void SieveParser::whitespace()
{
uint p;
do {
p = pos();
switch( nextChar() ) {
case '#':
case '/':
comment();
break;
case ' ':
case '\t':
case '\r':
case '\n':
step();
break;
}
} while ( ok() && pos() > p );
}
/* recebe um número inteiro */
void getNum(char *num){
int i;
if (!isdigit(look))
expected("Integer");
for (i = 0; isdigit(look); i++) {
if (i >= MAXNUM)
fatal("Integer too long!");
num[i] = look;
nextChar();
}
num[i] = '\0';
skipWhite();
}
Token::Ptr MutCTokenizer::extractToken ()
{
Token::Ptr token;
// terminate
if (currentChar () == EOF)
{
token = make_shared <TerminatorToken> (__source);
}
// skip space character
else if (isspace (currentChar ()))
{
nextChar ();
return extractToken ();
}
// number
else if (currentChar () >= '0' && currentChar () <= '9')
{
token = make_shared<NumberToken> (__source);
}
// identifier
else if (isalpha (currentChar ()) || currentChar () == '_')
{
token = make_shared <IdentifierToken> (__source);
}
// symbol
else if (! isalnum (currentChar ()) && currentChar () != '_')
{
token = make_shared <SymbolToken> (__source);
}
// string
else if (currentChar () == '"')
{
token = make_shared <StringToken> (__source);
}
else
{
// TODO error handling: unexpected beginning character
return nullptr;
}
token->build (__source);
return token;
}
/* Checks whether the parentheses are balanced or not
param: s pointer to a string
pre: s is not null
post:
*/
int isBalanced(char* s)
{
struct DynArr *array = newDynArr(10);
char c;
while((c = nextChar(s)) != '0'){
switch(c){
case '{' :
case '[' :
case '(' :
pushDynArr(array, c);
break;
case '}' :
if(topDynArr(array) == '{'){
popDynArr(array);
break;
}
return 0;
case ']' :
if(topDynArr(array) == '['){
popDynArr(array);
break;
}
return 0;
case ')' :
if(topDynArr(array) == '('){
popDynArr(array);
break;
}
return 0;
}
}
if(array->size != 0){
return 0;
}
deleteDynArr(array);
return 1;
}
static void cmdLnBatchFlushCrap(// FLUSH CARRIAGE-RETURNS, ETC
void )
{
int chr; // - next char
if( ! CompFlags.batch_file_eof ) {
for( ; ; ) {
chr = nextChar();
if( CompFlags.batch_file_eof ) break;
if( chr == '\n' ) {
++ CompInfo.fc_file_line;
continue;
}
-- batch_cursor;
*batch_cursor = chr;
++ batch_bytes;
break;
}
}
}
void TwoBitFile::createSequenceMeta()
{
// create SequenceMeta objects from name and offset
uint32_t seqNameLen, offset;
char seqName[SEQNAME_MAX_LEN];
std::string seqNameStr; // name as std::string
for (uint32_t i = 0; i < sequenceCount_; ++i) {
seqNameLen = nextChar(); // length
file_.read(seqName, seqNameLen); // sequence name
seqNameStr = std::string(seqName, seqNameLen);
offset = nextInt(); // offset
// add meta data.
