Update vendor

vendor/golang.org/x/text/encoding/internal/identifier/gen.go

@@ -0,0 +1,137 @@
+// Copyright 2015 The Go Authors. All rights reserved.
+// Use of this source code is governed by a BSD-style
+// license that can be found in the LICENSE file.
+
+// +build ignore
+
+package main
+
+import (
+	"bytes"
+	"encoding/xml"
+	"fmt"
+	"io"
+	"log"
+	"strings"
+
+	"golang.org/x/text/internal/gen"
+)
+
+type registry struct {
+	XMLName  xml.Name `xml:"registry"`
+	Updated  string   `xml:"updated"`
+	Registry []struct {
+		ID     string `xml:"id,attr"`
+		Record []struct {
+			Name string `xml:"name"`
+			Xref []struct {
+				Type string `xml:"type,attr"`
+				Data string `xml:"data,attr"`
+			} `xml:"xref"`
+			Desc struct {
+				Data string `xml:",innerxml"`
+				// Any []struct {
+				// 	Data string `xml:",chardata"`
+				// } `xml:",any"`
+				// Data string `xml:",chardata"`
+			} `xml:"description,"`
+			MIB   string   `xml:"value"`
+			Alias []string `xml:"alias"`
+			MIME  string   `xml:"preferred_alias"`
+		} `xml:"record"`
+	} `xml:"registry"`
+}
+
+func main() {
+	r := gen.OpenIANAFile("assignments/character-sets/character-sets.xml")
+	reg := &registry{}
+	if err := xml.NewDecoder(r).Decode(&reg); err != nil && err != io.EOF {
+		log.Fatalf("Error decoding charset registry: %v", err)
+	}
+	if len(reg.Registry) == 0 || reg.Registry[0].ID != "character-sets-1" {
+		log.Fatalf("Unexpected ID %s", reg.Registry[0].ID)
+	}
+
+	w := &bytes.Buffer{}
+	fmt.Fprintf(w, "const (\n")
+	for _, rec := range reg.Registry[0].Record {
+		constName := ""
+		for _, a := range rec.Alias {
+			if strings.HasPrefix(a, "cs") && strings.IndexByte(a, '-') == -1 {
+				// Some of the constant definitions have comments in them. Strip those.
+				constName = strings.Title(strings.SplitN(a[2:], "\n", 2)[0])
+			}
+		}
+		if constName == "" {
+			switch rec.MIB {
+			case "2085":
+				constName = "HZGB2312" // Not listed as alias for some reason.
+			default:
+				log.Fatalf("No cs alias defined for %s.", rec.MIB)
+			}
+		}
+		if rec.MIME != "" {
+			rec.MIME = fmt.Sprintf(" (MIME: %s)", rec.MIME)
+		}
+		fmt.Fprintf(w, "// %s is the MIB identifier with IANA name %s%s.\n//\n", constName, rec.Name, rec.MIME)
+		if len(rec.Desc.Data) > 0 {
+			fmt.Fprint(w, "// ")
+			d := xml.NewDecoder(strings.NewReader(rec.Desc.Data))
+			inElem := true
+			attr := ""
+			for {
+				t, err := d.Token()
+				if err != nil {
+					if err != io.EOF {
+						log.Fatal(err)
+					}
+					break
+				}
+				switch x := t.(type) {
+				case xml.CharData:
+					attr = "" // Don't need attribute info.
+					a := bytes.Split([]byte(x), []byte("\n"))
+					for i, b := range a {
+						if b = bytes.TrimSpace(b); len(b) != 0 {
+							if !inElem && i > 0 {
+								fmt.Fprint(w, "\n// ")
+							}
+							inElem = false
+							fmt.Fprintf(w, "%s ", string(b))
+						}
+					}
+				case xml.StartElement:
+					if x.Name.Local == "xref" {
+						inElem = true
+						use := false
+						for _, a := range x.Attr {
+							if a.Name.Local == "type" {
+								use = use || a.Value != "person"
+							}
+							if a.Name.Local == "data" && use {
+								attr = a.Value + " "
+							}
+						}
+					}
+				case xml.EndElement:
+					inElem = false
+					fmt.Fprint(w, attr)
+				}
+			}
+			fmt.Fprint(w, "\n")
+		}
+		for _, x := range rec.Xref {
+			switch x.Type {
+			case "rfc":
+				fmt.Fprintf(w, "// Reference: %s\n", strings.ToUpper(x.Data))
+			case "uri":
+				fmt.Fprintf(w, "// Reference: %s\n", x.Data)
+			}
+		}
+		fmt.Fprintf(w, "%s MIB = %s\n", constName, rec.MIB)
+		fmt.Fprintln(w)
+	}
+	fmt.Fprintln(w, ")")
+
+	gen.WriteGoFile("mib.go", "identifier", w.Bytes())
+}

vendor/golang.org/x/text/encoding/internal/identifier/identifier.go

@@ -0,0 +1,81 @@
+// Copyright 2015 The Go Authors. All rights reserved.
+// Use of this source code is governed by a BSD-style
+// license that can be found in the LICENSE file.
+
+//go:generate go run gen.go
+
+// Package identifier defines the contract between implementations of Encoding
+// and Index by defining identifiers that uniquely identify standardized coded
+// character sets (CCS) and character encoding schemes (CES), which we will
+// together refer to as encodings, for which Encoding implementations provide
+// converters to and from UTF-8. This package is typically only of concern to
+// implementers of Indexes and Encodings.
+//
+// One part of the identifier is the MIB code, which is defined by IANA and
+// uniquely identifies a CCS or CES. Each code is associated with data that
+// references authorities, official documentation as well as aliases and MIME
+// names.
+//
+// Not all CESs are covered by the IANA registry. The "other" string that is
+// returned by ID can be used to identify other character sets or versions of
+// existing ones.
+//
+// It is recommended that each package that provides a set of Encodings provide
+// the All and Common variables to reference all supported encodings and
+// commonly used subset. This allows Index implementations to include all
+// available encodings without explicitly referencing or knowing about them.
+package identifier
+
+// Note: this package is internal, but could be made public if there is a need
+// for writing third-party Indexes and Encodings.
+
+// References:
+// - http://source.icu-project.org/repos/icu/icu/trunk/source/data/mappings/convrtrs.txt
+// - http://www.iana.org/assignments/character-sets/character-sets.xhtml
+// - http://www.iana.org/assignments/ianacharset-mib/ianacharset-mib
+// - http://www.ietf.org/rfc/rfc2978.txt
+// - http://www.unicode.org/reports/tr22/
+// - http://www.w3.org/TR/encoding/
+// - https://encoding.spec.whatwg.org/
+// - https://encoding.spec.whatwg.org/encodings.json
+// - https://tools.ietf.org/html/rfc6657#section-5
+
+// Interface can be implemented by Encodings to define the CCS or CES for which
+// it implements conversions.
+type Interface interface {
+	// ID returns an encoding identifier. Exactly one of the mib and other
+	// values should be non-zero.
+	//
+	// In the usual case it is only necessary to indicate the MIB code. The
+	// other string can be used to specify encodings for which there is no MIB,
+	// such as "x-mac-dingbat".
+	//
+	// The other string may only contain the characters a-z, A-Z, 0-9, - and _.
+	ID() (mib MIB, other string)
+
+	// NOTE: the restrictions on the encoding are to allow extending the syntax
+	// with additional information such as versions, vendors and other variants.
+}
+
+// A MIB identifies an encoding. It is derived from the IANA MIB codes and adds
+// some identifiers for some encodings that are not covered by the IANA
+// standard.
+//
+// See http://www.iana.org/assignments/ianacharset-mib.
+type MIB uint16
+
+// These additional MIB types are not defined in IANA. They are added because
+// they are common and defined within the text repo.
+const (
+	// Unofficial marks the start of encodings not registered by IANA.
+	Unofficial MIB = 10000 + iota
+
+	// Replacement is the WhatWG replacement encoding.
+	Replacement
+
+	// XUserDefined is the code for x-user-defined.
+	XUserDefined
+
+	// MacintoshCyrillic is the code for x-mac-cyrillic.
+	MacintoshCyrillic
+)