Lexical Analysis

we have a C source program scanned and filtered as it was done in Session 1. We now take that modified file as input, and separate the lexemes first. We further recognize and mark the lexemes as different types of tokens like keywords, identifiers, operators, separators, parenthesis, numbers, etc.

Session 2 by Nafis Islam on Scribd

float x1 = 3.125; double f1(int x) { double z; z = 0.01+x*5.5; return z; } int main(void) { int n1; double z; n1=25; z=f1(n1); }

view raw input.txt hosted with ❤ by GitHub

	#include<bits/stdc++.h>
	using namespace std;
	bool comp(char a){
	if(a=='=' || a=='>' || a=='<' ) return false;
	return true;
	}
	bool col(char a){
	if(a==',' || a==';' || a=='+' || a=='-' || a=='*' || a=='/' || a=='(' || a==')' || a=='\'') return true;
	return false;
	}
	bool isnum(string sp){
	for(int i=0;i<sp.size();i++){
	if(sp[i]>='0' && sp[i]<='9') continue;
	if(sp[i]=='.') continue;
	return false;
	}
	return true;
	}
	map<string,string>mp;
	void t(){
	mp["return"] = "[kw return]";
	mp["int"] = "[kw int]";
	mp["float"] = "[kw float]";
	mp["double"] = "[kw double]";
	mp["long"] = "[kw long]";
	mp["char"] = "[kw char]";
	mp[";"] = "[sep ;]";
	mp[","] ="[sep ,]";
	mp["'"] = "[sep ']";
	mp["if"] = "[kw if]";
	mp["else"] = "[kw else]";
	mp["("] = "[par (]";
	mp[")"] = "[par )]";
	mp["{"] = "[par {]";
	mp["}"] = "[par }]";
	mp["+"] = "[op +]";
	mp["-"] = "[op -]";
	mp["*"] = "[op *]";
	mp["/"] = "[op /]";
	mp["="] = "[op =]";
	mp["=="] = "[op ==]";
	mp["<="] = "[op <=]";
	mp[">="] = "[op >=]";
	}
	int main(){
	freopen("input.txt","r",stdin);
	freopen("output.txt","w",stdout);
	string s;
	getline(cin,s);
	cerr<<"input:\n";
	cerr<<s<<"\n\n";
	string p = "";
	for(int i=0;i<s.size();i++){
	if(col(s[i]) && col(s[i+1])==false) p = p+" "+s[i]+" ";
	else if(col(s[i]) && col(s[i+1])) p = p+" "+s[i];
	else p += s[i];
	}
	s = p[0];
	for(int i=1;i<p.size()-1;i++){
	if(p[i]=='=' && comp(p[i-1]) && comp(p[i+1])) s = s+" "+p[i]+" ";
	else s +=p[i];
	}
	p = "";
	for(int i=0;i<s.size();i++){
	if(i!=s.size()-1 && s[i]!=' ' && s[i+1]==' ') p = p + s[i] + ' ';
	else if(s[i]!=' ') p += s[i];
	}
	s = p[0];
	for(int i=1;i<p.size()-1;i++){
	if(comp(p[i])==false && comp(p[i+1])==false){
	s = s + " "+ p[i]+p[i+1] + " ";
	i++;
	}
	else s += p[i];
	}
	s+= p[p.size()-1];
	cerr<<"step 1:\n";
	cerr<<s<<"\n\n";
	istringstream ss(s);
	t();
	cerr<<"step 2:\n";
	while(ss>>s){
	if(mp.find(s)==mp.end()){
	if(isnum(s)==false){
	if(s[0]>='0' && s[0]<='9'){
	cout<<"[unkn "+s+"] ";
	cerr<<"[unkn "+s+"] ";
	}
	else{
	cout<<"[id "+s+"] ";
	cerr<<"[id "+s+"] ";
	}
	}
	else{
	cout<<"[num "+s+"] ";
	cerr<<"[num "+s+"] ";
	}
	}
	else{
	cout<<mp[s]<<" ";
	cerr<<mp[s]<<" ";
	}
	}
	cout<<"\n";
	cerr<<"\n";
	return 0;
	}

view raw Lexical Analysis.cpp hosted with ❤ by GitHub

[kw float] [id x1] [op =] [num 3.125] [sep ;] [kw double] [id f1] [par (] [kw int] [id x] [par )] [par {] [kw double] [id z] [sep ;] [id z] [op =] [num 0.01] [op +] [id x] [op *] [num 5.5] [sep ;] [kw return] [id z] [sep ;] [par }] [kw int] [id main] [par (] [id void] [par )] [par {] [kw int] [id n1] [sep ;] [kw double] [id z] [sep ;] [id n1] [op =] [num 25] [sep ;] [id z] [op =] [id f1] [par (] [id n1] [par )] [sep ;] [par }]

view raw output.txt hosted with ❤ by GitHub