sequences_.emplace(seqNameStr,
TwoBitSequenceMeta(seqNameStr, offset, filename_, swapped_));
sequenceNames_.push_back(seqNameStr);
}
}
/*******************************************************************************
* Lexer Definitions
******************************************************************************/
KAbstractObjParserPrivate::token_id KAbstractObjParserPrivate::lexToken(token_type &token)
{
// Skip unimplemented features
switch (currToken())
{
case PT_GROUP:
case PT_OBJECT:
case PT_SMOOTHING:
case PT_MATERIAL:
nextLine();
break;
}
// Tokenization
for (;;)
{
switch (nextChar())
{
case KAbstractReader::EndOfFile:
return PT_EOF;
case WHITESPACE:
continue;
case '\n':
return PT_ENDSTATEMENT;
case '#':
nextLine();
return PT_ENDSTATEMENT;
case '/':
return PT_SEPARATOR;
case '.':
default:
if (Karma::isNumeric(currChar()))
return lexTokenInteger(token);
else if (Karma::isAlpha(currChar()))
return lexTokenIdentifier(token);
else
LEX_ERROR("Unexpected character at (%d:%d) '%c'!\n", (int)currLineCount(), (int)currCharCount(), (char)currChar());
}
}
}
static void skipToMatch (const char *const pair)
{
const int begin = pair [0], end = pair [1];
const unsigned long inputLineNumber = getInputLineNumber ();
int matchLevel = 1;
int c = '\0';
while (matchLevel > 0)
{
c = nextChar ();
if (c == begin)
++matchLevel;
else if (c == end)
--matchLevel;
else if (c == '\n')
break;
}
if (c == EOF)
verbose ("%s: failed to find match for '%c' at line %lu\n",
getInputFileName (), begin, inputLineNumber);
}
/*******************************************************************************
* Lexer Definitions
******************************************************************************/
KAbstractHdrParserPrivate::token_id KAbstractHdrParserPrivate::lexToken(KAbstractLexer::token_type &token)
{
// Tokenization
for (;;)
{
switch (nextChar())
{
case KAbstractReader::EndOfFile:
return PT_EOF;
case WHITESPACE:
return PT_ENDSTATEMENT;
case '\n':
return PT_ENDOFHEADER;
case '#':
nextLine();
return PT_ENDSTATEMENT;
default:
return lexTokenKeyValue(token);
}
}
}
bool tokenize() {
char c;
while(1) {
c = nextChar();
printf("%c\n", c);
switch ( getState(c) ) {
case START_STATE:
tokenIndex = 0;
memset(token, 0, 100);
break;
case VARIABLE_STATE:
if ( prevState != VARIABLE_STATE ) {
tokenIndex = 0;
memset(token, 0, 100);
}
concat(c);
break;
case INTEGER_STATE:
if ( prevState != VARIABLE_STATE ) {
tokenIndex = 0;
memset(token, 0, 100);
}
concat(c);
break;
case OPERATOR_STATE:
break;
case END_OPERATOR_STATE:
break;
case FINAL_STATE:
printf("Parse complete. Exiting.\n");
return true;
case ERROR_STATE:
printf("Syntax error. Exiting.\n");
return false;
default:
printf("Unexpected error!\n");
return false;
}
}
}
void InText::readDouble(double& d, PhysicalInStream& stream)
{
buf = "";
skipWhitespace(stream);
if(!isEof(stream) && (theChar == '-' || theChar == '+'))
{
buf += theChar;
nextChar(stream);
}
while(!isEof(stream) && isdigit(theChar))
{
buf += theChar;
nextChar(stream);
}
if(!isEof(stream) && theChar == '.')
{
buf += theChar;
nextChar(stream);
}
while(!isEof(stream) && isdigit(theChar))
{
buf += theChar;
nextChar(stream);
}
if(!isEof(stream) && (theChar == 'e' || theChar == 'E'))
{
buf += theChar;
nextChar(stream);
}
if(!isEof(stream) && (theChar == '-' || theChar == '+'))
{
buf += theChar;
nextChar(stream);
}
while(!isEof(stream) && isdigit(theChar))
{
buf += theChar;
nextChar(stream);
}
d = atof(buf.c_str());
skipWhitespace(stream);
}
int KAbstractObjParserPrivate::lexReadInteger(int *sign)
{
*sign = 1;
int integer = 0;
// Check for negation
if (currChar() == '-')
*sign = -1;
else if (currChar() == '+')
; // Do nothing, sign is already 1
