func main() {
gen.Init()
gen.Repackage("gen_common.go", "common.go", "language")
w := gen.NewCodeWriter()
defer w.WriteGoFile("tables.go", "language")
fmt.Fprintln(w, `import "golang.org/x/text/internal/tag"`)
b := newBuilder(w)
gen.WriteCLDRVersion(w)
b.parseIndices()
b.writeType(fromTo{})
b.writeLanguage()
b.writeScript()
b.writeRegion()
b.writeVariant()
// TODO: b.writeLocale()
b.computeRegionGroups()
b.writeLikelyData()
b.writeMatchData()
b.writeRegionInclusionData()
b.writeParents()
}
func main() {
gen.Init()
// Read the CLDR zip file.
r := gen.OpenCLDRCoreZip()
defer r.Close()
d := &cldr.Decoder{}
d.SetDirFilter("main", "supplemental")
d.SetSectionFilter("localeDisplayNames")
data, err := d.DecodeZip(r)
if err != nil {
log.Fatalf("DecodeZip: %v", err)
}
w := gen.NewCodeWriter()
defer w.WriteGoFile(*outputFile, "display")
gen.WriteCLDRVersion(w)
b := builder{
w: w,
data: data,
group: make(map[string]*group),
}
b.generate()
}
func main() {
gen.Init()
gen.Repackage("gen_common.go", "common.go", "currency")
// 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 {
log.Fatalf("DecodeZip: %v", err)
}
w := gen.NewCodeWriter()
defer w.WriteGoFile(*outputFile, "currency")
fmt.Fprintln(w, `import "golang.org/x/text/internal/tag"`)
gen.WriteCLDRVersion(w)
b := &builder{}
b.genCurrencies(w, data.Supplemental())
b.genSymbols(w, data)
}
func main() {
gen.Init()
rewriteCommon()
w := gen.NewCodeWriter()
defer w.WriteGoFile("tables.go", "language")
b := newBuilder(w)
fmt.Fprintf(w, version, cldr.Version)
b.parseIndices()
b.writeType(fromTo{})
b.writeLanguage()
b.writeScript()
b.writeRegion()
b.writeVariant()
// TODO: b.writeLocale()
b.writeCurrencies()
b.computeRegionGroups()
b.writeLikelyData()
b.writeMatchData()
b.writeRegionInclusionData()
b.writeParents()
}
func genTables() {
chars := parseUCD()
verifyProperties(chars)
t := triegen.NewTrie("case")
for i := range chars {
c := &chars[i]
makeEntry(c)
t.Insert(rune(i), uint64(c.entry))
}
w := gen.NewCodeWriter()
defer w.WriteGoFile("tables.go", "cases")
gen.WriteUnicodeVersion(w)
// TODO: write CLDR version after adding a mechanism to detect that the
// tables on which the manually created locale-sensitive casing code is
// based hasn't changed.
w.WriteVar("xorData", string(xorData))
w.WriteVar("exceptions", string(exceptionData))
sz, err := t.Gen(w, triegen.Compact(&sparseCompacter{}))
if err != nil {
log.Fatal(err)
}
w.Size += sz
}
func main() {
gen.Init()
const pkg = "number"
gen.Repackage("gen_common.go", "common.go", pkg)
// Read the CLDR zip file.
r := gen.OpenCLDRCoreZip()
defer r.Close()
d := &cldr.Decoder{}
d.SetDirFilter("supplemental", "main")
d.SetSectionFilter("numbers", "numberingSystem")
data, err := d.DecodeZip(r)
if err != nil {
log.Fatalf("DecodeZip: %v", err)
}
w := gen.NewCodeWriter()
defer w.WriteGoFile(*outputFile, pkg)
fmt.Fprintln(w, `import "golang.org/x/text/internal/stringset"`)
gen.WriteCLDRVersion(w)
genNumSystem(w, data)
genSymbols(w, data)
}
func main() {
gen.Init()
names, counts := parse()
appendRepeatNames(names, counts)
appendUniqueNames(names, counts)
table0, table1 := makeTables()
gen.Repackage("gen_bits.go", "bits.go", "runenames")
w := gen.NewCodeWriter()
w.WriteVar("table0", table0)
w.WriteVar("table1", table1)
w.WriteConst("data", string(data))
w.WriteGoFile("tables.go", "runenames")
}
func writeTables() {
propTrie := triegen.NewTrie("derivedProperties")
w := gen.NewCodeWriter()
defer w.WriteGoFile(*outputFile, "precis")
gen.WriteUnicodeVersion(w)
// Iterate over all the runes...
