func TestTables(t *testing.T) {
if !*long {
return
}
gen.Init()
// Read the CLDR zip file.
r := gen.OpenCLDRCoreZip()
defer r.Close()
d := &cldr.Decoder{}
d.SetDirFilter("supplemental", "main")
d.SetSectionFilter("numbers")
data, err := d.DecodeZip(r)
if err != nil {
t.Fatalf("DecodeZip: %v", err)
}
dr, err := cldr.ParseDraft(*draft)
if err != nil {
t.Fatalf("filter: %v", err)
}
for _, lang := range data.Locales() {
p := message.NewPrinter(language.MustParse(lang))
ldml := data.RawLDML(lang)
if ldml.Numbers == nil || ldml.Numbers.Currencies == nil {
continue
}
for _, c := range ldml.Numbers.Currencies.Currency {
syms := cldr.MakeSlice(&c.Symbol)
syms.SelectDraft(dr)
for _, sym := range c.Symbol {
cur, err := ParseISO(c.Type)
if err != nil {
continue
}
formatter := Symbol
switch sym.Alt {
case "":
case "narrow":
formatter = NarrowSymbol
default:
continue
}
want := sym.Data()
if got := p.Sprint(formatter(cur)); got != want {
t.Errorf("%s:%sSymbol(%s) = %s; want %s", lang, strings.Title(sym.Alt), c.Type, got, want)
}
}
}
}
}
func ExampleSlice() {
var dr *cldr.CLDR // assume this is initalized
x, _ := dr.LDML("en")
cs := x.Collations.Collation
// remove all but the default
cldr.MakeSlice(&cs).Filter(func(e cldr.Elem) bool {
return e.GetCommon().Type != x.Collations.Default()
})
for i, c := range cs {
fmt.Println(i, c.Type)
}
}
func (b *builder) filter() {
filter := func(s *cldr.Slice) {
if *short {
s.SelectOnePerGroup("alt", []string{"short", ""})
} else {
s.SelectOnePerGroup("alt", []string{"stand-alone", ""})
}
d, err := cldr.ParseDraft(*draft)
if err != nil {
log.Fatalf("filter: %v", err)
}
s.SelectDraft(d)
}
for _, loc := range b.data.Locales() {
if ldn := b.data.RawLDML(loc).LocaleDisplayNames; ldn != nil {
if ldn.Languages != nil {
s := cldr.MakeSlice(&ldn.Languages.Language)
if filter(&s); len(ldn.Languages.Language) == 0 {
ldn.Languages = nil
}
}
if ldn.Scripts != nil {
s := cldr.MakeSlice(&ldn.Scripts.Script)
if filter(&s); len(ldn.Scripts.Script) == 0 {
ldn.Scripts = nil
}
}
if ldn.Territories != nil {
s := cldr.MakeSlice(&ldn.Territories.Territory)
if filter(&s); len(ldn.Territories.Territory) == 0 {
ldn.Territories = nil
}
}
}
}
}
// parseCollation parses XML files in the collation directory of the CLDR core.zip file.
func parseCollation(b *build.Builder) {
d := &cldr.Decoder{}
d.SetDirFilter("collation")
data := decodeCLDR(d)
for _, loc := range data.Locales() {
x, err := data.LDML(loc)
failOnError(err)
if skipLang(x.Identity.Language.Type) {
continue
}
cs := x.Collations.Collation
sl := cldr.MakeSlice(&cs)
if len(types.s) == 0 {
sl.SelectAnyOf("type", x.Collations.Default())
} else if !types.all {
sl.SelectAnyOf("type", types.s...)
}
sl.SelectOnePerGroup("alt", altInclude())
for _, c := range cs {
id, err := language.Parse(loc)
if err != nil {
fmt.Fprintf(os.Stderr, "invalid locale: %q", err)
continue
}
// Support both old- and new-style defaults.
d := c.Type
if x.Collations.DefaultCollation == nil {
d = x.Collations.Default()
} else {
d = x.Collations.DefaultCollation.Data()
}
// We assume tables are being built either for search or collation,
// but not both. For search the default is always "search".
if d != c.Type && c.Type != "search" {
typ := c.Type
if len(c.Type) > 8 {
typ = typeMap[c.Type]
}
id, err = id.SetTypeForKey("co", typ)
failOnError(err)
}
t := b.Tailoring(id)
c.Process(processor{t})
}
}
}
// genSymbols generates the symbols used for currencies. Most symbols are
// defined in root and there is only very small variation per language.