else
integer = Karma::ctoi(currChar());
// Read the integer value
while (Karma::isNumeric(peekChar()))
{
integer *= 10;
integer += Karma::ctoi(nextChar());
}
return integer;
}
void Scanner::nextToken()
{
nextTokenInternal();
while (ftoken == CodeTypes::tStartComment)
{
// Comment ends with an end of line char
while ((fch != LF) && (fch != EOFCHAR))
fch = getCharFromBuffer();
//while ((fch != CR) && (fch != EOFCHAR))
// fch = getCharFromBuffer();
//while ((fch == LF) && (fch != EOFCHAR))
// fch = getCharFromBuffer();
while (fch == LF)
{
yylineno++;
//while (fch == LF)
// nextChar(); // Dump the linefeed
fch = nextChar();
}
nextTokenInternal(); // get the real next token
}
}
TokenT *_expofloat(TokenizerT *tk, int isFirst, int lastWasSign) {
nextChar(tk);
if(isdigit(tk->inputIter[0])) {
return _expofloat(tk, 0, 0);
} else if(tk->inputIter[0] == '+' || tk->inputIter[0] == '-') {
if(isFirst) {
return _expofloat(tk, 0, 1);
} else if(lastWasSign) {
return _invalid(tk);
} else {
return makeToken(tk, "float with exponent");
}
} else {
if(isFirst) {
return _invalid(tk);
} else if(lastWasSign) {
return _invalid(tk);
} else {
return makeToken(tk, "float with exponent");
}
}
}
QChar QComplexText::shapedCharacter( const QString &str, int pos, const QFontMetrics *fm )
{
const QChar *ch = str.unicode() + pos;
if ( ch->row() != 0x06 )
return *ch;
else {
int shape = glyphVariantLogical( str, pos );
//qDebug("mapping U+%x to shape %d glyph=0x%x", ch->unicode(), shape, arabicUnicodeMapping[ch->cell()][shape]);
// lam aleph ligatures
switch ( ch->cell() ) {
case 0x44: { // lam
const QChar *nch = nextChar( str, pos );
if ( nch->row() == 0x06 ) {
switch ( nch->cell() ) {
case 0x22:
case 0x23:
case 0x25:
case 0x27:
return QChar(arabicUnicodeLamAlefMapping[nch->cell() - 0x22][shape]);
default:
break;
}
}
break;
}
case 0x22: // alef with madda
case 0x23: // alef with hamza above
case 0x25: // alef with hamza below
case 0x27: // alef
if ( prevChar( str, pos )->unicode() == 0x0644 )
// have a lam alef ligature
return QChar(0);
default:
break;
}
return QChar( getShape( ch, ch->cell(), shape, fm ) );
}
}
LexBase::LexBase(const char * str) throw(ConfigurationException)
{
StringBuffer msg;
//--------
// Initialize state for the multi-byte functions in the C library.
//--------
memset(&m_mbtowcState, 0, sizeof(mbstate_t));
m_keywordInfoArray = 0;
m_keywordInfoArraySize = 0;
m_funcInfoArray = 0;
m_funcInfoArraySize = 0;
m_uidIdentifierProcessor = new UidIdentifierDummyProcessor();
m_amOwnerOfUidIdentifierProcessor = true;
m_sourceType = Configuration::INPUT_STRING;
m_source = str;
m_lineNum = 1;
m_ptr = m_source;
m_atEOF = false;
nextChar(); // initialize m_ch
}
void InConfig::skipWhitespace(PhysicalInStream& stream)
{
while(!isEof(stream) && isWhitespace())
{
while(!isEof(stream) && InText::isWhitespace())
nextChar(stream);
if(!isEof(stream))
{
if(theChar == '/' && theNextChar == '/')
{
skipLine(stream);
}
else if(theChar == '/' && theNextChar == '*')
{
skipComment(stream);
}
else if(theChar == '#')
{
skipLine(stream);
}
}
}
}
bool FlowLexer::initialize(std::istream *input, const std::string& name)
{
stream_ = input;
filename_ = name;
if (stream_ == NULL)
return false;
lastPos_.set(1, 1, 0);
currPos_.set(1, 1, 0);
nextPos_.set(1, 1, 0);
currentChar_ = '\0';
currLocation_.fileName = filename_;
currLocation_.begin.set(1, 1, 0);
currLocation_.end.set(1, 1, 0);
content_.clear();
nextChar();
nextToken();
return true;
}
/* Checks whether the (), {}, and [] are balanced or not
param: s pointer to a string
pre: s is not null
post:
*/
int isBalanced(char* s)
{
char c = ' ';
int ret_val = 0;
struct DynArr* stack = newDynArr(10);
