private bool ParseVariants(StringTokenEnumerator itr, ParseStatus sts)
{
if (itr.IsDone || sts.IsError)
{
return(false);
}
bool found = false;
while (!itr.IsDone)
{
string s = itr.Current;
if (!IsVariant(s))
{
break;
}
found = true;
if (!_variants.Any())
{
_variants = new List <string>(3);
}
_variants.Add(s);
sts.ParseLength = itr.CurrentEnd;
itr.MoveNext();
}
return(found);
}
private bool ParseExtlangs(StringTokenEnumerator itr, ParseStatus sts)
{
if (itr.IsDone || sts.IsError)
{
return(false);
}
bool found = false;
while (!itr.IsDone)
{
string s = itr.Current;
if (!IsExtlang(s))
{
break;
}
found = true;
if (!_extlangs.Any())
{
_extlangs = new List <string>(3);
}
_extlangs.Add(s);
sts.ParseLength = itr.CurrentEnd;
itr.MoveNext();
if (_extlangs.Count == 3)
{
// Maximum 3 extlangs
break;
}
}
return(found);
}
private bool ParseExtensions(StringTokenEnumerator itr, ParseStatus sts)
{
if (itr.IsDone || sts.IsError)
{
return(false);
}
bool 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.MoveNext();
while (!itr.IsDone)
{
s = itr.Current;
if (IsExtensionSubtag(s))
{
sb.Append(SEP).Append(s);
sts.ParseLength = itr.CurrentEnd;
}
else
{
break;
}
itr.MoveNext();
}
if (sts.ParseLength <= start)
{
sts.ErrorIndex = start;
sts.ErrorMessage = "Incomplete extension '" + singleton + "'";
break;
}
if (_extensions.Count == 0)
{
_extensions = new List <String>(4);
}
_extensions.Add(sb.ToString());
found = true;
}
else
{
break;
}
}
return(found);
}
/// <summary>
/// BNF in RFC5464
/// </summary>
/// <remarks>
/// 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))
/// </remarks>
public static LanguageTag Parse(string languageTag, ParseStatus sts)
{
if (sts == null)
{
sts = new ParseStatus();
}
else
{
sts.Reset();
}
StringTokenEnumerator itr;
bool isGrandfathered = false;
// Check if the tag is grandfathered
if (Grandfathered.TryGetValue(new AsciiCaseInsensitiveKey(languageTag), out string[] gfmap) && gfmap != null)
private bool ParsePrivateuse(StringTokenEnumerator itr, ParseStatus sts)
{
if (itr.IsDone || sts.IsError)
{
return(false);
}
bool found = false;
string s = itr.Current;
if (IsPrivateusePrefix(s))
{
int start = itr.CurrentStart;
StringBuilder sb = new StringBuilder(s);
itr.MoveNext();
while (!itr.IsDone)
{
s = itr.Current;
if (!IsPrivateuseSubtag(s))
{
break;
}
sb.Append(SEP).Append(s);
sts.ParseLength = itr.CurrentEnd;
itr.MoveNext();
}
if (sts.ParseLength <= start)
{
// need at least 1 private subtag
sts.ErrorIndex = start;
sts.ErrorMessage = "Incomplete privateuse";
}
else
{
_privateuse = sb.ToString();
found = true;
}
}
return(found);
}
private bool ParseRegion(StringTokenEnumerator itr, ParseStatus sts)
{
if (itr.IsDone || sts.IsError)
{
return(false);
}
bool found = false;
string s = itr.Current;
if (IsRegion(s))
{
found = true;
_region = s;
sts.ParseLength = itr.CurrentEnd;
itr.MoveNext();
}
return(found);
}
/// <summary>
/// BNF in RFC5464
/// </summary>
/// <remarks>
/// 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))
/// </remarks>
public static LanguageTag Parse(string languageTag, ParseStatus sts)
{
if (sts == null)
{
sts = new ParseStatus();
}
else
{
sts.Reset();
}
StringTokenEnumerator itr;
bool isGrandfathered = false;
// Check if the tag is grandfathered
string[] gfmap;
if (GRANDFATHERED.TryGetValue(new AsciiUtil.CaseInsensitiveKey(languageTag), out gfmap) && gfmap != null)
{
// use preferred mapping
itr = new StringTokenEnumerator(gfmap[1], SEP);
isGrandfathered = true;
}
else
{
itr = new StringTokenEnumerator(languageTag, SEP);
}
// ICU4N: Move to the first element
itr.MoveNext();
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 (isGrandfathered)
{
// Grandfathered tag is replaced with a well-formed tag above.
// However, the parsed length must be the original tag length.
Debug.Assert(itr.IsDone);
Debug.Assert(!sts.IsError);
sts.ParseLength = languageTag.Length;
}
else if (!itr.IsDone && !sts.IsError)
{
string s = itr.Current;
sts.ErrorIndex = itr.CurrentStart;
if (s.Length == 0)
{
sts.ErrorMessage = "Empty subtag";
}
else
{
sts.ErrorMessage = "Invalid subtag: " + s;
}
}
return(tag);
}