1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230
|
#include <iostream>
#include <fstream>
#include <string>
#include "sensitiveWords.h"
#include "message.h"
using namespace std;
int numSensitiveWords = 0;
const int MaxSensitiveWords = 5000;
std::string sensitiveWords[MaxSensitiveWords];
std::string toLowerCase (std::string word)
{
string result = word;
for (int i = 0; i < word.length(); ++i)
if (word[i] >= 'A' && word[i] <= 'Z')
result[i] = result[i] + 'a' - 'A';
return result;
}
bool isAlphanumeric (char c)
{
return (c >= 'A' && c <= 'Z')
|| (c >= 'a' && c <= 'z')
|| (c >= '0' && c <= '9');
}
bool sentencePunctuation (char c)
{
return c == '.' || c == '?' || c == '!';
}
/*
* Return true if the character at position pos is the first character
* of a word.
*/
bool wordBeginsAt (const std::string& message, int pos)
{
if (isAlphanumeric(message[pos] || sentencePunctuation(message[pos])))
{
if (pos > 0)
{
if (isAlphanumeric(message[pos-1]) || sentencePunctuation(message[pos-1]))
{
return false;
}
else
{
return true;
}
}
return false;
}
}
/*
* Return the string comprising the word that begins at
* position beginningAt.
*/
std::string extractWord (const std::string& fromMessage, int beginningAt)
{
int x = 0;
while(beginningAt + x <= fromMessage.length() && isAlphanumeric(fromMessage[beginningAt + x]))
{
x++;
}
string theWord = fromMessage.substr(beginningAt, x);
return theWord;
}
bool paragraphStart (const string& msg, int pos)
{
if (pos == 0)
return true;
if (pos == 1)
return false;
return msg[pos-1] == '\n' && msg[pos-2] == '\n';
}
/*
* Return the position that denotes the first character of the sentence
* that begins at or before position pos and that ends at or after
* that position.
*/
int findSentenceStart (const string& msg, int pos)
{
while (pos > 0 && !paragraphStart(msg,pos) && !sentencePunctuation(msg[pos]))
--pos;
if (sentencePunctuation(msg[pos]))
++pos;
return pos;
}
bool paragraphEnd (const string& msg, int pos)
{
if (pos == msg.length())
return true;
if (pos == msg.length()-1)
return false;
return msg[pos] == '\n' && msg[pos+1] == '\n';
}
/*
* Return the position that denotes the last character of the sentence
* that begins at or before position pos and that ends at or after
* that position.
*/
int findSentenceStop (const string& msg, int pos)
{
while (pos < msg.length()
&& !paragraphEnd(msg,pos)
&& !(pos > 0 && sentencePunctuation(msg[pos-1])))
++pos;
return pos;
}
/*
* Replace by '@' all characters (except '\n') of the sentence
* that begins at or before position pos and that ends at or after
* that position.
*/
void censorSentenceAt (string& msg, int pos)
{
int start = findSentenceStart(msg, pos);
int stop = findSentenceStop(msg, pos);
for (start; start != stop; start++)
{
if(msg.at(start) == '\n')
{
//blank
}
else
{
msg.at(start) = '@';
}
}
}
bool isSensitive(std::string& wordFromMessage)
{
string word = toLowerCase(wordFromMessage);
for (int i = 0; i < numSensitiveWords; ++i)
if (word == sensitiveWords[i])
return true;
return false;
}
void addSensitiveWord (std::string& wordFromMessage)
{
string word = toLowerCase(wordFromMessage);
if (!isSensitive(word))
{
sensitiveWords[numSensitiveWords] = word;
++numSensitiveWords;
}
}
///////////////////////////////////////////////////////
//!!
// The 4 functions below should remain in censor.cpp
// The functions and data above should be used to create
// two models, "sensistiveWords" and "message". Keep the
// cohesion high and the coupling low.
void censorMessage (string& msg)
{
for (int i = 0; i < msg.length(); ++i)
{
if (wordBeginsAt(msg, i))
{
string word = extractWord(msg, i);
if (isSensitive(word))
censorSentenceAt (msg, i);
}
}
}
void readSensitiveWords (istream& in)
{
string word;
while ((in >> word) && (word != "==="))
addSensitiveWord (word);
getline (in, word);
}
string readMessage (istream& in)
{
string msg;
string line;
getline (in, line);
while (in)
{
msg = msg + line + "\n";
getline (in, line);
}
return msg;
}
int main()
{
readSensitiveWords(cin);
string msg = readMessage(cin);
censorMessage (msg);
cout << msg << flush;
return 0;
}
| |