assert(stack != 0);
assert(s != 0);
while (c != '\0'){
ret_val = 1;
c = nextChar(s);
if (c == '(' || c == '[' || c == '{') pushDynArr(stack,c);
if (c == ')' || c == ']' || c == '}') {
if (c == ')' && topDynArr(stack) == '(') popDynArr(stack);
else if (c == ']' && topDynArr(stack) == '[') popDynArr(stack);
else if (c == '}' && topDynArr(stack) == '{') popDynArr(stack);
else return 0;
}
}
if (ret_val) ret_val = !(isEmptyDynArr(stack));
printf("return value %d\n", ret_val);
deleteDynArr(stack);
return ret_val;
}
int
thisIsTheEnd(OBJ inStream){
/*
* This is the end
* Beautiful friend
* This is the end
* My only friend, the end
*/
int end = 0;
char ch;
do{
//printf(CYN "\nendSearch: " RESET);
ch = nextChar(inStream);
if(ch == '\n' || ch == EOF){
//printf(RED "<END>" RESET);
end = 1;
break;
}
} while (isWhiteSpace(ch));
unreadChar(inStream, ch);
return end;
}
Statement* Parser::parse(const String& file, Engine::ErrorHandler errorHandler, void* userData)
{
this->errorHandler = errorHandler;
this->errorHandlerUserData = userData;
this->filePath = file;
try
{
if(!this->file.open(file))
{
errorHandler(errorHandlerUserData, file, 0, Error::getString());
throw false;
}
includeFile = new IncludeFile(engine);
includeFile->fileDir = File::getDirname(file);
nextChar(); // read first character
nextToken(); // read first symbol
return readFile();
}
catch(...)
{
return 0;
}
}
/*
* TKGetNextToken returns the next token from the token stream as a
* character string. Space for the returned token should be dynamically
* allocated. The caller is responsible for freeing the space once it is
* no longer needed.
*
* If the function succeeds, it returns a C string (delimited by '\0')
* containing the token. Else it returns 0.
*
* You need to fill in this function as part of your implementation.
*/
TokenT *TKGetNextToken(TokenizerT *tk) {
clearBuffer(tk);
char curr = tk->inputIter[0];
// skip all whitespace before next token
while(isspace(curr)) {
nextChar(tk);
clearBuffer(tk);
curr = tk->inputIter[0];
}
if(curr == '\0') {
return NULL;
} else if(isalpha(curr) || curr == '_') {
return _word(tk);
} else if(curr == '0') {
return _zero(tk);
} else if(isdigit(curr)) {
return _decimal(tk);
} else if(curr == '!') { // neq
return _neq(tk);
} else if(curr == '"') { // double_quote
return _double_quote(tk);
} else if(curr == '#') {
return _pound(tk);
} else if(curr == '$') { // INVALID
return _invalid(tk);
} else if(curr == '%') { // mod, mod_eq
return _mod(tk);
} else if(curr == '&') { // bit_and, log_and, address (?)
return _bit_and(tk);
} else if(curr == '\'') { // single_quote
return _single_quote(tk);
} else if(curr == '(') { // open_paren
return _open_paren(tk);
} else if(curr == ')') { // close_paren
return _close_paren(tk);
} else if(curr == '*') { // mult, mult_eq, pointer (?)
return _mult(tk);
} else if(curr == '+') { // plus, plus_eq, inc
return _plus(tk);
} else if(curr == ',') { // comma
return _comma(tk);
} else if(curr == '-') { // minus, minus_eq, dec, struct_pointer
return _minus(tk);
} else if(curr == '.') { // dot
return _dot(tk);
} else if(curr == '/') { // div, div_eq
return _div(tk);
} else if(curr == ':') { // ternary_colon
return _ternary_colon(tk);
} else if(curr == ';') { // semicolon
return _semicolon(tk);
} else if(curr == '<') { // lt, lshift, lt_eq
return _lt(tk);
} else if(curr == '=') { // eq, assign
return _eq(tk);
} else if(curr == '>') { // gt, rshift, gt_eq
return _gt(tk);
} else if(curr == '?') { // ternary_qmark
return _ternary_qmark(tk);
} else if(curr == '@') { // INVALID
return _invalid(tk);
} else if(curr == '[') { // open_bracket
return _open_bracket(tk);
} else if(curr == '\\') { // backslash (?)
