| Don Newton | 379ae25 | 2019-04-01 12:17:06 -0400 | [diff] [blame] | 1 | // Copyright 2017 The Go Authors. All rights reserved. |
| 2 | // Use of this source code is governed by a BSD-style |
| 3 | // license that can be found in the LICENSE file. |
| 4 | |
| 5 | // Package language implements BCP 47 language tags and related functionality. |
| 6 | // |
| 7 | // The most important function of package language is to match a list of |
| 8 | // user-preferred languages to a list of supported languages. |
| 9 | // It alleviates the developer of dealing with the complexity of this process |
| 10 | // and provides the user with the best experience |
| 11 | // (see https://blog.golang.org/matchlang). |
| 12 | // |
| 13 | // |
| 14 | // Matching preferred against supported languages |
| 15 | // |
| 16 | // A Matcher for an application that supports English, Australian English, |
| 17 | // Danish, and standard Mandarin can be created as follows: |
| 18 | // |
| 19 | // var matcher = language.NewMatcher([]language.Tag{ |
| 20 | // language.English, // The first language is used as fallback. |
| 21 | // language.MustParse("en-AU"), |
| 22 | // language.Danish, |
| 23 | // language.Chinese, |
| 24 | // }) |
| 25 | // |
| 26 | // This list of supported languages is typically implied by the languages for |
| 27 | // which there exists translations of the user interface. |
| 28 | // |
| 29 | // User-preferred languages usually come as a comma-separated list of BCP 47 |
| 30 | // language tags. |
| 31 | // The MatchString finds best matches for such strings: |
| 32 | // |
| 33 | // handler(w http.ResponseWriter, r *http.Request) { |
| 34 | // lang, _ := r.Cookie("lang") |
| 35 | // accept := r.Header.Get("Accept-Language") |
| 36 | // tag, _ := language.MatchStrings(matcher, lang.String(), accept) |
| 37 | // |
| 38 | // // tag should now be used for the initialization of any |
| 39 | // // locale-specific service. |
| 40 | // } |
| 41 | // |
| 42 | // The Matcher's Match method can be used to match Tags directly. |
| 43 | // |
| 44 | // Matchers are aware of the intricacies of equivalence between languages, such |
| 45 | // as deprecated subtags, legacy tags, macro languages, mutual |
| 46 | // intelligibility between scripts and languages, and transparently passing |
| 47 | // BCP 47 user configuration. |
| 48 | // For instance, it will know that a reader of Bokmål Danish can read Norwegian |
| 49 | // and will know that Cantonese ("yue") is a good match for "zh-HK". |
| 50 | // |
| 51 | // |
| 52 | // Using match results |
| 53 | // |
| 54 | // To guarantee a consistent user experience to the user it is important to |
| 55 | // use the same language tag for the selection of any locale-specific services. |
| 56 | // For example, it is utterly confusing to substitute spelled-out numbers |
| 57 | // or dates in one language in text of another language. |
| 58 | // More subtly confusing is using the wrong sorting order or casing |
| 59 | // algorithm for a certain language. |
| 60 | // |
| 61 | // All the packages in x/text that provide locale-specific services |
| 62 | // (e.g. collate, cases) should be initialized with the tag that was |
| 63 | // obtained at the start of an interaction with the user. |
| 64 | // |
| 65 | // Note that Tag that is returned by Match and MatchString may differ from any |
| 66 | // of the supported languages, as it may contain carried over settings from |
| 67 | // the user tags. |
| 68 | // This may be inconvenient when your application has some additional |
| 69 | // locale-specific data for your supported languages. |
| 70 | // Match and MatchString both return the index of the matched supported tag |
| 71 | // to simplify associating such data with the matched tag. |
| 72 | // |
| 73 | // |
| 74 | // Canonicalization |
| 75 | // |
| 76 | // If one uses the Matcher to compare languages one does not need to |
| 77 | // worry about canonicalization. |
| 78 | // |
| 79 | // The meaning of a Tag varies per application. The language package |
| 80 | // therefore delays canonicalization and preserves information as much |
| 81 | // as possible. The Matcher, however, will always take into account that |
| 82 | // two different tags may represent the same language. |
| 83 | // |
| 84 | // By default, only legacy and deprecated tags are converted into their |
| 85 | // canonical equivalent. All other information is preserved. This approach makes |
| 86 | // the confidence scores more accurate and allows matchers to distinguish |
| 87 | // between variants that are otherwise lost. |
| 88 | // |
| 89 | // As a consequence, two tags that should be treated as identical according to |
| 90 | // BCP 47 or CLDR, like "en-Latn" and "en", will be represented differently. The |
| 91 | // Matcher handles such distinctions, though, and is aware of the |
| 92 | // equivalence relations. The CanonType type can be used to alter the |
| 93 | // canonicalization form. |
| 94 | // |
| 95 | // References |
| 96 | // |
| 97 | // BCP 47 - Tags for Identifying Languages http://tools.ietf.org/html/bcp47 |
| 98 | // |
| 99 | package language // import "golang.org/x/text/language" |
| 100 | |
| 101 | // TODO: explanation on how to match languages for your own locale-specific |
| 102 | // service. |