for i := rune(0); i < unicode.MaxRune; i++ {
r := rune(i)
if !utf8.ValidRune(r) {
continue
}
e, ok := exceptions[i]
p := e.prop
switch {
case ok:
case !unicode.In(r, assigned):
p = unassigned
case r >= 0x0021 && r <= 0x007e: // Is ASCII 7
p = pValid
case unicode.In(r, disallowedRunes, unicode.Cc):
p = disallowed
case hasCompat(r):
p = idDisOrFreePVal
case isLetterDigits(r):
p = pValid
case isIdDisAndFreePVal(r):
p = idDisOrFreePVal
default:
p = disallowed
}
cat := runeCategory[r]
// Don't set category for runes that are disallowed.
if p == disallowed {
cat = exceptions[r].cat
}
propTrie.Insert(r, uint64(p)|uint64(cat))
}
sz, err := propTrie.Gen(w)
if err != nil {
log.Fatal(err)
}
w.Size += sz
}
func writeTables() {
propTrie := triegen.NewTrie("derivedProperties")
w := gen.NewCodeWriter()
defer w.WriteGoFile(*outputFile, "precis")
gen.WriteUnicodeVersion(w)
// Iterate over all the runes...
for i := uint32(0); i < unicode.MaxRune; i++ {
r := rune(i)
if !utf8.ValidRune(r) {
continue
}
p, ok := exceptions[i]
switch {
case ok:
case !unicode.In(r, assigned):
p = unassigned
case r >= 33 && r <= 126: // Is ASCII 7
p = pValid
case r == 0x200C || r == 0x200D: // Is join control
p = contextJ
case unicode.In(r, disallowedRunes, unicode.Cc):
p = disallowed
case isHasCompat(r):
p = idDis | freePVal
case isLetterDigits(r):
p = pValid
case isIdDisAndFreePVal(r):
p = idDis | freePVal
default:
p = disallowed
}
propTrie.Insert(r, uint64(p))
}
sz, err := propTrie.Gen(w)
if err != nil {
log.Fatal(err)
}
w.Size += sz
}
func main() {
gen.Init()
rewriteCommon()
// Read the CLDR zip file.
r := gen.OpenCLDRCoreZip()
defer r.Close()
d := &cldr.Decoder{}
d.SetDirFilter("supplemental")
data, err := d.DecodeZip(r)
if err != nil {
log.Fatalf("DecodeZip: %v", err)
}
w := gen.NewCodeWriter()
defer w.WriteGoFile(*outputFile, "currency")
fmt.Fprintln(w, `import "golang.org/x/text/internal/tag"`)
gen.WriteCLDRVersion(w)
genCurrencies(w, data.Supplemental())
}
func main() {
r := gen.OpenCLDRCoreZip()
defer r.Close()
d := &cldr.Decoder{}
data, err := d.DecodeZip(r)
if err != nil {
log.Fatalf("DecodeZip: %v", err)
}
w := gen.NewCodeWriter()
defer w.WriteGoFile("tables.go", "internal")
// Create parents table.
parents := make([]uint16, language.NumCompactTags)
for _, loc := range data.Locales() {
tag := language.MustParse(loc)
index, ok := language.CompactIndex(tag)
if !ok {
continue
}
parentIndex := 0 // und
for p := tag.Parent(); p != language.Und; p = p.Parent() {
if x, ok := language.CompactIndex(p); ok {
parentIndex = x
break
}
}
parents[index] = uint16(parentIndex)
}
w.WriteComment(`
Parent maps a compact index of a tag to the compact index of the parent of
this tag.`)
w.WriteVar("Parent", parents)
}
func genTables() {
if numClass > 0x0F {
log.Fatalf("Too many Class constants (%#x > 0x0F).", numClass)
}
w := gen.NewCodeWriter()
defer w.WriteGoFile(*outputFile, "bidi")
gen.WriteUnicodeVersion(w)
t := triegen.NewTrie("bidi")
// Build data about bracket mapping. These bits need to be or-ed with
// any other bits.
orMask := map[rune]uint64{}
xorMap := map[rune]int{}
xorMasks := []rune{0} // First value is no-op.
