TextToken* TextToken::tokenizeLinks(const wchar_t *text) {
TextToken *firstToken = NULL, *lastToken = NULL;
int textLen = 0;
int l = wcslen(text);
for (int i=0; i<=l;) {
int newTokenType, newTokenSize;
int urlLen = Utils::detectURL(text+i);
if (i == l) {
newTokenType = END;
newTokenSize = 1;
} else if (urlLen > 0) {
newTokenType = LINK;
newTokenSize = urlLen;
} else if (!wcsncmp(text+i, L"www.", 4)) {
newTokenType = WWWLINK;
newTokenSize = countNoWhitespace(text+i);
} else if (!wcsncmp(text+i, L"mailto:", 7)) {
newTokenType = LINK;
newTokenSize = countNoWhitespace(text+i);
} else {
newTokenType = TEXT;
newTokenSize = 1;
}
if (newTokenType != TEXT) {
if (textLen >0 ) {
TextToken *newToken = new TextToken(TEXT, text+i-textLen, textLen);
textLen = 0;
if (lastToken == NULL) {
firstToken = newToken;
} else {
lastToken->setNext(newToken);
}
lastToken = newToken;
}
if (newTokenType == WWWLINK || newTokenType == LINK) {
TextToken *newToken = new TextToken(newTokenType, text+i, newTokenSize);
newToken->setLink(newToken->getText());
if (lastToken == NULL) {
firstToken = newToken;
} else {
lastToken->setNext(newToken);
}
lastToken = newToken;
}
} else {
textLen += newTokenSize;
}
i += newTokenSize;
}
return firstToken;
}
int Utils::detectURL(const wchar_t *text)
{
int i;
for (i=0; text[i]!='\0'; i++) {
if (!((text[i] >= '0' && text[i]<='9') || iswalpha(text[i]))) {
break;
}
}
if (i > 0 && text[i]==':' && text[i+1]=='/' && text[i+2]=='/') {
i += countNoWhitespace(text+i);
for (; i > 0; i --) {
if ((text[i-1] >= '0' && text[i-1]<='9') || iswalpha(text[i-1]) || text[i-1]=='/') {
break;
}
}
return i;
}
return 0;
}
