char NameManager::chooseNextLetter(const char lastLetter, const char letterBeforeLast) {
if (letterBeforeLast == ' ' && lastLetter == ' ')
return 97 + System::random(25);
StringBuffer last;
last << Character::toLowerCase(lastLetter);
String inclusion = "abcdefghijklmnopqrstuvwxyz";
if (letterBeforeLast != ' ' && (!isVowel(lastLetter) && !isVowel(letterBeforeLast))) {
inclusion = letterMappings.get("doubleconsonent");
} else if ((letterBeforeLast != ' ' && isVowel(lastLetter) && isVowel(letterBeforeLast))) {
inclusion = letterMappings.get("doublevowel");
} else if ((letterBeforeLast != ' ' && lastLetter == 'u' && letterBeforeLast == 'q')) {
inclusion = letterMappings.get("qu");
} else if(letterMappings.contains(last.toString())) {
inclusion = letterMappings.get(last.toString());
}
return chooseLetterInclusive(inclusion);
}
String FrenchStemmer::retrieveRV(const String& buffer)
{
int32_t len = (int32_t)buffer.length();
if (buffer.length() > 3)
{
if (isVowel(buffer[0]) && isVowel(buffer[1]))
return buffer.substr(3);
else
{
int32_t pos = 0;
for (int32_t c = 1; c < len; ++c)
{
if (isVowel(buffer[c]))
{
pos = c;
break;
}
}
if (pos + 1 < len)
return buffer.substr(pos + 1);
else
return L"";
}
}
else
return L"";
}
String BrazilianStemmer::getR1(const String& value)
{
if (value.empty())
return L"";
// find 1st vowel
int32_t i = (int32_t)(value.length() - 1);
int32_t j = 0;
for (; j < i; ++j)
{
if (isVowel(value[j]))
break;
}
if (j >= i)
return L"";
// find 1st non-vowel
for (; j < i; ++j)
{
if (!isVowel(value[j]))
break;
}
if (j >= i)
return L"";
return value.substr(j + 1);
}
String FrenchStemmer::retrieveR(const String& buffer)
{
int32_t len = (int32_t)buffer.length();
int32_t pos = -1;
for (int32_t c = 0; c < len; ++c)
{
if (isVowel(buffer[c]))
{
pos = c;
break;
}
}
if (pos > -1)
{
int32_t consonne = -1;
for (int32_t c = pos; c < len; ++c)
{
if (!isVowel(buffer[c]))
{
consonne = c;
break;
}
}
if (consonne > -1 && (consonne + 1) < len)
return buffer.substr(consonne + 1);
else
return L"";
}
else
return L"";
}
void RussianStemmer::markPositions(const String& word)
{
RV = 0;
R1 = 0;
R2 = 0;
int32_t i = 0;
// find RV
while ((int32_t)word.length() > i && !isVowel(word[i]))
++i;
if ((int32_t)word.length() - 1 < ++i)
return; // RV zone is empty
RV = i;
// find R1
while ((int32_t)word.length() > i && isVowel(word[i]))
++i;
if ((int32_t)word.length() - 1 < ++i)
return; // R1 zone is empty
R1 = i;
// find R2
while ((int32_t)word.length() > i && !isVowel(word[i]))
++i;
if ((int32_t)word.length() - 1 < ++i)
return; // R2 zone is empty
while ((int32_t)word.length() > i && isVowel(word[i]))
++i;
if ((int32_t)word.length() - 1 < ++i)
return; // R2 zone is empty
R2 = i;
}
char* en_en::getVerbPreAdd(int v){
FILE* rFile=fopen(DICTIONARY EN_EN_FOLDER "verb_present","r");
gotoline(rFile,v);
char* buffer=(char*)malloc(BUFFER_SIZE);
fgets(buffer,BUFFER_SIZE-1,rFile);
fclose(rFile);
char t=buffer[0];
if (t=='1'){
//Look up second word form
int u=0,i=0;
while (u<2){
if (buffer[i]=='_')
u++;
else if (buffer[i]==0)
break;
else if (buffer[i]=='\n')
break;
i++;
}
u=0;
while (buffer[i]!='_' && buffer[i]!=0 && buffer[i]!='\n')
buffer[u++]=buffer[i++];
buffer[u++]=0;
}else if (t=='0'){
char* b=getVerb(v,10,0,1,&blank);
int i=0;
while (b[i]!=0) i++;
//[(space)] [\0]
//We are removing the space here, because it is added in getVerb because the function thinks we will just add it straight to the sentence.