parse("BidiBrackets.txt", func(p *ucd.Parser) {
r1 := p.Rune(0)
r2 := p.Rune(1)
xor := r1 ^ r2
if _, ok := xorMap[xor]; !ok {
xorMap[xor] = len(xorMasks)
xorMasks = append(xorMasks, xor)
}
entry := uint64(xorMap[xor]) << xorMaskShift
switch p.String(2) {
case "o":
entry |= openMask
case "c", "n":
default:
log.Fatalf("Unknown bracket class %q.", p.String(2))
}
orMask[r1] = entry
})
w.WriteComment(`
xorMasks contains masks to be xor-ed with brackets to get the reverse
version.`)
w.WriteVar("xorMasks", xorMasks)
done := map[rune]bool{}
insert := func(r rune, c class) {
if !done[r] {
t.Insert(r, orMask[r]|uint64(c))
done[r] = true
}
}
// Insert the derived BiDi properties.
parse("extracted/DerivedBidiClass.txt", func(p *ucd.Parser) {
r := p.Rune(0)
class, ok := bidiClass[p.String(1)]
if !ok {
log.Fatalf("%U: Unknown BiDi class %q", r, p.String(1))
}
insert(r, class)
})
visitDefaults(insert)
// TODO: use sparse blocks. This would reduce table size considerably
// from the looks of it.
sz, err := t.Gen(w)
if err != nil {
log.Fatal(err)
}
w.Size += sz
}
func main() {
mibs := map[string]bool{}
all := []string{}
w := gen.NewCodeWriter()
defer w.WriteGoFile("tables.go", "charmap")
printf := func(s string, a ...interface{}) { fmt.Fprintf(w, s, a...) }
printf("import (\n")
printf("\t\"golang.org/x/text/encoding\"\n")
printf("\t\"golang.org/x/text/encoding/internal/identifier\"\n")
printf(")\n\n")
for _, e := range encodings {
varNames := strings.Split(e.varName, ",")
all = append(all, varNames...)
varName := varNames[0]
switch {
case strings.HasPrefix(e.mapping, "http://encoding.spec.whatwg.org/"):
e.mapping = getWHATWG(e.mapping)
case strings.HasPrefix(e.mapping, "http://source.icu-project.org/repos/icu/data/trunk/charset/data/ucm/"):
e.mapping = getUCM(e.mapping)
}
asciiSuperset, low := strings.HasPrefix(e.mapping, ascii), 0x00
if asciiSuperset {
low = 0x80
}
lvn := 1
if strings.HasPrefix(varName, "ISO") || strings.HasPrefix(varName, "KOI") {
lvn = 3
}
lowerVarName := strings.ToLower(varName[:lvn]) + varName[lvn:]
printf("// %s is the %s encoding.\n", varName, e.name)
if e.comment != "" {
printf("//\n// %s\n", e.comment)
}
printf("var %s encoding.Encoding = &%s\n\nvar %s = charmap{\nname: %q,\n",
varName, lowerVarName, lowerVarName, e.name)
if mibs[e.mib] {
log.Fatalf("MIB type %q declared multiple times.", e.mib)
}
printf("mib: identifier.%s,\n", e.mib)
printf("asciiSuperset: %t,\n", asciiSuperset)
printf("low: 0x%02x,\n", low)
printf("replacement: 0x%02x,\n", e.replacement)
printf("decode: [256]utf8Enc{\n")
i, backMapping := 0, map[rune]byte{}
for _, c := range e.mapping {
if _, ok := backMapping[c]; !ok && c != utf8.RuneError {
backMapping[c] = byte(i)
}
var buf [8]byte
n := utf8.EncodeRune(buf[:], c)
if n > 3 {
panic(fmt.Sprintf("rune %q (%U) is too long", c, c))
}
printf("{%d,[3]byte{0x%02x,0x%02x,0x%02x}},", n, buf[0], buf[1], buf[2])
if i%2 == 1 {
printf("\n")
}
i++
}
printf("},\n")
printf("encode: [256]uint32{\n")
encode := make([]uint32, 0, 256)
for c, i := range backMapping {
encode = append(encode, uint32(i)<<24|uint32(c))
}
sort.Sort(byRune(encode))
for len(encode) < cap(encode) {
encode = append(encode, encode[len(encode)-1])
}
for i, enc := range encode {
printf("0x%08x,", enc)
if i%8 == 7 {
printf("\n")
}
}
printf("},\n}\n")
// Add an estimate of the size of a single charmap{} struct value, which
// includes two 256 elem arrays of 4 bytes and some extra fields, which
// align to 3 uint64s on 64-bit architectures.
w.Size += 2*4*256 + 3*8
}
// TODO: add proper line breaking.