// The following rules apply:
// - A symbol can be requested as normal or narrow.
// - If a symbol is not defined for a currency, it defaults to its ISO code.
func (b *builder) genSymbols(w *gen.CodeWriter, data *cldr.CLDR) {
d, err := cldr.ParseDraft(*draft)
if err != nil {
log.Fatalf("filter: %v", err)
}
const (
normal = iota
narrow
numTypes
)
// language -> currency -> type -> symbol
var symbols [language.NumCompactTags][][numTypes]*string
// Collect symbol information per language.
for _, lang := range data.Locales() {
ldml := data.RawLDML(lang)
if ldml.Numbers == nil || ldml.Numbers.Currencies == nil {
continue
}
langIndex, ok := language.CompactIndex(language.MustParse(lang))
if !ok {
log.Fatalf("No compact index for language %s", lang)
}
symbols[langIndex] = make([][numTypes]*string, b.numCurrencies+1)
for _, c := range ldml.Numbers.Currencies.Currency {
syms := cldr.MakeSlice(&c.Symbol)
syms.SelectDraft(d)
for _, sym := range c.Symbol {
v := sym.Data()
if v == c.Type {
// We define "" to mean the ISO symbol.
v = ""
}
cur := b.currencies.Index([]byte(c.Type))
// XXX gets reassigned to 0 in the package's code.
if c.Type == "XXX" {
cur = 0
}
if cur == -1 {
fmt.Println("Unsupported:", c.Type)
continue
}
switch sym.Alt {
case "":
symbols[langIndex][cur][normal] = &v
case "narrow":
symbols[langIndex][cur][narrow] = &v
}
}
}
}
// Remove values identical to the parent.
for langIndex, data := range symbols {
for curIndex, curs := range data {
for typ, sym := range curs {
if sym == nil {
continue
}
for p := uint16(langIndex); p != 0; {
p = internal.Parent[p]
x := symbols[p]
if x == nil {
continue
}
if v := x[curIndex][typ]; v != nil || p == 0 {
// Value is equal to the default value root value is undefined.
parentSym := ""
if v != nil {
parentSym = *v
}
if parentSym == *sym {
// Value is the same as parent.
data[curIndex][typ] = nil
}
break
}
}
}
}
}
// Create symbol index.
symbolData := []byte{0}
symbolLookup := map[string]uint16{"": 0} // 0 means default, so block that value.
for _, data := range symbols {
for _, curs := range data {
for _, sym := range curs {
if sym == nil {
continue
}
if _, ok := symbolLookup[*sym]; !ok {
symbolLookup[*sym] = uint16(len(symbolData))
symbolData = append(symbolData, byte(len(*sym)))
symbolData = append(symbolData, *sym...)
}
}
}
}
w.WriteComment(`
symbols holds symbol data of the form <n> <str>, where n is the length of
the symbol string str.`)
w.WriteConst("symbols", string(symbolData))
// Create index from language to currency lookup to symbol.
type curToIndex struct{ cur, idx uint16 }
w.WriteType(curToIndex{})
prefix := []string{"normal", "narrow"}
// Create data for regular and narrow symbol data.
for typ := normal; typ <= narrow; typ++ {
indexes := []curToIndex{} // maps currency to symbol index
languages := []uint16{}
for _, data := range symbols {
languages = append(languages, uint16(len(indexes)))
for curIndex, curs := range data {
if sym := curs[typ]; sym != nil {
indexes = append(indexes, curToIndex{uint16(curIndex), symbolLookup[*sym]})
}
}
}
languages = append(languages, uint16(len(indexes)))
w.WriteVar(prefix[typ]+"LangIndex", languages)
w.WriteVar(prefix[typ]+"SymIndex", indexes)
}
}
// writeMatchData writes tables with languages and scripts for which there is
// mutual intelligibility. The data is based on CLDR's languageMatching data.
// Note that we use a different algorithm than the one defined by CLDR and that
// we slightly modify the data. For example, we convert scores to confidence levels.
