├── FinalCode
    ├── Database
    │   ├── db1.txt
    │   ├── db2.txt
    │   ├── db3.txt
    │   ├── db4.txt
    │   ├── db5.txt
    │   └── db6.txt
    ├── Main.cpp
    ├── Main.exe
    ├── Main.o
    ├── final_merged.txt
    ├── merge.cpp
    ├── merge.exe
    ├── merge.txt
    ├── result.txt
    ├── s.PNG
    └── search.php
├── README.md
├── _config.yml
├── finalreport.pdf
└── proposal.pdf


/FinalCode/Database/db1.txt:
--------------------------------------------------------------------------------
1 | George studies at IIITA.George is from bangalore.


--------------------------------------------------------------------------------
/FinalCode/Database/db2.txt:
--------------------------------------------------------------------------------
1 | IIITA is in allahabad.IIITA is one of the best colleges in Allahabad.
2 | 


--------------------------------------------------------------------------------
/FinalCode/Database/db3.txt:
--------------------------------------------------------------------------------
1 | Paul was born in Allahabad.Allahabad is in UP.


--------------------------------------------------------------------------------
/FinalCode/Database/db4.txt:
--------------------------------------------------------------------------------
1 | Sangam is a holy river.Sangam is in Allahabad.


--------------------------------------------------------------------------------
/FinalCode/Database/db5.txt:
--------------------------------------------------------------------------------
1 | There are many colleges in Allahabad. MNNIT is in  Allahabad.
2 | 
3 | 
4 | 


--------------------------------------------------------------------------------
/FinalCode/Database/db6.txt:
--------------------------------------------------------------------------------
1 | Bangalore is a cool city. Bangalore is in south.


