const (
// Replace deprecated base languages with their preferred replacements.
DeprecatedBase CanonType = 1 << iota
// Replace deprecated scripts with their preferred replacements.
DeprecatedScript
// Replace deprecated regions with their preferred replacements.
DeprecatedRegion
// Remove redundant scripts.
SuppressScript
// Normalize legacy encodings. This includes legacy languages defined in
// CLDR as well as bibliographic codes defined in ISO-639.
Legacy
// Map the dominant language of a macro language group to the macro language
// subtag. For example cmn -> zh.
Macro
// The CLDR flag should be used if full compatibility with CLDR is required.
// There are a few cases where language.Tag may differ from CLDR. To follow all
// of CLDR's suggestions, use All|CLDR.
CLDR
// Raw can be used to Compose or Parse without Canonicalization.
Raw CanonType = 0
// Replace all deprecated tags with their preferred replacements.
Deprecated = DeprecatedBase | DeprecatedScript | DeprecatedRegion
// All canonicalizations recommended by BCP 47.
BCP47 = Deprecated | SuppressScript
// All canonicalizations.
All = BCP47 | Legacy | Macro
// Default is the canonicalization used by Parse, Make and Compose. To
// preserve as much information as possible, canonicalizations that remove
// potentially valuable information are not included. The Matcher is
// designed to recognize similar tags that would be the same if
// they were canonicalized using All.
Default = Deprecated | Legacy
)
CLDRVersion is the CLDR version from which the tables in this package are derived.
const CLDRVersion = "32"
NumCompactTags is the number of compact tags. The maximum tag is NumCompactTags-1.
const NumCompactTags = compact.NumCompactTags
ErrMissingLikelyTagsData indicates no information was available to compute likely values of missing tags.
var ErrMissingLikelyTagsData = errors.New("missing likely tags data")
func CompactIndex(t Tag) (index int, exact bool)
CompactIndex returns an index, where 0 <= index < NumCompactTags, for tags for which data exists in the text repository.The index will change over time and should not be stored in persistent storage. If t does not match a compact index, exact will be false and the compact index will be returned for the first match after repeatedly taking the Parent of t.
Base is an ISO 639 language code, used for encoding the base language of a language tag.
type Base struct {
// contains filtered or unexported fields
}
func MustParseBase(s string) Base
MustParseBase is like ParseBase, but panics if the given base cannot be parsed. It simplifies safe initialization of Base values.
func ParseBase(s string) (Base, error)
ParseBase parses a 2- or 3-letter ISO 639 code. It returns a ValueError if s is a well-formed but unknown language identifier or another error if another error occurred.
func (b Base) ISO3() string
ISO3 returns the ISO 639-3 language code.
func (b Base) IsPrivateUse() bool
IsPrivateUse reports whether this language code is reserved for private use.
func (b Base) String() string
String returns the BCP 47 representation of the base language.
CanonType can be used to enable or disable various types of canonicalization.
type CanonType int
func (c CanonType) Canonicalize(t Tag) (Tag, error)
Canonicalize returns the canonicalized equivalent of the tag.
func (c CanonType) Compose(part ...interface{}) (t Tag, err error)
Compose creates a Tag from individual parts, which may be of type Tag, Base, Script, Region, Variant, []Variant, Extension, []Extension or error. If a Base, Script or Region or slice of type Variant or Extension is passed more than once, the latter will overwrite the former. Variants and Extensions are accumulated, but if two extensions of the same type are passed, the latter will replace the former. For -u extensions, though, the key-type pairs are added, where later values overwrite older ones. A Tag overwrites all former values and typically only makes sense as the first argument. The resulting tag is returned after canonicalizing using CanonType c. If one or more errors are encountered, one of the errors is returned.
func (c CanonType) Make(s string) Tag
Make is a convenience wrapper for c.Parse that omits the error. In case of an error, a sensible default is returned.
func (c CanonType) MustParse(s string) Tag
MustParse is like Parse, but panics if the given BCP 47 tag cannot be parsed. It simplifies safe initialization of Tag values.
func (c CanonType) Parse(s string) (t Tag, err error)
Parse parses the given BCP 47 string and returns a valid Tag. If parsing failed it returns an error and any part of the tag that could be parsed. If parsing succeeded but an unknown value was found, it returns ValueError. The Tag returned in this case is just stripped of the unknown value. All other values are preserved. It accepts tags in the BCP 47 format and extensions to this standard defined in https://www.unicode.org/reports/tr35/#Unicode_Language_and_Locale_Identifiers. The resulting tag is canonicalized using the canonicalization type c.