return _invalid(tk);
} else if(curr == ']') { // close_bracket
return _close_bracket(tk);
} else if(curr == '^') { // bit_xor
return _bit_xor(tk);
} else if(curr == '`') { // INVALID
return _invalid(tk);
} else if(curr == '{') { // open_brace
return _open_brace(tk);
} else if(curr == '|') { // bit_or, log_or
return _bit_or(tk);
} else if(curr == '}') { // close_brace
return _close_brace(tk);
} else if(curr == '~') { // bit_not
return _bit_not(tk);
} else {
return _invalid(tk);
}
}
bool MorkParser::parseCell()
{
bool Result = true;
bool bColumnOid = false;
bool bValueOid = false;
bool bColumn = true;
int Corners = 0;
// Column = Value
QString Column;
QString Text;
char cur = nextChar();
// Process cell start with column (bColumn == true)
while (Result && cur != ')' && cur) {
switch (cur) {
case '^':
// Oids
Corners++;
if (Corners == 1) {
bColumnOid = true;
} else if (Corners == 2) {
bColumn = false;
bValueOid = true;
} else {
Text += cur;
}
break;
case '=':
// From column to value
if (bColumn) {
bColumn = false;
} else {
Text += cur;
}
break;
case '\\': {
// Get next two chars
char NextChar = nextChar();
if ('\r' != NextChar && '\n' != NextChar) {
Text += NextChar;
} else {
nextChar();
}
}
break;
case '$': {
// Get next two chars
QString HexChar;
HexChar += nextChar();
HexChar += nextChar();
Text += (char) HexChar.toInt(0, 16);
}
break;
default:
// Just a char
if (bColumn) {
Column += cur;
} else {
Text += cur;
}
break;
}
cur = nextChar();
}
Q_UNUSED(bColumnOid);
// Apply column and text
int ColumnId = Column.toInt(0, 16);
if (NPRows != nowParsing_) {
// Dicts
if (!Text.isEmpty()) {
if (nowParsing_ == NPColumns) {
mColumns[ ColumnId ] = Text;
//qCDebug(IMPORTWIZARD_LOG)<<" column :"<<ColumnId<<" Text "<<Text;
} else {
mValues[ ColumnId ] = Text;
//qCDebug(IMPORTWIZARD_LOG)<<" ColumnId "<<ColumnId<<" Value : "<<Text;
}
}
} else {
if (!Text.isEmpty()) {
// Rows
int ValueId = Text.toInt(0, 16);
if (bValueOid) {
(*mCurrentCells)[ ColumnId ] = ValueId;
} else {
mNextAddValueId--;
mValues[ mNextAddValueId ] = Text;
(*mCurrentCells)[ ColumnId ] = mNextAddValueId;
}
}
}
return Result;
}
TokenT *_pound(TokenizerT *tk) {
nextChar(tk);
return makeToken(tk, "include operator");
}
TokenT *_ternary_colon(TokenizerT *tk) {
nextChar(tk);
return makeToken(tk, "ternary colon operator");
}
TokenT *_close_brace(TokenizerT *tk) {
nextChar(tk);
return makeToken(tk, "closing brace");
}
TokenT *_open_brace(TokenizerT *tk) {
nextChar(tk);
return makeToken(tk, "opening brace");
}
TokenT *_bit_xor(TokenizerT *tk) {
nextChar(tk);
return makeToken(tk, "bitwise-xor operator");
}
TokenT *_ternary_qmark(TokenizerT *tk) {
nextChar(tk);
return makeToken(tk, "ternary question mark operator");
}
TokenT *_semicolon(TokenizerT *tk) {
nextChar(tk);
return makeToken(tk, "end-of-statement operator");
}