--------------------------------------------------------------------------------
/FinalCode/Main.cpp:
--------------------------------------------------------------------------------
  1 | #include <iostream>
  2 | #include <cstdio>
  3 | #include <vector>
  4 | #include <algorithm>
  5 | #include <cstdlib>
  6 | #include <string>
  7 | #include <set>
  8 | #include <map>
  9 | #include <queue>
 10 | #include <fstream>
 11 | #define SW 29
 12 | using namespace std;
 13 | 
 14 | 
 15 | vector<string> input;
 16 | vector< vector<string> > tokens;
 17 | string stopwords[SW] = { "the", "of", "in", "and", "a", "an", "to", "with", "is", "was",
 18 |                          "were", "by", "that", "for", "be", "from", "as", "are", "on", "or",
 19 |                          "this", "an", "not", "it", "which", "with", "too", "at", "these" };
 20 | set<string> words;
 21 | map< string, vector<int> > index;
 22 | string input1, input2;
 23 | 
 24 | void read()
 25 | {
 26 |     std::ofstream("result.txt");
 27 |     ifstream infile;
 28 |     infile.open("final_merged.txt");
 29 | 
 30 |      //cout << "INPUT\n";
 31 |      string s;
 32 |      while( getline(infile,s) ) {
 33 |             if( s[0] == '#' ) {
 34 |                 break;
 35 |             }
 36 |             cout << s << endl;
 37 |             input.push_back(s);
 38 |      }
 39 |      infile.close();
 40 | }
 41 | 
 42 | bool checkSW( string s )
 43 | {
 44 |      for( int a = 0; a < SW; a ++ ) {
 45 |           if( s.compare( stopwords[a] ) == 0 ) {
 46 |               return false;
 47 |           }
 48 |      }
 49 |      return true;
 50 | }
 51 | 
 52 | void tokenize()
 53 | {
 54 |      cout << "TOKENIZE\n";
 55 |      string s, s1;
 56 |      vector<string> temp;
 57 |      for( int a = 0; a < input.size(); a ++ ) {
 58 |           cout << a << " : ";
 59 |           s = input[a];
 60 |           s = s + " ";
 61 |           s1 = "";
 62 |           temp.clear();
 63 |           for( int b = 0; b < s.size(); b ++ ) {
 64 |                if( s[b] == ' ' ) {
 65 |                    if( checkSW(s1) ) {
 66 |                        temp.push_back(s1);
 67 |                        words.insert(s1);
 68 |                        cout << s1 << " , ";
 69 |                    }
 70 |                    s1 = "";
 71 |                } else {
 72 |                       if( s[b] >= 65 && s[b] <= 90 ) {
 73 |                           s[b] += 32;
 74 |                       }
 75 |                       s1 = s1 + s[b];
 76 |                }
 77 |           }
 78 |           tokens.push_back(temp);
 79 |           cout << "\b\b\b   \n";
 80 |      }
 81 | }
 82 | 
 83 | void createIndex()
 84 | {
 85 |      cout << "INDEX\n";
 86 |      set<string> :: iterator its;
 87 |      vector< int > temp;
 88 |      for( its = words.begin(); its != words.end(); its ++ ) {
 89 |           cout << *its << " : ";
 90 |           temp.clear();
 91 |           for( int a = 0; a < tokens.size(); a ++ ) {
 92 |                    if( find( tokens[a].begin(), tokens[a].end(), *its ) != tokens[a].end() ) {
 93 |                              cout << a << " , ";
 94 |                              temp.push_back(a);
 95 |                    }
 96 |           }
 97 |           index[*its] = temp;
 98 |           cout << "\b\b\b   \n";
 99 |      }
100 | }
101 | 
102 | void userInput(string arg1 , string arg2)
103 | {
104 |      cout << "User Input\n";
105 |      cout << "Word 1 : ";
106 |      input1=arg1;
107 |      //input1 = "ram";
108 |      cout << "Word 2 : ";
109 |      input2=arg2;
110 |      //input2 = "nepal";
111 | }
112 | 
113 | map< string, bool > visited;
114 | int cost;
115 | string final;
116 | 
117 | string getString(int a)
118 | {
119 |        string s = "";
120 |        if( a == 0 ) {
121 |             return "0";
122 | }
123 |        while( a != 0 ) {
124 |             s = s + char((a%10)+'0');
125 |             a = a / 10;
126 |        }
127 |        return s;
128 | }
129 | 
130 | void dfs( string w, int level, string cs, string cd )
131 | {
132 |      if( visited[w] == true ) {
133 |           return;
134 |      }
135 |      cs = cs + w;
136 |      cs = cs + ",";
137 |      visited[w] = true;
138 |      vector<int> doc = index[w];
139 |      string cs1;
140 |      string cd1;
141 |      int i;
142 |      for( int a = 0; a < doc.size(); a ++ ) {
143 |           i = doc[a];
144 |           cd1 = cd + getString(i);
145 |           cd1 = cd1 + ",";
146 |           for( int b = 0; b < tokens[i].size(); b ++ ) {
147 |                    if( visited[tokens[i][b]] == true ) {
148 |                        continue;
149 |                    } else if( input2.compare( tokens[i][b] ) == 0 ) {
150 |                        cs1 = cs + tokens[i][b];
151 |                        cout << a << " --- " << level << " --- " << cs1 << " --- " << cd1 << endl;
152 |                        if( level < cost ) {
153 |                             cost = level;
154 |                             final = cd1;
155 |                        }
156 |                    } else {
157 |                        dfs( tokens[i][b], level + 1, cs, cd1 );
158 |                    }
159 |           }
160 |      }
161 |      visited[w] = false;
162 | }
163 | 
164 | void execute()
165 | {
166 |      set< string > :: iterator its;
167 |      for( its = words.begin(); its != words.end(); its ++ ) {
168 |           visited[*its] = false;
169 |      }
170 |      cost = input.size() + 1;
171 |      final = "";
172 |      string cs = "";
173 |      string cd = "";
174 |      dfs(input1,0,cs,cd);
175 | }
176 | 
177 | void output()
178 | {
179 |     ofstream outfile;
180 |     outfile.open("result.txt");
181 |     cout << "FINAL\n";
182 |     cout << cost << " , " << final << endl;
183 | 
184 |     string s;
185 |     int i = 0, doc;
186 |     for( int a = 0; a <= cost; a ++ ) {
187 |          s = "";
188 |          while( final[i] != ',' ) {
189 |               s = s + final[i];
190 |               i ++;
191 |          }
192 |          i ++;
193 |          doc = atoi(s.c_str());
194 |          cout << doc << " : " << input[doc] << endl;
195 |          outfile<<input[doc]<<"\n";
196 |     }
197 |     outfile.close();
198 | }
199 | 
200 | int main(int argc, char* argv[])
201 | {
202 |      for (int i = 0; i<argc; i++)
203 |      printf("argv[%d] = %s\n", i, argv[i]);
204 |     read();
205 |     cout << endl;
206 |     tokenize();
207 |     cout << endl;
208 |     createIndex();
209 |     cout << endl;
210 |     userInput(argv[1],argv[2]);
211 |     cout << endl;
212 |     execute();
213 |     cout << endl;
214 |     output();
215 |     //system("pause");
216 |     return 0;
217 | }
218 | 


--------------------------------------------------------------------------------
/FinalCode/Main.exe:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/kckishan/knowledgegraph/0b531f926572a8339d7f05cece3324b7450c55aa/FinalCode/Main.exe


--------------------------------------------------------------------------------
/FinalCode/Main.o:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/kckishan/knowledgegraph/0b531f926572a8339d7f05cece3324b7450c55aa/FinalCode/Main.o