printf("var listAll = []encoding.Encoding{\n%s,\n}\n\n", strings.Join(all, ",\n"))
}
func main() {
gen.Init()
// Read the CLDR zip file.
r := gen.OpenCLDRCoreZip()
defer r.Close()
d := &cldr.Decoder{}
data, err := d.DecodeZip(r)
if err != nil {
log.Fatalf("DecodeZip: %v", err)
}
w := gen.NewCodeWriter()
defer func() {
buf := &bytes.Buffer{}
if _, err = w.WriteGo(buf, "language"); err != nil {
log.Fatalf("Error formatting file index.go: %v", err)
}
// Since we're generating a table for our own package we need to rewrite
// doing the equivalent of go fmt -r 'language.b -> b'. Using
// bytes.Replace will do.
out := bytes.Replace(buf.Bytes(), []byte("language."), nil, -1)
if err := ioutil.WriteFile("index.go", out, 0600); err != nil {
log.Fatalf("Could not create file index.go: %v", err)
}
}()
m := map[language.Tag]bool{}
for _, lang := range data.Locales() {
// We include all locales unconditionally to be consistent with en_US.
// We want en_US, even though it has no data associated with it.
// TODO: put any of the languages for which no data exists at the end
// of the index. This allows all components based on ICU to use that
// as the cutoff point.
// if x := data.RawLDML(lang); false ||
// x.LocaleDisplayNames != nil ||
// x.Characters != nil ||
// x.Delimiters != nil ||
// x.Measurement != nil ||
// x.Dates != nil ||
// x.Numbers != nil ||
// x.Units != nil ||
// x.ListPatterns != nil ||
// x.Collations != nil ||
// x.Segmentations != nil ||
// x.Rbnf != nil ||
// x.Annotations != nil ||
// x.Metadata != nil {
// TODO: support POSIX natively, albeit non-standard.
tag := language.Make(strings.Replace(lang, "_POSIX", "-u-va-posix", 1))
m[tag] = true
// }
}
// Include locales for plural rules, which uses a different structure.
for _, plurals := range data.Supplemental().Plurals {
for _, rules := range plurals.PluralRules {
for _, lang := range strings.Split(rules.Locales, " ") {
m[language.Make(lang)] = true
}
}
}
var core, special []language.Tag
for t := range m {
if x := t.Extensions(); len(x) != 0 && fmt.Sprint(x) != "[u-va-posix]" {
log.Fatalf("Unexpected extension %v in %v", x, t)
}
if len(t.Variants()) == 0 && len(t.Extensions()) == 0 {
core = append(core, t)
} else {
special = append(special, t)
}
}
w.WriteComment(`
NumCompactTags is the number of common tags. The maximum tag is
NumCompactTags-1.`)
w.WriteConst("NumCompactTags", len(core)+len(special))
sort.Sort(byAlpha(special))
w.WriteVar("specialTags", special)
// TODO: order by frequency?
sort.Sort(byAlpha(core))
// Size computations are just an estimate.
w.Size += int(reflect.TypeOf(map[uint32]uint16{}).Size())
w.Size += len(core) * 6 // size of uint32 and uint16
fmt.Fprintln(w)
fmt.Fprintln(w, "var coreTags = map[uint32]uint16{")
fmt.Fprintln(w, "0x0: 0, // und")
i := len(special) + 1 // Und and special tags already written.
for _, t := range core {
if t == language.Und {
continue
}
fmt.Fprint(w.Hash, t, i)
b, s, r := t.Raw()
fmt.Fprintf(w, "0x%s%s%s: %d, // %s\n",
getIndex(b, 3), // 3 is enough as it is guaranteed to be a compact number
getIndex(s, 2),
getIndex(r, 3),
i, t)
i++
}
fmt.Fprintln(w, "}")
}
func main() {
gen.Init()
// Read the CLDR zip file.
r := gen.OpenCLDRCoreZip()
defer r.Close()
d := &cldr.Decoder{}
data, err := d.DecodeZip(r)
if err != nil {
log.Fatalf("DecodeZip: %v", err)
}
w := gen.NewCodeWriter()
defer func() {
buf := &bytes.Buffer{}
if _, err = w.WriteGo(buf, "language"); err != nil {
log.Fatalf("Error formatting file index.go: %v", err)
}
// Since we're generating a table for our own package we need to rewrite
// doing the equivalent of go fmt -r 'language.b -> b'. Using
// bytes.Replace will do.
