
-string getWordTypeName(WordType type, string buffer) {
-    switch (type) {
-    // 运算符
-    case WordType::OP_ADD:
-    case WordType::OP_SUB:
-    case WordType::OP_MUL:
-    case WordType::OP_DIV:
-    case WordType::OP_MOD:
-    case WordType::OP_ASSIGN:
-    case WordType::OP_GT:
-    case WordType::OP_LT:
-    case WordType::OP_EQ:
-    case WordType::OP_LE:
-    case WordType::OP_GE:
-    case WordType::OP_NE:
-    case WordType::OP_AND:
-    case WordType::OP_OR:
-        return "OP";
-
-    // 界符
-    case WordType::SE_LBRAC:
-    case WordType::SE_RBRAC:
-    case WordType::SE_LCBRAC:
-    case WordType::SE_RCBRAC:
-    case WordType::SE_COMMA:
-    case WordType::SE_SEMI:
-        return "SE";
-
-    // 标识符和关键字
-    case WordType::IDN:
-        if (!buffer.compare("int") || 
-            !buffer.compare("void") || 
-            !buffer.compare("const") || 
-            !buffer.compare("return")||
-            !buffer.compare("if") ||
-            !buffer.compare("else") ||
-            !buffer.compare("float")
-        ){
-            return "KW";
-        }
-        else {
-            return "IDN";
-        }
-
-    // 整数(添加了浮点判断)
-    case WordType::INT_VAL:
-        return judeFloat(buffer);
-    
-    //浮点
-    // case FLOAT_VAL:
-    //     return "FLOAT";
-    
-    //default
-    default:
-        return "UNKNOWN";
-    }
-}
-
-//根据关键字属性
-string getWordAttribute(WordType type, string buffer) {
-    switch (type) {
-    // 运算符
-    case WordType::OP_ADD: return "6";
-    case WordType::OP_SUB: return "7";
-    case WordType::OP_MUL: return "8";
-    case WordType::OP_DIV: return "9";
-    case WordType::OP_MOD: return "10";
-    case WordType::OP_ASSIGN: return "11";
-    case WordType::OP_GT: return "12";
-    case WordType::OP_LT: return "13";
-    case WordType::OP_EQ: return "14";
-    case WordType::OP_LE: return "15";
-    case WordType::OP_GE: return "16";
-    case WordType::OP_NE: return "17";
-    case WordType::OP_AND:return "18";
-    case WordType::OP_OR: return "19";
-
-    // 界符
-    case WordType::SE_LBRAC: return "20";
-    case WordType::SE_RBRAC: return "21";
-    case WordType::SE_LCBRAC: return "22";
-    case WordType::SE_RCBRAC: return "23";
-    case WordType::SE_COMMA: return "25";
-    case WordType::SE_SEMI: return "24";
-
-
-    // 标识符和关键字
-    case WordType::IDN:
-        if (!buffer.compare("int")){
-            return "1";
-        }
-        else if (!buffer.compare("void")){
-            return "2";
-        }        
-        else if (!buffer.compare("return")){
-            return "3";
-        }
-        else if (!buffer.compare("const")){
-            return "4";
-        }        
-        else if (!buffer.compare("main")){
-            return "5";
-        }
-        else if (!buffer.compare("if")){
-            return "6";
-        }
-        else if (!buffer.compare("else")){
-            return "7";
-        }
-        else if (!buffer.compare("float")){
-            return "8";
-        }
-        else {
-            return buffer;
-        }
-
-    // 整数
-    case WordType::INT_VAL:
-        return buffer;
-
-    //浮点类型，理论不使用
-    case WordType::FLOAT_VAL:
-        return buffer;
-    
-    //default
-    default:
-        return "UNKNOWN";
-    }
-}
-
-// 读取文件
-string readfile(const string& filename)
-{
-    // 打开文件流并读取文件内容
-    ifstream file(filename);
-
-    // 使用istreambuf_iterator类逐字符从file中读取到content中
-    string content((istreambuf_iterator<char>(file)),istreambuf_iterator<char>());
-
-    // 去掉换行符
-    //remove函数的作用是将字符串中的某个字符移动到字符串的末尾，并返回一个指向该字符后面位置的指针。
