6-0-0.cpp

Accelerated C++ 课后练习题 本人自己完成、可供参考

#include<iostream>
#include<algorithm>
#include<vector>
#include<string>
#include<cctype>
using namespace std;


bool not_url_char(char c)
{
	//characters, in addition to alphanumerics, that an appear in a URL
	static const string url_ch= "~;/?:@=&$-_.+!*'(),";

	//see whether c can appear in a URL and return the negative
	return !(isalnum(c)||find(url_ch.begin(),url_ch.end(),c)!=url_ch.end());
}


string::const_iterator 
url_end(string::const_iterator b,string::const_iterator e)
{
	return find_if(b,e,not_url_char);
}

string::const_iterator 
url_beg(string::const_iterator b,string::const_iterator e)
{
	static const string sep="://";

	typedef string::const_iterator iter;

	//i marks where the separators was found
	iter i=b;
	while((i=search(i,e,sep.begin(),sep.end()))!=e)
	{
		//make sure the separator isn's the beginning or the end of the line
		if(i!=b&&i+sep.size()!=e)
		{
			//beg marks the beginning of the protocol-name
			iter beg=i;
			while(beg!=b&&isalpha(beg[-1]))
				--beg;

			//is there at least one appropriate charactor before and after the separator
			if(beg!=i&&!not_url_char(i[sep.size()]))
				return beg;
		}		
			//the separator we found wasn't part of a URL advance is part this separator
			i+=sep.size();
	}
	return e;
}

vector<string> find_urls(const string& s)
{
	vector<string> ret;
	typedef string::const_iterator iter;
	iter b=s.begin(),e=s.end();
	
	//look through th entire input
	while(b!=e)
	{
		//look for one or more letters followed by ://
		b=url_beg(b,e);

		//if we found it
		if(b!=e)
		{
			//get the rest of the URL
			iter after=url_end(b,e);

			//remember the URL
			ret.push_back(string(b,after));

			//advance b and check for more URLs on the line
			b=after;
		}
	}
	return ret;
}



int main()
{
	string s;
	getline(cin,s);

	vector<string> v=find_urls(s);

	for(vector<string>::size_type i=0;i<v.size();++i)
		cout<<v[i]<<endl;

	return 0;
}