--------------------------------------------------------------------------------
/FinalCode/final_merged.txt:
--------------------------------------------------------------------------------
 1 | George studies at IIITA
 2 | George is from bangalore
 3 | IIITA is in allahabad
 4 | IIITA is one of the best colleges in Allahabad
 5 |  Paul was born in Allahabad
 6 | Allahabad is in UP
 7 | Sangam is a holy river
 8 | Sangam is in Allahabad
 9 | There are many colleges in Allahabad
10 | MNNIT is in  Allahabad
11 | Bangalore is a cool city
12 | Bangalore is in south
13 |  


--------------------------------------------------------------------------------
/FinalCode/merge.cpp:
--------------------------------------------------------------------------------
 1 | #include <iostream>
 2 | #include <fstream>
 3 | #include <string>
 4 | 
 5 | 
 6 | using namespace std;
 7 | 
 8 | int main()
 9 | {
10 |     
11 |     std::ofstream("merge.txt");
12 |     std::ofstream("final_merged.txt");
13 |     int i, j, k, n;
14 |     system("type C:\\wamp\\www\\FinalCode\\Database\\*.txt >> merge.txt");  // Database is folder name where this c++ file is executed 
15 |     string line;
16 |     ofstream myfile;
17 |     myfile.open ("final_merged.txt");
18 |     ifstream infile;
19 |     infile.open ("merge.txt");
20 |     
21 |     if (infile.is_open() && myfile.is_open() )
22 |      { 
23 |        while ( infile.good() ) 
24 |        {
25 |        getline (infile, line);
26 |        if ( line[0] == ' ' )
27 |        {
28 |        } else 
29 |        {
30 |          myfile << line[0];
31 |        }     
32 |        for ( int i = 1; i < line.length(); i++ ) 
33 |            {
34 |              if ( line[i] == '?' || line[i] == '.' ) {
35 |              myfile << endl;
36 |              if ( i < line.length() - 1 && line[i+1] == ' ' )
37 |                 i++;
38 |           }
39 |           else myfile << line[i];           
40 |        }
41 |        myfile << " ";  
42 |       } 
43 |       infile.close();
44 |       myfile.close();
45 |     }
46 |     
47 |     system("pause");
48 |     return 0;
49 | }
50 | 


--------------------------------------------------------------------------------
/FinalCode/merge.exe:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/kckishan/knowledgegraph/0b531f926572a8339d7f05cece3324b7450c55aa/FinalCode/merge.exe


--------------------------------------------------------------------------------
/FinalCode/merge.txt:
--------------------------------------------------------------------------------
1 | George studies at IIITA.George is from bangalore.IIITA is in allahabad.IIITA is one of the best colleges in Allahabad.
2 | Paul was born in Allahabad.Allahabad is in UP.Sangam is a holy river.Sangam is in Allahabad.There are many colleges in Allahabad. MNNIT is in  Allahabad.
3 | 
4 | 
5 | Bangalore is a cool city. Bangalore is in south.


--------------------------------------------------------------------------------
/FinalCode/result.txt:
--------------------------------------------------------------------------------
1 | George studies at IIITA
2 | IIITA is in allahabad
3 |  Paul was born in Allahabad
4 | 


--------------------------------------------------------------------------------
/FinalCode/s.PNG:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/kckishan/knowledgegraph/0b531f926572a8339d7f05cece3324b7450c55aa/FinalCode/s.PNG


--------------------------------------------------------------------------------
/FinalCode/search.php:
--------------------------------------------------------------------------------
 1 | <!DOCTYPE html>
 2 | <html>
 3 | <head>
 4 | <title><Knowledge Graph Search></title>
 5 |  <style>
 6 | body
 7 | {
 8 | background-image:url('s.PNG');
 9 | background-repeat:no-repeat;
10 | background-position:100% -150%;
11 | margin-left:450px;
12 | margin-down:350px;
13 | }
14 | </style>
15 | </head>
16 | <body>
17 |              Knowlegde Graph Search
18 | <form method="post" action="search.php">
19 | <input type="text" size="20" maxlength="255" name="input1" />
20 | <input type="text" size="20" maxlength="255" name="input2" /> <br>
21 | <input type="submit" value="Search" />
22 | 
23 | </form>
24 | <?php
25 | if(empty($_POST["input1"]) || empty($_POST["input2"]))
26 | echo "<h4>please enter both fields</h4>";
27 | if(!empty($_POST["input1"]) && !empty($_POST["input2"]))
28 | {
29 | echo "<h4>Result</h4>";
30 | exec("merge.exe");
31 | $input1=$_POST["input1"];
32 | $input2=$_POST["input2"];
33 | $result=shell_exec("Main.exe"." ".$input1." ".$input2);
34 | $file = fopen("result.txt", "r") or exit("Unable to open file!");
35 | //Output a line of the file until the end is reached
36 | while(!feof($file))
37 |   {
38 |   echo "<b>".fgets($file)."</b>"."<br>";
39 |   }
40 | fclose($file);
41 | //$output = file_get_contents('http://127.0.0.1/search/result.txt');
42 | //echo $output;
43 | //echo $results;
44 | //unset($results);
45 | }
46 | ?>
47 | </body>
48 | </html>
49 | 


