github.com/liquid-dev/text@v0.3.3-liquid/encoding/htmlindex/htmlindex.go (about)

     1  // Copyright 2015 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  //go:generate go run gen.go
     6  
     7  // Package htmlindex maps character set encoding names to Encodings as
     8  // recommended by the W3C for use in HTML 5. See http://www.w3.org/TR/encoding.
     9  package htmlindex
    10  
    11  // TODO: perhaps have a "bare" version of the index (used by this package) that
    12  // is not pre-loaded with all encodings. Global variables in encodings prevent
    13  // the linker from being able to purge unneeded tables. This means that
    14  // referencing all encodings, as this package does for the default index, links
    15  // in all encodings unconditionally.
    16  //
    17  // This issue can be solved by either solving the linking issue (see
    18  // https://github.com/golang/go/issues/6330) or refactoring the encoding tables
    19  // (e.g. moving the tables to internal packages that do not use global
    20  // variables).
    21  
    22  // TODO: allow canonicalizing names
    23  
    24  import (
    25  	"errors"
    26  	"strings"
    27  	"sync"
    28  
    29  	"github.com/liquid-dev/text/encoding"
    30  	"github.com/liquid-dev/text/encoding/internal/identifier"
    31  	"github.com/liquid-dev/text/language"
    32  )
    33  
    34  var (
    35  	errInvalidName = errors.New("htmlindex: invalid encoding name")
    36  	errUnknown     = errors.New("htmlindex: unknown Encoding")
    37  	errUnsupported = errors.New("htmlindex: this encoding is not supported")
    38  )
    39  
    40  var (
    41  	matcherOnce sync.Once
    42  	matcher     language.Matcher
    43  )
    44  
    45  // LanguageDefault returns the canonical name of the default encoding for a
    46  // given language.
    47  func LanguageDefault(tag language.Tag) string {
    48  	matcherOnce.Do(func() {
    49  		tags := []language.Tag{}
    50  		for _, t := range strings.Split(locales, " ") {
    51  			tags = append(tags, language.MustParse(t))
    52  		}
    53  		matcher = language.NewMatcher(tags, language.PreferSameScript(true))
    54  	})
    55  	_, i, _ := matcher.Match(tag)
    56  	return canonical[localeMap[i]] // Default is Windows-1252.
    57  }
    58  
    59  // Get returns an Encoding for one of the names listed in
    60  // http://www.w3.org/TR/encoding using the Default Index. Matching is case-
    61  // insensitive.
    62  func Get(name string) (encoding.Encoding, error) {
    63  	x, ok := nameMap[strings.ToLower(strings.TrimSpace(name))]
    64  	if !ok {
    65  		return nil, errInvalidName
    66  	}
    67  	return encodings[x], nil
    68  }
    69  
    70  // Name reports the canonical name of the given Encoding. It will return
    71  // an error if e is not associated with a supported encoding scheme.
    72  func Name(e encoding.Encoding) (string, error) {
    73  	id, ok := e.(identifier.Interface)
    74  	if !ok {
    75  		return "", errUnknown
    76  	}
    77  	mib, _ := id.ID()
    78  	if mib == 0 {
    79  		return "", errUnknown
    80  	}
    81  	v, ok := mibMap[mib]
    82  	if !ok {
    83  		return "", errUnsupported
    84  	}
    85  	return canonical[v], nil
    86  }