Confidence indicates the level of certainty for a given return value. For example, Serbian may be written in Cyrillic or Latin script. The confidence level indicates whether a value was explicitly specified, whether it is typically the only possible value, or whether there is an ambiguity.
type Confidence int
const (
No Confidence = iota // full confidence that there was no match
Low // most likely value picked out of a set of alternatives
High // value is generally assumed to be the correct match
Exact // exact match or explicitly specified value
)
func Comprehends(speaker, alternative Tag) Confidence
Comprehends reports the confidence score for a speaker of a given language to being able to comprehend the written form of an alternative language.
func (c Confidence) String() string
The Coverage interface is used to define the level of coverage of an internationalization service. Note that not all types are supported by all services. As lists may be generated on the fly, it is recommended that users of a Coverage cache the results.
type Coverage interface {
// Tags returns the list of supported tags.
Tags() []Tag
// BaseLanguages returns the list of supported base languages.
BaseLanguages() []Base
// Scripts returns the list of supported scripts.
Scripts() []Script
// Regions returns the list of supported regions.
Regions() []Region
}
var (
// Supported defines a Coverage that lists all supported subtags. Tags
// always returns nil.
Supported Coverage = allSubtags{}
)
func NewCoverage(list ...interface{}) Coverage
NewCoverage returns a Coverage for the given lists. It is typically used by packages providing internationalization services to define their level of coverage. A list may be of type []T or func() []T, where T is either Tag, Base, Script or Region. The returned Coverage derives the value for Bases from Tags if no func or slice for []Base is specified. For other unspecified types the returned Coverage will return nil for the respective methods.
Extension is a single BCP 47 extension.
type Extension struct {
// contains filtered or unexported fields
}
func ParseExtension(s string) (e Extension, err error)
ParseExtension parses s as an extension and returns it on success.
func (e Extension) String() string
String returns the string representation of the extension, including the type tag.
func (e Extension) Tokens() []string
Tokens returns the list of tokens of e.
func (e Extension) Type() byte
Type returns the one-byte extension type of e. It returns 0 for the zero exception.
A MatchOption configures a Matcher.
type MatchOption func(*matcher)
func PreferSameScript(preferSame bool) MatchOption
PreferSameScript will, in the absence of a match, result in the first preferred tag with the same script as a supported tag to match this supported tag. The default is currently true, but this may change in the future.
Matcher is the interface that wraps the Match method.
Match returns the best match for any of the given tags, along with a unique index associated with the returned tag and a confidence score.
type Matcher interface {
Match(t ...Tag) (tag Tag, index int, c Confidence)
}
func NewMatcher(t []Tag, options ...MatchOption) Matcher
NewMatcher returns a Matcher that matches an ordered list of preferred tags against a list of supported tags based on written intelligibility, closeness of dialect, equivalence of subtags and various other rules. It is initialized with the list of supported tags. The first element is used as the default value in case no match is found.
Its Match method matches the first of the given Tags to reach a certain confidence threshold. The tags passed to Match should therefore be specified in order of preference. Extensions are ignored for matching.
The index returned by the Match method corresponds to the index of the matched tag in t, but is augmented with the Unicode extension ('u')of the corresponding preferred tag. This allows user locale options to be passed transparently.
Region is an ISO 3166-1 or UN M.49 code for representing countries and regions.
type Region struct {
// contains filtered or unexported fields
}
func EncodeM49(r int) (Region, error)
EncodeM49 returns the Region for the given UN M.49 code. It returns an error if r is not a valid code.
func MustParseRegion(s string) Region
MustParseRegion is like ParseRegion, but panics if the given region cannot be parsed. It simplifies safe initialization of Region values.
func ParseRegion(s string) (Region, error)
ParseRegion parses a 2- or 3-letter ISO 3166-1 or a UN M.49 code. It returns a ValueError if s is a well-formed but unknown region identifier or another error if another error occurred.
func (r Region) Canonicalize() Region
Canonicalize returns the region or a possible replacement if the region is deprecated. It will not return a replacement for deprecated regions that are split into multiple regions.