// We also drop all region-related data as we use a different algorithm to
// determine region equivalence.
func (b *builder) writeMatchData() {
b.writeType(mutualIntelligibility{})
b.writeType(scriptIntelligibility{})
lm := b.supp.LanguageMatching.LanguageMatches
cldr.MakeSlice(&lm).SelectAnyOf("type", "written")
matchLang := []mutualIntelligibility{}
matchScript := []scriptIntelligibility{}
// Convert the languageMatch entries in lists keyed by desired language.
for _, m := range lm[0].LanguageMatch {
// Different versions of CLDR use different separators.
desired := strings.Replace(m.Desired, "-", "_", -1)
supported := strings.Replace(m.Supported, "-", "_", -1)
d := strings.Split(desired, "_")
s := strings.Split(supported, "_")
if len(d) != len(s) || len(d) > 2 {
// Skip all entries with regions and work around CLDR bug.
continue
}
pct, _ := strconv.ParseInt(m.Percent, 10, 8)
if len(d) == 2 && d[0] == s[0] && len(d[1]) == 4 {
// language-script pair.
lang := uint16(0)
if d[0] != "*" {
lang = uint16(b.langIndex(d[0]))
}
matchScript = append(matchScript, scriptIntelligibility{
lang: lang,
want: uint8(b.script.index(d[1])),
have: uint8(b.script.index(s[1])),
conf: toConf(uint8(pct)),
})
if m.Oneway != "true" {
matchScript = append(matchScript, scriptIntelligibility{
lang: lang,
want: uint8(b.script.index(s[1])),
have: uint8(b.script.index(d[1])),
conf: toConf(uint8(pct)),
})
}
} else if len(d) == 1 && d[0] != "*" {
if pct == 100 {
// nb == no is already handled by macro mapping. Check there
// really is only this case.
if d[0] != "no" || s[0] != "nb" {
log.Fatalf("unhandled equivalence %s == %s", s[0], d[0])
}
continue
}
matchLang = append(matchLang, mutualIntelligibility{
want: uint16(b.langIndex(d[0])),
have: uint16(b.langIndex(s[0])),
conf: uint8(pct),
oneway: m.Oneway == "true",
})
} else {
// TODO: Handle other mappings.
a := []string{"*;*", "*_*;*_*", "es_MX;es_419"}
s := strings.Join([]string{desired, supported}, ";")
if i := sort.SearchStrings(a, s); i == len(a) || a[i] != s {
log.Printf("%q not handled", s)
}
}
}
sort.Stable(sortByConf(matchLang))
// collapse percentage into confidence classes
for i, m := range matchLang {
matchLang[i].conf = toConf(m.conf)
}
b.writeSlice("matchLang", matchLang)
b.writeSlice("matchScript", matchScript)
}
func genSymbols(w *gen.CodeWriter, data *cldr.CLDR) {
d, err := cldr.ParseDraft(*draft)
if err != nil {
log.Fatalf("invalid draft level: %v", err)
}
nNumberSystems := system(len(systemMap))
type symbols [NumSymbolTypes]string
type key struct {
tag int // from language.CompactIndex
system system
}
symbolMap := map[key]*symbols{}
defaults := map[int]system{}
for _, lang := range data.Locales() {
ldml := data.RawLDML(lang)
if ldml.Numbers == nil {
continue
}
langIndex, ok := language.CompactIndex(language.MustParse(lang))
if !ok {
log.Fatalf("No compact index for language %s", lang)
}
if d := ldml.Numbers.DefaultNumberingSystem; len(d) > 0 {
defaults[langIndex] = getNumberSystem(d[0].Data())
}
syms := cldr.MakeSlice(&ldml.Numbers.Symbols)
syms.SelectDraft(d)
for _, sym := range ldml.Numbers.Symbols {
if sym.NumberSystem == "" {
// This is just linking the default of root to "latn".