b[i-1]=0;
return b;
}else{
int i=0;
while(buffer[i]!='_' && buffer[i]!=0 && buffer[i]!='\n') i++;
i++;
int u=0;
while (buffer[i]!='_' && buffer[i]!=0 && buffer[i]!='\n')
buffer[u++]=buffer[i++];
//Now follow all the english rules
//http://www.oxforddictionaries.com/words/verb-tenses-adding-ed-and-ing
//http://www.grammar.cl/Notes/Spelling_ING.htm
if (buffer[u-1]=='e' && buffer[u-2]=='i'){
u-=2;
buffer[u++]='y';
}
else if (buffer[u-1]=='e' && (buffer[u-2]!='e' && buffer[u-2]!='y' && buffer[u-2]!='o'))
u-=1;
else if (buffer[u-1]=='c'){
buffer[u++]='k';
}
else if (!isVowel(buffer[u-3])&&isVowel(buffer[u-2])&&!isVowel(buffer[u-1])&&buffer[u-1]!='x'&&buffer[u-1]!='y'&&buffer[u-1]!='z'&&buffer[u-1]!='w'){
buffer[u]=buffer[u-1];
u++;
}
buffer[u++]=0;
}
return buffer;
}
inline void syllabize(
std::vector<std::string>& mTarget, const std::string& mWord)
{
auto itr(std::begin(mWord));
auto itrEnd(std::end(mWord));
auto valid([&itr, &itrEnd]() -> bool
{
return itr != itrEnd;
});
while(valid())
{
std::string currentSyllable;
// CASE: beginning VC
if(valid() && itr == std::begin(mWord) && isVowel(*itr) &&
isConsonant(*(itr + 1)))
{
currentSyllable += *itr++;
mTarget.emplace_back(currentSyllable);
continue;
}
// CASE: C...V
if(valid() && isConsonant(*itr))
{
while(valid() && isConsonant(*itr))
{
currentSyllable += *itr++;
if(valid() && isVowel(*itr))
{
currentSyllable += *itr++;
if(valid() && isConsonant(*itr))
{
char lastConsonant(*itr);
if(itr + 1 < itrEnd && *itr == lastConsonant &&
*(itr + 1) == lastConsonant)
{
currentSyllable += *itr++;
}
}
break;
}
}
}
// CASE: V
else if(valid() && isVowel(*itr))
{
currentSyllable += *itr++;
}
mTarget.emplace_back(currentSyllable);
}
}
string reverseVowels(string s) {
int i = 0, j = s.size() - 1;
while (i < j) {
while (i < j && !isVowel(s[i])) ++i;
while (i < j && !isVowel(s[j])) --j;
if (i < j) swap(s[i++], s[j--]);
}
return s;
}
int isIntervocalical(unsigned short string[], int size, int position)
{
if (position - 1 > 0 && position + 1 < size
&& ((isVowel(string[position - 1]) && isVowel(string[position + 1]))
|| (string[position - 1] != 0x0BCD
&& string[position + 1] != 0x0BCD))) {
return 1;
}
return 0;
}
string reverseVowels(string s) {
int i = 0, j = s.length()-1;
while (i < j) {
while (!isVowel(s[i])) ++i;
while (!isVowel(s[j])) --j;
if (i >= j) break;
swap(s[i++], s[j--]);
}
return s;
}
/* Like mgt0 above except we are looking for a value of m>1 instead
** or m>0
*/
static int m_gt_1(const char *z){
while( isVowel(z) ){ z++; }
if( *z==0 ) return 0;
while( isConsonant(z) ){ z++; }
if( *z==0 ) return 0;
while( isVowel(z) ){ z++; }
if( *z==0 ) return 0;
while( isConsonant(z) ){ z++; }
return *z!=0;
}
string reverseVowels(string s) {
// a e i o u
int lo = 0, hi = s.size() - 1;
while (lo < hi){
while (lo < s.size() && !isVowel(s[lo])) lo++;
if (lo > hi) break;
while (hi >= lo && !isVowel(s[hi])) hi--;
swap(s[lo++], s[hi--]);