-    //erase 函数的作用是删除字符串中指定区间内的所有字符，返回修改后的字符串
-    //content.erase(remove(content.begin(), content.end(), '\n'), content.end());
-
-    return content;
-}
-
-
-// 获取token名称
-string getWordTypeName(WordType type) {
-    auto it = WordTypeNames.find(type);
-    if (it != WordTypeNames.end()) {
-        return it->second;
-    } else {
-        return "UNKNOWN";
-    }
-}
-
-// 获取语法名称
-string getGrammarName(WordType type, string buffer) {
-    switch (type) {
-
-    case WordType::OP_ADD: return "+";
-    case WordType::OP_SUB: return "-";
-    case WordType::OP_MUL: return "*";
-    case WordType::OP_DIV: return "/";
-    case WordType::OP_MOD: return "%";
-    case WordType::OP_ASSIGN: return "=";
-    case WordType::OP_GT: return ">";
-    case WordType::OP_LT: return "<";	
-    case WordType::OP_EQ: return "==";
-    case WordType::OP_LE: return "<=";
-    case WordType::OP_GE: return ">=";
-    case WordType::OP_NE: return "!=";
-    case WordType::OP_AND: return "&&";
-    case WordType::OP_OR: return "||";
-
-    case WordType::SE_LBRAC: return "(";
-    case WordType::SE_RBRAC: return ")";
-    case WordType::SE_LCBRAC: return "{";
-    case WordType::SE_RCBRAC: return "}";
-    case WordType::SE_COMMA: return ",";
-    case WordType::SE_SEMI: return ";";
-
-    case WordType::IDN: 
-        if (!buffer.compare("int")) {
-            return "int";
-        }
-        else if (!buffer.compare("void")) {
-            return "void";
-        }
-        else if (!buffer.compare("return")) {
-            return "return";
-        }
-        else if (!buffer.compare("const")) {
-            return "const";
-        }
-        else if (!buffer.compare("main")) {
-            return "main";
-        }
-        else {
-            return "IDN";
-        }
-    case WordType::INT_VAL: return "INT";	
-    case WordType::FLOAT_VAL: return "FLOAT";	
-    default: cerr << "Token Error: "<< WordTypeNames.find(type)->second << endl; exit(-1);
-    }
-}

nfa/test/test_main.cpp

@@ -1,27 +0,0 @@
-#include <iostream>
-#include <fstream>
-#include <cassert>
-
-#include "nfa.h"
-using namespace std;
-
-int main(int argc, char** argv) {
-
-    NFA nfa = RexToNFA();
-    printNFA(nfa);
-    //cout<<"OK1"<<endl;
-    
-    DFA dfa = nfaToDFA(nfa);
-    printDFA(dfa);
-    //cout<<"OK2"<<endl;
-    
-    system("pause");
-    DFA minimizedDFA = minimizeDFA(minimizeDFA(dfa));
-    removeUnreachableStates(minimizedDFA);
-    printDFA(minimizedDFA);
-    //cout<<"OK3"<<endl;
-
-	
-
-	return 0;
-}

nfa/tool.cpp

@@ -0,0 +1,378 @@
+#include "nfa.h"
+
+/*
+扫描读入-->以字符的格式读入
+对于界符和部分运算符，显然是单个组成，即可以单独代表一个状态
+
+
+注意：
+1.字母需要区分大小写
+*/
+
+// 获取输入串的类型
+// 单独一位的读入-->下一步标识终态
+InputCharType getInputCharType(char c) {
+    switch (c) {
+    case '_': return UNDERLINE;
+    case '+': return ADD;
+    case '-': return SUB;
+    case '*': return MUL;
+    case '/': return DIV;
+    case '%': return MOD;
+    case '=': return EQ;
+    case '>': return GT;
+    case '<': return LT;
+    case '!': return NOT;
+    case '&': return AND;
+    case '|': return OR;
+    case '(': return LBRACKET;
+    case ')': return RBRACKET;
+    case '{': return LCBRAC;
+    case '}': return RCBRAC;
+    case ',': return COMMA;
+    case ';': return SEMI;
+    default:
+        if ((c >= 'a' && c <= 'z') || (c >= 'A' && c <= 'Z')) {
+            return LETTER;
+        }
+        else if (c >= '0' && c <= '9') {
+            return DIGIT;
+        }
+        else {
+            return EPSILON;
+        }
+    }
+}
+
+// 根据状态获取名称
+string getInputChartypeName(InputCharType type) {
+    switch (type)
+    {