continue
}
symbolMap[key{langIndex, getNumberSystem(sym.NumberSystem)}] = &symbols{
SymDecimal: getFirst("decimal", sym.Decimal),
SymGroup: getFirst("group", sym.Group),
SymList: getFirst("list", sym.List),
SymPercentSign: getFirst("percentSign", sym.PercentSign),
SymPlusSign: getFirst("plusSign", sym.PlusSign),
SymMinusSign: getFirst("minusSign", sym.MinusSign),
SymExponential: getFirst("exponential", sym.Exponential),
SymSuperscriptingExponent: getFirst("superscriptingExponent", sym.SuperscriptingExponent),
SymPerMille: getFirst("perMille", sym.PerMille),
SymInfinity: getFirst("infinity", sym.Infinity),
SymNan: getFirst("nan", sym.Nan),
SymTimeSeparator: getFirst("timeSeparator", sym.TimeSeparator),
}
}
}
// Expand all values.
for k, syms := range symbolMap {
for t := SymDecimal; t < NumSymbolTypes; t++ {
p := k.tag
for syms[t] == "" {
p = int(internal.Parent[p])
if pSyms, ok := symbolMap[key{p, k.system}]; ok && (*pSyms)[t] != "" {
syms[t] = (*pSyms)[t]
break
}
if p == 0 /* und */ {
// Default to root, latn.
syms[t] = (*symbolMap[key{}])[t]
}
}
}
}
// Unique the symbol sets and write the string data.
m := map[symbols]int{}
sb := stringset.NewBuilder()
symIndex := [][NumSymbolTypes]byte{}
for ns := system(0); ns < nNumberSystems; ns++ {
for _, l := range data.Locales() {
langIndex, _ := language.CompactIndex(language.MustParse(l))
s := symbolMap[key{langIndex, ns}]
if s == nil {
continue
}
if _, ok := m[*s]; !ok {
m[*s] = len(symIndex)
sb.Add(s[:]...)
var x [NumSymbolTypes]byte
for i := SymDecimal; i < NumSymbolTypes; i++ {
x[i] = byte(sb.Index((*s)[i]))
}
symIndex = append(symIndex, x)
}
}
}
w.WriteVar("symIndex", symIndex)
w.WriteVar("symData", sb.Set())
// resolveSymbolIndex gets the index from the closest matching locale,
// including the locale itself.
resolveSymbolIndex := func(langIndex int, ns system) byte {
for {
if sym := symbolMap[key{langIndex, ns}]; sym != nil {
return byte(m[*sym])
}
if langIndex == 0 {
return 0 // und, latn
}
langIndex = int(internal.Parent[langIndex])
}
}
// Create an index with the symbols for each locale for the latn numbering
// system. If this is not the default, or the only one, for a locale, we
// will overwrite the value later.
var langToDefaults [language.NumCompactTags]byte
for _, l := range data.Locales() {
langIndex, _ := language.CompactIndex(language.MustParse(l))
langToDefaults[langIndex] = resolveSymbolIndex(langIndex, 0)
}
// Delete redundant entries.
for _, l := range data.Locales() {
langIndex, _ := language.CompactIndex(language.MustParse(l))
def := defaults[langIndex]
syms := symbolMap[key{langIndex, def}]
if syms == nil {
continue
}
for ns := system(0); ns < nNumberSystems; ns++ {
if ns == def {
continue
}
if altSyms, ok := symbolMap[key{langIndex, ns}]; ok && *altSyms == *syms {
delete(symbolMap, key{langIndex, ns})
}
}
}
// Create a sorted list of alternatives per language. This will only need to
// be referenced if a user specified an alternative numbering system.
var langToAlt []altSymData
for _, l := range data.Locales() {
langIndex, _ := language.CompactIndex(language.MustParse(l))
start := len(langToAlt)
if start > 0x7F {
log.Fatal("Number of alternative assignments > 0x7F")
}
// Create the entry for the default value.
def := defaults[langIndex]
langToAlt = append(langToAlt, altSymData{
compactTag: uint16(langIndex),
system: def,
symIndex: resolveSymbolIndex(langIndex, def),
})
for ns := system(0); ns < nNumberSystems; ns++ {
if def == ns {
continue
}
if sym := symbolMap[key{langIndex, ns}]; sym != nil {
langToAlt = append(langToAlt, altSymData{
compactTag: uint16(langIndex),
system: ns,
symIndex: resolveSymbolIndex(langIndex, ns),
})
}
}
if def == 0 && len(langToAlt) == start+1 {
// No additional data: erase the entry.
langToAlt = langToAlt[:start]
} else {
// Overwrite the entry in langToDefaults.