out := bytes.Replace(buf.Bytes(), []byte("language."), nil, -1)
if err := ioutil.WriteFile("index.go", out, 0600); err != nil {
log.Fatalf("Could not create file index.go: %v", err)
}
}()
m := map[language.Tag]bool{}
for _, lang := range data.Locales() {
if x := data.RawLDML(lang); false ||
x.LocaleDisplayNames != nil ||
x.Characters != nil ||
x.Delimiters != nil ||
x.Measurement != nil ||
x.Dates != nil ||
x.Numbers != nil ||
x.Units != nil ||
x.ListPatterns != nil ||
x.Collations != nil ||
x.Segmentations != nil ||
x.Rbnf != nil ||
x.Annotations != nil ||
x.Metadata != nil {
// TODO: support POSIX natively, albeit non-standard.
tag := language.Make(strings.Replace(lang, "_POSIX", "-u-va-posix", 1))
m[tag] = true
}
}
var core, special []language.Tag
for t := range m {
if x := t.Extensions(); len(x) != 0 && fmt.Sprint(x) != "[u-va-posix]" {
log.Fatalf("Unexpected extension %v in %v", x, t)
}
if len(t.Variants()) == 0 && len(t.Extensions()) == 0 {
core = append(core, t)
} else {
special = append(special, t)
}
}
w.WriteComment(`
NumCompactTags is the number of common tags. The maximum tag is
NumCompactTags-1.`)
w.WriteConst("NumCompactTags", len(core)+len(special))
sort.Sort(byAlpha(special))
w.WriteVar("specialTags", special)
type coreKey struct {
base language.Base
script language.Script
region language.Region
}
w.WriteType(coreKey{})
// TODO: order by frequency?
sort.Sort(byAlpha(core))
// Size computations are just an estimate.
w.Size += int(reflect.TypeOf(map[coreKey]uint16{}).Size())
w.Size += len(core) * int(reflect.TypeOf(coreKey{}).Size()+2) // 2 is for uint16
fmt.Fprintln(w, "var coreTags = map[coreKey]uint16{")
fmt.Fprintln(w, "coreKey{}: 0, // und")
i := len(special) + 1 // Und and special tags already written.
for _, t := range core {
if t == language.Und {
continue
}
fmt.Fprint(w.Hash, t, i)
b, s, r := t.Raw()
key := fmt.Sprintf("%#v", coreKey{b, s, r})
key = strings.Replace(key[len("main."):], "language.", "", -1)
fmt.Fprintf(w, "%s: %d, // %s\n", key, i, t)
i++
}
fmt.Fprintln(w, "}")
}
func genTables() {
t := triegen.NewTrie("idna")
ucd.Parse(gen.OpenUCDFile("UnicodeData.txt"), func(p *ucd.Parser) {
r := p.Rune(0)
const cccVirama = 9
if p.Int(ucd.CanonicalCombiningClass) == cccVirama {
runes[p.Rune(0)] = viramaModifier
}
switch {
case unicode.In(r, unicode.Mark):
runes[r] |= modifier
}
})
ucd.Parse(gen.OpenUCDFile("extracted/DerivedJoiningType.txt"), func(p *ucd.Parser) {
switch v := p.String(1); v {
case "L", "D", "T", "R":
runes[p.Rune(0)] |= joinType[v] << joinShift
}
})
ucd.Parse(gen.OpenUnicodeFile("idna", "", "IdnaMappingTable.txt"), func(p *ucd.Parser) {
r := p.Rune(0)
// The mappings table explicitly defines surrogates as invalid.
if !utf8.ValidRune(r) {
return
}
cat := catFromEntry(p)
isMapped := cat == mapped || cat == disallowedSTD3Mapped || cat == deviation
if !isMapped {
// Only include additional category information for non-mapped
// runes. The additional information is only used after mapping and
// the bits would clash with mapping information.
// TODO: it would be possible to inline this data and avoid
// additional lookups. This is quite tedious, though, so let's first
// see if we need this.
cat |= category(runes[r])
}
s := string(p.Runes(2))
if s != "" && !isMapped {
log.Fatalf("%U: Mapping with non-mapping category %d", r, cat)
}
t.Insert(r, uint64(makeEntry(r, s))+uint64(cat))
})
w := gen.NewCodeWriter()
defer w.WriteGoFile("tables.go", "idna")
gen.WriteUnicodeVersion(w)
w.WriteVar("mappings", string(mappings))
w.WriteVar("xorData", string(xorData))
sz, err := t.Gen(w, triegen.Compact(&normCompacter{}))
if err != nil {
log.Fatal(err)
}
w.Size += sz
}