+    case LETTER:
+        return "LETTER";
+    case UNDERLINE:
+        return "UNDERLINE";
+    case DIGIT:
+        return "DIGIT";
+    case ADD:
+        return "+";
+    case SUB:
+        return "-";
+    case MUL:
+        return "*";
+    case DIV:
+        return "/";
+    case MOD:
+        return "%";
+    case EQ:
+        return "=";
+    case GT:
+        return ">";
+    case LT:
+        return "<";
+    case NOT:
+        return "!";
+    case AND:
+        return "&";
+    case OR:
+        return "|";
+    case LBRACKET:
+        return "(";
+    case RBRACKET:
+        return ")";
+    case LCBRAC:
+        return "{";
+    case RCBRAC:
+        return "}";
+    case COMMA:
+        return ",";
+    case SEMI:
+        return ";";
+    case EPSILON:
+        return "EPSILON";
+    default:
+        return "UNKOWN";
+    }
+}
+
+//根据关键字类型获取其所属的种别
+string getWordTypeName(WordType type, string buffer) {
+    switch (type) {
+    // 运算符
+    case OP_ADD:
+    case OP_SUB:
+    case OP_MUL:
+    case OP_DIV:
+    case OP_MOD:
+    case OP_ASSIGN:
+    case OP_GT:
+    case OP_LT:
+    case OP_EQ:
+    case OP_LE:
+    case OP_GE:
+    case OP_NE:
+    case OP_AND:
+    case OP_OR:
+        return "OP";
+
+    // 界符
+    case SE_LBRAC:
+    case SE_RBRAC:
+    case SE_LCBRAC:
+    case SE_RCBRAC:
+    case SE_COMMA:
+    case SE_SEMI:
+        return "SE";
+
+    // 标识符和关键字
+    case IDN:
+        if (!buffer.compare("int") || !buffer.compare("void") || !buffer.compare("const") || !buffer.compare("return")||!buffer.compare("main")){
+            return "KW";
+        }
+        else {
+            return "IDN";
+        }
+
+    // 整数
+    case INT_VAL:
+        return "INT";
+    
+    //default
+    default:
+        return "UNKNOWN";
+    }
+}
+
+//根据关键字属性
+string getWordAttribute(WordType type, string buffer) {
+    switch (type) {
+    // 运算符
+    case OP_ADD: return "6";
+    case OP_SUB: return "7";
+    case OP_MUL: return "8";
+    case OP_DIV: return "9";
+    case OP_MOD: return "10";
+    case OP_ASSIGN: return "11";
+    case OP_GT: return "12";
+    case OP_LT: return "13";
+    case OP_EQ: return "14";
+    case OP_LE: return "15";
+    case OP_GE: return "16";
+    case OP_NE: return "17";
+    case OP_AND:return "18";
+    case OP_OR: return "19";
+
+    // 界符
+    case SE_LBRAC: return "20";
+    case SE_RBRAC: return "21";
+    case SE_LCBRAC: return "22";
+    case SE_RCBRAC: return "23";
+    case SE_COMMA: return "25";
+    case SE_SEMI: return "24";
+
+
+    // 标识符和关键字
+    case IDN:
+        if (!buffer.compare("int")){
+            return "1";
+        }
+        else if (!buffer.compare("void")){
+            return "2";
+        }        
+        else if (!buffer.compare("return")){
+            return "3";
+        }
+        else if (!buffer.compare("const")){
+            return "4";
+        }        
+        else if (!buffer.compare("main")){
+            return "5";
+        }
+        else {
+            return buffer;
+        }
+
+    // 整数
+    case INT_VAL:
+        return buffer;
+    
+    //default
+    default:
+        return "UNKNOWN";
+    }
+}
+
+
+
+
+// 读取文件
+string readfile(const string& filename)
+{
+    // 打开文件流并读取文件内容
+    ifstream file(filename);
+
+    // 使用istreambuf_iterator类逐字符从file中读取到content中
+    string content((istreambuf_iterator<char>(file)),istreambuf_iterator<char>());
+
+    // 去掉换行符
+    //remove函数的作用是将字符串中的某个字符移动到字符串的末尾，并返回一个指向该字符后面位置的指针。
+    //erase 函数的作用是删除字符串中指定区间内的所有字符，返回修改后的字符串
+    //content.erase(remove(content.begin(), content.end(), '\n'), content.end());
