bool SingleLineDelimTextFileReader::detectAndHandleHeader()
{
if (!isHeaderLine(_sLine)) {
return false;
}
if (!_fullHeaderFound) {
_header += _sLine;
_header += "\n"; //add new line, since it was chomped by getline
}
return true;
}
void createHeader(FileWriter& writer, FileReader& reader) {
std::string line("");
while (true){
line = reader.getNextLine() + "\n";
if (isHeaderLine(line)) {
writer.writeLine(line);
} else if (isCommentLine(line)) {
writer.writeLine(line);
return;
}
if (!reader.isGood()) return;
}
};
bool SingleLineDelimTextFileReader::detectAndHandleHeader()
{
//not sure why the linker is giving me a hard time about
//passing a non-const string to isHeaderLine, but
//this const ref is a workaround.
const string &sLine2 = _sLine;
if (!isHeaderLine(sLine2) && (!(_inheader && _lineNum==1))) {
return false;
}
if (!_fullHeaderFound) {
_header += _sLine;
_header += "\n"; //add new line, since it was chomped by getline
}
return true;
}
void VcfFile::parseHeader() {
if ( isHeaderLine() ) {
lineTokens.ReplaceColumns(line, '\t');
verifyHeaderLine();
if ( lineTokens.Length() > 8 ) {
int sampleCount = lineTokens.Length() - 9;
vpVcfInds.resize(sampleCount);
for(int i=0; i < sampleCount; ++i) {
vpVcfInds[i] = new VcfInd(lineTokens[9+i]);
}
}
else {
for(int i=0; i < (int) vpVcfInds.size(); ++i) {
delete vpVcfInds[i];
}
vpVcfInds.clear();
}
}
else {
throw VcfFileException("Header line is not found : #CHROM...");
}
}
void LatexLexer::styleText(int start,int end)
{
// Ajouter support verbatim
// Colorier les erreurs de syntaxe
if (!editor())
return;
char *lineChars = new char[end - start+1];
editor()->SendScintilla(QsciScintilla::SCI_GETTEXTRANGE, start, end, lineChars);
QString source = QString(lineChars);
free(lineChars);
startStyling(start,0xFF);
QStringList list=source.split('\n');
int lineIndex=editor()->SendScintilla(QsciScintilla::SCI_LINEFROMPOSITION, start);
int style=Default,nextStyle=Default;
if(lineIndex>0){
int pos = editor()->SendScintilla(QsciScintilla::SCI_GETLINEENDPOSITION, lineIndex-1 );
if(pos>0){
int s = editor()->SendScintilla(QsciScintilla::SCI_GETSTYLEAT, pos);
if(s==MathInline || s==MathDisplay || s==Environment){
style=s;
nextStyle=s;
}
}
}
int level=QsciScintilla::SC_FOLDLEVELBASE;
if(lineIndex>0){
QString previousLine = getLine(lineIndex-1);
level=(editor()->SendScintilla(QsciScintilla::SCI_GETFOLDLEVEL,lineIndex-1)&QsciScintilla::SC_FOLDLEVELNUMBERMASK)+getDiffLevel(previousLine);
}
int nbCharsToStyle;
int styleBeforeMathDisplay=Default,styleBeforeMathInline=Default,styleInBrace=Default,styleBeforeBrace=Default;
for (int i = 0; i < list.size(); i++) {
QString line=list.at(i);
int lineLength=line.size();
if(style!=MathInline && style!=MathDisplay && style!=Environment){
style=Default;
nextStyle=Default;
}
int j=0;
while(j<lineLength){
QString l=line.mid(j);
if(l.startsWith("\\%")){
nbCharsToStyle=2;
nextStyle=style;
style=Command;
}
else if(l.startsWith("%")){
nbCharsToStyle=lineLength-j;
style=Comment;
nextStyle=Comment;
}
else if(l.startsWith("\\[")){
nbCharsToStyle=2;
styleBeforeMathDisplay=style;
style=Command;
nextStyle=MathDisplay;
}
else if(l.startsWith("\\]")){
nbCharsToStyle=2;
style=Command;
nextStyle=styleBeforeMathDisplay;
}
else if(l.startsWith("\\(")){
nbCharsToStyle=2;
styleBeforeMathInline=style;
style=Command;
nextStyle=MathInline;
}
else if(l.startsWith("\\)")){
nbCharsToStyle=2;
style=Command;
nextStyle=styleBeforeMathInline;
}
else if(l.startsWith("\\$") || l.startsWith("\\{") || l.startsWith("\\}")){
nbCharsToStyle=2;
nextStyle=style;
style=Command;
}
else if(l.startsWith("\\")){
nbCharsToStyle=1;
nextStyle=style;
while(nbCharsToStyle<l.size() && l.at(nbCharsToStyle).isLetter()){
nbCharsToStyle++;
}
QString s=l.left(nbCharsToStyle);
if(s=="\\begin" || s=="\\end"){
styleInBrace=Environment;
}
else if(s=="\\part"){
styleInBrace=Part;
}
else if(s=="\\chapter"){
styleInBrace=Chapter;
}
else if(s=="\\section"){
styleInBrace=Section;
}
else if(s=="\\subsection"){
styleInBrace=SubSection;
}
else if(s=="\\subsubsection"){
styleInBrace=SubSubSection;
}
else if(s=="\\paragraph"){
styleInBrace=Paragraph;
}
else if(s=="\\subparagraph"){
styleInBrace=SubParagraph;
}
style=Command;
}
else if(l.startsWith("$")){
nbCharsToStyle=1;
if(style==MathInline){
nextStyle=styleBeforeMathInline;
}
else{
styleBeforeMathInline=style;
nextStyle=MathInline;
}
style=SpecialChar;
}
else if(l.at(0).isDigit()){
bool isNumber=true;
nbCharsToStyle=1;
nextStyle=style;
while(isNumber && nbCharsToStyle<l.size()){
nbCharsToStyle++;
l.left(nbCharsToStyle).toFloat(&isNumber);
}
if(!isNumber){
nbCharsToStyle--;
}
style=Digit;
}
else if(l.startsWith("(")||l.startsWith(")")||l.startsWith("[")||l.startsWith("]")||l.startsWith("&")||l.startsWith("#")){
nbCharsToStyle=1;
nextStyle=style;
style=SpecialChar;
}
else if(l.startsWith("{")){
nbCharsToStyle=1;
styleBeforeBrace=style;
nextStyle=styleInBrace;
style=SpecialChar;
}
else if(l.startsWith("}")){
nbCharsToStyle=1;
nextStyle=styleBeforeBrace;
style=SpecialChar;
styleInBrace=Default;
}
else{
nbCharsToStyle=1;
if(l.at(0)!=' '){
styleInBrace=style;
}
}
setStyling(nbCharsToStyle,defaultStyle(style));
style=nextStyle;
j+=nbCharsToStyle;
}
setStyling(1,defaultStyle(style));
QString s=trimComment(line);
if(s.contains("\\part")){
level=2000;
}
else if(s.contains("\\chapter")){
level=2001;
}
else if(s.contains("\\section")){
level=2002;
}
else if(s.contains("\\subsection")){
level=2003;
}
else if(s.contains("\\subsubsection")){
level=2004;
}
else if(s.contains("\\paragraph")){
level=2005;
}
else if(s.contains("\\subparagraph")){
level=2006;
}
if(isHeaderLine(s)){
editor()->SendScintilla(QsciScintilla::SCI_SETFOLDLEVEL,lineIndex,level|QsciScintilla::SC_FOLDLEVELHEADERFLAG);
}
/*
else if(line.trimmed().isEmpty()){
editor()->SendScintilla(QsciScintilla::SCI_SETFOLDLEVEL,lineIndex,level|QsciScintilla::SC_FOLDLEVELWHITEFLAG);
}
*/
else{
editor()->SendScintilla(QsciScintilla::SCI_SETFOLDLEVEL,lineIndex,level);
}
level+=getDiffLevel(s);
lineIndex++;
}
}
bool FileRecordTypeChecker::isTextDelimtedFormat(const char *buffer, size_t len)
{
//Break single string buffer into vector of QuickStrings. Delimiter is newline.
_tokenizer.setKeepFinalIncompleteElem(Tokenizer::IGNORE);
int numLines = _tokenizer.tokenize(buffer, '\n', _eofHit);
//anticipated delimiter characters are tab, comma, and semi-colon.
//If we need new ones, they must be added in this method.
//search each line for delimiter characters.
vector<int> tabCounts;
vector<int> commaCounts;
vector<int> semicolonCounts;
tabCounts.reserve(numLines);
commaCounts.reserve(numLines);
semicolonCounts.reserve(numLines);
//loop through the lines, ignoring headers. Count potential delimiters,
//see if we can find a few lines with the same number of a given delimiter.
//delims are tested in hierarchical order, starting with tab,then comma, then semi-colon.
int validLinesFound=0;
int headerCount = 0;
int emptyLines = 0;
for (int i=0; i < numLines; i++ ) {
if (validLinesFound >=4) {
break; //really only need to look at like 4 lines of data, max.
}
const QuickString &line = _tokenizer.getElem(i);
int len =line.size();
//skip over any empty line
if (len == 0) {
emptyLines++;
continue;
}
//skip over any header line
if (isHeaderLine(line)) {
//clear any previously found supposedly valid data lines, because valid lines can only come after header lines.
if (_firstValidDataLineIdx > -1 && _firstValidDataLineIdx < i) {
_firstValidDataLineIdx = -1;
validLinesFound--;
headerCount++;
}
headerCount++;
continue;
}
//a line must have some alphanumeric characters in order to be valid.
bool hasAlphaNum = false;
for (int j=0; j < len; j++) {
if(isalnum(line[j])) {
hasAlphaNum = true;
break;
}
}
if (!hasAlphaNum) {
continue;
}
validLinesFound++;
if (_firstValidDataLineIdx == -1) {
_firstValidDataLineIdx = i;
}
int lineTabCount = 0, lineCommaCount=0, lineSemicolonCount =0;
for (int j=0; j < len; j++) {
char currChar = line[j];
if (currChar == '\t') {
lineTabCount++;
} else if (currChar == ',') {
lineCommaCount++;
} else if (currChar == ';') {
lineSemicolonCount++;
}
}
tabCounts.push_back(lineTabCount);
commaCounts.push_back(lineCommaCount);
semicolonCounts.push_back(lineSemicolonCount);
}
if (headerCount + emptyLines == numLines) {
_insufficientData = true;
}
if (validLinesFound == 0) {
return false;
}
_insufficientData = false;
if (delimiterTesting(tabCounts, '\t')) {
return true;
}
if (delimiterTesting(commaCounts, ',')) {
return true;
}
if (delimiterTesting(semicolonCounts, ';')) {
return true;
}
return false; //unable to detect delimited file.
}