}
return s;
}
string reverseVowels(string s) {
int left = 0, right = s.size() - 1;
while(left < right){
while(!isVowel(s[left])) ++left;
while(!isVowel(s[right])) --right;
if(left < right){
swap(s[left], s[right]);
}
++left;
--right;
}
return s;
}
string reverseVowels (string s) {
if (s.size() <= 1) return s;
int i = 0, j = s.size() - 1;
while (i < j) {
if (isVowel(s[i]) && isVowel(s[j]))
swap(s[i++], s[j--]);
else {
if (!isVowel(s[i])) ++i;
if (!isVowel(s[j])) --j;
}
}
return s;
}
int32_t DutchStemmer::getRIndex(int32_t start)
{
if (start == 0)
start = 1;
int32_t i = start;
for (; i < (int32_t)buffer.length(); ++i)
{
// first non-vowel preceded by a vowel
if (!isVowel(buffer[i]) && isVowel(buffer[i - 1]))
return i + 1;
}
return i + 1;
}
string reverseVowels(string s) {
int lo = -1,hi = s.length();
while(lo<hi){
if(isVowel(s[++lo])){
while(lo<hi&&!isVowel(s[--hi]));
s = swapChar(s,lo,hi);
}
}
return s;
}
string reverseVowels(string s) {
int l = 0, r = s.size() - 1;
while (l < r) {
while ((l < r) && !isVowel(s[l]))
l++;
while ((l < r) && !isVowel(s[r]))
r--;
if (l < r) {
swap(s[l], s[r]);
l++;
r--;
}
}
return s;
}
char* reverseVowels(char* s) {
int l = 0;
int r = strlen(s) - 1;
while (l < r) {
if (isVowel(s[l]) && isVowel(s[r]) ) {
swap(s + l, s + r);
l++;
r--;
} else {
if (!isVowel(s[l])) l++;
if (!isVowel(s[r])) r--;
}
}
return s;
}
/*
** Return TRUE if the word ends with three letters which
** are consonant-vowel-consonent and where the final consonant
** is not 'w', 'x', or 'y'.
**
** The word is reversed here. So we are really checking the
** first three letters and the first one cannot be in [wxy].
*/
static int star_oh(const char *z){
return
z[0]!=0 && isConsonant(z) &&
z[0]!='w' && z[0]!='x' && z[0]!='y' &&
z[1]!=0 && isVowel(z+1) &&
z[2]!=0 && isConsonant(z+2);
}
bool DutchStemmer::isValidSEnding(int32_t index)
{
wchar_t c = buffer[index];
if (isVowel(c) || c == L'j')
return false;
return true;
}
string toGoatLatin(string S) {
string result;
int n = S.size(), i = 0, count = 0;
while (i < n) {
++count;
string word;
while (i < n && S[i] != ' ') {
word += S[i++];
}
if (isVowel(word[0])) {
result += word + "ma";
}
else {
result += word.substr(1) + word.substr(0, 1) + "ma";
}
int j = count;
while (j--) {
result += 'a';
}
if (i < n) {
result += ' ';
}
++i;
}
return result;
}
char* removeVowels(char *sen) {
char *temp=sen, *returnVal;
int count = 0;
if (sen == NULL)
return NULL;
//find size of sen including \0
while (temp[count++] != '\0');
//alloc memory
returnVal = (char*)malloc(count*sizeof(char));
//again RESET TEMP, COUNT
temp = sen;count =0;
while (temp[0] != '\0') {
if (!isVowel(temp[0]))
returnVal[count++] = temp[0];
temp++;
}
returnVal[count]='\0';
return returnVal;
}
int nOfVowel(char * buffer, size_t stringLength)
{
if(stringLength==0)
return 0;
else
return isVowel(*buffer) + nOfVowel(buffer + 1, stringLength - 1);
}
main()
{