func (r Region) Contains(c Region) bool
Contains returns whether Region c is contained by Region r. It returns true if c == r.
func (r Region) ISO3() string
ISO3 returns the 3-letter ISO code of r. Note that not all regions have a 3-letter ISO code. In such cases this method returns "ZZZ".
func (r Region) IsCountry() bool
IsCountry returns whether this region is a country or autonomous area. This includes non-standard definitions from CLDR.
func (r Region) IsGroup() bool
IsGroup returns whether this region defines a collection of regions. This includes non-standard definitions from CLDR.
func (r Region) IsPrivateUse() bool
IsPrivateUse reports whether r has the ISO 3166 User-assigned status. This may include private-use tags that are assigned by CLDR and used in this implementation. So IsPrivateUse and IsCountry can be simultaneously true.
func (r Region) M49() int
M49 returns the UN M.49 encoding of r, or 0 if this encoding is not defined for r.
func (r Region) String() string
String returns the BCP 47 representation for the region. It returns "ZZ" for an unspecified region.
func (r Region) TLD() (Region, error)
TLD returns the country code top-level domain (ccTLD). UK is returned for GB. In all other cases it returns either the region itself or an error.
This method may return an error for a region for which there exists a canonical form with a ccTLD. To get that ccTLD canonicalize r first. The region will already be canonicalized it was obtained from a Tag that was obtained using any of the default methods.
Script is a 4-letter ISO 15924 code for representing scripts. It is idiomatically represented in title case.
type Script struct {
// contains filtered or unexported fields
}
func MustParseScript(s string) Script
MustParseScript is like ParseScript, but panics if the given script cannot be parsed. It simplifies safe initialization of Script values.
func ParseScript(s string) (Script, error)
ParseScript parses a 4-letter ISO 15924 code. It returns a ValueError if s is a well-formed but unknown script identifier or another error if another error occurred.
func (s Script) IsPrivateUse() bool
IsPrivateUse reports whether this script code is reserved for private use.
func (s Script) String() string
String returns the script code in title case. It returns "Zzzz" for an unspecified script.
Tag represents a BCP 47 language tag. It is used to specify an instance of a specific language or locale. All language tag values are guaranteed to be well-formed.
type Tag compact.Tag
var (
Und Tag = Tag{}
Afrikaans Tag = Tag(compact.Afrikaans)
Amharic Tag = Tag(compact.Amharic)
Arabic Tag = Tag(compact.Arabic)
ModernStandardArabic Tag = Tag(compact.ModernStandardArabic)
Azerbaijani Tag = Tag(compact.Azerbaijani)
Bulgarian Tag = Tag(compact.Bulgarian)
Bengali Tag = Tag(compact.Bengali)
Catalan Tag = Tag(compact.Catalan)
Czech Tag = Tag(compact.Czech)
Danish Tag = Tag(compact.Danish)
German Tag = Tag(compact.German)
Greek Tag = Tag(compact.Greek)
English Tag = Tag(compact.English)
AmericanEnglish Tag = Tag(compact.AmericanEnglish)
BritishEnglish Tag = Tag(compact.BritishEnglish)
Spanish Tag = Tag(compact.Spanish)
EuropeanSpanish Tag = Tag(compact.EuropeanSpanish)
LatinAmericanSpanish Tag = Tag(compact.LatinAmericanSpanish)
Estonian Tag = Tag(compact.Estonian)
Persian Tag = Tag(compact.Persian)
Finnish Tag = Tag(compact.Finnish)
Filipino Tag = Tag(compact.Filipino)
French Tag = Tag(compact.French)
CanadianFrench Tag = Tag(compact.CanadianFrench)
Gujarati Tag = Tag(compact.Gujarati)
Hebrew Tag = Tag(compact.Hebrew)
Hindi Tag = Tag(compact.Hindi)
Croatian Tag = Tag(compact.Croatian)
Hungarian Tag = Tag(compact.Hungarian)
Armenian Tag = Tag(compact.Armenian)
Indonesian Tag = Tag(compact.Indonesian)
