EE308 Lab1-2

[832001319]

The Link Your Class	https://bbs.csdn.net/forums/MUEE308FZU202201
The Link of Requirement of This Assignment	https://bbs.csdn.net/topics/608734907
The Aim of This Assignment	Write code that can extract keywords of different levels from the C or C++ code files that are read in.
MU STU ID and FZU STU ID	20122764_832001319

---

目录

1.PSP Table

2.Problem-solving ideas

3.Design and implementation process

4.Code description

5.Test

6.Performance analysis

7.Summary

---

Github Website Link

XINYUE1234/EE308 (github.com)

---

1.PSP Table

Personal Software Process Stages	Estimated Time(minutes)	Completed Time(minutes)
Planning	20	30
Estimate	-	-
Development	30	50
Analysis	200	300
Design Spec	10	20
Design Review	10	20
Coding Standard	10	20
Design	20	30
Coding	150	220
Code Review Planning	20	30
Test	10	15
Reporting	10	15
Test Report	10	10
Size Measurement	10	10
Postmortem&Process Improvement	20	20
Total	530	790

2.Problem-solving ideas

Program Requirements

1. Basic requirement: output "keyword" statistics
2. Advanced requirement: output the number of "switch case" structures, and output the number of "case" corresponding to each group
3. Uplifting requirement: output the number of "if else" structures
4. Ultimate requirement: output the number of "if, else if, else" structures
   Before completing the more difficult requirements, you need to complete the Lower requirements.

Because I am familiar with c++, I decided to use c++ to solve this task. This project requires us to complete four levels of tasks. First, we had to input the file and preprocess the file, then step through each level of code, and finally merge it to implement the functionality.

3.Design and implementation process

 

4.Code description

Read the file

First,I store the keywords in an array，then I  use ifstream to read the files, and after that I store them in a vector.

const string keywords[] = {"auto","break","case","char","const","continue","default","do",
	"double","else","enum","extern","float","for","goto","if","int",
	"long","register","return","short","signed","sizeof","static",
	"struct","switch","typedef","union","unsigned","void","volatile","while"};
vector<string> file_content;

void file_read(string filename){
	ifstream inFile;
	string line;
	inFile.open(filename.c_str());
	if (!inFile.is_open()){
		cout << "\nThe file was not successfully opened"
		<< "\n Please check that the file currently exists."
		<< endl;
		exit(1);
	} // check for successful open
	while (getline(inFile, line)) {
		file_content.push_back(line);
	}
	inFile.close();     //close the file
}

Delete the useless contents

To prevent possible keywords in the comment statements and strings from interfering with the extraction results, we need to remove the statements and strings in the comments. Here I use the find() and substr() functions.

void delete_useless_content(){
	string Line,words;
	int index;
	size_t tabs_location,annotation_location,quot_location,star1_location,star2_location;
	for(int i=0;i<file_content.size(); i++){
		Line=file_content[i];
		if(Line.find("\t")!=Line.npos&&Line.find("\t")==0){
			do{
				tabs_location=Line.find("\t")+1;
				Line=Line.substr(tabs_location,Line.length()-tabs_location);
			}while(Line.find("\t") != Line.npos && Line.find("\t") == 0);
			file_content[i] = Line;
		}
		if (Line.find("//") != Line.npos) {    
			annotation_location=Line.find("//");       
			if (annotation_location==0) {
				file_content.erase(file_content.begin()+i);      
				i--;
			} else {
				words = Line.substr(0,annotation_location);       
				file_content[i] = words;
			}
		}else if(Line.find("\"") !=Line.npos){
			size_t temp[50]={0};
			tabs_location=0;
			index=0;
			while ((quot_location=Line.find("\"",tabs_location)) != Line.npos) {
				temp[index]=quot_location;
				index++;
				tabs_location=quot_location+1;
			}
			temp[index]=Line.length();
			words= Line.substr(0,temp[0]);
			for (int j=1; temp[j]!=0; j+=2) {
				words += Line.substr(temp[j]+1,temp[j+1]-temp[j]-1);      
			}
			file_content[i]=words;	
		} else if(Line.find("/*") != Line.npos){
			star1_location=Line.find("/*");
			star2_location= Line.find("*/");
			if (star2_location!= Line.npos) {   
				if (star1_location== 0) {
					file_content[i] = Line.substr(star2_location+2,Line.length());
				} else {
					file_content[i] = Line.substr(0,star1_location);
				}
				i--;
			}else{
				file_content[i] = Line.substr(0,star1_location);
				i += 1;
				Line = file_content[i];
				while (Line.find("*/") == Line.npos) {
					file_content.erase(file_content.begin()+i);     
					Line = file_content[i];
				}
				star2_location = Line.find("*/")+2;
				file_content[i] = Line.substr(star2_location,Line.length()-star2_location);
			}
			