//get user input string
printf("Please enter a word to be turned to pig latin\n");
char str[100];
gets(str);
char first = str[0];
//perform the string manipulation to make pig latin
if (isVowel(first)==0)
{
char tmp[4];
tmp[0] = first; tmp[1] = 'a'; tmp[2] = 'y'; tmp[3] = '\0';
strcat(str, tmp);
memmove(str, str + 1, strlen(str));
printf("%s\n", str);
}
else
{
strcat(str, "yay");
printf("%s\n", str);
}
//stall indefinitely to show the result
while (1 == 1)
{
}
}
bool FrenchStemmer::deleteFromIfTestVowelBeforeIn(const String& source, Collection<String> search, bool vowel, const String& from)
{
bool found = false;
if (!source.empty() && !from.empty())
{
for (int32_t i = 0; i < search.size(); ++i)
{
if (boost::ends_with(source, search[i]))
{
if ((search[i].length() + 1) <= from.length())
{
bool test = isVowel(stringBuffer[stringBuffer.length() - (search[i].length() + 1)]);
if (test == vowel)
{
stringBuffer.resize(stringBuffer.length() - search[i].length());
modified = true;
found = true;
setStrings();
break;
}
}
}
}
}
return found;
}
void FrenchStemmer::step6()
{
if (!R0.empty())
{
bool seenVowel = false;
bool seenConson = false;
int32_t pos = -1;
for (int32_t i = (int32_t)(R0.length() - 1); i > -1; --i)
{
wchar_t ch = R0[i];
if (isVowel(ch))
{
if (!seenVowel)
{
if (ch == L'\x00e9' || ch == L'\x00e8')
{
pos = i;
break;
}
}
seenVowel = true;
}
else
{
if (seenVowel)
break;
else
seenConson = true;
}
}
if (pos > -1 && seenConson && !seenVowel)
stringBuffer[pos] = L'e';
}
}
string reverseVowels(string s) {
if(s.size() < 2)
return s;
std::deque<char> stack;
for(int i = 0; i < s.size(); i++){
if(isVowel(s[i]))
stack.push_back(s[i]);
}
for(int i = 0; i < s.size(); i++){
if(isVowel(s[i])){
s[i] = stack.back();
stack.pop_back();
}
}
return s;
}
const String NameManager::makeResourceName(bool isOrganic) {
int nameLength = 4 + System::random(6);
String name;
do {
name = "";
if (nameLength > 5 && System::random(2) == 1) {
addPrefix(name, isOrganic);
}
if(name.length() < 2) {
name += chooseNextLetter(' ', ' ');
name += chooseNextLetter(name[0], ' ');
}
assert(name.length() != 0);
while (name.length() < nameLength)
name += chooseNextLetter(name[name.length() - 1], name[name.length() - 2]);
if (!isVowel(name[name.length() - 1]) && name[name.length() - 1] != 'q' && System::random(1) == 1 )
addSuffix(name, isOrganic);
name[0] = Character::toUpperCase(name[0]);
} while (validateName(name, -1) != NameManagerResult::ACCEPTED);
return name;
}
void DutchStemmer::step4()
{
if (buffer.length() < 4)
return;
String end(buffer.substr(buffer.length() - 4));
if (end[1] == end[2] && end[3] != L'I' && end[1] != L'i' && isVowel(end[1]) && !isVowel(end[3]) && !isVowel(end[0]))
buffer.erase(buffer.length() - 2, 1);
}
static int isConsonant(const char *z){
int j;
char x = *z;
if( x==0 ) return 0;
assert( x>='a' && x<='z' );
j = cType[x-'a'];
if( j<2 ) return j;
return z[1]==0 || isVowel(z + 1);
}
