/*
* 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;
}
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;
}
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;
}