ires 0.1.3 → 0.1.4

data/ext/vendor/golang.org/x/text/language/lookup.go

@@ -0,0 +1,396 @@
+// Copyright 2013 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.
+
+package language
+
+import (
+	"bytes"
+	"fmt"
+	"sort"
+	"strconv"
+
+	"golang.org/x/text/internal/tag"
+)
+
+// findIndex tries to find the given tag in idx and returns a standardized error
+// if it could not be found.
+func findIndex(idx tag.Index, key []byte, form string) (index int, err error) {
+	if !tag.FixCase(form, key) {
+		return 0, errSyntax
+	}
+	i := idx.Index(key)
+	if i == -1 {
+		return 0, mkErrInvalid(key)
+	}
+	return i, nil
+}
+
+func searchUint(imap []uint16, key uint16) int {
+	return sort.Search(len(imap), func(i int) bool {
+		return imap[i] >= key
+	})
+}
+
+type langID uint16
+
+// getLangID returns the langID of s if s is a canonical subtag
+// or langUnknown if s is not a canonical subtag.
+func getLangID(s []byte) (langID, error) {
+	if len(s) == 2 {
+		return getLangISO2(s)
+	}
+	return getLangISO3(s)
+}
+
+// mapLang returns the mapped langID of id according to mapping m.
+func normLang(id langID) (langID, langAliasType) {
+	k := sort.Search(len(langAliasMap), func(i int) bool {
+		return langAliasMap[i].from >= uint16(id)
+	})
+	if k < len(langAliasMap) && langAliasMap[k].from == uint16(id) {
+		return langID(langAliasMap[k].to), langAliasTypes[k]
+	}
+	return id, langAliasTypeUnknown
+}
+
+// getLangISO2 returns the langID for the given 2-letter ISO language code
+// or unknownLang if this does not exist.
+func getLangISO2(s []byte) (langID, error) {
+	if !tag.FixCase("zz", s) {
+		return 0, errSyntax
+	}
+	if i := lang.Index(s); i != -1 && lang.Elem(i)[3] != 0 {
+		return langID(i), nil
+	}
+	return 0, mkErrInvalid(s)
+}
+
+const base = 'z' - 'a' + 1
+
+func strToInt(s []byte) uint {
+	v := uint(0)
+	for i := 0; i < len(s); i++ {
+		v *= base
+		v += uint(s[i] - 'a')
+	}
+	return v
+}
+
+// converts the given integer to the original ASCII string passed to strToInt.
+// len(s) must match the number of characters obtained.
+func intToStr(v uint, s []byte) {
+	for i := len(s) - 1; i >= 0; i-- {
+		s[i] = byte(v%base) + 'a'
+		v /= base
+	}
+}
+
+// getLangISO3 returns the langID for the given 3-letter ISO language code
+// or unknownLang if this does not exist.
+func getLangISO3(s []byte) (langID, error) {
+	if tag.FixCase("und", s) {
+		// first try to match canonical 3-letter entries
+		for i := lang.Index(s[:2]); i != -1; i = lang.Next(s[:2], i) {
+			if e := lang.Elem(i); e[3] == 0 && e[2] == s[2] {
+				// We treat "und" as special and always translate it to "unspecified".
+				// Note that ZZ and Zzzz are private use and are not treated as
+				// unspecified by default.
+				id := langID(i)
+				if id == nonCanonicalUnd {
+					return 0, nil
+				}
+				return id, nil
+			}
+		}
+		if i := altLangISO3.Index(s); i != -1 {
+			return langID(altLangIndex[altLangISO3.Elem(i)[3]]), nil
+		}
+		n := strToInt(s)
+		if langNoIndex[n/8]&(1<<(n%8)) != 0 {
+			return langID(n) + langNoIndexOffset, nil
+		}
+		// Check for non-canonical uses of ISO3.
+		for i := lang.Index(s[:1]); i != -1; i = lang.Next(s[:1], i) {
+			if e := lang.Elem(i); e[2] == s[1] && e[3] == s[2] {
+				return langID(i), nil
+			}
+		}
+		return 0, mkErrInvalid(s)
+	}
+	return 0, errSyntax
+}
+
+// stringToBuf writes the string to b and returns the number of bytes
+// written.  cap(b) must be >= 3.
+func (id langID) stringToBuf(b []byte) int {
+	if id >= langNoIndexOffset {
+		intToStr(uint(id)-langNoIndexOffset, b[:3])
+		return 3
+	} else if id == 0 {
+		return copy(b, "und")
+	}
+	l := lang[id<<2:]
+	if l[3] == 0 {
+		return copy(b, l[:3])
+	}
+	return copy(b, l[:2])
+}
+
+// String returns the BCP 47 representation of the langID.
+// Use b as variable name, instead of id, to ensure the variable
+// used is consistent with that of Base in which this type is embedded.
+func (b langID) String() string {
+	if b == 0 {
+		return "und"
+	} else if b >= langNoIndexOffset {
+		b -= langNoIndexOffset
+		buf := [3]byte{}
+		intToStr(uint(b), buf[:])
+		return string(buf[:])
+	}
+	l := lang.Elem(int(b))
+	if l[3] == 0 {
+		return l[:3]
+	}
+	return l[:2]
+}
+
+// ISO3 returns the ISO 639-3 language code.
+func (b langID) ISO3() string {
+	if b == 0 || b >= langNoIndexOffset {
+		return b.String()
+	}
+	l := lang.Elem(int(b))
+	if l[3] == 0 {
+		return l[:3]
+	} else if l[2] == 0 {
+		return altLangISO3.Elem(int(l[3]))[:3]
+	}
+	// This allocation will only happen for 3-letter ISO codes
+	// that are non-canonical BCP 47 language identifiers.
+	return l[0:1] + l[2:4]
+}
+
+// IsPrivateUse reports whether this language code is reserved for private use.
+func (b langID) IsPrivateUse() bool {
+	return langPrivateStart <= b && b <= langPrivateEnd
+}
+
+type regionID uint16
+
+// getRegionID returns the region id for s if s is a valid 2-letter region code
+// or unknownRegion.
+func getRegionID(s []byte) (regionID, error) {
+	if len(s) == 3 {
+		if isAlpha(s[0]) {
+			return getRegionISO3(s)
+		}
+		if i, err := strconv.ParseUint(string(s), 10, 10); err == nil {
+			return getRegionM49(int(i))
+		}
+	}
+	return getRegionISO2(s)
+}
+
+// getRegionISO2 returns the regionID for the given 2-letter ISO country code
+// or unknownRegion if this does not exist.
+func getRegionISO2(s []byte) (regionID, error) {
+	i, err := findIndex(regionISO, s, "ZZ")
+	if err != nil {
+		return 0, err
+	}
+	return regionID(i) + isoRegionOffset, nil
+}
+
+// getRegionISO3 returns the regionID for the given 3-letter ISO country code
+// or unknownRegion if this does not exist.
+func getRegionISO3(s []byte) (regionID, error) {
+	if tag.FixCase("ZZZ", s) {
+		for i := regionISO.Index(s[:1]); i != -1; i = regionISO.Next(s[:1], i) {
+			if e := regionISO.Elem(i); e[2] == s[1] && e[3] == s[2] {
+				return regionID(i) + isoRegionOffset, nil
+			}
+		}
+		for i := 0; i < len(altRegionISO3); i += 3 {
+			if tag.Compare(altRegionISO3[i:i+3], s) == 0 {
+				return regionID(altRegionIDs[i/3]), nil
+			}
+		}
+		return 0, mkErrInvalid(s)
+	}
+	return 0, errSyntax
+}
+
+func getRegionM49(n int) (regionID, error) {
+	if 0 < n && n <= 999 {
+		const (
+			searchBits = 7
+			regionBits = 9
+			regionMask = 1<<regionBits - 1
+		)
+		idx := n >> searchBits
+		buf := fromM49[m49Index[idx]:m49Index[idx+1]]
+		val := uint16(n) << regionBits // we rely on bits shifting out
+		i := sort.Search(len(buf), func(i int) bool {
+			return buf[i] >= val
+		})
+		if r := fromM49[int(m49Index[idx])+i]; r&^regionMask == val {
+			return regionID(r & regionMask), nil
+		}
+	}
+	var e ValueError
+	fmt.Fprint(bytes.NewBuffer([]byte(e.v[:])), n)
+	return 0, e
+}
+
+// normRegion returns a region if r is deprecated or 0 otherwise.
+// TODO: consider supporting BYS (-> BLR), CSK (-> 200 or CZ), PHI (-> PHL) and AFI (-> DJ).
+// TODO: consider mapping split up regions to new most populous one (like CLDR).
+func normRegion(r regionID) regionID {
+	m := regionOldMap
+	k := sort.Search(len(m), func(i int) bool {
+		return m[i].from >= uint16(r)
+	})
+	if k < len(m) && m[k].from == uint16(r) {
+		return regionID(m[k].to)
+	}
+	return 0
+}
+
+const (
+	iso3166UserAssigned = 1 << iota
+	ccTLD
+	bcp47Region
+)
+
+func (r regionID) typ() byte {
+	return regionTypes[r]
+}
+
+// String returns the BCP 47 representation for the region.
+// It returns "ZZ" for an unspecified region.
+func (r regionID) String() string {
+	if r < isoRegionOffset {
+		if r == 0 {
+			return "ZZ"
+		}
+		return fmt.Sprintf("%03d", r.M49())
+	}
+	r -= isoRegionOffset
+	return regionISO.Elem(int(r))[:2]
+}
+
+// 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 regionID) ISO3() string {
+	if r < isoRegionOffset {
+		return "ZZZ"
+	}
+	r -= isoRegionOffset
+	reg := regionISO.Elem(int(r))
+	switch reg[2] {
+	case 0:
+		return altRegionISO3[reg[3]:][:3]
+	case ' ':
+		return "ZZZ"
+	}
+	return reg[0:1] + reg[2:4]
+}
+
+// M49 returns the UN M.49 encoding of r, or 0 if this encoding
+// is not defined for r.
+func (r regionID) M49() int {
+	return int(m49[r])
+}
+
+// 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 regionID) IsPrivateUse() bool {
+	return r.typ()&iso3166UserAssigned != 0
+}
+
+type scriptID uint8
+
+// getScriptID returns the script id for string s. It assumes that s
+// is of the format [A-Z][a-z]{3}.
+func getScriptID(idx tag.Index, s []byte) (scriptID, error) {
+	i, err := findIndex(idx, s, "Zzzz")
+	return scriptID(i), err
+}
+
+// String returns the script code in title case.
+// It returns "Zzzz" for an unspecified script.
+func (s scriptID) String() string {
+	if s == 0 {
+		return "Zzzz"
+	}
+	return script.Elem(int(s))
+}
+
+// IsPrivateUse reports whether this script code is reserved for private use.
+func (s scriptID) IsPrivateUse() bool {
+	return _Qaaa <= s && s <= _Qabx
+}
+
+const (
+	maxAltTaglen = len("en-US-POSIX")
+	maxLen       = maxAltTaglen
+)
+
+var (
+	// grandfatheredMap holds a mapping from legacy and grandfathered tags to
+	// their base language or index to more elaborate tag.
+	grandfatheredMap = map[[maxLen]byte]int16{
+		[maxLen]byte{'a', 'r', 't', '-', 'l', 'o', 'j', 'b', 'a', 'n'}: _jbo, // art-lojban
+		[maxLen]byte{'i', '-', 'a', 'm', 'i'}:                          _ami, // i-ami
+		[maxLen]byte{'i', '-', 'b', 'n', 'n'}:                          _bnn, // i-bnn
+		[maxLen]byte{'i', '-', 'h', 'a', 'k'}:                          _hak, // i-hak
+		[maxLen]byte{'i', '-', 'k', 'l', 'i', 'n', 'g', 'o', 'n'}:      _tlh, // i-klingon
+		[maxLen]byte{'i', '-', 'l', 'u', 'x'}:                          _lb,  // i-lux
+		[maxLen]byte{'i', '-', 'n', 'a', 'v', 'a', 'j', 'o'}:           _nv,  // i-navajo
+		[maxLen]byte{'i', '-', 'p', 'w', 'n'}:                          _pwn, // i-pwn
+		[maxLen]byte{'i', '-', 't', 'a', 'o'}:                          _tao, // i-tao
+		[maxLen]byte{'i', '-', 't', 'a', 'y'}:                          _tay, // i-tay
+		[maxLen]byte{'i', '-', 't', 's', 'u'}:                          _tsu, // i-tsu
+		[maxLen]byte{'n', 'o', '-', 'b', 'o', 'k'}:                     _nb,  // no-bok
+		[maxLen]byte{'n', 'o', '-', 'n', 'y', 'n'}:                     _nn,  // no-nyn
+		[maxLen]byte{'s', 'g', 'n', '-', 'b', 'e', '-', 'f', 'r'}:      _sfb, // sgn-BE-FR
+		[maxLen]byte{'s', 'g', 'n', '-', 'b', 'e', '-', 'n', 'l'}:      _vgt, // sgn-BE-NL
+		[maxLen]byte{'s', 'g', 'n', '-', 'c', 'h', '-', 'd', 'e'}:      _sgg, // sgn-CH-DE
+		[maxLen]byte{'z', 'h', '-', 'g', 'u', 'o', 'y', 'u'}:           _cmn, // zh-guoyu
+		[maxLen]byte{'z', 'h', '-', 'h', 'a', 'k', 'k', 'a'}:           _hak, // zh-hakka
+		[maxLen]byte{'z', 'h', '-', 'm', 'i', 'n', '-', 'n', 'a', 'n'}: _nan, // zh-min-nan
+		[maxLen]byte{'z', 'h', '-', 'x', 'i', 'a', 'n', 'g'}:           _hsn, // zh-xiang
+
+		// Grandfathered tags with no modern replacement will be converted as
+		// follows:
+		[maxLen]byte{'c', 'e', 'l', '-', 'g', 'a', 'u', 'l', 'i', 's', 'h'}: -1, // cel-gaulish
+		[maxLen]byte{'e', 'n', '-', 'g', 'b', '-', 'o', 'e', 'd'}:           -2, // en-GB-oed
+		[maxLen]byte{'i', '-', 'd', 'e', 'f', 'a', 'u', 'l', 't'}:           -3, // i-default
+		[maxLen]byte{'i', '-', 'e', 'n', 'o', 'c', 'h', 'i', 'a', 'n'}:      -4, // i-enochian
+		[maxLen]byte{'i', '-', 'm', 'i', 'n', 'g', 'o'}:                     -5, // i-mingo
+		[maxLen]byte{'z', 'h', '-', 'm', 'i', 'n'}:                          -6, // zh-min
+
+		// CLDR-specific tag.
+		[maxLen]byte{'r', 'o', 'o', 't'}:                                    0,  // root
+		[maxLen]byte{'e', 'n', '-', 'u', 's', '-', 'p', 'o', 's', 'i', 'x'}: -7, // en_US_POSIX"
+	}
+
+	altTagIndex = [...]uint8{0, 17, 31, 45, 61, 74, 86, 102}
+
+	altTags = "xtg-x-cel-gaulishen-GB-oxendicten-x-i-defaultund-x-i-enochiansee-x-i-mingonan-x-zh-minen-US-u-va-posix"
+)
+
+func grandfathered(s [maxAltTaglen]byte) (t Tag, ok bool) {
+	if v, ok := grandfatheredMap[s]; ok {
+		if v < 0 {
+			return Make(altTags[altTagIndex[-v-1]:altTagIndex[-v]]), true
+		}
+		t.lang = langID(v)
+		return t, true
+	}
+	return t, false
+}

data/ext/vendor/golang.org/x/text/language/lookup_test.go

@@ -0,0 +1,457 @@
+// Copyright 2013 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.
+
+package language
+
+import (
+	"testing"
+
+	"golang.org/x/text/internal/tag"
+)
+
+func b(s string) []byte {
+	return []byte(s)
+}
+
+func TestLangID(t *testing.T) {
+	tests := []struct {
+		id, bcp47, iso3, norm string
+		err                   error
+	}{
+		{id: "", bcp47: "und", iso3: "und", err: errSyntax},
+		{id: "  ", bcp47: "und", iso3: "und", err: errSyntax},
+		{id: "   ", bcp47: "und", iso3: "und", err: errSyntax},
+		{id: "    ", bcp47: "und", iso3: "und", err: errSyntax},
+		{id: "xxx", bcp47: "und", iso3: "und", err: mkErrInvalid([]byte("xxx"))},
+		{id: "und", bcp47: "und", iso3: "und"},
+		{id: "aju", bcp47: "aju", iso3: "aju", norm: "jrb"},
+		{id: "jrb", bcp47: "jrb", iso3: "jrb"},
+		{id: "es", bcp47: "es", iso3: "spa"},
+		{id: "spa", bcp47: "es", iso3: "spa"},
+		{id: "ji", bcp47: "ji", iso3: "yid-", norm: "yi"},
+		{id: "jw", bcp47: "jw", iso3: "jav-", norm: "jv"},
+		{id: "ar", bcp47: "ar", iso3: "ara"},
+		{id: "kw", bcp47: "kw", iso3: "cor"},
+		{id: "arb", bcp47: "arb", iso3: "arb", norm: "ar"},
+		{id: "ar", bcp47: "ar", iso3: "ara"},
+		{id: "kur", bcp47: "ku", iso3: "kur"},
+		{id: "nl", bcp47: "nl", iso3: "nld"},
+		{id: "NL", bcp47: "nl", iso3: "nld"},
+		{id: "gsw", bcp47: "gsw", iso3: "gsw"},
+		{id: "gSW", bcp47: "gsw", iso3: "gsw"},
+		{id: "und", bcp47: "und", iso3: "und"},
+		{id: "sh", bcp47: "sh", iso3: "hbs", norm: "sr"},
+		{id: "hbs", bcp47: "sh", iso3: "hbs", norm: "sr"},
+		{id: "no", bcp47: "no", iso3: "nor", norm: "no"},
+		{id: "nor", bcp47: "no", iso3: "nor", norm: "no"},
+		{id: "cmn", bcp47: "cmn", iso3: "cmn", norm: "zh"},
+	}
+	for i, tt := range tests {
+		want, err := getLangID(b(tt.id))
+		if err != tt.err {
+			t.Errorf("%d:err(%s): found %q; want %q", i, tt.id, err, tt.err)
+		}
+		if err != nil {
+			continue
+		}
+		if id, _ := getLangISO2(b(tt.bcp47)); len(tt.bcp47) == 2 && want != id {
+			t.Errorf("%d:getISO2(%s): found %v; want %v", i, tt.bcp47, id, want)
+		}
+		if len(tt.iso3) == 3 {
+			if id, _ := getLangISO3(b(tt.iso3)); want != id {
+				t.Errorf("%d:getISO3(%s): found %q; want %q", i, tt.iso3, id, want)
+			}
+			if id, _ := getLangID(b(tt.iso3)); want != id {
+				t.Errorf("%d:getID3(%s): found %v; want %v", i, tt.iso3, id, want)
+			}
+		}
+		norm := want
+		if tt.norm != "" {
+			norm, _ = getLangID(b(tt.norm))
+		}
+		id, _ := normLang(want)
+		if id != norm {
+			t.Errorf("%d:norm(%s): found %v; want %v", i, tt.id, id, norm)
+		}
+		if id := want.String(); tt.bcp47 != id {
+			t.Errorf("%d:String(): found %s; want %s", i, id, tt.bcp47)
+		}
+		if id := want.ISO3(); tt.iso3[:3] != id {
+			t.Errorf("%d:iso3(): found %s; want %s", i, id, tt.iso3[:3])
+		}
+	}
+}
+
+func TestGrandfathered(t *testing.T) {
+	for _, tt := range []struct{ in, out string }{
+		{"art-lojban", "jbo"},
+		{"i-ami", "ami"},
+		{"i-bnn", "bnn"},
+		{"i-hak", "hak"},
+		{"i-klingon", "tlh"},
+		{"i-lux", "lb"},
+		{"i-navajo", "nv"},
+		{"i-pwn", "pwn"},
+		{"i-tao", "tao"},
+		{"i-tay", "tay"},
+		{"i-tsu", "tsu"},
+		{"no-bok", "nb"},
+		{"no-nyn", "nn"},
+		{"sgn-BE-FR", "sfb"},
+		{"sgn-BE-NL", "vgt"},
+		{"sgn-CH-DE", "sgg"},
+		{"sgn-ch-de", "sgg"},
+		{"zh-guoyu", "cmn"},
+		{"zh-hakka", "hak"},
+		{"zh-min-nan", "nan"},
+		{"zh-xiang", "hsn"},
+
+		// Grandfathered tags with no modern replacement will be converted as follows:
+		{"cel-gaulish", "xtg-x-cel-gaulish"},
+		{"en-GB-oed", "en-GB-oxendict"},
+		{"en-gb-oed", "en-GB-oxendict"},
+		{"i-default", "en-x-i-default"},
+		{"i-enochian", "und-x-i-enochian"},
+		{"i-mingo", "see-x-i-mingo"},
+		{"zh-min", "nan-x-zh-min"},
+
+		{"root", "und"},
+		{"en_US_POSIX", "en-US-u-va-posix"},
+		{"en_us_posix", "en-US-u-va-posix"},
+		{"en-us-posix", "en-US-u-va-posix"},
+	} {
+		got := Raw.Make(tt.in)
+		want := Raw.MustParse(tt.out)
+		if got != want {
+			t.Errorf("%s: got %q; want %q", tt.in, got, want)
+		}
+	}
+}
+
+func TestRegionID(t *testing.T) {
+	tests := []struct {
+		in, out string
+	}{
+		{"_  ", ""},
+		{"_000", ""},
+		{"419", "419"},
+		{"AA", "AA"},
+		{"ATF", "TF"},
+		{"HV", "HV"},
+		{"CT", "CT"},
+		{"DY", "DY"},
+		{"IC", "IC"},
+		{"FQ", "FQ"},
+		{"JT", "JT"},
+		{"ZZ", "ZZ"},
+		{"EU", "EU"},
+		{"QO", "QO"},
+		{"FX", "FX"},
+	}
+	for i, tt := range tests {
+		if tt.in[0] == '_' {
+			id := tt.in[1:]
+			if _, err := getRegionID(b(id)); err == nil {
+				t.Errorf("%d:err(%s): found nil; want error", i, id)
+			}
+			continue
+		}
+		want, _ := getRegionID(b(tt.in))
+		if s := want.String(); s != tt.out {
+			t.Errorf("%d:%s: found %q; want %q", i, tt.in, s, tt.out)
+		}
+		if len(tt.in) == 2 {
+			want, _ := getRegionISO2(b(tt.in))
+			if s := want.String(); s != tt.out {
+				t.Errorf("%d:getISO2(%s): found %q; want %q", i, tt.in, s, tt.out)
+			}
+		}
+	}
+}
+
+func TestRegionType(t *testing.T) {
+	for _, tt := range []struct {
+		r string
+		t byte
+	}{
+		{"NL", bcp47Region | ccTLD},
+		{"EU", bcp47Region | ccTLD}, // exceptionally reserved
+		{"AN", bcp47Region | ccTLD}, // transitionally reserved
+
+		{"DD", bcp47Region}, // deleted in ISO, deprecated in BCP 47
+		{"NT", bcp47Region}, // transitionally reserved, deprecated in BCP 47
+
+		{"XA", iso3166UserAssigned | bcp47Region},
+		{"ZZ", iso3166UserAssigned | bcp47Region},
+		{"AA", iso3166UserAssigned | bcp47Region},
+		{"QO", iso3166UserAssigned | bcp47Region},
+		{"QM", iso3166UserAssigned | bcp47Region},
+		{"XK", iso3166UserAssigned | bcp47Region},
+
+		{"CT", 0}, // deleted in ISO, not in BCP 47, canonicalized in CLDR
+	} {
+		r := MustParseRegion(tt.r)
+		if tp := r.typ(); tp != tt.t {
+			t.Errorf("Type(%s): got %x; want %x", tt.r, tp, tt.t)
+		}
+	}
+}
+
+func TestRegionISO3(t *testing.T) {
+	tests := []struct {
+		from, iso3, to string
+	}{
+		{"  ", "ZZZ", "ZZ"},
+		{"000", "ZZZ", "ZZ"},
+		{"AA", "AAA", ""},
+		{"CT", "CTE", ""},
+		{"DY", "DHY", ""},
+		{"EU", "QUU", ""},
+		{"HV", "HVO", ""},
+		{"IC", "ZZZ", "ZZ"},
+		{"JT", "JTN", ""},
+		{"PZ", "PCZ", ""},
+		{"QU", "QUU", "EU"},
+		{"QO", "QOO", ""},
+		{"YD", "YMD", ""},
+		{"FQ", "ATF", "TF"},
+		{"TF", "ATF", ""},
+		{"FX", "FXX", ""},
+		{"ZZ", "ZZZ", ""},
+		{"419", "ZZZ", "ZZ"},
+	}
+	for _, tt := range tests {
+		r, _ := getRegionID(b(tt.from))
+		if s := r.ISO3(); s != tt.iso3 {
+			t.Errorf("iso3(%q): found %q; want %q", tt.from, s, tt.iso3)
+		}
+		if tt.iso3 == "" {
+			continue
+		}
+		want := tt.to
+		if tt.to == "" {
+			want = tt.from
+		}
+		r, _ = getRegionID(b(want))
+		if id, _ := getRegionISO3(b(tt.iso3)); id != r {
+			t.Errorf("%s: found %q; want %q", tt.iso3, id, want)
+		}
+	}
+}
+
+func TestRegionM49(t *testing.T) {
+	fromTests := []struct {
+		m49 int
+		id  string
+	}{
+		{0, ""},
+		{-1, ""},
+		{1000, ""},
+		{10000, ""},
+
+		{001, "001"},
+		{104, "MM"},
+		{180, "CD"},
+		{230, "ET"},
+		{231, "ET"},
+		{249, "FX"},
+		{250, "FR"},
+		{276, "DE"},
+		{278, "DD"},
+		{280, "DE"},
+		{419, "419"},
+		{626, "TL"},
+		{736, "SD"},
+		{840, "US"},
+		{854, "BF"},
+		{891, "CS"},
+		{899, ""},
+		{958, "AA"},
+		{966, "QT"},
+		{967, "EU"},
+		{999, "ZZ"},
+	}
+	for _, tt := range fromTests {
+		id, err := getRegionM49(tt.m49)
+		if want, have := err != nil, tt.id == ""; want != have {
+			t.Errorf("error(%d): have %v; want %v", tt.m49, have, want)
+			continue
+		}
+		r, _ := getRegionID(b(tt.id))
+		if r != id {
+			t.Errorf("region(%d): have %s; want %s", tt.m49, id, r)
+		}
+	}
+
+	toTests := []struct {
+		m49 int
+		id  string
+	}{
+		{0, "000"},
+		{0, "IC"}, // Some codes don't have an ID
+
+		{001, "001"},
+		{104, "MM"},
+		{104, "BU"},
+		{180, "CD"},
+		{180, "ZR"},
+		{231, "ET"},
+		{250, "FR"},
+		{249, "FX"},
+		{276, "DE"},
+		{278, "DD"},
+		{419, "419"},
+		{626, "TL"},
+		{626, "TP"},
+		{729, "SD"},
+		{826, "GB"},
+		{840, "US"},
+		{854, "BF"},
+		{891, "YU"},
+		{891, "CS"},
+		{958, "AA"},
+		{966, "QT"},
+		{967, "EU"},
+		{967, "QU"},
+		{999, "ZZ"},
+		// For codes that don't have an M49 code use the replacement value,
+		// if available.
+		{854, "HV"}, // maps to Burkino Faso
+	}
+	for _, tt := range toTests {
+		r, _ := getRegionID(b(tt.id))
+		if r.M49() != tt.m49 {
+			t.Errorf("m49(%q): have %d; want %d", tt.id, r.M49(), tt.m49)
+		}
+	}
+}
+
+func TestRegionDeprecation(t *testing.T) {
+	tests := []struct{ in, out string }{
+		{"BU", "MM"},
+		{"BUR", "MM"},
+		{"CT", "KI"},
+		{"DD", "DE"},
+		{"DDR", "DE"},
+		{"DY", "BJ"},
+		{"FX", "FR"},
+		{"HV", "BF"},
+		{"JT", "UM"},
+		{"MI", "UM"},
+		{"NH", "VU"},
+		{"NQ", "AQ"},
+		{"PU", "UM"},
+		{"PZ", "PA"},
+		{"QU", "EU"},
+		{"RH", "ZW"},
+		{"TP", "TL"},
+		{"UK", "GB"},
+		{"VD", "VN"},
+		{"WK", "UM"},
+		{"YD", "YE"},
+		{"NL", "NL"},
+	}
+	for _, tt := range tests {
+		rIn, _ := getRegionID([]byte(tt.in))
+		rOut, _ := getRegionISO2([]byte(tt.out))
+		r := normRegion(rIn)
+		if rOut == rIn && r != 0 {
+			t.Errorf("%s: was %q; want %q", tt.in, r, tt.in)
+		}
+		if rOut != rIn && r != rOut {
+			t.Errorf("%s: was %q; want %q", tt.in, r, tt.out)
+		}
+
+	}
+}
+
+func TestGetScriptID(t *testing.T) {
+	idx := tag.Index("0000BbbbDdddEeeeZzzz\xff\xff\xff\xff")
+	tests := []struct {
+		in  string
+		out scriptID
+	}{
+		{"    ", 0},
+		{"      ", 0},
+		{"  ", 0},
+		{"", 0},
+		{"Aaaa", 0},
+		{"Bbbb", 1},
+		{"Dddd", 2},
+		{"dddd", 2},
+		{"dDDD", 2},
+		{"Eeee", 3},
+		{"Zzzz", 4},
+	}
+	for i, tt := range tests {
+		if id, err := getScriptID(idx, b(tt.in)); id != tt.out {
+			t.Errorf("%d:%s: found %d; want %d", i, tt.in, id, tt.out)
+		} else if id == 0 && err == nil {
+			t.Errorf("%d:%s: no error; expected one", i, tt.in)
+		}
+	}
+}
+
+func TestIsPrivateUse(t *testing.T) {
+	type test struct {
+		s       string
+		private bool
+	}
+	tests := []test{
+		{"en", false},
+		{"und", false},
+		{"pzn", false},
+		{"qaa", true},
+		{"qtz", true},
+		{"qua", false},
+	}
+	for i, tt := range tests {
+		x, _ := getLangID([]byte(tt.s))
+		if b := x.IsPrivateUse(); b != tt.private {
+			t.Errorf("%d: langID.IsPrivateUse(%s) was %v; want %v", i, tt.s, b, tt.private)
+		}
+	}
+	tests = []test{
+		{"001", false},
+		{"419", false},
+		{"899", false},
+		{"900", false},
+		{"957", false},
+		{"958", true},
+		{"AA", true},
+		{"AC", false},
+		{"EU", false}, // CLDR grouping, exceptionally reserved in ISO.
+		{"QU", true},  // Canonicalizes to EU, User-assigned in ISO.
+		{"QO", true},  // CLDR grouping, User-assigned in ISO.
+		{"QA", false},
+		{"QM", true},
+		{"QZ", true},
+		{"XA", true},
+		{"XK", true}, // Assigned to Kosovo in CLDR, User-assigned in ISO.
+		{"XZ", true},
+		{"ZW", false},
+		{"ZZ", true},
+	}
+	for i, tt := range tests {
+		x, _ := getRegionID([]byte(tt.s))
+		if b := x.IsPrivateUse(); b != tt.private {
+			t.Errorf("%d: regionID.IsPrivateUse(%s) was %v; want %v", i, tt.s, b, tt.private)
+		}
+	}
+	tests = []test{
+		{"Latn", false},
+		{"Laaa", false}, // invalid
+		{"Qaaa", true},
+		{"Qabx", true},
+		{"Qaby", false},
+		{"Zyyy", false},
+		{"Zzzz", false},
+	}
+	for i, tt := range tests {
+		x, _ := getScriptID(script, []byte(tt.s))
+		if b := x.IsPrivateUse(); b != tt.private {
+			t.Errorf("%d: scriptID.IsPrivateUse(%s) was %v; want %v", i, tt.s, b, tt.private)
+		}
+	}
+}