langToDefaults[langIndex] = 0x80 | byte(start)
}
}
w.WriteComment(`
langToDefaults maps a compact language index to the default numbering system
and default symbol set`)
w.WriteVar("langToDefaults", langToDefaults)
w.WriteComment(`
langToAlt is a list of numbering system and symbol set pairs, sorted and
marked by compact language index.`)
w.WriteVar("langToAlt", langToAlt)
}
func TestTables(t *testing.T) {
testtext.SkipIfNotLong(t)
// Read the CLDR zip file.
r := gen.OpenCLDRCoreZip()
defer r.Close()
d := &cldr.Decoder{}
d.SetDirFilter("supplemental", "main")
d.SetSectionFilter("numbers")
data, err := d.DecodeZip(r)
if err != nil {
t.Fatalf("DecodeZip: %v", err)
}
dr, err := cldr.ParseDraft(*draft)
if err != nil {
t.Fatalf("filter: %v", err)
}
for _, lang := range data.Locales() {
p := message.NewPrinter(language.MustParse(lang))
ldml := data.RawLDML(lang)
if ldml.Numbers == nil || ldml.Numbers.Currencies == nil {
continue
}
for _, c := range ldml.Numbers.Currencies.Currency {
syms := cldr.MakeSlice(&c.Symbol)
syms.SelectDraft(dr)
for _, sym := range c.Symbol {
cur, err := ParseISO(c.Type)
if err != nil {
continue
}
formatter := Symbol
switch sym.Alt {
case "":
case "narrow":
formatter = NarrowSymbol
default:
continue
}
want := sym.Data()
if got := p.Sprint(formatter(cur)); got != want {
t.Errorf("%s:%sSymbol(%s) = %s; want %s", lang, strings.Title(sym.Alt), c.Type, got, want)
}
}
}
}
for _, reg := range data.Supplemental().CurrencyData.Region {
i := 0
for ; regionData[i].Region().String() != reg.Iso3166; i++ {
}
it := Query(Historical, NonTender, Region(language.MustParseRegion(reg.Iso3166)))
for _, cur := range reg.Currency {
from, _ := time.Parse("2006-01-02", cur.From)
to, _ := time.Parse("2006-01-02", cur.To)
it.Next()
for j, r := range []QueryIter{&iter{regionInfo: ®ionData[i]}, it} {
if got, _ := r.From(); from != got {
t.Errorf("%d:%s:%s:from: got %v; want %v", j, reg.Iso3166, cur.Iso4217, got, from)
}
if got, _ := r.To(); to != got {
t.Errorf("%d:%s:%s:to: got %v; want %v", j, reg.Iso3166, cur.Iso4217, got, to)
}
}
i++
}
}
}
// genFormats generates the lookup table for decimal, scientific and percent
// patterns.
//
// CLDR allows for patterns to be different per language for different numbering
// systems. In practice the patterns are set to be consistent for a language
// independent of the numbering system. genFormats verifies that no language
// deviates from this.
func genFormats(w *gen.CodeWriter, data *cldr.CLDR) {
d, err := cldr.ParseDraft(*draft)
if err != nil {
log.Fatalf("invalid draft level: %v", err)
}
// Fill the first slot with a dummy so we can identify unspecified tags.
formats := []number.Format{{}}
patterns := map[string]int{}
// TODO: It would be possible to eliminate two of these slices by having
// another indirection and store a reference to the combination of patterns.
