Created
July 3, 2012 02:23
-
-
Save Answeror/3037132 to your computer and use it in GitHub Desktop.
交叉引用
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#include <map> | |
#include <string> | |
#include <vector> | |
#include <fstream> | |
#include <iostream> | |
#include <sstream> | |
#include <iterator> | |
#include <algorithm> | |
#include <string> | |
#include <vector> | |
#include <algorithm> | |
#include <functional> | |
#include <fstream> | |
#include <iterator> | |
#include <iostream> | |
using namespace std; | |
typedef string::const_iterator iter; | |
bool isurlch(char ch) | |
{ | |
static const string urlcs = "~;/?:@=&$-_.+!*'{},"; | |
return isalnum(ch) || find(urlcs.begin(), urlcs.end(), ch) != urlcs.end(); | |
} | |
iter url_end(iter begin, iter end) | |
{ | |
return find_if(begin, end, [](char ch){ return !isurlch(ch); }); | |
} | |
iter url_begin(iter begin, iter end) | |
{ | |
static const string sep = "://"; | |
iter i = begin; | |
while (true) | |
{ | |
i = search(i, end, sep.begin(), sep.end()); | |
if (i == end) break; | |
if (i != begin && i + sep.size() != end && isurlch(i[sep.size()])) | |
{ | |
iter result = i; | |
//while (result != begin && isalpha(result[-1])) --result; | |
result = find_if_not(string::const_reverse_iterator(i), string::const_reverse_iterator(begin), isalpha).base(); | |
if (result != i) return result; | |
} | |
if (i != end) i += sep.size(); | |
} | |
return end; | |
} | |
vector<string> extract_url(const string &text) | |
{ | |
vector<string> urls; | |
iter begin = text.begin(); | |
while (begin != text.end()) | |
{ | |
begin = url_begin(begin, text.end()); | |
if (begin != text.end()) | |
{ | |
iter end = url_end(begin, text.end()); | |
urls.push_back(string(begin, end)); | |
begin = end; | |
} | |
} | |
return urls; | |
} | |
typedef map<string, vector<int> > dict; | |
vector<string> split(const string &s) | |
{ | |
istringstream iss(s); | |
typedef istream_iterator<string> iter; | |
vector<string> v; | |
copy(iter(iss), iter(), back_inserter(v)); | |
return v; | |
} | |
dict xref(istream &is, | |
vector<string> find_words(const string&) = split) | |
{ | |
dict d; | |
string line; | |
int linecount = 0; | |
while (getline(is, line)) | |
{ | |
++linecount; | |
auto words = find_words(line); | |
if (!words.empty()) | |
{ | |
for (auto i = words.begin(); i != words.end(); ++i) | |
{ | |
d[*i].push_back(linecount); | |
} | |
} | |
} | |
for (auto i = d.begin(); i != d.end(); ++i) | |
{ | |
auto &lns = i->second; | |
lns.erase(unique(lns.begin(), lns.end()), lns.end()); | |
} | |
return d; | |
} | |
int main() | |
{ | |
ifstream ifs("in.txt"); | |
auto d = xref(ifs, extract_url); | |
for (auto i = d.begin(); i != d.end(); ++i) | |
{ | |
auto &lns = i->second; | |
cout << i->first << ": "; | |
copy(lns.begin(), lns.end(), | |
ostream_iterator<int>(cout, " ")); | |
cout << endl; | |
} | |
return 0; | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment