private boolean parseExtlangs(StringTokenIterator itr, ParseStatus sts) {
if (itr.isDone() || sts.isError()) {
return false;
}
boolean found = false;
while (!itr.isDone()) {
String s = itr.current();
if (!isExtlang(s)) {
break;
}
found = true;
if (extlangs.isEmpty()) {
extlangs = new ArrayList<>(3);
}
extlangs.add(s);
sts.parseLength = itr.currentEnd();
itr.next();
if (extlangs.size() == 3) {
// Maximum 3 extlangs
break;
}
}
return found;
}
private boolean parseRegion(StringTokenIterator itr, ParseStatus sts) {
if (itr.isDone() || sts.isError()) {
return false;
}
boolean found = false;
String s = itr.current();
if (isRegion(s)) {
found = true;
region = s;
sts.parseLength = itr.currentEnd();
itr.next();
}
return found;
}
private boolean parseExtensions(StringTokenIterator itr, ParseStatus sts) {
if (itr.isDone() || sts.isError()) {
return false;
}
boolean found = false;
while (!itr.isDone()) {
String s = itr.current();
if (isExtensionSingleton(s)) {
int start = itr.currentStart();
String singleton = s;
StringBuilder sb = new StringBuilder(singleton);
itr.next();
while (!itr.isDone()) {
s = itr.current();
if (isExtensionSubtag(s)) {
sb.append(SEP).append(s);
sts.parseLength = itr.currentEnd();
} else {
break;
}
itr.next();
}
if (sts.parseLength <= start) {
sts.errorIndex = start;
sts.errorMsg = "Incomplete extension '" + singleton + "'";
break;
}
if (extensions.isEmpty()) {
extensions = new ArrayList<>(4);
}
extensions.add(sb.toString());
found = true;
} else {
break;
}
}
return found;
}
/*
* BNF in RFC5646
*
* Language-Tag = langtag ; normal language tags
* / privateuse ; private use tag
* / grandfathered ; grandfathered tags
*
*
* langtag = language
* ["-" script]
* ["-" region]
* *("-" variant)
* *("-" extension)
* ["-" privateuse]
*
* language = 2*3ALPHA ; shortest ISO 639 code
* ["-" extlang] ; sometimes followed by
* ; extended language subtags
* / 4ALPHA ; or reserved for future use
* / 5*8ALPHA ; or registered language subtag
*
* extlang = 3ALPHA ; selected ISO 639 codes
* *2("-" 3ALPHA) ; permanently reserved
*
* script = 4ALPHA ; ISO 15924 code
*
* region = 2ALPHA ; ISO 3166-1 code
* / 3DIGIT ; UN M.49 code
*
* variant = 5*8alphanum ; registered variants
* / (DIGIT 3alphanum)
*
* extension = singleton 1*("-" (2*8alphanum))
*
* ; Single alphanumerics
* ; "x" reserved for private use
* singleton = DIGIT ; 0 - 9
* / %x41-57 ; A - W
* / %x59-5A ; Y - Z
* / %x61-77 ; a - w
* / %x79-7A ; y - z
*
* privateuse = "x" 1*("-" (1*8alphanum))
*
*/
public static LanguageTag parse(String languageTag, ParseStatus sts) {
if (sts == null) {
sts = new ParseStatus();
} else {
sts.reset();
}
StringTokenIterator itr;
// Check if the tag is grandfathered
String[] gfmap = GRANDFATHERED.get(LocaleUtils.toLowerString(languageTag));
if (gfmap != null) {
// use preferred mapping
itr = new StringTokenIterator(gfmap[1], SEP);
} else {
itr = new StringTokenIterator(languageTag, SEP);
}
LanguageTag tag = new LanguageTag();
// langtag must start with either language or privateuse
if (tag.parseLanguage(itr, sts)) {
tag.parseExtlangs(itr, sts);
tag.parseScript(itr, sts);
tag.parseRegion(itr, sts);
tag.parseVariants(itr, sts);
tag.parseExtensions(itr, sts);
}
tag.parsePrivateuse(itr, sts);
if (!itr.isDone() && !sts.isError()) {
String s = itr.current();
sts.errorIndex = itr.currentStart();
if (s.length() == 0) {
sts.errorMsg = "Empty subtag";
} else {
sts.errorMsg = "Invalid subtag: " + s;
}
}
return tag;
}
/**
* Parses Javadoc comment as DetailNode tree.
*
* @param javadocCommentAst DetailAST of Javadoc comment
* @return DetailNode tree of Javadoc comment
*/
public ParseStatus parseJavadocAsDetailNode(DetailAST javadocCommentAst) {
blockCommentLineNumber = javadocCommentAst.getLineNo();
final String javadocComment = JavadocUtils.getJavadocCommentContent(javadocCommentAst);
// Use a new error listener each time to be able to use
// one check instance for multiple files to be checked
// without getting side effects.
errorListener = new DescriptiveErrorListener();
// Log messages should have line number in scope of file,
// not in scope of Javadoc comment.
// Offset is line number of beginning of Javadoc comment.
errorListener.setOffset(javadocCommentAst.getLineNo() - 1);
final ParseStatus result = new ParseStatus();
try {
final ParseTree parseTree = parseJavadocAsParseTree(javadocComment);
final DetailNode tree = convertParseTreeToDetailNode(parseTree);
result.setTree(tree);
} catch (ParseCancellationException ex) {
// If syntax error occurs then message is printed by error listener
// and parser throws this runtime exception to stop parsing.
// Just stop processing current Javadoc comment.
ParseErrorMessage parseErrorMessage = errorListener.getErrorMessage();
// There are cases when antlr error listener does not handle syntax error
if (parseErrorMessage == null) {
parseErrorMessage =
new ParseErrorMessage(
javadocCommentAst.getLineNo(),
MSG_KEY_UNRECOGNIZED_ANTLR_ERROR,
javadocCommentAst.getColumnNo(),
ex.getMessage());
}
result.setParseErrorMessage(parseErrorMessage);
}
return result;
}
public static ParseStatus syntaxError(Integer tokenNumber, List<Token> tokens, String err) {
ParseStatus status = new ParseStatus();
status.columnNumber = -1;
status.tokenNumber = tokenNumber;
status.pointSet = new EmptyPointSet();
if (tokenNumber < tokens.size()) {
Token token = tokens.get(tokenNumber);
status.errMsg =
"Syntax error with token ("
+ token.getText()
+ ") near column "
+ token.getStart()
+ ": "
+ err;
} else {
Token token = tokens.get(tokenNumber - 1);
status.errMsg =
"Unexpected end of input after token ("
+ token.getText()
+ ") near column "
+ token.getStart()
+ ": context - "
+ err;
}
return status;
}
private boolean parseVariants(StringTokenIterator itr, ParseStatus sts) {
if (itr.isDone() || sts.isError()) {
return false;
}
boolean found = false;
while (!itr.isDone()) {
String s = itr.current();
if (!isVariant(s)) {
break;
}
found = true;
if (variants.isEmpty()) {
variants = new ArrayList<>(3);
}
variants.add(s);
sts.parseLength = itr.currentEnd();
itr.next();
}
return found;
}
private boolean parsePrivateuse(StringTokenIterator itr, ParseStatus sts) {
if (itr.isDone() || sts.isError()) {
return false;
}
boolean found = false;
String s = itr.current();
if (isPrivateusePrefix(s)) {
int start = itr.currentStart();
StringBuilder sb = new StringBuilder(s);
itr.next();
while (!itr.isDone()) {
s = itr.current();
if (!isPrivateuseSubtag(s)) {
break;
}
sb.append(SEP).append(s);
sts.parseLength = itr.currentEnd();
itr.next();
}
if (sts.parseLength <= start) {
// need at least 1 private subtag
sts.errorIndex = start;
sts.errorMsg = "Incomplete privateuse";
} else {
privateuse = sb.toString();
found = true;
}
}
return found;
}
/**
* Map function for distributed parsing of the CSV files.
*
* <p>In first phase it calculates the min, max, means, encodings and other statistics about the
* dataset, determines the number of columns.
*
* <p>The second pass then encodes the parsed dataset to the result key, splitting it into equal
* sized chunks.
*/
@Override
public void map(Key key) {
try {
Key aryKey = null;
boolean arraylet = key._kb[0] == Key.ARRAYLET_CHUNK;
boolean skipFirstLine = _skipFirstLine;
if (arraylet) {
aryKey = ValueArray.getArrayKey(key);
_chunkId = ValueArray.getChunkIndex(key);
skipFirstLine = skipFirstLine || (ValueArray.getChunkIndex(key) != 0);
}
switch (_phase) {
case ONE:
assert (_ncolumns != 0);
// initialize the column statistics
phaseOneInitialize();
// perform the parse
CsvParser p = new CsvParser(aryKey, _ncolumns, _sep, _decSep, this, skipFirstLine);
p.parse(key);
if (arraylet) {
long idx = ValueArray.getChunkIndex(key);
int idx2 = (int) idx;
assert idx2 == idx;
assert (_nrows[idx2] == 0)
: idx
+ ": "
+ Arrays.toString(_nrows)
+ " ("
+ _nrows[idx2]
+ " -- "
+ _myrows
+ ")";
_nrows[idx2] = _myrows;
}
break;
case TWO:
assert (_ncolumns != 0);
// initialize statistics - invalid rows, sigma and row size
phaseTwoInitialize();
// calculate the first row and the number of rows to parse
int firstRow = 0;
int lastRow = _myrows;
_myrows = 0;
if (arraylet) {
long origChunkIdx = ValueArray.getChunkIndex(key);
firstRow = (origChunkIdx == 0) ? 0 : _nrows[(int) origChunkIdx - 1];
lastRow = _nrows[(int) origChunkIdx];
}
int rowsToParse = lastRow - firstRow;
// create the output streams
_outputStreams2 = createRecords(firstRow, rowsToParse);
assert (_outputStreams2.length > 0);
_ab = _outputStreams2[0].initialize();
// perform the second parse pass
CsvParser p2 = new CsvParser(aryKey, _ncolumns, _sep, _decSep, this, skipFirstLine);
p2.parse(key);
// store the last stream if not stored during the parse
if (_ab != null) _outputStreams2[_outputIdx].store();
break;
default:
assert (false);
}
ParseStatus.update(_resultKey, DKV.get(key).length(), _phase);
} catch (Exception e) {
e.printStackTrace();
_error = e.getMessage();
}
}
public static ParseStatus nextPosition(int pos) {
ParseStatus status = new ParseStatus();
status.tokenNumber = pos;
return status;
}