decimal := make([]byte, language.NumCompactTags)
scientific := make([]byte, language.NumCompactTags)
percent := make([]byte, language.NumCompactTags)
for _, lang := range data.Locales() {
ldml := data.RawLDML(lang)
if ldml.Numbers == nil {
continue
}
langIndex, ok := language.CompactIndex(language.MustParse(lang))
if !ok {
log.Fatalf("No compact index for language %s", lang)
}
type patternSlice []*struct {
cldr.Common
Numbers string `xml:"numbers,attr"`
Count string `xml:"count,attr"`
}
add := func(name string, tags []byte, ps patternSlice) {
sl := cldr.MakeSlice(&ps)
sl.SelectDraft(d)
if len(ps) == 0 {
return
}
if len(ps) > 2 || len(ps) == 2 && ps[0] != ps[1] {
log.Fatalf("Inconsistent %d patterns for language %s", name, lang)
}
s := ps[0].Data()
index, ok := patterns[s]
if !ok {
nf, err := number.ParsePattern(s)
if err != nil {
log.Fatal(err)
}
index = len(formats)
patterns[s] = index
formats = append(formats, *nf)
}
tags[langIndex] = byte(index)
}
for _, df := range ldml.Numbers.DecimalFormats {
for _, l := range df.DecimalFormatLength {
if l.Type != "" {
continue
}
for _, f := range l.DecimalFormat {
add("decimal", decimal, f.Pattern)
}
}
}
for _, df := range ldml.Numbers.ScientificFormats {
for _, l := range df.ScientificFormatLength {
if l.Type != "" {
continue
}
for _, f := range l.ScientificFormat {
add("scientific", scientific, f.Pattern)
}
}
}
for _, df := range ldml.Numbers.PercentFormats {
for _, l := range df.PercentFormatLength {
if l.Type != "" {
continue
}
for _, f := range l.PercentFormat {
add("percent", percent, f.Pattern)
}
}
}
}
// Complete the parent tag array to reflect inheritance. An index of 0
// indicates an unspecified value.
for _, data := range [][]byte{decimal, scientific, percent} {
for i := range data {
p := uint16(i)
for ; data[p] == 0; p = internal.Parent[p] {
}
data[i] = data[p]
}
}
w.WriteVar("tagToDecimal", decimal)
w.WriteVar("tagToScientific", scientific)
w.WriteVar("tagToPercent", percent)
value := strings.Replace(fmt.Sprintf("%#v", formats), "number.", "", -1)
// Break up the lines. This won't give ideal perfect formatting, but it is
// better than one huge line.
value = strings.Replace(value, ", ", ",\n", -1)
fmt.Fprintf(w, "var formats = %s\n", value)
}
func TestSymbols(t *testing.T) {
testtext.SkipIfNotLong(t)
draft, err := cldr.ParseDraft(*draft)
if err != nil {
log.Fatalf("invalid draft level: %v", err)
}
r := gen.OpenCLDRCoreZip()
defer r.Close()
d := &cldr.Decoder{}
d.SetDirFilter("main")
d.SetSectionFilter("numbers")
data, err := d.DecodeZip(r)
if err != nil {
t.Fatalf("DecodeZip: %v", err)
}
for _, lang := range data.Locales() {
ldml := data.RawLDML(lang)
if ldml.Numbers == nil {
continue
}
langIndex, ok := language.CompactIndex(language.MustParse(lang))
if !ok {
t.Fatalf("No compact index for language %s", lang)
}
syms := cldr.MakeSlice(&ldml.Numbers.Symbols)
syms.SelectDraft(draft)
for _, sym := range ldml.Numbers.Symbols {
if sym.NumberSystem == "" {
continue
}
testCases := []struct {
name string
st SymbolType
x interface{}
}{
{"Decimal", SymDecimal, sym.Decimal},
{"Group", SymGroup, sym.Group},
{"List", SymList, sym.List},
{"PercentSign", SymPercentSign, sym.PercentSign},
{"PlusSign", SymPlusSign, sym.PlusSign},
{"MinusSign", SymMinusSign, sym.MinusSign},
{"Exponential", SymExponential, sym.Exponential},
{"SuperscriptingExponent", SymSuperscriptingExponent, sym.SuperscriptingExponent},
{"PerMille", SymPerMille, sym.PerMille},
{"Infinity", SymInfinity, sym.Infinity},
{"NaN", SymNan, sym.Nan},
{"TimeSeparator", SymTimeSeparator, sym.TimeSeparator},
}
info := InfoFromLangID(langIndex, sym.NumberSystem)
for _, tc := range testCases {
// Extract the wanted value.
v := reflect.ValueOf(tc.x)
if v.Len() == 0 {
return
}
if v.Len() > 1 {
t.Fatalf("Multiple values of %q within single symbol not supported.", tc.name)
}
want := v.Index(0).MethodByName("Data").Call(nil)[0].String()
got := info.Symbol(tc.st)
if got != want {
t.Errorf("%s:%s:%s: got %q; want %q", lang, sym.NumberSystem, tc.name, got, want)
}
}
}
}
}