		}
	}
}

Judge keywords

To prevent incorrect identification of keywords in non-keyword fields, check whether the keywords are independent. I use ASCII code to differentiate.

bool independence_judge(string line,long i){
	if (line[i] < 48 || (line[i] > 57 && line[i] < 65) || (line[i] > 90 && line[i] < 97) ||line[i] >122) {
		return true;
	} else {
		return false;
	}
}
bool involve_judge(string line, string word){
	size_t word_location;
	word_location=line.find(word);
	if (word_location == 0) {
		if (independence_judge(line, word.length()) || word.length() == line.length()) {
			return true;
		} else {
			return false;
		}
	} else {
		if (independence_judge(line, word_location-1) && (independence_judge(line, word_location+word.length()) || word_location+word.length() == line.length())) {
			return true;
		} else {
			return false;
		}
	}
	
}

Calculate the keywords number

void cal_keywords_num(){
	int keywords_num=0;
	string line;
	for (int i = 0; i<file_content.size(); i++) {
		line = file_content[i];
		for (int j=0; j<32; j++) {
			size_t keywords_location = line.find(keywords[j], 0);
			while (keywords_location!=line.npos && involve_judge(line,keywords[j])) {
				keywords_num++;
				keywords_location = line.find(keywords[j],keywords_location + 1);
			}
		}
	}
	cout<<"total num: "<<keywords_num<<endl;
}

Calculate switch and case numbers

void cal_switch_case_num(){
	int switch_num = 0,last = -1,case_num[200]={0};
	string line;
	for (int i = 0; i<file_content.size(); i++) {
		line = file_content[i];
		if (line.find("switch") != line.npos && involve_judge(line, "switch")) {        
			switch_num += 1;
			last += 1;
		}
		if (line.find("case") != line.npos && involve_judge(line, "case")) {        /*²éÕÒcase*/
			case_num[last] += 1;
		}
	}
	cout<<"switch num: "<<switch_num<<endl;
	cout<<"case num:";
	for (int j = 0; j<=last; j++) {
		cout<<" "<<case_num[j];
	}
	cout<<endl;	
}

Calculate if-else and if-elseif-else number

void cal_if_else_num(int level) {
	int if_else_num = 0,if_else_if_else_num= 0;
	stack<int> s;
	string line;
	for (int i = 0; i<file_content.size(); i++) {
		line = file_content[i];
		if (line.find("if") != line.npos && line.find("else") == line.npos && involve_judge(line, "if")) {      
			s.push(1);
		} else if (line.find("if") == line.npos && line.find("else") != line.npos &&  s.empty() == false) {
			if (s.top() == 1) {
				if_else_num++;    
			} else {
				if_else_if_else_num++;    
			}
			s.pop();       
			
		}else  if (line.find("if") != line.npos && line.find("else") != line.npos && involve_judge(line, "if")) {
			s.push(2);    
		}
	}
	if (level == 3) {
		cout<<"if-else num: "<<if_else_num<<endl;
	} else if (level == 4) {
		cout<<"if-else num: "<<if_else_num<<endl;
		cout<<"if-else-if num: "<<if_else_if_else_num<<endl;
	}
}

5.Test

Level 1:

Level 2:

 Level 3:

Level 4:

6.Performance analysis

The software I used has no performance test function, so this part was not carried out in this experiment.

7.Summary

Through this task, I mastered the use of CSDN and GitHub, and had a certain understanding of blog. I also learned some new codes by myself and got familiar with the task flow. I think this practice will enable me to better control the project schedule in future team projects.