Icelandic Tag = Tag(compact.Icelandic)
Italian Tag = Tag(compact.Italian)
Japanese Tag = Tag(compact.Japanese)
Georgian Tag = Tag(compact.Georgian)
Kazakh Tag = Tag(compact.Kazakh)
Khmer Tag = Tag(compact.Khmer)
Kannada Tag = Tag(compact.Kannada)
Korean Tag = Tag(compact.Korean)
Kirghiz Tag = Tag(compact.Kirghiz)
Lao Tag = Tag(compact.Lao)
Lithuanian Tag = Tag(compact.Lithuanian)
Latvian Tag = Tag(compact.Latvian)
Macedonian Tag = Tag(compact.Macedonian)
Malayalam Tag = Tag(compact.Malayalam)
Mongolian Tag = Tag(compact.Mongolian)
Marathi Tag = Tag(compact.Marathi)
Malay Tag = Tag(compact.Malay)
Burmese Tag = Tag(compact.Burmese)
Nepali Tag = Tag(compact.Nepali)
Dutch Tag = Tag(compact.Dutch)
Norwegian Tag = Tag(compact.Norwegian)
Punjabi Tag = Tag(compact.Punjabi)
Polish Tag = Tag(compact.Polish)
Portuguese Tag = Tag(compact.Portuguese)
BrazilianPortuguese Tag = Tag(compact.BrazilianPortuguese)
EuropeanPortuguese Tag = Tag(compact.EuropeanPortuguese)
Romanian Tag = Tag(compact.Romanian)
Russian Tag = Tag(compact.Russian)
Sinhala Tag = Tag(compact.Sinhala)
Slovak Tag = Tag(compact.Slovak)
Slovenian Tag = Tag(compact.Slovenian)
Albanian Tag = Tag(compact.Albanian)
Serbian Tag = Tag(compact.Serbian)
SerbianLatin Tag = Tag(compact.SerbianLatin)
Swedish Tag = Tag(compact.Swedish)
Swahili Tag = Tag(compact.Swahili)
Tamil Tag = Tag(compact.Tamil)
Telugu Tag = Tag(compact.Telugu)
Thai Tag = Tag(compact.Thai)
Turkish Tag = Tag(compact.Turkish)
Ukrainian Tag = Tag(compact.Ukrainian)
Urdu Tag = Tag(compact.Urdu)
Uzbek Tag = Tag(compact.Uzbek)
Vietnamese Tag = Tag(compact.Vietnamese)
Chinese Tag = Tag(compact.Chinese)
SimplifiedChinese Tag = Tag(compact.SimplifiedChinese)
TraditionalChinese Tag = Tag(compact.TraditionalChinese)
Zulu Tag = Tag(compact.Zulu)
)
func Compose(part ...interface{}) (t Tag, err error)
Compose creates a Tag from individual parts, which may be of type Tag, Base, Script, Region, Variant, []Variant, Extension, []Extension or error. If a Base, Script or Region or slice of type Variant or Extension is passed more than once, the latter will overwrite the former. Variants and Extensions are accumulated, but if two extensions of the same type are passed, the latter will replace the former. For -u extensions, though, the key-type pairs are added, where later values overwrite older ones. A Tag overwrites all former values and typically only makes sense as the first argument. The resulting tag is returned after canonicalizing using the Default CanonType. If one or more errors are encountered, one of the errors is returned.
func Make(s string) Tag
Make is a convenience wrapper for Parse that omits the error. In case of an error, a sensible default is returned.
func MatchStrings(m Matcher, lang ...string) (tag Tag, index int)
MatchStrings parses and matches the given strings until one of them matches the language in the Matcher. A string may be an Accept-Language header as handled by ParseAcceptLanguage. The default language is returned if no other language matched.
func MustParse(s string) Tag
MustParse is like Parse, but panics if the given BCP 47 tag cannot be parsed. It simplifies safe initialization of Tag values.
func Parse(s string) (t Tag, err error)
Parse parses the given BCP 47 string and returns a valid Tag. If parsing failed it returns an error and any part of the tag that could be parsed. If parsing succeeded but an unknown value was found, it returns ValueError. The Tag returned in this case is just stripped of the unknown value. All other values are preserved. It accepts tags in the BCP 47 format and extensions to this standard defined in https://www.unicode.org/reports/tr35/#Unicode_Language_and_Locale_Identifiers. The resulting tag is canonicalized using the default canonicalization type.