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
  1 | 
  2 | # Knowledge Graph
  3 | ## A search engine
  4 | 
  5 | ##### Kishan K.C. 
  6 | 
  7 | Steps: 
  8 | 
  9 | 1. Tokenizing Web Documents
 10 | 2. Indexing
 11 | 3. Forming Knowledge Graph
 12 | 4. Performing Search and Constructing Information.
 13 | 5. Displaying Information
 14 | 
 15 | The project uses c++. There are two C++ programs , main.cpp and merge.cpp.
 16 | 
 17 | 1. Merge.cpp
 18 | It merges all the content from different documents in a single text file named final_merged.txt.
 19 | Then it splits the whole document into individual sentences so that there is single sentence in
 20 | each line. It is necessary for indexing because sentences act as edges in the graph. So during
 21 | indexing sentence number is necessary.
 22 | 
 23 | 
 24 | System command “type *.txt >> merge.txt” is used to merge all the text files from folder
 25 | Database. After merging all the text documents into merge.txt, each sentences are arranged in a
 26 | single line. Whenever a full stop or question mark is found , the sentence is printed in new line.
 27 | 
 28 | 2. Main.cpp
 29 | 
 30 | There are several functions in it. They are described briefly below:
 31 | 
 32 | * read ();
 33 | This function opens the text document final_merged.txt and reads individual strings from the
 34 | file then it performs vector operation push_back to store the strings in vector of string named
 35 | vector<string> input.
 36 | 
 37 |  
 38 | * checkSW( string s )
 39 | This function checks whether the strings from input file final_merged.txt are useful for
 40 | tokenizing or not. The words that can be ignored are defined in an array called string
 41 | stopwords[SW].
 42 | ```
 43 | string stopwords[SW] = { "the", "of", "in", "and", "a", "an", "to", "with", "is", "was",
 44 | "were", "by", "that", "for", "be", "from", "as", "are", "on", "or", "this", "an", "not", "it", "which",
 45 | "with", "too", "at", "these" };
 46 | ```
 47 | 
 48 | The function checks the strings are one of these stop words or not.
 49 | 
 50 | 
 51 | * tokenize()
 52 | 
 53 | This function tokenizes the strings contained in final_merged.txt if they are not one of
 54 | the stop words defined above.
 55 | 
 56 | * createIndex()
 57 | 
 58 | After tokenization it is necessary to index the tokens , this function tags each token with
 59 | the sentence number it belongs to.
 60 | 
 61 | * userInput(string arg1 , string arg2)
 62 | 
 63 | This function takes input from the user. User is provided with two fields in search engines.
 64 | 
 65 | He can provide his query which must be a string in these fields.
 66 | 
 67 | * dfs( string w, int level, string cs, string cd )
 68 | 
 69 | Using tokens as nodes and sentences where they occur as edges a graph is made.
 70 | 
 71 | * execute()
 72 | 
 73 | This function executes dfs and finds the path between two search words in the graph.
 74 | 
 75 | * output()
 76 | 
 77 | This function provides the result in result.txt. The result is the path between two search
 78 | words provided by the user.
 79 | 
 80 | 
 81 | This function calls all the functions discussed above.
 82 | ```
 83 | int main(int argc, char* argv[]) { 
 84 | 
 85 |    for (int i = 0; i<argc; i++)
 86 |       printf("argv[%d] = %s\n", i, argv[i]);
 87 | 
 88 |    read();
 89 |    cout << endl;
 90 | 
 91 |    tokenize();
 92 |    cout << endl;
 93 | 
 94 |    createIndex();
 95 |    cout << endl;
 96 | 
 97 |    userInput(argv[1],argv[2]);
 98 |    cout << endl;
 99 | 
100 |    execute();
101 |    cout << endl;
102 | 
103 |    output();
104 |    return 0;
105 | }
106 | ```
107 | 


--------------------------------------------------------------------------------
/_config.yml:
--------------------------------------------------------------------------------
1 | theme: jekyll-theme-cayman


--------------------------------------------------------------------------------
/finalreport.pdf:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/kckishan/knowledgegraph/0b531f926572a8339d7f05cece3324b7450c55aa/finalreport.pdf


--------------------------------------------------------------------------------
/proposal.pdf:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/kckishan/knowledgegraph/0b531f926572a8339d7f05cece3324b7450c55aa/proposal.pdf


--------------------------------------------------------------------------------