+
+    return content;
+}
+
+// 获取关键字的Token种类
+TokenType getTokenType(WordType type,string buffer) {
+    switch (type) {
+    case OP_ADD:
+    case OP_SUB:
+    case OP_MUL:
+    case OP_DIV:
+    case OP_MOD:
+    case OP_ASSIGN:
+    case OP_GT:
+    case OP_LT:
+    case OP_EQ:
+    case OP_LE:
+    case OP_GE:
+    case OP_NE:
+    case OP_AND:
+    case OP_OR:
+        return TokenType::OP;
+
+    case SE_LBRAC:
+    case SE_RBRAC:
+    case SE_LCBRAC:
+    case SE_RCBRAC:
+    case SE_COMMA:
+    case SE_SEMI:
+        return TokenType::SE;
+
+    case IDN:
+        if (!buffer.compare("int") || !buffer.compare("void") || !buffer.compare("const") || !buffer.compare("return")|| !buffer.compare("main")) {
+            return TokenType::KW;
+        }
+        else {
+            return TokenType::IDN;
+        }
+
+    case INT_VAL:
+        return TokenType::INT;
+
+    default:
+        return TokenType::UNKNOWN;
+    }
+}
+
+// 获取token名称
+string getWordTypeName(WordType type) {
+    switch (type) {
+    case KW_INT:
+        return "KW_INT";
+    case KW_VOID:
+        return "KW_VOID";
+    case KW_RETURN:
+        return "KW_RETURN";
+    case KW_CONST:
+        return "KW_CONST";
+    case KW_MAIN:
+        return "KW_MAIN";
+    case OP_ADD:
+        return "OP_ADD";
+    case OP_SUB:
+        return "OP_SUB";
+    case OP_MUL:
+        return "OP_MUL";
+    case OP_DIV:
+        return "OP_DIV";
+    case OP_MOD:
+        return "OP_MOD";
+    case OP_ASSIGN:
+        return "OP_ASSIGN";
+    case OP_GT:
+        return "OP_GT";
+    case OP_LT:
+        return "OP_LT";
+    case OP_EQ:
+        return "OP_EQ";
+    case OP_LE:
+        return "OP_LE";
+    case OP_GE:
+        return "OP_GE";
+    case OP_NE:
+        return "OP_NE";
+    case OP_AND:
+        return "OP_AND";
+    case OP_OR:
+        return "OP_OR";
+    case SE_LBRAC:
+        return "SE_LBRAC";
+    case SE_RBRAC:
+        return "SE_RBRAC";
+    case SE_LCBRAC:
+        return "SE_LCBRAC";
+    case SE_RCBRAC:
+        return "SE_RCBRAC";
+    case SE_COMMA:
+        return "SE_COMMA";
+    case SE_SEMI:
+        return "SE_SEMI";
+    case IDN:
+        return "IDN";
+    case INT_VAL:
+        return "INT_VAL";
+    default:
+        return "UNKNOWN";
+    }
+}
+
+// 获取语法名称
+string getGrammarName(WordType type, string buffer) {
+    switch (type) {
+
+    case OP_ADD: return "+";
+    case OP_SUB: return "-";
+    case OP_MUL: return "*";
+    case OP_DIV: return "/";
+    case OP_MOD: return "%";
+    case OP_ASSIGN: return "=";
+    case OP_GT: return ">";
+    case OP_LT: return "<";	
+    case OP_EQ: return "==";
+    case OP_LE: return "<=";
+    case OP_GE: return ">=";
+    case OP_NE: return "!=";
+    case OP_AND: return "&&";
+    case OP_OR: return "||";
+
+    case SE_LBRAC: return "(";
+    case SE_RBRAC: return ")";
+    case SE_LCBRAC: return "{";
+    case SE_RCBRAC: return "}";
+    case SE_COMMA: return ",";
+    case SE_SEMI: return ";";
+
+    case IDN: 
+        if (!buffer.compare("int")) {
+            return "int";
+        }
+        else if (!buffer.compare("void")) {
+            return "void";
+        }
+        else if (!buffer.compare("return")) {
+            return "return";
+        }
+        else if (!buffer.compare("const")) {
+            return "const";
+        }
+        else if (!buffer.compare("main")) {
+            return "main";
+        }
+        else {
+            return "IDN";
+        }
+    case INT_VAL: return "INT";	
+    default: cerr << "Token Error: "<< type << endl; exit(-1);
+    }
+}