func ParseAcceptLanguage(s string) (tag []Tag, q []float32, err error)
ParseAcceptLanguage parses the contents of an Accept-Language header as defined in http://www.ietf.org/rfc/rfc2616.txt and returns a list of Tags and a list of corresponding quality weights. It is more permissive than RFC 2616 and may return non-nil slices even if the input is not valid. The Tags will be sorted by highest weight first and then by first occurrence. Tags with a weight of zero will be dropped. An error will be returned if the input could not be parsed.
func (t Tag) Base() (Base, Confidence)
Base returns the base language of the language tag. If the base language is unspecified, an attempt will be made to infer it from the context. It uses a variant of CLDR's Add Likely Subtags algorithm. This is subject to change.
func (t Tag) Extension(x byte) (ext Extension, ok bool)
Extension returns the extension of type x for tag t. It will return false for ok if t does not have the requested extension. The returned extension will be invalid in this case.
func (t Tag) Extensions() []Extension
Extensions returns all extensions of t.
func (t Tag) IsRoot() bool
IsRoot returns true if t is equal to language "und".
func (t Tag) MarshalText() (text []byte, err error)
MarshalText implements encoding.TextMarshaler.
func (t Tag) Parent() Tag
Parent returns the CLDR parent of t. In CLDR, missing fields in data for a specific language are substituted with fields from the parent language. The parent for a language may change for newer versions of CLDR.
Parent returns a tag for a less specific language that is mutually intelligible or Und if there is no such language. This may not be the same as simply stripping the last BCP 47 subtag. For instance, the parent of "zh-TW" is "zh-Hant", and the parent of "zh-Hant" is "und".
func (t Tag) Raw() (b Base, s Script, r Region)
Raw returns the raw base language, script and region, without making an attempt to infer their values.
func (t Tag) Region() (Region, Confidence)
Region returns the region for the language tag. If it was not explicitly given, it will infer a most likely candidate from the context. It uses a variant of CLDR's Add Likely Subtags algorithm. This is subject to change.
func (t Tag) Script() (Script, Confidence)
Script infers the script for the language tag. If it was not explicitly given, it will infer a most likely candidate. If more than one script is commonly used for a language, the most likely one is returned with a low confidence indication. For example, it returns (Cyrl, Low) for Serbian. If a script cannot be inferred (Zzzz, No) is returned. We do not use Zyyy (undetermined) as one would suspect from the IANA registry for BCP 47. In a Unicode context Zyyy marks common characters (like 1, 2, 3, '.', etc.) and is therefore more like multiple scripts. See https://www.unicode.org/reports/tr24/#Values for more details. Zzzz is also used for unknown value in CLDR. (Zzzz, Exact) is returned if Zzzz was explicitly specified. Note that an inferred script is never guaranteed to be the correct one. Latin is almost exclusively used for Afrikaans, but Arabic has been used for some texts in the past. Also, the script that is commonly used may change over time. It uses a variant of CLDR's Add Likely Subtags algorithm. This is subject to change.
func (t Tag) SetTypeForKey(key, value string) (Tag, error)
SetTypeForKey returns a new Tag with the key set to type, where key and type are of the allowed values defined for the Unicode locale extension ('u') in https://www.unicode.org/reports/tr35/#Unicode_Language_and_Locale_Identifiers. An empty value removes an existing pair with the same key.
func (t Tag) String() string
String returns the canonical string representation of the language tag.
func (t Tag) TypeForKey(key string) string
TypeForKey returns the type associated with the given key, where key and type are of the allowed values defined for the Unicode locale extension ('u') in https://www.unicode.org/reports/tr35/#Unicode_Language_and_Locale_Identifiers. TypeForKey will traverse the inheritance chain to get the correct value.
If there are multiple types associated with a key, only the first will be returned. If there is no type associated with a key, it returns the empty string.
func (t *Tag) UnmarshalText(text []byte) error
UnmarshalText implements encoding.TextUnmarshaler.
func (t Tag) Variants() []Variant
Variants returns the variants specified explicitly for this language tag. or nil if no variant was specified.
ValueError is returned by any of the parsing functions when the input is well-formed but the respective subtag is not recognized as a valid value.
type ValueError interface {
error
// Subtag returns the subtag for which the error occurred.
Subtag() string
}
Variant represents a registered variant of a language as defined by BCP 47.
type Variant struct {
// contains filtered or unexported fields
}
func ParseVariant(s string) (Variant, error)
ParseVariant parses and returns a Variant. An error is returned if s is not a valid variant.
func (v Variant) String() string
String returns the string representation of the variant.